diff options
Diffstat (limited to 'drivers/net/ethernet')
405 files changed, 48243 insertions, 6506 deletions
diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c index f66c9710cb81..b223769d6a5e 100644 --- a/drivers/net/ethernet/3com/3c509.c +++ b/drivers/net/ethernet/3com/3c509.c @@ -392,7 +392,7 @@ static struct isa_driver el3_isa_driver = { static int isa_registered; #ifdef CONFIG_PNP -static struct pnp_device_id el3_pnp_ids[] = { +static const struct pnp_device_id el3_pnp_ids[] = { { .id = "TCM5090" }, /* 3Com Etherlink III (TP) */ { .id = "TCM5091" }, /* 3Com Etherlink III */ { .id = "TCM5094" }, /* 3Com Etherlink III (combo) */ @@ -474,7 +474,7 @@ static int pnp_registered; #endif /* CONFIG_PNP */ #ifdef CONFIG_EISA -static struct eisa_device_id el3_eisa_ids[] = { +static const struct eisa_device_id el3_eisa_ids[] = { { "TCM5090" }, { "TCM5091" }, { "TCM5092" }, diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 3b516ebeeddb..402d9090ad29 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -900,7 +900,7 @@ static const struct dev_pm_ops vortex_pm_ops = { #endif /* !CONFIG_PM */ #ifdef CONFIG_EISA -static struct eisa_device_id vortex_eisa_ids[] = { +static const struct eisa_device_id vortex_eisa_ids[] = { { "TCM5920", CH_3C592 }, { "TCM5970", CH_3C597 }, { "" } diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index 05d9d3e2e92e..245554707163 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -585,7 +585,7 @@ static int ax_bb_get_data(struct mdiobb_ctrl *ctrl) return reg_memr & AX_MEMR_MDI ? 1 : 0; } -static struct mdiobb_ops bb_ops = { +static const struct mdiobb_ops bb_ops = { .owner = THIS_MODULE, .set_mdc = ax_bb_mdc, .set_mdio_dir = ax_bb_dir, diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index edae15ac0e98..c60421339a98 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -78,6 +78,7 @@ source "drivers/net/ethernet/freescale/Kconfig" source "drivers/net/ethernet/fujitsu/Kconfig" source "drivers/net/ethernet/hisilicon/Kconfig" source "drivers/net/ethernet/hp/Kconfig" +source "drivers/net/ethernet/huawei/Kconfig" source "drivers/net/ethernet/ibm/Kconfig" source "drivers/net/ethernet/intel/Kconfig" source "drivers/net/ethernet/i825xx/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index bf7f4502cabc..a0a03d4d939a 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/ obj-$(CONFIG_NET_VENDOR_FUJITSU) += fujitsu/ obj-$(CONFIG_NET_VENDOR_HISILICON) += hisilicon/ obj-$(CONFIG_NET_VENDOR_HP) += hp/ +obj-$(CONFIG_NET_VENDOR_HUAWEI) += huawei/ obj-$(CONFIG_NET_VENDOR_IBM) += ibm/ obj-$(CONFIG_NET_VENDOR_INTEL) += intel/ obj-$(CONFIG_NET_VENDOR_I825XX) += i825xx/ diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c index a9ac58c351a0..a251de8d9a91 100644 --- a/drivers/net/ethernet/adi/bfin_mac.c +++ b/drivers/net/ethernet/adi/bfin_mac.c @@ -986,7 +986,7 @@ static int bfin_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } -static struct ptp_clock_info bfin_ptp_caps = { +static const struct ptp_clock_info bfin_ptp_caps = { .owner = THIS_MODULE, .name = "BF518 clock", .max_adj = 0, diff --git a/drivers/net/ethernet/amd/a2065.c b/drivers/net/ethernet/amd/a2065.c index ee4b94e3cda9..e22f976a0d18 100644 --- a/drivers/net/ethernet/amd/a2065.c +++ b/drivers/net/ethernet/amd/a2065.c @@ -643,7 +643,7 @@ static int a2065_init_one(struct zorro_dev *z, static void a2065_remove_one(struct zorro_dev *z); -static struct zorro_device_id a2065_zorro_tbl[] = { +static const struct zorro_device_id a2065_zorro_tbl[] = { { ZORRO_PROD_CBM_A2065_1 }, { ZORRO_PROD_CBM_A2065_2 }, { ZORRO_PROD_AMERISTAR_A2065 }, diff --git a/drivers/net/ethernet/amd/ariadne.c b/drivers/net/ethernet/amd/ariadne.c index 5fd7b15b0574..4b6a5cb85dd2 100644 --- a/drivers/net/ethernet/amd/ariadne.c +++ b/drivers/net/ethernet/amd/ariadne.c @@ -692,7 +692,7 @@ static void ariadne_remove_one(struct zorro_dev *z) free_netdev(dev); } -static struct zorro_device_id ariadne_zorro_tbl[] = { +static const struct zorro_device_id ariadne_zorro_tbl[] = { { ZORRO_PROD_VILLAGE_TRONIC_ARIADNE }, { 0 } }; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 9795419aac2d..7ea72ef11a55 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -210,11 +210,15 @@ #define DMA_CH_CR_PBLX8_WIDTH 1 #define DMA_CH_CR_SPH_INDEX 24 #define DMA_CH_CR_SPH_WIDTH 1 -#define DMA_CH_IER_AIE_INDEX 15 +#define DMA_CH_IER_AIE20_INDEX 15 +#define DMA_CH_IER_AIE20_WIDTH 1 +#define DMA_CH_IER_AIE_INDEX 14 #define DMA_CH_IER_AIE_WIDTH 1 #define DMA_CH_IER_FBEE_INDEX 12 #define DMA_CH_IER_FBEE_WIDTH 1 -#define DMA_CH_IER_NIE_INDEX 16 +#define DMA_CH_IER_NIE20_INDEX 16 +#define DMA_CH_IER_NIE20_WIDTH 1 +#define DMA_CH_IER_NIE_INDEX 15 #define DMA_CH_IER_NIE_WIDTH 1 #define DMA_CH_IER_RBUE_INDEX 7 #define DMA_CH_IER_RBUE_WIDTH 1 @@ -298,6 +302,7 @@ #define MAC_RWKPFR 0x00c4 #define MAC_LPICSR 0x00d0 #define MAC_LPITCR 0x00d4 +#define MAC_TIR 0x00e0 #define MAC_VR 0x0110 #define MAC_DR 0x0114 #define MAC_HWF0R 0x011c @@ -364,6 +369,8 @@ #define MAC_HWF0R_TXCOESEL_WIDTH 1 #define MAC_HWF0R_VLHASH_INDEX 4 #define MAC_HWF0R_VLHASH_WIDTH 1 +#define MAC_HWF0R_VXN_INDEX 29 +#define MAC_HWF0R_VXN_WIDTH 1 #define MAC_HWF1R_ADDR64_INDEX 14 #define MAC_HWF1R_ADDR64_WIDTH 2 #define MAC_HWF1R_ADVTHWORD_INDEX 13 @@ -448,6 +455,8 @@ #define MAC_PFR_PR_WIDTH 1 #define MAC_PFR_VTFE_INDEX 16 #define MAC_PFR_VTFE_WIDTH 1 +#define MAC_PFR_VUCC_INDEX 22 +#define MAC_PFR_VUCC_WIDTH 1 #define MAC_PMTCSR_MGKPKTEN_INDEX 1 #define MAC_PMTCSR_MGKPKTEN_WIDTH 1 #define MAC_PMTCSR_PWRDWN_INDEX 0 @@ -510,6 +519,12 @@ #define MAC_TCR_SS_WIDTH 2 #define MAC_TCR_TE_INDEX 0 #define MAC_TCR_TE_WIDTH 1 +#define MAC_TCR_VNE_INDEX 24 +#define MAC_TCR_VNE_WIDTH 1 +#define MAC_TCR_VNM_INDEX 25 +#define MAC_TCR_VNM_WIDTH 1 +#define MAC_TIR_TNID_INDEX 0 +#define MAC_TIR_TNID_WIDTH 16 #define MAC_TSCR_AV8021ASMEN_INDEX 28 #define MAC_TSCR_AV8021ASMEN_WIDTH 1 #define MAC_TSCR_SNAPTYPSEL_INDEX 16 @@ -1153,11 +1168,17 @@ #define RX_PACKET_ATTRIBUTES_RSS_HASH_WIDTH 1 #define RX_PACKET_ATTRIBUTES_FIRST_INDEX 7 #define RX_PACKET_ATTRIBUTES_FIRST_WIDTH 1 +#define RX_PACKET_ATTRIBUTES_TNP_INDEX 8 +#define RX_PACKET_ATTRIBUTES_TNP_WIDTH 1 +#define RX_PACKET_ATTRIBUTES_TNPCSUM_DONE_INDEX 9 +#define RX_PACKET_ATTRIBUTES_TNPCSUM_DONE_WIDTH 1 #define RX_NORMAL_DESC0_OVT_INDEX 0 #define RX_NORMAL_DESC0_OVT_WIDTH 16 #define RX_NORMAL_DESC2_HL_INDEX 0 #define RX_NORMAL_DESC2_HL_WIDTH 10 +#define RX_NORMAL_DESC2_TNP_INDEX 11 +#define RX_NORMAL_DESC2_TNP_WIDTH 1 #define RX_NORMAL_DESC3_CDA_INDEX 27 #define RX_NORMAL_DESC3_CDA_WIDTH 1 #define RX_NORMAL_DESC3_CTXT_INDEX 30 @@ -1184,9 +1205,11 @@ #define RX_DESC3_L34T_IPV4_TCP 1 #define RX_DESC3_L34T_IPV4_UDP 2 #define RX_DESC3_L34T_IPV4_ICMP 3 +#define RX_DESC3_L34T_IPV4_UNKNOWN 7 #define RX_DESC3_L34T_IPV6_TCP 9 #define RX_DESC3_L34T_IPV6_UDP 10 #define RX_DESC3_L34T_IPV6_ICMP 11 +#define RX_DESC3_L34T_IPV6_UNKNOWN 15 #define RX_CONTEXT_DESC3_TSA_INDEX 4 #define RX_CONTEXT_DESC3_TSA_WIDTH 1 @@ -1201,6 +1224,8 @@ #define TX_PACKET_ATTRIBUTES_VLAN_CTAG_WIDTH 1 #define TX_PACKET_ATTRIBUTES_PTP_INDEX 3 #define TX_PACKET_ATTRIBUTES_PTP_WIDTH 1 +#define TX_PACKET_ATTRIBUTES_VXLAN_INDEX 4 +#define TX_PACKET_ATTRIBUTES_VXLAN_WIDTH 1 #define TX_CONTEXT_DESC2_MSS_INDEX 0 #define TX_CONTEXT_DESC2_MSS_WIDTH 15 @@ -1241,8 +1266,11 @@ #define TX_NORMAL_DESC3_TCPPL_WIDTH 18 #define TX_NORMAL_DESC3_TSE_INDEX 18 #define TX_NORMAL_DESC3_TSE_WIDTH 1 +#define TX_NORMAL_DESC3_VNP_INDEX 23 +#define TX_NORMAL_DESC3_VNP_WIDTH 3 #define TX_NORMAL_DESC2_VLAN_INSERT 0x2 +#define TX_NORMAL_DESC3_VXLAN_PACKET 0x3 /* MDIO undefined or vendor specific registers */ #ifndef MDIO_PMA_10GBR_PMD_CTRL @@ -1339,6 +1367,7 @@ #define XGBE_AN_CL37_PCS_MODE_BASEX 0x00 #define XGBE_AN_CL37_PCS_MODE_SGMII 0x04 #define XGBE_AN_CL37_TX_CONFIG_MASK 0x08 +#define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100 /* Bit setting and getting macros * The get macro will extract the current bit field value from within diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index 7546b660d6b5..7d128be61310 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -527,3 +527,28 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) debugfs_remove_recursive(pdata->xgbe_debugfs); pdata->xgbe_debugfs = NULL; } + +void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) +{ + struct dentry *pfile; + char *buf; + + if (!pdata->xgbe_debugfs) + return; + + buf = kasprintf(GFP_KERNEL, "amd-xgbe-%s", pdata->netdev->name); + if (!buf) + return; + + if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf)) + goto out; + + pfile = debugfs_rename(pdata->xgbe_debugfs->d_parent, + pdata->xgbe_debugfs, + pdata->xgbe_debugfs->d_parent, buf); + if (!pfile) + netdev_err(pdata->netdev, "debugfs_rename failed\n"); + +out: + kfree(buf); +} diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 06f953e1e9b2..e107e180e2c8 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -479,6 +479,50 @@ static bool xgbe_is_pfc_queue(struct xgbe_prv_data *pdata, return false; } +static void xgbe_set_vxlan_id(struct xgbe_prv_data *pdata) +{ + /* Program the VXLAN port */ + XGMAC_IOWRITE_BITS(pdata, MAC_TIR, TNID, pdata->vxlan_port); + + netif_dbg(pdata, drv, pdata->netdev, "VXLAN tunnel id set to %hx\n", + pdata->vxlan_port); +} + +static void xgbe_enable_vxlan(struct xgbe_prv_data *pdata) +{ + if (!pdata->hw_feat.vxn) + return; + + /* Program the VXLAN port */ + xgbe_set_vxlan_id(pdata); + + /* Allow for IPv6/UDP zero-checksum VXLAN packets */ + XGMAC_IOWRITE_BITS(pdata, MAC_PFR, VUCC, 1); + + /* Enable VXLAN tunneling mode */ + XGMAC_IOWRITE_BITS(pdata, MAC_TCR, VNM, 0); + XGMAC_IOWRITE_BITS(pdata, MAC_TCR, VNE, 1); + + netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration enabled\n"); +} + +static void xgbe_disable_vxlan(struct xgbe_prv_data *pdata) +{ + if (!pdata->hw_feat.vxn) + return; + + /* Disable tunneling mode */ + XGMAC_IOWRITE_BITS(pdata, MAC_TCR, VNE, 0); + + /* Clear IPv6/UDP zero-checksum VXLAN packets setting */ + XGMAC_IOWRITE_BITS(pdata, MAC_PFR, VUCC, 0); + + /* Clear the VXLAN port */ + XGMAC_IOWRITE_BITS(pdata, MAC_TIR, TNID, 0); + + netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration disabled\n"); +} + static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata) { unsigned int max_q_count, q_count; @@ -605,32 +649,38 @@ static void xgbe_config_flow_control(struct xgbe_prv_data *pdata) static void xgbe_enable_dma_interrupts(struct xgbe_prv_data *pdata) { struct xgbe_channel *channel; - unsigned int dma_ch_isr, dma_ch_ier; - unsigned int i; + unsigned int i, ver; /* Set the interrupt mode if supported */ if (pdata->channel_irq_mode) XGMAC_IOWRITE_BITS(pdata, DMA_MR, INTM, pdata->channel_irq_mode); + ver = XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER); + for (i = 0; i < pdata->channel_count; i++) { channel = pdata->channel[i]; /* Clear all the interrupts which are set */ - dma_ch_isr = XGMAC_DMA_IOREAD(channel, DMA_CH_SR); - XGMAC_DMA_IOWRITE(channel, DMA_CH_SR, dma_ch_isr); + XGMAC_DMA_IOWRITE(channel, DMA_CH_SR, + XGMAC_DMA_IOREAD(channel, DMA_CH_SR)); /* Clear all interrupt enable bits */ - dma_ch_ier = 0; + channel->curr_ier = 0; /* Enable following interrupts * NIE - Normal Interrupt Summary Enable * AIE - Abnormal Interrupt Summary Enable * FBEE - Fatal Bus Error Enable */ - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, NIE, 1); - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, AIE, 1); - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, FBEE, 1); + if (ver < 0x21) { + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, NIE20, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, AIE20, 1); + } else { + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, NIE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, AIE, 1); + } + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, FBEE, 1); if (channel->tx_ring) { /* Enable the following Tx interrupts @@ -639,7 +689,8 @@ static void xgbe_enable_dma_interrupts(struct xgbe_prv_data *pdata) * mode) */ if (!pdata->per_channel_irq || pdata->channel_irq_mode) - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TIE, 1); + XGMAC_SET_BITS(channel->curr_ier, + DMA_CH_IER, TIE, 1); } if (channel->rx_ring) { /* Enable following Rx interrupts @@ -648,12 +699,13 @@ static void xgbe_enable_dma_interrupts(struct xgbe_prv_data *pdata) * per channel interrupts in edge triggered * mode) */ - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RBUE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RBUE, 1); if (!pdata->per_channel_irq || pdata->channel_irq_mode) - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RIE, 1); + XGMAC_SET_BITS(channel->curr_ier, + DMA_CH_IER, RIE, 1); } - XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, dma_ch_ier); + XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, channel->curr_ier); } } @@ -1608,7 +1660,8 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) struct xgbe_ring_data *rdata; struct xgbe_ring_desc *rdesc; struct xgbe_packet_data *packet = &ring->packet_data; - unsigned int csum, tso, vlan; + unsigned int tx_packets, tx_bytes; + unsigned int csum, tso, vlan, vxlan; unsigned int tso_context, vlan_context; unsigned int tx_set_ic; int start_index = ring->cur; @@ -1617,12 +1670,17 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) DBGPR("-->xgbe_dev_xmit\n"); + tx_packets = packet->tx_packets; + tx_bytes = packet->tx_bytes; + csum = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, CSUM_ENABLE); tso = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, TSO_ENABLE); vlan = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, VLAN_CTAG); + vxlan = XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, + VXLAN); if (tso && (packet->mss != ring->tx.cur_mss)) tso_context = 1; @@ -1644,13 +1702,12 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) * - Addition of Tx frame count to the frame count since the * last interrupt was set does not exceed the frame count setting */ - ring->coalesce_count += packet->tx_packets; + ring->coalesce_count += tx_packets; if (!pdata->tx_frames) tx_set_ic = 0; - else if (packet->tx_packets > pdata->tx_frames) + else if (tx_packets > pdata->tx_frames) tx_set_ic = 1; - else if ((ring->coalesce_count % pdata->tx_frames) < - packet->tx_packets) + else if ((ring->coalesce_count % pdata->tx_frames) < tx_packets) tx_set_ic = 1; else tx_set_ic = 0; @@ -1740,7 +1797,7 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, TCPHDRLEN, packet->tcp_header_len / 4); - pdata->ext_stats.tx_tso_packets++; + pdata->ext_stats.tx_tso_packets += tx_packets; } else { /* Enable CRC and Pad Insertion */ XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, CPC, 0); @@ -1755,6 +1812,13 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) packet->length); } + if (vxlan) { + XGMAC_SET_BITS_LE(rdesc->desc3, TX_NORMAL_DESC3, VNP, + TX_NORMAL_DESC3_VXLAN_PACKET); + + pdata->ext_stats.tx_vxlan_packets += packet->tx_packets; + } + for (i = cur_index - start_index + 1; i < packet->rdesc_count; i++) { cur_index++; rdata = XGBE_GET_DESC_DATA(ring, cur_index); @@ -1788,8 +1852,11 @@ static void xgbe_dev_xmit(struct xgbe_channel *channel) XGMAC_SET_BITS_LE(rdesc->desc2, TX_NORMAL_DESC2, IC, 1); /* Save the Tx info to report back during cleanup */ - rdata->tx.packets = packet->tx_packets; - rdata->tx.bytes = packet->tx_bytes; + rdata->tx.packets = tx_packets; + rdata->tx.bytes = tx_bytes; + + pdata->ext_stats.txq_packets[channel->queue_index] += tx_packets; + pdata->ext_stats.txq_bytes[channel->queue_index] += tx_bytes; /* In case the Tx DMA engine is running, make sure everything * is written to the descriptor(s) before setting the OWN bit @@ -1913,9 +1980,28 @@ static int xgbe_dev_read(struct xgbe_channel *channel) rdata->rx.len = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, PL); /* Set checksum done indicator as appropriate */ - if (netdev->features & NETIF_F_RXCSUM) + if (netdev->features & NETIF_F_RXCSUM) { XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, CSUM_DONE, 1); + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + TNPCSUM_DONE, 1); + } + + /* Set the tunneled packet indicator */ + if (XGMAC_GET_BITS_LE(rdesc->desc2, RX_NORMAL_DESC2, TNP)) { + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + TNP, 1); + pdata->ext_stats.rx_vxlan_packets++; + + l34t = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, L34T); + switch (l34t) { + case RX_DESC3_L34T_IPV4_UNKNOWN: + case RX_DESC3_L34T_IPV6_UNKNOWN: + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + TNPCSUM_DONE, 0); + break; + } + } /* Check for errors (only valid in last descriptor) */ err = XGMAC_GET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, ES); @@ -1935,14 +2021,30 @@ static int xgbe_dev_read(struct xgbe_channel *channel) packet->vlan_ctag); } } else { - if ((etlt == 0x05) || (etlt == 0x06)) + unsigned int tnp = XGMAC_GET_BITS(packet->attributes, + RX_PACKET_ATTRIBUTES, TNP); + + if ((etlt == 0x05) || (etlt == 0x06)) { XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, CSUM_DONE, 0); - else + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + TNPCSUM_DONE, 0); + pdata->ext_stats.rx_csum_errors++; + } else if (tnp && ((etlt == 0x09) || (etlt == 0x0a))) { + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + CSUM_DONE, 0); + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + TNPCSUM_DONE, 0); + pdata->ext_stats.rx_vxlan_csum_errors++; + } else { XGMAC_SET_BITS(packet->errors, RX_PACKET_ERRORS, FRAME, 1); + } } + pdata->ext_stats.rxq_packets[channel->queue_index]++; + pdata->ext_stats.rxq_bytes[channel->queue_index] += rdata->rx.len; + DBGPR("<--xgbe_dev_read: %s - descriptor=%u (cur=%d)\n", channel->name, ring->cur & (ring->rdesc_count - 1), ring->cur); @@ -1964,44 +2066,40 @@ static int xgbe_is_last_desc(struct xgbe_ring_desc *rdesc) static int xgbe_enable_int(struct xgbe_channel *channel, enum xgbe_int int_id) { - unsigned int dma_ch_ier; - - dma_ch_ier = XGMAC_DMA_IOREAD(channel, DMA_CH_IER); - switch (int_id) { case XGMAC_INT_DMA_CH_SR_TI: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TIE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TIE, 1); break; case XGMAC_INT_DMA_CH_SR_TPS: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TXSE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TXSE, 1); break; case XGMAC_INT_DMA_CH_SR_TBU: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TBUE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TBUE, 1); break; case XGMAC_INT_DMA_CH_SR_RI: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RIE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RIE, 1); break; case XGMAC_INT_DMA_CH_SR_RBU: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RBUE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RBUE, 1); break; case XGMAC_INT_DMA_CH_SR_RPS: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RSE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RSE, 1); break; case XGMAC_INT_DMA_CH_SR_TI_RI: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TIE, 1); - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RIE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TIE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RIE, 1); break; case XGMAC_INT_DMA_CH_SR_FBE: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, FBEE, 1); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, FBEE, 1); break; case XGMAC_INT_DMA_ALL: - dma_ch_ier |= channel->saved_ier; + channel->curr_ier |= channel->saved_ier; break; default: return -1; } - XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, dma_ch_ier); + XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, channel->curr_ier); return 0; } @@ -2009,45 +2107,41 @@ static int xgbe_enable_int(struct xgbe_channel *channel, static int xgbe_disable_int(struct xgbe_channel *channel, enum xgbe_int int_id) { - unsigned int dma_ch_ier; - - dma_ch_ier = XGMAC_DMA_IOREAD(channel, DMA_CH_IER); - switch (int_id) { case XGMAC_INT_DMA_CH_SR_TI: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TIE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TIE, 0); break; case XGMAC_INT_DMA_CH_SR_TPS: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TXSE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TXSE, 0); break; case XGMAC_INT_DMA_CH_SR_TBU: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TBUE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TBUE, 0); break; case XGMAC_INT_DMA_CH_SR_RI: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RIE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RIE, 0); break; case XGMAC_INT_DMA_CH_SR_RBU: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RBUE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RBUE, 0); break; case XGMAC_INT_DMA_CH_SR_RPS: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RSE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RSE, 0); break; case XGMAC_INT_DMA_CH_SR_TI_RI: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, TIE, 0); - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, RIE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, TIE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, RIE, 0); break; case XGMAC_INT_DMA_CH_SR_FBE: - XGMAC_SET_BITS(dma_ch_ier, DMA_CH_IER, FBEE, 0); + XGMAC_SET_BITS(channel->curr_ier, DMA_CH_IER, FBEE, 0); break; case XGMAC_INT_DMA_ALL: - channel->saved_ier = dma_ch_ier & XGBE_DMA_INTERRUPT_MASK; - dma_ch_ier &= ~XGBE_DMA_INTERRUPT_MASK; + channel->saved_ier = channel->curr_ier; + channel->curr_ier = 0; break; default: return -1; } - XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, dma_ch_ier); + XGMAC_DMA_IOWRITE(channel, DMA_CH_IER, channel->curr_ier); return 0; } @@ -3534,5 +3628,10 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if) hw_if->disable_ecc_ded = xgbe_disable_ecc_ded; hw_if->disable_ecc_sec = xgbe_disable_ecc_sec; + /* For VXLAN */ + hw_if->enable_vxlan = xgbe_enable_vxlan; + hw_if->disable_vxlan = xgbe_disable_vxlan; + hw_if->set_vxlan_id = xgbe_set_vxlan_id; + DBGPR("<--xgbe_init_function_ptrs\n"); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index ecef3ee87b17..608693d11bd7 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -124,6 +124,7 @@ #include <linux/if_ether.h> #include <linux/net_tstamp.h> #include <linux/phy.h> +#include <net/vxlan.h> #include "xgbe.h" #include "xgbe-common.h" @@ -732,8 +733,6 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) unsigned int mac_hfr0, mac_hfr1, mac_hfr2; struct xgbe_hw_features *hw_feat = &pdata->hw_feat; - DBGPR("-->xgbe_get_all_hw_features\n"); - mac_hfr0 = XGMAC_IOREAD(pdata, MAC_HWF0R); mac_hfr1 = XGMAC_IOREAD(pdata, MAC_HWF1R); mac_hfr2 = XGMAC_IOREAD(pdata, MAC_HWF2R); @@ -758,6 +757,7 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) ADDMACADRSEL); hw_feat->ts_src = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, TSSTSSEL); hw_feat->sa_vlan_ins = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, SAVLANINS); + hw_feat->vxn = XGMAC_GET_BITS(mac_hfr0, MAC_HWF0R, VXN); /* Hardware feature register 1 */ hw_feat->rx_fifo_size = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, @@ -828,7 +828,193 @@ void xgbe_get_all_hw_features(struct xgbe_prv_data *pdata) hw_feat->rx_fifo_size = 1 << (hw_feat->rx_fifo_size + 7); hw_feat->tx_fifo_size = 1 << (hw_feat->tx_fifo_size + 7); - DBGPR("<--xgbe_get_all_hw_features\n"); + if (netif_msg_probe(pdata)) { + dev_dbg(pdata->dev, "Hardware features:\n"); + + /* Hardware feature register 0 */ + dev_dbg(pdata->dev, " 1GbE support : %s\n", + hw_feat->gmii ? "yes" : "no"); + dev_dbg(pdata->dev, " VLAN hash filter : %s\n", + hw_feat->vlhash ? "yes" : "no"); + dev_dbg(pdata->dev, " MDIO interface : %s\n", + hw_feat->sma ? "yes" : "no"); + dev_dbg(pdata->dev, " Wake-up packet support : %s\n", + hw_feat->rwk ? "yes" : "no"); + dev_dbg(pdata->dev, " Magic packet support : %s\n", + hw_feat->mgk ? "yes" : "no"); + dev_dbg(pdata->dev, " Management counters : %s\n", + hw_feat->mmc ? "yes" : "no"); + dev_dbg(pdata->dev, " ARP offload : %s\n", + hw_feat->aoe ? "yes" : "no"); + dev_dbg(pdata->dev, " IEEE 1588-2008 Timestamp : %s\n", + hw_feat->ts ? "yes" : "no"); + dev_dbg(pdata->dev, " Energy Efficient Ethernet : %s\n", + hw_feat->eee ? "yes" : "no"); + dev_dbg(pdata->dev, " TX checksum offload : %s\n", + hw_feat->tx_coe ? "yes" : "no"); + dev_dbg(pdata->dev, " RX checksum offload : %s\n", + hw_feat->rx_coe ? "yes" : "no"); + dev_dbg(pdata->dev, " Additional MAC addresses : %u\n", + hw_feat->addn_mac); + dev_dbg(pdata->dev, " Timestamp source : %s\n", + (hw_feat->ts_src == 1) ? "internal" : + (hw_feat->ts_src == 2) ? "external" : + (hw_feat->ts_src == 3) ? "internal/external" : "n/a"); + dev_dbg(pdata->dev, " SA/VLAN insertion : %s\n", + hw_feat->sa_vlan_ins ? "yes" : "no"); + dev_dbg(pdata->dev, " VXLAN/NVGRE support : %s\n", + hw_feat->vxn ? "yes" : "no"); + + /* Hardware feature register 1 */ + dev_dbg(pdata->dev, " RX fifo size : %u\n", + hw_feat->rx_fifo_size); + dev_dbg(pdata->dev, " TX fifo size : %u\n", + hw_feat->tx_fifo_size); + dev_dbg(pdata->dev, " IEEE 1588 high word : %s\n", + hw_feat->adv_ts_hi ? "yes" : "no"); + dev_dbg(pdata->dev, " DMA width : %u\n", + hw_feat->dma_width); + dev_dbg(pdata->dev, " Data Center Bridging : %s\n", + hw_feat->dcb ? "yes" : "no"); + dev_dbg(pdata->dev, " Split header : %s\n", + hw_feat->sph ? "yes" : "no"); + dev_dbg(pdata->dev, " TCP Segmentation Offload : %s\n", + hw_feat->tso ? "yes" : "no"); + dev_dbg(pdata->dev, " Debug memory interface : %s\n", + hw_feat->dma_debug ? "yes" : "no"); + dev_dbg(pdata->dev, " Receive Side Scaling : %s\n", + hw_feat->rss ? "yes" : "no"); + dev_dbg(pdata->dev, " Traffic Class count : %u\n", + hw_feat->tc_cnt); + dev_dbg(pdata->dev, " Hash table size : %u\n", + hw_feat->hash_table_size); + dev_dbg(pdata->dev, " L3/L4 Filters : %u\n", + hw_feat->l3l4_filter_num); + + /* Hardware feature register 2 */ + dev_dbg(pdata->dev, " RX queue count : %u\n", + hw_feat->rx_q_cnt); + dev_dbg(pdata->dev, " TX queue count : %u\n", + hw_feat->tx_q_cnt); + dev_dbg(pdata->dev, " RX DMA channel count : %u\n", + hw_feat->rx_ch_cnt); + dev_dbg(pdata->dev, " TX DMA channel count : %u\n", + hw_feat->rx_ch_cnt); + dev_dbg(pdata->dev, " PPS outputs : %u\n", + hw_feat->pps_out_num); + dev_dbg(pdata->dev, " Auxiliary snapshot inputs : %u\n", + hw_feat->aux_snap_num); + } +} + +static void xgbe_disable_vxlan_offloads(struct xgbe_prv_data *pdata) +{ + struct net_device *netdev = pdata->netdev; + + if (!pdata->vxlan_offloads_set) + return; + + netdev_info(netdev, "disabling VXLAN offloads\n"); + + netdev->hw_enc_features &= ~(NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_GRO | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM); + + netdev->features &= ~(NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM); + + pdata->vxlan_offloads_set = 0; +} + +static void xgbe_disable_vxlan_hw(struct xgbe_prv_data *pdata) +{ + if (!pdata->vxlan_port_set) + return; + + pdata->hw_if.disable_vxlan(pdata); + + pdata->vxlan_port_set = 0; + pdata->vxlan_port = 0; +} + +static void xgbe_disable_vxlan_accel(struct xgbe_prv_data *pdata) +{ + xgbe_disable_vxlan_offloads(pdata); + + xgbe_disable_vxlan_hw(pdata); +} + +static void xgbe_enable_vxlan_offloads(struct xgbe_prv_data *pdata) +{ + struct net_device *netdev = pdata->netdev; + + if (pdata->vxlan_offloads_set) + return; + + netdev_info(netdev, "enabling VXLAN offloads\n"); + + netdev->hw_enc_features |= NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_GRO | + pdata->vxlan_features; + + netdev->features |= pdata->vxlan_features; + + pdata->vxlan_offloads_set = 1; +} + +static void xgbe_enable_vxlan_hw(struct xgbe_prv_data *pdata) +{ + struct xgbe_vxlan_data *vdata; + + if (pdata->vxlan_port_set) + return; + + if (list_empty(&pdata->vxlan_ports)) + return; + + vdata = list_first_entry(&pdata->vxlan_ports, + struct xgbe_vxlan_data, list); + + pdata->vxlan_port_set = 1; + pdata->vxlan_port = be16_to_cpu(vdata->port); + + pdata->hw_if.enable_vxlan(pdata); +} + +static void xgbe_enable_vxlan_accel(struct xgbe_prv_data *pdata) +{ + /* VXLAN acceleration desired? */ + if (!pdata->vxlan_features) + return; + + /* VXLAN acceleration possible? */ + if (pdata->vxlan_force_disable) + return; + + xgbe_enable_vxlan_hw(pdata); + + xgbe_enable_vxlan_offloads(pdata); +} + +static void xgbe_reset_vxlan_accel(struct xgbe_prv_data *pdata) +{ + xgbe_disable_vxlan_hw(pdata); + + if (pdata->vxlan_features) + xgbe_enable_vxlan_offloads(pdata); + + pdata->vxlan_force_disable = 0; } static void xgbe_napi_enable(struct xgbe_prv_data *pdata, unsigned int add) @@ -887,7 +1073,7 @@ static int xgbe_request_irqs(struct xgbe_prv_data *pdata) (unsigned long)pdata); ret = devm_request_irq(pdata->dev, pdata->dev_irq, xgbe_isr, 0, - netdev->name, pdata); + netdev_name(netdev), pdata); if (ret) { netdev_alert(netdev, "error requesting irq %d\n", pdata->dev_irq); @@ -1154,6 +1340,8 @@ static int xgbe_start(struct xgbe_prv_data *pdata) hw_if->enable_tx(pdata); hw_if->enable_rx(pdata); + udp_tunnel_get_rx_info(netdev); + netif_tx_start_all_queues(netdev); xgbe_start_timers(pdata); @@ -1195,6 +1383,8 @@ static void xgbe_stop(struct xgbe_prv_data *pdata) xgbe_stop_timers(pdata); flush_workqueue(pdata->dev_workqueue); + xgbe_reset_vxlan_accel(pdata); + hw_if->disable_tx(pdata); hw_if->disable_rx(pdata); @@ -1483,10 +1673,18 @@ static int xgbe_prep_tso(struct sk_buff *skb, struct xgbe_packet_data *packet) if (ret) return ret; - packet->header_len = skb_transport_offset(skb) + tcp_hdrlen(skb); - packet->tcp_header_len = tcp_hdrlen(skb); + if (XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, VXLAN)) { + packet->header_len = skb_inner_transport_offset(skb) + + inner_tcp_hdrlen(skb); + packet->tcp_header_len = inner_tcp_hdrlen(skb); + } else { + packet->header_len = skb_transport_offset(skb) + + tcp_hdrlen(skb); + packet->tcp_header_len = tcp_hdrlen(skb); + } packet->tcp_payload_len = skb->len - packet->header_len; packet->mss = skb_shinfo(skb)->gso_size; + DBGPR(" packet->header_len=%u\n", packet->header_len); DBGPR(" packet->tcp_header_len=%u, packet->tcp_payload_len=%u\n", packet->tcp_header_len, packet->tcp_payload_len); @@ -1501,6 +1699,49 @@ static int xgbe_prep_tso(struct sk_buff *skb, struct xgbe_packet_data *packet) return 0; } +static bool xgbe_is_vxlan(struct xgbe_prv_data *pdata, struct sk_buff *skb) +{ + struct xgbe_vxlan_data *vdata; + + if (pdata->vxlan_force_disable) + return false; + + if (!skb->encapsulation) + return false; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return false; + + switch (skb->protocol) { + case htons(ETH_P_IP): + if (ip_hdr(skb)->protocol != IPPROTO_UDP) + return false; + break; + + case htons(ETH_P_IPV6): + if (ipv6_hdr(skb)->nexthdr != IPPROTO_UDP) + return false; + break; + + default: + return false; + } + + /* See if we have the UDP port in our list */ + list_for_each_entry(vdata, &pdata->vxlan_ports, list) { + if ((skb->protocol == htons(ETH_P_IP)) && + (vdata->sa_family == AF_INET) && + (vdata->port == udp_hdr(skb)->dest)) + return true; + else if ((skb->protocol == htons(ETH_P_IPV6)) && + (vdata->sa_family == AF_INET6) && + (vdata->port == udp_hdr(skb)->dest)) + return true; + } + + return false; +} + static int xgbe_is_tso(struct sk_buff *skb) { if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -1549,6 +1790,10 @@ static void xgbe_packet_info(struct xgbe_prv_data *pdata, XGMAC_SET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, CSUM_ENABLE, 1); + if (xgbe_is_vxlan(pdata, skb)) + XGMAC_SET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, + VXLAN, 1); + if (skb_vlan_tag_present(skb)) { /* VLAN requires an extra descriptor if tag is different */ if (skb_vlan_tag_get(skb) != ring->tx.cur_vlan_ctag) @@ -1589,16 +1834,42 @@ static int xgbe_open(struct net_device *netdev) DBGPR("-->xgbe_open\n"); + /* Create the various names based on netdev name */ + snprintf(pdata->an_name, sizeof(pdata->an_name) - 1, "%s-pcs", + netdev_name(netdev)); + + snprintf(pdata->ecc_name, sizeof(pdata->ecc_name) - 1, "%s-ecc", + netdev_name(netdev)); + + snprintf(pdata->i2c_name, sizeof(pdata->i2c_name) - 1, "%s-i2c", + netdev_name(netdev)); + + /* Create workqueues */ + pdata->dev_workqueue = + create_singlethread_workqueue(netdev_name(netdev)); + if (!pdata->dev_workqueue) { + netdev_err(netdev, "device workqueue creation failed\n"); + return -ENOMEM; + } + + pdata->an_workqueue = + create_singlethread_workqueue(pdata->an_name); + if (!pdata->an_workqueue) { + netdev_err(netdev, "phy workqueue creation failed\n"); + ret = -ENOMEM; + goto err_dev_wq; + } + /* Reset the phy settings */ ret = xgbe_phy_reset(pdata); if (ret) - return ret; + goto err_an_wq; /* Enable the clocks */ ret = clk_prepare_enable(pdata->sysclk); if (ret) { netdev_alert(netdev, "dma clk_prepare_enable failed\n"); - return ret; + goto err_an_wq; } ret = clk_prepare_enable(pdata->ptpclk); @@ -1651,6 +1922,12 @@ err_ptpclk: err_sysclk: clk_disable_unprepare(pdata->sysclk); +err_an_wq: + destroy_workqueue(pdata->an_workqueue); + +err_dev_wq: + destroy_workqueue(pdata->dev_workqueue); + return ret; } @@ -1674,6 +1951,12 @@ static int xgbe_close(struct net_device *netdev) clk_disable_unprepare(pdata->ptpclk); clk_disable_unprepare(pdata->sysclk); + flush_workqueue(pdata->an_workqueue); + destroy_workqueue(pdata->an_workqueue); + + flush_workqueue(pdata->dev_workqueue); + destroy_workqueue(pdata->dev_workqueue); + set_bit(XGBE_DOWN, &pdata->dev_state); DBGPR("<--xgbe_close\n"); @@ -1918,18 +2201,18 @@ static void xgbe_poll_controller(struct net_device *netdev) } #endif /* End CONFIG_NET_POLL_CONTROLLER */ -static int xgbe_setup_tc(struct net_device *netdev, u32 handle, u32 chain_index, - __be16 proto, - struct tc_to_netdev *tc_to_netdev) +static int xgbe_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) { struct xgbe_prv_data *pdata = netdev_priv(netdev); + struct tc_mqprio_qopt *mqprio = type_data; u8 tc; - if (tc_to_netdev->type != TC_SETUP_MQPRIO) - return -EINVAL; + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - tc_to_netdev->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - tc = tc_to_netdev->mqprio->num_tc; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + tc = mqprio->num_tc; if (tc > pdata->hw_feat.tc_cnt) return -EINVAL; @@ -1940,18 +2223,83 @@ static int xgbe_setup_tc(struct net_device *netdev, u32 handle, u32 chain_index, return 0; } +static netdev_features_t xgbe_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + struct xgbe_prv_data *pdata = netdev_priv(netdev); + netdev_features_t vxlan_base, vxlan_mask; + + vxlan_base = NETIF_F_GSO_UDP_TUNNEL | NETIF_F_RX_UDP_TUNNEL_PORT; + vxlan_mask = vxlan_base | NETIF_F_GSO_UDP_TUNNEL_CSUM; + + pdata->vxlan_features = features & vxlan_mask; + + /* Only fix VXLAN-related features */ + if (!pdata->vxlan_features) + return features; + + /* If VXLAN isn't supported then clear any features: + * This is needed because NETIF_F_RX_UDP_TUNNEL_PORT gets + * automatically set if ndo_udp_tunnel_add is set. + */ + if (!pdata->hw_feat.vxn) + return features & ~vxlan_mask; + + /* VXLAN CSUM requires VXLAN base */ + if ((features & NETIF_F_GSO_UDP_TUNNEL_CSUM) && + !(features & NETIF_F_GSO_UDP_TUNNEL)) { + netdev_notice(netdev, + "forcing tx udp tunnel support\n"); + features |= NETIF_F_GSO_UDP_TUNNEL; + } + + /* Can't do one without doing the other */ + if ((features & vxlan_base) != vxlan_base) { + netdev_notice(netdev, + "forcing both tx and rx udp tunnel support\n"); + features |= vxlan_base; + } + + if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { + if (!(features & NETIF_F_GSO_UDP_TUNNEL_CSUM)) { + netdev_notice(netdev, + "forcing tx udp tunnel checksumming on\n"); + features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + } else { + if (features & NETIF_F_GSO_UDP_TUNNEL_CSUM) { + netdev_notice(netdev, + "forcing tx udp tunnel checksumming off\n"); + features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + } + + pdata->vxlan_features = features & vxlan_mask; + + /* Adjust UDP Tunnel based on current state */ + if (pdata->vxlan_force_disable) { + netdev_notice(netdev, + "VXLAN acceleration disabled, turning off udp tunnel features\n"); + features &= ~vxlan_mask; + } + + return features; +} + static int xgbe_set_features(struct net_device *netdev, netdev_features_t features) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; netdev_features_t rxhash, rxcsum, rxvlan, rxvlan_filter; + netdev_features_t udp_tunnel; int ret = 0; rxhash = pdata->netdev_features & NETIF_F_RXHASH; rxcsum = pdata->netdev_features & NETIF_F_RXCSUM; rxvlan = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX; rxvlan_filter = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_FILTER; + udp_tunnel = pdata->netdev_features & NETIF_F_GSO_UDP_TUNNEL; if ((features & NETIF_F_RXHASH) && !rxhash) ret = hw_if->enable_rss(pdata); @@ -1975,6 +2323,11 @@ static int xgbe_set_features(struct net_device *netdev, else if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER) && rxvlan_filter) hw_if->disable_rx_vlan_filtering(pdata); + if ((features & NETIF_F_GSO_UDP_TUNNEL) && !udp_tunnel) + xgbe_enable_vxlan_accel(pdata); + else if (!(features & NETIF_F_GSO_UDP_TUNNEL) && udp_tunnel) + xgbe_disable_vxlan_accel(pdata); + pdata->netdev_features = features; DBGPR("<--xgbe_set_features\n"); @@ -1982,6 +2335,111 @@ static int xgbe_set_features(struct net_device *netdev, return 0; } +static void xgbe_udp_tunnel_add(struct net_device *netdev, + struct udp_tunnel_info *ti) +{ + struct xgbe_prv_data *pdata = netdev_priv(netdev); + struct xgbe_vxlan_data *vdata; + + if (!pdata->hw_feat.vxn) + return; + + if (ti->type != UDP_TUNNEL_TYPE_VXLAN) + return; + + pdata->vxlan_port_count++; + + netif_dbg(pdata, drv, netdev, + "adding VXLAN tunnel, family=%hx/port=%hx\n", + ti->sa_family, be16_to_cpu(ti->port)); + + if (pdata->vxlan_force_disable) + return; + + vdata = kzalloc(sizeof(*vdata), GFP_ATOMIC); + if (!vdata) { + /* Can no longer properly track VXLAN ports */ + pdata->vxlan_force_disable = 1; + netif_dbg(pdata, drv, netdev, + "internal error, disabling VXLAN accelerations\n"); + + xgbe_disable_vxlan_accel(pdata); + + return; + } + vdata->sa_family = ti->sa_family; + vdata->port = ti->port; + + list_add_tail(&vdata->list, &pdata->vxlan_ports); + + /* First port added? */ + if (pdata->vxlan_port_count == 1) { + xgbe_enable_vxlan_accel(pdata); + + return; + } +} + +static void xgbe_udp_tunnel_del(struct net_device *netdev, + struct udp_tunnel_info *ti) +{ + struct xgbe_prv_data *pdata = netdev_priv(netdev); + struct xgbe_vxlan_data *vdata; + + if (!pdata->hw_feat.vxn) + return; + + if (ti->type != UDP_TUNNEL_TYPE_VXLAN) + return; + + netif_dbg(pdata, drv, netdev, + "deleting VXLAN tunnel, family=%hx/port=%hx\n", + ti->sa_family, be16_to_cpu(ti->port)); + + /* Don't need safe version since loop terminates with deletion */ + list_for_each_entry(vdata, &pdata->vxlan_ports, list) { + if (vdata->sa_family != ti->sa_family) + continue; + + if (vdata->port != ti->port) + continue; + + list_del(&vdata->list); + kfree(vdata); + + break; + } + + pdata->vxlan_port_count--; + if (!pdata->vxlan_port_count) { + xgbe_reset_vxlan_accel(pdata); + + return; + } + + if (pdata->vxlan_force_disable) + return; + + /* See if VXLAN tunnel id needs to be changed */ + vdata = list_first_entry(&pdata->vxlan_ports, + struct xgbe_vxlan_data, list); + if (pdata->vxlan_port == be16_to_cpu(vdata->port)) + return; + + pdata->vxlan_port = be16_to_cpu(vdata->port); + pdata->hw_if.set_vxlan_id(pdata); +} + +static netdev_features_t xgbe_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + features = vlan_features_check(skb, features); + features = vxlan_features_check(skb, features); + + return features; +} + static const struct net_device_ops xgbe_netdev_ops = { .ndo_open = xgbe_open, .ndo_stop = xgbe_close, @@ -1999,7 +2457,11 @@ static const struct net_device_ops xgbe_netdev_ops = { .ndo_poll_controller = xgbe_poll_controller, #endif .ndo_setup_tc = xgbe_setup_tc, + .ndo_fix_features = xgbe_fix_features, .ndo_set_features = xgbe_set_features, + .ndo_udp_tunnel_add = xgbe_udp_tunnel_add, + .ndo_udp_tunnel_del = xgbe_udp_tunnel_del, + .ndo_features_check = xgbe_features_check, }; const struct net_device_ops *xgbe_get_netdev_ops(void) @@ -2312,6 +2774,15 @@ skip_data: skb->ip_summed = CHECKSUM_UNNECESSARY; if (XGMAC_GET_BITS(packet->attributes, + RX_PACKET_ATTRIBUTES, TNP)) { + skb->encapsulation = 1; + + if (XGMAC_GET_BITS(packet->attributes, + RX_PACKET_ATTRIBUTES, TNPCSUM_DONE)) + skb->csum_level = 1; + } + + if (XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, VLAN_CTAG)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), packet->vlan_ctag); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 67a2e52ad25d..ff397bb25042 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -146,6 +146,7 @@ static const struct xgbe_stats xgbe_gstring_stats[] = { XGMAC_MMC_STAT("tx_broadcast_packets", txbroadcastframes_gb), XGMAC_MMC_STAT("tx_multicast_packets", txmulticastframes_gb), XGMAC_MMC_STAT("tx_vlan_packets", txvlanframes_g), + XGMAC_EXT_STAT("tx_vxlan_packets", tx_vxlan_packets), XGMAC_EXT_STAT("tx_tso_packets", tx_tso_packets), XGMAC_MMC_STAT("tx_64_byte_packets", tx64octets_gb), XGMAC_MMC_STAT("tx_65_to_127_byte_packets", tx65to127octets_gb), @@ -162,6 +163,7 @@ static const struct xgbe_stats xgbe_gstring_stats[] = { XGMAC_MMC_STAT("rx_broadcast_packets", rxbroadcastframes_g), XGMAC_MMC_STAT("rx_multicast_packets", rxmulticastframes_g), XGMAC_MMC_STAT("rx_vlan_packets", rxvlanframes_gb), + XGMAC_EXT_STAT("rx_vxlan_packets", rx_vxlan_packets), XGMAC_MMC_STAT("rx_64_byte_packets", rx64octets_gb), XGMAC_MMC_STAT("rx_65_to_127_byte_packets", rx65to127octets_gb), XGMAC_MMC_STAT("rx_128_to_255_byte_packets", rx128to255octets_gb), @@ -177,6 +179,8 @@ static const struct xgbe_stats xgbe_gstring_stats[] = { XGMAC_MMC_STAT("rx_out_of_range_errors", rxoutofrangetype), XGMAC_MMC_STAT("rx_fifo_overflow_errors", rxfifooverflow), XGMAC_MMC_STAT("rx_watchdog_errors", rxwatchdogerror), + XGMAC_EXT_STAT("rx_csum_errors", rx_csum_errors), + XGMAC_EXT_STAT("rx_vxlan_csum_errors", rx_vxlan_csum_errors), XGMAC_MMC_STAT("rx_pause_frames", rxpauseframes), XGMAC_EXT_STAT("rx_split_header_packets", rx_split_header_packets), XGMAC_EXT_STAT("rx_buffer_unavailable", rx_buffer_unavailable), @@ -186,6 +190,7 @@ static const struct xgbe_stats xgbe_gstring_stats[] = { static void xgbe_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { + struct xgbe_prv_data *pdata = netdev_priv(netdev); int i; switch (stringset) { @@ -195,6 +200,18 @@ static void xgbe_get_strings(struct net_device *netdev, u32 stringset, u8 *data) ETH_GSTRING_LEN); data += ETH_GSTRING_LEN; } + for (i = 0; i < pdata->tx_ring_count; i++) { + sprintf(data, "txq_%u_packets", i); + data += ETH_GSTRING_LEN; + sprintf(data, "txq_%u_bytes", i); + data += ETH_GSTRING_LEN; + } + for (i = 0; i < pdata->rx_ring_count; i++) { + sprintf(data, "rxq_%u_packets", i); + data += ETH_GSTRING_LEN; + sprintf(data, "rxq_%u_bytes", i); + data += ETH_GSTRING_LEN; + } break; } } @@ -211,15 +228,26 @@ static void xgbe_get_ethtool_stats(struct net_device *netdev, stat = (u8 *)pdata + xgbe_gstring_stats[i].stat_offset; *data++ = *(u64 *)stat; } + for (i = 0; i < pdata->tx_ring_count; i++) { + *data++ = pdata->ext_stats.txq_packets[i]; + *data++ = pdata->ext_stats.txq_bytes[i]; + } + for (i = 0; i < pdata->rx_ring_count; i++) { + *data++ = pdata->ext_stats.rxq_packets[i]; + *data++ = pdata->ext_stats.rxq_bytes[i]; + } } static int xgbe_get_sset_count(struct net_device *netdev, int stringset) { + struct xgbe_prv_data *pdata = netdev_priv(netdev); int ret; switch (stringset) { case ETH_SS_STATS: - ret = XGBE_STATS_COUNT; + ret = XGBE_STATS_COUNT + + (pdata->tx_ring_count * 2) + + (pdata->rx_ring_count * 2); break; default: @@ -243,6 +271,7 @@ static int xgbe_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct xgbe_prv_data *pdata = netdev_priv(netdev); + struct ethtool_link_ksettings *lks = &pdata->phy.lks; int ret = 0; if (pause->autoneg && (pdata->phy.autoneg != AUTONEG_ENABLE)) { @@ -255,16 +284,21 @@ static int xgbe_set_pauseparam(struct net_device *netdev, pdata->phy.tx_pause = pause->tx_pause; pdata->phy.rx_pause = pause->rx_pause; - pdata->phy.advertising &= ~ADVERTISED_Pause; - pdata->phy.advertising &= ~ADVERTISED_Asym_Pause; + XGBE_CLR_ADV(lks, Pause); + XGBE_CLR_ADV(lks, Asym_Pause); if (pause->rx_pause) { - pdata->phy.advertising |= ADVERTISED_Pause; - pdata->phy.advertising |= ADVERTISED_Asym_Pause; + XGBE_SET_ADV(lks, Pause); + XGBE_SET_ADV(lks, Asym_Pause); } - if (pause->tx_pause) - pdata->phy.advertising ^= ADVERTISED_Asym_Pause; + if (pause->tx_pause) { + /* Equivalent to XOR of Asym_Pause */ + if (XGBE_ADV(lks, Asym_Pause)) + XGBE_CLR_ADV(lks, Asym_Pause); + else + XGBE_SET_ADV(lks, Asym_Pause); + } if (netif_running(netdev)) ret = pdata->phy_if.phy_config_aneg(pdata); @@ -276,22 +310,20 @@ static int xgbe_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { struct xgbe_prv_data *pdata = netdev_priv(netdev); + struct ethtool_link_ksettings *lks = &pdata->phy.lks; cmd->base.phy_address = pdata->phy.address; - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - pdata->phy.supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - pdata->phy.advertising); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising, - pdata->phy.lp_advertising); - cmd->base.autoneg = pdata->phy.autoneg; cmd->base.speed = pdata->phy.speed; cmd->base.duplex = pdata->phy.duplex; cmd->base.port = PORT_NONE; + XGBE_LM_COPY(cmd, supported, lks, supported); + XGBE_LM_COPY(cmd, advertising, lks, advertising); + XGBE_LM_COPY(cmd, lp_advertising, lks, lp_advertising); + return 0; } @@ -299,7 +331,8 @@ static int xgbe_set_link_ksettings(struct net_device *netdev, const struct ethtool_link_ksettings *cmd) { struct xgbe_prv_data *pdata = netdev_priv(netdev); - u32 advertising; + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); u32 speed; int ret; @@ -331,15 +364,17 @@ static int xgbe_set_link_ksettings(struct net_device *netdev, } } - ethtool_convert_link_mode_to_legacy_u32(&advertising, - cmd->link_modes.advertising); - netif_dbg(pdata, link, netdev, - "requested advertisement %#x, phy supported %#x\n", - advertising, pdata->phy.supported); + "requested advertisement 0x%*pb, phy supported 0x%*pb\n", + __ETHTOOL_LINK_MODE_MASK_NBITS, cmd->link_modes.advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS, lks->link_modes.supported); + + bitmap_and(advertising, + cmd->link_modes.advertising, lks->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); - advertising &= pdata->phy.supported; - if ((cmd->base.autoneg == AUTONEG_ENABLE) && !advertising) { + if ((cmd->base.autoneg == AUTONEG_ENABLE) && + bitmap_empty(advertising, __ETHTOOL_LINK_MODE_MASK_NBITS)) { netdev_err(netdev, "unsupported requested advertisement\n"); return -EINVAL; @@ -349,12 +384,13 @@ static int xgbe_set_link_ksettings(struct net_device *netdev, pdata->phy.autoneg = cmd->base.autoneg; pdata->phy.speed = speed; pdata->phy.duplex = cmd->base.duplex; - pdata->phy.advertising = advertising; + bitmap_copy(lks->link_modes.advertising, advertising, + __ETHTOOL_LINK_MODE_MASK_NBITS); if (cmd->base.autoneg == AUTONEG_ENABLE) - pdata->phy.advertising |= ADVERTISED_Autoneg; + XGBE_SET_ADV(lks, Autoneg); else - pdata->phy.advertising &= ~ADVERTISED_Autoneg; + XGBE_CLR_ADV(lks, Autoneg); if (netif_running(netdev)) ret = pdata->phy_if.phy_config_aneg(pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 500147d9e3c8..d91fa595be98 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -120,6 +120,7 @@ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/io.h> +#include <linux/notifier.h> #include "xgbe.h" #include "xgbe-common.h" @@ -192,6 +193,7 @@ struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev) mutex_init(&pdata->i2c_mutex); init_completion(&pdata->i2c_complete); init_completion(&pdata->mdio_complete); + INIT_LIST_HEAD(&pdata->vxlan_ports); pdata->msg_enable = netif_msg_init(debug, default_msg_level); @@ -373,6 +375,28 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata) if (pdata->hw_feat.rss) netdev->hw_features |= NETIF_F_RXHASH; + if (pdata->hw_feat.vxn) { + netdev->hw_enc_features = NETIF_F_SG | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_GRO | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_RX_UDP_TUNNEL_PORT; + + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_RX_UDP_TUNNEL_PORT; + + pdata->vxlan_offloads_set = 1; + pdata->vxlan_features = NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_RX_UDP_TUNNEL_PORT; + } + netdev->vlan_features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -399,35 +423,6 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata) return ret; } - /* Create the PHY/ANEG name based on netdev name */ - snprintf(pdata->an_name, sizeof(pdata->an_name) - 1, "%s-pcs", - netdev_name(netdev)); - - /* Create the ECC name based on netdev name */ - snprintf(pdata->ecc_name, sizeof(pdata->ecc_name) - 1, "%s-ecc", - netdev_name(netdev)); - - /* Create the I2C name based on netdev name */ - snprintf(pdata->i2c_name, sizeof(pdata->i2c_name) - 1, "%s-i2c", - netdev_name(netdev)); - - /* Create workqueues */ - pdata->dev_workqueue = - create_singlethread_workqueue(netdev_name(netdev)); - if (!pdata->dev_workqueue) { - netdev_err(netdev, "device workqueue creation failed\n"); - ret = -ENOMEM; - goto err_netdev; - } - - pdata->an_workqueue = - create_singlethread_workqueue(pdata->an_name); - if (!pdata->an_workqueue) { - netdev_err(netdev, "phy workqueue creation failed\n"); - ret = -ENOMEM; - goto err_wq; - } - if (IS_REACHABLE(CONFIG_PTP_1588_CLOCK)) xgbe_ptp_register(pdata); @@ -439,14 +434,6 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata) pdata->rx_ring_count); return 0; - -err_wq: - destroy_workqueue(pdata->dev_workqueue); - -err_netdev: - unregister_netdev(netdev); - - return ret; } void xgbe_deconfig_netdev(struct xgbe_prv_data *pdata) @@ -458,21 +445,45 @@ void xgbe_deconfig_netdev(struct xgbe_prv_data *pdata) if (IS_REACHABLE(CONFIG_PTP_1588_CLOCK)) xgbe_ptp_unregister(pdata); + unregister_netdev(netdev); + pdata->phy_if.phy_exit(pdata); +} - flush_workqueue(pdata->an_workqueue); - destroy_workqueue(pdata->an_workqueue); +static int xgbe_netdev_event(struct notifier_block *nb, unsigned long event, + void *data) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(data); + struct xgbe_prv_data *pdata = netdev_priv(netdev); - flush_workqueue(pdata->dev_workqueue); - destroy_workqueue(pdata->dev_workqueue); + if (netdev->netdev_ops != xgbe_get_netdev_ops()) + goto out; - unregister_netdev(netdev); + switch (event) { + case NETDEV_CHANGENAME: + xgbe_debugfs_rename(pdata); + break; + + default: + break; + } + +out: + return NOTIFY_DONE; } +static struct notifier_block xgbe_netdev_notifier = { + .notifier_call = xgbe_netdev_event, +}; + static int __init xgbe_mod_init(void) { int ret; + ret = register_netdevice_notifier(&xgbe_netdev_notifier); + if (ret) + return ret; + ret = xgbe_platform_init(); if (ret) return ret; @@ -489,6 +500,8 @@ static void __exit xgbe_mod_exit(void) xgbe_pci_exit(); xgbe_platform_exit(); + + unregister_netdevice_notifier(&xgbe_netdev_notifier); } module_init(xgbe_mod_init); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 80684914dd8a..072b9f664597 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -615,12 +615,14 @@ static enum xgbe_an xgbe_an73_page_received(struct xgbe_prv_data *pdata) static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + /* Be sure we aren't looping trying to negotiate */ if (xgbe_in_kr_mode(pdata)) { pdata->kr_state = XGBE_RX_ERROR; - if (!(pdata->phy.advertising & ADVERTISED_1000baseKX_Full) && - !(pdata->phy.advertising & ADVERTISED_2500baseX_Full)) + if (!XGBE_ADV(lks, 1000baseKX_Full) && + !XGBE_ADV(lks, 2500baseX_Full)) return XGBE_AN_NO_LINK; if (pdata->kx_state != XGBE_RX_BPA) @@ -628,7 +630,7 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata) } else { pdata->kx_state = XGBE_RX_ERROR; - if (!(pdata->phy.advertising & ADVERTISED_10000baseKR_Full)) + if (!XGBE_ADV(lks, 10000baseKR_Full)) return XGBE_AN_NO_LINK; if (pdata->kr_state != XGBE_RX_BPA) @@ -944,18 +946,19 @@ static void xgbe_an_state_machine(struct work_struct *work) static void xgbe_an37_init(struct xgbe_prv_data *pdata) { - unsigned int advertising, reg; + struct ethtool_link_ksettings lks; + unsigned int reg; - advertising = pdata->phy_if.phy_impl.an_advertising(pdata); + pdata->phy_if.phy_impl.an_advertising(pdata, &lks); /* Set up Advertisement register */ reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_ADVERTISE); - if (advertising & ADVERTISED_Pause) + if (XGBE_ADV(&lks, Pause)) reg |= 0x100; else reg &= ~0x100; - if (advertising & ADVERTISED_Asym_Pause) + if (XGBE_ADV(&lks, Asym_Pause)) reg |= 0x80; else reg &= ~0x80; @@ -982,6 +985,8 @@ static void xgbe_an37_init(struct xgbe_prv_data *pdata) break; } + reg |= XGBE_AN_CL37_MII_CTRL_8BIT; + XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_CTRL, reg); netif_dbg(pdata, link, pdata->netdev, "CL37 AN (%s) initialized\n", @@ -990,13 +995,14 @@ static void xgbe_an37_init(struct xgbe_prv_data *pdata) static void xgbe_an73_init(struct xgbe_prv_data *pdata) { - unsigned int advertising, reg; + struct ethtool_link_ksettings lks; + unsigned int reg; - advertising = pdata->phy_if.phy_impl.an_advertising(pdata); + pdata->phy_if.phy_impl.an_advertising(pdata, &lks); /* Set up Advertisement register 3 first */ reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2); - if (advertising & ADVERTISED_10000baseR_FEC) + if (XGBE_ADV(&lks, 10000baseR_FEC)) reg |= 0xc000; else reg &= ~0xc000; @@ -1005,13 +1011,13 @@ static void xgbe_an73_init(struct xgbe_prv_data *pdata) /* Set up Advertisement register 2 next */ reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1); - if (advertising & ADVERTISED_10000baseKR_Full) + if (XGBE_ADV(&lks, 10000baseKR_Full)) reg |= 0x80; else reg &= ~0x80; - if ((advertising & ADVERTISED_1000baseKX_Full) || - (advertising & ADVERTISED_2500baseX_Full)) + if (XGBE_ADV(&lks, 1000baseKX_Full) || + XGBE_ADV(&lks, 2500baseX_Full)) reg |= 0x20; else reg &= ~0x20; @@ -1020,12 +1026,12 @@ static void xgbe_an73_init(struct xgbe_prv_data *pdata) /* Set up Advertisement register 1 last */ reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE); - if (advertising & ADVERTISED_Pause) + if (XGBE_ADV(&lks, Pause)) reg |= 0x400; else reg &= ~0x400; - if (advertising & ADVERTISED_Asym_Pause) + if (XGBE_ADV(&lks, Asym_Pause)) reg |= 0x800; else reg &= ~0x800; @@ -1281,9 +1287,10 @@ static enum xgbe_mode xgbe_phy_status_aneg(struct xgbe_prv_data *pdata) static void xgbe_phy_status_result(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; - pdata->phy.lp_advertising = 0; + XGBE_ZERO_LP_ADV(lks); if ((pdata->phy.autoneg != AUTONEG_ENABLE) || pdata->parallel_detect) mode = xgbe_cur_mode(pdata); @@ -1513,17 +1520,21 @@ static void xgbe_dump_phy_registers(struct xgbe_prv_data *pdata) static int xgbe_phy_best_advertised_speed(struct xgbe_prv_data *pdata) { - if (pdata->phy.advertising & ADVERTISED_10000baseKR_Full) + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + + if (XGBE_ADV(lks, 10000baseKR_Full)) return SPEED_10000; - else if (pdata->phy.advertising & ADVERTISED_10000baseT_Full) + else if (XGBE_ADV(lks, 10000baseT_Full)) return SPEED_10000; - else if (pdata->phy.advertising & ADVERTISED_2500baseX_Full) + else if (XGBE_ADV(lks, 2500baseX_Full)) return SPEED_2500; - else if (pdata->phy.advertising & ADVERTISED_1000baseKX_Full) + else if (XGBE_ADV(lks, 2500baseT_Full)) + return SPEED_2500; + else if (XGBE_ADV(lks, 1000baseKX_Full)) return SPEED_1000; - else if (pdata->phy.advertising & ADVERTISED_1000baseT_Full) + else if (XGBE_ADV(lks, 1000baseT_Full)) return SPEED_1000; - else if (pdata->phy.advertising & ADVERTISED_100baseT_Full) + else if (XGBE_ADV(lks, 100baseT_Full)) return SPEED_100; return SPEED_UNKNOWN; @@ -1531,13 +1542,12 @@ static int xgbe_phy_best_advertised_speed(struct xgbe_prv_data *pdata) static void xgbe_phy_exit(struct xgbe_prv_data *pdata) { - xgbe_phy_stop(pdata); - pdata->phy_if.phy_impl.exit(pdata); } static int xgbe_phy_init(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; int ret; mutex_init(&pdata->an_mutex); @@ -1555,11 +1565,13 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) ret = pdata->phy_if.phy_impl.init(pdata); if (ret) return ret; - pdata->phy.advertising = pdata->phy.supported; + + /* Copy supported link modes to advertising link modes */ + XGBE_LM_COPY(lks, advertising, lks, supported); pdata->phy.address = 0; - if (pdata->phy.advertising & ADVERTISED_Autoneg) { + if (XGBE_ADV(lks, Autoneg)) { pdata->phy.autoneg = AUTONEG_ENABLE; pdata->phy.speed = SPEED_UNKNOWN; pdata->phy.duplex = DUPLEX_UNKNOWN; @@ -1576,16 +1588,21 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) pdata->phy.rx_pause = pdata->rx_pause; /* Fix up Flow Control advertising */ - pdata->phy.advertising &= ~ADVERTISED_Pause; - pdata->phy.advertising &= ~ADVERTISED_Asym_Pause; + XGBE_CLR_ADV(lks, Pause); + XGBE_CLR_ADV(lks, Asym_Pause); if (pdata->rx_pause) { - pdata->phy.advertising |= ADVERTISED_Pause; - pdata->phy.advertising |= ADVERTISED_Asym_Pause; + XGBE_SET_ADV(lks, Pause); + XGBE_SET_ADV(lks, Asym_Pause); } - if (pdata->tx_pause) - pdata->phy.advertising ^= ADVERTISED_Asym_Pause; + if (pdata->tx_pause) { + /* Equivalent to XOR of Asym_Pause */ + if (XGBE_ADV(lks, Asym_Pause)) + XGBE_CLR_ADV(lks, Asym_Pause); + else + XGBE_SET_ADV(lks, Asym_Pause); + } if (netif_msg_drv(pdata)) xgbe_dump_phy_registers(pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index 1e56ad7bd9a5..3e5833cf1fab 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -292,6 +292,10 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) pdata->xpcs_window_size = 1 << (pdata->xpcs_window_size + 7); pdata->xpcs_window_mask = pdata->xpcs_window_size - 1; if (netif_msg_probe(pdata)) { + dev_dbg(dev, "xpcs window def = %#010x\n", + pdata->xpcs_window_def_reg); + dev_dbg(dev, "xpcs window sel = %#010x\n", + pdata->xpcs_window_sel_reg); dev_dbg(dev, "xpcs window = %#010x\n", pdata->xpcs_window); dev_dbg(dev, "xpcs window size = %#010x\n", diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c index c75edcac5e0a..d16eae415f72 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v1.c @@ -231,20 +231,21 @@ static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata) static enum xgbe_mode xgbe_phy_an_outcome(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; enum xgbe_mode mode; unsigned int ad_reg, lp_reg; - pdata->phy.lp_advertising |= ADVERTISED_Autoneg; - pdata->phy.lp_advertising |= ADVERTISED_Backplane; + XGBE_SET_LP_ADV(lks, Autoneg); + XGBE_SET_LP_ADV(lks, Backplane); /* Compare Advertisement and Link Partner register 1 */ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA); if (lp_reg & 0x400) - pdata->phy.lp_advertising |= ADVERTISED_Pause; + XGBE_SET_LP_ADV(lks, Pause); if (lp_reg & 0x800) - pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause; + XGBE_SET_LP_ADV(lks, Asym_Pause); if (pdata->phy.pause_autoneg) { /* Set flow control based on auto-negotiation result */ @@ -266,12 +267,12 @@ static enum xgbe_mode xgbe_phy_an_outcome(struct xgbe_prv_data *pdata) ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1); if (lp_reg & 0x80) - pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_LP_ADV(lks, 10000baseKR_Full); if (lp_reg & 0x20) { if (phy_data->speed_set == XGBE_SPEEDSET_2500_10000) - pdata->phy.lp_advertising |= ADVERTISED_2500baseX_Full; + XGBE_SET_LP_ADV(lks, 2500baseX_Full); else - pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full; + XGBE_SET_LP_ADV(lks, 1000baseKX_Full); } ad_reg &= lp_reg; @@ -290,14 +291,17 @@ static enum xgbe_mode xgbe_phy_an_outcome(struct xgbe_prv_data *pdata) ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2); if (lp_reg & 0xc000) - pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC; + XGBE_SET_LP_ADV(lks, 10000baseR_FEC); return mode; } -static unsigned int xgbe_phy_an_advertising(struct xgbe_prv_data *pdata) +static void xgbe_phy_an_advertising(struct xgbe_prv_data *pdata, + struct ethtool_link_ksettings *dlks) { - return pdata->phy.advertising; + struct ethtool_link_ksettings *slks = &pdata->phy.lks; + + XGBE_LM_COPY(dlks, advertising, slks, advertising); } static int xgbe_phy_an_config(struct xgbe_prv_data *pdata) @@ -565,11 +569,10 @@ static void xgbe_phy_set_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) } static bool xgbe_phy_check_mode(struct xgbe_prv_data *pdata, - enum xgbe_mode mode, u32 advert) + enum xgbe_mode mode, bool advert) { if (pdata->phy.autoneg == AUTONEG_ENABLE) { - if (pdata->phy.advertising & advert) - return true; + return advert; } else { enum xgbe_mode cur_mode; @@ -583,16 +586,18 @@ static bool xgbe_phy_check_mode(struct xgbe_prv_data *pdata, static bool xgbe_phy_use_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + switch (mode) { case XGBE_MODE_KX_1000: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_1000baseKX_Full); + XGBE_ADV(lks, 1000baseKX_Full)); case XGBE_MODE_KX_2500: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_2500baseX_Full); + XGBE_ADV(lks, 2500baseX_Full)); case XGBE_MODE_KR: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_10000baseKR_Full); + XGBE_ADV(lks, 10000baseKR_Full)); default: return false; } @@ -672,6 +677,7 @@ static void xgbe_phy_exit(struct xgbe_prv_data *pdata) static int xgbe_phy_init(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data; int ret; @@ -790,21 +796,23 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) } /* Initialize supported features */ - pdata->phy.supported = SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_Backplane; - pdata->phy.supported |= SUPPORTED_10000baseKR_Full; + XGBE_ZERO_SUP(lks); + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, Backplane); + XGBE_SET_SUP(lks, 10000baseKR_Full); switch (phy_data->speed_set) { case XGBE_SPEEDSET_1000_10000: - pdata->phy.supported |= SUPPORTED_1000baseKX_Full; + XGBE_SET_SUP(lks, 1000baseKX_Full); break; case XGBE_SPEEDSET_2500_10000: - pdata->phy.supported |= SUPPORTED_2500baseX_Full; + XGBE_SET_SUP(lks, 2500baseX_Full); break; } if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE) - pdata->phy.supported |= SUPPORTED_10000baseR_FEC; + XGBE_SET_SUP(lks, 10000baseR_FEC); pdata->phy_data = phy_data; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 04b5c149caca..3304a291aa96 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -709,18 +709,13 @@ static int xgbe_phy_mii_read(struct mii_bus *mii, int addr, int reg) static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; if (!phy_data->sfp_mod_absent && !phy_data->sfp_changed) return; - pdata->phy.supported &= ~SUPPORTED_Autoneg; - pdata->phy.supported &= ~(SUPPORTED_Pause | SUPPORTED_Asym_Pause); - pdata->phy.supported &= ~SUPPORTED_TP; - pdata->phy.supported &= ~SUPPORTED_FIBRE; - pdata->phy.supported &= ~SUPPORTED_100baseT_Full; - pdata->phy.supported &= ~SUPPORTED_1000baseT_Full; - pdata->phy.supported &= ~SUPPORTED_10000baseT_Full; + XGBE_ZERO_SUP(lks); if (phy_data->sfp_mod_absent) { pdata->phy.speed = SPEED_UNKNOWN; @@ -728,18 +723,13 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) pdata->phy.autoneg = AUTONEG_ENABLE; pdata->phy.pause_autoneg = AUTONEG_ENABLE; - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_TP; - pdata->phy.supported |= SUPPORTED_FIBRE; - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) - pdata->phy.supported |= SUPPORTED_100baseT_Full; - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) - pdata->phy.supported |= SUPPORTED_1000baseT_Full; - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) - pdata->phy.supported |= SUPPORTED_10000baseT_Full; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, TP); + XGBE_SET_SUP(lks, FIBRE); - pdata->phy.advertising = pdata->phy.supported; + XGBE_LM_COPY(lks, advertising, lks, supported); return; } @@ -753,8 +743,18 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_UNKNOWN; pdata->phy.autoneg = AUTONEG_ENABLE; pdata->phy.pause_autoneg = AUTONEG_ENABLE; - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + if (phy_data->sfp_base == XGBE_SFP_BASE_1000_T) { + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) + XGBE_SET_SUP(lks, 100baseT_Full); + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) + XGBE_SET_SUP(lks, 1000baseT_Full); + } else { + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) + XGBE_SET_SUP(lks, 1000baseX_Full); + } break; case XGBE_SFP_BASE_10000_SR: case XGBE_SFP_BASE_10000_LR: @@ -765,6 +765,27 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) pdata->phy.duplex = DUPLEX_FULL; pdata->phy.autoneg = AUTONEG_DISABLE; pdata->phy.pause_autoneg = AUTONEG_DISABLE; + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) { + switch (phy_data->sfp_base) { + case XGBE_SFP_BASE_10000_SR: + XGBE_SET_SUP(lks, 10000baseSR_Full); + break; + case XGBE_SFP_BASE_10000_LR: + XGBE_SET_SUP(lks, 10000baseLR_Full); + break; + case XGBE_SFP_BASE_10000_LRM: + XGBE_SET_SUP(lks, 10000baseLRM_Full); + break; + case XGBE_SFP_BASE_10000_ER: + XGBE_SET_SUP(lks, 10000baseER_Full); + break; + case XGBE_SFP_BASE_10000_CR: + XGBE_SET_SUP(lks, 10000baseCR_Full); + break; + default: + break; + } + } break; default: pdata->phy.speed = SPEED_UNKNOWN; @@ -778,38 +799,14 @@ static void xgbe_phy_sfp_phy_settings(struct xgbe_prv_data *pdata) case XGBE_SFP_BASE_1000_T: case XGBE_SFP_BASE_1000_CX: case XGBE_SFP_BASE_10000_CR: - pdata->phy.supported |= SUPPORTED_TP; + XGBE_SET_SUP(lks, TP); break; default: - pdata->phy.supported |= SUPPORTED_FIBRE; - } - - switch (phy_data->sfp_speed) { - case XGBE_SFP_SPEED_100_1000: - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) - pdata->phy.supported |= SUPPORTED_100baseT_Full; - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) - pdata->phy.supported |= SUPPORTED_1000baseT_Full; - break; - case XGBE_SFP_SPEED_1000: - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) - pdata->phy.supported |= SUPPORTED_1000baseT_Full; + XGBE_SET_SUP(lks, FIBRE); break; - case XGBE_SFP_SPEED_10000: - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) - pdata->phy.supported |= SUPPORTED_10000baseT_Full; - break; - default: - /* Choose the fastest supported speed */ - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) - pdata->phy.supported |= SUPPORTED_10000baseT_Full; - else if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) - pdata->phy.supported |= SUPPORTED_1000baseT_Full; - else if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) - pdata->phy.supported |= SUPPORTED_100baseT_Full; } - pdata->phy.advertising = pdata->phy.supported; + XGBE_LM_COPY(lks, advertising, lks, supported); } static bool xgbe_phy_sfp_bit_rate(struct xgbe_sfp_eeprom *sfp_eeprom, @@ -886,8 +883,10 @@ static void xgbe_phy_external_phy_quirks(struct xgbe_prv_data *pdata) static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; struct phy_device *phydev; + u32 advertising; int ret; /* If we already have a PHY, just return */ @@ -943,7 +942,10 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata) phy_data->phydev = phydev; xgbe_phy_external_phy_quirks(pdata); - phydev->advertising &= pdata->phy.advertising; + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + lks->link_modes.advertising); + phydev->advertising &= advertising; phy_start_aneg(phy_data->phydev); @@ -1277,6 +1279,7 @@ put: static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; u16 lcl_adv = 0, rmt_adv = 0; u8 fc; @@ -1293,11 +1296,11 @@ static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata) lcl_adv |= ADVERTISE_PAUSE_ASYM; if (phy_data->phydev->pause) { - pdata->phy.lp_advertising |= ADVERTISED_Pause; + XGBE_SET_LP_ADV(lks, Pause); rmt_adv |= LPA_PAUSE_CAP; } if (phy_data->phydev->asym_pause) { - pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause; + XGBE_SET_LP_ADV(lks, Asym_Pause); rmt_adv |= LPA_PAUSE_ASYM; } @@ -1310,10 +1313,11 @@ static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata) static enum xgbe_mode xgbe_phy_an37_sgmii_outcome(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; - pdata->phy.lp_advertising |= ADVERTISED_Autoneg; - pdata->phy.lp_advertising |= ADVERTISED_TP; + XGBE_SET_LP_ADV(lks, Autoneg); + XGBE_SET_LP_ADV(lks, TP); /* Use external PHY to determine flow control */ if (pdata->phy.pause_autoneg) @@ -1322,21 +1326,21 @@ static enum xgbe_mode xgbe_phy_an37_sgmii_outcome(struct xgbe_prv_data *pdata) switch (pdata->an_status & XGBE_SGMII_AN_LINK_SPEED) { case XGBE_SGMII_AN_LINK_SPEED_100: if (pdata->an_status & XGBE_SGMII_AN_LINK_DUPLEX) { - pdata->phy.lp_advertising |= ADVERTISED_100baseT_Full; + XGBE_SET_LP_ADV(lks, 100baseT_Full); mode = XGBE_MODE_SGMII_100; } else { /* Half-duplex not supported */ - pdata->phy.lp_advertising |= ADVERTISED_100baseT_Half; + XGBE_SET_LP_ADV(lks, 100baseT_Half); mode = XGBE_MODE_UNKNOWN; } break; case XGBE_SGMII_AN_LINK_SPEED_1000: if (pdata->an_status & XGBE_SGMII_AN_LINK_DUPLEX) { - pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Full; + XGBE_SET_LP_ADV(lks, 1000baseT_Full); mode = XGBE_MODE_SGMII_1000; } else { /* Half-duplex not supported */ - pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Half; + XGBE_SET_LP_ADV(lks, 1000baseT_Half); mode = XGBE_MODE_UNKNOWN; } break; @@ -1349,19 +1353,20 @@ static enum xgbe_mode xgbe_phy_an37_sgmii_outcome(struct xgbe_prv_data *pdata) static enum xgbe_mode xgbe_phy_an37_outcome(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; unsigned int ad_reg, lp_reg; - pdata->phy.lp_advertising |= ADVERTISED_Autoneg; - pdata->phy.lp_advertising |= ADVERTISED_FIBRE; + XGBE_SET_LP_ADV(lks, Autoneg); + XGBE_SET_LP_ADV(lks, FIBRE); /* Compare Advertisement and Link Partner register */ ad_reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_ADVERTISE); lp_reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_VEND2_AN_LP_ABILITY); if (lp_reg & 0x100) - pdata->phy.lp_advertising |= ADVERTISED_Pause; + XGBE_SET_LP_ADV(lks, Pause); if (lp_reg & 0x80) - pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause; + XGBE_SET_LP_ADV(lks, Asym_Pause); if (pdata->phy.pause_autoneg) { /* Set flow control based on auto-negotiation result */ @@ -1379,10 +1384,8 @@ static enum xgbe_mode xgbe_phy_an37_outcome(struct xgbe_prv_data *pdata) } } - if (lp_reg & 0x40) - pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Half; if (lp_reg & 0x20) - pdata->phy.lp_advertising |= ADVERTISED_1000baseT_Full; + XGBE_SET_LP_ADV(lks, 1000baseX_Full); /* Half duplex is not supported */ ad_reg &= lp_reg; @@ -1393,12 +1396,13 @@ static enum xgbe_mode xgbe_phy_an37_outcome(struct xgbe_prv_data *pdata) static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; enum xgbe_mode mode; unsigned int ad_reg, lp_reg; - pdata->phy.lp_advertising |= ADVERTISED_Autoneg; - pdata->phy.lp_advertising |= ADVERTISED_Backplane; + XGBE_SET_LP_ADV(lks, Autoneg); + XGBE_SET_LP_ADV(lks, Backplane); /* Use external PHY to determine flow control */ if (pdata->phy.pause_autoneg) @@ -1408,9 +1412,9 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1); if (lp_reg & 0x80) - pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_LP_ADV(lks, 10000baseKR_Full); if (lp_reg & 0x20) - pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full; + XGBE_SET_LP_ADV(lks, 1000baseKX_Full); ad_reg &= lp_reg; if (ad_reg & 0x80) { @@ -1463,26 +1467,27 @@ static enum xgbe_mode xgbe_phy_an73_redrv_outcome(struct xgbe_prv_data *pdata) ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2); if (lp_reg & 0xc000) - pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC; + XGBE_SET_LP_ADV(lks, 10000baseR_FEC); return mode; } static enum xgbe_mode xgbe_phy_an73_outcome(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; enum xgbe_mode mode; unsigned int ad_reg, lp_reg; - pdata->phy.lp_advertising |= ADVERTISED_Autoneg; - pdata->phy.lp_advertising |= ADVERTISED_Backplane; + XGBE_SET_LP_ADV(lks, Autoneg); + XGBE_SET_LP_ADV(lks, Backplane); /* Compare Advertisement and Link Partner register 1 */ ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA); if (lp_reg & 0x400) - pdata->phy.lp_advertising |= ADVERTISED_Pause; + XGBE_SET_LP_ADV(lks, Pause); if (lp_reg & 0x800) - pdata->phy.lp_advertising |= ADVERTISED_Asym_Pause; + XGBE_SET_LP_ADV(lks, Asym_Pause); if (pdata->phy.pause_autoneg) { /* Set flow control based on auto-negotiation result */ @@ -1504,9 +1509,9 @@ static enum xgbe_mode xgbe_phy_an73_outcome(struct xgbe_prv_data *pdata) ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 1); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 1); if (lp_reg & 0x80) - pdata->phy.lp_advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_LP_ADV(lks, 10000baseKR_Full); if (lp_reg & 0x20) - pdata->phy.lp_advertising |= ADVERTISED_1000baseKX_Full; + XGBE_SET_LP_ADV(lks, 1000baseKX_Full); ad_reg &= lp_reg; if (ad_reg & 0x80) @@ -1520,7 +1525,7 @@ static enum xgbe_mode xgbe_phy_an73_outcome(struct xgbe_prv_data *pdata) ad_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_ADVERTISE + 2); lp_reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_AN_LPA + 2); if (lp_reg & 0xc000) - pdata->phy.lp_advertising |= ADVERTISED_10000baseR_FEC; + XGBE_SET_LP_ADV(lks, 10000baseR_FEC); return mode; } @@ -1541,41 +1546,43 @@ static enum xgbe_mode xgbe_phy_an_outcome(struct xgbe_prv_data *pdata) } } -static unsigned int xgbe_phy_an_advertising(struct xgbe_prv_data *pdata) +static void xgbe_phy_an_advertising(struct xgbe_prv_data *pdata, + struct ethtool_link_ksettings *dlks) { + struct ethtool_link_ksettings *slks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; - unsigned int advertising; + + XGBE_LM_COPY(dlks, advertising, slks, advertising); /* Without a re-driver, just return current advertising */ if (!phy_data->redrv) - return pdata->phy.advertising; + return; /* With the KR re-driver we need to advertise a single speed */ - advertising = pdata->phy.advertising; - advertising &= ~ADVERTISED_1000baseKX_Full; - advertising &= ~ADVERTISED_10000baseKR_Full; + XGBE_CLR_ADV(dlks, 1000baseKX_Full); + XGBE_CLR_ADV(dlks, 10000baseKR_Full); switch (phy_data->port_mode) { case XGBE_PORT_MODE_BACKPLANE: - advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_ADV(dlks, 10000baseKR_Full); break; case XGBE_PORT_MODE_BACKPLANE_2500: - advertising |= ADVERTISED_1000baseKX_Full; + XGBE_SET_ADV(dlks, 1000baseKX_Full); break; case XGBE_PORT_MODE_1000BASE_T: case XGBE_PORT_MODE_1000BASE_X: case XGBE_PORT_MODE_NBASE_T: - advertising |= ADVERTISED_1000baseKX_Full; + XGBE_SET_ADV(dlks, 1000baseKX_Full); break; case XGBE_PORT_MODE_10GBASE_T: if (phy_data->phydev && (phy_data->phydev->speed == SPEED_10000)) - advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_ADV(dlks, 10000baseKR_Full); else - advertising |= ADVERTISED_1000baseKX_Full; + XGBE_SET_ADV(dlks, 1000baseKX_Full); break; case XGBE_PORT_MODE_10GBASE_R: - advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_ADV(dlks, 10000baseKR_Full); break; case XGBE_PORT_MODE_SFP: switch (phy_data->sfp_base) { @@ -1583,24 +1590,24 @@ static unsigned int xgbe_phy_an_advertising(struct xgbe_prv_data *pdata) case XGBE_SFP_BASE_1000_SX: case XGBE_SFP_BASE_1000_LX: case XGBE_SFP_BASE_1000_CX: - advertising |= ADVERTISED_1000baseKX_Full; + XGBE_SET_ADV(dlks, 1000baseKX_Full); break; default: - advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_ADV(dlks, 10000baseKR_Full); break; } break; default: - advertising |= ADVERTISED_10000baseKR_Full; + XGBE_SET_ADV(dlks, 10000baseKR_Full); break; } - - return advertising; } static int xgbe_phy_an_config(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; + u32 advertising; int ret; ret = xgbe_phy_find_phy_device(pdata); @@ -1610,9 +1617,12 @@ static int xgbe_phy_an_config(struct xgbe_prv_data *pdata) if (!phy_data->phydev) return 0; + ethtool_convert_link_mode_to_legacy_u32(&advertising, + lks->link_modes.advertising); + phy_data->phydev->autoneg = pdata->phy.autoneg; phy_data->phydev->advertising = phy_data->phydev->supported & - pdata->phy.advertising; + advertising; if (pdata->phy.autoneg != AUTONEG_ENABLE) { phy_data->phydev->speed = pdata->phy.speed; @@ -2073,11 +2083,10 @@ static void xgbe_phy_set_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) } static bool xgbe_phy_check_mode(struct xgbe_prv_data *pdata, - enum xgbe_mode mode, u32 advert) + enum xgbe_mode mode, bool advert) { if (pdata->phy.autoneg == AUTONEG_ENABLE) { - if (pdata->phy.advertising & advert) - return true; + return advert; } else { enum xgbe_mode cur_mode; @@ -2092,13 +2101,15 @@ static bool xgbe_phy_check_mode(struct xgbe_prv_data *pdata, static bool xgbe_phy_use_basex_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + switch (mode) { case XGBE_MODE_X: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_1000baseT_Full); + XGBE_ADV(lks, 1000baseX_Full)); case XGBE_MODE_KR: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_10000baseT_Full); + XGBE_ADV(lks, 10000baseKR_Full)); default: return false; } @@ -2107,19 +2118,21 @@ static bool xgbe_phy_use_basex_mode(struct xgbe_prv_data *pdata, static bool xgbe_phy_use_baset_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + switch (mode) { case XGBE_MODE_SGMII_100: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_100baseT_Full); + XGBE_ADV(lks, 100baseT_Full)); case XGBE_MODE_SGMII_1000: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_1000baseT_Full); + XGBE_ADV(lks, 1000baseT_Full)); case XGBE_MODE_KX_2500: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_2500baseX_Full); + XGBE_ADV(lks, 2500baseT_Full)); case XGBE_MODE_KR: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_10000baseT_Full); + XGBE_ADV(lks, 10000baseT_Full)); default: return false; } @@ -2128,6 +2141,7 @@ static bool xgbe_phy_use_baset_mode(struct xgbe_prv_data *pdata, static bool xgbe_phy_use_sfp_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data = pdata->phy_data; switch (mode) { @@ -2135,22 +2149,26 @@ static bool xgbe_phy_use_sfp_mode(struct xgbe_prv_data *pdata, if (phy_data->sfp_base == XGBE_SFP_BASE_1000_T) return false; return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_1000baseT_Full); + XGBE_ADV(lks, 1000baseX_Full)); case XGBE_MODE_SGMII_100: if (phy_data->sfp_base != XGBE_SFP_BASE_1000_T) return false; return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_100baseT_Full); + XGBE_ADV(lks, 100baseT_Full)); case XGBE_MODE_SGMII_1000: if (phy_data->sfp_base != XGBE_SFP_BASE_1000_T) return false; return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_1000baseT_Full); + XGBE_ADV(lks, 1000baseT_Full)); case XGBE_MODE_SFI: if (phy_data->sfp_mod_absent) return true; return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_10000baseT_Full); + XGBE_ADV(lks, 10000baseSR_Full) || + XGBE_ADV(lks, 10000baseLR_Full) || + XGBE_ADV(lks, 10000baseLRM_Full) || + XGBE_ADV(lks, 10000baseER_Full) || + XGBE_ADV(lks, 10000baseCR_Full)); default: return false; } @@ -2159,10 +2177,12 @@ static bool xgbe_phy_use_sfp_mode(struct xgbe_prv_data *pdata, static bool xgbe_phy_use_bp_2500_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + switch (mode) { case XGBE_MODE_KX_2500: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_2500baseX_Full); + XGBE_ADV(lks, 2500baseX_Full)); default: return false; } @@ -2171,13 +2191,15 @@ static bool xgbe_phy_use_bp_2500_mode(struct xgbe_prv_data *pdata, static bool xgbe_phy_use_bp_mode(struct xgbe_prv_data *pdata, enum xgbe_mode mode) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; + switch (mode) { case XGBE_MODE_KX_1000: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_1000baseKX_Full); + XGBE_ADV(lks, 1000baseKX_Full)); case XGBE_MODE_KR: return xgbe_phy_check_mode(pdata, mode, - ADVERTISED_10000baseKR_Full); + XGBE_ADV(lks, 10000baseKR_Full)); default: return false; } @@ -2744,6 +2766,7 @@ static void xgbe_phy_exit(struct xgbe_prv_data *pdata) static int xgbe_phy_init(struct xgbe_prv_data *pdata) { + struct ethtool_link_ksettings *lks = &pdata->phy.lks; struct xgbe_phy_data *phy_data; struct mii_bus *mii; unsigned int reg; @@ -2823,32 +2846,33 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) phy_data->cur_mode = XGBE_MODE_UNKNOWN; /* Initialize supported features */ - pdata->phy.supported = 0; + XGBE_ZERO_SUP(lks); switch (phy_data->port_mode) { /* Backplane support */ case XGBE_PORT_MODE_BACKPLANE: - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_Backplane; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, Backplane); if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) { - pdata->phy.supported |= SUPPORTED_1000baseKX_Full; + XGBE_SET_SUP(lks, 1000baseKX_Full); phy_data->start_mode = XGBE_MODE_KX_1000; } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) { - pdata->phy.supported |= SUPPORTED_10000baseKR_Full; + XGBE_SET_SUP(lks, 10000baseKR_Full); if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE) - pdata->phy.supported |= - SUPPORTED_10000baseR_FEC; + XGBE_SET_SUP(lks, 10000baseR_FEC); phy_data->start_mode = XGBE_MODE_KR; } phy_data->phydev_mode = XGBE_MDIO_MODE_NONE; break; case XGBE_PORT_MODE_BACKPLANE_2500: - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_Backplane; - pdata->phy.supported |= SUPPORTED_2500baseX_Full; + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, Backplane); + XGBE_SET_SUP(lks, 2500baseX_Full); phy_data->start_mode = XGBE_MODE_KX_2500; phy_data->phydev_mode = XGBE_MDIO_MODE_NONE; @@ -2856,15 +2880,16 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) /* MDIO 1GBase-T support */ case XGBE_PORT_MODE_1000BASE_T: - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_TP; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, TP); if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) { - pdata->phy.supported |= SUPPORTED_100baseT_Full; + XGBE_SET_SUP(lks, 100baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_100; } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) { - pdata->phy.supported |= SUPPORTED_1000baseT_Full; + XGBE_SET_SUP(lks, 1000baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_1000; } @@ -2873,10 +2898,11 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) /* MDIO Base-X support */ case XGBE_PORT_MODE_1000BASE_X: - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_FIBRE; - pdata->phy.supported |= SUPPORTED_1000baseT_Full; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, FIBRE); + XGBE_SET_SUP(lks, 1000baseX_Full); phy_data->start_mode = XGBE_MODE_X; phy_data->phydev_mode = XGBE_MDIO_MODE_CL22; @@ -2884,19 +2910,20 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) /* MDIO NBase-T support */ case XGBE_PORT_MODE_NBASE_T: - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_TP; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, TP); if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) { - pdata->phy.supported |= SUPPORTED_100baseT_Full; + XGBE_SET_SUP(lks, 100baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_100; } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) { - pdata->phy.supported |= SUPPORTED_1000baseT_Full; + XGBE_SET_SUP(lks, 1000baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_1000; } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_2500) { - pdata->phy.supported |= SUPPORTED_2500baseX_Full; + XGBE_SET_SUP(lks, 2500baseT_Full); phy_data->start_mode = XGBE_MODE_KX_2500; } @@ -2905,33 +2932,38 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) /* 10GBase-T support */ case XGBE_PORT_MODE_10GBASE_T: - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_TP; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, TP); if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) { - pdata->phy.supported |= SUPPORTED_100baseT_Full; + XGBE_SET_SUP(lks, 100baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_100; } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) { - pdata->phy.supported |= SUPPORTED_1000baseT_Full; + XGBE_SET_SUP(lks, 1000baseT_Full); phy_data->start_mode = XGBE_MODE_SGMII_1000; } if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) { - pdata->phy.supported |= SUPPORTED_10000baseT_Full; + XGBE_SET_SUP(lks, 10000baseT_Full); phy_data->start_mode = XGBE_MODE_KR; } - phy_data->phydev_mode = XGBE_MDIO_MODE_NONE; + phy_data->phydev_mode = XGBE_MDIO_MODE_CL45; break; /* 10GBase-R support */ case XGBE_PORT_MODE_10GBASE_R: - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_TP; - pdata->phy.supported |= SUPPORTED_10000baseT_Full; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, FIBRE); + XGBE_SET_SUP(lks, 10000baseSR_Full); + XGBE_SET_SUP(lks, 10000baseLR_Full); + XGBE_SET_SUP(lks, 10000baseLRM_Full); + XGBE_SET_SUP(lks, 10000baseER_Full); if (pdata->fec_ability & MDIO_PMA_10GBR_FECABLE_ABLE) - pdata->phy.supported |= SUPPORTED_10000baseR_FEC; + XGBE_SET_SUP(lks, 10000baseR_FEC); phy_data->start_mode = XGBE_MODE_SFI; phy_data->phydev_mode = XGBE_MDIO_MODE_NONE; @@ -2939,22 +2971,17 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) /* SFP support */ case XGBE_PORT_MODE_SFP: - pdata->phy.supported |= SUPPORTED_Autoneg; - pdata->phy.supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - pdata->phy.supported |= SUPPORTED_TP; - pdata->phy.supported |= SUPPORTED_FIBRE; - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) { - pdata->phy.supported |= SUPPORTED_100baseT_Full; + XGBE_SET_SUP(lks, Autoneg); + XGBE_SET_SUP(lks, Pause); + XGBE_SET_SUP(lks, Asym_Pause); + XGBE_SET_SUP(lks, TP); + XGBE_SET_SUP(lks, FIBRE); + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_100) phy_data->start_mode = XGBE_MODE_SGMII_100; - } - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) { - pdata->phy.supported |= SUPPORTED_1000baseT_Full; + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_1000) phy_data->start_mode = XGBE_MODE_SGMII_1000; - } - if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) { - pdata->phy.supported |= SUPPORTED_10000baseT_Full; + if (phy_data->port_speeds & XGBE_PHY_PORT_SPEED_10000) phy_data->start_mode = XGBE_MODE_SFI; - } phy_data->phydev_mode = XGBE_MDIO_MODE_CL22; @@ -2965,8 +2992,9 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) } if (netif_msg_probe(pdata)) - dev_dbg(pdata->dev, "phy supported=%#x\n", - pdata->phy.supported); + dev_dbg(pdata->dev, "phy supported=0x%*pb\n", + __ETHTOOL_LINK_MODE_MASK_NBITS, + lks->link_modes.supported); if ((phy_data->conn_type & XGBE_CONN_TYPE_MDIO) && (phy_data->phydev_mode != XGBE_MDIO_MODE_NONE)) { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 0938294f640a..ad102c8bac7b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -129,6 +129,10 @@ #include <net/dcbnl.h> #include <linux/completion.h> #include <linux/cpumask.h> +#include <linux/interrupt.h> +#include <linux/dcache.h> +#include <linux/ethtool.h> +#include <linux/list.h> #define XGBE_DRV_NAME "amd-xgbe" #define XGBE_DRV_VERSION "1.0.3" @@ -180,8 +184,6 @@ #define XGBE_IRQ_MODE_EDGE 0 #define XGBE_IRQ_MODE_LEVEL 1 -#define XGBE_DMA_INTERRUPT_MASK 0x31c7 - #define XGMAC_MIN_PACKET 60 #define XGMAC_STD_PACKET_MTU 1500 #define XGMAC_MAX_STD_PACKET 1518 @@ -296,6 +298,48 @@ /* MDIO port types */ #define XGMAC_MAX_C22_PORT 3 +/* Link mode bit operations */ +#define XGBE_ZERO_SUP(_ls) \ + ethtool_link_ksettings_zero_link_mode((_ls), supported) + +#define XGBE_SET_SUP(_ls, _mode) \ + ethtool_link_ksettings_add_link_mode((_ls), supported, _mode) + +#define XGBE_CLR_SUP(_ls, _mode) \ + ethtool_link_ksettings_del_link_mode((_ls), supported, _mode) + +#define XGBE_IS_SUP(_ls, _mode) \ + ethtool_link_ksettings_test_link_mode((_ls), supported, _mode) + +#define XGBE_ZERO_ADV(_ls) \ + ethtool_link_ksettings_zero_link_mode((_ls), advertising) + +#define XGBE_SET_ADV(_ls, _mode) \ + ethtool_link_ksettings_add_link_mode((_ls), advertising, _mode) + +#define XGBE_CLR_ADV(_ls, _mode) \ + ethtool_link_ksettings_del_link_mode((_ls), advertising, _mode) + +#define XGBE_ADV(_ls, _mode) \ + ethtool_link_ksettings_test_link_mode((_ls), advertising, _mode) + +#define XGBE_ZERO_LP_ADV(_ls) \ + ethtool_link_ksettings_zero_link_mode((_ls), lp_advertising) + +#define XGBE_SET_LP_ADV(_ls, _mode) \ + ethtool_link_ksettings_add_link_mode((_ls), lp_advertising, _mode) + +#define XGBE_CLR_LP_ADV(_ls, _mode) \ + ethtool_link_ksettings_del_link_mode((_ls), lp_advertising, _mode) + +#define XGBE_LP_ADV(_ls, _mode) \ + ethtool_link_ksettings_test_link_mode((_ls), lp_advertising, _mode) + +#define XGBE_LM_COPY(_dst, _dname, _src, _sname) \ + bitmap_copy((_dst)->link_modes._dname, \ + (_src)->link_modes._sname, \ + __ETHTOOL_LINK_MODE_MASK_NBITS) + struct xgbe_prv_data; struct xgbe_packet_data { @@ -460,6 +504,8 @@ struct xgbe_channel { /* Netdev related settings */ struct napi_struct napi; + /* Per channel interrupt enablement tracker */ + unsigned int curr_ier; unsigned int saved_ier; unsigned int tx_timer_active; @@ -561,9 +607,7 @@ enum xgbe_mdio_mode { }; struct xgbe_phy { - u32 supported; - u32 advertising; - u32 lp_advertising; + struct ethtool_link_ksettings lks; int address; @@ -666,6 +710,16 @@ struct xgbe_ext_stats { u64 tx_tso_packets; u64 rx_split_header_packets; u64 rx_buffer_unavailable; + + u64 txq_packets[XGBE_MAX_DMA_CHANNELS]; + u64 txq_bytes[XGBE_MAX_DMA_CHANNELS]; + u64 rxq_packets[XGBE_MAX_DMA_CHANNELS]; + u64 rxq_bytes[XGBE_MAX_DMA_CHANNELS]; + + u64 tx_vxlan_packets; + u64 rx_vxlan_packets; + u64 rx_csum_errors; + u64 rx_vxlan_csum_errors; }; struct xgbe_hw_if { @@ -769,6 +823,11 @@ struct xgbe_hw_if { /* For ECC */ void (*disable_ecc_ded)(struct xgbe_prv_data *); void (*disable_ecc_sec)(struct xgbe_prv_data *, enum xgbe_ecc_sec); + + /* For VXLAN */ + void (*enable_vxlan)(struct xgbe_prv_data *); + void (*disable_vxlan)(struct xgbe_prv_data *); + void (*set_vxlan_id)(struct xgbe_prv_data *); }; /* This structure represents implementation specific routines for an @@ -810,7 +869,8 @@ struct xgbe_phy_impl_if { int (*an_config)(struct xgbe_prv_data *); /* Set/override auto-negotiation advertisement settings */ - unsigned int (*an_advertising)(struct xgbe_prv_data *); + void (*an_advertising)(struct xgbe_prv_data *, + struct ethtool_link_ksettings *); /* Process results of auto-negotiation */ enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *); @@ -892,6 +952,7 @@ struct xgbe_hw_features { unsigned int addn_mac; /* Additional MAC Addresses */ unsigned int ts_src; /* Timestamp Source */ unsigned int sa_vlan_ins; /* Source Address or VLAN Insertion */ + unsigned int vxn; /* VXLAN/NVGRE */ /* HW Feature Register1 */ unsigned int rx_fifo_size; /* MTL Receive FIFO Size */ @@ -930,6 +991,12 @@ struct xgbe_version_data { unsigned int rx_desc_prefetch; }; +struct xgbe_vxlan_data { + struct list_head list; + sa_family_t sa_family; + __be16 port; +}; + struct xgbe_prv_data { struct net_device *netdev; struct pci_dev *pcidev; @@ -1071,6 +1138,15 @@ struct xgbe_prv_data { u32 rss_table[XGBE_RSS_MAX_TABLE_SIZE]; u32 rss_options; + /* VXLAN settings */ + unsigned int vxlan_port_set; + unsigned int vxlan_offloads_set; + unsigned int vxlan_force_disable; + unsigned int vxlan_port_count; + struct list_head vxlan_ports; + u16 vxlan_port; + netdev_features_t vxlan_features; + /* Netdev related settings */ unsigned char mac_addr[ETH_ALEN]; netdev_features_t netdev_features; @@ -1171,7 +1247,6 @@ struct xgbe_prv_data { struct tasklet_struct tasklet_i2c; struct tasklet_struct tasklet_an; -#ifdef CONFIG_DEBUG_FS struct dentry *xgbe_debugfs; unsigned int debugfs_xgmac_reg; @@ -1182,7 +1257,6 @@ struct xgbe_prv_data { unsigned int debugfs_xprop_reg; unsigned int debugfs_xi2c_reg; -#endif }; /* Function prototypes*/ @@ -1231,9 +1305,11 @@ void xgbe_init_tx_coalesce(struct xgbe_prv_data *); #ifdef CONFIG_DEBUG_FS void xgbe_debugfs_init(struct xgbe_prv_data *); void xgbe_debugfs_exit(struct xgbe_prv_data *); +void xgbe_debugfs_rename(struct xgbe_prv_data *pdata); #else static inline void xgbe_debugfs_init(struct xgbe_prv_data *pdata) {} static inline void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) {} +static inline void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) {} #endif /* CONFIG_DEBUG_FS */ /* NOTE: Uncomment for function trace log messages in KERNEL LOG */ diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index e45b587c2994..3188f553da35 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -468,7 +468,6 @@ static void xgene_enet_configure_clock(struct xgene_enet_pdata *pdata) static void xgene_gmac_set_speed(struct xgene_enet_pdata *pdata) { - struct device *dev = &pdata->pdev->dev; u32 icm0, icm2, mc2; u32 intf_ctl, rgmii, value; @@ -500,10 +499,8 @@ static void xgene_gmac_set_speed(struct xgene_enet_pdata *pdata) intf_ctl |= ENET_GHD_MODE; CFG_MACMODE_SET(&icm0, 2); CFG_WAITASYNCRD_SET(&icm2, 0); - if (dev->of_node) { - CFG_TXCLK_MUXSEL0_SET(&rgmii, pdata->tx_delay); - CFG_RXCLK_MUXSEL0_SET(&rgmii, pdata->rx_delay); - } + CFG_TXCLK_MUXSEL0_SET(&rgmii, pdata->tx_delay); + CFG_RXCLK_MUXSEL0_SET(&rgmii, pdata->rx_delay); rgmii |= CFG_SPEED_1250; xgene_enet_rd_csr(pdata, DEBUG_REG_ADDR, &value); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 6e253d913fe2..3b889efddf78 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1591,7 +1591,7 @@ static int xgene_get_tx_delay(struct xgene_enet_pdata *pdata) struct device *dev = &pdata->pdev->dev; int delay, ret; - ret = of_property_read_u32(dev->of_node, "tx-delay", &delay); + ret = device_property_read_u32(dev, "tx-delay", &delay); if (ret) { pdata->tx_delay = 4; return 0; @@ -1612,7 +1612,7 @@ static int xgene_get_rx_delay(struct xgene_enet_pdata *pdata) struct device *dev = &pdata->pdev->dev; int delay, ret; - ret = of_property_read_u32(dev->of_node, "rx-delay", &delay); + ret = device_property_read_u32(dev, "rx-delay", &delay); if (ret) { pdata->rx_delay = 2; return 0; @@ -1674,8 +1674,6 @@ static void xgene_enet_check_phy_handle(struct xgene_enet_pdata *pdata) ret = xgene_enet_phy_connect(pdata->ndev); if (!ret) pdata->mdio_driver = true; - - return; } static void xgene_enet_gpiod_get(struct xgene_enet_pdata *pdata) diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index 96dd5300e0e5..e58b157b7d7c 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -114,8 +114,8 @@ static int mace_probe(struct macio_dev *mdev, const struct of_device_id *match) int j, rev, rc = -EBUSY; if (macio_resource_count(mdev) != 3 || macio_irq_count(mdev) != 3) { - printk(KERN_ERR "can't use MACE %s: need 3 addrs and 3 irqs\n", - mace->full_name); + printk(KERN_ERR "can't use MACE %pOF: need 3 addrs and 3 irqs\n", + mace); return -ENODEV; } @@ -123,8 +123,8 @@ static int mace_probe(struct macio_dev *mdev, const struct of_device_id *match) if (addr == NULL) { addr = of_get_property(mace, "local-mac-address", NULL); if (addr == NULL) { - printk(KERN_ERR "Can't get mac-address for MACE %s\n", - mace->full_name); + printk(KERN_ERR "Can't get mac-address for MACE %pOF\n", + mace); return -ENODEV; } } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index ec5579fb8268..4eee1996a825 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -133,7 +133,10 @@ static inline unsigned int aq_ring_dx_in_range(unsigned int h, unsigned int i, } #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) -int aq_ring_rx_clean(struct aq_ring_s *self, int *work_done, int budget) +int aq_ring_rx_clean(struct aq_ring_s *self, + struct napi_struct *napi, + int *work_done, + int budget) { struct net_device *ndev = aq_nic_get_ndev(self->aq_nic); int err = 0; @@ -239,7 +242,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self, int *work_done, int budget) skb_record_rx_queue(skb, self->idx); - netif_receive_skb(skb); + napi_gro_receive(napi, skb); ++self->stats.rx.packets; self->stats.rx.bytes += skb->len; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index eecd6d1c4d73..782176c5f4f8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -148,7 +148,10 @@ int aq_ring_init(struct aq_ring_s *self); void aq_ring_rx_deinit(struct aq_ring_s *self); void aq_ring_free(struct aq_ring_s *self); void aq_ring_tx_clean(struct aq_ring_s *self); -int aq_ring_rx_clean(struct aq_ring_s *self, int *work_done, int budget); +int aq_ring_rx_clean(struct aq_ring_s *self, + struct napi_struct *napi, + int *work_done, + int budget); int aq_ring_rx_fill(struct aq_ring_s *self); #endif /* AQ_RING_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index fee446af748f..ebf588004c46 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -76,6 +76,7 @@ static int aq_vec_poll(struct napi_struct *napi, int budget) if (ring[AQ_VEC_RX_ID].sw_head != ring[AQ_VEC_RX_ID].hw_head) { err = aq_ring_rx_clean(&ring[AQ_VEC_RX_ID], + napi, &work_done, budget - work_done); if (err < 0) diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 68de2f2652f2..3241af1ce718 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -720,6 +720,18 @@ static int arc_emac_set_address(struct net_device *ndev, void *p) return 0; } +static int arc_emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + if (!netif_running(dev)) + return -EINVAL; + + if (!dev->phydev) + return -ENODEV; + + return phy_mii_ioctl(dev->phydev, rq, cmd); +} + + static const struct net_device_ops arc_emac_netdev_ops = { .ndo_open = arc_emac_open, .ndo_stop = arc_emac_stop, @@ -727,6 +739,7 @@ static const struct net_device_ops arc_emac_netdev_ops = { .ndo_set_mac_address = arc_emac_set_address, .ndo_get_stats = arc_emac_stats, .ndo_set_rx_mode = arc_emac_set_rx_mode, + .ndo_do_ioctl = arc_emac_ioctl, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = arc_emac_poll_controller, #endif diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 96413808c726..67134ece1107 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -61,10 +61,12 @@ config BCM63XX_ENET config BCMGENET tristate "Broadcom GENET internal MAC support" + depends on OF && HAS_IOMEM select MII select PHYLIB select FIXED_PHY select BCM7XXX_PHY + select MDIO_BCM_UNIMAC help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. @@ -193,6 +195,7 @@ config SYSTEMPORT config BNXT tristate "Broadcom NetXtreme-C/E support" depends on PCI + depends on MAY_USE_DEVLINK select FW_LOADER select LIBCRC32C ---help--- @@ -209,6 +212,15 @@ config BNXT_SRIOV Virtualization support in the NetXtreme-C/E products. This allows for virtual function acceleration in virtual environments. +config BNXT_FLOWER_OFFLOAD + bool "TC Flower offload support for NetXtreme-C/E" + depends on BNXT + default y + ---help--- + This configuration parameter enables TC Flower packet classifier + offload for eswitch. This option enables SR-IOV switchdev eswitch + offload. + config BNXT_DCB bool "Data Center Bridging (DCB) Support" default n diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 61a88b64bd39..4f3845a58126 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -2674,7 +2674,7 @@ static int bcm_enetsw_set_ringparam(struct net_device *dev, return 0; } -static struct ethtool_ops bcm_enetsw_ethtool_ops = { +static const struct ethtool_ops bcm_enetsw_ethtool_ops = { .get_strings = bcm_enetsw_get_strings, .get_sset_count = bcm_enetsw_get_sset_count, .get_ethtool_stats = bcm_enetsw_get_ethtool_stats, diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index c28fa5a8734c..a6572b51435a 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -32,13 +32,13 @@ #define BCM_SYSPORT_IO_MACRO(name, offset) \ static inline u32 name##_readl(struct bcm_sysport_priv *priv, u32 off) \ { \ - u32 reg = __raw_readl(priv->base + offset + off); \ + u32 reg = readl_relaxed(priv->base + offset + off); \ return reg; \ } \ static inline void name##_writel(struct bcm_sysport_priv *priv, \ u32 val, u32 off) \ { \ - __raw_writel(val, priv->base + offset + off); \ + writel_relaxed(val, priv->base + offset + off); \ } \ BCM_SYSPORT_IO_MACRO(intrl2_0, SYS_PORT_INTRL2_0_OFFSET); @@ -59,14 +59,14 @@ static inline u32 rdma_readl(struct bcm_sysport_priv *priv, u32 off) { if (priv->is_lite && off >= RDMA_STATUS) off += 4; - return __raw_readl(priv->base + SYS_PORT_RDMA_OFFSET + off); + return readl_relaxed(priv->base + SYS_PORT_RDMA_OFFSET + off); } static inline void rdma_writel(struct bcm_sysport_priv *priv, u32 val, u32 off) { if (priv->is_lite && off >= RDMA_STATUS) off += 4; - __raw_writel(val, priv->base + SYS_PORT_RDMA_OFFSET + off); + writel_relaxed(val, priv->base + SYS_PORT_RDMA_OFFSET + off); } static inline u32 tdma_control_bit(struct bcm_sysport_priv *priv, u32 bit) @@ -110,10 +110,10 @@ static inline void dma_desc_set_addr(struct bcm_sysport_priv *priv, dma_addr_t addr) { #ifdef CONFIG_PHYS_ADDR_T_64BIT - __raw_writel(upper_32_bits(addr) & DESC_ADDR_HI_MASK, + writel_relaxed(upper_32_bits(addr) & DESC_ADDR_HI_MASK, d + DESC_ADDR_HI_STATUS_LEN); #endif - __raw_writel(lower_32_bits(addr), d + DESC_ADDR_LO); + writel_relaxed(lower_32_bits(addr), d + DESC_ADDR_LO); } static inline void tdma_port_write_desc_addr(struct bcm_sysport_priv *priv, @@ -201,10 +201,10 @@ static int bcm_sysport_set_features(struct net_device *dev, */ static const struct bcm_sysport_stats bcm_sysport_gstrings_stats[] = { /* general stats */ - STAT_NETDEV(rx_packets), - STAT_NETDEV(tx_packets), - STAT_NETDEV(rx_bytes), - STAT_NETDEV(tx_bytes), + STAT_NETDEV64(rx_packets), + STAT_NETDEV64(tx_packets), + STAT_NETDEV64(rx_bytes), + STAT_NETDEV64(tx_bytes), STAT_NETDEV(rx_errors), STAT_NETDEV(tx_errors), STAT_NETDEV(rx_dropped), @@ -316,6 +316,7 @@ static inline bool bcm_sysport_lite_stat_valid(enum bcm_sysport_stat_type type) { switch (type) { case BCM_SYSPORT_STAT_NETDEV: + case BCM_SYSPORT_STAT_NETDEV64: case BCM_SYSPORT_STAT_RXCHK: case BCM_SYSPORT_STAT_RBUF: case BCM_SYSPORT_STAT_SOFT: @@ -398,6 +399,7 @@ static void bcm_sysport_update_mib_counters(struct bcm_sysport_priv *priv) s = &bcm_sysport_gstrings_stats[i]; switch (s->type) { case BCM_SYSPORT_STAT_NETDEV: + case BCM_SYSPORT_STAT_NETDEV64: case BCM_SYSPORT_STAT_SOFT: continue; case BCM_SYSPORT_STAT_MIB_RX: @@ -434,7 +436,10 @@ static void bcm_sysport_get_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct bcm_sysport_priv *priv = netdev_priv(dev); + struct bcm_sysport_stats64 *stats64 = &priv->stats64; + struct u64_stats_sync *syncp = &priv->syncp; struct bcm_sysport_tx_ring *ring; + unsigned int start; int i, j; if (netif_running(dev)) @@ -447,14 +452,22 @@ static void bcm_sysport_get_stats(struct net_device *dev, s = &bcm_sysport_gstrings_stats[i]; if (s->type == BCM_SYSPORT_STAT_NETDEV) p = (char *)&dev->stats; + else if (s->type == BCM_SYSPORT_STAT_NETDEV64) + p = (char *)stats64; else p = (char *)priv; if (priv->is_lite && !bcm_sysport_lite_stat_valid(s->type)) continue; - p += s->stat_offset; - data[j] = *(unsigned long *)p; + + if (s->stat_sizeof == sizeof(u64)) + do { + start = u64_stats_fetch_begin_irq(syncp); + data[i] = *(u64 *)p; + } while (u64_stats_fetch_retry_irq(syncp, start)); + else + data[i] = *(u32 *)p; j++; } @@ -666,6 +679,7 @@ static int bcm_sysport_alloc_rx_bufs(struct bcm_sysport_priv *priv) static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, unsigned int budget) { + struct bcm_sysport_stats64 *stats64 = &priv->stats64; struct net_device *ndev = priv->netdev; unsigned int processed = 0, to_process; struct bcm_sysport_cb *cb; @@ -769,6 +783,10 @@ static unsigned int bcm_sysport_desc_rx(struct bcm_sysport_priv *priv, skb->protocol = eth_type_trans(skb, ndev); ndev->stats.rx_packets++; ndev->stats.rx_bytes += len; + u64_stats_update_begin(&priv->syncp); + stats64->rx_packets++; + stats64->rx_bytes += len; + u64_stats_update_end(&priv->syncp); napi_gro_receive(&priv->napi, skb); next: @@ -791,17 +809,15 @@ static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring, struct device *kdev = &priv->pdev->dev; if (cb->skb) { - ring->bytes += cb->skb->len; *bytes_compl += cb->skb->len; dma_unmap_single(kdev, dma_unmap_addr(cb, dma_addr), dma_unmap_len(cb, dma_len), DMA_TO_DEVICE); - ring->packets++; (*pkts_compl)++; bcm_sysport_free_cb(cb); /* SKB fragment */ } else if (dma_unmap_addr(cb, dma_addr)) { - ring->bytes += dma_unmap_len(cb, dma_len); + *bytes_compl += dma_unmap_len(cb, dma_len); dma_unmap_page(kdev, dma_unmap_addr(cb, dma_addr), dma_unmap_len(cb, dma_len), DMA_TO_DEVICE); dma_unmap_addr_set(cb, dma_addr, 0); @@ -812,9 +828,9 @@ static void bcm_sysport_tx_reclaim_one(struct bcm_sysport_tx_ring *ring, static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, struct bcm_sysport_tx_ring *ring) { - struct net_device *ndev = priv->netdev; unsigned int c_index, last_c_index, last_tx_cn, num_tx_cbs; unsigned int pkts_compl = 0, bytes_compl = 0; + struct net_device *ndev = priv->netdev; struct bcm_sysport_cb *cb; u32 hw_ind; @@ -853,6 +869,11 @@ static unsigned int __bcm_sysport_tx_reclaim(struct bcm_sysport_priv *priv, last_c_index &= (num_tx_cbs - 1); } + u64_stats_update_begin(&priv->syncp); + ring->packets += pkts_compl; + ring->bytes += bytes_compl; + u64_stats_update_end(&priv->syncp); + ring->c_index = c_index; netif_dbg(priv, tx_done, ndev, @@ -1371,6 +1392,19 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, tdma_writel(priv, RING_IGNORE_STATUS, TDMA_DESC_RING_MAPPING(index)); tdma_writel(priv, 0, TDMA_DESC_RING_PCP_DEI_VID(index)); + /* Do not use tdma_control_bit() here because TSB_SWAP1 collides + * with the original definition of ACB_ALGO + */ + reg = tdma_readl(priv, TDMA_CONTROL); + if (priv->is_lite) + reg &= ~BIT(TSB_SWAP1); + /* Set a correct TSB format based on host endian */ + if (!IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + reg |= tdma_control_bit(priv, TSB_SWAP0); + else + reg &= ~tdma_control_bit(priv, TSB_SWAP0); + tdma_writel(priv, reg, TDMA_CONTROL); + /* Program the number of descriptors as MAX_THRESHOLD and half of * its size for the hysteresis trigger */ @@ -1677,22 +1711,41 @@ static int bcm_sysport_change_mac(struct net_device *dev, void *p) return 0; } -static struct net_device_stats *bcm_sysport_get_nstats(struct net_device *dev) +static void bcm_sysport_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) { struct bcm_sysport_priv *priv = netdev_priv(dev); - unsigned long tx_bytes = 0, tx_packets = 0; + struct bcm_sysport_stats64 *stats64 = &priv->stats64; struct bcm_sysport_tx_ring *ring; + u64 tx_packets = 0, tx_bytes = 0; + unsigned int start; unsigned int q; + netdev_stats_to_stats64(stats, &dev->stats); + for (q = 0; q < dev->num_tx_queues; q++) { ring = &priv->tx_rings[q]; - tx_bytes += ring->bytes; - tx_packets += ring->packets; + do { + start = u64_stats_fetch_begin_irq(&priv->syncp); + tx_bytes = ring->bytes; + tx_packets = ring->packets; + } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); + + stats->tx_bytes += tx_bytes; + stats->tx_packets += tx_packets; } - dev->stats.tx_bytes = tx_bytes; - dev->stats.tx_packets = tx_packets; - return &dev->stats; + /* lockless update tx_bytes and tx_packets */ + u64_stats_update_begin(&priv->syncp); + stats64->tx_bytes = stats->tx_bytes; + stats64->tx_packets = stats->tx_packets; + u64_stats_update_end(&priv->syncp); + + do { + start = u64_stats_fetch_begin_irq(&priv->syncp); + stats->rx_packets = stats64->rx_packets; + stats->rx_bytes = stats64->rx_bytes; + } while (u64_stats_fetch_retry_irq(&priv->syncp, start)); } static void bcm_sysport_netif_start(struct net_device *dev) @@ -1724,10 +1777,14 @@ static void rbuf_init(struct bcm_sysport_priv *priv) reg = rbuf_readl(priv, RBUF_CONTROL); reg |= RBUF_4B_ALGN | RBUF_RSB_EN; /* Set a correct RSB format on SYSTEMPORT Lite */ - if (priv->is_lite) { + if (priv->is_lite) reg &= ~RBUF_RSB_SWAP1; + + /* Set a correct RSB format based on host endian */ + if (!IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) reg |= RBUF_RSB_SWAP0; - } + else + reg &= ~RBUF_RSB_SWAP0; rbuf_writel(priv, reg, RBUF_CONTROL); } @@ -1956,7 +2013,7 @@ static const struct net_device_ops bcm_sysport_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = bcm_sysport_poll_controller, #endif - .ndo_get_stats = bcm_sysport_get_nstats, + .ndo_get_stats64 = bcm_sysport_get_stats64, }; #define REV_FMT "v%2x.%02x" @@ -2104,6 +2161,8 @@ static int bcm_sysport_probe(struct platform_device *pdev) /* libphy will adjust the link state accordingly */ netif_carrier_off(dev); + u64_stats_init(&priv->syncp); + ret = register_netdev(dev); if (ret) { dev_err(&pdev->dev, "failed to register net_device\n"); diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 77a51c167a69..82e401df199e 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -449,7 +449,8 @@ struct bcm_rsb { /* Uses 2 bits on SYSTEMPORT Lite and shifts everything by 1 bit, we * keep the SYSTEMPORT layout here and adjust with tdma_control_bit() */ -#define TSB_SWAP 2 +#define TSB_SWAP0 2 +#define TSB_SWAP1 3 #define ACB_ALGO 3 #define BUF_DATA_OFFSET_SHIFT 4 #define BUF_DATA_OFFSET_MASK 0x3ff @@ -603,6 +604,7 @@ struct bcm_sysport_mib { /* HW maintains a large list of counters */ enum bcm_sysport_stat_type { BCM_SYSPORT_STAT_NETDEV = -1, + BCM_SYSPORT_STAT_NETDEV64, BCM_SYSPORT_STAT_MIB_RX, BCM_SYSPORT_STAT_MIB_TX, BCM_SYSPORT_STAT_RUNT, @@ -619,6 +621,13 @@ enum bcm_sysport_stat_type { .type = BCM_SYSPORT_STAT_NETDEV, \ } +#define STAT_NETDEV64(m) { \ + .stat_string = __stringify(m), \ + .stat_sizeof = sizeof(((struct bcm_sysport_stats64 *)0)->m), \ + .stat_offset = offsetof(struct bcm_sysport_stats64, m), \ + .type = BCM_SYSPORT_STAT_NETDEV64, \ +} + #define STAT_MIB(str, m, _type) { \ .stat_string = str, \ .stat_sizeof = sizeof(((struct bcm_sysport_priv *)0)->m), \ @@ -659,6 +668,14 @@ struct bcm_sysport_stats { u16 reg_offset; }; +struct bcm_sysport_stats64 { + /* 64bit stats on 32bit/64bit Machine */ + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; +}; + /* Software house keeping helper structure */ struct bcm_sysport_cb { struct sk_buff *skb; /* SKB for RX packets */ @@ -743,5 +760,10 @@ struct bcm_sysport_priv { /* Ethtool */ u32 msg_enable; + + struct bcm_sysport_stats64 stats64; + + /* For atomic update generic 64bit value on 32bit Machine */ + struct u64_stats_sync syncp; }; #endif /* __BCM_SYSPORT_H */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 67fe3d826566..1216c1f1e052 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -4284,15 +4284,17 @@ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc) return 0; } -int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc) +int __bnx2x_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; + struct tc_mqprio_qopt *mqprio = type_data; + + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - return bnx2x_setup_tc(dev, tc->mqprio->num_tc); + return bnx2x_setup_tc(dev, mqprio->num_tc); } /* called with rtnl_lock */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index c26688d2f326..a5265e1344f1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -486,8 +486,8 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev); /* setup_tc callback */ int bnx2x_setup_tc(struct net_device *dev, u8 num_tc); -int __bnx2x_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc); +int __bnx2x_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data); int bnx2x_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi); diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile index a7ca45b251cb..4f0cb8e1ffc0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/Makefile +++ b/drivers/net/ethernet/broadcom/bnxt/Makefile @@ -1,3 +1,3 @@ obj-$(CONFIG_BNXT) += bnxt_en.o -bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o +bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_tc.o diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f20b3d2a4c23..aacec8bc19d5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -33,6 +33,7 @@ #include <linux/mii.h> #include <linux/if.h> #include <linux/if_vlan.h> +#include <linux/if_bridge.h> #include <linux/rtc.h> #include <linux/bpf.h> #include <net/ip.h> @@ -48,6 +49,8 @@ #include <linux/aer.h> #include <linux/bitmap.h> #include <linux/cpu_rmap.h> +#include <linux/cpumask.h> +#include <net/pkt_cls.h> #include "bnxt_hsi.h" #include "bnxt.h" @@ -56,6 +59,8 @@ #include "bnxt_ethtool.h" #include "bnxt_dcb.h" #include "bnxt_xdp.h" +#include "bnxt_vfr.h" +#include "bnxt_tc.h" #define BNXT_TX_TIMEOUT (5 * HZ) @@ -101,6 +106,8 @@ enum board_idx { BCM57416_NPAR, BCM57452, BCM57454, + BCM58802, + BCM58808, NETXTREME_E_VF, NETXTREME_C_VF, }; @@ -109,39 +116,42 @@ enum board_idx { static const struct { char *name; } board_info[] = { - { "Broadcom BCM57301 NetXtreme-C 10Gb Ethernet" }, - { "Broadcom BCM57302 NetXtreme-C 10Gb/25Gb Ethernet" }, - { "Broadcom BCM57304 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" }, - { "Broadcom BCM57417 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM58700 Nitro 1Gb/2.5Gb/10Gb Ethernet" }, - { "Broadcom BCM57311 NetXtreme-C 10Gb Ethernet" }, - { "Broadcom BCM57312 NetXtreme-C 10Gb/25Gb Ethernet" }, - { "Broadcom BCM57402 NetXtreme-E 10Gb Ethernet" }, - { "Broadcom BCM57404 NetXtreme-E 10Gb/25Gb Ethernet" }, - { "Broadcom BCM57406 NetXtreme-E 10GBase-T Ethernet" }, - { "Broadcom BCM57402 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM57407 NetXtreme-E 10GBase-T Ethernet" }, - { "Broadcom BCM57412 NetXtreme-E 10Gb Ethernet" }, - { "Broadcom BCM57414 NetXtreme-E 10Gb/25Gb Ethernet" }, - { "Broadcom BCM57416 NetXtreme-E 10GBase-T Ethernet" }, - { "Broadcom BCM57417 NetXtreme-E 10GBase-T Ethernet" }, - { "Broadcom BCM57412 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM57314 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" }, - { "Broadcom BCM57417 NetXtreme-E 10Gb/25Gb Ethernet" }, - { "Broadcom BCM57416 NetXtreme-E 10Gb Ethernet" }, - { "Broadcom BCM57404 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM57406 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM57407 NetXtreme-E 25Gb Ethernet" }, - { "Broadcom BCM57407 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM57414 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM57416 NetXtreme-E Ethernet Partition" }, - { "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" }, - { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, - { "Broadcom NetXtreme-E Ethernet Virtual Function" }, - { "Broadcom NetXtreme-C Ethernet Virtual Function" }, + [BCM57301] = { "Broadcom BCM57301 NetXtreme-C 10Gb Ethernet" }, + [BCM57302] = { "Broadcom BCM57302 NetXtreme-C 10Gb/25Gb Ethernet" }, + [BCM57304] = { "Broadcom BCM57304 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" }, + [BCM57417_NPAR] = { "Broadcom BCM57417 NetXtreme-E Ethernet Partition" }, + [BCM58700] = { "Broadcom BCM58700 Nitro 1Gb/2.5Gb/10Gb Ethernet" }, + [BCM57311] = { "Broadcom BCM57311 NetXtreme-C 10Gb Ethernet" }, + [BCM57312] = { "Broadcom BCM57312 NetXtreme-C 10Gb/25Gb Ethernet" }, + [BCM57402] = { "Broadcom BCM57402 NetXtreme-E 10Gb Ethernet" }, + [BCM57404] = { "Broadcom BCM57404 NetXtreme-E 10Gb/25Gb Ethernet" }, + [BCM57406] = { "Broadcom BCM57406 NetXtreme-E 10GBase-T Ethernet" }, + [BCM57402_NPAR] = { "Broadcom BCM57402 NetXtreme-E Ethernet Partition" }, + [BCM57407] = { "Broadcom BCM57407 NetXtreme-E 10GBase-T Ethernet" }, + [BCM57412] = { "Broadcom BCM57412 NetXtreme-E 10Gb Ethernet" }, + [BCM57414] = { "Broadcom BCM57414 NetXtreme-E 10Gb/25Gb Ethernet" }, + [BCM57416] = { "Broadcom BCM57416 NetXtreme-E 10GBase-T Ethernet" }, + [BCM57417] = { "Broadcom BCM57417 NetXtreme-E 10GBase-T Ethernet" }, + [BCM57412_NPAR] = { "Broadcom BCM57412 NetXtreme-E Ethernet Partition" }, + [BCM57314] = { "Broadcom BCM57314 NetXtreme-C 10Gb/25Gb/40Gb/50Gb Ethernet" }, + [BCM57417_SFP] = { "Broadcom BCM57417 NetXtreme-E 10Gb/25Gb Ethernet" }, + [BCM57416_SFP] = { "Broadcom BCM57416 NetXtreme-E 10Gb Ethernet" }, + [BCM57404_NPAR] = { "Broadcom BCM57404 NetXtreme-E Ethernet Partition" }, + [BCM57406_NPAR] = { "Broadcom BCM57406 NetXtreme-E Ethernet Partition" }, + [BCM57407_SFP] = { "Broadcom BCM57407 NetXtreme-E 25Gb Ethernet" }, + [BCM57407_NPAR] = { "Broadcom BCM57407 NetXtreme-E Ethernet Partition" }, + [BCM57414_NPAR] = { "Broadcom BCM57414 NetXtreme-E Ethernet Partition" }, + [BCM57416_NPAR] = { "Broadcom BCM57416 NetXtreme-E Ethernet Partition" }, + [BCM57452] = { "Broadcom BCM57452 NetXtreme-E 10Gb/25Gb/40Gb/50Gb Ethernet" }, + [BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, + [BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" }, + [BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, + [NETXTREME_E_VF] = { "Broadcom NetXtreme-E Ethernet Virtual Function" }, + [NETXTREME_C_VF] = { "Broadcom NetXtreme-C Ethernet Virtual Function" }, }; static const struct pci_device_id bnxt_pci_tbl[] = { + { PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 }, { PCI_VDEVICE(BROADCOM, 0x16c0), .driver_data = BCM57417_NPAR }, { PCI_VDEVICE(BROADCOM, 0x16c8), .driver_data = BCM57301 }, { PCI_VDEVICE(BROADCOM, 0x16c9), .driver_data = BCM57302 }, @@ -172,8 +182,9 @@ static const struct pci_device_id bnxt_pci_tbl[] = { { PCI_VDEVICE(BROADCOM, 0x16ed), .driver_data = BCM57414_NPAR }, { PCI_VDEVICE(BROADCOM, 0x16ee), .driver_data = BCM57416_NPAR }, { PCI_VDEVICE(BROADCOM, 0x16ef), .driver_data = BCM57416_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 }, { PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 }, - { PCI_VDEVICE(BROADCOM, 0x1614), .driver_data = BCM57454 }, + { PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 }, #ifdef CONFIG_BNXT_SRIOV { PCI_VDEVICE(BROADCOM, 0x1606), .driver_data = NETXTREME_E_VF }, { PCI_VDEVICE(BROADCOM, 0x1609), .driver_data = NETXTREME_E_VF }, @@ -243,6 +254,16 @@ const u16 bnxt_lhint_arr[] = { TX_BD_FLAGS_LHINT_2048_AND_LARGER, }; +static u16 bnxt_xmit_get_cfa_action(struct sk_buff *skb) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + + if (!md_dst || md_dst->type != METADATA_HW_PORT_MUX) + return 0; + + return md_dst->u.port_info.port_id; +} + static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); @@ -287,7 +308,7 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_buf->nr_frags = last_frag; vlan_tag_flags = 0; - cfa_action = 0; + cfa_action = bnxt_xmit_get_cfa_action(skb); if (skb_vlan_tag_present(skb)) { vlan_tag_flags = TX_BD_CFA_META_KEY_VLAN | skb_vlan_tag_get(skb); @@ -322,7 +343,8 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_push1->tx_bd_hsize_lflags = 0; tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); - tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action); + tx_push1->tx_bd_cfa_action = + cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT); end = pdata + length; end = PTR_ALIGN(end, 8) - 1; @@ -427,7 +449,8 @@ normal_tx: txbd->tx_bd_len_flags_type = cpu_to_le32(flags); txbd1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); - txbd1->tx_bd_cfa_action = cpu_to_le32(cfa_action); + txbd1->tx_bd_cfa_action = + cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT); for (i = 0; i < last_frag; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -1032,7 +1055,10 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, bnxt_sched_reset(bp, rxr); return; } - + /* Store cfa_code in tpa_info to use in tpa_end + * completion processing. + */ + tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1); prod_rx_buf->data = tpa_info->data; prod_rx_buf->data_ptr = tpa_info->data_ptr; @@ -1267,6 +1293,17 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp, return skb; } +/* Given the cfa_code of a received packet determine which + * netdev (vf-rep or PF) the packet is destined to. + */ +static struct net_device *bnxt_get_pkt_dev(struct bnxt *bp, u16 cfa_code) +{ + struct net_device *dev = bnxt_get_vf_rep(bp, cfa_code); + + /* if vf-rep dev is NULL, the must belongs to the PF */ + return dev ? dev : bp->dev; +} + static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, @@ -1360,7 +1397,9 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, return NULL; } } - skb->protocol = eth_type_trans(skb, bp->dev); + + skb->protocol = + eth_type_trans(skb, bnxt_get_pkt_dev(bp, tpa_info->cfa_code)); if (tpa_info->hash_type != PKT_HASH_TYPE_NONE) skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type); @@ -1387,6 +1426,18 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, return skb; } +static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi, + struct sk_buff *skb) +{ + if (skb->dev != bp->dev) { + /* this packet belongs to a vf-rep */ + bnxt_vf_rep_rx(bp, skb); + return; + } + skb_record_rx_queue(skb, bnapi->index); + napi_gro_receive(&bnapi->napi, skb); +} + /* returns the following: * 1 - 1 packet successfully received * 0 - successful TPA_START, packet not completed yet @@ -1403,7 +1454,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, struct rx_cmp *rxcmp; struct rx_cmp_ext *rxcmp1; u32 tmp_raw_cons = *raw_cons; - u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons); + u16 cfa_code, cons, prod, cp_cons = RING_CMP(tmp_raw_cons); struct bnxt_sw_rx_bd *rx_buf; unsigned int len; u8 *data_ptr, agg_bufs, cmp_type; @@ -1445,8 +1496,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, rc = -ENOMEM; if (likely(skb)) { - skb_record_rx_queue(skb, bnapi->index); - napi_gro_receive(&bnapi->napi, skb); + bnxt_deliver_skb(bp, bnapi, skb); rc = 1; } *event |= BNXT_RX_EVENT; @@ -1535,7 +1585,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type); } - skb->protocol = eth_type_trans(skb, dev); + cfa_code = RX_CMP_CFA_CODE(rxcmp1); + skb->protocol = eth_type_trans(skb, bnxt_get_pkt_dev(bp, cfa_code)); if ((rxcmp1->rx_cmp_flags2 & cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN)) && @@ -1560,8 +1611,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_napi *bnapi, u32 *raw_cons, } } - skb_record_rx_queue(skb, bnapi->index); - napi_gro_receive(&bnapi->napi, skb); + bnxt_deliver_skb(bp, bnapi, skb); rc = 1; next_rx: @@ -1802,6 +1852,13 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget) &event); if (likely(rc >= 0)) rx_pkts += rc; + /* Increment rx_pkts when rc is -ENOMEM to count towards + * the NAPI budget. Otherwise, we may potentially loop + * here forever if we consistently cannot allocate + * buffers. + */ + else if (rc == -ENOMEM) + rx_pkts++; else if (rc == -EBUSY) /* partial completion */ break; } else if (unlikely((TX_CMP_TYPE(txcmp) == @@ -4420,9 +4477,33 @@ static int bnxt_hwrm_reserve_tx_rings(struct bnxt *bp, int *tx_rings) mutex_lock(&bp->hwrm_cmd_lock); rc = __bnxt_hwrm_get_tx_rings(bp, 0xffff, tx_rings); mutex_unlock(&bp->hwrm_cmd_lock); + if (!rc) + bp->tx_reserved_rings = *tx_rings; return rc; } +static int bnxt_hwrm_check_tx_rings(struct bnxt *bp, int tx_rings) +{ + struct hwrm_func_cfg_input req = {0}; + int rc; + + if (bp->hwrm_spec_code < 0x10801) + return 0; + + if (BNXT_VF(bp)) + return 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); + req.fid = cpu_to_le16(0xffff); + req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST); + req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS); + req.num_tx_rings = cpu_to_le16(tx_rings); + rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + return -ENOMEM; + return 0; +} + static void bnxt_hwrm_set_coal_params(struct bnxt *bp, u32 max_bufs, u32 buf_tmrs, u16 flags, struct hwrm_ring_cmpl_ring_cfg_aggint_params_input *req) @@ -4577,6 +4658,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) { struct hwrm_func_qcfg_input req = {0}; struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr; + u16 flags; int rc; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1); @@ -4593,15 +4675,15 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK; } #endif - if (BNXT_PF(bp)) { - u16 flags = le16_to_cpu(resp->flags); - - if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED | - FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) - bp->flags |= BNXT_FLAG_FW_LLDP_AGENT; - if (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST) - bp->flags |= BNXT_FLAG_MULTI_HOST; + flags = le16_to_cpu(resp->flags); + if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED | + FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) { + bp->flags |= BNXT_FLAG_FW_LLDP_AGENT; + if (flags & FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED) + bp->flags |= BNXT_FLAG_FW_DCBX_AGENT; } + if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)) + bp->flags |= BNXT_FLAG_MULTI_HOST; switch (resp->port_partition_type) { case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0: @@ -4610,6 +4692,13 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) bp->port_partition_type = resp->port_partition_type; break; } + if (bp->hwrm_spec_code < 0x10707 || + resp->evb_mode == FUNC_QCFG_RESP_EVB_MODE_VEB) + bp->br_mode = BRIDGE_MODE_VEB; + else if (resp->evb_mode == FUNC_QCFG_RESP_EVB_MODE_VEPA) + bp->br_mode = BRIDGE_MODE_VEPA; + else + bp->br_mode = BRIDGE_MODE_UNDEF; func_qcfg_exit: mutex_unlock(&bp->hwrm_cmd_lock); @@ -4900,6 +4989,26 @@ static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path, } } +static int bnxt_hwrm_set_br_mode(struct bnxt *bp, u16 br_mode) +{ + struct hwrm_func_cfg_input req = {0}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); + req.fid = cpu_to_le16(0xffff); + req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_EVB_MODE); + if (br_mode == BRIDGE_MODE_VEB) + req.evb_mode = FUNC_CFG_REQ_EVB_MODE_VEB; + else if (br_mode == BRIDGE_MODE_VEPA) + req.evb_mode = FUNC_CFG_REQ_EVB_MODE_VEPA; + else + return -EINVAL; + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + rc = -EIO; + return rc; +} + static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id) { struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; @@ -5035,6 +5144,15 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) rc); goto err_out; } + if (bp->tx_reserved_rings != bp->tx_nr_rings) { + int tx = bp->tx_nr_rings; + + if (bnxt_hwrm_reserve_tx_rings(bp, &tx) || + tx < bp->tx_nr_rings) { + rc = -ENOMEM; + goto err_out; + } + } } rc = bnxt_hwrm_ring_alloc(bp); @@ -5441,8 +5559,15 @@ static void bnxt_free_irq(struct bnxt *bp) for (i = 0; i < bp->cp_nr_rings; i++) { irq = &bp->irq_tbl[i]; - if (irq->requested) + if (irq->requested) { + if (irq->have_cpumask) { + irq_set_affinity_hint(irq->vector, NULL); + free_cpumask_var(irq->cpu_mask); + irq->have_cpumask = 0; + } free_irq(irq->vector, bp->bnapi[i]); + } + irq->requested = 0; } } @@ -5475,6 +5600,21 @@ static int bnxt_request_irq(struct bnxt *bp) break; irq->requested = 1; + + if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) { + int numa_node = dev_to_node(&bp->pdev->dev); + + irq->have_cpumask = 1; + cpumask_set_cpu(cpumask_local_spread(i, numa_node), + irq->cpu_mask); + rc = irq_set_affinity_hint(irq->vector, irq->cpu_mask); + if (rc) { + netdev_warn(bp->dev, + "Set affinity failed, IRQ = %d\n", + irq->vector); + break; + } + } } return rc; } @@ -5548,12 +5688,10 @@ void bnxt_tx_disable(struct bnxt *bp) { int i; struct bnxt_tx_ring_info *txr; - struct netdev_queue *txq; if (bp->tx_ring) { for (i = 0; i < bp->tx_nr_rings; i++) { txr = &bp->tx_ring[i]; - txq = netdev_get_tx_queue(bp->dev, i); txr->dev_state = BNXT_DEV_STATE_CLOSING; } } @@ -5566,11 +5704,9 @@ void bnxt_tx_enable(struct bnxt *bp) { int i; struct bnxt_tx_ring_info *txr; - struct netdev_queue *txq; for (i = 0; i < bp->tx_nr_rings; i++) { txr = &bp->tx_ring[i]; - txq = netdev_get_tx_queue(bp->dev, i); txr->dev_state = 0; } netif_tx_wake_all_queues(bp->dev); @@ -5635,7 +5771,7 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) if (rc) goto hwrm_phy_qcaps_exit; - if (resp->eee_supported & PORT_PHY_QCAPS_RESP_EEE_SUPPORTED) { + if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED) { struct ethtool_eee *eee = &bp->eee; u16 fw_speeds = le16_to_cpu(resp->supported_speeds_eee_mode); @@ -5650,6 +5786,8 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) link_info->support_auto_speeds = le16_to_cpu(resp->supported_speeds_auto_mode); + bp->port_count = resp->port_cnt; + hwrm_phy_qcaps_exit: mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -5675,13 +5813,15 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state) memcpy(&link_info->phy_qcfg_resp, resp, sizeof(*resp)); link_info->phy_link_status = resp->link; - link_info->duplex = resp->duplex; + link_info->duplex = resp->duplex_cfg; + if (bp->hwrm_spec_code >= 0x10800) + link_info->duplex = resp->duplex_state; link_info->pause = resp->pause; link_info->auto_mode = resp->auto_mode; link_info->auto_pause_setting = resp->auto_pause; link_info->lp_pause = resp->link_partner_adv_pause; link_info->force_pause_setting = resp->force_pause; - link_info->duplex_setting = resp->duplex; + link_info->duplex_setting = resp->duplex_cfg; if (link_info->phy_link_status == BNXT_LINK_LINK) link_info->link_speed = le16_to_cpu(resp->link_speed); else @@ -6203,6 +6343,9 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* Poll link status and check for SFP+ module status */ bnxt_get_port_module_status(bp); + /* VF-reps may need to be re-opened after the PF is re-opened */ + if (BNXT_PF(bp)) + bnxt_vf_reps_open(bp); return 0; open_err: @@ -6291,6 +6434,10 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) if (rc) netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n"); } + + /* Close the VF-reps before closing PF */ + if (BNXT_PF(bp)) + bnxt_vf_reps_close(bp); #endif /* Change device state to avoid TX queue wake up's */ bnxt_tx_disable(bp); @@ -6802,7 +6949,8 @@ static void bnxt_timer(unsigned long data) if (atomic_read(&bp->intr_sem) != 0) goto bnxt_restart_timer; - if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS)) { + if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS) && + bp->stats_coal_ticks) { set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event); schedule_work(&bp->sp_task); } @@ -6912,8 +7060,8 @@ static void bnxt_sp_task(struct work_struct *work) } /* Under rtnl_lock */ -int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, - int tx_xdp) +int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, + int tx_xdp) { int max_rx, max_tx, tx_sets = 1; int tx_rings_needed; @@ -6933,10 +7081,7 @@ int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, if (max_tx < tx_rings_needed) return -ENOMEM; - if (bnxt_hwrm_reserve_tx_rings(bp, &tx_rings_needed) || - tx_rings_needed < (tx * tx_sets + tx_xdp)) - return -ENOMEM; - return 0; + return bnxt_hwrm_check_tx_rings(bp, tx_rings_needed); } static void bnxt_unmap_bars(struct bnxt *bp, struct pci_dev *pdev) @@ -7125,8 +7270,8 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc) if (bp->flags & BNXT_FLAG_SHARED_RINGS) sh = true; - rc = bnxt_reserve_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings, - sh, tc, bp->tx_nr_rings_xdp); + rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings, + sh, tc, bp->tx_nr_rings_xdp); if (rc) return rc; @@ -7152,15 +7297,33 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc) return 0; } -static int bnxt_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *ntc) +static int bnxt_setup_flower(struct net_device *dev, + struct tc_cls_flower_offload *cls_flower) { - if (ntc->type != TC_SETUP_MQPRIO) - return -EINVAL; + struct bnxt *bp = netdev_priv(dev); - ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (BNXT_VF(bp)) + return -EOPNOTSUPP; - return bnxt_setup_mq_tc(dev, ntc->mqprio->num_tc); + return bnxt_tc_setup_flower(bp, bp->pf.fw_fid, cls_flower); +} + +static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_CLSFLOWER: + return bnxt_setup_flower(dev, type_data); + case TC_SETUP_MQPRIO: { + struct tc_mqprio_qopt *mqprio = type_data; + + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return bnxt_setup_mq_tc(dev, mqprio->num_tc); + } + default: + return -EOPNOTSUPP; + } } #ifdef CONFIG_RFS_ACCEL @@ -7412,6 +7575,102 @@ static void bnxt_udp_tunnel_del(struct net_device *dev, schedule_work(&bp->sp_task); } +static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, + int nlflags) +{ + struct bnxt *bp = netdev_priv(dev); + + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, bp->br_mode, 0, 0, + nlflags, filter_mask, NULL); +} + +static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, + u16 flags) +{ + struct bnxt *bp = netdev_priv(dev); + struct nlattr *attr, *br_spec; + int rem, rc = 0; + + if (bp->hwrm_spec_code < 0x10708 || !BNXT_SINGLE_PF(bp)) + return -EOPNOTSUPP; + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; + + nla_for_each_nested(attr, br_spec, rem) { + u16 mode; + + if (nla_type(attr) != IFLA_BRIDGE_MODE) + continue; + + if (nla_len(attr) < sizeof(mode)) + return -EINVAL; + + mode = nla_get_u16(attr); + if (mode == bp->br_mode) + break; + + rc = bnxt_hwrm_set_br_mode(bp, mode); + if (!rc) + bp->br_mode = mode; + break; + } + return rc; +} + +static int bnxt_get_phys_port_name(struct net_device *dev, char *buf, + size_t len) +{ + struct bnxt *bp = netdev_priv(dev); + int rc; + + /* The PF and it's VF-reps only support the switchdev framework */ + if (!BNXT_PF(bp)) + return -EOPNOTSUPP; + + rc = snprintf(buf, len, "p%d", bp->pf.port_id); + + if (rc >= len) + return -EOPNOTSUPP; + return 0; +} + +int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr) +{ + if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) + return -EOPNOTSUPP; + + /* The PF and it's VF-reps only support the switchdev framework */ + if (!BNXT_PF(bp)) + return -EOPNOTSUPP; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: + /* In SRIOV each PF-pool (PF + child VFs) serves as a + * switching domain, the PF's perm mac-addr can be used + * as the unique parent-id + */ + attr->u.ppid.id_len = ETH_ALEN; + ether_addr_copy(attr->u.ppid.id, bp->pf.mac_addr); + break; + default: + return -EOPNOTSUPP; + } + return 0; +} + +static int bnxt_swdev_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) +{ + return bnxt_port_attr_get(netdev_priv(dev), attr); +} + +static const struct switchdev_ops bnxt_switchdev_ops = { + .switchdev_port_attr_get = bnxt_swdev_port_attr_get +}; + static const struct net_device_ops bnxt_netdev_ops = { .ndo_open = bnxt_open, .ndo_start_xmit = bnxt_start_xmit, @@ -7443,6 +7702,9 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_udp_tunnel_add = bnxt_udp_tunnel_add, .ndo_udp_tunnel_del = bnxt_udp_tunnel_del, .ndo_xdp = bnxt_xdp, + .ndo_bridge_getlink = bnxt_bridge_getlink, + .ndo_bridge_setlink = bnxt_bridge_setlink, + .ndo_get_phys_port_name = bnxt_get_phys_port_name }; static void bnxt_remove_one(struct pci_dev *pdev) @@ -7450,11 +7712,14 @@ static void bnxt_remove_one(struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(dev); - if (BNXT_PF(bp)) + if (BNXT_PF(bp)) { bnxt_sriov_disable(bp); + bnxt_dl_unregister(bp); + } pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); + bnxt_shutdown_tc(bp); cancel_work_sync(&bp->sp_task); bp->sp_event = 0; @@ -7623,6 +7888,9 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh) if (sh) bp->flags |= BNXT_FLAG_SHARED_RINGS; dflt_rings = netif_get_num_default_rss_queues(); + /* Reduce default rings to reduce memory usage on multi-port cards */ + if (bp->port_count > 1) + dflt_rings = min_t(int, dflt_rings, 4); rc = bnxt_get_dflt_rings(bp, &max_rx_rings, &max_tx_rings, sh); if (rc) return rc; @@ -7722,6 +7990,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->netdev_ops = &bnxt_netdev_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; + SWITCHDEV_SET_OPS(dev, &bnxt_switchdev_ops); pci_set_drvdata(pdev, dev); rc = bnxt_alloc_hwrm_resources(bp); @@ -7776,6 +8045,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) #ifdef CONFIG_BNXT_SRIOV init_waitqueue_head(&bp->sriov_cfg_wait); + mutex_init(&bp->sriov_lock); #endif bp->gro_func = bnxt_gro_func_5730x; if (BNXT_CHIP_P4_PLUS(bp)) @@ -7820,6 +8090,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_ethtool_init(bp); bnxt_dcb_init(bp); + rc = bnxt_probe_phy(bp); + if (rc) + goto init_err_pci_clean; + bnxt_set_rx_skb_mode(bp, false); bnxt_set_tpa_flags(bp); bnxt_set_ring_params(bp); @@ -7854,10 +8128,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (dev->hw_features & NETIF_F_HW_VLAN_CTAG_RX) bp->flags |= BNXT_FLAG_STRIP_VLAN; - rc = bnxt_probe_phy(bp); - if (rc) - goto init_err_pci_clean; - rc = bnxt_init_int_mode(bp); if (rc) goto init_err_pci_clean; @@ -7868,9 +8138,15 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) else device_set_wakeup_capable(&pdev->dev, false); + if (BNXT_PF(bp)) + bnxt_init_tc(bp); + rc = register_netdev(dev); if (rc) - goto init_err_clr_int; + goto init_err_cleanup_tc; + + if (BNXT_PF(bp)) + bnxt_dl_register(bp); netdev_info(dev, "%s found at mem %lx, node addr %pM\n", board_info[ent->driver_data].name, @@ -7880,7 +8156,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; -init_err_clr_int: +init_err_cleanup_tc: + bnxt_shutdown_tc(bp); bnxt_clear_int_mode(bp); init_err_pci_clean: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index f34691f85602..7b888d4b2b55 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -12,13 +12,17 @@ #define BNXT_H #define DRV_MODULE_NAME "bnxt_en" -#define DRV_MODULE_VERSION "1.7.0" +#define DRV_MODULE_VERSION "1.8.0" #define DRV_VER_MAJ 1 -#define DRV_VER_MIN 7 +#define DRV_VER_MIN 8 #define DRV_VER_UPD 0 #include <linux/interrupt.h> +#include <linux/rhashtable.h> +#include <net/devlink.h> +#include <net/dst_metadata.h> +#include <net/switchdev.h> struct tx_bd { __le32 tx_bd_len_flags_type; @@ -242,6 +246,10 @@ struct rx_cmp_ext { ((le32_to_cpu((rxcmp1)->rx_cmp_flags2) & \ RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3) +#define RX_CMP_CFA_CODE(rxcmpl1) \ + ((le32_to_cpu((rxcmpl1)->rx_cmp_cfa_code_errors_v2) & \ + RX_CMPL_CFA_CODE_MASK) >> RX_CMPL_CFA_CODE_SFT) + struct rx_agg_cmp { __le32 rx_agg_cmp_len_flags_type; #define RX_AGG_CMP_TYPE (0x3f << 0) @@ -311,6 +319,10 @@ struct rx_tpa_start_cmp_ext { __le32 rx_tpa_start_cmp_hdr_info; }; +#define TPA_START_CFA_CODE(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) & \ + RX_TPA_START_CMP_CFA_CODE) >> RX_TPA_START_CMPL_CFA_CODE_SHIFT) + struct rx_tpa_end_cmp { __le32 rx_tpa_end_cmp_len_flags_type; #define RX_TPA_END_CMP_TYPE (0x3f << 0) @@ -618,6 +630,8 @@ struct bnxt_tpa_info { #define BNXT_TPA_OUTER_L3_OFF(hdr_info) \ ((hdr_info) & 0x1ff) + + u16 cfa_code; /* cfa_code in TPA start compl */ }; struct bnxt_rx_ring_info { @@ -688,8 +702,10 @@ struct bnxt_napi { struct bnxt_irq { irq_handler_t handler; unsigned int vector; - u8 requested; + u8 requested:1; + u8 have_cpumask:1; char name[IFNAMSIZ + 2]; + cpumask_var_t cpu_mask; }; #define HWRM_RING_ALLOC_TX 0x1 @@ -825,8 +841,8 @@ struct bnxt_link_info { u8 loop_back; u8 link_up; u8 duplex; -#define BNXT_LINK_DUPLEX_HALF PORT_PHY_QCFG_RESP_DUPLEX_HALF -#define BNXT_LINK_DUPLEX_FULL PORT_PHY_QCFG_RESP_DUPLEX_FULL +#define BNXT_LINK_DUPLEX_HALF PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF +#define BNXT_LINK_DUPLEX_FULL PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL u8 pause; #define BNXT_LINK_PAUSE_TX PORT_PHY_QCFG_RESP_PAUSE_TX #define BNXT_LINK_PAUSE_RX PORT_PHY_QCFG_RESP_PAUSE_RX @@ -928,6 +944,45 @@ struct bnxt_test_info { #define BNXT_CAG_REG_LEGACY_INT_STATUS 0x4014 #define BNXT_CAG_REG_BASE 0x300000 +struct bnxt_tc_info { + bool enabled; + + /* hash table to store TC offloaded flows */ + struct rhashtable flow_table; + struct rhashtable_params flow_ht_params; + + /* hash table to store L2 keys of TC flows */ + struct rhashtable l2_table; + struct rhashtable_params l2_ht_params; + + /* lock to atomically add/del an l2 node when a flow is + * added or deleted. + */ + struct mutex lock; + + /* Stat counter mask (width) */ + u64 bytes_mask; + u64 packets_mask; +}; + +struct bnxt_vf_rep_stats { + u64 packets; + u64 bytes; + u64 dropped; +}; + +struct bnxt_vf_rep { + struct bnxt *bp; + struct net_device *dev; + struct metadata_dst *dst; + u16 vf_idx; + u16 tx_cfa_action; + u16 rx_cfa_code; + + struct bnxt_vf_rep_stats rx_stats; + struct bnxt_vf_rep_stats tx_stats; +}; + struct bnxt { void __iomem *bar0; void __iomem *bar1; @@ -957,6 +1012,9 @@ struct bnxt { #define CHIP_NUM_5745X 0xd730 +#define CHIP_NUM_58802 0xd802 +#define CHIP_NUM_58808 0xd808 + #define BNXT_CHIP_NUM_5730X(chip_num) \ ((chip_num) >= CHIP_NUM_57301 && \ (chip_num) <= CHIP_NUM_57304) @@ -988,6 +1046,10 @@ struct bnxt { #define BNXT_CHIP_NUM_57X1X(chip_num) \ (BNXT_CHIP_NUM_5731X(chip_num) || BNXT_CHIP_NUM_5741X(chip_num)) +#define BNXT_CHIP_NUM_588XX(chip_num) \ + ((chip_num) == CHIP_NUM_58802 || \ + (chip_num) == CHIP_NUM_58808) + struct net_device *dev; struct pci_dev *pdev; @@ -1027,6 +1089,7 @@ struct bnxt { #define BNXT_FLAG_MULTI_HOST 0x100000 #define BNXT_FLAG_SHORT_CMD 0x200000 #define BNXT_FLAG_DOUBLE_DB 0x400000 + #define BNXT_FLAG_FW_DCBX_AGENT 0x800000 #define BNXT_FLAG_CHIP_NITRO_A0 0x1000000 #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ @@ -1045,6 +1108,7 @@ struct bnxt { #define BNXT_CHIP_P4_PLUS(bp) \ (BNXT_CHIP_NUM_57X1X((bp)->chip_num) || \ BNXT_CHIP_NUM_5745X((bp)->chip_num) || \ + BNXT_CHIP_NUM_588XX((bp)->chip_num) || \ (BNXT_CHIP_NUM_58700((bp)->chip_num) && \ !BNXT_CHIP_TYPE_NITRO_A0(bp))) @@ -1086,6 +1150,7 @@ struct bnxt { int tx_nr_rings; int tx_nr_rings_per_tc; int tx_nr_rings_xdp; + int tx_reserved_rings; int tx_wake_thresh; int tx_push_thresh; @@ -1164,6 +1229,8 @@ struct bnxt { u8 nge_port_cnt; __le16 nge_fw_dst_port_id; u8 port_partition_type; + u8 port_count; + u16 br_mode; u16 rx_coal_ticks; u16 rx_coal_ticks_irq; @@ -1206,6 +1273,12 @@ struct bnxt { wait_queue_head_t sriov_cfg_wait; bool sriov_cfg; #define BNXT_SRIOV_CFG_WAIT_TMO msecs_to_jiffies(10000) + + /* lock to protect VF-rep creation/cleanup via + * multiple paths such as ->sriov_configure() and + * devlink ->eswitch_mode_set() + */ + struct mutex sriov_lock; #endif #define BNXT_NTP_FLTR_MAX_FLTR 4096 @@ -1232,6 +1305,13 @@ struct bnxt { struct bnxt_led_info leds[BNXT_MAX_LED]; struct bpf_prog *xdp_prog; + + /* devlink interface and vf-rep structs */ + struct devlink *dl; + enum devlink_eswitch_mode eswitch_mode; + struct bnxt_vf_rep **vf_reps; /* array of vf-rep ptrs */ + u16 *cfa_code_map; /* cfa_code -> vf_idx map */ + struct bnxt_tc_info tc_info; }; #define BNXT_RX_STATS_OFFSET(counter) \ @@ -1301,9 +1381,10 @@ int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); int bnxt_close_nic(struct bnxt *, bool, bool); -int bnxt_reserve_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, - int tx_xdp); +int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, + int tx_xdp); int bnxt_setup_mq_tc(struct net_device *dev, u8 tc); int bnxt_get_max_rings(struct bnxt *, int *, int *, bool); void bnxt_restore_pf_fw_resources(struct bnxt *bp); +int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 5c6dd0ce209f..aa1f3a2c7a78 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -93,6 +93,12 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets, cos2bw.tsa = QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_ETS; cos2bw.bw_weight = ets->tc_tx_bw[i]; + /* older firmware requires min_bw to be set to the + * same weight value in percent. + */ + cos2bw.min_bw = + cpu_to_le32((ets->tc_tx_bw[i] * 100) | + BW_VALUE_UNIT_PERCENT1_100); } memcpy(data, &cos2bw.queue_id, sizeof(cos2bw) - 4); if (i == 0) { @@ -549,13 +555,18 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode) { struct bnxt *bp = netdev_priv(dev); - /* only support IEEE */ - if ((mode & DCB_CAP_DCBX_VER_CEE) || !(mode & DCB_CAP_DCBX_VER_IEEE)) + /* All firmware DCBX settings are set in NVRAM */ + if (bp->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) return 1; if (mode & DCB_CAP_DCBX_HOST) { if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT)) return 1; + + /* only support IEEE */ + if ((mode & DCB_CAP_DCBX_VER_CEE) || + !(mode & DCB_CAP_DCBX_VER_IEEE)) + return 1; } if (mode == bp->dcbx_cap) @@ -584,7 +595,7 @@ void bnxt_dcb_init(struct bnxt *bp) bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE; if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT)) bp->dcbx_cap |= DCB_CAP_DCBX_HOST; - else + else if (bp->flags & BNXT_FLAG_FW_DCBX_AGENT) bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED; bp->dev->dcbnl_ops = &dcbnl_ops; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h index ecd0a5e46a49..d2e0af960bf5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h @@ -26,6 +26,7 @@ struct bnxt_cos2bw_cfg { u8 queue_id; __le32 min_bw; __le32 max_bw; +#define BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) u8 tsa; u8 pri_lvl; u8 bw_weight; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index be6acadcb202..8eff05a3e0e4 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -86,9 +86,11 @@ static int bnxt_set_coalesce(struct net_device *dev, if (bp->stats_coal_ticks != coal->stats_block_coalesce_usecs) { u32 stats_ticks = coal->stats_block_coalesce_usecs; - stats_ticks = clamp_t(u32, stats_ticks, - BNXT_MIN_STATS_COAL_TICKS, - BNXT_MAX_STATS_COAL_TICKS); + /* Allow 0, which means disable. */ + if (stats_ticks) + stats_ticks = clamp_t(u32, stats_ticks, + BNXT_MIN_STATS_COAL_TICKS, + BNXT_MAX_STATS_COAL_TICKS); stats_ticks = rounddown(stats_ticks, BNXT_MIN_STATS_COAL_TICKS); bp->stats_coal_ticks = stats_ticks; update_stats = true; @@ -198,19 +200,23 @@ static const struct { #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr) +static int bnxt_get_num_stats(struct bnxt *bp) +{ + int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings; + + if (bp->flags & BNXT_FLAG_PORT_STATS) + num_stats += BNXT_NUM_PORT_STATS; + + return num_stats; +} + static int bnxt_get_sset_count(struct net_device *dev, int sset) { struct bnxt *bp = netdev_priv(dev); switch (sset) { - case ETH_SS_STATS: { - int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings; - - if (bp->flags & BNXT_FLAG_PORT_STATS) - num_stats += BNXT_NUM_PORT_STATS; - - return num_stats; - } + case ETH_SS_STATS: + return bnxt_get_num_stats(bp); case ETH_SS_TEST: if (!bp->num_tests) return -EOPNOTSUPP; @@ -225,11 +231,8 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, { u32 i, j = 0; struct bnxt *bp = netdev_priv(dev); - u32 buf_size = sizeof(struct ctx_hw_stats) * bp->cp_nr_rings; u32 stat_fields = sizeof(struct ctx_hw_stats) / 8; - memset(buf, 0, buf_size); - if (!bp->bnapi) return; @@ -432,8 +435,7 @@ static int bnxt_set_channels(struct net_device *dev, } tx_xdp = req_rx_rings; } - rc = bnxt_reserve_rings(bp, req_tx_rings, req_rx_rings, sh, tcs, - tx_xdp); + rc = bnxt_check_rings(bp, req_tx_rings, req_rx_rings, sh, tcs, tx_xdp); if (rc) { netdev_warn(dev, "Unable to allocate the requested rings\n"); return rc; @@ -520,7 +522,7 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd) struct flow_keys *fkeys; int i, rc = -EINVAL; - if (fs->location < 0 || fs->location >= BNXT_NTP_FLTR_MAX_FLTR) + if (fs->location >= BNXT_NTP_FLTR_MAX_FLTR) return rc; for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) { @@ -835,7 +837,7 @@ static void bnxt_get_drvinfo(struct net_device *dev, strlcpy(info->fw_version, bp->fw_ver_str, sizeof(info->fw_version)); strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info)); - info->n_stats = BNXT_NUM_STATS * bp->cp_nr_rings; + info->n_stats = bnxt_get_num_stats(bp); info->testinfo_len = bp->num_tests; /* TODO CHIMP_FW: eeprom dump details */ info->eedump_len = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 7dc71bb95837..cb04cc76e8ad 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -11,14 +11,14 @@ #ifndef BNXT_HSI_H #define BNXT_HSI_H -/* HSI and HWRM Specification 1.7.6 */ +/* HSI and HWRM Specification 1.8.1 */ #define HWRM_VERSION_MAJOR 1 -#define HWRM_VERSION_MINOR 7 -#define HWRM_VERSION_UPDATE 6 +#define HWRM_VERSION_MINOR 8 +#define HWRM_VERSION_UPDATE 1 -#define HWRM_VERSION_RSVD 2 /* non-zero means beta version */ +#define HWRM_VERSION_RSVD 4 /* non-zero means beta version */ -#define HWRM_VERSION_STR "1.7.6.2" +#define HWRM_VERSION_STR "1.8.1.4" /* * Following is the signature for HWRM message field that indicates not * applicable (All F's). Need to cast it the size of the field if needed. @@ -813,7 +813,7 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED 0x4UL #define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED 0x8UL #define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED 0x10UL - #define FUNC_QCFG_RESP_FLAGS_MULTI_HOST 0x20UL + #define FUNC_QCFG_RESP_FLAGS_MULTI_HOST 0x20UL u8 mac_address[6]; __le16 pci_id; __le16 alloc_rsscos_ctx; @@ -835,9 +835,8 @@ struct hwrm_func_qcfg_output { u8 port_pf_cnt; #define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL 0x0UL __le16 dflt_vnic_id; - u8 host_cnt; - #define FUNC_QCFG_RESP_HOST_CNT_UNAVAIL 0x0UL u8 unused_0; + u8 unused_1; __le32 min_bw; #define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK 0xfffffffUL #define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT 0 @@ -874,12 +873,56 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_EVB_MODE_NO_EVB 0x0UL #define FUNC_QCFG_RESP_EVB_MODE_VEB 0x1UL #define FUNC_QCFG_RESP_EVB_MODE_VEPA 0x2UL - u8 unused_1; + u8 unused_2; __le16 alloc_vfs; __le32 alloc_mcast_filters; __le32 alloc_hw_ring_grps; __le16 alloc_sp_tx_rings; + u8 unused_3; + u8 valid; +}; + +/* hwrm_func_vlan_cfg */ +/* Input (48 bytes) */ +struct hwrm_func_vlan_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 fid; + u8 unused_0; + u8 unused_1; + __le32 enables; + #define FUNC_VLAN_CFG_REQ_ENABLES_STAG_VID 0x1UL + #define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_VID 0x2UL + #define FUNC_VLAN_CFG_REQ_ENABLES_STAG_PCP 0x4UL + #define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_PCP 0x8UL + #define FUNC_VLAN_CFG_REQ_ENABLES_STAG_TPID 0x10UL + #define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_TPID 0x20UL + __le16 stag_vid; + u8 stag_pcp; + u8 unused_2; + __be16 stag_tpid; + __le16 ctag_vid; + u8 ctag_pcp; + u8 unused_3; + __be16 ctag_tpid; + __le32 rsvd1; + __le32 rsvd2; + __le32 unused_4; +}; + +/* Output (16 bytes) */ +struct hwrm_func_vlan_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 unused_0; + u8 unused_1; u8 unused_2; + u8 unused_3; u8 valid; }; @@ -902,6 +945,8 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE 0x200UL #define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE 0x400UL #define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST 0x800UL + #define FUNC_CFG_REQ_FLAGS_NO_AUTOCLEAR_STATISTIC 0x1000UL + #define FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST 0x2000UL __le32 enables; #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL @@ -1456,9 +1501,9 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB 0x1f4UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB 0xffffUL - u8 duplex; - #define PORT_PHY_QCFG_RESP_DUPLEX_HALF 0x0UL - #define PORT_PHY_QCFG_RESP_DUPLEX_FULL 0x1UL + u8 duplex_cfg; + #define PORT_PHY_QCFG_RESP_DUPLEX_CFG_HALF 0x0UL + #define PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL 0x1UL u8 pause; #define PORT_PHY_QCFG_RESP_PAUSE_TX 0x1UL #define PORT_PHY_QCFG_RESP_PAUSE_RX 0x2UL @@ -1573,6 +1618,9 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASELR4 0x16UL #define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASEER4 0x17UL #define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_ACTIVE_CABLE 0x18UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASET 0x19UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASESX 0x1aUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASECX 0x1bUL u8 media_type; #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN 0x0UL #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP 0x1UL @@ -1651,14 +1699,16 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED 0x10UL #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED 0x20UL #define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED 0x40UL + u8 duplex_state; + #define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF 0x0UL + #define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL 0x1UL u8 unused_1; - u8 unused_2; char phy_vendor_name[16]; char phy_vendor_partnumber[16]; - __le32 unused_3; + __le32 unused_2; + u8 unused_3; u8 unused_4; u8 unused_5; - u8 unused_6; u8 valid; }; @@ -1744,6 +1794,51 @@ struct hwrm_port_mac_cfg_output { u8 valid; }; +/* hwrm_port_mac_ptp_qcfg */ +/* Input (24 bytes) */ +struct hwrm_port_mac_ptp_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 port_id; + __le16 unused_0[3]; +}; + +/* Output (80 bytes) */ +struct hwrm_port_mac_ptp_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 flags; + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS 0x1UL + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS 0x2UL + u8 unused_0; + __le16 unused_1; + __le32 rx_ts_reg_off_lower; + __le32 rx_ts_reg_off_upper; + __le32 rx_ts_reg_off_seq_id; + __le32 rx_ts_reg_off_src_id_0; + __le32 rx_ts_reg_off_src_id_1; + __le32 rx_ts_reg_off_src_id_2; + __le32 rx_ts_reg_off_domain_id; + __le32 rx_ts_reg_off_fifo; + __le32 rx_ts_reg_off_fifo_adv; + __le32 rx_ts_reg_off_granularity; + __le32 tx_ts_reg_off_lower; + __le32 tx_ts_reg_off_upper; + __le32 tx_ts_reg_off_seq_id; + __le32 tx_ts_reg_off_fifo; + __le32 tx_ts_reg_off_granularity; + __le32 unused_2; + u8 unused_3; + u8 unused_4; + u8 unused_5; + u8 valid; +}; + /* hwrm_port_qstats */ /* Input (40 bytes) */ struct hwrm_port_qstats_input { @@ -1874,11 +1969,16 @@ struct hwrm_port_phy_qcaps_output { __le16 req_type; __le16 seq_id; __le16 resp_len; - u8 eee_supported; - #define PORT_PHY_QCAPS_RESP_EEE_SUPPORTED 0x1UL - #define PORT_PHY_QCAPS_RESP_RSVD1_MASK 0xfeUL - #define PORT_PHY_QCAPS_RESP_RSVD1_SFT 1 - u8 unused_0; + u8 flags; + #define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED 0x1UL + #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK 0xfeUL + #define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT 1 + u8 port_cnt; + #define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL + #define PORT_PHY_QCAPS_RESP_PORT_CNT_1 0x1UL + #define PORT_PHY_QCAPS_RESP_PORT_CNT_2 0x2UL + #define PORT_PHY_QCAPS_RESP_PORT_CNT_3 0x3UL + #define PORT_PHY_QCAPS_RESP_PORT_CNT_4 0x4UL __le16 supported_speeds_force_mode; #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD 0x1UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB 0x2UL @@ -3152,6 +3252,95 @@ struct hwrm_queue_cos2bw_cfg_output { u8 valid; }; +/* hwrm_queue_dscp_qcaps */ +/* Input (24 bytes) */ +struct hwrm_queue_dscp_qcaps_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 port_id; + u8 unused_0[7]; +}; + +/* Output (16 bytes) */ +struct hwrm_queue_dscp_qcaps_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 num_dscp_bits; + u8 unused_0; + __le16 max_entries; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + +/* hwrm_queue_dscp2pri_qcfg */ +/* Input (32 bytes) */ +struct hwrm_queue_dscp2pri_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le64 dest_data_addr; + u8 port_id; + u8 unused_0; + __le16 dest_data_buffer_size; + __le32 unused_1; +}; + +/* Output (16 bytes) */ +struct hwrm_queue_dscp2pri_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 entry_cnt; + u8 default_pri; + u8 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + +/* hwrm_queue_dscp2pri_cfg */ +/* Input (40 bytes) */ +struct hwrm_queue_dscp2pri_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le64 src_data_addr; + __le32 flags; + #define QUEUE_DSCP2PRI_CFG_REQ_FLAGS_USE_HW_DEFAULT_PRI 0x1UL + __le32 enables; + #define QUEUE_DSCP2PRI_CFG_REQ_ENABLES_DEFAULT_PRI 0x1UL + u8 port_id; + u8 default_pri; + __le16 entry_cnt; + __le32 unused_0; +}; + +/* Output (16 bytes) */ +struct hwrm_queue_dscp2pri_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + /* hwrm_vnic_alloc */ /* Input (24 bytes) */ struct hwrm_vnic_alloc_input { @@ -4038,7 +4227,7 @@ struct hwrm_cfa_encap_record_alloc_input { #define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE 0x8UL u8 unused_0; __le16 unused_1; - __le32 encap_data[16]; + __le32 encap_data[20]; }; /* Output (16 bytes) */ @@ -4120,8 +4309,8 @@ struct hwrm_cfa_ntuple_filter_alloc_input { #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6 0x6UL u8 ip_protocol; #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL - #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP 0x6UL - #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP 0x11UL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP 0x6UL + #define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP 0x11UL __le16 dst_id; __le16 mirror_vnic_id; u8 tunnel_type; @@ -4224,6 +4413,216 @@ struct hwrm_cfa_ntuple_filter_cfg_output { u8 valid; }; +/* hwrm_cfa_flow_alloc */ +/* Input (128 bytes) */ +struct hwrm_cfa_flow_alloc_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 flags; + #define CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL 0x1UL + #define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_MASK 0x6UL + #define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_SFT 1 + #define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_NONE (0x0UL << 1) + #define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE (0x1UL << 1) + #define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO (0x2UL << 1) + #define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_LAST CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO + #define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_MASK 0x38UL + #define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_SFT 3 + #define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2 (0x0UL << 3) + #define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4 (0x1UL << 3) + #define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6 (0x2UL << 3) + #define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_LAST CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6 + __le16 src_fid; + __le32 tunnel_handle; + __le16 action_flags; + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD 0x1UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE 0x2UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP 0x4UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER 0x8UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL 0x10UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC 0x20UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST 0x40UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS 0x80UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE 0x100UL + #define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT 0x200UL + __le16 dst_fid; + __be16 l2_rewrite_vlan_tpid; + __be16 l2_rewrite_vlan_tci; + __le16 act_meter_id; + __le16 ref_flow_handle; + __be16 ethertype; + __be16 outer_vlan_tci; + __be16 dmac[3]; + __be16 inner_vlan_tci; + __be16 smac[3]; + u8 ip_dst_mask_len; + u8 ip_src_mask_len; + __be32 ip_dst[4]; + __be32 ip_src[4]; + __be16 l4_src_port; + __be16 l4_src_port_mask; + __be16 l4_dst_port; + __be16 l4_dst_port_mask; + __be32 nat_ip_address[4]; + __be16 l2_rewrite_dmac[3]; + __be16 nat_port; + __be16 l2_rewrite_smac[3]; + u8 ip_proto; + u8 unused_0; +}; + +/* Output (16 bytes) */ +struct hwrm_cfa_flow_alloc_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 flow_handle; + u8 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 unused_4; + u8 valid; +}; + +/* hwrm_cfa_flow_free */ +/* Input (24 bytes) */ +struct hwrm_cfa_flow_free_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 flow_handle; + __le16 unused_0[3]; +}; + +/* Output (32 bytes) */ +struct hwrm_cfa_flow_free_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le64 packet; + __le64 byte; + __le32 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + +/* hwrm_cfa_flow_stats */ +/* Input (40 bytes) */ +struct hwrm_cfa_flow_stats_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 num_flows; + __le16 flow_handle_0; + __le16 flow_handle_1; + __le16 flow_handle_2; + __le16 flow_handle_3; + __le16 flow_handle_4; + __le16 flow_handle_5; + __le16 flow_handle_6; + __le16 flow_handle_7; + __le16 flow_handle_8; + __le16 flow_handle_9; + __le16 unused_0; +}; + +/* Output (176 bytes) */ +struct hwrm_cfa_flow_stats_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le64 packet_0; + __le64 packet_1; + __le64 packet_2; + __le64 packet_3; + __le64 packet_4; + __le64 packet_5; + __le64 packet_6; + __le64 packet_7; + __le64 packet_8; + __le64 packet_9; + __le64 byte_0; + __le64 byte_1; + __le64 byte_2; + __le64 byte_3; + __le64 byte_4; + __le64 byte_5; + __le64 byte_6; + __le64 byte_7; + __le64 byte_8; + __le64 byte_9; + __le32 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + +/* hwrm_cfa_vfr_alloc */ +/* Input (32 bytes) */ +struct hwrm_cfa_vfr_alloc_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 vf_id; + __le16 reserved; + __le32 unused_0; + char vfr_name[32]; +}; + +/* Output (16 bytes) */ +struct hwrm_cfa_vfr_alloc_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le16 rx_cfa_code; + __le16 tx_cfa_action; + u8 unused_0; + u8 unused_1; + u8 unused_2; + u8 valid; +}; + +/* hwrm_cfa_vfr_free */ +/* Input (24 bytes) */ +struct hwrm_cfa_vfr_free_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + char vfr_name[32]; +}; + +/* Output (16 bytes) */ +struct hwrm_cfa_vfr_free_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 unused_0; + u8 unused_1; + u8 unused_2; + u8 unused_3; + u8 valid; +}; + /* hwrm_tunnel_dst_port_query */ /* Input (24 bytes) */ struct hwrm_tunnel_dst_port_query_input { @@ -4448,12 +4847,13 @@ struct hwrm_fw_reset_input { #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT 0x1UL #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE 0x3UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_RSVD 0x4UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST 0x4UL u8 selfrst_status; #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE 0x0UL #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP 0x1UL #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST 0x2UL - __le16 unused_0[3]; + u8 host_idx; + u8 unused_0[5]; }; /* Output (16 bytes) */ @@ -4487,7 +4887,7 @@ struct hwrm_fw_qstatus_input { #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_MGMT 0x1UL #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_ROCE 0x3UL - #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_RSVD 0x4UL + #define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_HOST 0x4UL u8 unused_0[7]; }; @@ -4572,6 +4972,16 @@ struct hwrm_fw_set_structured_data_output { u8 valid; }; +/* Command specific Error Codes (8 bytes) */ +struct hwrm_fw_set_structured_data_cmd_err { + u8 code; + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT 0x1UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT 0x2UL + #define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID 0x3UL + u8 unused_0[7]; +}; + /* hwrm_fw_get_structured_data */ /* Input (32 bytes) */ struct hwrm_fw_get_structured_data_input { @@ -4611,6 +5021,14 @@ struct hwrm_fw_get_structured_data_output { u8 valid; }; +/* Command specific Error Codes (8 bytes) */ +struct hwrm_fw_get_structured_data_cmd_err { + u8 code; + #define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL + #define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID 0x3UL + u8 unused_0[7]; +}; + /* hwrm_exec_fwd_resp */ /* Input (128 bytes) */ struct hwrm_exec_fwd_resp_input { @@ -5280,11 +5698,15 @@ struct hwrm_selftest_qlist_output { #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST 0x2UL #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST 0x4UL #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST 0x8UL + #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_EYE_TEST 0x10UL + #define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_EYE_TEST 0x20UL u8 offline_tests; #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST 0x1UL #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST 0x2UL #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST 0x4UL #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST 0x8UL + #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_EYE_TEST 0x10UL + #define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_EYE_TEST 0x20UL u8 unused_0; __le16 test_timeout; u8 unused_1; @@ -5312,6 +5734,8 @@ struct hwrm_selftest_exec_input { #define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST 0x2UL #define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST 0x4UL #define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST 0x8UL + #define SELFTEST_EXEC_REQ_FLAGS_PCIE_EYE_TEST 0x10UL + #define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_EYE_TEST 0x20UL u8 unused_0[7]; }; @@ -5326,11 +5750,15 @@ struct hwrm_selftest_exec_output { #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST 0x2UL #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST 0x4UL #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST 0x8UL + #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_EYE_TEST 0x10UL + #define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_EYE_TEST 0x20UL u8 test_success; #define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST 0x1UL #define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST 0x2UL #define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST 0x4UL #define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST 0x8UL + #define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_EYE_TEST 0x10UL + #define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_EYE_TEST 0x20UL __le16 unused_0[3]; }; @@ -5411,7 +5839,7 @@ struct cmd_nums { #define HWRM_PORT_LPBK_CLR_STATS (0x26UL) #define HWRM_PORT_PHY_QCFG (0x27UL) #define HWRM_PORT_MAC_QCFG (0x28UL) - #define RESERVED7 (0x29UL) + #define HWRM_PORT_MAC_PTP_QCFG (0x29UL) #define HWRM_PORT_PHY_QCAPS (0x2aUL) #define HWRM_PORT_PHY_I2C_WRITE (0x2bUL) #define HWRM_PORT_PHY_I2C_READ (0x2cUL) @@ -5421,14 +5849,17 @@ struct cmd_nums { #define HWRM_QUEUE_QPORTCFG (0x30UL) #define HWRM_QUEUE_QCFG (0x31UL) #define HWRM_QUEUE_CFG (0x32UL) - #define RESERVED2 (0x33UL) - #define RESERVED3 (0x34UL) + #define HWRM_FUNC_VLAN_CFG (0x33UL) + #define HWRM_FUNC_VLAN_QCFG (0x34UL) #define HWRM_QUEUE_PFCENABLE_QCFG (0x35UL) #define HWRM_QUEUE_PFCENABLE_CFG (0x36UL) #define HWRM_QUEUE_PRI2COS_QCFG (0x37UL) #define HWRM_QUEUE_PRI2COS_CFG (0x38UL) #define HWRM_QUEUE_COS2BW_QCFG (0x39UL) #define HWRM_QUEUE_COS2BW_CFG (0x3aUL) + #define HWRM_QUEUE_DSCP_QCAPS (0x3bUL) + #define HWRM_QUEUE_DSCP2PRI_QCFG (0x3cUL) + #define HWRM_QUEUE_DSCP2PRI_CFG (0x3dUL) #define HWRM_VNIC_ALLOC (0x40UL) #define HWRM_VNIC_FREE (0x41UL) #define HWRM_VNIC_CFG (0x42UL) @@ -5455,7 +5886,7 @@ struct cmd_nums { #define HWRM_CFA_L2_FILTER_FREE (0x91UL) #define HWRM_CFA_L2_FILTER_CFG (0x92UL) #define HWRM_CFA_L2_SET_RX_MASK (0x93UL) - #define RESERVED4 (0x94UL) + #define HWRM_CFA_VLAN_ANTISPOOF_CFG (0x94UL) #define HWRM_CFA_TUNNEL_FILTER_ALLOC (0x95UL) #define HWRM_CFA_TUNNEL_FILTER_FREE (0x96UL) #define HWRM_CFA_ENCAP_RECORD_ALLOC (0x97UL) @@ -5494,6 +5925,8 @@ struct cmd_nums { #define HWRM_CFA_METER_PROFILE_CFG (0xf7UL) #define HWRM_CFA_METER_INSTANCE_ALLOC (0xf8UL) #define HWRM_CFA_METER_INSTANCE_FREE (0xf9UL) + #define HWRM_CFA_VFR_ALLOC (0xfdUL) + #define HWRM_CFA_VFR_FREE (0xfeUL) #define HWRM_CFA_VF_PAIR_ALLOC (0x100UL) #define HWRM_CFA_VF_PAIR_FREE (0x101UL) #define HWRM_CFA_VF_PAIR_INFO (0x102UL) @@ -5502,14 +5935,20 @@ struct cmd_nums { #define HWRM_CFA_FLOW_FLUSH (0x105UL) #define HWRM_CFA_FLOW_STATS (0x106UL) #define HWRM_CFA_FLOW_INFO (0x107UL) + #define HWRM_CFA_DECAP_FILTER_ALLOC (0x108UL) + #define HWRM_CFA_DECAP_FILTER_FREE (0x109UL) + #define HWRM_CFA_VLAN_ANTISPOOF_QCFG (0x10aUL) #define HWRM_SELFTEST_QLIST (0x200UL) #define HWRM_SELFTEST_EXEC (0x201UL) #define HWRM_SELFTEST_IRQ (0x202UL) + #define HWRM_SELFTEST_RETREIVE_EYE_DATA (0x203UL) #define HWRM_DBG_READ_DIRECT (0xff10UL) #define HWRM_DBG_READ_INDIRECT (0xff11UL) #define HWRM_DBG_WRITE_DIRECT (0xff12UL) #define HWRM_DBG_WRITE_INDIRECT (0xff13UL) #define HWRM_DBG_DUMP (0xff14UL) + #define HWRM_DBG_ERASE_NVM (0xff15UL) + #define HWRM_DBG_CFG (0xff16UL) #define HWRM_NVM_FACTORY_DEFAULTS (0xffeeUL) #define HWRM_NVM_VALIDATE_OPTION (0xffefUL) #define HWRM_NVM_FLUSH (0xfff0UL) @@ -5720,6 +6159,7 @@ struct hwrm_struct_hdr { #define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE 0x426UL #define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE 0x1UL #define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION 0xaUL + #define STRUCT_HDR_STRUCT_ID_RSS_V2 0x64UL __le16 len; u8 version; u8 count; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index b8e7248294d9..d37925a8a65b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -18,6 +18,7 @@ #include "bnxt.h" #include "bnxt_ulp.h" #include "bnxt_sriov.h" +#include "bnxt_vfr.h" #include "bnxt_ethtool.h" #ifdef CONFIG_BNXT_SRIOV @@ -587,6 +588,10 @@ void bnxt_sriov_disable(struct bnxt *bp) if (!num_vfs) return; + /* synchronize VF and VF-rep create and destroy */ + mutex_lock(&bp->sriov_lock); + bnxt_vf_reps_destroy(bp); + if (pci_vfs_assigned(bp->pdev)) { bnxt_hwrm_fwd_async_event_cmpl( bp, NULL, ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD); @@ -597,6 +602,7 @@ void bnxt_sriov_disable(struct bnxt *bp) /* Free the HW resources reserved for various VF's */ bnxt_hwrm_func_vf_resource_free(bp, num_vfs); } + mutex_unlock(&bp->sriov_lock); bnxt_free_vf_resources(bp); @@ -794,8 +800,10 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) PORT_PHY_QCFG_RESP_LINK_LINK; phy_qcfg_resp.link_speed = cpu_to_le16( PORT_PHY_QCFG_RESP_LINK_SPEED_10GB); - phy_qcfg_resp.duplex = - PORT_PHY_QCFG_RESP_DUPLEX_FULL; + phy_qcfg_resp.duplex_cfg = + PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL; + phy_qcfg_resp.duplex_state = + PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL; phy_qcfg_resp.pause = (PORT_PHY_QCFG_RESP_PAUSE_TX | PORT_PHY_QCFG_RESP_PAUSE_RX); @@ -804,7 +812,8 @@ static int bnxt_vf_set_link(struct bnxt *bp, struct bnxt_vf_info *vf) /* force link down */ phy_qcfg_resp.link = PORT_PHY_QCFG_RESP_LINK_NO_LINK; phy_qcfg_resp.link_speed = 0; - phy_qcfg_resp.duplex = PORT_PHY_QCFG_RESP_DUPLEX_HALF; + phy_qcfg_resp.duplex_state = + PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF; phy_qcfg_resp.pause = 0; } rc = bnxt_hwrm_fwd_resp(bp, vf, &phy_qcfg_resp, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c new file mode 100644 index 000000000000..ccd699fb2d70 --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -0,0 +1,834 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2017 Broadcom Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/if_vlan.h> +#include <net/flow_dissector.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_skbedit.h> +#include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_vlan.h> + +#include "bnxt_hsi.h" +#include "bnxt.h" +#include "bnxt_sriov.h" +#include "bnxt_tc.h" +#include "bnxt_vfr.h" + +#ifdef CONFIG_BNXT_FLOWER_OFFLOAD + +#define BNXT_FID_INVALID 0xffff +#define VLAN_TCI(vid, prio) ((vid) | ((prio) << VLAN_PRIO_SHIFT)) + +/* Return the dst fid of the func for flow forwarding + * For PFs: src_fid is the fid of the PF + * For VF-reps: src_fid the fid of the VF + */ +static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev) +{ + struct bnxt *bp; + + /* check if dev belongs to the same switch */ + if (!switchdev_port_same_parent_id(pf_bp->dev, dev)) { + netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch", + dev->ifindex); + return BNXT_FID_INVALID; + } + + /* Is dev a VF-rep? */ + if (dev != pf_bp->dev) + return bnxt_vf_rep_get_fid(dev); + + bp = netdev_priv(dev); + return bp->pf.fw_fid; +} + +static int bnxt_tc_parse_redir(struct bnxt *bp, + struct bnxt_tc_actions *actions, + const struct tc_action *tc_act) +{ + int ifindex = tcf_mirred_ifindex(tc_act); + struct net_device *dev; + u16 dst_fid; + + dev = __dev_get_by_index(dev_net(bp->dev), ifindex); + if (!dev) { + netdev_info(bp->dev, "no dev for ifindex=%d", ifindex); + return -EINVAL; + } + + /* find the FID from dev */ + dst_fid = bnxt_flow_get_dst_fid(bp, dev); + if (dst_fid == BNXT_FID_INVALID) { + netdev_info(bp->dev, "can't get fid for ifindex=%d", ifindex); + return -EINVAL; + } + + actions->flags |= BNXT_TC_ACTION_FLAG_FWD; + actions->dst_fid = dst_fid; + actions->dst_dev = dev; + return 0; +} + +static void bnxt_tc_parse_vlan(struct bnxt *bp, + struct bnxt_tc_actions *actions, + const struct tc_action *tc_act) +{ + if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_POP) { + actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN; + } else if (tcf_vlan_action(tc_act) == TCA_VLAN_ACT_PUSH) { + actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN; + actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act)); + actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act); + } +} + +static int bnxt_tc_parse_actions(struct bnxt *bp, + struct bnxt_tc_actions *actions, + struct tcf_exts *tc_exts) +{ + const struct tc_action *tc_act; + LIST_HEAD(tc_actions); + int rc; + + if (!tcf_exts_has_actions(tc_exts)) { + netdev_info(bp->dev, "no actions"); + return -EINVAL; + } + + tcf_exts_to_list(tc_exts, &tc_actions); + list_for_each_entry(tc_act, &tc_actions, list) { + /* Drop action */ + if (is_tcf_gact_shot(tc_act)) { + actions->flags |= BNXT_TC_ACTION_FLAG_DROP; + return 0; /* don't bother with other actions */ + } + + /* Redirect action */ + if (is_tcf_mirred_egress_redirect(tc_act)) { + rc = bnxt_tc_parse_redir(bp, actions, tc_act); + if (rc) + return rc; + continue; + } + + /* Push/pop VLAN */ + if (is_tcf_vlan(tc_act)) { + bnxt_tc_parse_vlan(bp, actions, tc_act); + continue; + } + } + + return 0; +} + +#define GET_KEY(flow_cmd, key_type) \ + skb_flow_dissector_target((flow_cmd)->dissector, key_type,\ + (flow_cmd)->key) +#define GET_MASK(flow_cmd, key_type) \ + skb_flow_dissector_target((flow_cmd)->dissector, key_type,\ + (flow_cmd)->mask) + +static int bnxt_tc_parse_flow(struct bnxt *bp, + struct tc_cls_flower_offload *tc_flow_cmd, + struct bnxt_tc_flow *flow) +{ + struct flow_dissector *dissector = tc_flow_cmd->dissector; + u16 addr_type = 0; + + /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ + if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || + (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) == 0) { + netdev_info(bp->dev, "cannot form TC key: used_keys = 0x%x", + dissector->used_keys); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_dissector_key_control *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_CONTROL); + + addr_type = key->addr_type; + } + + if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); + struct flow_dissector_key_basic *mask = + GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); + + flow->l2_key.ether_type = key->n_proto; + flow->l2_mask.ether_type = mask->n_proto; + + if (key->n_proto == htons(ETH_P_IP) || + key->n_proto == htons(ETH_P_IPV6)) { + flow->l4_key.ip_proto = key->ip_proto; + flow->l4_mask.ip_proto = mask->ip_proto; + } + } + + if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS); + struct flow_dissector_key_eth_addrs *mask = + GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS); + + flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS; + ether_addr_copy(flow->l2_key.dmac, key->dst); + ether_addr_copy(flow->l2_mask.dmac, mask->dst); + ether_addr_copy(flow->l2_key.smac, key->src); + ether_addr_copy(flow->l2_mask.smac, mask->src); + } + + if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN); + struct flow_dissector_key_vlan *mask = + GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN); + + flow->l2_key.inner_vlan_tci = + cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority)); + flow->l2_mask.inner_vlan_tci = + cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority))); + flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q); + flow->l2_mask.inner_vlan_tpid = htons(0xffff); + flow->l2_key.num_vlans = 1; + } + + if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + struct flow_dissector_key_ipv4_addrs *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS); + struct flow_dissector_key_ipv4_addrs *mask = + GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS); + + flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS; + flow->l3_key.ipv4.daddr.s_addr = key->dst; + flow->l3_mask.ipv4.daddr.s_addr = mask->dst; + flow->l3_key.ipv4.saddr.s_addr = key->src; + flow->l3_mask.ipv4.saddr.s_addr = mask->src; + } else if (dissector_uses_key(dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_dissector_key_ipv6_addrs *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS); + struct flow_dissector_key_ipv6_addrs *mask = + GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS); + + flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS; + flow->l3_key.ipv6.daddr = key->dst; + flow->l3_mask.ipv6.daddr = mask->dst; + flow->l3_key.ipv6.saddr = key->src; + flow->l3_mask.ipv6.saddr = mask->src; + } + + if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_dissector_key_ports *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS); + struct flow_dissector_key_ports *mask = + GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS); + + flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS; + flow->l4_key.ports.dport = key->dst; + flow->l4_mask.ports.dport = mask->dst; + flow->l4_key.ports.sport = key->src; + flow->l4_mask.ports.sport = mask->src; + } + + if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) { + struct flow_dissector_key_icmp *key = + GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP); + struct flow_dissector_key_icmp *mask = + GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP); + + flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP; + flow->l4_key.icmp.type = key->type; + flow->l4_key.icmp.code = key->code; + flow->l4_mask.icmp.type = mask->type; + flow->l4_mask.icmp.code = mask->code; + } + + return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts); +} + +static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle) +{ + struct hwrm_cfa_flow_free_input req = { 0 }; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_FREE, -1, -1); + req.flow_handle = flow_handle; + + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + netdev_info(bp->dev, "Error: %s: flow_handle=0x%x rc=%d", + __func__, flow_handle, rc); + return rc; +} + +static int ipv6_mask_len(struct in6_addr *mask) +{ + int mask_len = 0, i; + + for (i = 0; i < 4; i++) + mask_len += inet_mask_len(mask->s6_addr32[i]); + + return mask_len; +} + +static bool is_wildcard(void *mask, int len) +{ + const u8 *p = mask; + int i; + + for (i = 0; i < len; i++) { + if (p[i] != 0) + return false; + } + return true; +} + +static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow, + __le16 ref_flow_handle, __le16 *flow_handle) +{ + struct hwrm_cfa_flow_alloc_output *resp = bp->hwrm_cmd_resp_addr; + struct bnxt_tc_actions *actions = &flow->actions; + struct bnxt_tc_l3_key *l3_mask = &flow->l3_mask; + struct bnxt_tc_l3_key *l3_key = &flow->l3_key; + struct hwrm_cfa_flow_alloc_input req = { 0 }; + u16 flow_flags = 0, action_flags = 0; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_ALLOC, -1, -1); + + req.src_fid = cpu_to_le16(flow->src_fid); + req.ref_flow_handle = ref_flow_handle; + req.ethertype = flow->l2_key.ether_type; + req.ip_proto = flow->l4_key.ip_proto; + + if (flow->flags & BNXT_TC_FLOW_FLAGS_ETH_ADDRS) { + memcpy(req.dmac, flow->l2_key.dmac, ETH_ALEN); + memcpy(req.smac, flow->l2_key.smac, ETH_ALEN); + } + + if (flow->l2_key.num_vlans > 0) { + flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE; + /* FW expects the inner_vlan_tci value to be set + * in outer_vlan_tci when num_vlans is 1 (which is + * always the case in TC.) + */ + req.outer_vlan_tci = flow->l2_key.inner_vlan_tci; + } + + /* If all IP and L4 fields are wildcarded then this is an L2 flow */ + if (is_wildcard(&l3_mask, sizeof(l3_mask)) && + is_wildcard(&flow->l4_mask, sizeof(flow->l4_mask))) { + flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2; + } else { + flow_flags |= flow->l2_key.ether_type == htons(ETH_P_IP) ? + CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4 : + CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6; + + if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV4_ADDRS) { + req.ip_dst[0] = l3_key->ipv4.daddr.s_addr; + req.ip_dst_mask_len = + inet_mask_len(l3_mask->ipv4.daddr.s_addr); + req.ip_src[0] = l3_key->ipv4.saddr.s_addr; + req.ip_src_mask_len = + inet_mask_len(l3_mask->ipv4.saddr.s_addr); + } else if (flow->flags & BNXT_TC_FLOW_FLAGS_IPV6_ADDRS) { + memcpy(req.ip_dst, l3_key->ipv6.daddr.s6_addr32, + sizeof(req.ip_dst)); + req.ip_dst_mask_len = + ipv6_mask_len(&l3_mask->ipv6.daddr); + memcpy(req.ip_src, l3_key->ipv6.saddr.s6_addr32, + sizeof(req.ip_src)); + req.ip_src_mask_len = + ipv6_mask_len(&l3_mask->ipv6.saddr); + } + } + + if (flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) { + req.l4_src_port = flow->l4_key.ports.sport; + req.l4_src_port_mask = flow->l4_mask.ports.sport; + req.l4_dst_port = flow->l4_key.ports.dport; + req.l4_dst_port_mask = flow->l4_mask.ports.dport; + } else if (flow->flags & BNXT_TC_FLOW_FLAGS_ICMP) { + /* l4 ports serve as type/code when ip_proto is ICMP */ + req.l4_src_port = htons(flow->l4_key.icmp.type); + req.l4_src_port_mask = htons(flow->l4_mask.icmp.type); + req.l4_dst_port = htons(flow->l4_key.icmp.code); + req.l4_dst_port_mask = htons(flow->l4_mask.icmp.code); + } + req.flags = cpu_to_le16(flow_flags); + + if (actions->flags & BNXT_TC_ACTION_FLAG_DROP) { + action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP; + } else { + if (actions->flags & BNXT_TC_ACTION_FLAG_FWD) { + action_flags |= CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD; + req.dst_fid = cpu_to_le16(actions->dst_fid); + } + if (actions->flags & BNXT_TC_ACTION_FLAG_PUSH_VLAN) { + action_flags |= + CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE; + req.l2_rewrite_vlan_tpid = actions->push_vlan_tpid; + req.l2_rewrite_vlan_tci = actions->push_vlan_tci; + memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN); + memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN); + } + if (actions->flags & BNXT_TC_ACTION_FLAG_POP_VLAN) { + action_flags |= + CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE; + /* Rewrite config with tpid = 0 implies vlan pop */ + req.l2_rewrite_vlan_tpid = 0; + memcpy(&req.l2_rewrite_dmac, &req.dmac, ETH_ALEN); + memcpy(&req.l2_rewrite_smac, &req.smac, ETH_ALEN); + } + } + req.action_flags = cpu_to_le16(action_flags); + + mutex_lock(&bp->hwrm_cmd_lock); + + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) + *flow_handle = resp->flow_handle; + + mutex_unlock(&bp->hwrm_cmd_lock); + + return rc; +} + +/* Add val to accum while handling a possible wraparound + * of val. Eventhough val is of type u64, its actual width + * is denoted by mask and will wrap-around beyond that width. + */ +static void accumulate_val(u64 *accum, u64 val, u64 mask) +{ +#define low_bits(x, mask) ((x) & (mask)) +#define high_bits(x, mask) ((x) & ~(mask)) + bool wrapped = val < low_bits(*accum, mask); + + *accum = high_bits(*accum, mask) + val; + if (wrapped) + *accum += (mask + 1); +} + +/* The HW counters' width is much less than 64bits. + * Handle possible wrap-around while updating the stat counters + */ +static void bnxt_flow_stats_fix_wraparound(struct bnxt_tc_info *tc_info, + struct bnxt_tc_flow_stats *stats, + struct bnxt_tc_flow_stats *hw_stats) +{ + accumulate_val(&stats->bytes, hw_stats->bytes, tc_info->bytes_mask); + accumulate_val(&stats->packets, hw_stats->packets, + tc_info->packets_mask); +} + +/* Fix possible wraparound of the stats queried from HW, calculate + * the delta from prev_stats, and also update the prev_stats. + * The HW flow stats are fetched under the hwrm_cmd_lock mutex. + * This routine is best called while under the mutex so that the + * stats processing happens atomically. + */ +static void bnxt_flow_stats_calc(struct bnxt_tc_info *tc_info, + struct bnxt_tc_flow *flow, + struct bnxt_tc_flow_stats *stats) +{ + struct bnxt_tc_flow_stats *acc_stats, *prev_stats; + + acc_stats = &flow->stats; + bnxt_flow_stats_fix_wraparound(tc_info, acc_stats, stats); + + prev_stats = &flow->prev_stats; + stats->bytes = acc_stats->bytes - prev_stats->bytes; + stats->packets = acc_stats->packets - prev_stats->packets; + *prev_stats = *acc_stats; +} + +static int bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, + __le16 flow_handle, + struct bnxt_tc_flow *flow, + struct bnxt_tc_flow_stats *stats) +{ + struct hwrm_cfa_flow_stats_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_cfa_flow_stats_input req = { 0 }; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1); + req.num_flows = cpu_to_le16(1); + req.flow_handle_0 = flow_handle; + + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) { + stats->packets = le64_to_cpu(resp->packet_0); + stats->bytes = le64_to_cpu(resp->byte_0); + bnxt_flow_stats_calc(&bp->tc_info, flow, stats); + } else { + netdev_info(bp->dev, "error rc=%d", rc); + } + + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +static int bnxt_tc_put_l2_node(struct bnxt *bp, + struct bnxt_tc_flow_node *flow_node) +{ + struct bnxt_tc_l2_node *l2_node = flow_node->l2_node; + struct bnxt_tc_info *tc_info = &bp->tc_info; + int rc; + + /* remove flow_node from the L2 shared flow list */ + list_del(&flow_node->l2_list_node); + if (--l2_node->refcount == 0) { + rc = rhashtable_remove_fast(&tc_info->l2_table, &l2_node->node, + tc_info->l2_ht_params); + if (rc) + netdev_err(bp->dev, + "Error: %s: rhashtable_remove_fast: %d", + __func__, rc); + kfree_rcu(l2_node, rcu); + } + return 0; +} + +static struct bnxt_tc_l2_node * +bnxt_tc_get_l2_node(struct bnxt *bp, struct rhashtable *l2_table, + struct rhashtable_params ht_params, + struct bnxt_tc_l2_key *l2_key) +{ + struct bnxt_tc_l2_node *l2_node; + int rc; + + l2_node = rhashtable_lookup_fast(l2_table, l2_key, ht_params); + if (!l2_node) { + l2_node = kzalloc(sizeof(*l2_node), GFP_KERNEL); + if (!l2_node) { + rc = -ENOMEM; + return NULL; + } + + l2_node->key = *l2_key; + rc = rhashtable_insert_fast(l2_table, &l2_node->node, + ht_params); + if (rc) { + kfree(l2_node); + netdev_err(bp->dev, + "Error: %s: rhashtable_insert_fast: %d", + __func__, rc); + return NULL; + } + INIT_LIST_HEAD(&l2_node->common_l2_flows); + } + return l2_node; +} + +/* Get the ref_flow_handle for a flow by checking if there are any other + * flows that share the same L2 key as this flow. + */ +static int +bnxt_tc_get_ref_flow_handle(struct bnxt *bp, struct bnxt_tc_flow *flow, + struct bnxt_tc_flow_node *flow_node, + __le16 *ref_flow_handle) +{ + struct bnxt_tc_info *tc_info = &bp->tc_info; + struct bnxt_tc_flow_node *ref_flow_node; + struct bnxt_tc_l2_node *l2_node; + + l2_node = bnxt_tc_get_l2_node(bp, &tc_info->l2_table, + tc_info->l2_ht_params, + &flow->l2_key); + if (!l2_node) + return -1; + + /* If any other flow is using this l2_node, use it's flow_handle + * as the ref_flow_handle + */ + if (l2_node->refcount > 0) { + ref_flow_node = list_first_entry(&l2_node->common_l2_flows, + struct bnxt_tc_flow_node, + l2_list_node); + *ref_flow_handle = ref_flow_node->flow_handle; + } else { + *ref_flow_handle = cpu_to_le16(0xffff); + } + + /* Insert the l2_node into the flow_node so that subsequent flows + * with a matching l2 key can use the flow_handle of this flow + * as their ref_flow_handle + */ + flow_node->l2_node = l2_node; + list_add(&flow_node->l2_list_node, &l2_node->common_l2_flows); + l2_node->refcount++; + return 0; +} + +/* After the flow parsing is done, this routine is used for checking + * if there are any aspects of the flow that prevent it from being + * offloaded. + */ +static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow) +{ + /* If L4 ports are specified then ip_proto must be TCP or UDP */ + if ((flow->flags & BNXT_TC_FLOW_FLAGS_PORTS) && + (flow->l4_key.ip_proto != IPPROTO_TCP && + flow->l4_key.ip_proto != IPPROTO_UDP)) { + netdev_info(bp->dev, "Cannot offload non-TCP/UDP (%d) ports", + flow->l4_key.ip_proto); + return false; + } + + return true; +} + +static int __bnxt_tc_del_flow(struct bnxt *bp, + struct bnxt_tc_flow_node *flow_node) +{ + struct bnxt_tc_info *tc_info = &bp->tc_info; + int rc; + + /* send HWRM cmd to free the flow-id */ + bnxt_hwrm_cfa_flow_free(bp, flow_node->flow_handle); + + mutex_lock(&tc_info->lock); + + /* release reference to l2 node */ + bnxt_tc_put_l2_node(bp, flow_node); + + mutex_unlock(&tc_info->lock); + + rc = rhashtable_remove_fast(&tc_info->flow_table, &flow_node->node, + tc_info->flow_ht_params); + if (rc) + netdev_err(bp->dev, "Error: %s: rhashtable_remove_fast rc=%d", + __func__, rc); + + kfree_rcu(flow_node, rcu); + return 0; +} + +/* Add a new flow or replace an existing flow. + * Notes on locking: + * There are essentially two critical sections here. + * 1. while adding a new flow + * a) lookup l2-key + * b) issue HWRM cmd and get flow_handle + * c) link l2-key with flow + * 2. while deleting a flow + * a) unlinking l2-key from flow + * A lock is needed to protect these two critical sections. + * + * The hash-tables are already protected by the rhashtable API. + */ +static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid, + struct tc_cls_flower_offload *tc_flow_cmd) +{ + struct bnxt_tc_flow_node *new_node, *old_node; + struct bnxt_tc_info *tc_info = &bp->tc_info; + struct bnxt_tc_flow *flow; + __le16 ref_flow_handle; + int rc; + + /* allocate memory for the new flow and it's node */ + new_node = kzalloc(sizeof(*new_node), GFP_KERNEL); + if (!new_node) { + rc = -ENOMEM; + goto done; + } + new_node->cookie = tc_flow_cmd->cookie; + flow = &new_node->flow; + + rc = bnxt_tc_parse_flow(bp, tc_flow_cmd, flow); + if (rc) + goto free_node; + flow->src_fid = src_fid; + + if (!bnxt_tc_can_offload(bp, flow)) { + rc = -ENOSPC; + goto free_node; + } + + /* If a flow exists with the same cookie, delete it */ + old_node = rhashtable_lookup_fast(&tc_info->flow_table, + &tc_flow_cmd->cookie, + tc_info->flow_ht_params); + if (old_node) + __bnxt_tc_del_flow(bp, old_node); + + /* Check if the L2 part of the flow has been offloaded already. + * If so, bump up it's refcnt and get it's reference handle. + */ + mutex_lock(&tc_info->lock); + rc = bnxt_tc_get_ref_flow_handle(bp, flow, new_node, &ref_flow_handle); + if (rc) + goto unlock; + + /* send HWRM cmd to alloc the flow */ + rc = bnxt_hwrm_cfa_flow_alloc(bp, flow, ref_flow_handle, + &new_node->flow_handle); + if (rc) + goto put_l2; + + /* add new flow to flow-table */ + rc = rhashtable_insert_fast(&tc_info->flow_table, &new_node->node, + tc_info->flow_ht_params); + if (rc) + goto hwrm_flow_free; + + mutex_unlock(&tc_info->lock); + return 0; + +hwrm_flow_free: + bnxt_hwrm_cfa_flow_free(bp, new_node->flow_handle); +put_l2: + bnxt_tc_put_l2_node(bp, new_node); +unlock: + mutex_unlock(&tc_info->lock); +free_node: + kfree(new_node); +done: + netdev_err(bp->dev, "Error: %s: cookie=0x%lx error=%d", + __func__, tc_flow_cmd->cookie, rc); + return rc; +} + +static int bnxt_tc_del_flow(struct bnxt *bp, + struct tc_cls_flower_offload *tc_flow_cmd) +{ + struct bnxt_tc_info *tc_info = &bp->tc_info; + struct bnxt_tc_flow_node *flow_node; + + flow_node = rhashtable_lookup_fast(&tc_info->flow_table, + &tc_flow_cmd->cookie, + tc_info->flow_ht_params); + if (!flow_node) { + netdev_info(bp->dev, "ERROR: no flow_node for cookie %lx", + tc_flow_cmd->cookie); + return -EINVAL; + } + + return __bnxt_tc_del_flow(bp, flow_node); +} + +static int bnxt_tc_get_flow_stats(struct bnxt *bp, + struct tc_cls_flower_offload *tc_flow_cmd) +{ + struct bnxt_tc_info *tc_info = &bp->tc_info; + struct bnxt_tc_flow_node *flow_node; + struct bnxt_tc_flow_stats stats; + int rc; + + flow_node = rhashtable_lookup_fast(&tc_info->flow_table, + &tc_flow_cmd->cookie, + tc_info->flow_ht_params); + if (!flow_node) { + netdev_info(bp->dev, "Error: no flow_node for cookie %lx", + tc_flow_cmd->cookie); + return -1; + } + + rc = bnxt_hwrm_cfa_flow_stats_get(bp, flow_node->flow_handle, + &flow_node->flow, &stats); + if (rc) + return rc; + + tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets, 0); + return 0; +} + +int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid, + struct tc_cls_flower_offload *cls_flower) +{ + int rc = 0; + + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + rc = bnxt_tc_add_flow(bp, src_fid, cls_flower); + break; + + case TC_CLSFLOWER_DESTROY: + rc = bnxt_tc_del_flow(bp, cls_flower); + break; + + case TC_CLSFLOWER_STATS: + rc = bnxt_tc_get_flow_stats(bp, cls_flower); + break; + } + return rc; +} + +static const struct rhashtable_params bnxt_tc_flow_ht_params = { + .head_offset = offsetof(struct bnxt_tc_flow_node, node), + .key_offset = offsetof(struct bnxt_tc_flow_node, cookie), + .key_len = sizeof(((struct bnxt_tc_flow_node *)0)->cookie), + .automatic_shrinking = true +}; + +static const struct rhashtable_params bnxt_tc_l2_ht_params = { + .head_offset = offsetof(struct bnxt_tc_l2_node, node), + .key_offset = offsetof(struct bnxt_tc_l2_node, key), + .key_len = BNXT_TC_L2_KEY_LEN, + .automatic_shrinking = true +}; + +/* convert counter width in bits to a mask */ +#define mask(width) ((u64)~0 >> (64 - (width))) + +int bnxt_init_tc(struct bnxt *bp) +{ + struct bnxt_tc_info *tc_info = &bp->tc_info; + int rc; + + if (bp->hwrm_spec_code < 0x10800) { + netdev_warn(bp->dev, + "Firmware does not support TC flower offload.\n"); + return -ENOTSUPP; + } + mutex_init(&tc_info->lock); + + /* Counter widths are programmed by FW */ + tc_info->bytes_mask = mask(36); + tc_info->packets_mask = mask(28); + + tc_info->flow_ht_params = bnxt_tc_flow_ht_params; + rc = rhashtable_init(&tc_info->flow_table, &tc_info->flow_ht_params); + if (rc) + return rc; + + tc_info->l2_ht_params = bnxt_tc_l2_ht_params; + rc = rhashtable_init(&tc_info->l2_table, &tc_info->l2_ht_params); + if (rc) + goto destroy_flow_table; + + tc_info->enabled = true; + bp->dev->hw_features |= NETIF_F_HW_TC; + bp->dev->features |= NETIF_F_HW_TC; + return 0; + +destroy_flow_table: + rhashtable_destroy(&tc_info->flow_table); + return rc; +} + +void bnxt_shutdown_tc(struct bnxt *bp) +{ + struct bnxt_tc_info *tc_info = &bp->tc_info; + + if (!tc_info->enabled) + return; + + rhashtable_destroy(&tc_info->flow_table); + rhashtable_destroy(&tc_info->l2_table); +} + +#else +#endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h new file mode 100644 index 000000000000..6c4c1ed279ef --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h @@ -0,0 +1,158 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2017 Broadcom Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#ifndef BNXT_TC_H +#define BNXT_TC_H + +#ifdef CONFIG_BNXT_FLOWER_OFFLOAD + +/* Structs used for storing the filter/actions of the TC cmd. + */ +struct bnxt_tc_l2_key { + u8 dmac[ETH_ALEN]; + u8 smac[ETH_ALEN]; + __be16 inner_vlan_tpid; + __be16 inner_vlan_tci; + __be16 ether_type; + u8 num_vlans; +}; + +struct bnxt_tc_l3_key { + union { + struct { + struct in_addr daddr; + struct in_addr saddr; + } ipv4; + struct { + struct in6_addr daddr; + struct in6_addr saddr; + } ipv6; + }; +}; + +struct bnxt_tc_l4_key { + u8 ip_proto; + union { + struct { + __be16 sport; + __be16 dport; + } ports; + struct { + u8 type; + u8 code; + } icmp; + }; +}; + +struct bnxt_tc_actions { + u32 flags; +#define BNXT_TC_ACTION_FLAG_FWD BIT(0) +#define BNXT_TC_ACTION_FLAG_FWD_VXLAN BIT(1) +#define BNXT_TC_ACTION_FLAG_PUSH_VLAN BIT(3) +#define BNXT_TC_ACTION_FLAG_POP_VLAN BIT(4) +#define BNXT_TC_ACTION_FLAG_DROP BIT(5) + + u16 dst_fid; + struct net_device *dst_dev; + __be16 push_vlan_tpid; + __be16 push_vlan_tci; +}; + +struct bnxt_tc_flow_stats { + u64 packets; + u64 bytes; +}; + +struct bnxt_tc_flow { + u32 flags; +#define BNXT_TC_FLOW_FLAGS_ETH_ADDRS BIT(1) +#define BNXT_TC_FLOW_FLAGS_IPV4_ADDRS BIT(2) +#define BNXT_TC_FLOW_FLAGS_IPV6_ADDRS BIT(3) +#define BNXT_TC_FLOW_FLAGS_PORTS BIT(4) +#define BNXT_TC_FLOW_FLAGS_ICMP BIT(5) + + /* flow applicable to pkts ingressing on this fid */ + u16 src_fid; + struct bnxt_tc_l2_key l2_key; + struct bnxt_tc_l2_key l2_mask; + struct bnxt_tc_l3_key l3_key; + struct bnxt_tc_l3_key l3_mask; + struct bnxt_tc_l4_key l4_key; + struct bnxt_tc_l4_key l4_mask; + + struct bnxt_tc_actions actions; + + /* updated stats accounting for hw-counter wrap-around */ + struct bnxt_tc_flow_stats stats; + /* previous snap-shot of stats */ + struct bnxt_tc_flow_stats prev_stats; + unsigned long lastused; /* jiffies */ +}; + +/* L2 hash table + * This data-struct is used for L2-flow table. + * The L2 part of a flow is stored in a hash table. + * A flow that shares the same L2 key/mask with an + * already existing flow must refer to it's flow handle. + */ +struct bnxt_tc_l2_node { + /* hash key: first 16b of key */ +#define BNXT_TC_L2_KEY_LEN 16 + struct bnxt_tc_l2_key key; + struct rhash_head node; + + /* a linked list of flows that share the same l2 key */ + struct list_head common_l2_flows; + + /* number of flows sharing the l2 key */ + u16 refcount; + + struct rcu_head rcu; +}; + +struct bnxt_tc_flow_node { + /* hash key: provided by TC */ + unsigned long cookie; + struct rhash_head node; + + struct bnxt_tc_flow flow; + + __le16 flow_handle; + + /* L2 node in l2 hashtable that shares flow's l2 key */ + struct bnxt_tc_l2_node *l2_node; + /* for the shared_flows list maintained in l2_node */ + struct list_head l2_list_node; + + struct rcu_head rcu; +}; + +int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid, + struct tc_cls_flower_offload *cls_flower); +int bnxt_init_tc(struct bnxt *bp); +void bnxt_shutdown_tc(struct bnxt *bp); + +#else /* CONFIG_BNXT_FLOWER_OFFLOAD */ + +static inline int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid, + struct tc_cls_flower_offload *cls_flower) +{ + return -EOPNOTSUPP; +} + +static inline int bnxt_init_tc(struct bnxt *bp) +{ + return 0; +} + +static inline void bnxt_shutdown_tc(struct bnxt *bp) +{ +} +#endif /* CONFIG_BNXT_FLOWER_OFFLOAD */ +#endif /* BNXT_TC_H */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c new file mode 100644 index 000000000000..e75db04c6cdc --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -0,0 +1,513 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2016-2017 Broadcom Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/jhash.h> +#include <net/pkt_cls.h> + +#include "bnxt_hsi.h" +#include "bnxt.h" +#include "bnxt_vfr.h" +#include "bnxt_tc.h" + +#ifdef CONFIG_BNXT_SRIOV + +#define CFA_HANDLE_INVALID 0xffff +#define VF_IDX_INVALID 0xffff + +static int hwrm_cfa_vfr_alloc(struct bnxt *bp, u16 vf_idx, + u16 *tx_cfa_action, u16 *rx_cfa_code) +{ + struct hwrm_cfa_vfr_alloc_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_cfa_vfr_alloc_input req = { 0 }; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_ALLOC, -1, -1); + req.vf_id = cpu_to_le16(vf_idx); + sprintf(req.vfr_name, "vfr%d", vf_idx); + + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) { + *tx_cfa_action = le16_to_cpu(resp->tx_cfa_action); + *rx_cfa_code = le16_to_cpu(resp->rx_cfa_code); + netdev_dbg(bp->dev, "tx_cfa_action=0x%x, rx_cfa_code=0x%x", + *tx_cfa_action, *rx_cfa_code); + } else { + netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + } + + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +static int hwrm_cfa_vfr_free(struct bnxt *bp, u16 vf_idx) +{ + struct hwrm_cfa_vfr_free_input req = { 0 }; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_VFR_FREE, -1, -1); + sprintf(req.vfr_name, "vfr%d", vf_idx); + + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + netdev_info(bp->dev, "%s error rc=%d", __func__, rc); + return rc; +} + +static int bnxt_vf_rep_open(struct net_device *dev) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(dev); + struct bnxt *bp = vf_rep->bp; + + /* Enable link and TX only if the parent PF is open. */ + if (netif_running(bp->dev)) { + netif_carrier_on(dev); + netif_tx_start_all_queues(dev); + } + return 0; +} + +static int bnxt_vf_rep_close(struct net_device *dev) +{ + netif_carrier_off(dev); + netif_tx_disable(dev); + + return 0; +} + +static netdev_tx_t bnxt_vf_rep_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(dev); + int rc, len = skb->len; + + skb_dst_drop(skb); + dst_hold((struct dst_entry *)vf_rep->dst); + skb_dst_set(skb, (struct dst_entry *)vf_rep->dst); + skb->dev = vf_rep->dst->u.port_info.lower_dev; + + rc = dev_queue_xmit(skb); + if (!rc) { + vf_rep->tx_stats.packets++; + vf_rep->tx_stats.bytes += len; + } + return rc; +} + +static void +bnxt_vf_rep_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(dev); + + stats->rx_packets = vf_rep->rx_stats.packets; + stats->rx_bytes = vf_rep->rx_stats.bytes; + stats->tx_packets = vf_rep->tx_stats.packets; + stats->tx_bytes = vf_rep->tx_stats.bytes; +} + +static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(dev); + struct bnxt *bp = vf_rep->bp; + int vf_fid = bp->pf.vf[vf_rep->vf_idx].fw_fid; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return bnxt_tc_setup_flower(bp, vf_fid, type_data); + default: + return -EOPNOTSUPP; + } +} + +struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code) +{ + u16 vf_idx; + + if (cfa_code && bp->cfa_code_map && BNXT_PF(bp)) { + vf_idx = bp->cfa_code_map[cfa_code]; + if (vf_idx != VF_IDX_INVALID) + return bp->vf_reps[vf_idx]->dev; + } + return NULL; +} + +void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(skb->dev); + struct bnxt_vf_rep_stats *rx_stats; + + rx_stats = &vf_rep->rx_stats; + vf_rep->rx_stats.bytes += skb->len; + vf_rep->rx_stats.packets++; + + netif_receive_skb(skb); +} + +static int bnxt_vf_rep_get_phys_port_name(struct net_device *dev, char *buf, + size_t len) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(dev); + struct pci_dev *pf_pdev = vf_rep->bp->pdev; + int rc; + + rc = snprintf(buf, len, "pf%dvf%d", PCI_FUNC(pf_pdev->devfn), + vf_rep->vf_idx); + if (rc >= len) + return -EOPNOTSUPP; + return 0; +} + +static void bnxt_vf_rep_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver)); + strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version)); +} + +static int bnxt_vf_rep_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(dev); + + /* as only PORT_PARENT_ID is supported currently use common code + * between PF and VF-rep for now. + */ + return bnxt_port_attr_get(vf_rep->bp, attr); +} + +static const struct switchdev_ops bnxt_vf_rep_switchdev_ops = { + .switchdev_port_attr_get = bnxt_vf_rep_port_attr_get +}; + +static const struct ethtool_ops bnxt_vf_rep_ethtool_ops = { + .get_drvinfo = bnxt_vf_rep_get_drvinfo +}; + +static const struct net_device_ops bnxt_vf_rep_netdev_ops = { + .ndo_open = bnxt_vf_rep_open, + .ndo_stop = bnxt_vf_rep_close, + .ndo_start_xmit = bnxt_vf_rep_xmit, + .ndo_get_stats64 = bnxt_vf_rep_get_stats64, + .ndo_setup_tc = bnxt_vf_rep_setup_tc, + .ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name +}; + +/* Called when the parent PF interface is closed: + * As the mode transition from SWITCHDEV to LEGACY + * happens under the rtnl_lock() this routine is safe + * under the rtnl_lock() + */ +void bnxt_vf_reps_close(struct bnxt *bp) +{ + struct bnxt_vf_rep *vf_rep; + u16 num_vfs, i; + + if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) + return; + + num_vfs = pci_num_vf(bp->pdev); + for (i = 0; i < num_vfs; i++) { + vf_rep = bp->vf_reps[i]; + if (netif_running(vf_rep->dev)) + bnxt_vf_rep_close(vf_rep->dev); + } +} + +/* Called when the parent PF interface is opened (re-opened): + * As the mode transition from SWITCHDEV to LEGACY + * happen under the rtnl_lock() this routine is safe + * under the rtnl_lock() + */ +void bnxt_vf_reps_open(struct bnxt *bp) +{ + int i; + + if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) + return; + + for (i = 0; i < pci_num_vf(bp->pdev); i++) + bnxt_vf_rep_open(bp->vf_reps[i]->dev); +} + +static void __bnxt_vf_reps_destroy(struct bnxt *bp) +{ + u16 num_vfs = pci_num_vf(bp->pdev); + struct bnxt_vf_rep *vf_rep; + int i; + + for (i = 0; i < num_vfs; i++) { + vf_rep = bp->vf_reps[i]; + if (vf_rep) { + dst_release((struct dst_entry *)vf_rep->dst); + + if (vf_rep->tx_cfa_action != CFA_HANDLE_INVALID) + hwrm_cfa_vfr_free(bp, vf_rep->vf_idx); + + if (vf_rep->dev) { + /* if register_netdev failed, then netdev_ops + * would have been set to NULL + */ + if (vf_rep->dev->netdev_ops) + unregister_netdev(vf_rep->dev); + free_netdev(vf_rep->dev); + } + } + } + + kfree(bp->vf_reps); + bp->vf_reps = NULL; +} + +void bnxt_vf_reps_destroy(struct bnxt *bp) +{ + bool closed = false; + + if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) + return; + + if (!bp->vf_reps) + return; + + /* Ensure that parent PF's and VF-reps' RX/TX has been quiesced + * before proceeding with VF-rep cleanup. + */ + rtnl_lock(); + if (netif_running(bp->dev)) { + bnxt_close_nic(bp, false, false); + closed = true; + } + /* un-publish cfa_code_map so that RX path can't see it anymore */ + kfree(bp->cfa_code_map); + bp->cfa_code_map = NULL; + bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY; + + if (closed) + bnxt_open_nic(bp, false, false); + rtnl_unlock(); + + /* Need to call vf_reps_destroy() outside of rntl_lock + * as unregister_netdev takes rtnl_lock + */ + __bnxt_vf_reps_destroy(bp); +} + +/* Use the OUI of the PF's perm addr and report the same mac addr + * for the same VF-rep each time + */ +static void bnxt_vf_rep_eth_addr_gen(u8 *src_mac, u16 vf_idx, u8 *mac) +{ + u32 addr; + + ether_addr_copy(mac, src_mac); + + addr = jhash(src_mac, ETH_ALEN, 0) + vf_idx; + mac[3] = (u8)(addr & 0xFF); + mac[4] = (u8)((addr >> 8) & 0xFF); + mac[5] = (u8)((addr >> 16) & 0xFF); +} + +static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep, + struct net_device *dev) +{ + struct net_device *pf_dev = bp->dev; + + dev->netdev_ops = &bnxt_vf_rep_netdev_ops; + dev->ethtool_ops = &bnxt_vf_rep_ethtool_ops; + SWITCHDEV_SET_OPS(dev, &bnxt_vf_rep_switchdev_ops); + /* Just inherit all the featues of the parent PF as the VF-R + * uses the RX/TX rings of the parent PF + */ + dev->hw_features = pf_dev->hw_features; + dev->gso_partial_features = pf_dev->gso_partial_features; + dev->vlan_features = pf_dev->vlan_features; + dev->hw_enc_features = pf_dev->hw_enc_features; + dev->features |= pf_dev->features; + bnxt_vf_rep_eth_addr_gen(bp->pf.mac_addr, vf_rep->vf_idx, + dev->perm_addr); + ether_addr_copy(dev->dev_addr, dev->perm_addr); +} + +static int bnxt_vf_reps_create(struct bnxt *bp) +{ + u16 *cfa_code_map = NULL, num_vfs = pci_num_vf(bp->pdev); + struct bnxt_vf_rep *vf_rep; + struct net_device *dev; + int rc, i; + + bp->vf_reps = kcalloc(num_vfs, sizeof(vf_rep), GFP_KERNEL); + if (!bp->vf_reps) + return -ENOMEM; + + /* storage for cfa_code to vf-idx mapping */ + cfa_code_map = kmalloc(sizeof(*bp->cfa_code_map) * MAX_CFA_CODE, + GFP_KERNEL); + if (!cfa_code_map) { + rc = -ENOMEM; + goto err; + } + for (i = 0; i < MAX_CFA_CODE; i++) + cfa_code_map[i] = VF_IDX_INVALID; + + for (i = 0; i < num_vfs; i++) { + dev = alloc_etherdev(sizeof(*vf_rep)); + if (!dev) { + rc = -ENOMEM; + goto err; + } + + vf_rep = netdev_priv(dev); + bp->vf_reps[i] = vf_rep; + vf_rep->dev = dev; + vf_rep->bp = bp; + vf_rep->vf_idx = i; + vf_rep->tx_cfa_action = CFA_HANDLE_INVALID; + + /* get cfa handles from FW */ + rc = hwrm_cfa_vfr_alloc(bp, vf_rep->vf_idx, + &vf_rep->tx_cfa_action, + &vf_rep->rx_cfa_code); + if (rc) { + rc = -ENOLINK; + goto err; + } + cfa_code_map[vf_rep->rx_cfa_code] = vf_rep->vf_idx; + + vf_rep->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, + GFP_KERNEL); + if (!vf_rep->dst) { + rc = -ENOMEM; + goto err; + } + /* only cfa_action is needed to mux a packet while TXing */ + vf_rep->dst->u.port_info.port_id = vf_rep->tx_cfa_action; + vf_rep->dst->u.port_info.lower_dev = bp->dev; + + bnxt_vf_rep_netdev_init(bp, vf_rep, dev); + rc = register_netdev(dev); + if (rc) { + /* no need for unregister_netdev in cleanup */ + dev->netdev_ops = NULL; + goto err; + } + } + + /* publish cfa_code_map only after all VF-reps have been initialized */ + bp->cfa_code_map = cfa_code_map; + bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV; + netif_keep_dst(bp->dev); + return 0; + +err: + netdev_info(bp->dev, "%s error=%d", __func__, rc); + kfree(cfa_code_map); + __bnxt_vf_reps_destroy(bp); + return rc; +} + +/* Devlink related routines */ +static int bnxt_dl_eswitch_mode_get(struct devlink *devlink, u16 *mode) +{ + struct bnxt *bp = bnxt_get_bp_from_dl(devlink); + + *mode = bp->eswitch_mode; + return 0; +} + +static int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode) +{ + struct bnxt *bp = bnxt_get_bp_from_dl(devlink); + int rc = 0; + + mutex_lock(&bp->sriov_lock); + if (bp->eswitch_mode == mode) { + netdev_info(bp->dev, "already in %s eswitch mode", + mode == DEVLINK_ESWITCH_MODE_LEGACY ? + "legacy" : "switchdev"); + rc = -EINVAL; + goto done; + } + + switch (mode) { + case DEVLINK_ESWITCH_MODE_LEGACY: + bnxt_vf_reps_destroy(bp); + break; + + case DEVLINK_ESWITCH_MODE_SWITCHDEV: + if (pci_num_vf(bp->pdev) == 0) { + netdev_info(bp->dev, + "Enable VFs before setting switchdev mode"); + rc = -EPERM; + goto done; + } + rc = bnxt_vf_reps_create(bp); + break; + + default: + rc = -EINVAL; + goto done; + } +done: + mutex_unlock(&bp->sriov_lock); + return rc; +} + +static const struct devlink_ops bnxt_dl_ops = { + .eswitch_mode_set = bnxt_dl_eswitch_mode_set, + .eswitch_mode_get = bnxt_dl_eswitch_mode_get +}; + +int bnxt_dl_register(struct bnxt *bp) +{ + struct devlink *dl; + int rc; + + if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV)) + return 0; + + if (bp->hwrm_spec_code < 0x10800) { + netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n"); + return -ENOTSUPP; + } + + dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl)); + if (!dl) { + netdev_warn(bp->dev, "devlink_alloc failed"); + return -ENOMEM; + } + + bnxt_link_bp_to_dl(bp, dl); + bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY; + rc = devlink_register(dl, &bp->pdev->dev); + if (rc) { + bnxt_link_bp_to_dl(bp, NULL); + devlink_free(dl); + netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc); + return rc; + } + + return 0; +} + +void bnxt_dl_unregister(struct bnxt *bp) +{ + struct devlink *dl = bp->dl; + + if (!dl) + return; + + devlink_unregister(dl); + devlink_free(dl); +} + +#endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h new file mode 100644 index 000000000000..7787cd24606a --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.h @@ -0,0 +1,89 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2016-2017 Broadcom Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#ifndef BNXT_VFR_H +#define BNXT_VFR_H + +#ifdef CONFIG_BNXT_SRIOV + +#define MAX_CFA_CODE 65536 + +/* Struct to hold housekeeping info needed by devlink interface */ +struct bnxt_dl { + struct bnxt *bp; /* back ptr to the controlling dev */ +}; + +static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl) +{ + return ((struct bnxt_dl *)devlink_priv(dl))->bp; +} + +/* To clear devlink pointer from bp, pass NULL dl */ +static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) +{ + bp->dl = dl; + + /* add a back pointer in dl to bp */ + if (dl) { + struct bnxt_dl *bp_dl = devlink_priv(dl); + + bp_dl->bp = bp; + } +} + +int bnxt_dl_register(struct bnxt *bp); +void bnxt_dl_unregister(struct bnxt *bp); +void bnxt_vf_reps_destroy(struct bnxt *bp); +void bnxt_vf_reps_close(struct bnxt *bp); +void bnxt_vf_reps_open(struct bnxt *bp); +void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb); +struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code); + +static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev) +{ + struct bnxt_vf_rep *vf_rep = netdev_priv(dev); + struct bnxt *bp = vf_rep->bp; + + return bp->pf.vf[vf_rep->vf_idx].fw_fid; +} + +#else + +static inline int bnxt_dl_register(struct bnxt *bp) +{ + return 0; +} + +static inline void bnxt_dl_unregister(struct bnxt *bp) +{ +} + +static inline void bnxt_vf_reps_close(struct bnxt *bp) +{ +} + +static inline void bnxt_vf_reps_open(struct bnxt *bp) +{ +} + +static inline void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb) +{ +} + +static inline struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code) +{ + return NULL; +} + +static inline u16 bnxt_vf_rep_get_fid(struct net_device *dev) +{ + return 0; +} +#endif /* CONFIG_BNXT_SRIOV */ +#endif /* BNXT_VFR_H */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 3961a6807454..d8f0c837b72c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -169,8 +169,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) tc = netdev_get_num_tc(dev); if (!tc) tc = 1; - rc = bnxt_reserve_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings, - true, tc, tx_xdp); + rc = bnxt_check_rings(bp, bp->tx_nr_rings_per_tc, bp->rx_nr_rings, + true, tc, tx_xdp); if (rc) { netdev_warn(dev, "Unable to reserve enough TX rings to support XDP.\n"); return rc; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index fea3f9a5fb2d..9cebca896913 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -72,23 +72,42 @@ #define GENET_RDMA_REG_OFF (priv->hw_params->rdma_offset + \ TOTAL_DESC * DMA_DESC_SIZE) +static inline void bcmgenet_writel(u32 value, void __iomem *offset) +{ + /* MIPS chips strapped for BE will automagically configure the + * peripheral registers for CPU-native byte order. + */ + if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + __raw_writel(value, offset); + else + writel_relaxed(value, offset); +} + +static inline u32 bcmgenet_readl(void __iomem *offset) +{ + if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + return __raw_readl(offset); + else + return readl_relaxed(offset); +} + static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv, void __iomem *d, u32 value) { - __raw_writel(value, d + DMA_DESC_LENGTH_STATUS); + bcmgenet_writel(value, d + DMA_DESC_LENGTH_STATUS); } static inline u32 dmadesc_get_length_status(struct bcmgenet_priv *priv, void __iomem *d) { - return __raw_readl(d + DMA_DESC_LENGTH_STATUS); + return bcmgenet_readl(d + DMA_DESC_LENGTH_STATUS); } static inline void dmadesc_set_addr(struct bcmgenet_priv *priv, void __iomem *d, dma_addr_t addr) { - __raw_writel(lower_32_bits(addr), d + DMA_DESC_ADDRESS_LO); + bcmgenet_writel(lower_32_bits(addr), d + DMA_DESC_ADDRESS_LO); /* Register writes to GISB bus can take couple hundred nanoseconds * and are done for each packet, save these expensive writes unless @@ -96,7 +115,7 @@ static inline void dmadesc_set_addr(struct bcmgenet_priv *priv, */ #ifdef CONFIG_PHYS_ADDR_T_64BIT if (priv->hw_params->flags & GENET_HAS_40BITS) - __raw_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI); + bcmgenet_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI); #endif } @@ -113,7 +132,7 @@ static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv, { dma_addr_t addr; - addr = __raw_readl(d + DMA_DESC_ADDRESS_LO); + addr = bcmgenet_readl(d + DMA_DESC_ADDRESS_LO); /* Register writes to GISB bus can take couple hundred nanoseconds * and are done for each packet, save these expensive writes unless @@ -121,7 +140,7 @@ static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv, */ #ifdef CONFIG_PHYS_ADDR_T_64BIT if (priv->hw_params->flags & GENET_HAS_40BITS) - addr |= (u64)__raw_readl(d + DMA_DESC_ADDRESS_HI) << 32; + addr |= (u64)bcmgenet_readl(d + DMA_DESC_ADDRESS_HI) << 32; #endif return addr; } @@ -156,8 +175,8 @@ static inline u32 bcmgenet_tbuf_ctrl_get(struct bcmgenet_priv *priv) if (GENET_IS_V1(priv)) return bcmgenet_rbuf_readl(priv, TBUF_CTRL_V1); else - return __raw_readl(priv->base + - priv->hw_params->tbuf_offset + TBUF_CTRL); + return bcmgenet_readl(priv->base + + priv->hw_params->tbuf_offset + TBUF_CTRL); } static inline void bcmgenet_tbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val) @@ -165,7 +184,7 @@ static inline void bcmgenet_tbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val) if (GENET_IS_V1(priv)) bcmgenet_rbuf_writel(priv, val, TBUF_CTRL_V1); else - __raw_writel(val, priv->base + + bcmgenet_writel(val, priv->base + priv->hw_params->tbuf_offset + TBUF_CTRL); } @@ -174,8 +193,8 @@ static inline u32 bcmgenet_bp_mc_get(struct bcmgenet_priv *priv) if (GENET_IS_V1(priv)) return bcmgenet_rbuf_readl(priv, TBUF_BP_MC_V1); else - return __raw_readl(priv->base + - priv->hw_params->tbuf_offset + TBUF_BP_MC); + return bcmgenet_readl(priv->base + + priv->hw_params->tbuf_offset + TBUF_BP_MC); } static inline void bcmgenet_bp_mc_set(struct bcmgenet_priv *priv, u32 val) @@ -183,7 +202,7 @@ static inline void bcmgenet_bp_mc_set(struct bcmgenet_priv *priv, u32 val) if (GENET_IS_V1(priv)) bcmgenet_rbuf_writel(priv, val, TBUF_BP_MC_V1); else - __raw_writel(val, priv->base + + bcmgenet_writel(val, priv->base + priv->hw_params->tbuf_offset + TBUF_BP_MC); } @@ -326,28 +345,28 @@ static inline struct bcmgenet_priv *dev_to_priv(struct device *dev) static inline u32 bcmgenet_tdma_readl(struct bcmgenet_priv *priv, enum dma_reg r) { - return __raw_readl(priv->base + GENET_TDMA_REG_OFF + - DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); + return bcmgenet_readl(priv->base + GENET_TDMA_REG_OFF + + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); } static inline void bcmgenet_tdma_writel(struct bcmgenet_priv *priv, u32 val, enum dma_reg r) { - __raw_writel(val, priv->base + GENET_TDMA_REG_OFF + + bcmgenet_writel(val, priv->base + GENET_TDMA_REG_OFF + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); } static inline u32 bcmgenet_rdma_readl(struct bcmgenet_priv *priv, enum dma_reg r) { - return __raw_readl(priv->base + GENET_RDMA_REG_OFF + - DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); + return bcmgenet_readl(priv->base + GENET_RDMA_REG_OFF + + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); } static inline void bcmgenet_rdma_writel(struct bcmgenet_priv *priv, u32 val, enum dma_reg r) { - __raw_writel(val, priv->base + GENET_RDMA_REG_OFF + + bcmgenet_writel(val, priv->base + GENET_RDMA_REG_OFF + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); } @@ -418,16 +437,16 @@ static inline u32 bcmgenet_tdma_ring_readl(struct bcmgenet_priv *priv, unsigned int ring, enum dma_ring_reg r) { - return __raw_readl(priv->base + GENET_TDMA_REG_OFF + - (DMA_RING_SIZE * ring) + - genet_dma_ring_regs[r]); + return bcmgenet_readl(priv->base + GENET_TDMA_REG_OFF + + (DMA_RING_SIZE * ring) + + genet_dma_ring_regs[r]); } static inline void bcmgenet_tdma_ring_writel(struct bcmgenet_priv *priv, unsigned int ring, u32 val, enum dma_ring_reg r) { - __raw_writel(val, priv->base + GENET_TDMA_REG_OFF + + bcmgenet_writel(val, priv->base + GENET_TDMA_REG_OFF + (DMA_RING_SIZE * ring) + genet_dma_ring_regs[r]); } @@ -436,16 +455,16 @@ static inline u32 bcmgenet_rdma_ring_readl(struct bcmgenet_priv *priv, unsigned int ring, enum dma_ring_reg r) { - return __raw_readl(priv->base + GENET_RDMA_REG_OFF + - (DMA_RING_SIZE * ring) + - genet_dma_ring_regs[r]); + return bcmgenet_readl(priv->base + GENET_RDMA_REG_OFF + + (DMA_RING_SIZE * ring) + + genet_dma_ring_regs[r]); } static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv, unsigned int ring, u32 val, enum dma_ring_reg r) { - __raw_writel(val, priv->base + GENET_RDMA_REG_OFF + + bcmgenet_writel(val, priv->base + GENET_RDMA_REG_OFF + (DMA_RING_SIZE * ring) + genet_dma_ring_regs[r]); } @@ -991,12 +1010,12 @@ static void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) bcmgenet_umac_writel(priv, reg, UMAC_EEE_CTRL); /* Enable EEE and switch to a 27Mhz clock automatically */ - reg = __raw_readl(priv->base + off); + reg = bcmgenet_readl(priv->base + off); if (enable) reg |= TBUF_EEE_EN | TBUF_PM_EN; else reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); - __raw_writel(reg, priv->base + off); + bcmgenet_writel(reg, priv->base + off); /* Do the same for thing for RBUF */ reg = bcmgenet_rbuf_readl(priv, RBUF_ENERGY_CTRL); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 3a34fdba5301..4c49d0b97748 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -657,6 +657,7 @@ struct bcmgenet_priv { struct clk *clk; struct platform_device *pdev; + struct platform_device *mii_pdev; /* WOL */ struct clk *clk_wol; @@ -671,12 +672,21 @@ struct bcmgenet_priv { static inline u32 bcmgenet_##name##_readl(struct bcmgenet_priv *priv, \ u32 off) \ { \ - return __raw_readl(priv->base + offset + off); \ + /* MIPS chips strapped for BE will automagically configure the \ + * peripheral registers for CPU-native byte order. \ + */ \ + if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) \ + return __raw_readl(priv->base + offset + off); \ + else \ + return readl_relaxed(priv->base + offset + off); \ } \ static inline void bcmgenet_##name##_writel(struct bcmgenet_priv *priv, \ u32 val, u32 off) \ { \ - __raw_writel(val, priv->base + offset + off); \ + if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) \ + __raw_writel(val, priv->base + offset + off); \ + else \ + writel_relaxed(val, priv->base + offset + off); \ } GENET_IO_MACRO(ext, GENET_EXT_OFF); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 30cb97b4a1d7..18f5723be2c9 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -24,62 +24,10 @@ #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/platform_data/bcmgenet.h> +#include <linux/platform_data/mdio-bcm-unimac.h> #include "bcmgenet.h" -/* read a value from the MII */ -static int bcmgenet_mii_read(struct mii_bus *bus, int phy_id, int location) -{ - int ret; - struct net_device *dev = bus->priv; - struct bcmgenet_priv *priv = netdev_priv(dev); - u32 reg; - - bcmgenet_umac_writel(priv, (MDIO_RD | (phy_id << MDIO_PMD_SHIFT) | - (location << MDIO_REG_SHIFT)), UMAC_MDIO_CMD); - /* Start MDIO transaction*/ - reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD); - reg |= MDIO_START_BUSY; - bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD); - wait_event_timeout(priv->wq, - !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD) - & MDIO_START_BUSY), - HZ / 100); - ret = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD); - - /* Some broken devices are known not to release the line during - * turn-around, e.g: Broadcom BCM53125 external switches, so check for - * that condition here and ignore the MDIO controller read failure - * indication. - */ - if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (ret & MDIO_READ_FAIL)) - return -EIO; - - return ret & 0xffff; -} - -/* write a value to the MII */ -static int bcmgenet_mii_write(struct mii_bus *bus, int phy_id, - int location, u16 val) -{ - struct net_device *dev = bus->priv; - struct bcmgenet_priv *priv = netdev_priv(dev); - u32 reg; - - bcmgenet_umac_writel(priv, (MDIO_WR | (phy_id << MDIO_PMD_SHIFT) | - (location << MDIO_REG_SHIFT) | (0xffff & val)), - UMAC_MDIO_CMD); - reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD); - reg |= MDIO_START_BUSY; - bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD); - wait_event_timeout(priv->wq, - !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD) & - MDIO_START_BUSY), - HZ / 100); - - return 0; -} - /* setup netdev link state when PHY link status change and * update UMAC and RGMII block when link up */ @@ -393,104 +341,121 @@ int bcmgenet_mii_probe(struct net_device *dev) return 0; } -/* Workaround for integrated BCM7xxx Gigabit PHYs which have a problem with - * their internal MDIO management controller making them fail to successfully - * be read from or written to for the first transaction. We insert a dummy - * BMSR read here to make sure that phy_get_device() and get_phy_id() can - * correctly read the PHY MII_PHYSID1/2 registers and successfully register a - * PHY device for this peripheral. - * - * Once the PHY driver is registered, we can workaround subsequent reads from - * there (e.g: during system-wide power management). - * - * bus->reset is invoked before mdiobus_scan during mdiobus_register and is - * therefore the right location to stick that workaround. Since we do not want - * to read from non-existing PHYs, we either use bus->phy_mask or do a manual - * Device Tree scan to limit the search area. - */ -static int bcmgenet_mii_bus_reset(struct mii_bus *bus) +static struct device_node *bcmgenet_mii_of_find_mdio(struct bcmgenet_priv *priv) { - struct net_device *dev = bus->priv; - struct bcmgenet_priv *priv = netdev_priv(dev); - struct device_node *np = priv->mdio_dn; - struct device_node *child = NULL; - u32 read_mask = 0; - int addr = 0; + struct device_node *dn = priv->pdev->dev.of_node; + struct device *kdev = &priv->pdev->dev; + char *compat; - if (!np) { - read_mask = 1 << priv->phy_addr; - } else { - for_each_available_child_of_node(np, child) { - addr = of_mdio_parse_addr(&dev->dev, child); - if (addr < 0) - continue; + compat = kasprintf(GFP_KERNEL, "brcm,genet-mdio-v%d", priv->version); + if (!compat) + return NULL; - read_mask |= 1 << addr; - } + priv->mdio_dn = of_find_compatible_node(dn, NULL, compat); + kfree(compat); + if (!priv->mdio_dn) { + dev_err(kdev, "unable to find MDIO bus node\n"); + return NULL; } - for (addr = 0; addr < PHY_MAX_ADDR; addr++) { - if (read_mask & 1 << addr) { - dev_dbg(&dev->dev, "Workaround for PHY @ %d\n", addr); - mdiobus_read(bus, addr, MII_BMSR); - } + return priv->mdio_dn; +} + +static void bcmgenet_mii_pdata_init(struct bcmgenet_priv *priv, + struct unimac_mdio_pdata *ppd) +{ + struct device *kdev = &priv->pdev->dev; + struct bcmgenet_platform_data *pd = kdev->platform_data; + + if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) { + /* + * Internal or external PHY with MDIO access + */ + if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR) + ppd->phy_mask = 1 << pd->phy_address; + else + ppd->phy_mask = 0; } +} +static int bcmgenet_mii_wait(void *wait_func_data) +{ + struct bcmgenet_priv *priv = wait_func_data; + + wait_event_timeout(priv->wq, + !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD) + & MDIO_START_BUSY), + HZ / 100); return 0; } -static int bcmgenet_mii_alloc(struct bcmgenet_priv *priv) +static int bcmgenet_mii_register(struct bcmgenet_priv *priv) { - struct mii_bus *bus; + struct platform_device *pdev = priv->pdev; + struct bcmgenet_platform_data *pdata = pdev->dev.platform_data; + struct device_node *dn = pdev->dev.of_node; + struct unimac_mdio_pdata ppd; + struct platform_device *ppdev; + struct resource *pres, res; + int id, ret; + + pres = platform_get_resource(pdev, IORESOURCE_MEM, 0); + memset(&res, 0, sizeof(res)); + memset(&ppd, 0, sizeof(ppd)); + + ppd.wait_func = bcmgenet_mii_wait; + ppd.wait_func_data = priv; + ppd.bus_name = "bcmgenet MII bus"; + + /* Unimac MDIO bus controller starts at UniMAC offset + MDIO_CMD + * and is 2 * 32-bits word long, 8 bytes total. + */ + res.start = pres->start + GENET_UMAC_OFF + UMAC_MDIO_CMD; + res.end = res.start + 8; + res.flags = IORESOURCE_MEM; - if (priv->mii_bus) - return 0; + if (dn) + id = of_alias_get_id(dn, "eth"); + else + id = pdev->id; - priv->mii_bus = mdiobus_alloc(); - if (!priv->mii_bus) { - pr_err("failed to allocate\n"); + ppdev = platform_device_alloc(UNIMAC_MDIO_DRV_NAME, id); + if (!ppdev) return -ENOMEM; - } - bus = priv->mii_bus; - bus->priv = priv->dev; - bus->name = "bcmgenet MII bus"; - bus->parent = &priv->pdev->dev; - bus->read = bcmgenet_mii_read; - bus->write = bcmgenet_mii_write; - bus->reset = bcmgenet_mii_bus_reset; - snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", - priv->pdev->name, priv->pdev->id); + /* Retain this platform_device pointer for later cleanup */ + priv->mii_pdev = ppdev; + ppdev->dev.parent = &pdev->dev; + ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv); + if (pdata) + bcmgenet_mii_pdata_init(priv, &ppd); + + ret = platform_device_add_resources(ppdev, &res, 1); + if (ret) + goto out; + + ret = platform_device_add_data(ppdev, &ppd, sizeof(ppd)); + if (ret) + goto out; + + ret = platform_device_add(ppdev); + if (ret) + goto out; return 0; +out: + platform_device_put(ppdev); + return ret; } static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) { struct device_node *dn = priv->pdev->dev.of_node; struct device *kdev = &priv->pdev->dev; - struct phy_device *phydev = NULL; - char *compat; + struct phy_device *phydev; int phy_mode; int ret; - compat = kasprintf(GFP_KERNEL, "brcm,genet-mdio-v%d", priv->version); - if (!compat) - return -ENOMEM; - - priv->mdio_dn = of_find_compatible_node(dn, NULL, compat); - kfree(compat); - if (!priv->mdio_dn) { - dev_err(kdev, "unable to find MDIO bus node\n"); - return -ENODEV; - } - - ret = of_mdiobus_register(priv->mii_bus, priv->mdio_dn); - if (ret) { - dev_err(kdev, "failed to register MDIO bus\n"); - return ret; - } - /* Fetch the PHY phandle */ priv->phy_dn = of_parse_phandle(dn, "phy-handle", 0); @@ -537,33 +502,23 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) { struct device *kdev = &priv->pdev->dev; struct bcmgenet_platform_data *pd = kdev->platform_data; - struct mii_bus *mdio = priv->mii_bus; + char phy_name[MII_BUS_ID_SIZE + 3]; + char mdio_bus_id[MII_BUS_ID_SIZE]; struct phy_device *phydev; - int ret; + + snprintf(mdio_bus_id, MII_BUS_ID_SIZE, "%s-%d", + UNIMAC_MDIO_DRV_NAME, priv->pdev->id); if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) { + snprintf(phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT, + mdio_bus_id, pd->phy_address); + /* * Internal or external PHY with MDIO access */ - if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR) - mdio->phy_mask = ~(1 << pd->phy_address); - else - mdio->phy_mask = 0; - - ret = mdiobus_register(mdio); - if (ret) { - dev_err(kdev, "failed to register MDIO bus\n"); - return ret; - } - - if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR) - phydev = mdiobus_get_phy(mdio, pd->phy_address); - else - phydev = phy_find_first(mdio); - + phydev = phy_attach(priv->dev, phy_name, pd->phy_interface); if (!phydev) { dev_err(kdev, "failed to register PHY device\n"); - mdiobus_unregister(mdio); return -ENODEV; } } else { @@ -609,10 +564,9 @@ static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) int bcmgenet_mii_init(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct device_node *dn = priv->pdev->dev.of_node; int ret; - ret = bcmgenet_mii_alloc(priv); + ret = bcmgenet_mii_register(priv); if (ret) return ret; @@ -623,11 +577,7 @@ int bcmgenet_mii_init(struct net_device *dev) return 0; out: - if (of_phy_is_fixed_link(dn)) - of_phy_deregister_fixed_link(dn); - of_node_put(priv->phy_dn); - mdiobus_unregister(priv->mii_bus); - mdiobus_free(priv->mii_bus); + bcmgenet_mii_exit(dev); return ret; } @@ -639,6 +589,6 @@ void bcmgenet_mii_exit(struct net_device *dev) if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); - mdiobus_unregister(priv->mii_bus); - mdiobus_free(priv->mii_bus); + platform_device_unregister(priv->mii_pdev); + platform_device_put(priv->mii_pdev); } diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 16a0f192daec..ecdef42f0ae6 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -1367,15 +1367,11 @@ static int sbmac_initctx(struct sbmac_softc *s) static void sbdma_uninitctx(struct sbmacdma *d) { - if (d->sbdma_dscrtable_unaligned) { - kfree(d->sbdma_dscrtable_unaligned); - d->sbdma_dscrtable_unaligned = d->sbdma_dscrtable = NULL; - } + kfree(d->sbdma_dscrtable_unaligned); + d->sbdma_dscrtable_unaligned = d->sbdma_dscrtable = NULL; - if (d->sbdma_ctxtable) { - kfree(d->sbdma_ctxtable); - d->sbdma_ctxtable = NULL; - } + kfree(d->sbdma_ctxtable); + d->sbdma_ctxtable = NULL; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index d600c41fb1dc..af33dc15c55f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6587,7 +6587,7 @@ static void tg3_tx(struct tg3_napi *tnapi) pkts_compl++; bytes_compl += skb->len; - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); if (unlikely(tx_bug)) { tg3_tx_recover(tp); @@ -7829,7 +7829,7 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, } } - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); *pskb = new_skb; return ret; } @@ -7882,7 +7882,7 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi, } while (segs); tg3_tso_bug_end: - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); return NETDEV_TX_OK; } @@ -8543,7 +8543,7 @@ static void tg3_free_rings(struct tg3 *tp) tg3_tx_skb_unmap(tnapi, i, skb_shinfo(skb)->nr_frags - 1); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); } netdev_tx_reset_queue(netdev_get_tx_queue(tp->dev, j)); } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 26d25749c3e4..6df2cad61647 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -68,7 +68,7 @@ #define GEM_MAX_TX_LEN ((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1))) #define GEM_MTU_MIN_SIZE ETH_MIN_MTU -#define MACB_NETIF_LSO (NETIF_F_TSO | NETIF_F_UFO) +#define MACB_NETIF_LSO NETIF_F_TSO #define MACB_WOL_HAS_MAGIC_PACKET (0x1 << 0) #define MACB_WOL_ENABLED (0x1 << 1) diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c index 9906fda76087..248a8fc45069 100644 --- a/drivers/net/ethernet/cadence/macb_pci.c +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -128,7 +128,7 @@ static void macb_remove(struct pci_dev *pdev) clk_unregister(plat_data->hclk); } -static struct pci_device_id dev_id_table[] = { +static const struct pci_device_id dev_id_table[] = { { PCI_DEVICE(CDNS_VENDOR_ID, CDNS_DEVICE_ID), }, { 0, } }; diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 67cca08472b7..2220c771092b 100755 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -192,7 +192,7 @@ static int gem_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } -static struct ptp_clock_info gem_ptp_caps_template = { +static const struct ptp_clock_info gem_ptp_caps_template = { .owner = THIS_MODULE, .name = GEM_PTP_TIMER_NAME, .max_adj = 0, diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index 4b0ca9fb2cb4..e8b290473ee2 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1150,14 +1150,50 @@ static void cn23xx_get_pcie_qlmport(struct octeon_device *oct) oct->pcie_port); } -static void cn23xx_get_pf_num(struct octeon_device *oct) +static int cn23xx_get_pf_num(struct octeon_device *oct) { u32 fdl_bit = 0; + u64 pkt0_in_ctl, d64; + int pfnum, mac, trs, ret; + + ret = 0; /** Read Function Dependency Link reg to get the function number */ - pci_read_config_dword(oct->pci_dev, CN23XX_PCIE_SRIOV_FDL, &fdl_bit); - oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) & - CN23XX_PCIE_SRIOV_FDL_MASK); + if (pci_read_config_dword(oct->pci_dev, CN23XX_PCIE_SRIOV_FDL, + &fdl_bit) == 0) { + oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) & + CN23XX_PCIE_SRIOV_FDL_MASK); + } else { + ret = EINVAL; + + /* Under some virtual environments, extended PCI regs are + * inaccessible, in which case the above read will have failed. + * In this case, read the PF number from the + * SLI_PKT0_INPUT_CONTROL reg (written by f/w) + */ + pkt0_in_ctl = octeon_read_csr64(oct, + CN23XX_SLI_IQ_PKT_CONTROL64(0)); + pfnum = (pkt0_in_ctl >> CN23XX_PKT_INPUT_CTL_PF_NUM_POS) & + CN23XX_PKT_INPUT_CTL_PF_NUM_MASK; + mac = (octeon_read_csr(oct, CN23XX_SLI_MAC_NUMBER)) & 0xff; + + /* validate PF num by reading RINFO; f/w writes RINFO.trs == 1*/ + d64 = octeon_read_csr64(oct, + CN23XX_SLI_PKT_MAC_RINFO64(mac, pfnum)); + trs = (int)(d64 >> CN23XX_PKT_MAC_CTL_RINFO_TRS_BIT_POS) & 0xff; + if (trs == 1) { + dev_err(&oct->pci_dev->dev, + "OCTEON: error reading PCI cfg space pfnum, re-read %u\n", + pfnum); + oct->pf_num = pfnum; + ret = 0; + } else { + dev_err(&oct->pci_dev->dev, + "OCTEON: error reading PCI cfg space pfnum; could not ascertain PF number\n"); + } + } + + return ret; } static void cn23xx_setup_reg_address(struct octeon_device *oct) @@ -1269,6 +1305,26 @@ static int cn23xx_sriov_config(struct octeon_device *oct) int setup_cn23xx_octeon_pf_device(struct octeon_device *oct) { + u32 data32; + u64 BAR0, BAR1; + + pci_read_config_dword(oct->pci_dev, PCI_BASE_ADDRESS_0, &data32); + BAR0 = (u64)(data32 & ~0xf); + pci_read_config_dword(oct->pci_dev, PCI_BASE_ADDRESS_1, &data32); + BAR0 |= ((u64)data32 << 32); + pci_read_config_dword(oct->pci_dev, PCI_BASE_ADDRESS_2, &data32); + BAR1 = (u64)(data32 & ~0xf); + pci_read_config_dword(oct->pci_dev, PCI_BASE_ADDRESS_3, &data32); + BAR1 |= ((u64)data32 << 32); + + if (!BAR0 || !BAR1) { + if (!BAR0) + dev_err(&oct->pci_dev->dev, "device BAR0 unassigned\n"); + if (!BAR1) + dev_err(&oct->pci_dev->dev, "device BAR1 unassigned\n"); + return 1; + } + if (octeon_map_pci_barx(oct, 0, 0)) return 1; @@ -1279,7 +1335,8 @@ int setup_cn23xx_octeon_pf_device(struct octeon_device *oct) return 1; } - cn23xx_get_pf_num(oct); + if (cn23xx_get_pf_num(oct) != 0) + return 1; if (cn23xx_sriov_config(oct)) { octeon_unmap_pci_barx(oct, 0); @@ -1405,8 +1462,19 @@ int cn23xx_fw_loaded(struct octeon_device *oct) { u64 val; - val = octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1); - return (val >> 1) & 1ULL; + /* If there's more than one active PF on this NIC, then that + * implies that the NIC firmware is loaded and running. This check + * prevents a rare false negative that might occur if we only relied + * on checking the SCR2_BIT_FW_LOADED flag. The false negative would + * happen if the PF driver sees SCR2_BIT_FW_LOADED as cleared even + * though the firmware was already loaded but still booting and has yet + * to set SCR2_BIT_FW_LOADED. + */ + if (atomic_read(oct->adapter_refcount) > 1) + return 1; + + val = octeon_read_csr64(oct, CN23XX_SLI_SCRATCH2); + return (val >> SCR2_BIT_FW_LOADED) & 1ULL; } void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx, diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h index dee604651ba7..2aba5247b6d8 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h @@ -24,8 +24,6 @@ #include "cn23xx_pf_regs.h" -#define LIO_CMD_WAIT_TM 100 - /* Register address and configuration for a CN23XX devices. * If device specific changes need to be made then add a struct to include * device specific fields as shown in the commented section diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h index 3f98c7334957..2d06097d3f61 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h @@ -36,8 +36,6 @@ struct octeon_cn23xx_vf { #define CN23XX_MAILBOX_MSGPARAM_SIZE 6 -#define MAX_VF_IP_OP_PENDING_PKT_COUNT 100 - void cn23xx_vf_ask_pf_to_do_flr(struct octeon_device *oct); int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index adde7745d069..23f6b60030c5 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -165,9 +165,6 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr) /* If command is successful, change the MTU. */ netif_info(lio, probe, lio->netdev, "MTU Changed from %d to %d\n", netdev->mtu, nctrl->ncmd.s.param1); - dev_info(&oct->pci_dev->dev, "%s MTU Changed from %d to %d\n", - netdev->name, netdev->mtu, - nctrl->ncmd.s.param1); netdev->mtu = nctrl->ncmd.s.param1; queue_delayed_work(lio->link_status_wq.wq, &lio->link_status_wq.wk.work, 0); @@ -275,6 +272,11 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr) netif_info(lio, probe, lio->netdev, "Set RX/TX flow control parameters\n"); break; + case OCTNET_CMD_QUEUE_COUNT_CTL: + netif_info(lio, probe, lio->netdev, "Queue count updated to %d\n", + nctrl->ncmd.s.param1); + break; + default: dev_err(&oct->pci_dev->dev, "%s Unknown cmd %d\n", __func__, nctrl->ncmd.s.cmd); @@ -364,3 +366,723 @@ void cleanup_rx_oom_poll_fn(struct net_device *netdev) destroy_workqueue(lio->rxq_status_wq.wq); } } + +/* Runs in interrupt context. */ +static void lio_update_txq_status(struct octeon_device *oct, int iq_num) +{ + struct octeon_instr_queue *iq = oct->instr_queue[iq_num]; + struct net_device *netdev; + struct lio *lio; + + netdev = oct->props[iq->ifidx].netdev; + + /* This is needed because the first IQ does not have + * a netdev associated with it. + */ + if (!netdev) + return; + + lio = GET_LIO(netdev); + if (netif_is_multiqueue(netdev)) { + if (__netif_subqueue_stopped(netdev, iq->q_index) && + lio->linfo.link.s.link_up && + (!octnet_iq_is_full(oct, iq_num))) { + netif_wake_subqueue(netdev, iq->q_index); + INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num, + tx_restart, 1); + } + } else if (netif_queue_stopped(netdev) && + lio->linfo.link.s.link_up && + (!octnet_iq_is_full(oct, lio->txq))) { + INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, lio->txq, + tx_restart, 1); + netif_wake_queue(netdev); + } +} + +/** + * \brief Setup output queue + * @param oct octeon device + * @param q_no which queue + * @param num_descs how many descriptors + * @param desc_size size of each descriptor + * @param app_ctx application context + */ +static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs, + int desc_size, void *app_ctx) +{ + int ret_val; + + dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no); + /* droq creation and local register settings. */ + ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx); + if (ret_val < 0) + return ret_val; + + if (ret_val == 1) { + dev_dbg(&oct->pci_dev->dev, "Using default droq %d\n", q_no); + return 0; + } + + /* Enable the droq queues */ + octeon_set_droq_pkt_op(oct, q_no, 1); + + /* Send Credit for Octeon Output queues. Credits are always + * sent after the output queue is enabled. + */ + writel(oct->droq[q_no]->max_count, oct->droq[q_no]->pkts_credit_reg); + + return ret_val; +} + +/** Routine to push packets arriving on Octeon interface upto network layer. + * @param oct_id - octeon device id. + * @param skbuff - skbuff struct to be passed to network layer. + * @param len - size of total data received. + * @param rh - Control header associated with the packet + * @param param - additional control data with the packet + * @param arg - farg registered in droq_ops + */ +static void +liquidio_push_packet(u32 octeon_id __attribute__((unused)), + void *skbuff, + u32 len, + union octeon_rh *rh, + void *param, + void *arg) +{ + struct net_device *netdev = (struct net_device *)arg; + struct octeon_droq *droq = + container_of(param, struct octeon_droq, napi); + struct sk_buff *skb = (struct sk_buff *)skbuff; + struct skb_shared_hwtstamps *shhwtstamps; + struct napi_struct *napi = param; + u16 vtag = 0; + u32 r_dh_off; + u64 ns; + + if (netdev) { + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + int packet_was_received; + + /* Do not proceed if the interface is not in RUNNING state. */ + if (!ifstate_check(lio, LIO_IFSTATE_RUNNING)) { + recv_buffer_free(skb); + droq->stats.rx_dropped++; + return; + } + + skb->dev = netdev; + + skb_record_rx_queue(skb, droq->q_no); + if (likely(len > MIN_SKB_SIZE)) { + struct octeon_skb_page_info *pg_info; + unsigned char *va; + + pg_info = ((struct octeon_skb_page_info *)(skb->cb)); + if (pg_info->page) { + /* For Paged allocation use the frags */ + va = page_address(pg_info->page) + + pg_info->page_offset; + memcpy(skb->data, va, MIN_SKB_SIZE); + skb_put(skb, MIN_SKB_SIZE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + pg_info->page, + pg_info->page_offset + + MIN_SKB_SIZE, + len - MIN_SKB_SIZE, + LIO_RXBUFFER_SZ); + } + } else { + struct octeon_skb_page_info *pg_info = + ((struct octeon_skb_page_info *)(skb->cb)); + skb_copy_to_linear_data(skb, page_address(pg_info->page) + + pg_info->page_offset, len); + skb_put(skb, len); + put_page(pg_info->page); + } + + r_dh_off = (rh->r_dh.len - 1) * BYTES_PER_DHLEN_UNIT; + + if (oct->ptp_enable) { + if (rh->r_dh.has_hwtstamp) { + /* timestamp is included from the hardware at + * the beginning of the packet. + */ + if (ifstate_check + (lio, + LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) { + /* Nanoseconds are in the first 64-bits + * of the packet. + */ + memcpy(&ns, (skb->data + r_dh_off), + sizeof(ns)); + r_dh_off -= BYTES_PER_DHLEN_UNIT; + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = + ns_to_ktime(ns + + lio->ptp_adjust); + } + } + } + + if (rh->r_dh.has_hash) { + __be32 *hash_be = (__be32 *)(skb->data + r_dh_off); + u32 hash = be32_to_cpu(*hash_be); + + skb_set_hash(skb, hash, PKT_HASH_TYPE_L4); + r_dh_off -= BYTES_PER_DHLEN_UNIT; + } + + skb_pull(skb, rh->r_dh.len * BYTES_PER_DHLEN_UNIT); + skb->protocol = eth_type_trans(skb, skb->dev); + + if ((netdev->features & NETIF_F_RXCSUM) && + (((rh->r_dh.encap_on) && + (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) || + (!(rh->r_dh.encap_on) && + (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED)))) + /* checksum has already been verified */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + else + skb->ip_summed = CHECKSUM_NONE; + + /* Setting Encapsulation field on basis of status received + * from the firmware + */ + if (rh->r_dh.encap_on) { + skb->encapsulation = 1; + skb->csum_level = 1; + droq->stats.rx_vxlan++; + } + + /* inbound VLAN tag */ + if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && + rh->r_dh.vlan) { + u16 priority = rh->r_dh.priority; + u16 vid = rh->r_dh.vlan; + + vtag = (priority << VLAN_PRIO_SHIFT) | vid; + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vtag); + } + + packet_was_received = (napi_gro_receive(napi, skb) != GRO_DROP); + + if (packet_was_received) { + droq->stats.rx_bytes_received += len; + droq->stats.rx_pkts_received++; + } else { + droq->stats.rx_dropped++; + netif_info(lio, rx_err, lio->netdev, + "droq:%d error rx_dropped:%llu\n", + droq->q_no, droq->stats.rx_dropped); + } + + } else { + recv_buffer_free(skb); + } +} + +/** + * \brief wrapper for calling napi_schedule + * @param param parameters to pass to napi_schedule + * + * Used when scheduling on different CPUs + */ +static void napi_schedule_wrapper(void *param) +{ + struct napi_struct *napi = param; + + napi_schedule(napi); +} + +/** + * \brief callback when receive interrupt occurs and we are in NAPI mode + * @param arg pointer to octeon output queue + */ +static void liquidio_napi_drv_callback(void *arg) +{ + struct octeon_device *oct; + struct octeon_droq *droq = arg; + int this_cpu = smp_processor_id(); + + oct = droq->oct_dev; + + if (OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct) || + droq->cpu_id == this_cpu) { + napi_schedule_irqoff(&droq->napi); + } else { + call_single_data_t *csd = &droq->csd; + + csd->func = napi_schedule_wrapper; + csd->info = &droq->napi; + csd->flags = 0; + + smp_call_function_single_async(droq->cpu_id, csd); + } +} + +/** + * \brief Entry point for NAPI polling + * @param napi NAPI structure + * @param budget maximum number of items to process + */ +static int liquidio_napi_poll(struct napi_struct *napi, int budget) +{ + struct octeon_instr_queue *iq; + struct octeon_device *oct; + struct octeon_droq *droq; + int tx_done = 0, iq_no; + int work_done; + + droq = container_of(napi, struct octeon_droq, napi); + oct = droq->oct_dev; + iq_no = droq->q_no; + + /* Handle Droq descriptors */ + work_done = octeon_process_droq_poll_cmd(oct, droq->q_no, + POLL_EVENT_PROCESS_PKTS, + budget); + + /* Flush the instruction queue */ + iq = oct->instr_queue[iq_no]; + if (iq) { + /* TODO: move this check to inside octeon_flush_iq, + * once check_db_timeout is removed + */ + if (atomic_read(&iq->instr_pending)) + /* Process iq buffers with in the budget limits */ + tx_done = octeon_flush_iq(oct, iq, budget); + else + tx_done = 1; + /* Update iq read-index rather than waiting for next interrupt. + * Return back if tx_done is false. + */ + /* sub-queue status update */ + lio_update_txq_status(oct, iq_no); + } else { + dev_err(&oct->pci_dev->dev, "%s: iq (%d) num invalid\n", + __func__, iq_no); + } + +#define MAX_REG_CNT 2000000U + /* force enable interrupt if reg cnts are high to avoid wraparound */ + if ((work_done < budget && tx_done) || + (iq && iq->pkt_in_done >= MAX_REG_CNT) || + (droq->pkt_count >= MAX_REG_CNT)) { + tx_done = 1; + napi_complete_done(napi, work_done); + + octeon_process_droq_poll_cmd(droq->oct_dev, droq->q_no, + POLL_EVENT_ENABLE_INTR, 0); + return 0; + } + + return (!tx_done) ? (budget) : (work_done); +} + +/** + * \brief Setup input and output queues + * @param octeon_dev octeon device + * @param ifidx Interface index + * + * Note: Queues are with respect to the octeon device. Thus + * an input queue is for egress packets, and output queues + * are for ingress packets. + */ +int liquidio_setup_io_queues(struct octeon_device *octeon_dev, int ifidx, + u32 num_iqs, u32 num_oqs) +{ + struct octeon_droq_ops droq_ops; + struct net_device *netdev; + struct octeon_droq *droq; + struct napi_struct *napi; + int cpu_id_modulus; + int num_tx_descs; + struct lio *lio; + int retval = 0; + int q, q_no; + int cpu_id; + + netdev = octeon_dev->props[ifidx].netdev; + + lio = GET_LIO(netdev); + + memset(&droq_ops, 0, sizeof(struct octeon_droq_ops)); + + droq_ops.fptr = liquidio_push_packet; + droq_ops.farg = netdev; + + droq_ops.poll_mode = 1; + droq_ops.napi_fn = liquidio_napi_drv_callback; + cpu_id = 0; + cpu_id_modulus = num_present_cpus(); + + /* set up DROQs. */ + for (q = 0; q < num_oqs; q++) { + q_no = lio->linfo.rxpciq[q].s.q_no; + dev_dbg(&octeon_dev->pci_dev->dev, + "%s index:%d linfo.rxpciq.s.q_no:%d\n", + __func__, q, q_no); + retval = octeon_setup_droq( + octeon_dev, q_no, + CFG_GET_NUM_RX_DESCS_NIC_IF(octeon_get_conf(octeon_dev), + lio->ifidx), + CFG_GET_NUM_RX_BUF_SIZE_NIC_IF(octeon_get_conf(octeon_dev), + lio->ifidx), + NULL); + if (retval) { + dev_err(&octeon_dev->pci_dev->dev, + "%s : Runtime DROQ(RxQ) creation failed.\n", + __func__); + return 1; + } + + droq = octeon_dev->droq[q_no]; + napi = &droq->napi; + dev_dbg(&octeon_dev->pci_dev->dev, "netif_napi_add netdev:%llx oct:%llx\n", + (u64)netdev, (u64)octeon_dev); + netif_napi_add(netdev, napi, liquidio_napi_poll, 64); + + /* designate a CPU for this droq */ + droq->cpu_id = cpu_id; + cpu_id++; + if (cpu_id >= cpu_id_modulus) + cpu_id = 0; + + octeon_register_droq_ops(octeon_dev, q_no, &droq_ops); + } + + if (OCTEON_CN23XX_PF(octeon_dev) || OCTEON_CN23XX_VF(octeon_dev)) { + /* 23XX PF/VF can send/recv control messages (via the first + * PF/VF-owned droq) from the firmware even if the ethX + * interface is down, so that's why poll_mode must be off + * for the first droq. + */ + octeon_dev->droq[0]->ops.poll_mode = 0; + } + + /* set up IQs. */ + for (q = 0; q < num_iqs; q++) { + num_tx_descs = CFG_GET_NUM_TX_DESCS_NIC_IF( + octeon_get_conf(octeon_dev), lio->ifidx); + retval = octeon_setup_iq(octeon_dev, ifidx, q, + lio->linfo.txpciq[q], num_tx_descs, + netdev_get_tx_queue(netdev, q)); + if (retval) { + dev_err(&octeon_dev->pci_dev->dev, + " %s : Runtime IQ(TxQ) creation failed.\n", + __func__); + return 1; + } + + /* XPS */ + if (!OCTEON_CN23XX_VF(octeon_dev) && octeon_dev->msix_on && + octeon_dev->ioq_vector) { + struct octeon_ioq_vector *ioq_vector; + + ioq_vector = &octeon_dev->ioq_vector[q]; + netif_set_xps_queue(netdev, + &ioq_vector->affinity_mask, + ioq_vector->iq_index); + } + } + + return 0; +} + +static +int liquidio_schedule_msix_droq_pkt_handler(struct octeon_droq *droq, u64 ret) +{ + struct octeon_device *oct = droq->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; + + if (droq->ops.poll_mode) { + droq->ops.napi_fn(droq); + } else { + if (ret & MSIX_PO_INT) { + if (OCTEON_CN23XX_VF(oct)) + dev_err(&oct->pci_dev->dev, + "should not come here should not get rx when poll mode = 0 for vf\n"); + tasklet_schedule(&oct_priv->droq_tasklet); + return 1; + } + /* this will be flushed periodically by check iq db */ + if (ret & MSIX_PI_INT) + return 0; + } + + return 0; +} + +irqreturn_t +liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev) +{ + struct octeon_ioq_vector *ioq_vector = (struct octeon_ioq_vector *)dev; + struct octeon_device *oct = ioq_vector->oct_dev; + struct octeon_droq *droq = oct->droq[ioq_vector->droq_index]; + u64 ret; + + ret = oct->fn_list.msix_interrupt_handler(ioq_vector); + + if (ret & MSIX_PO_INT || ret & MSIX_PI_INT) + liquidio_schedule_msix_droq_pkt_handler(droq, ret); + + return IRQ_HANDLED; +} + +/** + * \brief Droq packet processor sceduler + * @param oct octeon device + */ +static void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct) +{ + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; + struct octeon_droq *droq; + u64 oq_no; + + if (oct->int_status & OCT_DEV_INTR_PKT_DATA) { + for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct); + oq_no++) { + if (!(oct->droq_intr & BIT_ULL(oq_no))) + continue; + + droq = oct->droq[oq_no]; + + if (droq->ops.poll_mode) { + droq->ops.napi_fn(droq); + oct_priv->napi_mask |= (1 << oq_no); + } else { + tasklet_schedule(&oct_priv->droq_tasklet); + } + } + } +} + +/** + * \brief Interrupt handler for octeon + * @param irq unused + * @param dev octeon device + */ +static +irqreturn_t liquidio_legacy_intr_handler(int irq __attribute__((unused)), + void *dev) +{ + struct octeon_device *oct = (struct octeon_device *)dev; + irqreturn_t ret; + + /* Disable our interrupts for the duration of ISR */ + oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR); + + ret = oct->fn_list.process_interrupt_regs(oct); + + if (ret == IRQ_HANDLED) + liquidio_schedule_droq_pkt_handlers(oct); + + /* Re-enable our interrupts */ + if (!(atomic_read(&oct->status) == OCT_DEV_IN_RESET)) + oct->fn_list.enable_interrupt(oct, OCTEON_ALL_INTR); + + return ret; +} + +/** + * \brief Setup interrupt for octeon device + * @param oct octeon device + * + * Enable interrupt in Octeon device as given in the PCI interrupt mask. + */ +int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs) +{ + struct msix_entry *msix_entries; + char *queue_irq_names = NULL; + int i, num_interrupts = 0; + int num_alloc_ioq_vectors; + char *aux_irq_name = NULL; + int num_ioq_vectors; + int irqret, err; + + oct->num_msix_irqs = num_ioqs; + if (oct->msix_on) { + if (OCTEON_CN23XX_PF(oct)) { + num_interrupts = MAX_IOQ_INTERRUPTS_PER_PF + 1; + + /* one non ioq interrupt for handling + * sli_mac_pf_int_sum + */ + oct->num_msix_irqs += 1; + } else if (OCTEON_CN23XX_VF(oct)) { + num_interrupts = MAX_IOQ_INTERRUPTS_PER_VF; + } + + /* allocate storage for the names assigned to each irq */ + oct->irq_name_storage = + kcalloc(num_interrupts, INTRNAMSIZ, GFP_KERNEL); + if (!oct->irq_name_storage) { + dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n"); + return -ENOMEM; + } + + queue_irq_names = oct->irq_name_storage; + + if (OCTEON_CN23XX_PF(oct)) + aux_irq_name = &queue_irq_names + [IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)]; + + oct->msix_entries = kcalloc(oct->num_msix_irqs, + sizeof(struct msix_entry), + GFP_KERNEL); + if (!oct->msix_entries) { + dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n"); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return -ENOMEM; + } + + msix_entries = (struct msix_entry *)oct->msix_entries; + + /*Assumption is that pf msix vectors start from pf srn to pf to + * trs and not from 0. if not change this code + */ + if (OCTEON_CN23XX_PF(oct)) { + for (i = 0; i < oct->num_msix_irqs - 1; i++) + msix_entries[i].entry = + oct->sriov_info.pf_srn + i; + + msix_entries[oct->num_msix_irqs - 1].entry = + oct->sriov_info.trs; + } else if (OCTEON_CN23XX_VF(oct)) { + for (i = 0; i < oct->num_msix_irqs; i++) + msix_entries[i].entry = i; + } + num_alloc_ioq_vectors = pci_enable_msix_range( + oct->pci_dev, msix_entries, + oct->num_msix_irqs, + oct->num_msix_irqs); + if (num_alloc_ioq_vectors < 0) { + dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n"); + kfree(oct->msix_entries); + oct->msix_entries = NULL; + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return num_alloc_ioq_vectors; + } + + dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n"); + + num_ioq_vectors = oct->num_msix_irqs; + /** For PF, there is one non-ioq interrupt handler */ + if (OCTEON_CN23XX_PF(oct)) { + num_ioq_vectors -= 1; + + snprintf(aux_irq_name, INTRNAMSIZ, + "LiquidIO%u-pf%u-aux", oct->octeon_id, + oct->pf_num); + irqret = request_irq( + msix_entries[num_ioq_vectors].vector, + liquidio_legacy_intr_handler, 0, + aux_irq_name, oct); + if (irqret) { + dev_err(&oct->pci_dev->dev, + "Request_irq failed for MSIX interrupt Error: %d\n", + irqret); + pci_disable_msix(oct->pci_dev); + kfree(oct->msix_entries); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + oct->msix_entries = NULL; + return irqret; + } + } + for (i = 0 ; i < num_ioq_vectors ; i++) { + if (OCTEON_CN23XX_PF(oct)) + snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], + INTRNAMSIZ, "LiquidIO%u-pf%u-rxtx-%u", + oct->octeon_id, oct->pf_num, i); + + if (OCTEON_CN23XX_VF(oct)) + snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], + INTRNAMSIZ, "LiquidIO%u-vf%u-rxtx-%u", + oct->octeon_id, oct->vf_num, i); + + irqret = request_irq(msix_entries[i].vector, + liquidio_msix_intr_handler, 0, + &queue_irq_names[IRQ_NAME_OFF(i)], + &oct->ioq_vector[i]); + + if (irqret) { + dev_err(&oct->pci_dev->dev, + "Request_irq failed for MSIX interrupt Error: %d\n", + irqret); + /** Freeing the non-ioq irq vector here . */ + free_irq(msix_entries[num_ioq_vectors].vector, + oct); + + while (i) { + i--; + /** clearing affinity mask. */ + irq_set_affinity_hint( + msix_entries[i].vector, + NULL); + free_irq(msix_entries[i].vector, + &oct->ioq_vector[i]); + } + pci_disable_msix(oct->pci_dev); + kfree(oct->msix_entries); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + oct->msix_entries = NULL; + return irqret; + } + oct->ioq_vector[i].vector = msix_entries[i].vector; + /* assign the cpu mask for this msix interrupt vector */ + irq_set_affinity_hint(msix_entries[i].vector, + &oct->ioq_vector[i].affinity_mask + ); + } + dev_dbg(&oct->pci_dev->dev, "OCTEON[%d]: MSI-X enabled\n", + oct->octeon_id); + } else { + err = pci_enable_msi(oct->pci_dev); + if (err) + dev_warn(&oct->pci_dev->dev, "Reverting to legacy interrupts. Error: %d\n", + err); + else + oct->flags |= LIO_FLAG_MSI_ENABLED; + + /* allocate storage for the names assigned to the irq */ + oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL); + if (!oct->irq_name_storage) + return -ENOMEM; + + queue_irq_names = oct->irq_name_storage; + + if (OCTEON_CN23XX_PF(oct)) + snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ, + "LiquidIO%u-pf%u-rxtx-%u", + oct->octeon_id, oct->pf_num, 0); + + if (OCTEON_CN23XX_VF(oct)) + snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ, + "LiquidIO%u-vf%u-rxtx-%u", + oct->octeon_id, oct->vf_num, 0); + + irqret = request_irq(oct->pci_dev->irq, + liquidio_legacy_intr_handler, + IRQF_SHARED, + &queue_irq_names[IRQ_NAME_OFF(0)], oct); + if (irqret) { + if (oct->flags & LIO_FLAG_MSI_ENABLED) + pci_disable_msi(oct->pci_dev); + dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n", + irqret); + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + return irqret; + } + } + return 0; +} diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index ebd353bc78ff..a63ddf07f168 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -31,6 +31,7 @@ #include "cn23xx_pf_device.h" #include "cn23xx_vf_device.h" +static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs); static int octnet_get_link_stats(struct net_device *netdev); struct oct_intrmod_context { @@ -105,6 +106,7 @@ static const char oct_stats_strings[][ETH_GSTRING_LEN] = { "tx_total_sent", "tx_total_fwd", "tx_err_pko", + "tx_err_pki", "tx_err_link", "tx_err_drop", @@ -299,6 +301,35 @@ lio_get_vf_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) strncpy(drvinfo->bus_info, pci_name(oct->pci_dev), 32); } +static int +lio_send_queue_count_update(struct net_device *netdev, uint32_t num_queues) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + struct octnic_ctrl_pkt nctrl; + int ret = 0; + + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + + nctrl.ncmd.u64 = 0; + nctrl.ncmd.s.cmd = OCTNET_CMD_QUEUE_COUNT_CTL; + nctrl.ncmd.s.param1 = num_queues; + nctrl.ncmd.s.param2 = num_queues; + nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; + nctrl.wait_time = 100; + nctrl.netpndev = (u64)netdev; + nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; + + ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); + if (ret < 0) { + dev_err(&oct->pci_dev->dev, "Failed to send Queue reset command (ret: 0x%x)\n", + ret); + return -1; + } + + return 0; +} + static void lio_ethtool_get_channels(struct net_device *dev, struct ethtool_channels *channel) @@ -306,6 +337,7 @@ lio_ethtool_get_channels(struct net_device *dev, struct lio *lio = GET_LIO(dev); struct octeon_device *oct = lio->oct_dev; u32 max_rx = 0, max_tx = 0, tx_count = 0, rx_count = 0; + u32 combined_count = 0, max_combined = 0; if (OCTEON_CN6XXX(oct)) { struct octeon_config *conf6x = CHIP_CONF(oct, cn6xxx); @@ -315,22 +347,137 @@ lio_ethtool_get_channels(struct net_device *dev, rx_count = CFG_GET_NUM_RXQS_NIC_IF(conf6x, lio->ifidx); tx_count = CFG_GET_NUM_TXQS_NIC_IF(conf6x, lio->ifidx); } else if (OCTEON_CN23XX_PF(oct)) { - - max_rx = oct->sriov_info.num_pf_rings; - max_tx = oct->sriov_info.num_pf_rings; - rx_count = lio->linfo.num_rxpciq; - tx_count = lio->linfo.num_txpciq; + max_combined = lio->linfo.num_txpciq; + combined_count = oct->num_iqs; } else if (OCTEON_CN23XX_VF(oct)) { - max_tx = oct->sriov_info.rings_per_vf; - max_rx = oct->sriov_info.rings_per_vf; - rx_count = lio->linfo.num_rxpciq; - tx_count = lio->linfo.num_txpciq; + u64 reg_val = 0ULL; + u64 ctrl = CN23XX_VF_SLI_IQ_PKT_CONTROL64(0); + + reg_val = octeon_read_csr64(oct, ctrl); + reg_val = reg_val >> CN23XX_PKT_INPUT_CTL_RPVF_POS; + max_combined = reg_val & CN23XX_PKT_INPUT_CTL_RPVF_MASK; + combined_count = oct->num_iqs; } channel->max_rx = max_rx; channel->max_tx = max_tx; + channel->max_combined = max_combined; channel->rx_count = rx_count; channel->tx_count = tx_count; + channel->combined_count = combined_count; +} + +static int +lio_irq_reallocate_irqs(struct octeon_device *oct, uint32_t num_ioqs) +{ + struct msix_entry *msix_entries; + int num_msix_irqs = 0; + int i; + + if (!oct->msix_on) + return 0; + + /* Disable the input and output queues now. No more packets will + * arrive from Octeon. + */ + oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR); + + if (oct->msix_on) { + if (OCTEON_CN23XX_PF(oct)) + num_msix_irqs = oct->num_msix_irqs - 1; + else if (OCTEON_CN23XX_VF(oct)) + num_msix_irqs = oct->num_msix_irqs; + + msix_entries = (struct msix_entry *)oct->msix_entries; + for (i = 0; i < num_msix_irqs; i++) { + if (oct->ioq_vector[i].vector) { + /* clear the affinity_cpumask */ + irq_set_affinity_hint(msix_entries[i].vector, + NULL); + free_irq(msix_entries[i].vector, + &oct->ioq_vector[i]); + oct->ioq_vector[i].vector = 0; + } + } + + /* non-iov vector's argument is oct struct */ + if (OCTEON_CN23XX_PF(oct)) + free_irq(msix_entries[i].vector, oct); + + pci_disable_msix(oct->pci_dev); + kfree(oct->msix_entries); + oct->msix_entries = NULL; + } + + kfree(oct->irq_name_storage); + oct->irq_name_storage = NULL; + if (octeon_setup_interrupt(oct, num_ioqs)) { + dev_info(&oct->pci_dev->dev, "Setup interrupt failed\n"); + return 1; + } + + /* Enable Octeon device interrupts */ + oct->fn_list.enable_interrupt(oct, OCTEON_ALL_INTR); + + return 0; +} + +static int +lio_ethtool_set_channels(struct net_device *dev, + struct ethtool_channels *channel) +{ + u32 combined_count, max_combined; + struct lio *lio = GET_LIO(dev); + struct octeon_device *oct = lio->oct_dev; + int stopped = 0; + + if (strcmp(oct->fw_info.liquidio_firmware_version, "1.6.1") < 0) { + dev_err(&oct->pci_dev->dev, "Minimum firmware version required is 1.6.1\n"); + return -EINVAL; + } + + if (!channel->combined_count || channel->other_count || + channel->rx_count || channel->tx_count) + return -EINVAL; + + combined_count = channel->combined_count; + + if (OCTEON_CN23XX_PF(oct)) { + max_combined = channel->max_combined; + } else if (OCTEON_CN23XX_VF(oct)) { + u64 reg_val = 0ULL; + u64 ctrl = CN23XX_VF_SLI_IQ_PKT_CONTROL64(0); + + reg_val = octeon_read_csr64(oct, ctrl); + reg_val = reg_val >> CN23XX_PKT_INPUT_CTL_RPVF_POS; + max_combined = reg_val & CN23XX_PKT_INPUT_CTL_RPVF_MASK; + } else { + return -EINVAL; + } + + if (combined_count > max_combined || combined_count < 1) + return -EINVAL; + + if (combined_count == oct->num_iqs) + return 0; + + ifstate_set(lio, LIO_IFSTATE_RESETTING); + + if (netif_running(dev)) { + dev->netdev_ops->ndo_stop(dev); + stopped = 1; + } + + if (lio_reset_queues(dev, combined_count)) + return -EINVAL; + + lio_irq_reallocate_irqs(oct, combined_count); + if (stopped) + dev->netdev_ops->ndo_open(dev); + + ifstate_reset(lio, LIO_IFSTATE_RESETTING); + + return 0; } static int lio_get_eeprom_len(struct net_device *netdev) @@ -577,23 +724,18 @@ static int lio_set_phys_id(struct net_device *netdev, break; case ETHTOOL_ID_ON: - if (oct->chip_id == OCTEON_CN66XX) { + if (oct->chip_id == OCTEON_CN66XX) octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG, VITESSE_PHY_GPIO_HIGH); - - } else if (oct->chip_id == OCTEON_CN68XX) { - return -EINVAL; - } else { + else return -EINVAL; - } + break; case ETHTOOL_ID_OFF: if (oct->chip_id == OCTEON_CN66XX) octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG, VITESSE_PHY_GPIO_LOW); - else if (oct->chip_id == OCTEON_CN68XX) - return -EINVAL; else return -EINVAL; @@ -641,6 +783,9 @@ lio_ethtool_get_ringparam(struct net_device *netdev, u32 tx_max_pending = 0, rx_max_pending = 0, tx_pending = 0, rx_pending = 0; + if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) + return; + if (OCTEON_CN6XXX(oct)) { struct octeon_config *conf6x = CHIP_CONF(oct, cn6xxx); @@ -648,33 +793,147 @@ lio_ethtool_get_ringparam(struct net_device *netdev, rx_max_pending = CN6XXX_MAX_OQ_DESCRIPTORS; rx_pending = CFG_GET_NUM_RX_DESCS_NIC_IF(conf6x, lio->ifidx); tx_pending = CFG_GET_NUM_TX_DESCS_NIC_IF(conf6x, lio->ifidx); - } else if (OCTEON_CN23XX_PF(oct)) { - struct octeon_config *conf23 = CHIP_CONF(oct, cn23xx_pf); - + } else if (OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) { tx_max_pending = CN23XX_MAX_IQ_DESCRIPTORS; rx_max_pending = CN23XX_MAX_OQ_DESCRIPTORS; - rx_pending = CFG_GET_NUM_RX_DESCS_NIC_IF(conf23, lio->ifidx); - tx_pending = CFG_GET_NUM_TX_DESCS_NIC_IF(conf23, lio->ifidx); - } - - if (lio->mtu > OCTNET_DEFAULT_FRM_SIZE - OCTNET_FRM_HEADER_SIZE) { - ering->rx_pending = 0; - ering->rx_max_pending = 0; - ering->rx_mini_pending = 0; - ering->rx_jumbo_pending = rx_pending; - ering->rx_mini_max_pending = 0; - ering->rx_jumbo_max_pending = rx_max_pending; - } else { - ering->rx_pending = rx_pending; - ering->rx_max_pending = rx_max_pending; - ering->rx_mini_pending = 0; - ering->rx_jumbo_pending = 0; - ering->rx_mini_max_pending = 0; - ering->rx_jumbo_max_pending = 0; + rx_pending = oct->droq[0]->max_count; + tx_pending = oct->instr_queue[0]->max_count; } ering->tx_pending = tx_pending; ering->tx_max_pending = tx_max_pending; + ering->rx_pending = rx_pending; + ering->rx_max_pending = rx_max_pending; + ering->rx_mini_pending = 0; + ering->rx_jumbo_pending = 0; + ering->rx_mini_max_pending = 0; + ering->rx_jumbo_max_pending = 0; +} + +static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + struct napi_struct *napi, *n; + int i, update = 0; + + if (wait_for_pending_requests(oct)) + dev_err(&oct->pci_dev->dev, "There were pending requests\n"); + + if (lio_wait_for_instr_fetch(oct)) + dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n"); + + if (octeon_set_io_queues_off(oct)) { + dev_err(&oct->pci_dev->dev, "setting io queues off failed\n"); + return -1; + } + + /* Disable the input and output queues now. No more packets will + * arrive from Octeon. + */ + oct->fn_list.disable_io_queues(oct); + /* Delete NAPI */ + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) + netif_napi_del(napi); + + if (num_qs != oct->num_iqs) { + netif_set_real_num_rx_queues(netdev, num_qs); + netif_set_real_num_tx_queues(netdev, num_qs); + update = 1; + } + + for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) { + if (!(oct->io_qmask.oq & BIT_ULL(i))) + continue; + octeon_delete_droq(oct, i); + } + + for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) { + if (!(oct->io_qmask.iq & BIT_ULL(i))) + continue; + octeon_delete_instr_queue(oct, i); + } + + if (oct->fn_list.setup_device_regs(oct)) { + dev_err(&oct->pci_dev->dev, "Failed to configure device registers\n"); + return -1; + } + + if (liquidio_setup_io_queues(oct, 0, num_qs, num_qs)) { + dev_err(&oct->pci_dev->dev, "IO queues initialization failed\n"); + return -1; + } + + /* Enable the input and output queues for this Octeon device */ + if (oct->fn_list.enable_io_queues(oct)) { + dev_err(&oct->pci_dev->dev, "Failed to enable input/output queues"); + return -1; + } + + if (update && lio_send_queue_count_update(netdev, num_qs)) + return -1; + + return 0; +} + +static int lio_ethtool_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering) +{ + u32 rx_count, tx_count, rx_count_old, tx_count_old; + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + int stopped = 0; + + if (!OCTEON_CN23XX_PF(oct) && !OCTEON_CN23XX_VF(oct)) + return -EINVAL; + + if (ering->rx_mini_pending || ering->rx_jumbo_pending) + return -EINVAL; + + rx_count = clamp_t(u32, ering->rx_pending, CN23XX_MIN_OQ_DESCRIPTORS, + CN23XX_MAX_OQ_DESCRIPTORS); + tx_count = clamp_t(u32, ering->tx_pending, CN23XX_MIN_IQ_DESCRIPTORS, + CN23XX_MAX_IQ_DESCRIPTORS); + + rx_count_old = oct->droq[0]->max_count; + tx_count_old = oct->instr_queue[0]->max_count; + + if (rx_count == rx_count_old && tx_count == tx_count_old) + return 0; + + ifstate_set(lio, LIO_IFSTATE_RESETTING); + + if (netif_running(netdev)) { + netdev->netdev_ops->ndo_stop(netdev); + stopped = 1; + } + + /* Change RX/TX DESCS count */ + if (tx_count != tx_count_old) + CFG_SET_NUM_TX_DESCS_NIC_IF(octeon_get_conf(oct), lio->ifidx, + tx_count); + if (rx_count != rx_count_old) + CFG_SET_NUM_RX_DESCS_NIC_IF(octeon_get_conf(oct), lio->ifidx, + rx_count); + + if (lio_reset_queues(netdev, lio->linfo.num_txpciq)) + goto err_lio_reset_queues; + + if (stopped) + netdev->netdev_ops->ndo_open(netdev); + + ifstate_reset(lio, LIO_IFSTATE_RESETTING); + + return 0; + +err_lio_reset_queues: + if (tx_count != tx_count_old) + CFG_SET_NUM_TX_DESCS_NIC_IF(octeon_get_conf(oct), lio->ifidx, + tx_count_old); + if (rx_count != rx_count_old) + CFG_SET_NUM_RX_DESCS_NIC_IF(octeon_get_conf(oct), lio->ifidx, + rx_count_old); + return -EINVAL; } static u32 lio_get_msglevel(struct net_device *netdev) @@ -795,6 +1054,9 @@ lio_get_ethtool_stats(struct net_device *netdev, struct net_device_stats *netstats = &netdev->stats; int i = 0, j; + if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) + return; + netdev->netdev_ops->ndo_get_stats(netdev); octnet_get_link_stats(netdev); @@ -826,6 +1088,8 @@ lio_get_ethtool_stats(struct net_device *netdev, data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_total_fwd); /*per_core_stats[j].link_stats[i].fromhost.fw_err_pko */ data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_pko); + /*per_core_stats[j].link_stats[i].fromhost.fw_err_pki */ + data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_pki); /*per_core_stats[j].link_stats[i].fromhost.fw_err_link */ data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_err_link); /*per_core_stats[cvmx_get_core_num()].link_stats[idx].fromhost. @@ -1057,6 +1321,9 @@ static void lio_vf_get_ethtool_stats(struct net_device *netdev, struct octeon_device *oct_dev = lio->oct_dev; int i = 0, j, vj; + if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) + return; + netdev->netdev_ops->ndo_get_stats(netdev); /* sum of oct->droq[oq_no]->stats->rx_pkts_received */ data[i++] = CVM_CAST64(netstats->rx_packets); @@ -1079,7 +1346,7 @@ static void lio_vf_get_ethtool_stats(struct net_device *netdev, /* lio->link_changes */ data[i++] = CVM_CAST64(lio->link_changes); - for (vj = 0; vj < lio->linfo.num_txpciq; vj++) { + for (vj = 0; vj < oct_dev->num_iqs; vj++) { j = lio->linfo.txpciq[vj].s.q_no; /* packets to network port */ @@ -1121,7 +1388,7 @@ static void lio_vf_get_ethtool_stats(struct net_device *netdev, } /* RX */ - for (vj = 0; vj < lio->linfo.num_rxpciq; vj++) { + for (vj = 0; vj < oct_dev->num_oqs; vj++) { j = lio->linfo.rxpciq[vj].s.q_no; /* packets send to TCP/IP network stack */ @@ -1568,6 +1835,7 @@ octnet_nic_stats_callback(struct octeon_device *oct_dev, tstats->fw_total_sent = rsp_tstats->fw_total_sent; tstats->fw_total_fwd = rsp_tstats->fw_total_fwd; tstats->fw_err_pko = rsp_tstats->fw_err_pko; + tstats->fw_err_pki = rsp_tstats->fw_err_pki; tstats->fw_err_link = rsp_tstats->fw_err_link; tstats->fw_err_drop = rsp_tstats->fw_err_drop; tstats->fw_tso = rsp_tstats->fw_tso; @@ -2587,7 +2855,9 @@ static const struct ethtool_ops lio_ethtool_ops = { .get_link = ethtool_op_get_link, .get_drvinfo = lio_get_drvinfo, .get_ringparam = lio_ethtool_get_ringparam, + .set_ringparam = lio_ethtool_set_ringparam, .get_channels = lio_ethtool_get_channels, + .set_channels = lio_ethtool_set_channels, .set_phys_id = lio_set_phys_id, .get_eeprom_len = lio_get_eeprom_len, .get_eeprom = lio_get_eeprom, @@ -2612,7 +2882,9 @@ static const struct ethtool_ops lio_vf_ethtool_ops = { .get_link = ethtool_op_get_link, .get_drvinfo = lio_get_vf_drvinfo, .get_ringparam = lio_ethtool_get_ringparam, + .set_ringparam = lio_ethtool_set_ringparam, .get_channels = lio_ethtool_get_channels, + .set_channels = lio_ethtool_set_channels, .get_strings = lio_vf_get_strings, .get_ethtool_stats = lio_vf_get_ethtool_stats, .get_regs_len = lio_get_regs_len, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 120b6e537b28..e7f54948173f 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -39,10 +39,14 @@ MODULE_AUTHOR("Cavium Networks, <support@cavium.com>"); MODULE_DESCRIPTION("Cavium LiquidIO Intelligent Server Adapter Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(LIQUIDIO_VERSION); -MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_210SV_NAME LIO_FW_NAME_SUFFIX); -MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_210NV_NAME LIO_FW_NAME_SUFFIX); -MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_410NV_NAME LIO_FW_NAME_SUFFIX); -MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_23XX_NAME LIO_FW_NAME_SUFFIX); +MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_210SV_NAME + "_" LIO_FW_NAME_TYPE_NIC LIO_FW_NAME_SUFFIX); +MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_210NV_NAME + "_" LIO_FW_NAME_TYPE_NIC LIO_FW_NAME_SUFFIX); +MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_410NV_NAME + "_" LIO_FW_NAME_TYPE_NIC LIO_FW_NAME_SUFFIX); +MODULE_FIRMWARE(LIO_FW_DIR LIO_FW_BASE_NAME LIO_23XX_NAME + "_" LIO_FW_NAME_TYPE_NIC LIO_FW_NAME_SUFFIX); static int ddr_timeout = 10000; module_param(ddr_timeout, int, 0644); @@ -55,11 +59,24 @@ static int debug = -1; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "NETIF_MSG debug bits"); -static char fw_type[LIO_MAX_FW_TYPE_LEN]; -module_param_string(fw_type, fw_type, sizeof(fw_type), 0000); -MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\""); +static char fw_type[LIO_MAX_FW_TYPE_LEN] = LIO_FW_NAME_TYPE_NIC; +module_param_string(fw_type, fw_type, sizeof(fw_type), 0444); +MODULE_PARM_DESC(fw_type, "Type of firmware to be loaded. Default \"nic\". Use \"none\" to load firmware from flash."); -static int ptp_enable = 1; +static u32 console_bitmask; +module_param(console_bitmask, int, 0644); +MODULE_PARM_DESC(console_bitmask, + "Bitmask indicating which consoles have debug output redirected to syslog."); + +/** + * \brief determines if a given console has debug enabled. + * @param console console to check + * @returns 1 = enabled. 0 otherwise + */ +static int octeon_console_debug_enabled(u32 console) +{ + return (console_bitmask >> (console)) & 0x1; +} /* Polling interval for determining when NIC application is alive */ #define LIQUIDIO_STARTER_POLL_INTERVAL_MS 100 @@ -158,16 +175,13 @@ struct handshake { int started_ok; }; -struct octeon_device_priv { - /** Tasklet structures for this device. */ - struct tasklet_struct droq_tasklet; - unsigned long napi_mask; -}; - #ifdef CONFIG_PCI_IOV static int liquidio_enable_sriov(struct pci_dev *dev, int num_vfs); #endif +static int octeon_dbg_console_print(struct octeon_device *oct, u32 console_num, + char *prefix, char *suffix); + static int octeon_device_init(struct octeon_device *); static int liquidio_stop(struct net_device *netdev); static void liquidio_remove(struct pci_dev *pdev); @@ -256,32 +270,6 @@ static void force_io_queues_off(struct octeon_device *oct) } /** - * \brief wait for all pending requests to complete - * @param oct Pointer to Octeon device - * - * Called during shutdown sequence - */ -static int wait_for_pending_requests(struct octeon_device *oct) -{ - int i, pcount = 0; - - for (i = 0; i < 100; i++) { - pcount = - atomic_read(&oct->response_list - [OCTEON_ORDERED_SC_LIST].pending_req_count); - if (pcount) - schedule_timeout_uninterruptible(HZ / 10); - else - break; - } - - if (pcount) - return 1; - - return 0; -} - -/** * \brief Cause device to go quiet so it can be safely removed/reset/etc * @param oct Pointer to Octeon device */ @@ -572,7 +560,7 @@ static inline void txqs_wake(struct net_device *netdev) for (i = 0; i < netdev->num_tx_queues; i++) { int qno = lio->linfo.txpciq[i % - (lio->linfo.num_txpciq)].s.q_no; + lio->oct_dev->num_iqs].s.q_no; if (__netif_subqueue_stopped(netdev, i)) { INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, qno, @@ -652,7 +640,7 @@ static inline int check_txq_status(struct lio *lio) /* check each sub-queue state */ for (q = 0; q < numqs; q++) { iq = lio->linfo.txpciq[q % - (lio->linfo.num_txpciq)].s.q_no; + lio->oct_dev->num_iqs].s.q_no; if (octnet_iq_is_full(lio->oct_dev, iq)) continue; if (__netif_subqueue_stopped(lio->netdev, q)) { @@ -823,7 +811,8 @@ static void print_link_info(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); - if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) { + if (!ifstate_check(lio, LIO_IFSTATE_RESETTING) && + ifstate_check(lio, LIO_IFSTATE_REGISTERED)) { struct oct_link_info *linfo = &lio->linfo; if (linfo->link.s.link_up) { @@ -912,295 +901,6 @@ static inline void update_link_status(struct net_device *netdev, } } -/* Runs in interrupt context. */ -static void update_txq_status(struct octeon_device *oct, int iq_num) -{ - struct net_device *netdev; - struct lio *lio; - struct octeon_instr_queue *iq = oct->instr_queue[iq_num]; - - netdev = oct->props[iq->ifidx].netdev; - - /* This is needed because the first IQ does not have - * a netdev associated with it. - */ - if (!netdev) - return; - - lio = GET_LIO(netdev); - if (netif_is_multiqueue(netdev)) { - if (__netif_subqueue_stopped(netdev, iq->q_index) && - lio->linfo.link.s.link_up && - (!octnet_iq_is_full(oct, iq_num))) { - INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num, - tx_restart, 1); - netif_wake_subqueue(netdev, iq->q_index); - } - } else if (netif_queue_stopped(netdev) && - lio->linfo.link.s.link_up && - (!octnet_iq_is_full(oct, lio->txq))) { - INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, - lio->txq, tx_restart, 1); - netif_wake_queue(netdev); - } -} - -static -int liquidio_schedule_msix_droq_pkt_handler(struct octeon_droq *droq, u64 ret) -{ - struct octeon_device *oct = droq->oct_dev; - struct octeon_device_priv *oct_priv = - (struct octeon_device_priv *)oct->priv; - - if (droq->ops.poll_mode) { - droq->ops.napi_fn(droq); - } else { - if (ret & MSIX_PO_INT) { - tasklet_schedule(&oct_priv->droq_tasklet); - return 1; - } - /* this will be flushed periodically by check iq db */ - if (ret & MSIX_PI_INT) - return 0; - } - return 0; -} - -/** - * \brief Droq packet processor sceduler - * @param oct octeon device - */ -static void liquidio_schedule_droq_pkt_handlers(struct octeon_device *oct) -{ - struct octeon_device_priv *oct_priv = - (struct octeon_device_priv *)oct->priv; - u64 oq_no; - struct octeon_droq *droq; - - if (oct->int_status & OCT_DEV_INTR_PKT_DATA) { - for (oq_no = 0; oq_no < MAX_OCTEON_OUTPUT_QUEUES(oct); - oq_no++) { - if (!(oct->droq_intr & BIT_ULL(oq_no))) - continue; - - droq = oct->droq[oq_no]; - - if (droq->ops.poll_mode) { - droq->ops.napi_fn(droq); - oct_priv->napi_mask |= (1 << oq_no); - } else { - tasklet_schedule(&oct_priv->droq_tasklet); - } - } - } -} - -static irqreturn_t -liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev) -{ - u64 ret; - struct octeon_ioq_vector *ioq_vector = (struct octeon_ioq_vector *)dev; - struct octeon_device *oct = ioq_vector->oct_dev; - struct octeon_droq *droq = oct->droq[ioq_vector->droq_index]; - - ret = oct->fn_list.msix_interrupt_handler(ioq_vector); - - if ((ret & MSIX_PO_INT) || (ret & MSIX_PI_INT)) - liquidio_schedule_msix_droq_pkt_handler(droq, ret); - - return IRQ_HANDLED; -} - -/** - * \brief Interrupt handler for octeon - * @param irq unused - * @param dev octeon device - */ -static -irqreturn_t liquidio_legacy_intr_handler(int irq __attribute__((unused)), - void *dev) -{ - struct octeon_device *oct = (struct octeon_device *)dev; - irqreturn_t ret; - - /* Disable our interrupts for the duration of ISR */ - oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR); - - ret = oct->fn_list.process_interrupt_regs(oct); - - if (ret == IRQ_HANDLED) - liquidio_schedule_droq_pkt_handlers(oct); - - /* Re-enable our interrupts */ - if (!(atomic_read(&oct->status) == OCT_DEV_IN_RESET)) - oct->fn_list.enable_interrupt(oct, OCTEON_ALL_INTR); - - return ret; -} - -/** - * \brief Setup interrupt for octeon device - * @param oct octeon device - * - * Enable interrupt in Octeon device as given in the PCI interrupt mask. - */ -static int octeon_setup_interrupt(struct octeon_device *oct) -{ - int irqret, err; - struct msix_entry *msix_entries; - int i; - int num_ioq_vectors; - int num_alloc_ioq_vectors; - char *queue_irq_names = NULL; - char *aux_irq_name = NULL; - - if (OCTEON_CN23XX_PF(oct) && oct->msix_on) { - oct->num_msix_irqs = oct->sriov_info.num_pf_rings; - /* one non ioq interrupt for handling sli_mac_pf_int_sum */ - oct->num_msix_irqs += 1; - - /* allocate storage for the names assigned to each irq */ - oct->irq_name_storage = - kcalloc((MAX_IOQ_INTERRUPTS_PER_PF + 1), INTRNAMSIZ, - GFP_KERNEL); - if (!oct->irq_name_storage) { - dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n"); - return -ENOMEM; - } - - queue_irq_names = oct->irq_name_storage; - aux_irq_name = &queue_irq_names - [IRQ_NAME_OFF(MAX_IOQ_INTERRUPTS_PER_PF)]; - - oct->msix_entries = kcalloc( - oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL); - if (!oct->msix_entries) { - dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n"); - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return -ENOMEM; - } - - msix_entries = (struct msix_entry *)oct->msix_entries; - /*Assumption is that pf msix vectors start from pf srn to pf to - * trs and not from 0. if not change this code - */ - for (i = 0; i < oct->num_msix_irqs - 1; i++) - msix_entries[i].entry = oct->sriov_info.pf_srn + i; - msix_entries[oct->num_msix_irqs - 1].entry = - oct->sriov_info.trs; - num_alloc_ioq_vectors = pci_enable_msix_range( - oct->pci_dev, msix_entries, - oct->num_msix_irqs, - oct->num_msix_irqs); - if (num_alloc_ioq_vectors < 0) { - dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n"); - kfree(oct->msix_entries); - oct->msix_entries = NULL; - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return num_alloc_ioq_vectors; - } - dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n"); - - num_ioq_vectors = oct->num_msix_irqs; - - /** For PF, there is one non-ioq interrupt handler */ - num_ioq_vectors -= 1; - - snprintf(aux_irq_name, INTRNAMSIZ, - "LiquidIO%u-pf%u-aux", oct->octeon_id, oct->pf_num); - irqret = request_irq(msix_entries[num_ioq_vectors].vector, - liquidio_legacy_intr_handler, 0, - aux_irq_name, oct); - if (irqret) { - dev_err(&oct->pci_dev->dev, - "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", - irqret); - pci_disable_msix(oct->pci_dev); - kfree(oct->msix_entries); - oct->msix_entries = NULL; - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return irqret; - } - - for (i = 0; i < num_ioq_vectors; i++) { - snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ, - "LiquidIO%u-pf%u-rxtx-%u", - oct->octeon_id, oct->pf_num, i); - - irqret = request_irq(msix_entries[i].vector, - liquidio_msix_intr_handler, 0, - &queue_irq_names[IRQ_NAME_OFF(i)], - &oct->ioq_vector[i]); - if (irqret) { - dev_err(&oct->pci_dev->dev, - "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", - irqret); - /** Freeing the non-ioq irq vector here . */ - free_irq(msix_entries[num_ioq_vectors].vector, - oct); - - while (i) { - i--; - /** clearing affinity mask. */ - irq_set_affinity_hint( - msix_entries[i].vector, NULL); - free_irq(msix_entries[i].vector, - &oct->ioq_vector[i]); - } - pci_disable_msix(oct->pci_dev); - kfree(oct->msix_entries); - oct->msix_entries = NULL; - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return irqret; - } - oct->ioq_vector[i].vector = msix_entries[i].vector; - /* assign the cpu mask for this msix interrupt vector */ - irq_set_affinity_hint( - msix_entries[i].vector, - (&oct->ioq_vector[i].affinity_mask)); - } - dev_dbg(&oct->pci_dev->dev, "OCTEON[%d]: MSI-X enabled\n", - oct->octeon_id); - } else { - err = pci_enable_msi(oct->pci_dev); - if (err) - dev_warn(&oct->pci_dev->dev, "Reverting to legacy interrupts. Error: %d\n", - err); - else - oct->flags |= LIO_FLAG_MSI_ENABLED; - - /* allocate storage for the names assigned to the irq */ - oct->irq_name_storage = kcalloc(1, INTRNAMSIZ, GFP_KERNEL); - if (!oct->irq_name_storage) - return -ENOMEM; - - queue_irq_names = oct->irq_name_storage; - - snprintf(&queue_irq_names[IRQ_NAME_OFF(0)], INTRNAMSIZ, - "LiquidIO%u-pf%u-rxtx-%u", - oct->octeon_id, oct->pf_num, 0); - - irqret = request_irq(oct->pci_dev->irq, - liquidio_legacy_intr_handler, - IRQF_SHARED, - &queue_irq_names[IRQ_NAME_OFF(0)], oct); - if (irqret) { - if (oct->flags & LIO_FLAG_MSI_ENABLED) - pci_disable_msi(oct->pci_dev); - dev_err(&oct->pci_dev->dev, "Request IRQ failed with code: %d\n", - irqret); - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return irqret; - } - } - return 0; -} - static struct octeon_device *get_other_octeon_device(struct octeon_device *oct) { struct octeon_device *other_oct; @@ -1344,6 +1044,13 @@ liquidio_probe(struct pci_dev *pdev, if (pdev->device == OCTEON_CN23XX_PF_VID) oct_dev->msix_on = LIO_FLAG_MSIX_ENABLED; + /* Enable PTP for 6XXX Device */ + if (((pdev->device == OCTEON_CN66XX) || + (pdev->device == OCTEON_CN68XX))) + oct_dev->ptp_enable = true; + else + oct_dev->ptp_enable = false; + dev_info(&pdev->dev, "Initializing device %x:%x.\n", (u32)pdev->vendor, (u32)pdev->device); @@ -1415,6 +1122,33 @@ static bool fw_type_is_none(void) } /** + * \brief PCI FLR for each Octeon device. + * @param oct octeon device + */ +static void octeon_pci_flr(struct octeon_device *oct) +{ + int rc; + + pci_save_state(oct->pci_dev); + + pci_cfg_access_lock(oct->pci_dev); + + /* Quiesce the device completely */ + pci_write_config_word(oct->pci_dev, PCI_COMMAND, + PCI_COMMAND_INTX_DISABLE); + + rc = __pci_reset_function_locked(oct->pci_dev); + + if (rc != 0) + dev_err(&oct->pci_dev->dev, "Error %d resetting PCI function %d\n", + rc, oct->pf_num); + + pci_cfg_access_unlock(oct->pci_dev); + + pci_restore_state(oct->pci_dev); +} + +/** *\brief Destroy resources associated with octeon device * @param pdev PCI device structure * @param ent unused @@ -1474,11 +1208,15 @@ static void octeon_destroy_resources(struct octeon_device *oct) if (oct->msix_on) { msix_entries = (struct msix_entry *)oct->msix_entries; for (i = 0; i < oct->num_msix_irqs - 1; i++) { - /* clear the affinity_cpumask */ - irq_set_affinity_hint(msix_entries[i].vector, - NULL); - free_irq(msix_entries[i].vector, - &oct->ioq_vector[i]); + if (oct->ioq_vector[i].vector) { + /* clear the affinity_cpumask */ + irq_set_affinity_hint( + msix_entries[i].vector, + NULL); + free_irq(msix_entries[i].vector, + &oct->ioq_vector[i]); + oct->ioq_vector[i].vector = 0; + } } /* non-iov vector's argument is oct struct */ free_irq(msix_entries[i].vector, oct); @@ -1558,14 +1296,16 @@ static void octeon_destroy_resources(struct octeon_device *oct) case OCT_DEV_PCI_MAP_DONE: refcount = octeon_deregister_device(oct); - if (!fw_type_is_none()) { - /* Soft reset the octeon device before exiting. - * Implementation note: here, we reset the device - * if it is a CN6XXX OR the last CN23XX device. - */ - if (OCTEON_CN6XXX(oct) || !refcount) - oct->fn_list.soft_reset(oct); - } + /* Soft reset the octeon device before exiting. + * However, if fw was loaded from card (i.e. autoboot), + * perform an FLR instead. + * Implementation note: only soft-reset the device + * if it is a CN6XXX OR the LAST CN23XX device. + */ + if (fw_type_is_none()) + octeon_pci_flr(oct); + else if (OCTEON_CN6XXX(oct) || !refcount) + oct->fn_list.soft_reset(oct); octeon_unmap_pci_barx(oct, 0); octeon_unmap_pci_barx(oct, 1); @@ -1698,15 +1438,6 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) if (atomic_read(&lio->ifstate) & LIO_IFSTATE_RUNNING) liquidio_stop(netdev); - if (fw_type_is_none()) { - struct octnic_ctrl_pkt nctrl; - - memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); - nctrl.ncmd.s.cmd = OCTNET_CMD_RESET_PF; - nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - octnet_send_nic_ctrl_pkt(oct, &nctrl); - } - if (oct->props[lio->ifidx].napi_enabled == 1) { list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) napi_disable(napi); @@ -1717,6 +1448,10 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) oct->droq[0]->ops.poll_mode = 0; } + /* Delete NAPI */ + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) + netif_napi_del(napi); + if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) unregister_netdev(netdev); @@ -1754,7 +1489,7 @@ static int liquidio_stop_nic_module(struct octeon_device *oct) for (i = 0; i < oct->ifcount; i++) { lio = GET_LIO(oct->props[i].netdev); - for (j = 0; j < lio->linfo.num_rxpciq; j++) + for (j = 0; j < oct->num_oqs; j++) octeon_unregister_droq_ops(oct, lio->linfo.rxpciq[j].s.q_no); } @@ -1825,6 +1560,13 @@ static int octeon_chip_specific_setup(struct octeon_device *oct) case OCTEON_CN23XX_PCIID_PF: oct->chip_id = OCTEON_CN23XX_PF_VID; ret = setup_cn23xx_octeon_pf_device(oct); + if (ret) + break; +#ifdef CONFIG_PCI_IOV + if (!ret) + pci_sriov_set_totalvfs(oct->pci_dev, + oct->sriov_info.max_vfs); +#endif s = "CN23XX"; break; @@ -1889,7 +1631,7 @@ static inline int check_txq_state(struct lio *lio, struct sk_buff *skb) if (netif_is_multiqueue(lio->netdev)) { q = skb->queue_mapping; - iq = lio->linfo.txpciq[(q % (lio->linfo.num_txpciq))].s.q_no; + iq = lio->linfo.txpciq[(q % lio->oct_dev->num_iqs)].s.q_no; } else { iq = lio->txq; q = iq; @@ -2192,11 +1934,6 @@ static int load_firmware(struct octeon_device *oct) char fw_name[LIO_MAX_FW_FILENAME_LEN]; char *tmp_fw_type; - if (fw_type_is_none()) { - dev_info(&oct->pci_dev->dev, "Skipping firmware load\n"); - return ret; - } - if (fw_type[0] == '\0') tmp_fw_type = LIO_FW_NAME_TYPE_NIC; else @@ -2222,43 +1959,6 @@ static int load_firmware(struct octeon_device *oct) } /** - * \brief Setup output queue - * @param oct octeon device - * @param q_no which queue - * @param num_descs how many descriptors - * @param desc_size size of each descriptor - * @param app_ctx application context - */ -static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs, - int desc_size, void *app_ctx) -{ - int ret_val = 0; - - dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no); - /* droq creation and local register settings. */ - ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx); - if (ret_val < 0) - return ret_val; - - if (ret_val == 1) { - dev_dbg(&oct->pci_dev->dev, "Using default droq %d\n", q_no); - return 0; - } - /* tasklet creation for the droq */ - - /* Enable the droq queues */ - octeon_set_droq_pkt_op(oct, q_no, 1); - - /* Send Credit for Octeon Output queues. Credits are always - * sent after the output queue is enabled. - */ - writel(oct->droq[q_no]->max_count, - oct->droq[q_no]->pkts_credit_reg); - - return ret_val; -} - -/** * \brief Callback for getting interface configuration * @param status status of request * @param buf pointer to resp structure @@ -2291,352 +1991,6 @@ static void if_cfg_callback(struct octeon_device *oct, wake_up_interruptible(&ctx->wc); } -/** Routine to push packets arriving on Octeon interface upto network layer. - * @param oct_id - octeon device id. - * @param skbuff - skbuff struct to be passed to network layer. - * @param len - size of total data received. - * @param rh - Control header associated with the packet - * @param param - additional control data with the packet - * @param arg - farg registered in droq_ops - */ -static void -liquidio_push_packet(u32 octeon_id __attribute__((unused)), - void *skbuff, - u32 len, - union octeon_rh *rh, - void *param, - void *arg) -{ - struct napi_struct *napi = param; - struct sk_buff *skb = (struct sk_buff *)skbuff; - struct skb_shared_hwtstamps *shhwtstamps; - u64 ns; - u16 vtag = 0; - u32 r_dh_off; - struct net_device *netdev = (struct net_device *)arg; - struct octeon_droq *droq = container_of(param, struct octeon_droq, - napi); - if (netdev) { - int packet_was_received; - struct lio *lio = GET_LIO(netdev); - struct octeon_device *oct = lio->oct_dev; - - /* Do not proceed if the interface is not in RUNNING state. */ - if (!ifstate_check(lio, LIO_IFSTATE_RUNNING)) { - recv_buffer_free(skb); - droq->stats.rx_dropped++; - return; - } - - skb->dev = netdev; - - skb_record_rx_queue(skb, droq->q_no); - if (likely(len > MIN_SKB_SIZE)) { - struct octeon_skb_page_info *pg_info; - unsigned char *va; - - pg_info = ((struct octeon_skb_page_info *)(skb->cb)); - if (pg_info->page) { - /* For Paged allocation use the frags */ - va = page_address(pg_info->page) + - pg_info->page_offset; - memcpy(skb->data, va, MIN_SKB_SIZE); - skb_put(skb, MIN_SKB_SIZE); - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - pg_info->page, - pg_info->page_offset + - MIN_SKB_SIZE, - len - MIN_SKB_SIZE, - LIO_RXBUFFER_SZ); - } - } else { - struct octeon_skb_page_info *pg_info = - ((struct octeon_skb_page_info *)(skb->cb)); - skb_copy_to_linear_data(skb, page_address(pg_info->page) - + pg_info->page_offset, len); - skb_put(skb, len); - put_page(pg_info->page); - } - - r_dh_off = (rh->r_dh.len - 1) * BYTES_PER_DHLEN_UNIT; - - if (((oct->chip_id == OCTEON_CN66XX) || - (oct->chip_id == OCTEON_CN68XX)) && - ptp_enable) { - if (rh->r_dh.has_hwtstamp) { - /* timestamp is included from the hardware at - * the beginning of the packet. - */ - if (ifstate_check - (lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED)) { - /* Nanoseconds are in the first 64-bits - * of the packet. - */ - memcpy(&ns, (skb->data + r_dh_off), - sizeof(ns)); - r_dh_off -= BYTES_PER_DHLEN_UNIT; - shhwtstamps = skb_hwtstamps(skb); - shhwtstamps->hwtstamp = - ns_to_ktime(ns + - lio->ptp_adjust); - } - } - } - - if (rh->r_dh.has_hash) { - __be32 *hash_be = (__be32 *)(skb->data + r_dh_off); - u32 hash = be32_to_cpu(*hash_be); - - skb_set_hash(skb, hash, PKT_HASH_TYPE_L4); - r_dh_off -= BYTES_PER_DHLEN_UNIT; - } - - skb_pull(skb, rh->r_dh.len * BYTES_PER_DHLEN_UNIT); - - skb->protocol = eth_type_trans(skb, skb->dev); - if ((netdev->features & NETIF_F_RXCSUM) && - (((rh->r_dh.encap_on) && - (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) || - (!(rh->r_dh.encap_on) && - (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED)))) - /* checksum has already been verified */ - skb->ip_summed = CHECKSUM_UNNECESSARY; - else - skb->ip_summed = CHECKSUM_NONE; - - /* Setting Encapsulation field on basis of status received - * from the firmware - */ - if (rh->r_dh.encap_on) { - skb->encapsulation = 1; - skb->csum_level = 1; - droq->stats.rx_vxlan++; - } - - /* inbound VLAN tag */ - if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && - (rh->r_dh.vlan != 0)) { - u16 vid = rh->r_dh.vlan; - u16 priority = rh->r_dh.priority; - - vtag = priority << 13 | vid; - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vtag); - } - - packet_was_received = napi_gro_receive(napi, skb) != GRO_DROP; - - if (packet_was_received) { - droq->stats.rx_bytes_received += len; - droq->stats.rx_pkts_received++; - } else { - droq->stats.rx_dropped++; - netif_info(lio, rx_err, lio->netdev, - "droq:%d error rx_dropped:%llu\n", - droq->q_no, droq->stats.rx_dropped); - } - - } else { - recv_buffer_free(skb); - } -} - -/** - * \brief wrapper for calling napi_schedule - * @param param parameters to pass to napi_schedule - * - * Used when scheduling on different CPUs - */ -static void napi_schedule_wrapper(void *param) -{ - struct napi_struct *napi = param; - - napi_schedule(napi); -} - -/** - * \brief callback when receive interrupt occurs and we are in NAPI mode - * @param arg pointer to octeon output queue - */ -static void liquidio_napi_drv_callback(void *arg) -{ - struct octeon_device *oct; - struct octeon_droq *droq = arg; - int this_cpu = smp_processor_id(); - - oct = droq->oct_dev; - - if (OCTEON_CN23XX_PF(oct) || droq->cpu_id == this_cpu) { - napi_schedule_irqoff(&droq->napi); - } else { - call_single_data_t *csd = &droq->csd; - - csd->func = napi_schedule_wrapper; - csd->info = &droq->napi; - csd->flags = 0; - - smp_call_function_single_async(droq->cpu_id, csd); - } -} - -/** - * \brief Entry point for NAPI polling - * @param napi NAPI structure - * @param budget maximum number of items to process - */ -static int liquidio_napi_poll(struct napi_struct *napi, int budget) -{ - struct octeon_droq *droq; - int work_done; - int tx_done = 0, iq_no; - struct octeon_instr_queue *iq; - struct octeon_device *oct; - - droq = container_of(napi, struct octeon_droq, napi); - oct = droq->oct_dev; - iq_no = droq->q_no; - /* Handle Droq descriptors */ - work_done = octeon_process_droq_poll_cmd(oct, droq->q_no, - POLL_EVENT_PROCESS_PKTS, - budget); - - /* Flush the instruction queue */ - iq = oct->instr_queue[iq_no]; - if (iq) { - if (atomic_read(&iq->instr_pending)) - /* Process iq buffers with in the budget limits */ - tx_done = octeon_flush_iq(oct, iq, budget); - else - tx_done = 1; - /* Update iq read-index rather than waiting for next interrupt. - * Return back if tx_done is false. - */ - update_txq_status(oct, iq_no); - } else { - dev_err(&oct->pci_dev->dev, "%s: iq (%d) num invalid\n", - __func__, iq_no); - } - - /* force enable interrupt if reg cnts are high to avoid wraparound */ - if ((work_done < budget && tx_done) || - (iq && iq->pkt_in_done >= MAX_REG_CNT) || - (droq->pkt_count >= MAX_REG_CNT)) { - tx_done = 1; - napi_complete_done(napi, work_done); - octeon_process_droq_poll_cmd(droq->oct_dev, droq->q_no, - POLL_EVENT_ENABLE_INTR, 0); - return 0; - } - - return (!tx_done) ? (budget) : (work_done); -} - -/** - * \brief Setup input and output queues - * @param octeon_dev octeon device - * @param ifidx Interface Index - * - * Note: Queues are with respect to the octeon device. Thus - * an input queue is for egress packets, and output queues - * are for ingress packets. - */ -static inline int setup_io_queues(struct octeon_device *octeon_dev, - int ifidx) -{ - struct octeon_droq_ops droq_ops; - struct net_device *netdev; - static int cpu_id; - static int cpu_id_modulus; - struct octeon_droq *droq; - struct napi_struct *napi; - int q, q_no, retval = 0; - struct lio *lio; - int num_tx_descs; - - netdev = octeon_dev->props[ifidx].netdev; - - lio = GET_LIO(netdev); - - memset(&droq_ops, 0, sizeof(struct octeon_droq_ops)); - - droq_ops.fptr = liquidio_push_packet; - droq_ops.farg = (void *)netdev; - - droq_ops.poll_mode = 1; - droq_ops.napi_fn = liquidio_napi_drv_callback; - cpu_id = 0; - cpu_id_modulus = num_present_cpus(); - - /* set up DROQs. */ - for (q = 0; q < lio->linfo.num_rxpciq; q++) { - q_no = lio->linfo.rxpciq[q].s.q_no; - dev_dbg(&octeon_dev->pci_dev->dev, - "setup_io_queues index:%d linfo.rxpciq.s.q_no:%d\n", - q, q_no); - retval = octeon_setup_droq(octeon_dev, q_no, - CFG_GET_NUM_RX_DESCS_NIC_IF - (octeon_get_conf(octeon_dev), - lio->ifidx), - CFG_GET_NUM_RX_BUF_SIZE_NIC_IF - (octeon_get_conf(octeon_dev), - lio->ifidx), NULL); - if (retval) { - dev_err(&octeon_dev->pci_dev->dev, - "%s : Runtime DROQ(RxQ) creation failed.\n", - __func__); - return 1; - } - - droq = octeon_dev->droq[q_no]; - napi = &droq->napi; - dev_dbg(&octeon_dev->pci_dev->dev, "netif_napi_add netdev:%llx oct:%llx pf_num:%d\n", - (u64)netdev, (u64)octeon_dev, octeon_dev->pf_num); - netif_napi_add(netdev, napi, liquidio_napi_poll, 64); - - /* designate a CPU for this droq */ - droq->cpu_id = cpu_id; - cpu_id++; - if (cpu_id >= cpu_id_modulus) - cpu_id = 0; - - octeon_register_droq_ops(octeon_dev, q_no, &droq_ops); - } - - if (OCTEON_CN23XX_PF(octeon_dev)) { - /* 23XX PF can receive control messages (via the first PF-owned - * droq) from the firmware even if the ethX interface is down, - * so that's why poll_mode must be off for the first droq. - */ - octeon_dev->droq[0]->ops.poll_mode = 0; - } - - /* set up IQs. */ - for (q = 0; q < lio->linfo.num_txpciq; q++) { - num_tx_descs = CFG_GET_NUM_TX_DESCS_NIC_IF(octeon_get_conf - (octeon_dev), - lio->ifidx); - retval = octeon_setup_iq(octeon_dev, ifidx, q, - lio->linfo.txpciq[q], num_tx_descs, - netdev_get_tx_queue(netdev, q)); - if (retval) { - dev_err(&octeon_dev->pci_dev->dev, - " %s : Runtime IQ(TxQ) creation failed.\n", - __func__); - return 1; - } - - if (octeon_dev->ioq_vector) { - struct octeon_ioq_vector *ioq_vector; - - ioq_vector = &octeon_dev->ioq_vector[q]; - netif_set_xps_queue(netdev, - &ioq_vector->affinity_mask, - ioq_vector->iq_index); - } - } - - return 0; -} - /** * \brief Poll routine for checking transmit queue status * @param work work_struct data structure @@ -2707,8 +2061,7 @@ static int liquidio_open(struct net_device *netdev) oct->droq[0]->ops.poll_mode = 1; } - if ((oct->chip_id == OCTEON_CN66XX || oct->chip_id == OCTEON_CN68XX) && - ptp_enable) + if (oct->ptp_enable) oct_ptp_open(netdev); ifstate_set(lio, LIO_IFSTATE_RUNNING); @@ -2746,6 +2099,17 @@ static int liquidio_stop(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct napi_struct *napi, *n; + + if (oct->props[lio->ifidx].napi_enabled) { + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) + napi_disable(napi); + + oct->props[lio->ifidx].napi_enabled = 0; + + if (OCTEON_CN23XX_PF(oct)) + oct->droq[0]->ops.poll_mode = 0; + } ifstate_reset(lio, LIO_IFSTATE_RUNNING); @@ -2916,7 +2280,10 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) oct = lio->oct_dev; - for (i = 0; i < lio->linfo.num_txpciq; i++) { + if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) + return stats; + + for (i = 0; i < oct->num_iqs; i++) { iq_no = lio->linfo.txpciq[i].s.q_no; iq_stats = &oct->instr_queue[iq_no]->stats; pkts += iq_stats->tx_done; @@ -2932,7 +2299,7 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) drop = 0; bytes = 0; - for (i = 0; i < lio->linfo.num_rxpciq; i++) { + for (i = 0; i < oct->num_oqs; i++) { oq_no = lio->linfo.rxpciq[i].s.q_no; oq_stats = &oct->droq[oq_no]->stats; pkts += oq_stats->rx_pkts_received; @@ -3052,8 +2419,7 @@ static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) switch (cmd) { case SIOCSHWTSTAMP: - if ((lio->oct_dev->chip_id == OCTEON_CN66XX || - lio->oct_dev->chip_id == OCTEON_CN68XX) && ptp_enable) + if (lio->oct_dev->ptp_enable) return hwtstamp_ioctl(netdev, ifr); default: return -EOPNOTSUPP; @@ -4188,7 +3554,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) */ lio->txq = lio->linfo.txpciq[0].s.q_no; lio->rxq = lio->linfo.rxpciq[0].s.q_no; - if (setup_io_queues(octeon_dev, i)) { + if (liquidio_setup_io_queues(octeon_dev, i, + lio->linfo.num_txpciq, + lio->linfo.num_rxpciq)) { dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n"); goto setup_nic_dev_fail; } @@ -4516,6 +3884,7 @@ static int octeon_device_init(struct octeon_device *octeon_dev) int j, ret; int fw_loaded = 0; char bootcmd[] = "\n"; + char *dbg_enb = NULL; struct octeon_device_priv *oct_priv = (struct octeon_device_priv *)octeon_dev->priv; atomic_set(&octeon_dev->status, OCT_DEV_BEGIN_STATE); @@ -4548,18 +3917,16 @@ static int octeon_device_init(struct octeon_device *octeon_dev) octeon_dev->app_mode = CVM_DRV_INVALID_APP; if (OCTEON_CN23XX_PF(octeon_dev)) { - if (!cn23xx_fw_loaded(octeon_dev)) { + if (!cn23xx_fw_loaded(octeon_dev) && !fw_type_is_none()) { fw_loaded = 0; - if (!fw_type_is_none()) { - /* Do a soft reset of the Octeon device. */ - if (octeon_dev->fn_list.soft_reset(octeon_dev)) - return 1; - /* things might have changed */ - if (!cn23xx_fw_loaded(octeon_dev)) - fw_loaded = 0; - else - fw_loaded = 1; - } + /* Do a soft reset of the Octeon device. */ + if (octeon_dev->fn_list.soft_reset(octeon_dev)) + return 1; + /* things might have changed */ + if (!cn23xx_fw_loaded(octeon_dev)) + fw_loaded = 0; + else + fw_loaded = 1; } else { fw_loaded = 1; } @@ -4666,7 +4033,8 @@ static int octeon_device_init(struct octeon_device *octeon_dev) /* Setup the interrupt handler and record the INT SUM register address */ - if (octeon_setup_interrupt(octeon_dev)) + if (octeon_setup_interrupt(octeon_dev, + octeon_dev->sriov_info.num_pf_rings)) return 1; /* Enable Octeon device interrupts */ @@ -4674,6 +4042,18 @@ static int octeon_device_init(struct octeon_device *octeon_dev) atomic_set(&octeon_dev->status, OCT_DEV_INTR_SET_DONE); + /* Send Credit for Octeon Output queues. Credits are always sent BEFORE + * the output queue is enabled. + * This ensures that we'll receive the f/w CORE DRV_ACTIVE message in + * case we've configured CN23XX_SLI_GBL_CONTROL[NOPTR_D] = 0. + * Otherwise, it is possible that the DRV_ACTIVE message will be sent + * before any credits have been issued, causing the ring to be reset + * (and the f/w appear to never have started). + */ + for (j = 0; j < octeon_dev->num_oqs; j++) + writel(octeon_dev->droq[j]->max_count, + octeon_dev->droq[j]->pkts_credit_reg); + /* Enable the input and output queues for this Octeon device */ ret = octeon_dev->fn_list.enable_io_queues(octeon_dev); if (ret) { @@ -4722,10 +4102,19 @@ static int octeon_device_init(struct octeon_device *octeon_dev) dev_err(&octeon_dev->pci_dev->dev, "Could not access board consoles\n"); return 1; } - ret = octeon_add_console(octeon_dev, 0); + /* If console debug enabled, specify empty string to use default + * enablement ELSE specify NULL string for 'disabled'. + */ + dbg_enb = octeon_console_debug_enabled(0) ? "" : NULL; + ret = octeon_add_console(octeon_dev, 0, dbg_enb); if (ret) { dev_err(&octeon_dev->pci_dev->dev, "Could not access board console\n"); return 1; + } else if (octeon_console_debug_enabled(0)) { + /* If console was added AND we're logging console output + * then set our console print function. + */ + octeon_dev->console[0].print = octeon_dbg_console_print; } atomic_set(&octeon_dev->status, OCT_DEV_CONSOLE_INIT_DONE); @@ -4736,12 +4125,6 @@ static int octeon_device_init(struct octeon_device *octeon_dev) dev_err(&octeon_dev->pci_dev->dev, "Could not load firmware to board\n"); return 1; } - /* set bit 1 of SLI_SCRATCH_1 to indicate that firmware is - * loaded - */ - if (OCTEON_CN23XX_PF(octeon_dev)) - octeon_write_csr64(octeon_dev, CN23XX_SLI_SCRATCH1, - 2ULL); } handshake[octeon_dev->octeon_id].init_ok = 1; @@ -4749,14 +4132,33 @@ static int octeon_device_init(struct octeon_device *octeon_dev) atomic_set(&octeon_dev->status, OCT_DEV_HOST_OK); - /* Send Credit for Octeon Output queues. Credits are always sent after - * the output queue is enabled. - */ - for (j = 0; j < octeon_dev->num_oqs; j++) - writel(octeon_dev->droq[j]->max_count, - octeon_dev->droq[j]->pkts_credit_reg); + return 0; +} + +/** + * \brief Debug console print function + * @param octeon_dev octeon device + * @param console_num console number + * @param prefix first portion of line to display + * @param suffix second portion of line to display + * + * The OCTEON debug console outputs entire lines (excluding '\n'). + * Normally, the line will be passed in the 'prefix' parameter. + * However, due to buffering, it is possible for a line to be split into two + * parts, in which case they will be passed as the 'prefix' parameter and + * 'suffix' parameter. + */ +static int octeon_dbg_console_print(struct octeon_device *oct, u32 console_num, + char *prefix, char *suffix) +{ + if (prefix && suffix) + dev_info(&oct->pci_dev->dev, "%u: %s%s\n", console_num, prefix, + suffix); + else if (prefix) + dev_info(&oct->pci_dev->dev, "%u: %s\n", console_num, prefix); + else if (suffix) + dev_info(&oct->pci_dev->dev, "%u: %s\n", console_num, suffix); - /* Packets can start arriving on the output queues from this point. */ return 0; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 9b247102eb92..2e993ce43b66 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -107,12 +107,6 @@ struct octnic_gather { dma_addr_t sg_dma_ptr; }; -struct octeon_device_priv { - /* Tasklet structures for this device. */ - struct tasklet_struct droq_tasklet; - unsigned long napi_mask; -}; - static int liquidio_vf_probe(struct pci_dev *pdev, const struct pci_device_id *ent); static void liquidio_vf_remove(struct pci_dev *pdev); @@ -123,7 +117,7 @@ static int lio_wait_for_oq_pkts(struct octeon_device *oct) { struct octeon_device_priv *oct_priv = (struct octeon_device_priv *)oct->priv; - int retry = MAX_VF_IP_OP_PENDING_PKT_COUNT; + int retry = MAX_IO_PENDING_PKT_COUNT; int pkt_cnt = 0, pending_pkts; int i; @@ -148,32 +142,6 @@ static int lio_wait_for_oq_pkts(struct octeon_device *oct) } /** - * \brief wait for all pending requests to complete - * @param oct Pointer to Octeon device - * - * Called during shutdown sequence - */ -static int wait_for_pending_requests(struct octeon_device *oct) -{ - int i, pcount = 0; - - for (i = 0; i < MAX_VF_IP_OP_PENDING_PKT_COUNT; i++) { - pcount = atomic_read( - &oct->response_list[OCTEON_ORDERED_SC_LIST] - .pending_req_count); - if (pcount) - schedule_timeout_uninterruptible(HZ / 10); - else - break; - } - - if (pcount) - return 1; - - return 0; -} - -/** * \brief Cause device to go quiet so it can be safely removed/reset/etc * @param oct Pointer to Octeon device */ @@ -374,7 +342,7 @@ static void txqs_wake(struct net_device *netdev) int i; for (i = 0; i < netdev->num_tx_queues; i++) { - int qno = lio->linfo.txpciq[i % (lio->linfo.num_txpciq)] + int qno = lio->linfo.txpciq[i % lio->oct_dev->num_iqs] .s.q_no; if (__netif_subqueue_stopped(netdev, i)) { INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, qno, @@ -574,7 +542,8 @@ static void print_link_info(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); - if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) { + if (!ifstate_check(lio, LIO_IFSTATE_RESETTING) && + ifstate_check(lio, LIO_IFSTATE_REGISTERED)) { struct oct_link_info *linfo = &lio->linfo; if (linfo->link.s.link_up) { @@ -661,6 +630,12 @@ static void update_link_status(struct net_device *netdev, txqs_stop(netdev); } + if (lio->linfo.link.s.mtu != netdev->max_mtu) { + dev_info(&oct->pci_dev->dev, "Max MTU Changed from %d to %d\n", + netdev->max_mtu, lio->linfo.link.s.mtu); + netdev->max_mtu = lio->linfo.link.s.mtu; + } + if (lio->linfo.link.s.mtu < netdev->mtu) { dev_warn(&oct->pci_dev->dev, "PF has changed the MTU for gmx port. Reducing the mtu from %d to %d\n", @@ -673,167 +648,6 @@ static void update_link_status(struct net_device *netdev, } } -static void update_txq_status(struct octeon_device *oct, int iq_num) -{ - struct octeon_instr_queue *iq = oct->instr_queue[iq_num]; - struct net_device *netdev; - struct lio *lio; - - netdev = oct->props[iq->ifidx].netdev; - lio = GET_LIO(netdev); - if (netif_is_multiqueue(netdev)) { - if (__netif_subqueue_stopped(netdev, iq->q_index) && - lio->linfo.link.s.link_up && - (!octnet_iq_is_full(oct, iq_num))) { - netif_wake_subqueue(netdev, iq->q_index); - INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, iq_num, - tx_restart, 1); - } - } else if (netif_queue_stopped(netdev) && lio->linfo.link.s.link_up && - (!octnet_iq_is_full(oct, lio->txq))) { - INCR_INSTRQUEUE_PKT_COUNT(lio->oct_dev, - lio->txq, tx_restart, 1); - netif_wake_queue(netdev); - } -} - -static -int liquidio_schedule_msix_droq_pkt_handler(struct octeon_droq *droq, u64 ret) -{ - struct octeon_device *oct = droq->oct_dev; - struct octeon_device_priv *oct_priv = - (struct octeon_device_priv *)oct->priv; - - if (droq->ops.poll_mode) { - droq->ops.napi_fn(droq); - } else { - if (ret & MSIX_PO_INT) { - dev_err(&oct->pci_dev->dev, - "should not come here should not get rx when poll mode = 0 for vf\n"); - tasklet_schedule(&oct_priv->droq_tasklet); - return 1; - } - /* this will be flushed periodically by check iq db */ - if (ret & MSIX_PI_INT) - return 0; - } - return 0; -} - -static irqreturn_t -liquidio_msix_intr_handler(int irq __attribute__((unused)), void *dev) -{ - struct octeon_ioq_vector *ioq_vector = (struct octeon_ioq_vector *)dev; - struct octeon_device *oct = ioq_vector->oct_dev; - struct octeon_droq *droq = oct->droq[ioq_vector->droq_index]; - u64 ret; - - ret = oct->fn_list.msix_interrupt_handler(ioq_vector); - - if ((ret & MSIX_PO_INT) || (ret & MSIX_PI_INT)) - liquidio_schedule_msix_droq_pkt_handler(droq, ret); - - return IRQ_HANDLED; -} - -/** - * \brief Setup interrupt for octeon device - * @param oct octeon device - * - * Enable interrupt in Octeon device as given in the PCI interrupt mask. - */ -static int octeon_setup_interrupt(struct octeon_device *oct) -{ - struct msix_entry *msix_entries; - char *queue_irq_names = NULL; - int num_alloc_ioq_vectors; - int num_ioq_vectors; - int irqret; - int i; - - if (oct->msix_on) { - oct->num_msix_irqs = oct->sriov_info.rings_per_vf; - - /* allocate storage for the names assigned to each irq */ - oct->irq_name_storage = - kcalloc(MAX_IOQ_INTERRUPTS_PER_VF, INTRNAMSIZ, - GFP_KERNEL); - if (!oct->irq_name_storage) { - dev_err(&oct->pci_dev->dev, "Irq name storage alloc failed...\n"); - return -ENOMEM; - } - - queue_irq_names = oct->irq_name_storage; - - oct->msix_entries = kcalloc( - oct->num_msix_irqs, sizeof(struct msix_entry), GFP_KERNEL); - if (!oct->msix_entries) { - dev_err(&oct->pci_dev->dev, "Memory Alloc failed...\n"); - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return -ENOMEM; - } - - msix_entries = (struct msix_entry *)oct->msix_entries; - - for (i = 0; i < oct->num_msix_irqs; i++) - msix_entries[i].entry = i; - num_alloc_ioq_vectors = pci_enable_msix_range( - oct->pci_dev, msix_entries, - oct->num_msix_irqs, - oct->num_msix_irqs); - if (num_alloc_ioq_vectors < 0) { - dev_err(&oct->pci_dev->dev, "unable to Allocate MSI-X interrupts\n"); - kfree(oct->msix_entries); - oct->msix_entries = NULL; - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return num_alloc_ioq_vectors; - } - dev_dbg(&oct->pci_dev->dev, "OCTEON: Enough MSI-X interrupts are allocated...\n"); - - num_ioq_vectors = oct->num_msix_irqs; - - for (i = 0; i < num_ioq_vectors; i++) { - snprintf(&queue_irq_names[IRQ_NAME_OFF(i)], INTRNAMSIZ, - "LiquidIO%u-vf%u-rxtx-%u", - oct->octeon_id, oct->vf_num, i); - - irqret = request_irq(msix_entries[i].vector, - liquidio_msix_intr_handler, 0, - &queue_irq_names[IRQ_NAME_OFF(i)], - &oct->ioq_vector[i]); - if (irqret) { - dev_err(&oct->pci_dev->dev, - "OCTEON: Request_irq failed for MSIX interrupt Error: %d\n", - irqret); - - while (i) { - i--; - irq_set_affinity_hint( - msix_entries[i].vector, NULL); - free_irq(msix_entries[i].vector, - &oct->ioq_vector[i]); - } - pci_disable_msix(oct->pci_dev); - kfree(oct->msix_entries); - oct->msix_entries = NULL; - kfree(oct->irq_name_storage); - oct->irq_name_storage = NULL; - return irqret; - } - oct->ioq_vector[i].vector = msix_entries[i].vector; - /* assign the cpu mask for this msix interrupt vector */ - irq_set_affinity_hint( - msix_entries[i].vector, - (&oct->ioq_vector[i].affinity_mask)); - } - dev_dbg(&oct->pci_dev->dev, - "OCTEON[%d]: MSI-X enabled\n", oct->octeon_id); - } - return 0; -} - /** * \brief PCI probe handler * @param pdev PCI device structure @@ -942,10 +756,14 @@ static void octeon_destroy_resources(struct octeon_device *oct) if (oct->msix_on) { msix_entries = (struct msix_entry *)oct->msix_entries; for (i = 0; i < oct->num_msix_irqs; i++) { - irq_set_affinity_hint(msix_entries[i].vector, - NULL); - free_irq(msix_entries[i].vector, - &oct->ioq_vector[i]); + if (oct->ioq_vector[i].vector) { + irq_set_affinity_hint( + msix_entries[i].vector, + NULL); + free_irq(msix_entries[i].vector, + &oct->ioq_vector[i]); + oct->ioq_vector[i].vector = 0; + } } pci_disable_msix(oct->pci_dev); kfree(oct->msix_entries); @@ -1137,6 +955,10 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) oct->droq[0]->ops.poll_mode = 0; } + /* Delete NAPI */ + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) + netif_napi_del(napi); + if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) unregister_netdev(netdev); @@ -1174,7 +996,7 @@ static int liquidio_stop_nic_module(struct octeon_device *oct) for (i = 0; i < oct->ifcount; i++) { lio = GET_LIO(oct->props[i].netdev); - for (j = 0; j < lio->linfo.num_rxpciq; j++) + for (j = 0; j < oct->num_oqs; j++) octeon_unregister_droq_ops(oct, lio->linfo.rxpciq[j].s.q_no); } @@ -1262,7 +1084,7 @@ static int check_txq_state(struct lio *lio, struct sk_buff *skb) if (netif_is_multiqueue(lio->netdev)) { q = skb->queue_mapping; - iq = lio->linfo.txpciq[(q % (lio->linfo.num_txpciq))].s.q_no; + iq = lio->linfo.txpciq[q % lio->oct_dev->num_iqs].s.q_no; } else { iq = lio->txq; q = iq; @@ -1391,41 +1213,6 @@ static void free_netsgbuf_with_resp(void *buf) } /** - * \brief Setup output queue - * @param oct octeon device - * @param q_no which queue - * @param num_descs how many descriptors - * @param desc_size size of each descriptor - * @param app_ctx application context - */ -static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs, - int desc_size, void *app_ctx) -{ - int ret_val; - - dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no); - /* droq creation and local register settings. */ - ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx); - if (ret_val < 0) - return ret_val; - - if (ret_val == 1) { - dev_dbg(&oct->pci_dev->dev, "Using default droq %d\n", q_no); - return 0; - } - - /* Enable the droq queues */ - octeon_set_droq_pkt_op(oct, q_no, 1); - - /* Send Credit for Octeon Output queues. Credits are always - * sent after the output queue is enabled. - */ - writel(oct->droq[q_no]->max_count, oct->droq[q_no]->pkts_credit_reg); - - return ret_val; -} - -/** * \brief Callback for getting interface configuration * @param status status of request * @param buf pointer to resp structure @@ -1457,290 +1244,6 @@ static void if_cfg_callback(struct octeon_device *oct, wake_up_interruptible(&ctx->wc); } -/** Routine to push packets arriving on Octeon interface upto network layer. - * @param oct_id - octeon device id. - * @param skbuff - skbuff struct to be passed to network layer. - * @param len - size of total data received. - * @param rh - Control header associated with the packet - * @param param - additional control data with the packet - * @param arg - farg registered in droq_ops - */ -static void -liquidio_push_packet(u32 octeon_id __attribute__((unused)), - void *skbuff, - u32 len, - union octeon_rh *rh, - void *param, - void *arg) -{ - struct napi_struct *napi = param; - struct octeon_droq *droq = - container_of(param, struct octeon_droq, napi); - struct net_device *netdev = (struct net_device *)arg; - struct sk_buff *skb = (struct sk_buff *)skbuff; - u16 vtag = 0; - u32 r_dh_off; - - if (netdev) { - struct lio *lio = GET_LIO(netdev); - int packet_was_received; - - /* Do not proceed if the interface is not in RUNNING state. */ - if (!ifstate_check(lio, LIO_IFSTATE_RUNNING)) { - recv_buffer_free(skb); - droq->stats.rx_dropped++; - return; - } - - skb->dev = netdev; - - skb_record_rx_queue(skb, droq->q_no); - if (likely(len > MIN_SKB_SIZE)) { - struct octeon_skb_page_info *pg_info; - unsigned char *va; - - pg_info = ((struct octeon_skb_page_info *)(skb->cb)); - if (pg_info->page) { - /* For Paged allocation use the frags */ - va = page_address(pg_info->page) + - pg_info->page_offset; - memcpy(skb->data, va, MIN_SKB_SIZE); - skb_put(skb, MIN_SKB_SIZE); - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, - pg_info->page, - pg_info->page_offset + - MIN_SKB_SIZE, - len - MIN_SKB_SIZE, - LIO_RXBUFFER_SZ); - } - } else { - struct octeon_skb_page_info *pg_info = - ((struct octeon_skb_page_info *)(skb->cb)); - skb_copy_to_linear_data(skb, - page_address(pg_info->page) + - pg_info->page_offset, len); - skb_put(skb, len); - put_page(pg_info->page); - } - - r_dh_off = (rh->r_dh.len - 1) * BYTES_PER_DHLEN_UNIT; - - if (rh->r_dh.has_hwtstamp) - r_dh_off -= BYTES_PER_DHLEN_UNIT; - - if (rh->r_dh.has_hash) { - __be32 *hash_be = (__be32 *)(skb->data + r_dh_off); - u32 hash = be32_to_cpu(*hash_be); - - skb_set_hash(skb, hash, PKT_HASH_TYPE_L4); - r_dh_off -= BYTES_PER_DHLEN_UNIT; - } - - skb_pull(skb, rh->r_dh.len * BYTES_PER_DHLEN_UNIT); - skb->protocol = eth_type_trans(skb, skb->dev); - - if ((netdev->features & NETIF_F_RXCSUM) && - (((rh->r_dh.encap_on) && - (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) || - (!(rh->r_dh.encap_on) && - (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED)))) - /* checksum has already been verified */ - skb->ip_summed = CHECKSUM_UNNECESSARY; - else - skb->ip_summed = CHECKSUM_NONE; - - /* Setting Encapsulation field on basis of status received - * from the firmware - */ - if (rh->r_dh.encap_on) { - skb->encapsulation = 1; - skb->csum_level = 1; - droq->stats.rx_vxlan++; - } - - /* inbound VLAN tag */ - if ((netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && - rh->r_dh.vlan) { - u16 priority = rh->r_dh.priority; - u16 vid = rh->r_dh.vlan; - - vtag = (priority << VLAN_PRIO_SHIFT) | vid; - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vtag); - } - - packet_was_received = (napi_gro_receive(napi, skb) != GRO_DROP); - - if (packet_was_received) { - droq->stats.rx_bytes_received += len; - droq->stats.rx_pkts_received++; - } else { - droq->stats.rx_dropped++; - netif_info(lio, rx_err, lio->netdev, - "droq:%d error rx_dropped:%llu\n", - droq->q_no, droq->stats.rx_dropped); - } - - } else { - recv_buffer_free(skb); - } -} - -/** - * \brief callback when receive interrupt occurs and we are in NAPI mode - * @param arg pointer to octeon output queue - */ -static void liquidio_vf_napi_drv_callback(void *arg) -{ - struct octeon_droq *droq = arg; - - napi_schedule_irqoff(&droq->napi); -} - -/** - * \brief Entry point for NAPI polling - * @param napi NAPI structure - * @param budget maximum number of items to process - */ -static int liquidio_napi_poll(struct napi_struct *napi, int budget) -{ - struct octeon_instr_queue *iq; - struct octeon_device *oct; - struct octeon_droq *droq; - int tx_done = 0, iq_no; - int work_done; - - droq = container_of(napi, struct octeon_droq, napi); - oct = droq->oct_dev; - iq_no = droq->q_no; - - /* Handle Droq descriptors */ - work_done = octeon_process_droq_poll_cmd(oct, droq->q_no, - POLL_EVENT_PROCESS_PKTS, - budget); - - /* Flush the instruction queue */ - iq = oct->instr_queue[iq_no]; - if (iq) { - if (atomic_read(&iq->instr_pending)) - /* Process iq buffers with in the budget limits */ - tx_done = octeon_flush_iq(oct, iq, budget); - else - tx_done = 1; - - /* Update iq read-index rather than waiting for next interrupt. - * Return back if tx_done is false. - */ - update_txq_status(oct, iq_no); - } else { - dev_err(&oct->pci_dev->dev, "%s: iq (%d) num invalid\n", - __func__, iq_no); - } - - /* force enable interrupt if reg cnts are high to avoid wraparound */ - if ((work_done < budget && tx_done) || - (iq && iq->pkt_in_done >= MAX_REG_CNT) || - (droq->pkt_count >= MAX_REG_CNT)) { - tx_done = 1; - napi_complete_done(napi, work_done); - octeon_process_droq_poll_cmd(droq->oct_dev, droq->q_no, - POLL_EVENT_ENABLE_INTR, 0); - return 0; - } - - return (!tx_done) ? (budget) : (work_done); -} - -/** - * \brief Setup input and output queues - * @param octeon_dev octeon device - * @param ifidx Interface index - * - * Note: Queues are with respect to the octeon device. Thus - * an input queue is for egress packets, and output queues - * are for ingress packets. - */ -static int setup_io_queues(struct octeon_device *octeon_dev, int ifidx) -{ - struct octeon_droq_ops droq_ops; - struct net_device *netdev; - static int cpu_id_modulus; - struct octeon_droq *droq; - struct napi_struct *napi; - static int cpu_id; - int num_tx_descs; - struct lio *lio; - int retval = 0; - int q, q_no; - - netdev = octeon_dev->props[ifidx].netdev; - - lio = GET_LIO(netdev); - - memset(&droq_ops, 0, sizeof(struct octeon_droq_ops)); - - droq_ops.fptr = liquidio_push_packet; - droq_ops.farg = netdev; - - droq_ops.poll_mode = 1; - droq_ops.napi_fn = liquidio_vf_napi_drv_callback; - cpu_id = 0; - cpu_id_modulus = num_present_cpus(); - - /* set up DROQs. */ - for (q = 0; q < lio->linfo.num_rxpciq; q++) { - q_no = lio->linfo.rxpciq[q].s.q_no; - - retval = octeon_setup_droq( - octeon_dev, q_no, - CFG_GET_NUM_RX_DESCS_NIC_IF(octeon_get_conf(octeon_dev), - lio->ifidx), - CFG_GET_NUM_RX_BUF_SIZE_NIC_IF(octeon_get_conf(octeon_dev), - lio->ifidx), - NULL); - if (retval) { - dev_err(&octeon_dev->pci_dev->dev, - "%s : Runtime DROQ(RxQ) creation failed.\n", - __func__); - return 1; - } - - droq = octeon_dev->droq[q_no]; - napi = &droq->napi; - netif_napi_add(netdev, napi, liquidio_napi_poll, 64); - - /* designate a CPU for this droq */ - droq->cpu_id = cpu_id; - cpu_id++; - if (cpu_id >= cpu_id_modulus) - cpu_id = 0; - - octeon_register_droq_ops(octeon_dev, q_no, &droq_ops); - } - - /* 23XX VF can send/recv control messages (via the first VF-owned - * droq) from the firmware even if the ethX interface is down, - * so that's why poll_mode must be off for the first droq. - */ - octeon_dev->droq[0]->ops.poll_mode = 0; - - /* set up IQs. */ - for (q = 0; q < lio->linfo.num_txpciq; q++) { - num_tx_descs = CFG_GET_NUM_TX_DESCS_NIC_IF( - octeon_get_conf(octeon_dev), lio->ifidx); - retval = octeon_setup_iq(octeon_dev, ifidx, q, - lio->linfo.txpciq[q], num_tx_descs, - netdev_get_tx_queue(netdev, q)); - if (retval) { - dev_err(&octeon_dev->pci_dev->dev, - " %s : Runtime IQ(TxQ) creation failed.\n", - __func__); - return 1; - } - } - - return 0; -} - /** * \brief Net device open for LiquidIO * @param netdev network device @@ -1784,6 +1287,16 @@ static int liquidio_stop(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct napi_struct *napi, *n; + + if (oct->props[lio->ifidx].napi_enabled) { + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) + napi_disable(napi); + + oct->props[lio->ifidx].napi_enabled = 0; + + oct->droq[0]->ops.poll_mode = 0; + } netif_info(lio, ifdown, lio->netdev, "Stopping interface!\n"); /* Inform that netif carrier is down */ @@ -1988,7 +1501,10 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) oct = lio->oct_dev; - for (i = 0; i < lio->linfo.num_txpciq; i++) { + if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) + return stats; + + for (i = 0; i < oct->num_iqs; i++) { iq_no = lio->linfo.txpciq[i].s.q_no; iq_stats = &oct->instr_queue[iq_no]->stats; pkts += iq_stats->tx_done; @@ -2004,7 +1520,7 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) drop = 0; bytes = 0; - for (i = 0; i < lio->linfo.num_rxpciq; i++) { + for (i = 0; i < oct->num_oqs; i++) { oq_no = lio->linfo.rxpciq[i].s.q_no; oq_stats = &oct->droq[oq_no]->stats; pkts += oq_stats->rx_pkts_received; @@ -2028,17 +1544,31 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) */ static int liquidio_change_mtu(struct net_device *netdev, int new_mtu) { - struct lio *lio = GET_LIO(netdev); - struct octeon_device *oct = lio->oct_dev; + struct octnic_ctrl_pkt nctrl; + struct octeon_device *oct; + struct lio *lio; + int ret = 0; - lio->mtu = new_mtu; + lio = GET_LIO(netdev); + oct = lio->oct_dev; + + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); - netif_info(lio, probe, lio->netdev, "MTU Changed from %d to %d\n", - netdev->mtu, new_mtu); - dev_info(&oct->pci_dev->dev, "%s MTU Changed from %d to %d\n", - netdev->name, netdev->mtu, new_mtu); + nctrl.ncmd.u64 = 0; + nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MTU; + nctrl.ncmd.s.param1 = new_mtu; + nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; + nctrl.wait_time = LIO_CMD_WAIT_TM; + nctrl.netpndev = (u64)netdev; + nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; - netdev->mtu = new_mtu; + ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); + if (ret < 0) { + dev_err(&oct->pci_dev->dev, "Failed to set MTU\n"); + return -EIO; + } + + lio->mtu = new_mtu; return 0; } @@ -2959,7 +2489,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) /* Copy MAC Address to OS network device structure */ ether_addr_copy(netdev->dev_addr, mac); - if (setup_io_queues(octeon_dev, i)) { + if (liquidio_setup_io_queues(octeon_dev, i, + lio->linfo.num_txpciq, + lio->linfo.num_rxpciq)) { dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n"); goto setup_nic_dev_fail; } @@ -3182,7 +2714,7 @@ static int octeon_device_init(struct octeon_device *oct) LIQUIDIO_VERSION, oct->sriov_info.rings_per_vf); /* Setup the interrupt handler and record the INT SUM register address*/ - if (octeon_setup_interrupt(oct)) + if (octeon_setup_interrupt(oct, oct->sriov_info.rings_per_vf)) return 1; atomic_set(&oct->status, OCT_DEV_INTR_SET_DONE); diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h index 231dd7fbfb80..3788c8cd082a 100644 --- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h +++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h @@ -27,7 +27,7 @@ #define LIQUIDIO_PACKAGE "" #define LIQUIDIO_BASE_MAJOR_VERSION 1 -#define LIQUIDIO_BASE_MINOR_VERSION 5 +#define LIQUIDIO_BASE_MINOR_VERSION 6 #define LIQUIDIO_BASE_MICRO_VERSION 1 #define LIQUIDIO_BASE_VERSION __stringify(LIQUIDIO_BASE_MAJOR_VERSION) "." \ __stringify(LIQUIDIO_BASE_MINOR_VERSION) @@ -106,6 +106,7 @@ enum octeon_tag_type { #define MAX_IOQ_INTERRUPTS_PER_PF (64 * 2) #define MAX_IOQ_INTERRUPTS_PER_VF (8 * 2) +#define SCR2_BIT_FW_LOADED 63 static inline u32 incr_index(u32 index, u32 count, u32 max) { @@ -189,7 +190,6 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_Q 0 /* NIC Command types */ -#define OCTNET_CMD_RESET_PF 0x0 #define OCTNET_CMD_CHANGE_MTU 0x1 #define OCTNET_CMD_CHANGE_MACADDR 0x2 #define OCTNET_CMD_CHANGE_DEVFLAGS 0x3 @@ -226,6 +226,9 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_SET_UC_LIST 0x1b #define OCTNET_CMD_SET_VF_LINKSTATE 0x1c + +#define OCTNET_CMD_QUEUE_COUNT_CTL 0x1f + #define OCTNET_CMD_VXLAN_PORT_ADD 0x0 #define OCTNET_CMD_VXLAN_PORT_DEL 0x1 #define OCTNET_CMD_RXCSUM_ENABLE 0x0 @@ -235,6 +238,8 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_VLAN_FILTER_ENABLE 0x1 #define OCTNET_CMD_VLAN_FILTER_DISABLE 0x0 +#define LIO_CMD_WAIT_TM 100 + /* RX(packets coming from wire) Checksum verification flags */ /* TCP/UDP csum */ #define CNNIC_L4SUM_VERIFIED 0x1 @@ -768,6 +773,7 @@ struct nic_rx_stats { /* firmware stats */ u64 fw_total_rcvd; u64 fw_total_fwd; + u64 fw_total_fwd_bytes; u64 fw_err_pko; u64 fw_err_link; u64 fw_err_drop; @@ -814,6 +820,7 @@ struct nic_tx_stats { u64 fw_tso; /* number of tso requests */ u64 fw_tso_fwd; /* number of packets segmented in tso */ u64 fw_tx_vxlan; + u64 fw_err_pki; }; struct oct_link_stats { diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h index f229d792c2b3..63bd9c94e547 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h @@ -71,13 +71,17 @@ #define CN23XX_MAX_RINGS_PER_VF 8 #define CN23XX_MAX_INPUT_QUEUES CN23XX_MAX_RINGS_PER_PF -#define CN23XX_MAX_IQ_DESCRIPTORS 512 +#define CN23XX_MAX_IQ_DESCRIPTORS 2048 +#define CN23XX_DEFAULT_IQ_DESCRIPTORS 512 +#define CN23XX_MIN_IQ_DESCRIPTORS 128 #define CN23XX_DB_MIN 1 #define CN23XX_DB_MAX 8 #define CN23XX_DB_TIMEOUT 1 #define CN23XX_MAX_OUTPUT_QUEUES CN23XX_MAX_RINGS_PER_PF -#define CN23XX_MAX_OQ_DESCRIPTORS 512 +#define CN23XX_MAX_OQ_DESCRIPTORS 2048 +#define CN23XX_DEFAULT_OQ_DESCRIPTORS 512 +#define CN23XX_MIN_OQ_DESCRIPTORS 128 #define CN23XX_OQ_BUF_SIZE 1664 #define CN23XX_OQ_PKTSPER_INTR 128 /*#define CAVIUM_ONLY_CN23XX_RX_PERF*/ @@ -163,6 +167,11 @@ ((cfg)->misc.oct_link_query_interval) #define CFG_GET_IS_SLI_BP_ON(cfg) ((cfg)->misc.enable_sli_oq_bp) +#define CFG_SET_NUM_RX_DESCS_NIC_IF(cfg, idx, value) \ + ((cfg)->nic_if_cfg[idx].num_rx_descs = value) +#define CFG_SET_NUM_TX_DESCS_NIC_IF(cfg, idx, value) \ + ((cfg)->nic_if_cfg[idx].num_tx_descs = value) + /* Max IOQs per OCTEON Link */ #define MAX_IOQS_PER_NICIF 64 diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c index e08f7600f986..ec3dd69cd6b2 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c @@ -37,13 +37,6 @@ static u64 cvmx_bootmem_phy_named_block_find(struct octeon_device *oct, u32 flags); static int octeon_console_read(struct octeon_device *oct, u32 console_num, char *buffer, u32 buf_size); -static u32 console_bitmask; -module_param(console_bitmask, int, 0644); -MODULE_PARM_DESC(console_bitmask, - "Bitmask indicating which consoles have debug output redirected to syslog."); - -#define MIN(a, b) min((a), (b)) -#define CAST_ULL(v) ((u64)(v)) #define BOOTLOADER_PCI_READ_BUFFER_DATA_ADDR 0x0006c008 #define BOOTLOADER_PCI_READ_BUFFER_LEN_ADDR 0x0006c004 @@ -139,16 +132,6 @@ struct octeon_pci_console_desc { }; /** - * \brief determines if a given console has debug enabled. - * @param console console to check - * @returns 1 = enabled. 0 otherwise - */ -static int octeon_console_debug_enabled(u32 console) -{ - return (console_bitmask >> (console)) & 0x1; -} - -/** * This function is the implementation of the get macros defined * for individual structure members. The argument are generated * by the macros inorder to read only the needed memory. @@ -234,7 +217,7 @@ static int __cvmx_bootmem_check_version(struct octeon_device *oct, (exact_match && major_version != exact_match)) { dev_err(&oct->pci_dev->dev, "bootmem ver mismatch %d.%d addr:0x%llx\n", major_version, minor_version, - CAST_ULL(oct->bootmem_desc_addr)); + (long long)oct->bootmem_desc_addr); return -1; } else { return 0; @@ -454,20 +437,31 @@ static void output_console_line(struct octeon_device *oct, { char *line; s32 i; + size_t len; line = console_buffer; for (i = 0; i < bytes_read; i++) { /* Output a line at a time, prefixed */ if (console_buffer[i] == '\n') { console_buffer[i] = '\0'; - if (console->leftover[0]) { - dev_info(&oct->pci_dev->dev, "%lu: %s%s\n", - console_num, console->leftover, - line); + /* We need to output 'line', prefaced by 'leftover'. + * However, it is possible we're being called to + * output 'leftover' by itself (in the case of nothing + * having been read from the console). + * + * To avoid duplication, check for this condition. + */ + if (console->leftover[0] && + (line != console->leftover)) { + if (console->print) + (*console->print)(oct, (u32)console_num, + console->leftover, + line); console->leftover[0] = '\0'; } else { - dev_info(&oct->pci_dev->dev, "%lu: %s\n", - console_num, line); + if (console->print) + (*console->print)(oct, (u32)console_num, + line, NULL); } line = &console_buffer[i + 1]; } @@ -476,13 +470,16 @@ static void output_console_line(struct octeon_device *oct, /* Save off any leftovers */ if (line != &console_buffer[bytes_read]) { console_buffer[bytes_read] = '\0'; - strcpy(console->leftover, line); + len = strlen(console->leftover); + strncpy(&console->leftover[len], line, + sizeof(console->leftover) - len); } } static void check_console(struct work_struct *work) { s32 bytes_read, tries, total_read; + size_t len; struct octeon_console *console; struct cavium_wk *wk = (struct cavium_wk *)work; struct octeon_device *oct = (struct octeon_device *)wk->ctxptr; @@ -504,7 +501,7 @@ static void check_console(struct work_struct *work) total_read += bytes_read; if (console->waiting) octeon_console_handle_result(oct, console_num); - if (octeon_console_debug_enabled(console_num)) { + if (console->print) { output_console_line(oct, console, console_num, console_buffer, bytes_read); } @@ -519,10 +516,13 @@ static void check_console(struct work_struct *work) /* If nothing is read after polling the console, * output any leftovers if any */ - if (octeon_console_debug_enabled(console_num) && - (total_read == 0) && (console->leftover[0])) { - dev_info(&oct->pci_dev->dev, "%u: %s\n", - console_num, console->leftover); + if (console->print && (total_read == 0) && + (console->leftover[0])) { + /* append '\n' as terminator for 'output_console_line' */ + len = strlen(console->leftover); + console->leftover[len] = '\n'; + output_console_line(oct, console, console_num, + console->leftover, (s32)(len + 1)); console->leftover[0] = '\0'; } @@ -574,7 +574,84 @@ int octeon_init_consoles(struct octeon_device *oct) return ret; } -int octeon_add_console(struct octeon_device *oct, u32 console_num) +static void octeon_get_uboot_version(struct octeon_device *oct) +{ + s32 bytes_read, tries, total_read; + struct octeon_console *console; + u32 console_num = 0; + char *uboot_ver; + char *buf; + char *p; + +#define OCTEON_UBOOT_VER_BUF_SIZE 512 + buf = kmalloc(OCTEON_UBOOT_VER_BUF_SIZE, GFP_KERNEL); + if (!buf) + return; + + if (octeon_console_send_cmd(oct, "setenv stdout pci\n", 50)) { + kfree(buf); + return; + } + + if (octeon_console_send_cmd(oct, "version\n", 1)) { + kfree(buf); + return; + } + + console = &oct->console[console_num]; + tries = 0; + total_read = 0; + + do { + /* Take console output regardless of whether it will + * be logged + */ + bytes_read = + octeon_console_read(oct, + console_num, buf + total_read, + OCTEON_UBOOT_VER_BUF_SIZE - 1 - + total_read); + if (bytes_read > 0) { + buf[bytes_read] = '\0'; + + total_read += bytes_read; + if (console->waiting) + octeon_console_handle_result(oct, console_num); + } else if (bytes_read < 0) { + dev_err(&oct->pci_dev->dev, "Error reading console %u, ret=%d\n", + console_num, bytes_read); + } + + tries++; + } while ((bytes_read > 0) && (tries < 16)); + + /* If nothing is read after polling the console, + * output any leftovers if any + */ + if ((total_read == 0) && (console->leftover[0])) { + dev_dbg(&oct->pci_dev->dev, "%u: %s\n", + console_num, console->leftover); + console->leftover[0] = '\0'; + } + + buf[OCTEON_UBOOT_VER_BUF_SIZE - 1] = '\0'; + + uboot_ver = strstr(buf, "U-Boot"); + if (uboot_ver) { + p = strstr(uboot_ver, "mips"); + if (p) { + p--; + *p = '\0'; + dev_info(&oct->pci_dev->dev, "%s\n", uboot_ver); + } + } + + kfree(buf); + octeon_console_send_cmd(oct, "setenv stdout serial\n", 50); +} + +int octeon_add_console(struct octeon_device *oct, u32 console_num, + char *dbg_enb) { int ret = 0; u32 delay; @@ -610,17 +687,19 @@ int octeon_add_console(struct octeon_device *oct, u32 console_num) work = &oct->console_poll_work[console_num].work; + octeon_get_uboot_version(oct); + INIT_DELAYED_WORK(work, check_console); oct->console_poll_work[console_num].ctxptr = (void *)oct; oct->console_poll_work[console_num].ctxul = console_num; delay = OCTEON_CONSOLE_POLL_INTERVAL_MS; schedule_delayed_work(work, msecs_to_jiffies(delay)); - if (octeon_console_debug_enabled(console_num)) { - ret = octeon_console_send_cmd(oct, - "setenv pci_console_active 1", - 2000); - } + /* an empty string means use default debug console enablement */ + if (dbg_enb && !dbg_enb[0]) + dbg_enb = "setenv pci_console_active 1"; + if (dbg_enb) + ret = octeon_console_send_cmd(oct, dbg_enb, 2000); console->active = 1; } @@ -704,7 +783,7 @@ static int octeon_console_read(struct octeon_device *oct, u32 console_num, if (bytes_to_read <= 0) return bytes_to_read; - bytes_to_read = MIN(bytes_to_read, (s32)buf_size); + bytes_to_read = min_t(s32, bytes_to_read, buf_size); /* Check to see if what we want to read is not contiguous, and limit * ourselves to the contiguous block diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index 623e28ca736e..29d53b1763a7 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -418,7 +418,7 @@ static struct octeon_config default_cn23xx_conf = { /** IQ attributes */ .iq = { .max_iqs = CN23XX_CFG_IO_QUEUES, - .pending_list_size = (CN23XX_MAX_IQ_DESCRIPTORS * + .pending_list_size = (CN23XX_DEFAULT_IQ_DESCRIPTORS * CN23XX_CFG_IO_QUEUES), .instr_type = OCTEON_64BYTE_INSTR, .db_min = CN23XX_DB_MIN, @@ -436,8 +436,8 @@ static struct octeon_config default_cn23xx_conf = { }, .num_nic_ports = DEFAULT_NUM_NIC_PORTS_23XX, - .num_def_rx_descs = CN23XX_MAX_OQ_DESCRIPTORS, - .num_def_tx_descs = CN23XX_MAX_IQ_DESCRIPTORS, + .num_def_rx_descs = CN23XX_DEFAULT_OQ_DESCRIPTORS, + .num_def_tx_descs = CN23XX_DEFAULT_IQ_DESCRIPTORS, .def_rx_buf_size = CN23XX_OQ_BUF_SIZE, /* For ethernet interface 0: Port cfg Attributes */ @@ -455,10 +455,10 @@ static struct octeon_config default_cn23xx_conf = { .num_rxqs = DEF_RXQS_PER_INTF, /* Num of desc for rx rings */ - .num_rx_descs = CN23XX_MAX_OQ_DESCRIPTORS, + .num_rx_descs = CN23XX_DEFAULT_OQ_DESCRIPTORS, /* Num of desc for tx rings */ - .num_tx_descs = CN23XX_MAX_IQ_DESCRIPTORS, + .num_tx_descs = CN23XX_DEFAULT_IQ_DESCRIPTORS, /* SKB size, We need not change buf size even for Jumbo frames. * Octeon can send jumbo frames in 4 consecutive descriptors, @@ -484,10 +484,10 @@ static struct octeon_config default_cn23xx_conf = { .num_rxqs = DEF_RXQS_PER_INTF, /* Num of desc for rx rings */ - .num_rx_descs = CN23XX_MAX_OQ_DESCRIPTORS, + .num_rx_descs = CN23XX_DEFAULT_OQ_DESCRIPTORS, /* Num of desc for tx rings */ - .num_tx_descs = CN23XX_MAX_IQ_DESCRIPTORS, + .num_tx_descs = CN23XX_DEFAULT_IQ_DESCRIPTORS, /* SKB size, We need not change buf size even for Jumbo frames. * Octeon can send jumbo frames in 4 consecutive descriptors, @@ -528,9 +528,10 @@ static struct octeon_config_ptr { }; static char oct_dev_state_str[OCT_DEV_STATES + 1][32] = { - "BEGIN", "PCI-MAP-DONE", "DISPATCH-INIT-DONE", + "BEGIN", "PCI-ENABLE-DONE", "PCI-MAP-DONE", "DISPATCH-INIT-DONE", "IQ-INIT-DONE", "SCBUFF-POOL-INIT-DONE", "RESPLIST-INIT-DONE", - "DROQ-INIT-DONE", "IO-QUEUES-INIT-DONE", "CONSOLE-INIT-DONE", + "DROQ-INIT-DONE", "MBOX-SETUP-DONE", "MSIX-ALLOC-VECTOR-DONE", + "INTR-SET-DONE", "IO-QUEUES-INIT-DONE", "CONSOLE-INIT-DONE", "HOST-READY", "CORE-READY", "RUNNING", "IN-RESET", "INVALID" }; @@ -876,11 +877,11 @@ int octeon_setup_instr_queues(struct octeon_device *oct) oct->num_iqs = 0; - oct->instr_queue[0] = vmalloc_node(sizeof(*oct->instr_queue[0]), + oct->instr_queue[0] = vzalloc_node(sizeof(*oct->instr_queue[0]), numa_node); if (!oct->instr_queue[0]) oct->instr_queue[0] = - vmalloc(sizeof(struct octeon_instr_queue)); + vzalloc(sizeof(struct octeon_instr_queue)); if (!oct->instr_queue[0]) return 1; memset(oct->instr_queue[0], 0, sizeof(struct octeon_instr_queue)); @@ -923,9 +924,9 @@ int octeon_setup_output_queues(struct octeon_device *oct) desc_size = CFG_GET_DEF_RX_BUF_SIZE(CHIP_CONF(oct, cn23xx_vf)); } oct->num_oqs = 0; - oct->droq[0] = vmalloc_node(sizeof(*oct->droq[0]), numa_node); + oct->droq[0] = vzalloc_node(sizeof(*oct->droq[0]), numa_node); if (!oct->droq[0]) - oct->droq[0] = vmalloc(sizeof(*oct->droq[0])); + oct->droq[0] = vzalloc(sizeof(*oct->droq[0])); if (!oct->droq[0]) return 1; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index c90ed48ae8ab..894af199ddef 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -22,6 +22,8 @@ #ifndef _OCTEON_DEVICE_H_ #define _OCTEON_DEVICE_H_ +#include <linux/interrupt.h> + /** PCI VendorId Device Id */ #define OCTEON_CN68XX_PCIID 0x91177d #define OCTEON_CN66XX_PCIID 0x92177d @@ -192,6 +194,8 @@ struct octeon_reg_list { }; #define OCTEON_CONSOLE_MAX_READ_BYTES 512 +typedef int (*octeon_console_print_fn)(struct octeon_device *oct, + u32 num, char *pre, char *suf); struct octeon_console { u32 active; u32 waiting; @@ -199,6 +203,7 @@ struct octeon_console { u32 buffer_size; u64 input_base_addr; u64 output_base_addr; + octeon_console_print_fn print; char leftover[OCTEON_CONSOLE_MAX_READ_BYTES]; }; @@ -552,6 +557,7 @@ struct octeon_device { } loc; atomic_t *adapter_refcount; /* reference count of adapter */ + bool ptp_enable; }; #define OCT_DRV_ONLINE 1 @@ -565,6 +571,8 @@ struct octeon_device { #define CHIP_CONF(oct, TYPE) \ (((struct octeon_ ## TYPE *)((oct)->chip))->conf) +#define MAX_IO_PENDING_PKT_COUNT 100 + /*------------------ Function Prototypes ----------------------*/ /** Initialize device list memory */ @@ -740,11 +748,17 @@ int octeon_init_consoles(struct octeon_device *oct); /** * Adds access to a console to the device. * - * @param oct which octeon to add to - * @param console_num which console + * @param oct: which octeon to add to + * @param console_num: which console + * @param dbg_enb: ptr to debug enablement string, one of: + * * NULL for no debug output (i.e. disabled) + * * empty string enables debug output (via default method) + * * specific string to enable debug console output + * * @return Zero on success, negative on failure. */ -int octeon_add_console(struct octeon_device *oct, u32 console_num); +int octeon_add_console(struct octeon_device *oct, u32 console_num, + char *dbg_enb); /** write or read from a console */ int octeon_console_write(struct octeon_device *oct, u32 console_num, diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index 2e190deb2233..9372d4ce9954 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -145,6 +145,8 @@ octeon_droq_destroy_ring_buffers(struct octeon_device *oct, for (i = 0; i < droq->max_count; i++) { pg_info = &droq->recv_buf_list[i].pg_info; + if (!pg_info) + continue; if (pg_info->dma) lio_unmap_ring(oct->pci_dev, @@ -207,6 +209,10 @@ int octeon_delete_droq(struct octeon_device *oct, u32 q_no) droq->desc_ring, droq->desc_ring_dma); memset(droq, 0, OCT_DROQ_SIZE); + oct->io_qmask.oq &= ~(1ULL << q_no); + vfree(oct->droq[q_no]); + oct->droq[q_no] = NULL; + oct->num_oqs--; return 0; } @@ -275,12 +281,12 @@ int octeon_init_droq(struct octeon_device *oct, droq->max_count); droq->recv_buf_list = (struct octeon_recv_buffer *) - vmalloc_node(droq->max_count * + vzalloc_node(droq->max_count * OCT_DROQ_RECVBUF_SIZE, numa_node); if (!droq->recv_buf_list) droq->recv_buf_list = (struct octeon_recv_buffer *) - vmalloc(droq->max_count * + vzalloc(droq->max_count * OCT_DROQ_RECVBUF_SIZE); if (!droq->recv_buf_list) { dev_err(&oct->pci_dev->dev, "Output queue recv buf list alloc failed\n"); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h index 7ccffbb0019e..32ef3a7d88d8 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h @@ -35,6 +35,12 @@ #define DRV_NAME "LiquidIO" +struct octeon_device_priv { + /** Tasklet structures for this device. */ + struct tasklet_struct droq_tasklet; + unsigned long napi_mask; +}; + /** This structure is used by NIC driver to store information required * to free the sk_buff when the packet has been fetched by Octeon. * Bytes offset below assume worst-case of a 64-bit system. diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index ec8504b2942d..9e36319cead6 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -33,6 +33,7 @@ #define LIO_IFSTATE_REGISTERED 0x02 #define LIO_IFSTATE_RUNNING 0x04 #define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08 +#define LIO_IFSTATE_RESETTING 0x10 struct oct_nic_stats_resp { u64 rh; @@ -166,6 +167,14 @@ void cleanup_rx_oom_poll_fn(struct net_device *netdev); */ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr); +int liquidio_setup_io_queues(struct octeon_device *octeon_dev, int ifidx, + u32 num_iqs, u32 num_oqs); + +irqreturn_t liquidio_msix_intr_handler(int irq __attribute__((unused)), + void *dev); + +int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs); + /** * \brief Register ethtool operations * @param netdev pointer to network device @@ -448,4 +457,30 @@ static inline void ifstate_reset(struct lio *lio, int state_flag) atomic_set(&lio->ifstate, (atomic_read(&lio->ifstate) & ~(state_flag))); } +/** + * \brief wait for all pending requests to complete + * @param oct Pointer to Octeon device + * + * Called during shutdown sequence + */ +static inline int wait_for_pending_requests(struct octeon_device *oct) +{ + int i, pcount = 0; + + for (i = 0; i < MAX_IO_PENDING_PKT_COUNT; i++) { + pcount = atomic_read( + &oct->response_list[OCTEON_ORDERED_SC_LIST] + .pending_req_count); + if (pcount) + schedule_timeout_uninterruptible(HZ / 10); + else + break; + } + + if (pcount) + return 1; + + return 0; +} + #endif diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index 7b297f1f6dbe..1e0fbce86d60 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -77,13 +77,6 @@ int octeon_init_instr_queue(struct octeon_device *oct, return 1; } - if (num_descs & (num_descs - 1)) { - dev_err(&oct->pci_dev->dev, - "Number of descriptors for instr queue %d not in power of 2.\n", - iq_no); - return 1; - } - q_size = (u32)conf->instr_type * num_descs; iq = oct->instr_queue[iq_no]; @@ -190,6 +183,10 @@ int octeon_delete_instr_queue(struct octeon_device *oct, u32 iq_no) q_size = iq->max_count * desc_size; lio_dma_free(oct, (u32)q_size, iq->base_addr, iq->base_addr_dma); + oct->io_qmask.iq &= ~(1ULL << iq_no); + vfree(oct->instr_queue[iq_no]); + oct->instr_queue[iq_no] = NULL; + oct->num_iqs--; return 0; } return 1; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 57858522c33c..67d1a3230773 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -277,7 +277,6 @@ struct snd_queue { u16 xdp_free_cnt; bool is_xdp; -#define TSO_HEADER_SIZE 128 /* For TSO segment's header */ char *tso_hdrs; dma_addr_t tso_hdrs_phys; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 0bc6a4ffce30..6a015362c340 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -793,7 +793,9 @@ static struct attribute *cxgb3_attrs[] = { NULL }; -static struct attribute_group cxgb3_attr_group = {.attrs = cxgb3_attrs }; +static const struct attribute_group cxgb3_attr_group = { + .attrs = cxgb3_attrs, +}; static ssize_t tm_attr_show(struct device *d, char *buf, int sched) @@ -880,7 +882,9 @@ static struct attribute *offload_attrs[] = { NULL }; -static struct attribute_group offload_attr_group = {.attrs = offload_attrs }; +static const struct attribute_group offload_attr_group = { + .attrs = offload_attrs, +}; /* * Sends an sk_buff to an offload queue driver diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 09ea62ee96d3..ea72d2d2e1b4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -104,13 +104,13 @@ enum dev_state { DEV_STATE_ERR }; -enum { +enum cc_pause { PAUSE_RX = 1 << 0, PAUSE_TX = 1 << 1, PAUSE_AUTONEG = 1 << 2 }; -enum { +enum cc_fec { FEC_AUTO = 1 << 0, /* IEEE 802.3 "automatic" */ FEC_RS = 1 << 1, /* Reed-Solomon */ FEC_BASER_RS = 1 << 2 /* BaseR/Reed-Solomon */ @@ -338,10 +338,12 @@ struct adapter_params { unsigned int sf_nsec; /* # of flash sectors */ unsigned int sf_fw_start; /* start of FW image in flash */ - unsigned int fw_vers; - unsigned int bs_vers; /* bootstrap version */ - unsigned int tp_vers; - unsigned int er_vers; /* expansion ROM version */ + unsigned int fw_vers; /* firmware version */ + unsigned int bs_vers; /* bootstrap version */ + unsigned int tp_vers; /* TP microcode version */ + unsigned int er_vers; /* expansion ROM version */ + unsigned int scfg_vers; /* Serial Configuration version */ + unsigned int vpd_vers; /* VPD Version */ u8 api_vers[7]; unsigned short mtus[NMTUS]; @@ -364,6 +366,7 @@ struct adapter_params { unsigned int max_ordird_qp; /* Max read depth per RDMA QP */ unsigned int max_ird_adapter; /* Max read depth per adapter */ bool fr_nsmr_tpte_wr_support; /* FW support for FR_NSMR_TPTE_WR */ + u8 fw_caps_support; /* 32-bit Port Capabilities */ /* MPS Buffer Group Map[per Port]. Bit i is set if buffer group i is * used by the Port @@ -437,18 +440,34 @@ struct trace_params { unsigned char port; }; +/* Firmware Port Capabilities types. */ + +typedef u16 fw_port_cap16_t; /* 16-bit Port Capabilities integral value */ +typedef u32 fw_port_cap32_t; /* 32-bit Port Capabilities integral value */ + +enum fw_caps { + FW_CAPS_UNKNOWN = 0, /* 0'ed out initial state */ + FW_CAPS16 = 1, /* old Firmware: 16-bit Port Capabilities */ + FW_CAPS32 = 2, /* new Firmware: 32-bit Port Capabilities */ +}; + struct link_config { - unsigned short supported; /* link capabilities */ - unsigned short advertising; /* advertised capabilities */ - unsigned short lp_advertising; /* peer advertised capabilities */ - unsigned int requested_speed; /* speed user has requested */ - unsigned int speed; /* actual link speed */ - unsigned char requested_fc; /* flow control user has requested */ - unsigned char fc; /* actual link flow control */ - unsigned char auto_fec; /* Forward Error Correction: */ - unsigned char requested_fec; /* "automatic" (IEEE 802.3), */ - unsigned char fec; /* requested, and actual in use */ + fw_port_cap32_t pcaps; /* link capabilities */ + fw_port_cap32_t def_acaps; /* default advertised capabilities */ + fw_port_cap32_t acaps; /* advertised capabilities */ + fw_port_cap32_t lpacaps; /* peer advertised capabilities */ + + fw_port_cap32_t speed_caps; /* speed(s) user has requested */ + unsigned int speed; /* actual link speed (Mb/s) */ + + enum cc_pause requested_fc; /* flow control user has requested */ + enum cc_pause fc; /* actual link flow control */ + + enum cc_fec requested_fec; /* Forward Error Correction: */ + enum cc_fec fec; /* requested and actual in use */ + unsigned char autoneg; /* autonegotiating? */ + unsigned char link_ok; /* link up? */ unsigned char link_down_rc; /* link down reason */ }; @@ -1404,10 +1423,15 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox, int t4_fl_pkt_align(struct adapter *adap); unsigned int t4_flash_cfg_addr(struct adapter *adapter); int t4_check_fw_version(struct adapter *adap); +int t4_load_cfg(struct adapter *adapter, const u8 *cfg_data, unsigned int size); int t4_get_fw_version(struct adapter *adapter, u32 *vers); int t4_get_bs_version(struct adapter *adapter, u32 *vers); int t4_get_tp_version(struct adapter *adapter, u32 *vers); int t4_get_exprom_version(struct adapter *adapter, u32 *vers); +int t4_get_scfg_version(struct adapter *adapter, u32 *vers); +int t4_get_vpd_version(struct adapter *adapter, u32 *vers); +int t4_get_version_info(struct adapter *adapter); +void t4_dump_version_info(struct adapter *adapter); int t4_prep_fw(struct adapter *adap, struct fw_info *fw_info, const u8 *fw_data, unsigned int fw_size, struct fw_hdr *card_fw, enum dev_state state, int *reset); @@ -1573,6 +1597,8 @@ int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf, int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox); void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl); int t4_update_port_info(struct port_info *pi); +int t4_get_link_params(struct port_info *pi, unsigned int *link_okp, + unsigned int *speedp, unsigned int *mtup); int t4_handle_fw_rpl(struct adapter *adap, const __be64 *rpl); void t4_db_full(struct adapter *adapter); void t4_db_dropped(struct adapter *adapter); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 26eb00a45db1..a71af1e587e2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -533,17 +533,23 @@ static int from_fw_port_mod_type(enum fw_port_type port_type, static unsigned int speed_to_fw_caps(int speed) { if (speed == 100) - return FW_PORT_CAP_SPEED_100M; + return FW_PORT_CAP32_SPEED_100M; if (speed == 1000) - return FW_PORT_CAP_SPEED_1G; + return FW_PORT_CAP32_SPEED_1G; if (speed == 10000) - return FW_PORT_CAP_SPEED_10G; + return FW_PORT_CAP32_SPEED_10G; if (speed == 25000) - return FW_PORT_CAP_SPEED_25G; + return FW_PORT_CAP32_SPEED_25G; if (speed == 40000) - return FW_PORT_CAP_SPEED_40G; + return FW_PORT_CAP32_SPEED_40G; + if (speed == 50000) + return FW_PORT_CAP32_SPEED_50G; if (speed == 100000) - return FW_PORT_CAP_SPEED_100G; + return FW_PORT_CAP32_SPEED_100G; + if (speed == 200000) + return FW_PORT_CAP32_SPEED_200G; + if (speed == 400000) + return FW_PORT_CAP32_SPEED_400G; return 0; } @@ -560,12 +566,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, unsigned int fw_caps, unsigned long *link_mode_mask) { - #define SET_LMM(__lmm_name) __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name \ - ## _BIT, link_mode_mask) + #define SET_LMM(__lmm_name) \ + __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \ + link_mode_mask) #define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \ do { \ - if (fw_caps & FW_PORT_CAP_ ## __fw_name) \ + if (fw_caps & FW_PORT_CAP32_ ## __fw_name) \ SET_LMM(__lmm_name); \ } while (0) @@ -645,7 +652,10 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, case FW_PORT_TYPE_KR4_100G: case FW_PORT_TYPE_CR4_QSFP: SET_LMM(FIBRE); - SET_LMM(100000baseCR4_Full); + FW_CAPS_TO_LMM(SPEED_40G, 40000baseSR4_Full); + FW_CAPS_TO_LMM(SPEED_25G, 25000baseCR_Full); + FW_CAPS_TO_LMM(SPEED_50G, 50000baseCR2_Full); + FW_CAPS_TO_LMM(SPEED_100G, 100000baseCR4_Full); break; default: @@ -663,8 +673,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, /** * lmm_to_fw_caps - translate ethtool Link Mode Mask to Firmware * capabilities - * - * @link_mode_mask: ethtool Link Mode Mask + * @et_lmm: ethtool Link Mode Mask * * Translate ethtool Link Mode Mask into a Firmware Port capabilities * value. @@ -677,7 +686,7 @@ static unsigned int lmm_to_fw_caps(const unsigned long *link_mode_mask) do { \ if (test_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \ link_mode_mask)) \ - fw_caps |= FW_PORT_CAP_ ## __fw_name; \ + fw_caps |= FW_PORT_CAP32_ ## __fw_name; \ } while (0) LMM_TO_FW_CAPS(100baseT_Full, SPEED_100M); @@ -685,6 +694,7 @@ static unsigned int lmm_to_fw_caps(const unsigned long *link_mode_mask) LMM_TO_FW_CAPS(10000baseT_Full, SPEED_10G); LMM_TO_FW_CAPS(40000baseSR4_Full, SPEED_40G); LMM_TO_FW_CAPS(25000baseCR_Full, SPEED_25G); + LMM_TO_FW_CAPS(50000baseCR2_Full, SPEED_50G); LMM_TO_FW_CAPS(100000baseCR4_Full, SPEED_100G); #undef LMM_TO_FW_CAPS @@ -698,10 +708,6 @@ static int get_link_ksettings(struct net_device *dev, struct port_info *pi = netdev_priv(dev); struct ethtool_link_settings *base = &link_ksettings->base; - ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); - ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); - ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); - /* For the nonce, the Firmware doesn't send up Port State changes * when the Virtual Interface attached to the Port is down. So * if it's down, let's grab any changes. @@ -709,6 +715,10 @@ static int get_link_ksettings(struct net_device *dev, if (!netif_running(dev)) (void)t4_update_port_info(pi); + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); + base->port = from_fw_port_mod_type(pi->port_type, pi->mod_type); if (pi->mdio_addr >= 0) { @@ -721,11 +731,11 @@ static int get_link_ksettings(struct net_device *dev, base->mdio_support = 0; } - fw_caps_to_lmm(pi->port_type, pi->link_cfg.supported, + fw_caps_to_lmm(pi->port_type, pi->link_cfg.pcaps, link_ksettings->link_modes.supported); - fw_caps_to_lmm(pi->port_type, pi->link_cfg.advertising, + fw_caps_to_lmm(pi->port_type, pi->link_cfg.acaps, link_ksettings->link_modes.advertising); - fw_caps_to_lmm(pi->port_type, pi->link_cfg.lp_advertising, + fw_caps_to_lmm(pi->port_type, pi->link_cfg.lpacaps, link_ksettings->link_modes.lp_advertising); if (netif_carrier_ok(dev)) { @@ -736,8 +746,24 @@ static int get_link_ksettings(struct net_device *dev, base->duplex = DUPLEX_UNKNOWN; } + if (pi->link_cfg.fc & PAUSE_RX) { + if (pi->link_cfg.fc & PAUSE_TX) { + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, + Pause); + } else { + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, + Asym_Pause); + } + } else if (pi->link_cfg.fc & PAUSE_TX) { + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, + Asym_Pause); + } + base->autoneg = pi->link_cfg.autoneg; - if (pi->link_cfg.supported & FW_PORT_CAP_ANEG) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_ANEG) ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Autoneg); if (pi->link_cfg.autoneg) @@ -748,8 +774,7 @@ static int get_link_ksettings(struct net_device *dev, } static int set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings - *link_ksettings) + const struct ethtool_link_ksettings *link_ksettings) { struct port_info *pi = netdev_priv(dev); struct link_config *lc = &pi->link_cfg; @@ -762,12 +787,12 @@ static int set_link_ksettings(struct net_device *dev, if (base->duplex != DUPLEX_FULL) return -EINVAL; - if (!(lc->supported & FW_PORT_CAP_ANEG)) { + if (!(lc->pcaps & FW_PORT_CAP32_ANEG)) { /* PHY offers a single speed. See if that's what's * being requested. */ if (base->autoneg == AUTONEG_DISABLE && - (lc->supported & speed_to_fw_caps(base->speed))) + (lc->pcaps & speed_to_fw_caps(base->speed))) return 0; return -EINVAL; } @@ -776,18 +801,17 @@ static int set_link_ksettings(struct net_device *dev, if (base->autoneg == AUTONEG_DISABLE) { fw_caps = speed_to_fw_caps(base->speed); - if (!(lc->supported & fw_caps)) + if (!(lc->pcaps & fw_caps)) return -EINVAL; - lc->requested_speed = fw_caps; - lc->advertising = 0; + lc->speed_caps = fw_caps; + lc->acaps = 0; } else { fw_caps = - lmm_to_fw_caps(link_ksettings->link_modes.advertising); - - if (!(lc->supported & fw_caps)) + lmm_to_fw_caps(link_ksettings->link_modes.advertising); + if (!(lc->pcaps & fw_caps)) return -EINVAL; - lc->requested_speed = 0; - lc->advertising = fw_caps | FW_PORT_CAP_ANEG; + lc->speed_caps = 0; + lc->acaps = fw_caps | FW_PORT_CAP32_ANEG; } lc->autoneg = base->autoneg; @@ -801,6 +825,104 @@ static int set_link_ksettings(struct net_device *dev, return ret; } +/* Translate the Firmware FEC value into the ethtool value. */ +static inline unsigned int fwcap_to_eth_fec(unsigned int fw_fec) +{ + unsigned int eth_fec = 0; + + if (fw_fec & FW_PORT_CAP32_FEC_RS) + eth_fec |= ETHTOOL_FEC_RS; + if (fw_fec & FW_PORT_CAP32_FEC_BASER_RS) + eth_fec |= ETHTOOL_FEC_BASER; + + /* if nothing is set, then FEC is off */ + if (!eth_fec) + eth_fec = ETHTOOL_FEC_OFF; + + return eth_fec; +} + +/* Translate Common Code FEC value into ethtool value. */ +static inline unsigned int cc_to_eth_fec(unsigned int cc_fec) +{ + unsigned int eth_fec = 0; + + if (cc_fec & FEC_AUTO) + eth_fec |= ETHTOOL_FEC_AUTO; + if (cc_fec & FEC_RS) + eth_fec |= ETHTOOL_FEC_RS; + if (cc_fec & FEC_BASER_RS) + eth_fec |= ETHTOOL_FEC_BASER; + + /* if nothing is set, then FEC is off */ + if (!eth_fec) + eth_fec = ETHTOOL_FEC_OFF; + + return eth_fec; +} + +/* Translate ethtool FEC value into Common Code value. */ +static inline unsigned int eth_to_cc_fec(unsigned int eth_fec) +{ + unsigned int cc_fec = 0; + + if (eth_fec & ETHTOOL_FEC_OFF) + return cc_fec; + + if (eth_fec & ETHTOOL_FEC_AUTO) + cc_fec |= FEC_AUTO; + if (eth_fec & ETHTOOL_FEC_RS) + cc_fec |= FEC_RS; + if (eth_fec & ETHTOOL_FEC_BASER) + cc_fec |= FEC_BASER_RS; + + return cc_fec; +} + +static int get_fecparam(struct net_device *dev, struct ethtool_fecparam *fec) +{ + const struct port_info *pi = netdev_priv(dev); + const struct link_config *lc = &pi->link_cfg; + + /* Translate the Firmware FEC Support into the ethtool value. We + * always support IEEE 802.3 "automatic" selection of Link FEC type if + * any FEC is supported. + */ + fec->fec = fwcap_to_eth_fec(lc->pcaps); + if (fec->fec != ETHTOOL_FEC_OFF) + fec->fec |= ETHTOOL_FEC_AUTO; + + /* Translate the current internal FEC parameters into the + * ethtool values. + */ + fec->active_fec = cc_to_eth_fec(lc->fec); + + return 0; +} + +static int set_fecparam(struct net_device *dev, struct ethtool_fecparam *fec) +{ + struct port_info *pi = netdev_priv(dev); + struct link_config *lc = &pi->link_cfg; + struct link_config old_lc; + int ret; + + /* Save old Link Configuration in case the L1 Configure below + * fails. + */ + old_lc = *lc; + + /* Try to perform the L1 Configure and return the result of that + * effort. If it fails, revert the attempted change. + */ + lc->requested_fec = eth_to_cc_fec(fec->fec); + ret = t4_link_l1cfg(pi->adapter, pi->adapter->mbox, + pi->tx_chan, lc); + if (ret) + *lc = old_lc; + return ret; +} + static void get_pauseparam(struct net_device *dev, struct ethtool_pauseparam *epause) { @@ -819,7 +941,7 @@ static int set_pauseparam(struct net_device *dev, if (epause->autoneg == AUTONEG_DISABLE) lc->requested_fc = 0; - else if (lc->supported & FW_PORT_CAP_ANEG) + else if (lc->pcaps & FW_PORT_CAP32_ANEG) lc->requested_fc = PAUSE_AUTONEG; else return -EINVAL; @@ -1255,6 +1377,8 @@ static int get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, static const struct ethtool_ops cxgb_ethtool_ops = { .get_link_ksettings = get_link_ksettings, .set_link_ksettings = set_link_ksettings, + .get_fecparam = get_fecparam, + .set_fecparam = set_fecparam, .get_drvinfo = get_drvinfo, .get_msglevel = get_msglevel, .set_msglevel = set_msglevel, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 33bb8678833a..92d9d795d874 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -530,15 +530,22 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp, FW_PORT_CMD_ACTION_G(ntohl(pcmd->action_to_len16)); if (cmd == FW_PORT_CMD && - action == FW_PORT_ACTION_GET_PORT_INFO) { + (action == FW_PORT_ACTION_GET_PORT_INFO || + action == FW_PORT_ACTION_GET_PORT_INFO32)) { int port = FW_PORT_CMD_PORTID_G( be32_to_cpu(pcmd->op_to_portid)); - struct net_device *dev = - q->adap->port[q->adap->chan_map[port]]; - int state_input = ((pcmd->u.info.dcbxdis_pkd & - FW_PORT_CMD_DCBXDIS_F) - ? CXGB4_DCB_INPUT_FW_DISABLED - : CXGB4_DCB_INPUT_FW_ENABLED); + struct net_device *dev; + int dcbxdis, state_input; + + dev = q->adap->port[q->adap->chan_map[port]]; + dcbxdis = (action == FW_PORT_ACTION_GET_PORT_INFO + ? !!(pcmd->u.info.dcbxdis_pkd & + FW_PORT_CMD_DCBXDIS_F) + : !!(pcmd->u.info32.lstatus32_to_cbllen32 & + FW_PORT_CMD_DCBXDIS32_F)); + state_input = (dcbxdis + ? CXGB4_DCB_INPUT_FW_DISABLED + : CXGB4_DCB_INPUT_FW_ENABLED); cxgb4_dcb_state_fsm(dev, state_input); } @@ -2672,11 +2679,10 @@ static int cxgb_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, { struct port_info *pi = netdev_priv(dev); struct adapter *adap = pi->adapter; - struct fw_port_cmd port_cmd, port_rpl; - u32 link_status, speed = 0; + unsigned int link_ok, speed, mtu; u32 fw_pfvf, fw_class; int class_id = vf; - int link_ok, ret; + int ret; u16 pktsize; if (vf >= adap->num_vfs) @@ -2688,41 +2694,18 @@ static int cxgb_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, min_tx_rate, vf); return -EINVAL; } - /* Retrieve link details for VF port */ - memset(&port_cmd, 0, sizeof(port_cmd)); - port_cmd.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | - FW_CMD_REQUEST_F | - FW_CMD_READ_F | - FW_PORT_CMD_PORTID_V(pi->port_id)); - port_cmd.action_to_len16 = - cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_GET_PORT_INFO) | - FW_LEN16(port_cmd)); - ret = t4_wr_mbox(adap, adap->mbox, &port_cmd, sizeof(port_cmd), - &port_rpl); + + ret = t4_get_link_params(pi, &link_ok, &speed, &mtu); if (ret != FW_SUCCESS) { dev_err(adap->pdev_dev, - "Failed to get link status for VF %d\n", vf); + "Failed to get link information for VF %d\n", vf); return -EINVAL; } - link_status = be32_to_cpu(port_rpl.u.info.lstatus_to_modtype); - link_ok = (link_status & FW_PORT_CMD_LSTATUS_F) != 0; + if (!link_ok) { dev_err(adap->pdev_dev, "Link down for VF %d\n", vf); return -EINVAL; } - /* Determine link speed */ - if (link_status & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100M)) - speed = 100; - else if (link_status & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_1G)) - speed = 1000; - else if (link_status & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G)) - speed = 10000; - else if (link_status & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G)) - speed = 25000; - else if (link_status & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G)) - speed = 40000; - else if (link_status & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G)) - speed = 100000; if (max_tx_rate > speed) { dev_err(adap->pdev_dev, @@ -2730,7 +2713,8 @@ static int cxgb_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, max_tx_rate, vf, speed); return -EINVAL; } - pktsize = be16_to_cpu(port_rpl.u.info.mtu); + + pktsize = mtu; /* subtract ethhdr size and 4 bytes crc since, f/w appends it */ pktsize = pktsize - sizeof(struct ethhdr) - 4; /* subtract ipv4 hdr size, tcp hdr size to get typical IPv4 MSS size */ @@ -2741,7 +2725,7 @@ static int cxgb_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, SCHED_CLASS_MODE_CLASS, SCHED_CLASS_RATEUNIT_BITS, SCHED_CLASS_RATEMODE_ABS, - pi->port_id, class_id, 0, + pi->tx_chan, class_id, 0, max_tx_rate * 1000, 0, pktsize); if (ret) { dev_err(adap->pdev_dev, "Err %d for Traffic Class config\n", @@ -2889,14 +2873,29 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate) return err; } -static int cxgb_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc) +static int cxgb_setup_tc_cls_u32(struct net_device *dev, + struct tc_cls_u32_offload *cls_u32) { - struct port_info *pi = netdev2pinfo(dev); - struct adapter *adap = netdev2adap(dev); + if (!is_classid_clsact_ingress(cls_u32->common.classid) || + cls_u32->common.chain_index) + return -EOPNOTSUPP; - if (chain_index) + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return cxgb4_config_knode(dev, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return cxgb4_delete_knode(dev, cls_u32); + default: return -EOPNOTSUPP; + } +} + +static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct port_info *pi = netdev2pinfo(dev); + struct adapter *adap = netdev2adap(dev); if (!(adap->flags & FULL_INIT_DONE)) { dev_err(adap->pdev_dev, @@ -2905,20 +2904,12 @@ static int cxgb_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, return -EINVAL; } - if (TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS) && - tc->type == TC_SETUP_CLSU32) { - switch (tc->cls_u32->command) { - case TC_CLSU32_NEW_KNODE: - case TC_CLSU32_REPLACE_KNODE: - return cxgb4_config_knode(dev, proto, tc->cls_u32); - case TC_CLSU32_DELETE_KNODE: - return cxgb4_delete_knode(dev, proto, tc->cls_u32); - default: - return -EOPNOTSUPP; - } + switch (type) { + case TC_SETUP_CLSU32: + return cxgb_setup_tc_cls_u32(dev, type_data); + default: + return -EOPNOTSUPP; } - - return -EOPNOTSUPP; } static netdev_features_t cxgb_fix_features(struct net_device *dev, @@ -3610,11 +3601,8 @@ static int adap_init0(struct adapter *adap) * later reporting and B. to warn if the currently loaded firmware * is excessively mismatched relative to the driver.) */ - t4_get_fw_version(adap, &adap->params.fw_vers); - t4_get_bs_version(adap, &adap->params.bs_vers); - t4_get_tp_version(adap, &adap->params.tp_vers); - t4_get_exprom_version(adap, &adap->params.er_vers); + t4_get_version_info(adap); ret = t4_check_fw_version(adap); /* If firmware is too old (not supported by driver) force an update. */ if (ret) @@ -4204,8 +4192,9 @@ static inline bool is_x_10g_port(const struct link_config *lc) { unsigned int speeds, high_speeds; - speeds = FW_PORT_CAP_SPEED_V(FW_PORT_CAP_SPEED_G(lc->supported)); - high_speeds = speeds & ~(FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G); + speeds = FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_G(lc->pcaps)); + high_speeds = speeds & + ~(FW_PORT_CAP32_SPEED_100M | FW_PORT_CAP32_SPEED_1G); return high_speeds != 0; } @@ -4560,56 +4549,8 @@ static void cxgb4_check_pcie_caps(struct adapter *adap) /* Dump basic information about the adapter */ static void print_adapter_info(struct adapter *adapter) { - /* Device information */ - dev_info(adapter->pdev_dev, "Chelsio %s rev %d\n", - adapter->params.vpd.id, - CHELSIO_CHIP_RELEASE(adapter->params.chip)); - dev_info(adapter->pdev_dev, "S/N: %s, P/N: %s\n", - adapter->params.vpd.sn, adapter->params.vpd.pn); - - /* Firmware Version */ - if (!adapter->params.fw_vers) - dev_warn(adapter->pdev_dev, "No firmware loaded\n"); - else - dev_info(adapter->pdev_dev, "Firmware version: %u.%u.%u.%u\n", - FW_HDR_FW_VER_MAJOR_G(adapter->params.fw_vers), - FW_HDR_FW_VER_MINOR_G(adapter->params.fw_vers), - FW_HDR_FW_VER_MICRO_G(adapter->params.fw_vers), - FW_HDR_FW_VER_BUILD_G(adapter->params.fw_vers)); - - /* Bootstrap Firmware Version. (Some adapters don't have Bootstrap - * Firmware, so dev_info() is more appropriate here.) - */ - if (!adapter->params.bs_vers) - dev_info(adapter->pdev_dev, "No bootstrap loaded\n"); - else - dev_info(adapter->pdev_dev, "Bootstrap version: %u.%u.%u.%u\n", - FW_HDR_FW_VER_MAJOR_G(adapter->params.bs_vers), - FW_HDR_FW_VER_MINOR_G(adapter->params.bs_vers), - FW_HDR_FW_VER_MICRO_G(adapter->params.bs_vers), - FW_HDR_FW_VER_BUILD_G(adapter->params.bs_vers)); - - /* TP Microcode Version */ - if (!adapter->params.tp_vers) - dev_warn(adapter->pdev_dev, "No TP Microcode loaded\n"); - else - dev_info(adapter->pdev_dev, - "TP Microcode version: %u.%u.%u.%u\n", - FW_HDR_FW_VER_MAJOR_G(adapter->params.tp_vers), - FW_HDR_FW_VER_MINOR_G(adapter->params.tp_vers), - FW_HDR_FW_VER_MICRO_G(adapter->params.tp_vers), - FW_HDR_FW_VER_BUILD_G(adapter->params.tp_vers)); - - /* Expansion ROM version */ - if (!adapter->params.er_vers) - dev_info(adapter->pdev_dev, "No Expansion ROM loaded\n"); - else - dev_info(adapter->pdev_dev, - "Expansion ROM version: %u.%u.%u.%u\n", - FW_HDR_FW_VER_MAJOR_G(adapter->params.er_vers), - FW_HDR_FW_VER_MINOR_G(adapter->params.er_vers), - FW_HDR_FW_VER_MICRO_G(adapter->params.er_vers), - FW_HDR_FW_VER_BUILD_G(adapter->params.er_vers)); + /* Hardware/Firmware/etc. Version/Revision IDs */ + t4_dump_version_info(adapter); /* Software/Hardware configuration */ dev_info(adapter->pdev_dev, "Configuration: %sNIC %s, %s capable\n", @@ -4634,18 +4575,24 @@ static void print_port_info(const struct net_device *dev) else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_8_0GB) spd = " 8 GT/s"; - if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_100M) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_100M) bufp += sprintf(bufp, "100M/"); - if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_1G) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_1G) bufp += sprintf(bufp, "1G/"); - if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_10G) bufp += sprintf(bufp, "10G/"); - if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_25G) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_25G) bufp += sprintf(bufp, "25G/"); - if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_40G) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_40G) bufp += sprintf(bufp, "40G/"); - if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_100G) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_50G) + bufp += sprintf(bufp, "50G/"); + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_100G) bufp += sprintf(bufp, "100G/"); + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_200G) + bufp += sprintf(bufp, "200G/"); + if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_400G) + bufp += sprintf(bufp, "400G/"); if (bufp != buf) --bufp; sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type)); @@ -4751,10 +4698,11 @@ static int config_mgmt_dev(struct pci_dev *pdev) pi = netdev_priv(netdev); pi->adapter = adap; - pi->port_id = adap->pf % adap->params.nports; + pi->tx_chan = adap->pf % adap->params.nports; SET_NETDEV_DEV(netdev, &pdev->dev); adap->port[0] = netdev; + pi->port_id = 0; err = register_netdev(adap->port[0]); if (err) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c index ef06ce8247ab..48970ba08bdc 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c @@ -96,7 +96,7 @@ static int fill_action_fields(struct adapter *adap, LIST_HEAD(actions); exts = cls->knode.exts; - if (tc_no_actions(exts)) + if (!tcf_exts_has_actions(exts)) return -EINVAL; tcf_exts_to_list(exts, &actions); @@ -146,11 +146,11 @@ static int fill_action_fields(struct adapter *adap, return 0; } -int cxgb4_config_knode(struct net_device *dev, __be16 protocol, - struct tc_cls_u32_offload *cls) +int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls) { const struct cxgb4_match_field *start, *link_start = NULL; struct adapter *adapter = netdev2adap(dev); + __be16 protocol = cls->common.protocol; struct ch_filter_specification fs; struct cxgb4_tc_u32_table *t; struct cxgb4_link *link; @@ -338,8 +338,7 @@ out: return ret; } -int cxgb4_delete_knode(struct net_device *dev, __be16 protocol, - struct tc_cls_u32_offload *cls) +int cxgb4_delete_knode(struct net_device *dev, struct tc_cls_u32_offload *cls) { struct adapter *adapter = netdev2adap(dev); unsigned int filter_id, max_tids, i, j; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.h index 021261a41c13..70a07b7cca56 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.h @@ -44,10 +44,8 @@ static inline bool can_tc_u32_offload(struct net_device *dev) return (dev->features & NETIF_F_HW_TC) && adap->tc_u32 ? true : false; } -int cxgb4_config_knode(struct net_device *dev, __be16 protocol, - struct tc_cls_u32_offload *cls); -int cxgb4_delete_knode(struct net_device *dev, __be16 protocol, - struct tc_cls_u32_offload *cls); +int cxgb4_config_knode(struct net_device *dev, struct tc_cls_u32_offload *cls); +int cxgb4_delete_knode(struct net_device *dev, struct tc_cls_u32_offload *cls); void cxgb4_cleanup_tc_u32(struct adapter *adapter); struct cxgb4_tc_u32_table *cxgb4_init_tc_u32(struct adapter *adap); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index 02acff741f11..9148abb7994c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -533,10 +533,10 @@ struct sched_table *t4_init_sched(unsigned int sched_size) void t4_cleanup_sched(struct adapter *adap) { struct sched_table *s; - unsigned int i; + unsigned int j, i; - for_each_port(adap, i) { - struct port_info *pi = netdev2pinfo(adap->port[i]); + for_each_port(adap, j) { + struct port_info *pi = netdev2pinfo(adap->port[j]); s = pi->sched_tbl; for (i = 0; i < s->sched_size; i++) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 0293b41171a5..b65ce26ff72f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -913,7 +913,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0xd010, 0xd03c, 0xdfc0, 0xdfe0, 0xe000, 0xea7c, - 0xf000, 0x11190, + 0xf000, 0x11110, + 0x11118, 0x11190, 0x19040, 0x1906c, 0x19078, 0x19080, 0x1908c, 0x190e4, @@ -1439,8 +1440,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x1ff00, 0x1ff84, 0x1ffc0, 0x1ffc8, 0x30000, 0x30030, - 0x30038, 0x30038, - 0x30040, 0x30040, 0x30100, 0x30144, 0x30190, 0x301a0, 0x301a8, 0x301b8, @@ -1551,8 +1550,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x33c3c, 0x33c50, 0x33cf0, 0x33cfc, 0x34000, 0x34030, - 0x34038, 0x34038, - 0x34040, 0x34040, 0x34100, 0x34144, 0x34190, 0x341a0, 0x341a8, 0x341b8, @@ -1663,8 +1660,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x37c3c, 0x37c50, 0x37cf0, 0x37cfc, 0x38000, 0x38030, - 0x38038, 0x38038, - 0x38040, 0x38040, 0x38100, 0x38144, 0x38190, 0x381a0, 0x381a8, 0x381b8, @@ -1775,8 +1770,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x3bc3c, 0x3bc50, 0x3bcf0, 0x3bcfc, 0x3c000, 0x3c030, - 0x3c038, 0x3c038, - 0x3c040, 0x3c040, 0x3c100, 0x3c144, 0x3c190, 0x3c1a0, 0x3c1a8, 0x3c1b8, @@ -2040,12 +2033,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x1190, 0x1194, 0x11a0, 0x11a4, 0x11b0, 0x11b4, - 0x11fc, 0x1258, - 0x1280, 0x12d4, - 0x12d9, 0x12d9, - 0x12de, 0x12de, - 0x12e3, 0x12e3, - 0x12e8, 0x133c, + 0x11fc, 0x1274, + 0x1280, 0x133c, 0x1800, 0x18fc, 0x3000, 0x302c, 0x3060, 0x30b0, @@ -2076,6 +2065,9 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x5ea0, 0x5eb0, 0x5ec0, 0x5ec0, 0x5ec8, 0x5ed0, + 0x5ee0, 0x5ee0, + 0x5ef0, 0x5ef0, + 0x5f00, 0x5f00, 0x6000, 0x6020, 0x6028, 0x6040, 0x6058, 0x609c, @@ -2133,6 +2125,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0xd300, 0xd31c, 0xdfc0, 0xdfe0, 0xe000, 0xf008, + 0xf010, 0xf018, + 0xf020, 0xf028, 0x11000, 0x11014, 0x11048, 0x1106c, 0x11074, 0x11088, @@ -2256,13 +2250,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x1ff00, 0x1ff84, 0x1ffc0, 0x1ffc8, 0x30000, 0x30030, - 0x30038, 0x30038, - 0x30040, 0x30040, - 0x30048, 0x30048, - 0x30050, 0x30050, - 0x3005c, 0x30060, - 0x30068, 0x30068, - 0x30070, 0x30070, 0x30100, 0x30168, 0x30190, 0x301a0, 0x301a8, 0x301b8, @@ -2325,13 +2312,12 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x326a8, 0x326a8, 0x326ec, 0x326ec, 0x32a00, 0x32abc, - 0x32b00, 0x32b38, + 0x32b00, 0x32b18, + 0x32b20, 0x32b38, 0x32b40, 0x32b58, 0x32b60, 0x32b78, 0x32c00, 0x32c00, 0x32c08, 0x32c3c, - 0x32e00, 0x32e2c, - 0x32f00, 0x32f2c, 0x33000, 0x3302c, 0x33034, 0x33050, 0x33058, 0x33058, @@ -2396,13 +2382,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x33c38, 0x33c50, 0x33cf0, 0x33cfc, 0x34000, 0x34030, - 0x34038, 0x34038, - 0x34040, 0x34040, - 0x34048, 0x34048, - 0x34050, 0x34050, - 0x3405c, 0x34060, - 0x34068, 0x34068, - 0x34070, 0x34070, 0x34100, 0x34168, 0x34190, 0x341a0, 0x341a8, 0x341b8, @@ -2465,13 +2444,12 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x366a8, 0x366a8, 0x366ec, 0x366ec, 0x36a00, 0x36abc, - 0x36b00, 0x36b38, + 0x36b00, 0x36b18, + 0x36b20, 0x36b38, 0x36b40, 0x36b58, 0x36b60, 0x36b78, 0x36c00, 0x36c00, 0x36c08, 0x36c3c, - 0x36e00, 0x36e2c, - 0x36f00, 0x36f2c, 0x37000, 0x3702c, 0x37034, 0x37050, 0x37058, 0x37058, @@ -2545,8 +2523,7 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x40280, 0x40280, 0x40304, 0x40304, 0x40330, 0x4033c, - 0x41304, 0x413b8, - 0x413c0, 0x413c8, + 0x41304, 0x413c8, 0x413d0, 0x413dc, 0x413f0, 0x413f0, 0x41400, 0x4140c, @@ -3100,6 +3077,179 @@ int t4_get_exprom_version(struct adapter *adap, u32 *vers) } /** + * t4_get_vpd_version - return the VPD version + * @adapter: the adapter + * @vers: where to place the version + * + * Reads the VPD via the Firmware interface (thus this can only be called + * once we're ready to issue Firmware commands). The format of the + * VPD version is adapter specific. Returns 0 on success, an error on + * failure. + * + * Note that early versions of the Firmware didn't include the ability + * to retrieve the VPD version, so we zero-out the return-value parameter + * in that case to avoid leaving it with garbage in it. + * + * Also note that the Firmware will return its cached copy of the VPD + * Revision ID, not the actual Revision ID as written in the Serial + * EEPROM. This is only an issue if a new VPD has been written and the + * Firmware/Chip haven't yet gone through a RESET sequence. So it's best + * to defer calling this routine till after a FW_RESET_CMD has been issued + * if the Host Driver will be performing a full adapter initialization. + */ +int t4_get_vpd_version(struct adapter *adapter, u32 *vers) +{ + u32 vpdrev_param; + int ret; + + vpdrev_param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_VPDREV)); + ret = t4_query_params(adapter, adapter->mbox, adapter->pf, 0, + 1, &vpdrev_param, vers); + if (ret) + *vers = 0; + return ret; +} + +/** + * t4_get_scfg_version - return the Serial Configuration version + * @adapter: the adapter + * @vers: where to place the version + * + * Reads the Serial Configuration Version via the Firmware interface + * (thus this can only be called once we're ready to issue Firmware + * commands). The format of the Serial Configuration version is + * adapter specific. Returns 0 on success, an error on failure. + * + * Note that early versions of the Firmware didn't include the ability + * to retrieve the Serial Configuration version, so we zero-out the + * return-value parameter in that case to avoid leaving it with + * garbage in it. + * + * Also note that the Firmware will return its cached copy of the Serial + * Initialization Revision ID, not the actual Revision ID as written in + * the Serial EEPROM. This is only an issue if a new VPD has been written + * and the Firmware/Chip haven't yet gone through a RESET sequence. So + * it's best to defer calling this routine till after a FW_RESET_CMD has + * been issued if the Host Driver will be performing a full adapter + * initialization. + */ +int t4_get_scfg_version(struct adapter *adapter, u32 *vers) +{ + u32 scfgrev_param; + int ret; + + scfgrev_param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_SCFGREV)); + ret = t4_query_params(adapter, adapter->mbox, adapter->pf, 0, + 1, &scfgrev_param, vers); + if (ret) + *vers = 0; + return ret; +} + +/** + * t4_get_version_info - extract various chip/firmware version information + * @adapter: the adapter + * + * Reads various chip/firmware version numbers and stores them into the + * adapter Adapter Parameters structure. If any of the efforts fails + * the first failure will be returned, but all of the version numbers + * will be read. + */ +int t4_get_version_info(struct adapter *adapter) +{ + int ret = 0; + + #define FIRST_RET(__getvinfo) \ + do { \ + int __ret = __getvinfo; \ + if (__ret && !ret) \ + ret = __ret; \ + } while (0) + + FIRST_RET(t4_get_fw_version(adapter, &adapter->params.fw_vers)); + FIRST_RET(t4_get_bs_version(adapter, &adapter->params.bs_vers)); + FIRST_RET(t4_get_tp_version(adapter, &adapter->params.tp_vers)); + FIRST_RET(t4_get_exprom_version(adapter, &adapter->params.er_vers)); + FIRST_RET(t4_get_scfg_version(adapter, &adapter->params.scfg_vers)); + FIRST_RET(t4_get_vpd_version(adapter, &adapter->params.vpd_vers)); + + #undef FIRST_RET + return ret; +} + +/** + * t4_dump_version_info - dump all of the adapter configuration IDs + * @adapter: the adapter + * + * Dumps all of the various bits of adapter configuration version/revision + * IDs information. This is typically called at some point after + * t4_get_version_info() has been called. + */ +void t4_dump_version_info(struct adapter *adapter) +{ + /* Device information */ + dev_info(adapter->pdev_dev, "Chelsio %s rev %d\n", + adapter->params.vpd.id, + CHELSIO_CHIP_RELEASE(adapter->params.chip)); + dev_info(adapter->pdev_dev, "S/N: %s, P/N: %s\n", + adapter->params.vpd.sn, adapter->params.vpd.pn); + + /* Firmware Version */ + if (!adapter->params.fw_vers) + dev_warn(adapter->pdev_dev, "No firmware loaded\n"); + else + dev_info(adapter->pdev_dev, "Firmware version: %u.%u.%u.%u\n", + FW_HDR_FW_VER_MAJOR_G(adapter->params.fw_vers), + FW_HDR_FW_VER_MINOR_G(adapter->params.fw_vers), + FW_HDR_FW_VER_MICRO_G(adapter->params.fw_vers), + FW_HDR_FW_VER_BUILD_G(adapter->params.fw_vers)); + + /* Bootstrap Firmware Version. (Some adapters don't have Bootstrap + * Firmware, so dev_info() is more appropriate here.) + */ + if (!adapter->params.bs_vers) + dev_info(adapter->pdev_dev, "No bootstrap loaded\n"); + else + dev_info(adapter->pdev_dev, "Bootstrap version: %u.%u.%u.%u\n", + FW_HDR_FW_VER_MAJOR_G(adapter->params.bs_vers), + FW_HDR_FW_VER_MINOR_G(adapter->params.bs_vers), + FW_HDR_FW_VER_MICRO_G(adapter->params.bs_vers), + FW_HDR_FW_VER_BUILD_G(adapter->params.bs_vers)); + + /* TP Microcode Version */ + if (!adapter->params.tp_vers) + dev_warn(adapter->pdev_dev, "No TP Microcode loaded\n"); + else + dev_info(adapter->pdev_dev, + "TP Microcode version: %u.%u.%u.%u\n", + FW_HDR_FW_VER_MAJOR_G(adapter->params.tp_vers), + FW_HDR_FW_VER_MINOR_G(adapter->params.tp_vers), + FW_HDR_FW_VER_MICRO_G(adapter->params.tp_vers), + FW_HDR_FW_VER_BUILD_G(adapter->params.tp_vers)); + + /* Expansion ROM version */ + if (!adapter->params.er_vers) + dev_info(adapter->pdev_dev, "No Expansion ROM loaded\n"); + else + dev_info(adapter->pdev_dev, + "Expansion ROM version: %u.%u.%u.%u\n", + FW_HDR_FW_VER_MAJOR_G(adapter->params.er_vers), + FW_HDR_FW_VER_MINOR_G(adapter->params.er_vers), + FW_HDR_FW_VER_MICRO_G(adapter->params.er_vers), + FW_HDR_FW_VER_BUILD_G(adapter->params.er_vers)); + + /* Serial Configuration version */ + dev_info(adapter->pdev_dev, "Serial Configuration version: %#x\n", + adapter->params.scfg_vers); + + /* VPD Version */ + dev_info(adapter->pdev_dev, "VPD version: %#x\n", + adapter->params.vpd_vers); +} + +/** * t4_check_fw_version - check if the FW is supported with this driver * @adap: the adapter * @@ -3685,16 +3835,143 @@ void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf) } } -#define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\ - FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_25G | \ - FW_PORT_CAP_SPEED_40G | FW_PORT_CAP_SPEED_100G | \ - FW_PORT_CAP_ANEG) +#define ADVERT_MASK (FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_M) | \ + FW_PORT_CAP32_ANEG) + +/** + * fwcaps16_to_caps32 - convert 16-bit Port Capabilities to 32-bits + * @caps16: a 16-bit Port Capabilities value + * + * Returns the equivalent 32-bit Port Capabilities value. + */ +static fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16) +{ + fw_port_cap32_t caps32 = 0; + + #define CAP16_TO_CAP32(__cap) \ + do { \ + if (caps16 & FW_PORT_CAP_##__cap) \ + caps32 |= FW_PORT_CAP32_##__cap; \ + } while (0) + + CAP16_TO_CAP32(SPEED_100M); + CAP16_TO_CAP32(SPEED_1G); + CAP16_TO_CAP32(SPEED_25G); + CAP16_TO_CAP32(SPEED_10G); + CAP16_TO_CAP32(SPEED_40G); + CAP16_TO_CAP32(SPEED_100G); + CAP16_TO_CAP32(FC_RX); + CAP16_TO_CAP32(FC_TX); + CAP16_TO_CAP32(ANEG); + CAP16_TO_CAP32(MDIX); + CAP16_TO_CAP32(MDIAUTO); + CAP16_TO_CAP32(FEC_RS); + CAP16_TO_CAP32(FEC_BASER_RS); + CAP16_TO_CAP32(802_3_PAUSE); + CAP16_TO_CAP32(802_3_ASM_DIR); + + #undef CAP16_TO_CAP32 + + return caps32; +} + +/** + * fwcaps32_to_caps16 - convert 32-bit Port Capabilities to 16-bits + * @caps32: a 32-bit Port Capabilities value + * + * Returns the equivalent 16-bit Port Capabilities value. Note that + * not all 32-bit Port Capabilities can be represented in the 16-bit + * Port Capabilities and some fields/values may not make it. + */ +static fw_port_cap16_t fwcaps32_to_caps16(fw_port_cap32_t caps32) +{ + fw_port_cap16_t caps16 = 0; + + #define CAP32_TO_CAP16(__cap) \ + do { \ + if (caps32 & FW_PORT_CAP32_##__cap) \ + caps16 |= FW_PORT_CAP_##__cap; \ + } while (0) + + CAP32_TO_CAP16(SPEED_100M); + CAP32_TO_CAP16(SPEED_1G); + CAP32_TO_CAP16(SPEED_10G); + CAP32_TO_CAP16(SPEED_25G); + CAP32_TO_CAP16(SPEED_40G); + CAP32_TO_CAP16(SPEED_100G); + CAP32_TO_CAP16(FC_RX); + CAP32_TO_CAP16(FC_TX); + CAP32_TO_CAP16(802_3_PAUSE); + CAP32_TO_CAP16(802_3_ASM_DIR); + CAP32_TO_CAP16(ANEG); + CAP32_TO_CAP16(MDIX); + CAP32_TO_CAP16(MDIAUTO); + CAP32_TO_CAP16(FEC_RS); + CAP32_TO_CAP16(FEC_BASER_RS); + + #undef CAP32_TO_CAP16 + + return caps16; +} + +/* Translate Firmware Port Capabilities Pause specification to Common Code */ +static inline enum cc_pause fwcap_to_cc_pause(fw_port_cap32_t fw_pause) +{ + enum cc_pause cc_pause = 0; + + if (fw_pause & FW_PORT_CAP32_FC_RX) + cc_pause |= PAUSE_RX; + if (fw_pause & FW_PORT_CAP32_FC_TX) + cc_pause |= PAUSE_TX; + + return cc_pause; +} + +/* Translate Common Code Pause specification into Firmware Port Capabilities */ +static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause) +{ + fw_port_cap32_t fw_pause = 0; + + if (cc_pause & PAUSE_RX) + fw_pause |= FW_PORT_CAP32_FC_RX; + if (cc_pause & PAUSE_TX) + fw_pause |= FW_PORT_CAP32_FC_TX; + + return fw_pause; +} + +/* Translate Firmware Forward Error Correction specification to Common Code */ +static inline enum cc_fec fwcap_to_cc_fec(fw_port_cap32_t fw_fec) +{ + enum cc_fec cc_fec = 0; + + if (fw_fec & FW_PORT_CAP32_FEC_RS) + cc_fec |= FEC_RS; + if (fw_fec & FW_PORT_CAP32_FEC_BASER_RS) + cc_fec |= FEC_BASER_RS; + + return cc_fec; +} + +/* Translate Common Code Forward Error Correction specification to Firmware */ +static inline fw_port_cap32_t cc_to_fwcap_fec(enum cc_fec cc_fec) +{ + fw_port_cap32_t fw_fec = 0; + + if (cc_fec & FEC_RS) + fw_fec |= FW_PORT_CAP32_FEC_RS; + if (cc_fec & FEC_BASER_RS) + fw_fec |= FW_PORT_CAP32_FEC_BASER_RS; + + return fw_fec; +} /** * t4_link_l1cfg - apply link configuration to MAC/PHY - * @phy: the PHY to setup - * @mac: the MAC to setup - * @lc: the requested link configuration + * @adapter: the adapter + * @mbox: the Firmware Mailbox to use + * @port: the Port ID + * @lc: the Port's Link Configuration * * Set up a port's MAC and PHY according to a desired link configuration. * - If the PHY can auto-negotiate first decide what to advertise, then @@ -3703,47 +3980,64 @@ void t4_ulprx_read_la(struct adapter *adap, u32 *la_buf) * - If auto-negotiation is off set the MAC to the proper speed/duplex/FC, * otherwise do it later based on the outcome of auto-negotiation. */ -int t4_link_l1cfg(struct adapter *adap, unsigned int mbox, unsigned int port, - struct link_config *lc) +int t4_link_l1cfg(struct adapter *adapter, unsigned int mbox, + unsigned int port, struct link_config *lc) { - struct fw_port_cmd c; - unsigned int mdi = FW_PORT_CAP_MDI_V(FW_PORT_CAP_MDI_AUTO); - unsigned int fc = 0, fec = 0, fw_fec = 0; + unsigned int fw_caps = adapter->params.fw_caps_support; + struct fw_port_cmd cmd; + unsigned int fw_mdi = FW_PORT_CAP32_MDI_V(FW_PORT_CAP32_MDI_AUTO); + fw_port_cap32_t fw_fc, cc_fec, fw_fec, rcap; lc->link_ok = 0; - if (lc->requested_fc & PAUSE_RX) - fc |= FW_PORT_CAP_FC_RX; - if (lc->requested_fc & PAUSE_TX) - fc |= FW_PORT_CAP_FC_TX; - - fec = lc->requested_fec & FEC_AUTO ? lc->auto_fec : lc->requested_fec; - - if (fec & FEC_RS) - fw_fec |= FW_PORT_CAP_FEC_RS; - if (fec & FEC_BASER_RS) - fw_fec |= FW_PORT_CAP_FEC_BASER_RS; - memset(&c, 0, sizeof(c)); - c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | - FW_CMD_REQUEST_F | FW_CMD_EXEC_F | - FW_PORT_CMD_PORTID_V(port)); - c.action_to_len16 = - cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) | - FW_LEN16(c)); + /* Convert driver coding of Pause Frame Flow Control settings into the + * Firmware's API. + */ + fw_fc = cc_to_fwcap_pause(lc->requested_fc); + + /* Convert Common Code Forward Error Control settings into the + * Firmware's API. If the current Requested FEC has "Automatic" + * (IEEE 802.3) specified, then we use whatever the Firmware + * sent us as part of it's IEEE 802.3-based interpratation of + * the Transceiver Module EPROM FEC parameters. Otherwise we + * use whatever is in the current Requested FEC settings. + */ + if (lc->requested_fec & FEC_AUTO) + cc_fec = fwcap_to_cc_fec(lc->def_acaps); + else + cc_fec = lc->requested_fec; + fw_fec = cc_to_fwcap_fec(cc_fec); - if (!(lc->supported & FW_PORT_CAP_ANEG)) { - c.u.l1cfg.rcap = cpu_to_be32((lc->supported & ADVERT_MASK) | - fc | fw_fec); - lc->fc = lc->requested_fc & (PAUSE_RX | PAUSE_TX); + /* Figure out what our Requested Port Capabilities are going to be. + */ + if (!(lc->pcaps & FW_PORT_CAP32_ANEG)) { + rcap = (lc->pcaps & ADVERT_MASK) | fw_fc | fw_fec; + lc->fc = lc->requested_fc & ~PAUSE_AUTONEG; + lc->fec = cc_fec; } else if (lc->autoneg == AUTONEG_DISABLE) { - c.u.l1cfg.rcap = cpu_to_be32(lc->requested_speed | fc | - fw_fec | mdi); - lc->fc = lc->requested_fc & (PAUSE_RX | PAUSE_TX); - } else - c.u.l1cfg.rcap = cpu_to_be32(lc->advertising | fc | - fw_fec | mdi); + rcap = lc->speed_caps | fw_fc | fw_fec | fw_mdi; + lc->fc = lc->requested_fc & ~PAUSE_AUTONEG; + lc->fec = cc_fec; + } else { + rcap = lc->acaps | fw_fc | fw_fec | fw_mdi; + } - return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); + /* And send that on to the Firmware ... + */ + memset(&cmd, 0, sizeof(cmd)); + cmd.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | + FW_CMD_REQUEST_F | FW_CMD_EXEC_F | + FW_PORT_CMD_PORTID_V(port)); + cmd.action_to_len16 = + cpu_to_be32(FW_PORT_CMD_ACTION_V(fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_L1_CFG + : FW_PORT_ACTION_L1_CFG32) | + FW_LEN16(cmd)); + if (fw_caps == FW_CAPS16) + cmd.u.l1cfg.rcap = cpu_to_be32(fwcaps32_to_caps16(rcap)); + else + cmd.u.l1cfg32.rcap32 = cpu_to_be32(rcap); + return t4_wr_mbox(adapter, mbox, &cmd, sizeof(cmd), NULL); } /** @@ -3765,7 +4059,7 @@ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port) c.action_to_len16 = cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_L1_CFG) | FW_LEN16(c)); - c.u.l1cfg.rcap = cpu_to_be32(FW_PORT_CAP_ANEG); + c.u.l1cfg.rcap = cpu_to_be32(FW_PORT_CAP32_ANEG); return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL); } @@ -4254,6 +4548,18 @@ static void mps_intr_handler(struct adapter *adapter) { FRMERR_F, "MPS Tx framing error", -1, 1 }, { 0 } }; + static const struct intr_info t6_mps_tx_intr_info[] = { + { TPFIFO_V(TPFIFO_M), "MPS Tx TP FIFO parity error", -1, 1 }, + { NCSIFIFO_F, "MPS Tx NC-SI FIFO parity error", -1, 1 }, + { TXDATAFIFO_V(TXDATAFIFO_M), "MPS Tx data FIFO parity error", + -1, 1 }, + { TXDESCFIFO_V(TXDESCFIFO_M), "MPS Tx desc FIFO parity error", + -1, 1 }, + /* MPS Tx Bubble is normal for T6 */ + { SECNTERR_F, "MPS Tx SOP/EOP error", -1, 1 }, + { FRMERR_F, "MPS Tx framing error", -1, 1 }, + { 0 } + }; static const struct intr_info mps_trc_intr_info[] = { { FILTMEM_V(FILTMEM_M), "MPS TRC filter parity error", -1, 1 }, { PKTFIFO_V(PKTFIFO_M), "MPS TRC packet FIFO parity error", @@ -4285,7 +4591,9 @@ static void mps_intr_handler(struct adapter *adapter) fat = t4_handle_intr_status(adapter, MPS_RX_PERR_INT_CAUSE_A, mps_rx_intr_info) + t4_handle_intr_status(adapter, MPS_TX_INT_CAUSE_A, - mps_tx_intr_info) + + is_t6(adapter->params.chip) + ? t6_mps_tx_intr_info + : mps_tx_intr_info) + t4_handle_intr_status(adapter, MPS_TRC_INT_CAUSE_A, mps_trc_intr_info) + t4_handle_intr_status(adapter, MPS_STAT_PERR_INT_CAUSE_SRAM_A, @@ -5693,10 +6001,8 @@ void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p) p->tx_ppp7 = GET_STAT(TX_PORT_PPP7); if (CHELSIO_CHIP_VERSION(adap->params.chip) >= CHELSIO_T5) { - if (stat_ctl & COUNTPAUSESTATTX_F) { - p->tx_frames -= p->tx_pause; - p->tx_octets -= p->tx_pause * 64; - } + if (stat_ctl & COUNTPAUSESTATTX_F) + p->tx_frames_64 -= p->tx_pause; if (stat_ctl & COUNTPAUSEMCTX_F) p->tx_mcast_frames -= p->tx_pause; } @@ -5729,10 +6035,8 @@ void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p) p->rx_ppp7 = GET_STAT(RX_PORT_PPP7); if (CHELSIO_CHIP_VERSION(adap->params.chip) >= CHELSIO_T5) { - if (stat_ctl & COUNTPAUSESTATRX_F) { - p->rx_frames -= p->rx_pause; - p->rx_octets -= p->rx_pause * 64; - } + if (stat_ctl & COUNTPAUSESTATRX_F) + p->rx_frames_64 -= p->rx_pause; if (stat_ctl & COUNTPAUSEMCRX_F) p->rx_mcast_frames -= p->rx_pause; } @@ -6449,6 +6753,17 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox, goto out; /* + * If there was a Firmware Configuration File stored in FLASH, + * there's a good chance that it won't be compatible with the new + * Firmware. In order to prevent difficult to diagnose adapter + * initialization issues, we clear out the Firmware Configuration File + * portion of the FLASH . The user will need to re-FLASH a new + * Firmware Configuration File which is compatible with the new + * Firmware if that's desired. + */ + (void)t4_load_cfg(adap, NULL, 0); + + /* * Older versions of the firmware don't understand the new * PCIE_FW.HALT flag and so won't know to perform a RESET when they * restart. So for newly loaded older firmware we'll have to do the @@ -7471,6 +7786,98 @@ static const char *t4_link_down_rc_str(unsigned char link_down_rc) } /** + * Return the highest speed set in the port capabilities, in Mb/s. + */ +static unsigned int fwcap_to_speed(fw_port_cap32_t caps) +{ + #define TEST_SPEED_RETURN(__caps_speed, __speed) \ + do { \ + if (caps & FW_PORT_CAP32_SPEED_##__caps_speed) \ + return __speed; \ + } while (0) + + TEST_SPEED_RETURN(400G, 400000); + TEST_SPEED_RETURN(200G, 200000); + TEST_SPEED_RETURN(100G, 100000); + TEST_SPEED_RETURN(50G, 50000); + TEST_SPEED_RETURN(40G, 40000); + TEST_SPEED_RETURN(25G, 25000); + TEST_SPEED_RETURN(10G, 10000); + TEST_SPEED_RETURN(1G, 1000); + TEST_SPEED_RETURN(100M, 100); + + #undef TEST_SPEED_RETURN + + return 0; +} + +/** + * fwcap_to_fwspeed - return highest speed in Port Capabilities + * @acaps: advertised Port Capabilities + * + * Get the highest speed for the port from the advertised Port + * Capabilities. It will be either the highest speed from the list of + * speeds or whatever user has set using ethtool. + */ +static fw_port_cap32_t fwcap_to_fwspeed(fw_port_cap32_t acaps) +{ + #define TEST_SPEED_RETURN(__caps_speed) \ + do { \ + if (acaps & FW_PORT_CAP32_SPEED_##__caps_speed) \ + return FW_PORT_CAP32_SPEED_##__caps_speed; \ + } while (0) + + TEST_SPEED_RETURN(400G); + TEST_SPEED_RETURN(200G); + TEST_SPEED_RETURN(100G); + TEST_SPEED_RETURN(50G); + TEST_SPEED_RETURN(40G); + TEST_SPEED_RETURN(25G); + TEST_SPEED_RETURN(10G); + TEST_SPEED_RETURN(1G); + TEST_SPEED_RETURN(100M); + + #undef TEST_SPEED_RETURN + + return 0; +} + +/** + * lstatus_to_fwcap - translate old lstatus to 32-bit Port Capabilities + * @lstatus: old FW_PORT_ACTION_GET_PORT_INFO lstatus value + * + * Translates old FW_PORT_ACTION_GET_PORT_INFO lstatus field into new + * 32-bit Port Capabilities value. + */ +static fw_port_cap32_t lstatus_to_fwcap(u32 lstatus) +{ + fw_port_cap32_t linkattr = 0; + + /* Unfortunately the format of the Link Status in the old + * 16-bit Port Information message isn't the same as the + * 16-bit Port Capabilities bitfield used everywhere else ... + */ + if (lstatus & FW_PORT_CMD_RXPAUSE_F) + linkattr |= FW_PORT_CAP32_FC_RX; + if (lstatus & FW_PORT_CMD_TXPAUSE_F) + linkattr |= FW_PORT_CAP32_FC_TX; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100M)) + linkattr |= FW_PORT_CAP32_SPEED_100M; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_1G)) + linkattr |= FW_PORT_CAP32_SPEED_1G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G)) + linkattr |= FW_PORT_CAP32_SPEED_10G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G)) + linkattr |= FW_PORT_CAP32_SPEED_25G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G)) + linkattr |= FW_PORT_CAP32_SPEED_40G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G)) + linkattr |= FW_PORT_CAP32_SPEED_100G; + + return linkattr; +} + +/** * t4_handle_get_port_info - process a FW reply message * @pi: the port info * @rpl: start of the FW message @@ -7479,56 +7886,123 @@ static const char *t4_link_down_rc_str(unsigned char link_down_rc) */ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) { - const struct fw_port_cmd *p = (const void *)rpl; - struct adapter *adap = pi->adapter; - - /* link/module state change message */ - int speed = 0, fc = 0; - struct link_config *lc; - u32 stat = be32_to_cpu(p->u.info.lstatus_to_modtype); - int link_ok = (stat & FW_PORT_CMD_LSTATUS_F) != 0; - u32 mod = FW_PORT_CMD_MODTYPE_G(stat); - - if (stat & FW_PORT_CMD_RXPAUSE_F) - fc |= PAUSE_RX; - if (stat & FW_PORT_CMD_TXPAUSE_F) - fc |= PAUSE_TX; - if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100M)) - speed = 100; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_1G)) - speed = 1000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G)) - speed = 10000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G)) - speed = 25000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G)) - speed = 40000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G)) - speed = 100000; - - lc = &pi->link_cfg; - - if (mod != pi->mod_type) { - pi->mod_type = mod; - t4_os_portmod_changed(adap, pi->port_id); + const struct fw_port_cmd *cmd = (const void *)rpl; + int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); + struct adapter *adapter = pi->adapter; + struct link_config *lc = &pi->link_cfg; + int link_ok, linkdnrc; + enum fw_port_type port_type; + enum fw_port_module_type mod_type; + unsigned int speed, fc, fec; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + + /* Extract the various fields from the Port Information message. + */ + switch (action) { + case FW_PORT_ACTION_GET_PORT_INFO: { + u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); + + link_ok = (lstatus & FW_PORT_CMD_LSTATUS_F) != 0; + linkdnrc = FW_PORT_CMD_LINKDNRC_G(lstatus); + port_type = FW_PORT_CMD_PTYPE_G(lstatus); + mod_type = FW_PORT_CMD_MODTYPE_G(lstatus); + pcaps = fwcaps16_to_caps32(be16_to_cpu(cmd->u.info.pcap)); + acaps = fwcaps16_to_caps32(be16_to_cpu(cmd->u.info.acap)); + lpacaps = fwcaps16_to_caps32(be16_to_cpu(cmd->u.info.lpacap)); + linkattr = lstatus_to_fwcap(lstatus); + break; } + + case FW_PORT_ACTION_GET_PORT_INFO32: { + u32 lstatus32; + + lstatus32 = be32_to_cpu(cmd->u.info32.lstatus32_to_cbllen32); + link_ok = (lstatus32 & FW_PORT_CMD_LSTATUS32_F) != 0; + linkdnrc = FW_PORT_CMD_LINKDNRC32_G(lstatus32); + port_type = FW_PORT_CMD_PORTTYPE32_G(lstatus32); + mod_type = FW_PORT_CMD_MODTYPE32_G(lstatus32); + pcaps = be32_to_cpu(cmd->u.info32.pcaps32); + acaps = be32_to_cpu(cmd->u.info32.acaps32); + lpacaps = be32_to_cpu(cmd->u.info32.lpacaps32); + linkattr = be32_to_cpu(cmd->u.info32.linkattr32); + break; + } + + default: + dev_err(adapter->pdev_dev, "Handle Port Information: Bad Command/Action %#x\n", + be32_to_cpu(cmd->action_to_len16)); + return; + } + + fec = fwcap_to_cc_fec(acaps); + fc = fwcap_to_cc_pause(linkattr); + speed = fwcap_to_speed(linkattr); + + if (mod_type != pi->mod_type) { + /* With the newer SFP28 and QSFP28 Transceiver Module Types, + * various fundamental Port Capabilities which used to be + * immutable can now change radically. We can now have + * Speeds, Auto-Negotiation, Forward Error Correction, etc. + * all change based on what Transceiver Module is inserted. + * So we need to record the Physical "Port" Capabilities on + * every Transceiver Module change. + */ + lc->pcaps = pcaps; + + /* When a new Transceiver Module is inserted, the Firmware + * will examine its i2c EPROM to determine its type and + * general operating parameters including things like Forward + * Error Control, etc. Various IEEE 802.3 standards dictate + * how to interpret these i2c values to determine default + * "sutomatic" settings. We record these for future use when + * the user explicitly requests these standards-based values. + */ + lc->def_acaps = acaps; + + /* Some versions of the early T6 Firmware "cheated" when + * handling different Transceiver Modules by changing the + * underlaying Port Type reported to the Host Drivers. As + * such we need to capture whatever Port Type the Firmware + * sends us and record it in case it's different from what we + * were told earlier. Unfortunately, since Firmware is + * forever, we'll need to keep this code here forever, but in + * later T6 Firmware it should just be an assignment of the + * same value already recorded. + */ + pi->port_type = port_type; + + pi->mod_type = mod_type; + t4_os_portmod_changed(adapter, pi->port_id); + } + if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc) { /* something changed */ + fc != lc->fc || fec != lc->fec) { /* something changed */ if (!link_ok && lc->link_ok) { - unsigned char rc = FW_PORT_CMD_LINKDNRC_G(stat); - - lc->link_down_rc = rc; - dev_warn(adap->pdev_dev, - "Port %d link down, reason: %s\n", - pi->port_id, t4_link_down_rc_str(rc)); + lc->link_down_rc = linkdnrc; + dev_warn(adapter->pdev_dev, "Port %d link down, reason: %s\n", + pi->tx_chan, t4_link_down_rc_str(linkdnrc)); } lc->link_ok = link_ok; lc->speed = speed; lc->fc = fc; - lc->supported = be16_to_cpu(p->u.info.pcap); - lc->lp_advertising = be16_to_cpu(p->u.info.lpacap); + lc->fec = fec; - t4_os_link_changed(adap, pi->port_id, link_ok); + lc->lpacaps = lpacaps; + lc->acaps = acaps & ADVERT_MASK; + + if (lc->acaps & FW_PORT_CAP32_ANEG) { + lc->autoneg = AUTONEG_ENABLE; + } else { + /* When Autoneg is disabled, user needs to set + * single speed. + * Similar to cxgb4_ethtool.c: set_link_ksettings + */ + lc->acaps = 0; + lc->speed_caps = fwcap_to_fwspeed(acaps); + lc->autoneg = AUTONEG_DISABLE; + } + + t4_os_link_changed(adapter, pi->port_id, link_ok); } } @@ -7542,15 +8016,18 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl) */ int t4_update_port_info(struct port_info *pi) { + unsigned int fw_caps = pi->adapter->params.fw_caps_support; struct fw_port_cmd port_cmd; int ret; memset(&port_cmd, 0, sizeof(port_cmd)); port_cmd.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | FW_CMD_REQUEST_F | FW_CMD_READ_F | - FW_PORT_CMD_PORTID_V(pi->port_id)); + FW_PORT_CMD_PORTID_V(pi->tx_chan)); port_cmd.action_to_len16 = cpu_to_be32( - FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_GET_PORT_INFO) | + FW_PORT_CMD_ACTION_V(fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_GET_PORT_INFO + : FW_PORT_ACTION_GET_PORT_INFO32) | FW_LEN16(port_cmd)); ret = t4_wr_mbox(pi->adapter, pi->adapter->mbox, &port_cmd, sizeof(port_cmd), &port_cmd); @@ -7562,6 +8039,65 @@ int t4_update_port_info(struct port_info *pi) } /** + * t4_get_link_params - retrieve basic link parameters for given port + * @pi: the port + * @link_okp: value return pointer for link up/down + * @speedp: value return pointer for speed (Mb/s) + * @mtup: value return pointer for mtu + * + * Retrieves basic link parameters for a port: link up/down, speed (Mb/s), + * and MTU for a specified port. A negative error is returned on + * failure; 0 on success. + */ +int t4_get_link_params(struct port_info *pi, unsigned int *link_okp, + unsigned int *speedp, unsigned int *mtup) +{ + unsigned int fw_caps = pi->adapter->params.fw_caps_support; + struct fw_port_cmd port_cmd; + unsigned int action, link_ok, speed, mtu; + fw_port_cap32_t linkattr; + int ret; + + memset(&port_cmd, 0, sizeof(port_cmd)); + port_cmd.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | + FW_CMD_REQUEST_F | FW_CMD_READ_F | + FW_PORT_CMD_PORTID_V(pi->tx_chan)); + action = (fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_GET_PORT_INFO + : FW_PORT_ACTION_GET_PORT_INFO32); + port_cmd.action_to_len16 = cpu_to_be32( + FW_PORT_CMD_ACTION_V(action) | + FW_LEN16(port_cmd)); + ret = t4_wr_mbox(pi->adapter, pi->adapter->mbox, + &port_cmd, sizeof(port_cmd), &port_cmd); + if (ret) + return ret; + + if (action == FW_PORT_ACTION_GET_PORT_INFO) { + u32 lstatus = be32_to_cpu(port_cmd.u.info.lstatus_to_modtype); + + link_ok = !!(lstatus & FW_PORT_CMD_LSTATUS_F); + linkattr = lstatus_to_fwcap(lstatus); + mtu = be16_to_cpu(port_cmd.u.info.mtu); + } else { + u32 lstatus32 = + be32_to_cpu(port_cmd.u.info32.lstatus32_to_cbllen32); + + link_ok = !!(lstatus32 & FW_PORT_CMD_LSTATUS32_F); + linkattr = be32_to_cpu(port_cmd.u.info32.linkattr32); + mtu = FW_PORT_CMD_MTU32_G( + be32_to_cpu(port_cmd.u.info32.auxlinfo32_mtu32)); + } + speed = fwcap_to_speed(linkattr); + + *link_okp = link_ok; + *speedp = fwcap_to_speed(linkattr); + *mtup = mtu; + + return 0; +} + +/** * t4_handle_fw_rpl - process a FW reply message * @adap: the adapter * @rpl: start of the FW message @@ -7581,7 +8117,9 @@ int t4_handle_fw_rpl(struct adapter *adap, const __be64 *rpl) unsigned int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(p->action_to_len16)); - if (opcode == FW_PORT_CMD && action == FW_PORT_ACTION_GET_PORT_INFO) { + if (opcode == FW_PORT_CMD && + (action == FW_PORT_ACTION_GET_PORT_INFO || + action == FW_PORT_ACTION_GET_PORT_INFO32)) { int i; int chan = FW_PORT_CMD_PORTID_G(be32_to_cpu(p->op_to_portid)); struct port_info *pi = NULL; @@ -7594,7 +8132,8 @@ int t4_handle_fw_rpl(struct adapter *adap, const __be64 *rpl) t4_handle_get_port_info(pi, rpl); } else { - dev_warn(adap->pdev_dev, "Unknown firmware reply %d\n", opcode); + dev_warn(adap->pdev_dev, "Unknown firmware reply %d\n", + opcode); return -EINVAL; } return 0; @@ -7613,38 +8152,35 @@ static void get_pci_mode(struct adapter *adapter, struct pci_params *p) /** * init_link_config - initialize a link's SW state - * @lc: structure holding the link state - * @caps: link capabilities + * @lc: pointer to structure holding the link state + * @pcaps: link Port Capabilities + * @acaps: link current Advertised Port Capabilities * * Initializes the SW state maintained for each link, including the link's * capabilities and default speed/flow-control/autonegotiation settings. */ -static void init_link_config(struct link_config *lc, unsigned int pcaps, - unsigned int acaps) +static void init_link_config(struct link_config *lc, fw_port_cap32_t pcaps, + fw_port_cap32_t acaps) { - lc->supported = pcaps; - lc->lp_advertising = 0; - lc->requested_speed = 0; + lc->pcaps = pcaps; + lc->def_acaps = acaps; + lc->lpacaps = 0; + lc->speed_caps = 0; lc->speed = 0; lc->requested_fc = lc->fc = PAUSE_RX | PAUSE_TX; - lc->auto_fec = 0; /* For Forward Error Control, we default to whatever the Firmware * tells us the Link is currently advertising. */ - if (acaps & FW_PORT_CAP_FEC_RS) - lc->auto_fec |= FEC_RS; - if (acaps & FW_PORT_CAP_FEC_BASER_RS) - lc->auto_fec |= FEC_BASER_RS; lc->requested_fec = FEC_AUTO; - lc->fec = lc->auto_fec; + lc->fec = fwcap_to_cc_fec(lc->def_acaps); - if (lc->supported & FW_PORT_CAP_ANEG) { - lc->advertising = lc->supported & ADVERT_MASK; + if (lc->pcaps & FW_PORT_CAP32_ANEG) { + lc->acaps = lc->pcaps & ADVERT_MASK; lc->autoneg = AUTONEG_ENABLE; lc->requested_fc |= PAUSE_AUTONEG; } else { - lc->advertising = 0; + lc->acaps = 0; lc->autoneg = AUTONEG_DISABLE; } } @@ -8169,7 +8705,7 @@ int t4_init_rss_mode(struct adapter *adap, int mbox) } /** - * t4_init_portinfo - allocate a virtual interface amd initialize port_info + * t4_init_portinfo - allocate a virtual interface and initialize port_info * @pi: the port_info * @mbox: mailbox to use for the FW command * @port: physical port associated with the VI @@ -8185,21 +8721,67 @@ int t4_init_rss_mode(struct adapter *adap, int mbox) int t4_init_portinfo(struct port_info *pi, int mbox, int port, int pf, int vf, u8 mac[]) { - int ret; - struct fw_port_cmd c; + struct adapter *adapter = pi->adapter; + unsigned int fw_caps = adapter->params.fw_caps_support; + struct fw_port_cmd cmd; unsigned int rss_size; + enum fw_port_type port_type; + int mdio_addr; + fw_port_cap32_t pcaps, acaps; + int ret; - memset(&c, 0, sizeof(c)); - c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | - FW_CMD_REQUEST_F | FW_CMD_READ_F | - FW_PORT_CMD_PORTID_V(port)); - c.action_to_len16 = cpu_to_be32( - FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_GET_PORT_INFO) | - FW_LEN16(c)); - ret = t4_wr_mbox(pi->adapter, mbox, &c, sizeof(c), &c); + /* If we haven't yet determined whether we're talking to Firmware + * which knows the new 32-bit Port Capabilities, it's time to find + * out now. This will also tell new Firmware to send us Port Status + * Updates using the new 32-bit Port Capabilities version of the + * Port Information message. + */ + if (fw_caps == FW_CAPS_UNKNOWN) { + u32 param, val; + + param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_PORT_CAPS32)); + val = 1; + ret = t4_set_params(adapter, mbox, pf, vf, 1, ¶m, &val); + fw_caps = (ret == 0 ? FW_CAPS32 : FW_CAPS16); + adapter->params.fw_caps_support = fw_caps; + } + + memset(&cmd, 0, sizeof(cmd)); + cmd.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | + FW_CMD_REQUEST_F | FW_CMD_READ_F | + FW_PORT_CMD_PORTID_V(port)); + cmd.action_to_len16 = cpu_to_be32( + FW_PORT_CMD_ACTION_V(fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_GET_PORT_INFO + : FW_PORT_ACTION_GET_PORT_INFO32) | + FW_LEN16(cmd)); + ret = t4_wr_mbox(pi->adapter, mbox, &cmd, sizeof(cmd), &cmd); if (ret) return ret; + /* Extract the various fields from the Port Information message. + */ + if (fw_caps == FW_CAPS16) { + u32 lstatus = be32_to_cpu(cmd.u.info.lstatus_to_modtype); + + port_type = FW_PORT_CMD_PTYPE_G(lstatus); + mdio_addr = ((lstatus & FW_PORT_CMD_MDIOCAP_F) + ? FW_PORT_CMD_MDIOADDR_G(lstatus) + : -1); + pcaps = fwcaps16_to_caps32(be16_to_cpu(cmd.u.info.pcap)); + acaps = fwcaps16_to_caps32(be16_to_cpu(cmd.u.info.acap)); + } else { + u32 lstatus32 = be32_to_cpu(cmd.u.info32.lstatus32_to_cbllen32); + + port_type = FW_PORT_CMD_PORTTYPE32_G(lstatus32); + mdio_addr = ((lstatus32 & FW_PORT_CMD_MDIOCAP32_F) + ? FW_PORT_CMD_MDIOADDR32_G(lstatus32) + : -1); + pcaps = be32_to_cpu(cmd.u.info32.pcaps32); + acaps = be32_to_cpu(cmd.u.info32.acaps32); + } + ret = t4_alloc_vi(pi->adapter, mbox, port, pf, vf, 1, mac, &rss_size); if (ret < 0) return ret; @@ -8209,14 +8791,11 @@ int t4_init_portinfo(struct port_info *pi, int mbox, pi->lport = port; pi->rss_size = rss_size; - ret = be32_to_cpu(c.u.info.lstatus_to_modtype); - pi->mdio_addr = (ret & FW_PORT_CMD_MDIOCAP_F) ? - FW_PORT_CMD_MDIOADDR_G(ret) : -1; - pi->port_type = FW_PORT_CMD_PTYPE_G(ret); + pi->port_type = port_type; + pi->mdio_addr = mdio_addr; pi->mod_type = FW_PORT_MOD_TYPE_NA; - init_link_config(&pi->link_cfg, be16_to_cpu(c.u.info.pcap), - be16_to_cpu(c.u.info.acap)); + init_link_config(&pi->link_cfg, pcaps, acaps); return 0; } @@ -8664,6 +9243,65 @@ void t4_idma_monitor(struct adapter *adapter, } /** + * t4_load_cfg - download config file + * @adap: the adapter + * @cfg_data: the cfg text file to write + * @size: text file size + * + * Write the supplied config text file to the card's serial flash. + */ +int t4_load_cfg(struct adapter *adap, const u8 *cfg_data, unsigned int size) +{ + int ret, i, n, cfg_addr; + unsigned int addr; + unsigned int flash_cfg_start_sec; + unsigned int sf_sec_size = adap->params.sf_size / adap->params.sf_nsec; + + cfg_addr = t4_flash_cfg_addr(adap); + if (cfg_addr < 0) + return cfg_addr; + + addr = cfg_addr; + flash_cfg_start_sec = addr / SF_SEC_SIZE; + + if (size > FLASH_CFG_MAX_SIZE) { + dev_err(adap->pdev_dev, "cfg file too large, max is %u bytes\n", + FLASH_CFG_MAX_SIZE); + return -EFBIG; + } + + i = DIV_ROUND_UP(FLASH_CFG_MAX_SIZE, /* # of sectors spanned */ + sf_sec_size); + ret = t4_flash_erase_sectors(adap, flash_cfg_start_sec, + flash_cfg_start_sec + i - 1); + /* If size == 0 then we're simply erasing the FLASH sectors associated + * with the on-adapter Firmware Configuration File. + */ + if (ret || size == 0) + goto out; + + /* this will write to the flash up to SF_PAGE_SIZE at a time */ + for (i = 0; i < size; i += SF_PAGE_SIZE) { + if ((size - i) < SF_PAGE_SIZE) + n = size - i; + else + n = SF_PAGE_SIZE; + ret = t4_write_flash(adap, addr, n, cfg_data); + if (ret) + goto out; + + addr += SF_PAGE_SIZE; + cfg_data += SF_PAGE_SIZE; + } + +out: + if (ret) + dev_err(adap->pdev_dev, "config file %s failed %d\n", + (size == 0 ? "clear" : "download"), ret); + return ret; +} + +/** * t4_set_vf_mac - Set MAC address for the specified VF * @adapter: The adapter * @vf: one of the VFs instantiated by the specified PF diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 0ebed64d62d3..ca2756dcefc5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -1124,6 +1124,8 @@ enum fw_params_param_dev { FW_PARAMS_PARAM_DEV_MAXIRD_ADAPTER = 0x14, /* max supported adap IRD */ FW_PARAMS_PARAM_DEV_ULPTX_MEMWRITE_DSGL = 0x17, FW_PARAMS_PARAM_DEV_FWCACHE = 0x18, + FW_PARAMS_PARAM_DEV_SCFGREV = 0x1A, + FW_PARAMS_PARAM_DEV_VPDREV = 0x1B, FW_PARAMS_PARAM_DEV_RI_FR_NSMR_TPTE_WR = 0x1C, FW_PARAMS_PARAM_DEV_MPSBGMAP = 0x1E, }; @@ -1171,7 +1173,8 @@ enum fw_params_param_pfvf { FW_PARAMS_PARAM_PFVF_ACTIVE_FILTER_END = 0x2E, FW_PARAMS_PARAM_PFVF_ETHOFLD_END = 0x30, FW_PARAMS_PARAM_PFVF_CPLFW4MSG_ENCAP = 0x31, - FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x32 + FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x32, + FW_PARAMS_PARAM_PFVF_PORT_CAPS32 = 0x3A, }; /* @@ -2254,6 +2257,7 @@ struct fw_acl_vlan_cmd { #define FW_ACL_VLAN_CMD_FM_S 6 #define FW_ACL_VLAN_CMD_FM_V(x) ((x) << FW_ACL_VLAN_CMD_FM_S) +/* old 16-bit port capabilities bitmap (fw_port_cap16_t) */ enum fw_port_cap { FW_PORT_CAP_SPEED_100M = 0x0001, FW_PORT_CAP_SPEED_1G = 0x0002, @@ -2289,6 +2293,84 @@ enum fw_port_mdi { #define FW_PORT_CAP_MDI_S 9 #define FW_PORT_CAP_MDI_V(x) ((x) << FW_PORT_CAP_MDI_S) +/* new 32-bit port capabilities bitmap (fw_port_cap32_t) */ +#define FW_PORT_CAP32_SPEED_100M 0x00000001UL +#define FW_PORT_CAP32_SPEED_1G 0x00000002UL +#define FW_PORT_CAP32_SPEED_10G 0x00000004UL +#define FW_PORT_CAP32_SPEED_25G 0x00000008UL +#define FW_PORT_CAP32_SPEED_40G 0x00000010UL +#define FW_PORT_CAP32_SPEED_50G 0x00000020UL +#define FW_PORT_CAP32_SPEED_100G 0x00000040UL +#define FW_PORT_CAP32_SPEED_200G 0x00000080UL +#define FW_PORT_CAP32_SPEED_400G 0x00000100UL +#define FW_PORT_CAP32_SPEED_RESERVED1 0x00000200UL +#define FW_PORT_CAP32_SPEED_RESERVED2 0x00000400UL +#define FW_PORT_CAP32_SPEED_RESERVED3 0x00000800UL +#define FW_PORT_CAP32_RESERVED1 0x0000f000UL +#define FW_PORT_CAP32_FC_RX 0x00010000UL +#define FW_PORT_CAP32_FC_TX 0x00020000UL +#define FW_PORT_CAP32_802_3_PAUSE 0x00040000UL +#define FW_PORT_CAP32_802_3_ASM_DIR 0x00080000UL +#define FW_PORT_CAP32_ANEG 0x00100000UL +#define FW_PORT_CAP32_MDIX 0x00200000UL +#define FW_PORT_CAP32_MDIAUTO 0x00400000UL +#define FW_PORT_CAP32_FEC_RS 0x00800000UL +#define FW_PORT_CAP32_FEC_BASER_RS 0x01000000UL +#define FW_PORT_CAP32_FEC_RESERVED1 0x02000000UL +#define FW_PORT_CAP32_FEC_RESERVED2 0x04000000UL +#define FW_PORT_CAP32_FEC_RESERVED3 0x08000000UL +#define FW_PORT_CAP32_RESERVED2 0xf0000000UL + +#define FW_PORT_CAP32_SPEED_S 0 +#define FW_PORT_CAP32_SPEED_M 0xfff +#define FW_PORT_CAP32_SPEED_V(x) ((x) << FW_PORT_CAP32_SPEED_S) +#define FW_PORT_CAP32_SPEED_G(x) \ + (((x) >> FW_PORT_CAP32_SPEED_S) & FW_PORT_CAP32_SPEED_M) + +#define FW_PORT_CAP32_FC_S 16 +#define FW_PORT_CAP32_FC_M 0x3 +#define FW_PORT_CAP32_FC_V(x) ((x) << FW_PORT_CAP32_FC_S) +#define FW_PORT_CAP32_FC_G(x) \ + (((x) >> FW_PORT_CAP32_FC_S) & FW_PORT_CAP32_FC_M) + +#define FW_PORT_CAP32_802_3_S 18 +#define FW_PORT_CAP32_802_3_M 0x3 +#define FW_PORT_CAP32_802_3_V(x) ((x) << FW_PORT_CAP32_802_3_S) +#define FW_PORT_CAP32_802_3_G(x) \ + (((x) >> FW_PORT_CAP32_802_3_S) & FW_PORT_CAP32_802_3_M) + +#define FW_PORT_CAP32_ANEG_S 20 +#define FW_PORT_CAP32_ANEG_M 0x1 +#define FW_PORT_CAP32_ANEG_V(x) ((x) << FW_PORT_CAP32_ANEG_S) +#define FW_PORT_CAP32_ANEG_G(x) \ + (((x) >> FW_PORT_CAP32_ANEG_S) & FW_PORT_CAP32_ANEG_M) + +enum fw_port_mdi32 { + FW_PORT_CAP32_MDI_UNCHANGED, + FW_PORT_CAP32_MDI_AUTO, + FW_PORT_CAP32_MDI_F_STRAIGHT, + FW_PORT_CAP32_MDI_F_CROSSOVER +}; + +#define FW_PORT_CAP32_MDI_S 21 +#define FW_PORT_CAP32_MDI_M 3 +#define FW_PORT_CAP32_MDI_V(x) ((x) << FW_PORT_CAP32_MDI_S) +#define FW_PORT_CAP32_MDI_G(x) \ + (((x) >> FW_PORT_CAP32_MDI_S) & FW_PORT_CAP32_MDI_M) + +#define FW_PORT_CAP32_FEC_S 23 +#define FW_PORT_CAP32_FEC_M 0x1f +#define FW_PORT_CAP32_FEC_V(x) ((x) << FW_PORT_CAP32_FEC_S) +#define FW_PORT_CAP32_FEC_G(x) \ + (((x) >> FW_PORT_CAP32_FEC_S) & FW_PORT_CAP32_FEC_M) + +/* macros to isolate various 32-bit Port Capabilities sub-fields */ +#define CAP32_SPEED(__cap32) \ + (FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_M) & __cap32) + +#define CAP32_FEC(__cap32) \ + (FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M) & __cap32) + enum fw_port_action { FW_PORT_ACTION_L1_CFG = 0x0001, FW_PORT_ACTION_L2_CFG = 0x0002, @@ -2298,6 +2380,8 @@ enum fw_port_action { FW_PORT_ACTION_DCB_READ_TRANS = 0x0006, FW_PORT_ACTION_DCB_READ_RECV = 0x0007, FW_PORT_ACTION_DCB_READ_DET = 0x0008, + FW_PORT_ACTION_L1_CFG32 = 0x0009, + FW_PORT_ACTION_GET_PORT_INFO32 = 0x000a, FW_PORT_ACTION_LOW_PWR_TO_NORMAL = 0x0010, FW_PORT_ACTION_L1_LOW_PWR_EN = 0x0011, FW_PORT_ACTION_L2_WOL_MODE_EN = 0x0012, @@ -2445,6 +2529,18 @@ struct fw_port_cmd { __be64 r12; } control; } dcb; + struct fw_port_l1cfg32 { + __be32 rcap32; + __be32 r; + } l1cfg32; + struct fw_port_info32 { + __be32 lstatus32_to_cbllen32; + __be32 auxlinfo32_mtu32; + __be32 linkattr32; + __be32 pcaps32; + __be32 acaps32; + __be32 lpacaps32; + } info32; } u; }; @@ -2553,6 +2649,85 @@ struct fw_port_cmd { #define FW_PORT_CMD_DCB_VERSION_G(x) \ (((x) >> FW_PORT_CMD_DCB_VERSION_S) & FW_PORT_CMD_DCB_VERSION_M) +#define FW_PORT_CMD_LSTATUS32_S 31 +#define FW_PORT_CMD_LSTATUS32_M 0x1 +#define FW_PORT_CMD_LSTATUS32_V(x) ((x) << FW_PORT_CMD_LSTATUS32_S) +#define FW_PORT_CMD_LSTATUS32_G(x) \ + (((x) >> FW_PORT_CMD_LSTATUS32_S) & FW_PORT_CMD_LSTATUS32_M) +#define FW_PORT_CMD_LSTATUS32_F FW_PORT_CMD_LSTATUS32_V(1U) + +#define FW_PORT_CMD_LINKDNRC32_S 28 +#define FW_PORT_CMD_LINKDNRC32_M 0x7 +#define FW_PORT_CMD_LINKDNRC32_V(x) ((x) << FW_PORT_CMD_LINKDNRC32_S) +#define FW_PORT_CMD_LINKDNRC32_G(x) \ + (((x) >> FW_PORT_CMD_LINKDNRC32_S) & FW_PORT_CMD_LINKDNRC32_M) + +#define FW_PORT_CMD_DCBXDIS32_S 27 +#define FW_PORT_CMD_DCBXDIS32_M 0x1 +#define FW_PORT_CMD_DCBXDIS32_V(x) ((x) << FW_PORT_CMD_DCBXDIS32_S) +#define FW_PORT_CMD_DCBXDIS32_G(x) \ + (((x) >> FW_PORT_CMD_DCBXDIS32_S) & FW_PORT_CMD_DCBXDIS32_M) +#define FW_PORT_CMD_DCBXDIS32_F FW_PORT_CMD_DCBXDIS32_V(1U) + +#define FW_PORT_CMD_MDIOCAP32_S 26 +#define FW_PORT_CMD_MDIOCAP32_M 0x1 +#define FW_PORT_CMD_MDIOCAP32_V(x) ((x) << FW_PORT_CMD_MDIOCAP32_S) +#define FW_PORT_CMD_MDIOCAP32_G(x) \ + (((x) >> FW_PORT_CMD_MDIOCAP32_S) & FW_PORT_CMD_MDIOCAP32_M) +#define FW_PORT_CMD_MDIOCAP32_F FW_PORT_CMD_MDIOCAP32_V(1U) + +#define FW_PORT_CMD_MDIOADDR32_S 21 +#define FW_PORT_CMD_MDIOADDR32_M 0x1f +#define FW_PORT_CMD_MDIOADDR32_V(x) ((x) << FW_PORT_CMD_MDIOADDR32_S) +#define FW_PORT_CMD_MDIOADDR32_G(x) \ + (((x) >> FW_PORT_CMD_MDIOADDR32_S) & FW_PORT_CMD_MDIOADDR32_M) + +#define FW_PORT_CMD_PORTTYPE32_S 13 +#define FW_PORT_CMD_PORTTYPE32_M 0xff +#define FW_PORT_CMD_PORTTYPE32_V(x) ((x) << FW_PORT_CMD_PORTTYPE32_S) +#define FW_PORT_CMD_PORTTYPE32_G(x) \ + (((x) >> FW_PORT_CMD_PORTTYPE32_S) & FW_PORT_CMD_PORTTYPE32_M) + +#define FW_PORT_CMD_MODTYPE32_S 8 +#define FW_PORT_CMD_MODTYPE32_M 0x1f +#define FW_PORT_CMD_MODTYPE32_V(x) ((x) << FW_PORT_CMD_MODTYPE32_S) +#define FW_PORT_CMD_MODTYPE32_G(x) \ + (((x) >> FW_PORT_CMD_MODTYPE32_S) & FW_PORT_CMD_MODTYPE32_M) + +#define FW_PORT_CMD_CBLLEN32_S 0 +#define FW_PORT_CMD_CBLLEN32_M 0xff +#define FW_PORT_CMD_CBLLEN32_V(x) ((x) << FW_PORT_CMD_CBLLEN32_S) +#define FW_PORT_CMD_CBLLEN32_G(x) \ + (((x) >> FW_PORT_CMD_CBLLEN32_S) & FW_PORT_CMD_CBLLEN32_M) + +#define FW_PORT_CMD_AUXLINFO32_S 24 +#define FW_PORT_CMD_AUXLINFO32_M 0xff +#define FW_PORT_CMD_AUXLINFO32_V(x) ((x) << FW_PORT_CMD_AUXLINFO32_S) +#define FW_PORT_CMD_AUXLINFO32_G(x) \ + (((x) >> FW_PORT_CMD_AUXLINFO32_S) & FW_PORT_CMD_AUXLINFO32_M) + +#define FW_PORT_AUXLINFO32_KX4_S 2 +#define FW_PORT_AUXLINFO32_KX4_M 0x1 +#define FW_PORT_AUXLINFO32_KX4_V(x) \ + ((x) << FW_PORT_AUXLINFO32_KX4_S) +#define FW_PORT_AUXLINFO32_KX4_G(x) \ + (((x) >> FW_PORT_AUXLINFO32_KX4_S) & FW_PORT_AUXLINFO32_KX4_M) +#define FW_PORT_AUXLINFO32_KX4_F FW_PORT_AUXLINFO32_KX4_V(1U) + +#define FW_PORT_AUXLINFO32_KR_S 1 +#define FW_PORT_AUXLINFO32_KR_M 0x1 +#define FW_PORT_AUXLINFO32_KR_V(x) \ + ((x) << FW_PORT_AUXLINFO32_KR_S) +#define FW_PORT_AUXLINFO32_KR_G(x) \ + (((x) >> FW_PORT_AUXLINFO32_KR_S) & FW_PORT_AUXLINFO32_KR_M) +#define FW_PORT_AUXLINFO32_KR_F FW_PORT_AUXLINFO32_KR_V(1U) + +#define FW_PORT_CMD_MTU32_S 0 +#define FW_PORT_CMD_MTU32_M 0xffff +#define FW_PORT_CMD_MTU32_V(x) ((x) << FW_PORT_CMD_MTU32_S) +#define FW_PORT_CMD_MTU32_G(x) \ + (((x) >> FW_PORT_CMD_MTU32_S) & FW_PORT_CMD_MTU32_M) + enum fw_port_type { FW_PORT_TYPE_FIBER_XFI, FW_PORT_TYPE_FIBER_XAUI, diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 2b85b874fd0d..8996ebbd222e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -182,7 +182,7 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok) break; } - switch (pi->link_cfg.fc) { + switch ((int)pi->link_cfg.fc) { case PAUSE_RX: fc = "RX"; break; @@ -191,7 +191,7 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok) fc = "TX"; break; - case PAUSE_RX|PAUSE_TX: + case PAUSE_RX | PAUSE_TX: fc = "RX/TX"; break; @@ -1213,7 +1213,11 @@ static int from_fw_port_mod_type(enum fw_port_type port_type, } else if (port_type == FW_PORT_TYPE_SFP || port_type == FW_PORT_TYPE_QSFP_10G || port_type == FW_PORT_TYPE_QSA || - port_type == FW_PORT_TYPE_QSFP) { + port_type == FW_PORT_TYPE_QSFP || + port_type == FW_PORT_TYPE_CR4_QSFP || + port_type == FW_PORT_TYPE_CR_QSFP || + port_type == FW_PORT_TYPE_CR2_QSFP || + port_type == FW_PORT_TYPE_SFP28) { if (mod_type == FW_PORT_MOD_TYPE_LR || mod_type == FW_PORT_MOD_TYPE_SR || mod_type == FW_PORT_MOD_TYPE_ER || @@ -1224,6 +1228,9 @@ static int from_fw_port_mod_type(enum fw_port_type port_type, return PORT_DA; else return PORT_OTHER; + } else if (port_type == FW_PORT_TYPE_KR4_100G || + port_type == FW_PORT_TYPE_KR_SFP28) { + return PORT_NONE; } return PORT_OTHER; @@ -1242,12 +1249,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, unsigned int fw_caps, unsigned long *link_mode_mask) { - #define SET_LMM(__lmm_name) __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name\ - ## _BIT, link_mode_mask) + #define SET_LMM(__lmm_name) \ + __set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \ + link_mode_mask) #define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \ do { \ - if (fw_caps & FW_PORT_CAP_ ## __fw_name) \ + if (fw_caps & FW_PORT_CAP32_ ## __fw_name) \ SET_LMM(__lmm_name); \ } while (0) @@ -1310,6 +1318,16 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, SET_LMM(25000baseCR_Full); break; + case FW_PORT_TYPE_KR_SFP28: + SET_LMM(Backplane); + SET_LMM(25000baseKR_Full); + break; + + case FW_PORT_TYPE_CR2_QSFP: + SET_LMM(FIBRE); + SET_LMM(50000baseSR2_Full); + break; + case FW_PORT_TYPE_KR4_100G: case FW_PORT_TYPE_CR4_QSFP: SET_LMM(FIBRE); @@ -1329,12 +1347,18 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, } static int cxgb4vf_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings - *link_ksettings) + struct ethtool_link_ksettings *link_ksettings) { - const struct port_info *pi = netdev_priv(dev); + struct port_info *pi = netdev_priv(dev); struct ethtool_link_settings *base = &link_ksettings->base; + /* For the nonce, the Firmware doesn't send up Port State changes + * when the Virtual Interface attached to the Port is down. So + * if it's down, let's grab any changes. + */ + if (!netif_running(dev)) + (void)t4vf_update_port_info(pi); + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); ethtool_link_ksettings_zero_link_mode(link_ksettings, lp_advertising); @@ -1351,11 +1375,11 @@ static int cxgb4vf_get_link_ksettings(struct net_device *dev, base->mdio_support = 0; } - fw_caps_to_lmm(pi->port_type, pi->link_cfg.supported, + fw_caps_to_lmm(pi->port_type, pi->link_cfg.pcaps, link_ksettings->link_modes.supported); - fw_caps_to_lmm(pi->port_type, pi->link_cfg.advertising, + fw_caps_to_lmm(pi->port_type, pi->link_cfg.acaps, link_ksettings->link_modes.advertising); - fw_caps_to_lmm(pi->port_type, pi->link_cfg.lp_advertising, + fw_caps_to_lmm(pi->port_type, pi->link_cfg.lpacaps, link_ksettings->link_modes.lp_advertising); if (netif_carrier_ok(dev)) { @@ -1367,7 +1391,7 @@ static int cxgb4vf_get_link_ksettings(struct net_device *dev, } base->autoneg = pi->link_cfg.autoneg; - if (pi->link_cfg.supported & FW_PORT_CAP_ANEG) + if (pi->link_cfg.pcaps & FW_PORT_CAP32_ANEG) ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Autoneg); if (pi->link_cfg.autoneg) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h index b3903fe411aa..9cf9c56b0f73 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_common.h @@ -104,24 +104,62 @@ struct t4vf_port_stats { /* * Per-"port" (Virtual Interface) link configuration ... */ -struct link_config { - unsigned int supported; /* link capabilities */ - unsigned int advertising; /* advertised capabilities */ - unsigned short lp_advertising; /* peer advertised capabilities */ - unsigned int requested_speed; /* speed user has requested */ - unsigned int speed; /* actual link speed */ - unsigned char requested_fc; /* flow control user has requested */ - unsigned char fc; /* actual link flow control */ - unsigned char autoneg; /* autonegotiating? */ - unsigned char link_ok; /* link up? */ +typedef u16 fw_port_cap16_t; /* 16-bit Port Capabilities integral value */ +typedef u32 fw_port_cap32_t; /* 32-bit Port Capabilities integral value */ + +enum fw_caps { + FW_CAPS_UNKNOWN = 0, /* 0'ed out initial state */ + FW_CAPS16 = 1, /* old Firmware: 16-bit Port Capabilities */ + FW_CAPS32 = 2, /* new Firmware: 32-bit Port Capabilities */ }; -enum { - PAUSE_RX = 1 << 0, - PAUSE_TX = 1 << 1, - PAUSE_AUTONEG = 1 << 2 +enum cc_pause { + PAUSE_RX = 1 << 0, + PAUSE_TX = 1 << 1, + PAUSE_AUTONEG = 1 << 2 +}; + +enum cc_fec { + FEC_AUTO = 1 << 0, /* IEEE 802.3 "automatic" */ + FEC_RS = 1 << 1, /* Reed-Solomon */ + FEC_BASER_RS = 1 << 2, /* BaseR/Reed-Solomon */ +}; + +struct link_config { + fw_port_cap32_t pcaps; /* link capabilities */ + fw_port_cap32_t acaps; /* advertised capabilities */ + fw_port_cap32_t lpacaps; /* peer advertised capabilities */ + + fw_port_cap32_t speed_caps; /* speed(s) user has requested */ + u32 speed; /* actual link speed */ + + enum cc_pause requested_fc; /* flow control user has requested */ + enum cc_pause fc; /* actual link flow control */ + + enum cc_fec auto_fec; /* Forward Error Correction: */ + enum cc_fec requested_fec; /* "automatic" (IEEE 802.3), */ + enum cc_fec fec; /* requested, and actual in use */ + + unsigned char autoneg; /* autonegotiating? */ + + unsigned char link_ok; /* link up? */ + unsigned char link_down_rc; /* link down reason */ }; +/* Return true if the Link Configuration supports "High Speeds" (those greater + * than 1Gb/s). + */ +static inline bool is_x_10g_port(const struct link_config *lc) +{ + fw_port_cap32_t speeds, high_speeds; + + speeds = FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_G(lc->pcaps)); + high_speeds = + speeds & ~(FW_PORT_CAP32_SPEED_100M | FW_PORT_CAP32_SPEED_1G); + + return high_speeds != 0; +} + /* * General device parameters ... */ @@ -227,6 +265,7 @@ struct adapter_params { struct arch_specific_params arch; /* chip specific params */ enum chip_type chip; /* chip code */ u8 nports; /* # of Ethernet "ports" */ + u8 fw_caps_support; /* 32-bit Port Capabilities */ }; /* Firmware Mailbox Command/Reply log. All values are in Host-Endian format. @@ -266,24 +305,6 @@ static inline struct mbox_cmd *mbox_cmd_log_entry(struct mbox_cmd_log *log, #define for_each_port(adapter, iter) \ for (iter = 0; iter < (adapter)->params.nports; iter++) -static inline bool is_10g_port(const struct link_config *lc) -{ - return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0; -} - -/* Return true if the Link Configuration supports "High Speeds" (those greater - * than 1Gb/s). - */ -static inline bool is_x_10g_port(const struct link_config *lc) -{ - unsigned int speeds, high_speeds; - - speeds = FW_PORT_CAP_SPEED_V(FW_PORT_CAP_SPEED_G(lc->supported)); - high_speeds = speeds & ~(FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G); - - return high_speeds != 0; -} - static inline unsigned int core_ticks_per_usec(const struct adapter *adapter) { return adapter->params.vpd.cclk / 1000; @@ -387,6 +408,7 @@ int t4vf_iq_free(struct adapter *, unsigned int, unsigned int, unsigned int, unsigned int); int t4vf_eth_eq_free(struct adapter *, unsigned int); +int t4vf_update_port_info(struct port_info *pi); int t4vf_handle_fw_rpl(struct adapter *, const __be64 *); int t4vf_prep_adapter(struct adapter *); int t4vf_get_vf_mac_acl(struct adapter *adapter, unsigned int pf, diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c index e98248f00fef..a8d94963b4d0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c @@ -313,32 +313,130 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size, return ret; } -#define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\ - FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_25G | \ - FW_PORT_CAP_SPEED_40G | FW_PORT_CAP_SPEED_100G | \ - FW_PORT_CAP_ANEG) +#define ADVERT_MASK (FW_PORT_CAP32_SPEED_V(FW_PORT_CAP32_SPEED_M) | \ + FW_PORT_CAP32_ANEG) /** + * fwcaps16_to_caps32 - convert 16-bit Port Capabilities to 32-bits + * @caps16: a 16-bit Port Capabilities value + * + * Returns the equivalent 32-bit Port Capabilities value. + */ +static fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16) +{ + fw_port_cap32_t caps32 = 0; + + #define CAP16_TO_CAP32(__cap) \ + do { \ + if (caps16 & FW_PORT_CAP_##__cap) \ + caps32 |= FW_PORT_CAP32_##__cap; \ + } while (0) + + CAP16_TO_CAP32(SPEED_100M); + CAP16_TO_CAP32(SPEED_1G); + CAP16_TO_CAP32(SPEED_25G); + CAP16_TO_CAP32(SPEED_10G); + CAP16_TO_CAP32(SPEED_40G); + CAP16_TO_CAP32(SPEED_100G); + CAP16_TO_CAP32(FC_RX); + CAP16_TO_CAP32(FC_TX); + CAP16_TO_CAP32(ANEG); + CAP16_TO_CAP32(MDIX); + CAP16_TO_CAP32(MDIAUTO); + CAP16_TO_CAP32(FEC_RS); + CAP16_TO_CAP32(FEC_BASER_RS); + CAP16_TO_CAP32(802_3_PAUSE); + CAP16_TO_CAP32(802_3_ASM_DIR); + + #undef CAP16_TO_CAP32 + + return caps32; +} + +/* Translate Firmware Pause specification to Common Code */ +static inline enum cc_pause fwcap_to_cc_pause(fw_port_cap32_t fw_pause) +{ + enum cc_pause cc_pause = 0; + + if (fw_pause & FW_PORT_CAP32_FC_RX) + cc_pause |= PAUSE_RX; + if (fw_pause & FW_PORT_CAP32_FC_TX) + cc_pause |= PAUSE_TX; + + return cc_pause; +} + +/* Translate Firmware Forward Error Correction specification to Common Code */ +static inline enum cc_fec fwcap_to_cc_fec(fw_port_cap32_t fw_fec) +{ + enum cc_fec cc_fec = 0; + + if (fw_fec & FW_PORT_CAP32_FEC_RS) + cc_fec |= FEC_RS; + if (fw_fec & FW_PORT_CAP32_FEC_BASER_RS) + cc_fec |= FEC_BASER_RS; + + return cc_fec; +} + +/** + * Return the highest speed set in the port capabilities, in Mb/s. + */ +static unsigned int fwcap_to_speed(fw_port_cap32_t caps) +{ + #define TEST_SPEED_RETURN(__caps_speed, __speed) \ + do { \ + if (caps & FW_PORT_CAP32_SPEED_##__caps_speed) \ + return __speed; \ + } while (0) + + TEST_SPEED_RETURN(400G, 400000); + TEST_SPEED_RETURN(200G, 200000); + TEST_SPEED_RETURN(100G, 100000); + TEST_SPEED_RETURN(50G, 50000); + TEST_SPEED_RETURN(40G, 40000); + TEST_SPEED_RETURN(25G, 25000); + TEST_SPEED_RETURN(10G, 10000); + TEST_SPEED_RETURN(1G, 1000); + TEST_SPEED_RETURN(100M, 100); + + #undef TEST_SPEED_RETURN + + return 0; +} + +/* * init_link_config - initialize a link's SW state * @lc: structure holding the link state - * @caps: link capabilities + * @pcaps: link Port Capabilities + * @acaps: link current Advertised Port Capabilities * * Initializes the SW state maintained for each link, including the link's * capabilities and default speed/flow-control/autonegotiation settings. */ -static void init_link_config(struct link_config *lc, unsigned int caps) +static void init_link_config(struct link_config *lc, + fw_port_cap32_t pcaps, + fw_port_cap32_t acaps) { - lc->supported = caps; - lc->lp_advertising = 0; - lc->requested_speed = 0; + lc->pcaps = pcaps; + lc->lpacaps = 0; + lc->speed_caps = 0; lc->speed = 0; lc->requested_fc = lc->fc = PAUSE_RX | PAUSE_TX; - if (lc->supported & FW_PORT_CAP_ANEG) { - lc->advertising = lc->supported & ADVERT_MASK; + + /* For Forward Error Control, we default to whatever the Firmware + * tells us the Link is currently advertising. + */ + lc->auto_fec = fwcap_to_cc_fec(acaps); + lc->requested_fec = FEC_AUTO; + lc->fec = lc->auto_fec; + + if (lc->pcaps & FW_PORT_CAP32_ANEG) { + lc->acaps = acaps & ADVERT_MASK; lc->autoneg = AUTONEG_ENABLE; lc->requested_fc |= PAUSE_AUTONEG; } else { - lc->advertising = 0; + lc->acaps = 0; lc->autoneg = AUTONEG_DISABLE; } } @@ -351,9 +449,30 @@ static void init_link_config(struct link_config *lc, unsigned int caps) int t4vf_port_init(struct adapter *adapter, int pidx) { struct port_info *pi = adap2pinfo(adapter, pidx); + unsigned int fw_caps = adapter->params.fw_caps_support; struct fw_vi_cmd vi_cmd, vi_rpl; struct fw_port_cmd port_cmd, port_rpl; - int v; + enum fw_port_type port_type; + int mdio_addr; + fw_port_cap32_t pcaps, acaps; + int ret; + + /* If we haven't yet determined whether we're talking to Firmware + * which knows the new 32-bit Port Capabilities, it's time to find + * out now. This will also tell new Firmware to send us Port Status + * Updates using the new 32-bit Port Capabilities version of the + * Port Information message. + */ + if (fw_caps == FW_CAPS_UNKNOWN) { + u32 param, val; + + param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_PORT_CAPS32)); + val = 1; + ret = t4vf_set_params(adapter, 1, ¶m, &val); + fw_caps = (ret == 0 ? FW_CAPS32 : FW_CAPS16); + adapter->params.fw_caps_support = fw_caps; + } /* * Execute a VI Read command to get our Virtual Interface information @@ -365,9 +484,9 @@ int t4vf_port_init(struct adapter *adapter, int pidx) FW_CMD_READ_F); vi_cmd.alloc_to_len16 = cpu_to_be32(FW_LEN16(vi_cmd)); vi_cmd.type_viid = cpu_to_be16(FW_VI_CMD_VIID_V(pi->viid)); - v = t4vf_wr_mbox(adapter, &vi_cmd, sizeof(vi_cmd), &vi_rpl); - if (v) - return v; + ret = t4vf_wr_mbox(adapter, &vi_cmd, sizeof(vi_cmd), &vi_rpl); + if (ret != FW_SUCCESS) + return ret; BUG_ON(pi->port_id != FW_VI_CMD_PORTID_G(vi_rpl.portid_pkd)); pi->rss_size = FW_VI_CMD_RSSSIZE_G(be16_to_cpu(vi_rpl.rsssize_pkd)); @@ -385,21 +504,42 @@ int t4vf_port_init(struct adapter *adapter, int pidx) FW_CMD_REQUEST_F | FW_CMD_READ_F | FW_PORT_CMD_PORTID_V(pi->port_id)); - port_cmd.action_to_len16 = - cpu_to_be32(FW_PORT_CMD_ACTION_V(FW_PORT_ACTION_GET_PORT_INFO) | - FW_LEN16(port_cmd)); - v = t4vf_wr_mbox(adapter, &port_cmd, sizeof(port_cmd), &port_rpl); - if (v) - return v; + port_cmd.action_to_len16 = cpu_to_be32( + FW_PORT_CMD_ACTION_V(fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_GET_PORT_INFO + : FW_PORT_ACTION_GET_PORT_INFO32) | + FW_LEN16(port_cmd)); + ret = t4vf_wr_mbox(adapter, &port_cmd, sizeof(port_cmd), &port_rpl); + if (ret != FW_SUCCESS) + return ret; - v = be32_to_cpu(port_rpl.u.info.lstatus_to_modtype); - pi->mdio_addr = (v & FW_PORT_CMD_MDIOCAP_F) ? - FW_PORT_CMD_MDIOADDR_G(v) : -1; - pi->port_type = FW_PORT_CMD_PTYPE_G(v); - pi->mod_type = FW_PORT_MOD_TYPE_NA; + /* Extract the various fields from the Port Information message. */ + if (fw_caps == FW_CAPS16) { + u32 lstatus = be32_to_cpu(port_rpl.u.info.lstatus_to_modtype); - init_link_config(&pi->link_cfg, be16_to_cpu(port_rpl.u.info.pcap)); + port_type = FW_PORT_CMD_PTYPE_G(lstatus); + mdio_addr = ((lstatus & FW_PORT_CMD_MDIOCAP_F) + ? FW_PORT_CMD_MDIOADDR_G(lstatus) + : -1); + pcaps = fwcaps16_to_caps32(be16_to_cpu(port_rpl.u.info.pcap)); + acaps = fwcaps16_to_caps32(be16_to_cpu(port_rpl.u.info.acap)); + } else { + u32 lstatus32 = + be32_to_cpu(port_rpl.u.info32.lstatus32_to_cbllen32); + + port_type = FW_PORT_CMD_PORTTYPE32_G(lstatus32); + mdio_addr = ((lstatus32 & FW_PORT_CMD_MDIOCAP32_F) + ? FW_PORT_CMD_MDIOADDR32_G(lstatus32) + : -1); + pcaps = be32_to_cpu(port_rpl.u.info32.pcaps32); + acaps = be32_to_cpu(port_rpl.u.info32.acaps32); + } + pi->port_type = port_type; + pi->mdio_addr = mdio_addr; + pi->mod_type = FW_PORT_MOD_TYPE_NA; + + init_link_config(&pi->link_cfg, pcaps, acaps); return 0; } @@ -1667,6 +1807,202 @@ int t4vf_eth_eq_free(struct adapter *adapter, unsigned int eqid) } /** + * t4vf_link_down_rc_str - return a string for a Link Down Reason Code + * @link_down_rc: Link Down Reason Code + * + * Returns a string representation of the Link Down Reason Code. + */ +const char *t4vf_link_down_rc_str(unsigned char link_down_rc) +{ + static const char * const reason[] = { + "Link Down", + "Remote Fault", + "Auto-negotiation Failure", + "Reserved", + "Insufficient Airflow", + "Unable To Determine Reason", + "No RX Signal Detected", + "Reserved", + }; + + if (link_down_rc >= ARRAY_SIZE(reason)) + return "Bad Reason Code"; + + return reason[link_down_rc]; +} + +/** + * t4vf_handle_get_port_info - process a FW reply message + * @pi: the port info + * @rpl: start of the FW message + * + * Processes a GET_PORT_INFO FW reply message. + */ +void t4vf_handle_get_port_info(struct port_info *pi, + const struct fw_port_cmd *cmd) +{ + int action = FW_PORT_CMD_ACTION_G(be32_to_cpu(cmd->action_to_len16)); + struct adapter *adapter = pi->adapter; + struct link_config *lc = &pi->link_cfg; + int link_ok, linkdnrc; + enum fw_port_type port_type; + enum fw_port_module_type mod_type; + unsigned int speed, fc, fec; + fw_port_cap32_t pcaps, acaps, lpacaps, linkattr; + + /* Extract the various fields from the Port Information message. */ + switch (action) { + case FW_PORT_ACTION_GET_PORT_INFO: { + u32 lstatus = be32_to_cpu(cmd->u.info.lstatus_to_modtype); + + link_ok = (lstatus & FW_PORT_CMD_LSTATUS_F) != 0; + linkdnrc = FW_PORT_CMD_LINKDNRC_G(lstatus); + port_type = FW_PORT_CMD_PTYPE_G(lstatus); + mod_type = FW_PORT_CMD_MODTYPE_G(lstatus); + pcaps = fwcaps16_to_caps32(be16_to_cpu(cmd->u.info.pcap)); + acaps = fwcaps16_to_caps32(be16_to_cpu(cmd->u.info.acap)); + lpacaps = fwcaps16_to_caps32(be16_to_cpu(cmd->u.info.lpacap)); + + /* Unfortunately the format of the Link Status in the old + * 16-bit Port Information message isn't the same as the + * 16-bit Port Capabilities bitfield used everywhere else ... + */ + linkattr = 0; + if (lstatus & FW_PORT_CMD_RXPAUSE_F) + linkattr |= FW_PORT_CAP32_FC_RX; + if (lstatus & FW_PORT_CMD_TXPAUSE_F) + linkattr |= FW_PORT_CAP32_FC_TX; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100M)) + linkattr |= FW_PORT_CAP32_SPEED_100M; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_1G)) + linkattr |= FW_PORT_CAP32_SPEED_1G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G)) + linkattr |= FW_PORT_CAP32_SPEED_10G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G)) + linkattr |= FW_PORT_CAP32_SPEED_25G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G)) + linkattr |= FW_PORT_CAP32_SPEED_40G; + if (lstatus & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G)) + linkattr |= FW_PORT_CAP32_SPEED_100G; + + break; + } + + case FW_PORT_ACTION_GET_PORT_INFO32: { + u32 lstatus32; + + lstatus32 = be32_to_cpu(cmd->u.info32.lstatus32_to_cbllen32); + link_ok = (lstatus32 & FW_PORT_CMD_LSTATUS32_F) != 0; + linkdnrc = FW_PORT_CMD_LINKDNRC32_G(lstatus32); + port_type = FW_PORT_CMD_PORTTYPE32_G(lstatus32); + mod_type = FW_PORT_CMD_MODTYPE32_G(lstatus32); + pcaps = be32_to_cpu(cmd->u.info32.pcaps32); + acaps = be32_to_cpu(cmd->u.info32.acaps32); + lpacaps = be32_to_cpu(cmd->u.info32.lpacaps32); + linkattr = be32_to_cpu(cmd->u.info32.linkattr32); + break; + } + + default: + dev_err(adapter->pdev_dev, "Handle Port Information: Bad Command/Action %#x\n", + be32_to_cpu(cmd->action_to_len16)); + return; + } + + fec = fwcap_to_cc_fec(acaps); + fc = fwcap_to_cc_pause(linkattr); + speed = fwcap_to_speed(linkattr); + + if (mod_type != pi->mod_type) { + /* When a new Transceiver Module is inserted, the Firmware + * will examine any Forward Error Correction parameters + * present in the Transceiver Module i2c EPROM and determine + * the supported and recommended FEC settings from those + * based on IEEE 802.3 standards. We always record the + * IEEE 802.3 recommended "automatic" settings. + */ + lc->auto_fec = fec; + + /* Some versions of the early T6 Firmware "cheated" when + * handling different Transceiver Modules by changing the + * underlaying Port Type reported to the Host Drivers. As + * such we need to capture whatever Port Type the Firmware + * sends us and record it in case it's different from what we + * were told earlier. Unfortunately, since Firmware is + * forever, we'll need to keep this code here forever, but in + * later T6 Firmware it should just be an assignment of the + * same value already recorded. + */ + pi->port_type = port_type; + + pi->mod_type = mod_type; + t4vf_os_portmod_changed(adapter, pi->pidx); + } + + if (link_ok != lc->link_ok || speed != lc->speed || + fc != lc->fc || fec != lc->fec) { /* something changed */ + if (!link_ok && lc->link_ok) { + lc->link_down_rc = linkdnrc; + dev_warn(adapter->pdev_dev, "Port %d link down, reason: %s\n", + pi->port_id, t4vf_link_down_rc_str(linkdnrc)); + } + lc->link_ok = link_ok; + lc->speed = speed; + lc->fc = fc; + lc->fec = fec; + + lc->pcaps = pcaps; + lc->lpacaps = lpacaps; + lc->acaps = acaps & ADVERT_MASK; + + if (lc->acaps & FW_PORT_CAP32_ANEG) { + lc->autoneg = AUTONEG_ENABLE; + } else { + /* When Autoneg is disabled, user needs to set + * single speed. + * Similar to cxgb4_ethtool.c: set_link_ksettings + */ + lc->acaps = 0; + lc->speed_caps = fwcap_to_speed(acaps); + lc->autoneg = AUTONEG_DISABLE; + } + + t4vf_os_link_changed(adapter, pi->pidx, link_ok); + } +} + +/** + * t4vf_update_port_info - retrieve and update port information if changed + * @pi: the port_info + * + * We issue a Get Port Information Command to the Firmware and, if + * successful, we check to see if anything is different from what we + * last recorded and update things accordingly. + */ +int t4vf_update_port_info(struct port_info *pi) +{ + unsigned int fw_caps = pi->adapter->params.fw_caps_support; + struct fw_port_cmd port_cmd; + int ret; + + memset(&port_cmd, 0, sizeof(port_cmd)); + port_cmd.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) | + FW_CMD_REQUEST_F | FW_CMD_READ_F | + FW_PORT_CMD_PORTID_V(pi->port_id)); + port_cmd.action_to_len16 = cpu_to_be32( + FW_PORT_CMD_ACTION_V(fw_caps == FW_CAPS16 + ? FW_PORT_ACTION_GET_PORT_INFO + : FW_PORT_ACTION_GET_PORT_INFO32) | + FW_LEN16(port_cmd)); + ret = t4vf_wr_mbox(pi->adapter, &port_cmd, sizeof(port_cmd), + &port_cmd); + if (ret) + return ret; + t4vf_handle_get_port_info(pi, &port_cmd); + return 0; +} + +/** * t4vf_handle_fw_rpl - process a firmware reply message * @adapter: the adapter * @rpl: start of the firmware message @@ -1685,15 +2021,12 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl) */ const struct fw_port_cmd *port_cmd = (const struct fw_port_cmd *)rpl; - u32 stat, mod; - int action, port_id, link_ok, speed, fc, pidx; - - /* - * Extract various fields from port status change message. - */ - action = FW_PORT_CMD_ACTION_G( + int action = FW_PORT_CMD_ACTION_G( be32_to_cpu(port_cmd->action_to_len16)); - if (action != FW_PORT_ACTION_GET_PORT_INFO) { + int port_id, pidx; + + if (action != FW_PORT_ACTION_GET_PORT_INFO && + action != FW_PORT_ACTION_GET_PORT_INFO32) { dev_err(adapter->pdev_dev, "Unknown firmware PORT reply action %x\n", action); @@ -1702,61 +2035,12 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl) port_id = FW_PORT_CMD_PORTID_G( be32_to_cpu(port_cmd->op_to_portid)); - - stat = be32_to_cpu(port_cmd->u.info.lstatus_to_modtype); - link_ok = (stat & FW_PORT_CMD_LSTATUS_F) != 0; - speed = 0; - fc = 0; - if (stat & FW_PORT_CMD_RXPAUSE_F) - fc |= PAUSE_RX; - if (stat & FW_PORT_CMD_TXPAUSE_F) - fc |= PAUSE_TX; - if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100M)) - speed = 100; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_1G)) - speed = 1000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G)) - speed = 10000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G)) - speed = 25000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G)) - speed = 40000; - else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G)) - speed = 100000; - - /* - * Scan all of our "ports" (Virtual Interfaces) looking for - * those bound to the physical port which has changed. If - * our recorded state doesn't match the current state, - * signal that change to the OS code. - */ for_each_port(adapter, pidx) { struct port_info *pi = adap2pinfo(adapter, pidx); - struct link_config *lc; if (pi->port_id != port_id) continue; - - lc = &pi->link_cfg; - - mod = FW_PORT_CMD_MODTYPE_G(stat); - if (mod != pi->mod_type) { - pi->mod_type = mod; - t4vf_os_portmod_changed(adapter, pidx); - } - - if (link_ok != lc->link_ok || speed != lc->speed || - fc != lc->fc) { - /* something changed */ - lc->link_ok = link_ok; - lc->speed = speed; - lc->fc = fc; - lc->supported = - be16_to_cpu(port_cmd->u.info.pcap); - lc->lp_advertising = - be16_to_cpu(port_cmd->u.info.lpacap); - t4vf_os_link_changed(adapter, pidx, link_ok); - } + t4vf_handle_get_port_info(pi, port_cmd); } break; } diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 47be5018d35d..0affee9c8aa2 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -2094,7 +2094,7 @@ static int de4x5_eisa_remove(struct device *device) return 0; } -static struct eisa_device_id de4x5_eisa_ids[] = { +static const struct eisa_device_id de4x5_eisa_ids[] = { { "DEC4250", 0 }, /* 0 is the board name index... */ { "" } }; diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index 17e566a8b345..84394b43c0a1 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1303,7 +1303,6 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) 0x00, 'L', 'i', 'n', 'u', 'x' }; static int last_irq; - static int multiport_cnt; /* For four-port boards w/one EEPROM */ int i, irq; unsigned short sum; unsigned char *ee_data; @@ -1557,7 +1556,6 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } else if (ee_data[0] == 0xff && ee_data[1] == 0xff && ee_data[2] == 0) { sa_offset = 2; /* Grrr, damn Matrox boards. */ - multiport_cnt = 4; } #ifdef CONFIG_MIPS_COBALT if ((pdev->bus->number == 0) && diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index 4ee042c034a1..1b79a6defd56 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -73,7 +73,7 @@ #define ETHERCAT_MASTER_ID 0x14 -static struct pci_device_id ids[] = { +static const struct pci_device_id ids[] = { { PCI_DEVICE(0x15ec, 0x5000), }, { 0, } }; diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c index 2b62841c4c63..05989aafaf32 100644 --- a/drivers/net/ethernet/emulex/benet/be_roce.c +++ b/drivers/net/ethernet/emulex/benet/be_roce.c @@ -139,10 +139,7 @@ int be_roce_register_driver(struct ocrdma_driver *drv) } ocrdma_drv = drv; list_for_each_entry(dev, &be_adapter_list, entry) { - struct net_device *netdev; - _be_roce_dev_add(dev); - netdev = dev->netdev; } mutex_unlock(&be_adapter_list_lock); return 0; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 59da7ac3c108..9ed8e4b81530 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1623,6 +1623,8 @@ static const struct net_device_ops ftgmac100_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ftgmac100_poll_controller, #endif + .ndo_vlan_rx_add_vid = ncsi_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ncsi_vlan_rx_kill_vid, }; static int ftgmac100_setup_mdio(struct net_device *netdev) @@ -1837,6 +1839,9 @@ static int ftgmac100_probe(struct platform_device *pdev) NETIF_F_GRO | NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX; + if (priv->use_ncsi) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + /* AST2400 doesn't have working HW checksum generation */ if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac"))) netdev->hw_features &= ~NETIF_F_HW_CSUM; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 757b873735a5..42258060f142 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -158,7 +158,7 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms"); #define DPAA_RX_PRIV_DATA_SIZE (u16)(DPAA_TX_PRIV_DATA_SIZE + \ dpaa_rx_extra_headroom) -#define DPAA_ETH_RX_QUEUES 128 +#define DPAA_ETH_PCD_RXQ_NUM 128 #define DPAA_ENQUEUE_RETRIES 100000 @@ -169,6 +169,7 @@ struct fm_port_fqs { struct dpaa_fq *tx_errq; struct dpaa_fq *rx_defq; struct dpaa_fq *rx_errq; + struct dpaa_fq *rx_pcdq; }; /* All the dpa bps in use at any moment */ @@ -235,7 +236,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, net_dev->max_mtu = dpaa_get_max_mtu(); net_dev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_LLTX); + NETIF_F_LLTX | NETIF_F_RXHASH); net_dev->hw_features |= NETIF_F_SG | NETIF_F_HIGHDMA; /* The kernels enables GSO automatically, if we declare NETIF_F_SG. @@ -342,18 +343,19 @@ static void dpaa_get_stats64(struct net_device *net_dev, } } -static int dpaa_setup_tc(struct net_device *net_dev, u32 handle, - u32 chain_index, __be16 proto, struct tc_to_netdev *tc) +static int dpaa_setup_tc(struct net_device *net_dev, enum tc_setup_type type, + void *type_data) { struct dpaa_priv *priv = netdev_priv(net_dev); + struct tc_mqprio_qopt *mqprio = type_data; u8 num_tc; int i; - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - num_tc = tc->mqprio->num_tc; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + num_tc = mqprio->num_tc; if (num_tc == priv->num_tc) return 0; @@ -398,8 +400,8 @@ static struct mac_device *dpaa_mac_dev_get(struct platform_device *pdev) of_dev = of_find_device_by_node(mac_node); if (!of_dev) { - dev_err(dpaa_dev, "of_find_device_by_node(%s) failed\n", - mac_node->full_name); + dev_err(dpaa_dev, "of_find_device_by_node(%pOF) failed\n", + mac_node); of_node_put(mac_node); return ERR_PTR(-EINVAL); } @@ -627,6 +629,7 @@ static inline void dpaa_assign_wq(struct dpaa_fq *fq, int idx) fq->wq = 5; break; case FQ_TYPE_RX_DEFAULT: + case FQ_TYPE_RX_PCD: fq->wq = 6; break; case FQ_TYPE_TX: @@ -687,6 +690,7 @@ static int dpaa_alloc_all_fqs(struct device *dev, struct list_head *list, struct fm_port_fqs *port_fqs) { struct dpaa_fq *dpaa_fq; + u32 fq_base, fq_base_aligned, i; dpaa_fq = dpaa_fq_alloc(dev, 0, 1, list, FQ_TYPE_RX_ERROR); if (!dpaa_fq) @@ -700,6 +704,26 @@ static int dpaa_alloc_all_fqs(struct device *dev, struct list_head *list, port_fqs->rx_defq = &dpaa_fq[0]; + /* the PCD FQIDs range needs to be aligned for correct operation */ + if (qman_alloc_fqid_range(&fq_base, 2 * DPAA_ETH_PCD_RXQ_NUM)) + goto fq_alloc_failed; + + fq_base_aligned = ALIGN(fq_base, DPAA_ETH_PCD_RXQ_NUM); + + for (i = fq_base; i < fq_base_aligned; i++) + qman_release_fqid(i); + + for (i = fq_base_aligned + DPAA_ETH_PCD_RXQ_NUM; + i < (fq_base + 2 * DPAA_ETH_PCD_RXQ_NUM); i++) + qman_release_fqid(i); + + dpaa_fq = dpaa_fq_alloc(dev, fq_base_aligned, DPAA_ETH_PCD_RXQ_NUM, + list, FQ_TYPE_RX_PCD); + if (!dpaa_fq) + goto fq_alloc_failed; + + port_fqs->rx_pcdq = &dpaa_fq[0]; + if (!dpaa_fq_alloc(dev, 0, DPAA_ETH_TXQ_NUM, list, FQ_TYPE_TX_CONF_MQ)) goto fq_alloc_failed; @@ -869,13 +893,14 @@ static void dpaa_fq_setup(struct dpaa_priv *priv, const struct dpaa_fq_cbs *fq_cbs, struct fman_port *tx_port) { - int egress_cnt = 0, conf_cnt = 0, num_portals = 0, cpu; + int egress_cnt = 0, conf_cnt = 0, num_portals = 0, portal_cnt = 0, cpu; const cpumask_t *affine_cpus = qman_affine_cpus(); - u16 portals[NR_CPUS]; + u16 channels[NR_CPUS]; struct dpaa_fq *fq; for_each_cpu(cpu, affine_cpus) - portals[num_portals++] = qman_affine_channel(cpu); + channels[num_portals++] = qman_affine_channel(cpu); + if (num_portals == 0) dev_err(priv->net_dev->dev.parent, "No Qman software (affine) channels found"); @@ -889,6 +914,12 @@ static void dpaa_fq_setup(struct dpaa_priv *priv, case FQ_TYPE_RX_ERROR: dpaa_setup_ingress(priv, fq, &fq_cbs->rx_errq); break; + case FQ_TYPE_RX_PCD: + if (!num_portals) + continue; + dpaa_setup_ingress(priv, fq, &fq_cbs->rx_defq); + fq->channel = channels[portal_cnt++ % num_portals]; + break; case FQ_TYPE_TX: dpaa_setup_egress(priv, fq, tx_port, &fq_cbs->egress_ern); @@ -1038,7 +1069,8 @@ static int dpaa_fq_init(struct dpaa_fq *dpaa_fq, bool td_enable) /* Put all the ingress queues in our "ingress CGR". */ if (priv->use_ingress_cgr && (dpaa_fq->fq_type == FQ_TYPE_RX_DEFAULT || - dpaa_fq->fq_type == FQ_TYPE_RX_ERROR)) { + dpaa_fq->fq_type == FQ_TYPE_RX_ERROR || + dpaa_fq->fq_type == FQ_TYPE_RX_PCD)) { initfq.we_mask |= cpu_to_be16(QM_INITFQ_WE_CGID); initfq.fqd.fq_ctrl |= cpu_to_be16(QM_FQCTRL_CGE); initfq.fqd.cgid = (u8)priv->ingress_cgr.cgrid; @@ -1169,7 +1201,7 @@ static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq, static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, size_t count, struct dpaa_fq *errq, - struct dpaa_fq *defq, + struct dpaa_fq *defq, struct dpaa_fq *pcdq, struct dpaa_buffer_layout *buf_layout) { struct fman_buffer_prefix_content buf_prefix_content; @@ -1189,6 +1221,10 @@ static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps, rx_p = ¶ms.specific_params.rx_params; rx_p->err_fqid = errq->fqid; rx_p->dflt_fqid = defq->fqid; + if (pcdq) { + rx_p->pcd_base_fqid = pcdq->fqid; + rx_p->pcd_fqs_count = DPAA_ETH_PCD_RXQ_NUM; + } count = min(ARRAY_SIZE(rx_p->ext_buf_pools.ext_buf_pool), count); rx_p->ext_buf_pools.num_of_pools_used = (u8)count; @@ -1233,7 +1269,8 @@ static int dpaa_eth_init_ports(struct mac_device *mac_dev, return err; err = dpaa_eth_init_rx_port(rxport, bps, count, port_fqs->rx_errq, - port_fqs->rx_defq, &buf_layout[RX]); + port_fqs->rx_defq, port_fqs->rx_pcdq, + &buf_layout[RX]); return err; } @@ -2200,12 +2237,13 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, dma_addr_t addr = qm_fd_addr(fd); enum qm_fd_format fd_format; struct net_device *net_dev; - u32 fd_status; + u32 fd_status, hash_offset; struct dpaa_bp *dpaa_bp; struct dpaa_priv *priv; unsigned int skb_len; struct sk_buff *skb; int *count_ptr; + void *vaddr; fd_status = be32_to_cpu(fd->status); fd_format = qm_fd_get_format(fd); @@ -2251,7 +2289,8 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, dma_unmap_single(dpaa_bp->dev, addr, dpaa_bp->size, DMA_FROM_DEVICE); /* prefetch the first 64 bytes of the frame or the SGT start */ - prefetch(phys_to_virt(addr) + qm_fd_get_offset(fd)); + vaddr = phys_to_virt(addr); + prefetch(vaddr + qm_fd_get_offset(fd)); fd_format = qm_fd_get_format(fd); /* The only FD types that we may receive are contig and S/G */ @@ -2272,6 +2311,18 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, skb->protocol = eth_type_trans(skb, net_dev); + if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use && + !fman_port_get_hash_result_offset(priv->mac_dev->port[RX], + &hash_offset)) { + enum pkt_hash_types type; + + /* if L4 exists, it was used in the hash generation */ + type = be32_to_cpu(fd->status) & FM_FD_STAT_L4CV ? + PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3; + skb_set_hash(skb, be32_to_cpu(*(u32 *)(vaddr + hash_offset)), + type); + } + skb_len = skb->len; if (unlikely(netif_receive_skb(skb) == NET_RX_DROP)) @@ -2510,6 +2561,9 @@ static struct dpaa_bp *dpaa_bp_alloc(struct device *dev) dpaa_bp->bpid = FSL_DPAA_BPID_INV; dpaa_bp->percpu_count = devm_alloc_percpu(dev, *dpaa_bp->percpu_count); + if (!dpaa_bp->percpu_count) + return ERR_PTR(-ENOMEM); + dpaa_bp->config_count = FSL_DPAA_ETH_MAX_BUF_COUNT; dpaa_bp->seed_cb = dpaa_bp_seed; @@ -2737,6 +2791,9 @@ static int dpaa_eth_probe(struct platform_device *pdev) if (err) goto init_ports_failed; + /* Rx traffic distribution based on keygen hashing defaults to on */ + priv->keygen_in_use = true; + priv->percpu_priv = devm_alloc_percpu(dev, *priv->percpu_priv); if (!priv->percpu_priv) { dev_err(dev, "devm_alloc_percpu() failed\n"); @@ -2829,7 +2886,7 @@ static int dpaa_remove(struct platform_device *pdev) return err; } -static struct platform_device_id dpaa_devtype[] = { +static const struct platform_device_id dpaa_devtype[] = { { .name = "dpaa-ethernet", .driver_data = 0, diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h index 9941a7866ebe..bd9422082f83 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h @@ -52,6 +52,7 @@ enum dpaa_fq_type { FQ_TYPE_RX_DEFAULT = 1, /* Rx Default FQs */ FQ_TYPE_RX_ERROR, /* Rx Error FQs */ + FQ_TYPE_RX_PCD, /* Rx Parse Classify Distribute FQs */ FQ_TYPE_TX, /* "Real" Tx FQs */ FQ_TYPE_TX_CONFIRM, /* Tx default Conf FQ (actually an Rx FQ) */ FQ_TYPE_TX_CONF_MQ, /* Tx conf FQs (one for each Tx FQ) */ @@ -158,6 +159,7 @@ struct dpaa_priv { struct list_head dpaa_fq_list; u8 num_tc; + bool keygen_in_use; u32 msg_enable; /* net_device message level */ struct { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c index ec75d1c6fa89..0d9b185e317f 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c @@ -71,6 +71,9 @@ static ssize_t dpaa_eth_show_fqids(struct device *dev, case FQ_TYPE_RX_ERROR: str = "Rx error"; break; + case FQ_TYPE_RX_PCD: + str = "Rx PCD"; + break; case FQ_TYPE_TX_CONFIRM: str = "Tx default confirmation"; break; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index aad825088357..faea674094b9 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -399,6 +399,122 @@ static void dpaa_get_strings(struct net_device *net_dev, u32 stringset, memcpy(strings, dpaa_stats_global, size); } +static int dpaa_get_hash_opts(struct net_device *dev, + struct ethtool_rxnfc *cmd) +{ + struct dpaa_priv *priv = netdev_priv(dev); + + cmd->data = 0; + + switch (cmd->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + case UDP_V4_FLOW: + case UDP_V6_FLOW: + if (priv->keygen_in_use) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + /* Fall through */ + case IPV4_FLOW: + case IPV6_FLOW: + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + case AH_ESP_V4_FLOW: + case AH_ESP_V6_FLOW: + case AH_V4_FLOW: + case AH_V6_FLOW: + case ESP_V4_FLOW: + case ESP_V6_FLOW: + if (priv->keygen_in_use) + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + cmd->data = 0; + break; + } + + return 0; +} + +static int dpaa_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, + u32 *unused) +{ + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXFH: + ret = dpaa_get_hash_opts(dev, cmd); + break; + default: + break; + } + + return ret; +} + +static void dpaa_set_hash(struct net_device *net_dev, bool enable) +{ + struct mac_device *mac_dev; + struct fman_port *rxport; + struct dpaa_priv *priv; + + priv = netdev_priv(net_dev); + mac_dev = priv->mac_dev; + rxport = mac_dev->port[0]; + + fman_port_use_kg_hash(rxport, enable); + priv->keygen_in_use = enable; +} + +static int dpaa_set_hash_opts(struct net_device *dev, + struct ethtool_rxnfc *nfc) +{ + int ret = -EINVAL; + + /* we support hashing on IPv4/v6 src/dest IP and L4 src/dest port */ + if (nfc->data & + ~(RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + case UDP_V4_FLOW: + case UDP_V6_FLOW: + case IPV4_FLOW: + case IPV6_FLOW: + case SCTP_V4_FLOW: + case SCTP_V6_FLOW: + case AH_ESP_V4_FLOW: + case AH_ESP_V6_FLOW: + case AH_V4_FLOW: + case AH_V6_FLOW: + case ESP_V4_FLOW: + case ESP_V6_FLOW: + dpaa_set_hash(dev, !!nfc->data); + ret = 0; + break; + default: + break; + } + + return ret; +} + +static int dpaa_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXFH: + ret = dpaa_set_hash_opts(dev, cmd); + break; + default: + break; + } + + return ret; +} + const struct ethtool_ops dpaa_ethtool_ops = { .get_drvinfo = dpaa_get_drvinfo, .get_msglevel = dpaa_get_msglevel, @@ -412,4 +528,6 @@ const struct ethtool_ops dpaa_ethtool_ops = { .get_strings = dpaa_get_strings, .get_link_ksettings = dpaa_get_link_ksettings, .set_link_ksettings = dpaa_set_link_ksettings, + .get_rxnfc = dpaa_get_rxnfc, + .set_rxnfc = dpaa_set_rxnfc, }; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index a6e323f15637..56f56d6ada9c 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -173,10 +173,12 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); #endif /* CONFIG_M5272 */ /* The FEC stores dest/src/type/vlan, data, and checksum for receive packets. + * + * 2048 byte skbufs are allocated. However, alignment requirements + * varies between FEC variants. Worst case is 64, so round down by 64. */ -#define PKT_MAXBUF_SIZE 1522 +#define PKT_MAXBUF_SIZE (round_down(2048 - 64, 64)) #define PKT_MINBUF_SIZE 64 -#define PKT_MAXBLR_SIZE 1536 /* FEC receive acceleration */ #define FEC_RACC_IPDIS (1 << 1) @@ -224,7 +226,6 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); #define COPYBREAK_DEFAULT 256 -#define TSO_HEADER_SIZE 128 /* Max number of allowed TCP segments for software TSO */ #define FEC_MAX_TSO_SEGS 100 #define FEC_MAX_SKB_DESCS (FEC_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS) @@ -851,7 +852,7 @@ static void fec_enet_enable_ring(struct net_device *ndev) for (i = 0; i < fep->num_rx_queues; i++) { rxq = fep->rx_queue[i]; writel(rxq->bd.dma, fep->hwp + FEC_R_DES_START(i)); - writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i)); + writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i)); /* enable DMA1/2 */ if (i) @@ -1904,8 +1905,10 @@ static int fec_enet_mii_probe(struct net_device *ndev) phy_dev = of_phy_connect(ndev, fep->phy_node, &fec_enet_adjust_link, 0, fep->phy_interface); - if (!phy_dev) + if (!phy_dev) { + netdev_err(ndev, "Unable to connect to phy\n"); return -ENODEV; + } } else { /* check for attached phy */ for (phy_id = 0; (phy_id < PHY_MAX_ADDR); phy_id++) { diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index aa8cf5d2a53c..6d7269d87a85 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -960,8 +960,8 @@ static int mpc52xx_fec_probe(struct platform_device *op) /* We're done ! */ platform_set_drvdata(op, ndev); - netdev_info(ndev, "%s MAC %pM\n", - op->dev.of_node->full_name, ndev->dev_addr); + netdev_info(ndev, "%pOF MAC %pM\n", + op->dev.of_node, ndev->dev_addr); return 0; diff --git a/drivers/net/ethernet/freescale/fman/Makefile b/drivers/net/ethernet/freescale/fman/Makefile index 60491779e49f..2c38119b172c 100644 --- a/drivers/net/ethernet/freescale/fman/Makefile +++ b/drivers/net/ethernet/freescale/fman/Makefile @@ -4,6 +4,6 @@ obj-$(CONFIG_FSL_FMAN) += fsl_fman.o obj-$(CONFIG_FSL_FMAN) += fsl_fman_port.o obj-$(CONFIG_FSL_FMAN) += fsl_mac.o -fsl_fman-objs := fman_muram.o fman.o fman_sp.o +fsl_fman-objs := fman_muram.o fman.o fman_sp.o fman_keygen.o fsl_fman_port-objs := fman_port.o fsl_mac-objs:= mac.o fman_dtsec.o fman_memac.o fman_tgec.o diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c index 4aefe2438969..9530405030a7 100644 --- a/drivers/net/ethernet/freescale/fman/fman.c +++ b/drivers/net/ethernet/freescale/fman/fman.c @@ -32,9 +32,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include "fman.h" -#include "fman_muram.h" - #include <linux/fsl/guts.h> #include <linux/slab.h> #include <linux/delay.h> @@ -46,6 +43,10 @@ #include <linux/interrupt.h> #include <linux/libfdt_env.h> +#include "fman.h" +#include "fman_muram.h" +#include "fman_keygen.h" + /* General defines */ #define FMAN_LIODN_TBL 64 /* size of LIODN table */ #define MAX_NUM_OF_MACS 10 @@ -56,6 +57,7 @@ /* Modules registers offsets */ #define BMI_OFFSET 0x00080000 #define QMI_OFFSET 0x00080400 +#define KG_OFFSET 0x000C1000 #define DMA_OFFSET 0x000C2000 #define FPM_OFFSET 0x000C3000 #define IMEM_OFFSET 0x000C4000 @@ -564,80 +566,6 @@ struct fman_cfg { u32 qmi_def_tnums_thresh; }; -/* Structure that holds information received from device tree */ -struct fman_dts_params { - void __iomem *base_addr; /* FMan virtual address */ - struct resource *res; /* FMan memory resource */ - u8 id; /* FMan ID */ - - int err_irq; /* FMan Error IRQ */ - - u16 clk_freq; /* FMan clock freq (In Mhz) */ - - u32 qman_channel_base; /* QMan channels base */ - u32 num_of_qman_channels; /* Number of QMan channels */ - - struct resource muram_res; /* MURAM resource */ -}; - -/** fman_exceptions_cb - * fman - Pointer to FMan - * exception - The exception. - * - * Exceptions user callback routine, will be called upon an exception - * passing the exception identification. - * - * Return: irq status - */ -typedef irqreturn_t (fman_exceptions_cb)(struct fman *fman, - enum fman_exceptions exception); - -/** fman_bus_error_cb - * fman - Pointer to FMan - * port_id - Port id - * addr - Address that caused the error - * tnum - Owner of error - * liodn - Logical IO device number - * - * Bus error user callback routine, will be called upon bus error, - * passing parameters describing the errors and the owner. - * - * Return: IRQ status - */ -typedef irqreturn_t (fman_bus_error_cb)(struct fman *fman, u8 port_id, - u64 addr, u8 tnum, u16 liodn); - -struct fman { - struct device *dev; - void __iomem *base_addr; - struct fman_intr_src intr_mng[FMAN_EV_CNT]; - - struct fman_fpm_regs __iomem *fpm_regs; - struct fman_bmi_regs __iomem *bmi_regs; - struct fman_qmi_regs __iomem *qmi_regs; - struct fman_dma_regs __iomem *dma_regs; - struct fman_hwp_regs __iomem *hwp_regs; - fman_exceptions_cb *exception_cb; - fman_bus_error_cb *bus_error_cb; - /* Spinlock for FMan use */ - spinlock_t spinlock; - struct fman_state_struct *state; - - struct fman_cfg *cfg; - struct muram_info *muram; - /* cam section in muram */ - unsigned long cam_offset; - size_t cam_size; - /* Fifo in MURAM */ - unsigned long fifo_offset; - size_t fifo_size; - - u32 liodn_base[64]; - u32 liodn_offset[64]; - - struct fman_dts_params dts_params; -}; - static irqreturn_t fman_exceptions(struct fman *fman, enum fman_exceptions exception) { @@ -1811,6 +1739,7 @@ static int fman_config(struct fman *fman) fman->qmi_regs = base_addr + QMI_OFFSET; fman->dma_regs = base_addr + DMA_OFFSET; fman->hwp_regs = base_addr + HWP_OFFSET; + fman->kg_regs = base_addr + KG_OFFSET; fman->base_addr = base_addr; spin_lock_init(&fman->spinlock); @@ -1925,8 +1854,8 @@ static int fman_reset(struct fman *fman) guts_regs = of_iomap(guts_node, 0); if (!guts_regs) { - dev_err(fman->dev, "%s: Couldn't map %s regs\n", - __func__, guts_node->full_name); + dev_err(fman->dev, "%s: Couldn't map %pOF regs\n", + __func__, guts_node); goto guts_regs; } #define FMAN1_ALL_MACS_MASK 0xFCC00000 @@ -2083,6 +2012,11 @@ static int fman_init(struct fman *fman) /* Init HW Parser */ hwp_init(fman->hwp_regs); + /* Init KeyGen */ + fman->keygen = keygen_init(fman->kg_regs); + if (!fman->keygen) + return -EINVAL; + err = enable(fman, cfg); if (err != 0) return err; @@ -2434,15 +2368,21 @@ u32 fman_get_qman_channel_id(struct fman *fman, u32 port_id) int i; if (fman->state->rev_info.major >= 6) { - u32 port_ids[] = {0x30, 0x31, 0x28, 0x29, 0x2a, 0x2b, - 0x2c, 0x2d, 0x2, 0x3, 0x4, 0x5, 0x7, 0x7}; + static const u32 port_ids[] = { + 0x30, 0x31, 0x28, 0x29, 0x2a, 0x2b, + 0x2c, 0x2d, 0x2, 0x3, 0x4, 0x5, 0x7, 0x7 + }; + for (i = 0; i < fman->state->num_of_qman_channels; i++) { if (port_ids[i] == port_id) break; } } else { - u32 port_ids[] = {0x30, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x1, - 0x2, 0x3, 0x4, 0x5, 0x7, 0x7}; + static const u32 port_ids[] = { + 0x30, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x1, + 0x2, 0x3, 0x4, 0x5, 0x7, 0x7 + }; + for (i = 0; i < fman->state->num_of_qman_channels; i++) { if (port_ids[i] == port_id) break; @@ -2780,8 +2720,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) err = of_property_read_u32(fm_node, "cell-index", &val); if (err) { - dev_err(&of_dev->dev, "%s: failed to read cell-index for %s\n", - __func__, fm_node->full_name); + dev_err(&of_dev->dev, "%s: failed to read cell-index for %pOF\n", + __func__, fm_node); goto fman_node_put; } fman->dts_params.id = (u8)val; @@ -2834,8 +2774,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev) err = of_property_read_u32_array(fm_node, "fsl,qman-channel-range", &range[0], 2); if (err) { - dev_err(&of_dev->dev, "%s: failed to read fsl,qman-channel-range for %s\n", - __func__, fm_node->full_name); + dev_err(&of_dev->dev, "%s: failed to read fsl,qman-channel-range for %pOF\n", + __func__, fm_node); goto fman_node_put; } fman->dts_params.qman_channel_base = range[0]; diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h index f53e1473dbcc..bfa02e0014ae 100644 --- a/drivers/net/ethernet/freescale/fman/fman.h +++ b/drivers/net/ethernet/freescale/fman/fman.h @@ -34,6 +34,8 @@ #define __FM_H #include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/of_irq.h> /* FM Frame descriptor macros */ /* Frame queue Context Override */ @@ -274,6 +276,81 @@ struct fman_intr_src { void *src_handle; }; +/** fman_exceptions_cb + * fman - Pointer to FMan + * exception - The exception. + * + * Exceptions user callback routine, will be called upon an exception + * passing the exception identification. + * + * Return: irq status + */ +typedef irqreturn_t (fman_exceptions_cb)(struct fman *fman, + enum fman_exceptions exception); +/** fman_bus_error_cb + * fman - Pointer to FMan + * port_id - Port id + * addr - Address that caused the error + * tnum - Owner of error + * liodn - Logical IO device number + * + * Bus error user callback routine, will be called upon bus error, + * passing parameters describing the errors and the owner. + * + * Return: IRQ status + */ +typedef irqreturn_t (fman_bus_error_cb)(struct fman *fman, u8 port_id, + u64 addr, u8 tnum, u16 liodn); + +/* Structure that holds information received from device tree */ +struct fman_dts_params { + void __iomem *base_addr; /* FMan virtual address */ + struct resource *res; /* FMan memory resource */ + u8 id; /* FMan ID */ + + int err_irq; /* FMan Error IRQ */ + + u16 clk_freq; /* FMan clock freq (In Mhz) */ + + u32 qman_channel_base; /* QMan channels base */ + u32 num_of_qman_channels; /* Number of QMan channels */ + + struct resource muram_res; /* MURAM resource */ +}; + +struct fman { + struct device *dev; + void __iomem *base_addr; + struct fman_intr_src intr_mng[FMAN_EV_CNT]; + + struct fman_fpm_regs __iomem *fpm_regs; + struct fman_bmi_regs __iomem *bmi_regs; + struct fman_qmi_regs __iomem *qmi_regs; + struct fman_dma_regs __iomem *dma_regs; + struct fman_hwp_regs __iomem *hwp_regs; + struct fman_kg_regs __iomem *kg_regs; + fman_exceptions_cb *exception_cb; + fman_bus_error_cb *bus_error_cb; + /* Spinlock for FMan use */ + spinlock_t spinlock; + struct fman_state_struct *state; + + struct fman_cfg *cfg; + struct muram_info *muram; + struct fman_keygen *keygen; + /* cam section in muram */ + unsigned long cam_offset; + size_t cam_size; + /* Fifo in MURAM */ + unsigned long fifo_offset; + size_t fifo_size; + + u32 liodn_base[64]; + u32 liodn_offset[64]; + + struct fman_dts_params dts_params; +}; + /* Structure for port-FM communication during fman_port_init. */ struct fman_port_init_params { u8 port_id; /* port Id */ diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 98bba10fc38c..ea43b4974149 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -123,7 +123,7 @@ #define DTSEC_ECNTRL_R100M 0x00000008 #define DTSEC_ECNTRL_QSGMIIM 0x00000001 -#define DTSEC_TCTRL_GTS 0x00000020 +#define TCTRL_GTS 0x00000020 #define RCTRL_PAL_MASK 0x001f0000 #define RCTRL_PAL_SHIFT 16 @@ -863,6 +863,52 @@ int dtsec_cfg_pad_and_crc(struct fman_mac *dtsec, bool new_val) return 0; } +static void graceful_start(struct fman_mac *dtsec, enum comm_mode mode) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + + if (mode & COMM_MODE_TX) + iowrite32be(ioread32be(®s->tctrl) & + ~TCTRL_GTS, ®s->tctrl); + if (mode & COMM_MODE_RX) + iowrite32be(ioread32be(®s->rctrl) & + ~RCTRL_GRS, ®s->rctrl); +} + +static void graceful_stop(struct fman_mac *dtsec, enum comm_mode mode) +{ + struct dtsec_regs __iomem *regs = dtsec->regs; + u32 tmp; + + /* Graceful stop - Assert the graceful Rx stop bit */ + if (mode & COMM_MODE_RX) { + tmp = ioread32be(®s->rctrl) | RCTRL_GRS; + iowrite32be(tmp, ®s->rctrl); + + if (dtsec->fm_rev_info.major == 2) { + /* Workaround for dTSEC Errata A002 */ + usleep_range(100, 200); + } else { + /* Workaround for dTSEC Errata A004839 */ + usleep_range(10, 50); + } + } + + /* Graceful stop - Assert the graceful Tx stop bit */ + if (mode & COMM_MODE_TX) { + if (dtsec->fm_rev_info.major == 2) { + /* dTSEC Errata A004: Do not use TCTRL[GTS]=1 */ + pr_debug("GTS not supported due to DTSEC_A004 Errata.\n"); + } else { + tmp = ioread32be(®s->tctrl) | TCTRL_GTS; + iowrite32be(tmp, ®s->tctrl); + + /* Workaround for dTSEC Errata A0012, A0014 */ + usleep_range(10, 50); + } + } +} + int dtsec_enable(struct fman_mac *dtsec, enum comm_mode mode) { struct dtsec_regs __iomem *regs = dtsec->regs; @@ -880,13 +926,8 @@ int dtsec_enable(struct fman_mac *dtsec, enum comm_mode mode) iowrite32be(tmp, ®s->maccfg1); - /* Graceful start - clear the graceful receive stop bit */ - if (mode & COMM_MODE_TX) - iowrite32be(ioread32be(®s->tctrl) & ~DTSEC_TCTRL_GTS, - ®s->tctrl); - if (mode & COMM_MODE_RX) - iowrite32be(ioread32be(®s->rctrl) & ~RCTRL_GRS, - ®s->rctrl); + /* Graceful start - clear the graceful Rx/Tx stop bit */ + graceful_start(dtsec, mode); return 0; } @@ -899,23 +940,8 @@ int dtsec_disable(struct fman_mac *dtsec, enum comm_mode mode) if (!is_init_done(dtsec->dtsec_drv_param)) return -EINVAL; - /* Gracefull stop - Assert the graceful transmit stop bit */ - if (mode & COMM_MODE_RX) { - tmp = ioread32be(®s->rctrl) | RCTRL_GRS; - iowrite32be(tmp, ®s->rctrl); - - if (dtsec->fm_rev_info.major == 2) - usleep_range(100, 200); - else - udelay(10); - } - - if (mode & COMM_MODE_TX) { - if (dtsec->fm_rev_info.major == 2) - pr_debug("GTS not supported due to DTSEC_A004 errata.\n"); - else - pr_debug("GTS not supported due to DTSEC_A0014 errata.\n"); - } + /* Graceful stop - Assert the graceful Rx/Tx stop bit */ + graceful_stop(dtsec, mode); tmp = ioread32be(®s->maccfg1); if (mode & COMM_MODE_RX) @@ -933,11 +959,19 @@ int dtsec_set_tx_pause_frames(struct fman_mac *dtsec, u16 pause_time, u16 __maybe_unused thresh_time) { struct dtsec_regs __iomem *regs = dtsec->regs; + enum comm_mode mode = COMM_MODE_NONE; u32 ptv = 0; if (!is_init_done(dtsec->dtsec_drv_param)) return -EINVAL; + if ((ioread32be(®s->rctrl) & RCTRL_GRS) == 0) + mode |= COMM_MODE_RX; + if ((ioread32be(®s->tctrl) & TCTRL_GTS) == 0) + mode |= COMM_MODE_TX; + + graceful_stop(dtsec, mode); + if (pause_time) { /* FM_BAD_TX_TS_IN_B_2_B_ERRATA_DTSEC_A003 Errata workaround */ if (dtsec->fm_rev_info.major == 2 && pause_time <= 320) { @@ -958,17 +992,27 @@ int dtsec_set_tx_pause_frames(struct fman_mac *dtsec, iowrite32be(ioread32be(®s->maccfg1) & ~MACCFG1_TX_FLOW, ®s->maccfg1); + graceful_start(dtsec, mode); + return 0; } int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) { struct dtsec_regs __iomem *regs = dtsec->regs; + enum comm_mode mode = COMM_MODE_NONE; u32 tmp; if (!is_init_done(dtsec->dtsec_drv_param)) return -EINVAL; + if ((ioread32be(®s->rctrl) & RCTRL_GRS) == 0) + mode |= COMM_MODE_RX; + if ((ioread32be(®s->tctrl) & TCTRL_GTS) == 0) + mode |= COMM_MODE_TX; + + graceful_stop(dtsec, mode); + tmp = ioread32be(®s->maccfg1); if (en) tmp |= MACCFG1_RX_FLOW; @@ -976,20 +1020,34 @@ int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) tmp &= ~MACCFG1_RX_FLOW; iowrite32be(tmp, ®s->maccfg1); + graceful_start(dtsec, mode); + return 0; } int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) { + struct dtsec_regs __iomem *regs = dtsec->regs; + enum comm_mode mode = COMM_MODE_NONE; + if (!is_init_done(dtsec->dtsec_drv_param)) return -EINVAL; + if ((ioread32be(®s->rctrl) & RCTRL_GRS) == 0) + mode |= COMM_MODE_RX; + if ((ioread32be(®s->tctrl) & TCTRL_GTS) == 0) + mode |= COMM_MODE_TX; + + graceful_stop(dtsec, mode); + /* Initialize MAC Station Address registers (1 & 2) * Station address have to be swapped (big endian to little endian */ dtsec->addr = ENET_ADDR_TO_UINT64(*enet_addr); set_mac_address(dtsec->regs, (u8 *)(*enet_addr)); + graceful_start(dtsec, mode); + return 0; } @@ -1162,11 +1220,19 @@ int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val) int dtsec_adjust_link(struct fman_mac *dtsec, u16 speed) { struct dtsec_regs __iomem *regs = dtsec->regs; + enum comm_mode mode = COMM_MODE_NONE; u32 tmp; if (!is_init_done(dtsec->dtsec_drv_param)) return -EINVAL; + if ((ioread32be(®s->rctrl) & RCTRL_GRS) == 0) + mode |= COMM_MODE_RX; + if ((ioread32be(®s->tctrl) & TCTRL_GTS) == 0) + mode |= COMM_MODE_TX; + + graceful_stop(dtsec, mode); + tmp = ioread32be(®s->maccfg2); /* Full Duplex */ @@ -1186,6 +1252,8 @@ int dtsec_adjust_link(struct fman_mac *dtsec, u16 speed) tmp &= ~DTSEC_ECNTRL_R100M; iowrite32be(tmp, ®s->ecntrl); + graceful_start(dtsec, mode); + return 0; } diff --git a/drivers/net/ethernet/freescale/fman/fman_keygen.c b/drivers/net/ethernet/freescale/fman/fman_keygen.c new file mode 100644 index 000000000000..f54da3c684d0 --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_keygen.c @@ -0,0 +1,783 @@ +/* + * Copyright 2017 NXP + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of NXP nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY NXP ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL NXP BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> + +#include "fman_keygen.h" + +/* Maximum number of HW Ports */ +#define FMAN_MAX_NUM_OF_HW_PORTS 64 + +/* Maximum number of KeyGen Schemes */ +#define FM_KG_MAX_NUM_OF_SCHEMES 32 + +/* Number of generic KeyGen Generic Extract Command Registers */ +#define FM_KG_NUM_OF_GENERIC_REGS 8 + +/* Dummy port ID */ +#define DUMMY_PORT_ID 0 + +/* Select Scheme Value Register */ +#define KG_SCH_DEF_USE_KGSE_DV_0 2 +#define KG_SCH_DEF_USE_KGSE_DV_1 3 + +/* Registers Shifting values */ +#define FM_KG_KGAR_NUM_SHIFT 16 +#define KG_SCH_DEF_L4_PORT_SHIFT 8 +#define KG_SCH_DEF_IP_ADDR_SHIFT 18 +#define KG_SCH_HASH_CONFIG_SHIFT_SHIFT 24 + +/* KeyGen Registers bit field masks: */ + +/* Enable bit field mask for KeyGen General Configuration Register */ +#define FM_KG_KGGCR_EN 0x80000000 + +/* KeyGen Global Registers bit field masks */ +#define FM_KG_KGAR_GO 0x80000000 +#define FM_KG_KGAR_READ 0x40000000 +#define FM_KG_KGAR_WRITE 0x00000000 +#define FM_KG_KGAR_SEL_SCHEME_ENTRY 0x00000000 +#define FM_KG_KGAR_SCM_WSEL_UPDATE_CNT 0x00008000 + +#define FM_KG_KGAR_ERR 0x20000000 +#define FM_KG_KGAR_SEL_CLS_PLAN_ENTRY 0x01000000 +#define FM_KG_KGAR_SEL_PORT_ENTRY 0x02000000 +#define FM_KG_KGAR_SEL_PORT_WSEL_SP 0x00008000 +#define FM_KG_KGAR_SEL_PORT_WSEL_CPP 0x00004000 + +/* Error events exceptions */ +#define FM_EX_KG_DOUBLE_ECC 0x80000000 +#define FM_EX_KG_KEYSIZE_OVERFLOW 0x40000000 + +/* Scheme Registers bit field masks */ +#define KG_SCH_MODE_EN 0x80000000 +#define KG_SCH_VSP_NO_KSP_EN 0x80000000 +#define KG_SCH_HASH_CONFIG_SYM 0x40000000 + +/* Known Protocol field codes */ +#define KG_SCH_KN_PORT_ID 0x80000000 +#define KG_SCH_KN_MACDST 0x40000000 +#define KG_SCH_KN_MACSRC 0x20000000 +#define KG_SCH_KN_TCI1 0x10000000 +#define KG_SCH_KN_TCI2 0x08000000 +#define KG_SCH_KN_ETYPE 0x04000000 +#define KG_SCH_KN_PPPSID 0x02000000 +#define KG_SCH_KN_PPPID 0x01000000 +#define KG_SCH_KN_MPLS1 0x00800000 +#define KG_SCH_KN_MPLS2 0x00400000 +#define KG_SCH_KN_MPLS_LAST 0x00200000 +#define KG_SCH_KN_IPSRC1 0x00100000 +#define KG_SCH_KN_IPDST1 0x00080000 +#define KG_SCH_KN_PTYPE1 0x00040000 +#define KG_SCH_KN_IPTOS_TC1 0x00020000 +#define KG_SCH_KN_IPV6FL1 0x00010000 +#define KG_SCH_KN_IPSRC2 0x00008000 +#define KG_SCH_KN_IPDST2 0x00004000 +#define KG_SCH_KN_PTYPE2 0x00002000 +#define KG_SCH_KN_IPTOS_TC2 0x00001000 +#define KG_SCH_KN_IPV6FL2 0x00000800 +#define KG_SCH_KN_GREPTYPE 0x00000400 +#define KG_SCH_KN_IPSEC_SPI 0x00000200 +#define KG_SCH_KN_IPSEC_NH 0x00000100 +#define KG_SCH_KN_IPPID 0x00000080 +#define KG_SCH_KN_L4PSRC 0x00000004 +#define KG_SCH_KN_L4PDST 0x00000002 +#define KG_SCH_KN_TFLG 0x00000001 + +/* NIA values */ +#define NIA_ENG_BMI 0x00500000 +#define NIA_BMI_AC_ENQ_FRAME 0x00000002 +#define ENQUEUE_KG_DFLT_NIA (NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME) + +/* Hard-coded configuration: + * These values are used as hard-coded values for KeyGen configuration + * and they replace user selections for this hard-coded version + */ + +/* Hash distribution shift */ +#define DEFAULT_HASH_DIST_FQID_SHIFT 0 + +/* Hash shift */ +#define DEFAULT_HASH_SHIFT 0 + +/* Symmetric hash usage: + * Warning: + * - the value for symmetric hash usage must be in accordance with hash + * key defined below + * - according to tests performed, spreading is not working if symmetric + * hash is set on true + * So ultimately symmetric hash functionality should be always disabled: + */ +#define DEFAULT_SYMMETRIC_HASH false + +/* Hash Key extraction fields: */ +#define DEFAULT_HASH_KEY_EXTRACT_FIELDS \ + (KG_SCH_KN_IPSRC1 | KG_SCH_KN_IPDST1 | \ + KG_SCH_KN_L4PSRC | KG_SCH_KN_L4PDST) + +/* Default values to be used as hash key in case IPv4 or L4 (TCP, UDP) + * don't exist in the frame + */ +/* Default IPv4 address */ +#define DEFAULT_HASH_KEY_IPv4_ADDR 0x0A0A0A0A +/* Default L4 port */ +#define DEFAULT_HASH_KEY_L4_PORT 0x0B0B0B0B + +/* KeyGen Memory Mapped Registers: */ + +/* Scheme Configuration RAM Registers */ +struct fman_kg_scheme_regs { + u32 kgse_mode; /* 0x100: MODE */ + u32 kgse_ekfc; /* 0x104: Extract Known Fields Command */ + u32 kgse_ekdv; /* 0x108: Extract Known Default Value */ + u32 kgse_bmch; /* 0x10C: Bit Mask Command High */ + u32 kgse_bmcl; /* 0x110: Bit Mask Command Low */ + u32 kgse_fqb; /* 0x114: Frame Queue Base */ + u32 kgse_hc; /* 0x118: Hash Command */ + u32 kgse_ppc; /* 0x11C: Policer Profile Command */ + u32 kgse_gec[FM_KG_NUM_OF_GENERIC_REGS]; + /* 0x120: Generic Extract Command */ + u32 kgse_spc; + /* 0x140: KeyGen Scheme Entry Statistic Packet Counter */ + u32 kgse_dv0; /* 0x144: KeyGen Scheme Entry Default Value 0 */ + u32 kgse_dv1; /* 0x148: KeyGen Scheme Entry Default Value 1 */ + u32 kgse_ccbs; + /* 0x14C: KeyGen Scheme Entry Coarse Classification Bit*/ + u32 kgse_mv; /* 0x150: KeyGen Scheme Entry Match vector */ + u32 kgse_om; /* 0x154: KeyGen Scheme Entry Operation Mode bits */ + u32 kgse_vsp; + /* 0x158: KeyGen Scheme Entry Virtual Storage Profile */ +}; + +/* Port Partition Configuration Registers */ +struct fman_kg_pe_regs { + u32 fmkg_pe_sp; /* 0x100: KeyGen Port entry Scheme Partition */ + u32 fmkg_pe_cpp; + /* 0x104: KeyGen Port Entry Classification Plan Partition */ +}; + +/* General Configuration and Status Registers + * Global Statistic Counters + * KeyGen Global Registers + */ +struct fman_kg_regs { + u32 fmkg_gcr; /* 0x000: KeyGen General Configuration Register */ + u32 res004; /* 0x004: Reserved */ + u32 res008; /* 0x008: Reserved */ + u32 fmkg_eer; /* 0x00C: KeyGen Error Event Register */ + u32 fmkg_eeer; /* 0x010: KeyGen Error Event Enable Register */ + u32 res014; /* 0x014: Reserved */ + u32 res018; /* 0x018: Reserved */ + u32 fmkg_seer; /* 0x01C: KeyGen Scheme Error Event Register */ + u32 fmkg_seeer; /* 0x020: KeyGen Scheme Error Event Enable Register */ + u32 fmkg_gsr; /* 0x024: KeyGen Global Status Register */ + u32 fmkg_tpc; /* 0x028: Total Packet Counter Register */ + u32 fmkg_serc; /* 0x02C: Soft Error Capture Register */ + u32 res030[4]; /* 0x030: Reserved */ + u32 fmkg_fdor; /* 0x034: Frame Data Offset Register */ + u32 fmkg_gdv0r; /* 0x038: Global Default Value Register 0 */ + u32 fmkg_gdv1r; /* 0x03C: Global Default Value Register 1 */ + u32 res04c[6]; /* 0x040: Reserved */ + u32 fmkg_feer; /* 0x044: Force Error Event Register */ + u32 res068[38]; /* 0x048: Reserved */ + union { + u32 fmkg_indirect[63]; /* 0x100: Indirect Access Registers */ + struct fman_kg_scheme_regs fmkg_sch; /* Scheme Registers */ + struct fman_kg_pe_regs fmkg_pe; /* Port Partition Registers */ + }; + u32 fmkg_ar; /* 0x1FC: KeyGen Action Register */ +}; + +/* KeyGen Scheme data */ +struct keygen_scheme { + bool used; /* Specifies if this scheme is used */ + u8 hw_port_id; + /* Hardware port ID + * schemes sharing between multiple ports is not + * currently supported + * so we have only one port id bound to a scheme + */ + u32 base_fqid; + /* Base FQID: + * Must be between 1 and 2^24-1 + * If hash is used and an even distribution is + * expected according to hash_fqid_count, + * base_fqid must be aligned to hash_fqid_count + */ + u32 hash_fqid_count; + /* FQ range for hash distribution: + * Must be a power of 2 + * Represents the range of queues for spreading + */ + bool use_hashing; /* Usage of Hashing and spreading over FQ */ + bool symmetric_hash; /* Symmetric Hash option usage */ + u8 hashShift; + /* Hash result right shift. + * Select the 24 bits out of the 64 hash result. + * 0 means using the 24 LSB's, otherwise + * use the 24 LSB's after shifting right + */ + u32 match_vector; /* Match Vector */ +}; + +/* KeyGen driver data */ +struct fman_keygen { + struct keygen_scheme schemes[FM_KG_MAX_NUM_OF_SCHEMES]; + /* Array of schemes */ + struct fman_kg_regs __iomem *keygen_regs; /* KeyGen registers */ +}; + +/* keygen_write_ar_wait + * + * Write Action Register with specified value, wait for GO bit field to be + * idle and then read the error + * + * regs: KeyGen registers + * fmkg_ar: Action Register value + * + * Return: Zero for success or error code in case of failure + */ +static int keygen_write_ar_wait(struct fman_kg_regs __iomem *regs, u32 fmkg_ar) +{ + iowrite32be(fmkg_ar, ®s->fmkg_ar); + + /* Wait for GO bit field to be idle */ + while (fmkg_ar & FM_KG_KGAR_GO) + fmkg_ar = ioread32be(®s->fmkg_ar); + + if (fmkg_ar & FM_KG_KGAR_ERR) + return -EINVAL; + + return 0; +} + +/* build_ar_scheme + * + * Build Action Register value for scheme settings + * + * scheme_id: Scheme ID + * update_counter: update scheme counter + * write: true for action to write the scheme or false for read action + * + * Return: AR value + */ +static u32 build_ar_scheme(u8 scheme_id, bool update_counter, bool write) +{ + u32 rw = (u32)(write ? FM_KG_KGAR_WRITE : FM_KG_KGAR_READ); + + return (u32)(FM_KG_KGAR_GO | + rw | + FM_KG_KGAR_SEL_SCHEME_ENTRY | + DUMMY_PORT_ID | + ((u32)scheme_id << FM_KG_KGAR_NUM_SHIFT) | + (update_counter ? FM_KG_KGAR_SCM_WSEL_UPDATE_CNT : 0)); +} + +/* build_ar_bind_scheme + * + * Build Action Register value for port binding to schemes + * + * hwport_id: HW Port ID + * write: true for action to write the bind or false for read action + * + * Return: AR value + */ +static u32 build_ar_bind_scheme(u8 hwport_id, bool write) +{ + u32 rw = write ? (u32)FM_KG_KGAR_WRITE : (u32)FM_KG_KGAR_READ; + + return (u32)(FM_KG_KGAR_GO | + rw | + FM_KG_KGAR_SEL_PORT_ENTRY | + hwport_id | + FM_KG_KGAR_SEL_PORT_WSEL_SP); +} + +/* keygen_write_sp + * + * Write Scheme Partition Register with specified value + * + * regs: KeyGen Registers + * sp: Scheme Partition register value + * add: true to add a scheme partition or false to clear + * + * Return: none + */ +static void keygen_write_sp(struct fman_kg_regs __iomem *regs, u32 sp, bool add) +{ + u32 tmp; + + tmp = ioread32be(®s->fmkg_pe.fmkg_pe_sp); + + if (add) + tmp |= sp; + else + tmp &= ~sp; + + iowrite32be(tmp, ®s->fmkg_pe.fmkg_pe_sp); +} + +/* build_ar_bind_cls_plan + * + * Build Action Register value for Classification Plan + * + * hwport_id: HW Port ID + * write: true for action to write the CP or false for read action + * + * Return: AR value + */ +static u32 build_ar_bind_cls_plan(u8 hwport_id, bool write) +{ + u32 rw = write ? (u32)FM_KG_KGAR_WRITE : (u32)FM_KG_KGAR_READ; + + return (u32)(FM_KG_KGAR_GO | + rw | + FM_KG_KGAR_SEL_PORT_ENTRY | + hwport_id | + FM_KG_KGAR_SEL_PORT_WSEL_CPP); +} + +/* keygen_write_cpp + * + * Write Classification Plan Partition Register with specified value + * + * regs: KeyGen Registers + * cpp: CPP register value + * + * Return: none + */ +static void keygen_write_cpp(struct fman_kg_regs __iomem *regs, u32 cpp) +{ + iowrite32be(cpp, ®s->fmkg_pe.fmkg_pe_cpp); +} + +/* keygen_write_scheme + * + * Write all Schemes Registers with specified values + * + * regs: KeyGen Registers + * scheme_id: Scheme ID + * scheme_regs: Scheme registers values desired to be written + * update_counter: update scheme counter + * + * Return: Zero for success or error code in case of failure + */ +static int keygen_write_scheme(struct fman_kg_regs __iomem *regs, u8 scheme_id, + struct fman_kg_scheme_regs *scheme_regs, + bool update_counter) +{ + u32 ar_reg; + int err, i; + + /* Write indirect scheme registers */ + iowrite32be(scheme_regs->kgse_mode, ®s->fmkg_sch.kgse_mode); + iowrite32be(scheme_regs->kgse_ekfc, ®s->fmkg_sch.kgse_ekfc); + iowrite32be(scheme_regs->kgse_ekdv, ®s->fmkg_sch.kgse_ekdv); + iowrite32be(scheme_regs->kgse_bmch, ®s->fmkg_sch.kgse_bmch); + iowrite32be(scheme_regs->kgse_bmcl, ®s->fmkg_sch.kgse_bmcl); + iowrite32be(scheme_regs->kgse_fqb, ®s->fmkg_sch.kgse_fqb); + iowrite32be(scheme_regs->kgse_hc, ®s->fmkg_sch.kgse_hc); + iowrite32be(scheme_regs->kgse_ppc, ®s->fmkg_sch.kgse_ppc); + iowrite32be(scheme_regs->kgse_spc, ®s->fmkg_sch.kgse_spc); + iowrite32be(scheme_regs->kgse_dv0, ®s->fmkg_sch.kgse_dv0); + iowrite32be(scheme_regs->kgse_dv1, ®s->fmkg_sch.kgse_dv1); + iowrite32be(scheme_regs->kgse_ccbs, ®s->fmkg_sch.kgse_ccbs); + iowrite32be(scheme_regs->kgse_mv, ®s->fmkg_sch.kgse_mv); + iowrite32be(scheme_regs->kgse_om, ®s->fmkg_sch.kgse_om); + iowrite32be(scheme_regs->kgse_vsp, ®s->fmkg_sch.kgse_vsp); + + for (i = 0 ; i < FM_KG_NUM_OF_GENERIC_REGS ; i++) + iowrite32be(scheme_regs->kgse_gec[i], + ®s->fmkg_sch.kgse_gec[i]); + + /* Write AR (Action register) */ + ar_reg = build_ar_scheme(scheme_id, update_counter, true); + err = keygen_write_ar_wait(regs, ar_reg); + if (err != 0) { + pr_err("Writing Action Register failed\n"); + return err; + } + + return err; +} + +/* get_free_scheme_id + * + * Find the first free scheme available to be used + * + * keygen: KeyGen handle + * scheme_id: pointer to scheme id + * + * Return: 0 on success, -EINVAL when the are no available free schemes + */ +static int get_free_scheme_id(struct fman_keygen *keygen, u8 *scheme_id) +{ + u8 i; + + for (i = 0; i < FM_KG_MAX_NUM_OF_SCHEMES; i++) + if (!keygen->schemes[i].used) { + *scheme_id = i; + return 0; + } + + return -EINVAL; +} + +/* get_scheme + * + * Provides the scheme for specified ID + * + * keygen: KeyGen handle + * scheme_id: Scheme ID + * + * Return: handle to required scheme + */ +static struct keygen_scheme *get_scheme(struct fman_keygen *keygen, + u8 scheme_id) +{ + if (scheme_id >= FM_KG_MAX_NUM_OF_SCHEMES) + return NULL; + return &keygen->schemes[scheme_id]; +} + +/* keygen_bind_port_to_schemes + * + * Bind the port to schemes + * + * keygen: KeyGen handle + * scheme_id: id of the scheme to bind to + * bind: true to bind the port or false to unbind it + * + * Return: Zero for success or error code in case of failure + */ +static int keygen_bind_port_to_schemes(struct fman_keygen *keygen, + u8 scheme_id, + bool bind) +{ + struct fman_kg_regs __iomem *keygen_regs = keygen->keygen_regs; + struct keygen_scheme *scheme; + u32 ar_reg; + u32 schemes_vector = 0; + int err; + + scheme = get_scheme(keygen, scheme_id); + if (!scheme) { + pr_err("Requested Scheme does not exist\n"); + return -EINVAL; + } + if (!scheme->used) { + pr_err("Cannot bind port to an invalid scheme\n"); + return -EINVAL; + } + + schemes_vector |= 1 << (31 - scheme_id); + + ar_reg = build_ar_bind_scheme(scheme->hw_port_id, false); + err = keygen_write_ar_wait(keygen_regs, ar_reg); + if (err != 0) { + pr_err("Reading Action Register failed\n"); + return err; + } + + keygen_write_sp(keygen_regs, schemes_vector, bind); + + ar_reg = build_ar_bind_scheme(scheme->hw_port_id, true); + err = keygen_write_ar_wait(keygen_regs, ar_reg); + if (err != 0) { + pr_err("Writing Action Register failed\n"); + return err; + } + + return 0; +} + +/* keygen_scheme_setup + * + * Setup the scheme according to required configuration + * + * keygen: KeyGen handle + * scheme_id: scheme ID + * enable: true to enable scheme or false to disable it + * + * Return: Zero for success or error code in case of failure + */ +static int keygen_scheme_setup(struct fman_keygen *keygen, u8 scheme_id, + bool enable) +{ + struct fman_kg_regs __iomem *keygen_regs = keygen->keygen_regs; + struct fman_kg_scheme_regs scheme_regs; + struct keygen_scheme *scheme; + u32 tmp_reg; + int err; + + scheme = get_scheme(keygen, scheme_id); + if (!scheme) { + pr_err("Requested Scheme does not exist\n"); + return -EINVAL; + } + if (enable && scheme->used) { + pr_err("The requested Scheme is already used\n"); + return -EINVAL; + } + + /* Clear scheme registers */ + memset(&scheme_regs, 0, sizeof(struct fman_kg_scheme_regs)); + + /* Setup all scheme registers: */ + tmp_reg = 0; + + if (enable) { + /* Enable Scheme */ + tmp_reg |= KG_SCH_MODE_EN; + /* Enqueue frame NIA */ + tmp_reg |= ENQUEUE_KG_DFLT_NIA; + } + + scheme_regs.kgse_mode = tmp_reg; + + scheme_regs.kgse_mv = scheme->match_vector; + + /* Scheme don't override StorageProfile: + * valid only for DPAA_VERSION >= 11 + */ + scheme_regs.kgse_vsp = KG_SCH_VSP_NO_KSP_EN; + + /* Configure Hard-Coded Rx Hashing: */ + + if (scheme->use_hashing) { + /* configure kgse_ekfc */ + scheme_regs.kgse_ekfc = DEFAULT_HASH_KEY_EXTRACT_FIELDS; + + /* configure kgse_ekdv */ + tmp_reg = 0; + tmp_reg |= (KG_SCH_DEF_USE_KGSE_DV_0 << + KG_SCH_DEF_IP_ADDR_SHIFT); + tmp_reg |= (KG_SCH_DEF_USE_KGSE_DV_1 << + KG_SCH_DEF_L4_PORT_SHIFT); + scheme_regs.kgse_ekdv = tmp_reg; + + /* configure kgse_dv0 */ + scheme_regs.kgse_dv0 = DEFAULT_HASH_KEY_IPv4_ADDR; + /* configure kgse_dv1 */ + scheme_regs.kgse_dv1 = DEFAULT_HASH_KEY_L4_PORT; + + /* configure kgse_hc */ + tmp_reg = 0; + tmp_reg |= ((scheme->hash_fqid_count - 1) << + DEFAULT_HASH_DIST_FQID_SHIFT); + tmp_reg |= scheme->hashShift << KG_SCH_HASH_CONFIG_SHIFT_SHIFT; + + if (scheme->symmetric_hash) { + /* Normally extraction key should be verified if + * complies with symmetric hash + * But because extraction is hard-coded, we are sure + * the key is symmetric + */ + tmp_reg |= KG_SCH_HASH_CONFIG_SYM; + } + scheme_regs.kgse_hc = tmp_reg; + } else { + scheme_regs.kgse_ekfc = 0; + scheme_regs.kgse_hc = 0; + scheme_regs.kgse_ekdv = 0; + scheme_regs.kgse_dv0 = 0; + scheme_regs.kgse_dv1 = 0; + } + + /* configure kgse_fqb: Scheme FQID base */ + tmp_reg = 0; + tmp_reg |= scheme->base_fqid; + scheme_regs.kgse_fqb = tmp_reg; + + /* features not used by hard-coded configuration */ + scheme_regs.kgse_bmch = 0; + scheme_regs.kgse_bmcl = 0; + scheme_regs.kgse_spc = 0; + + /* Write scheme registers */ + err = keygen_write_scheme(keygen_regs, scheme_id, &scheme_regs, true); + if (err != 0) { + pr_err("Writing scheme registers failed\n"); + return err; + } + + /* Update used field for Scheme */ + scheme->used = enable; + + return 0; +} + +/* keygen_init + * + * KeyGen initialization: + * Initializes and enables KeyGen, allocate driver memory, setup registers, + * clear port bindings, invalidate all schemes + * + * keygen_regs: KeyGen registers base address + * + * Return: Handle to KeyGen driver + */ +struct fman_keygen *keygen_init(struct fman_kg_regs __iomem *keygen_regs) +{ + struct fman_keygen *keygen; + u32 ar; + int i; + + /* Allocate memory for KeyGen driver */ + keygen = kzalloc(sizeof(*keygen), GFP_KERNEL); + if (!keygen) + return NULL; + + keygen->keygen_regs = keygen_regs; + + /* KeyGen initialization (for Master partition): + * Setup KeyGen registers + */ + iowrite32be(ENQUEUE_KG_DFLT_NIA, &keygen_regs->fmkg_gcr); + + iowrite32be(FM_EX_KG_DOUBLE_ECC | FM_EX_KG_KEYSIZE_OVERFLOW, + &keygen_regs->fmkg_eer); + + iowrite32be(0, &keygen_regs->fmkg_fdor); + iowrite32be(0, &keygen_regs->fmkg_gdv0r); + iowrite32be(0, &keygen_regs->fmkg_gdv1r); + + /* Clear binding between ports to schemes and classification plans + * so that all ports are not bound to any scheme/classification plan + */ + for (i = 0; i < FMAN_MAX_NUM_OF_HW_PORTS; i++) { + /* Clear all pe sp schemes registers */ + keygen_write_sp(keygen_regs, 0xffffffff, false); + ar = build_ar_bind_scheme(i, true); + keygen_write_ar_wait(keygen_regs, ar); + + /* Clear all pe cpp classification plans registers */ + keygen_write_cpp(keygen_regs, 0); + ar = build_ar_bind_cls_plan(i, true); + keygen_write_ar_wait(keygen_regs, ar); + } + + /* Enable all scheme interrupts */ + iowrite32be(0xFFFFFFFF, &keygen_regs->fmkg_seer); + iowrite32be(0xFFFFFFFF, &keygen_regs->fmkg_seeer); + + /* Enable KyeGen */ + iowrite32be(ioread32be(&keygen_regs->fmkg_gcr) | FM_KG_KGGCR_EN, + &keygen_regs->fmkg_gcr); + + return keygen; +} +EXPORT_SYMBOL(keygen_init); + +/* keygen_port_hashing_init + * + * Initializes a port for Rx Hashing with specified configuration parameters + * + * keygen: KeyGen handle + * hw_port_id: HW Port ID + * hash_base_fqid: Hashing Base FQID used for spreading + * hash_size: Hashing size + * + * Return: Zero for success or error code in case of failure + */ +int keygen_port_hashing_init(struct fman_keygen *keygen, u8 hw_port_id, + u32 hash_base_fqid, u32 hash_size) +{ + struct keygen_scheme *scheme; + u8 scheme_id; + int err; + + /* Validate Scheme configuration parameters */ + if (hash_base_fqid == 0 || (hash_base_fqid & ~0x00FFFFFF)) { + pr_err("Base FQID must be between 1 and 2^24-1\n"); + return -EINVAL; + } + if (hash_size == 0 || (hash_size & (hash_size - 1)) != 0) { + pr_err("Hash size must be power of two\n"); + return -EINVAL; + } + + /* Find a free scheme */ + err = get_free_scheme_id(keygen, &scheme_id); + if (err) { + pr_err("The maximum number of available Schemes has been exceeded\n"); + return -EINVAL; + } + + /* Create and configure Hard-Coded Scheme: */ + + scheme = get_scheme(keygen, scheme_id); + if (!scheme) { + pr_err("Requested Scheme does not exist\n"); + return -EINVAL; + } + if (scheme->used) { + pr_err("The requested Scheme is already used\n"); + return -EINVAL; + } + + /* Clear all scheme fields because the scheme may have been + * previously used + */ + memset(scheme, 0, sizeof(struct keygen_scheme)); + + /* Setup scheme: */ + scheme->hw_port_id = hw_port_id; + scheme->use_hashing = true; + scheme->base_fqid = hash_base_fqid; + scheme->hash_fqid_count = hash_size; + scheme->symmetric_hash = DEFAULT_SYMMETRIC_HASH; + scheme->hashShift = DEFAULT_HASH_SHIFT; + + /* All Schemes in hard-coded configuration + * are Indirect Schemes + */ + scheme->match_vector = 0; + + err = keygen_scheme_setup(keygen, scheme_id, true); + if (err != 0) { + pr_err("Scheme setup failed\n"); + return err; + } + + /* Bind Rx port to Scheme */ + err = keygen_bind_port_to_schemes(keygen, scheme_id, true); + if (err != 0) { + pr_err("Binding port to schemes failed\n"); + return err; + } + + return 0; +} +EXPORT_SYMBOL(keygen_port_hashing_init); diff --git a/drivers/net/ethernet/freescale/fman/fman_keygen.h b/drivers/net/ethernet/freescale/fman/fman_keygen.h new file mode 100644 index 000000000000..c4640de3f4cb --- /dev/null +++ b/drivers/net/ethernet/freescale/fman/fman_keygen.h @@ -0,0 +1,46 @@ +/* + * Copyright 2017 NXP + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * * Neither the name of NXP nor the + * names of its contributors may be used to endorse or promote products + * derived from this software without specific prior written permission. + * + * + * ALTERNATIVELY, this software may be distributed under the terms of the + * GNU General Public License ("GPL") as published by the Free Software + * Foundation, either version 2 of that License or (at your option) any + * later version. + * + * THIS SOFTWARE IS PROVIDED BY NXP ``AS IS'' AND ANY + * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED + * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE + * DISCLAIMED. IN NO EVENT SHALL NXP BE LIABLE FOR ANY + * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; + * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS + * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef __KEYGEN_H +#define __KEYGEN_H + +#include <linux/io.h> + +struct fman_keygen; +struct fman_kg_regs; + +struct fman_keygen *keygen_init(struct fman_kg_regs __iomem *keygen_regs); + +int keygen_port_hashing_init(struct fman_keygen *keygen, u8 hw_port_id, + u32 hash_base_fqid, u32 hash_size); + +#endif /* __KEYGEN_H */ diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 57bf44fa16a1..1789b206be58 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -32,10 +32,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include "fman_port.h" -#include "fman.h" -#include "fman_sp.h" - #include <linux/io.h> #include <linux/slab.h> #include <linux/module.h> @@ -45,6 +41,11 @@ #include <linux/delay.h> #include <linux/libfdt_env.h> +#include "fman.h" +#include "fman_port.h" +#include "fman_sp.h" +#include "fman_keygen.h" + /* Queue ID */ #define DFLT_FQ_ID 0x00FFFFFF @@ -184,6 +185,7 @@ #define NIA_ENG_QMI_ENQ 0x00540000 #define NIA_ENG_QMI_DEQ 0x00580000 #define NIA_ENG_HWP 0x00440000 +#define NIA_ENG_HWK 0x00480000 #define NIA_BMI_AC_ENQ_FRAME 0x00000002 #define NIA_BMI_AC_TX_RELEASE 0x000002C0 #define NIA_BMI_AC_RELEASE 0x000000C0 @@ -394,6 +396,8 @@ struct fman_port_bpools { struct fman_port_cfg { u32 dflt_fqid; u32 err_fqid; + u32 pcd_base_fqid; + u32 pcd_fqs_count; u8 deq_sp; bool deq_high_priority; enum fman_port_deq_type deq_type; @@ -1271,6 +1275,10 @@ static void set_rx_dflt_cfg(struct fman_port *port, port_params->specific_params.rx_params.err_fqid; port->cfg->dflt_fqid = port_params->specific_params.rx_params.dflt_fqid; + port->cfg->pcd_base_fqid = + port_params->specific_params.rx_params.pcd_base_fqid; + port->cfg->pcd_fqs_count = + port_params->specific_params.rx_params.pcd_fqs_count; } static void set_tx_dflt_cfg(struct fman_port *port, @@ -1398,6 +1406,24 @@ err_port_cfg: EXPORT_SYMBOL(fman_port_config); /** + * fman_port_use_kg_hash + * port: A pointer to a FM Port module. + * Sets the HW KeyGen or the BMI as HW Parser next engine, enabling + * or bypassing the KeyGen hashing of Rx traffic + */ +void fman_port_use_kg_hash(struct fman_port *port, bool enable) +{ + if (enable) + /* After the Parser frames go to KeyGen */ + iowrite32be(NIA_ENG_HWK, &port->bmi_regs->rx.fmbm_rfpne); + else + /* After the Parser frames go to BMI */ + iowrite32be(NIA_ENG_BMI | NIA_BMI_AC_ENQ_FRAME, + &port->bmi_regs->rx.fmbm_rfpne); +} +EXPORT_SYMBOL(fman_port_use_kg_hash); + +/** * fman_port_init * port: A pointer to a FM Port module. * Initializes the FM PORT module by defining the software structure and @@ -1407,9 +1433,10 @@ EXPORT_SYMBOL(fman_port_config); */ int fman_port_init(struct fman_port *port) { + struct fman_port_init_params params; + struct fman_keygen *keygen; struct fman_port_cfg *cfg; int err; - struct fman_port_init_params params; if (is_init_done(port->cfg)) return -EINVAL; @@ -1472,6 +1499,17 @@ int fman_port_init(struct fman_port *port) if (err) return err; + if (port->cfg->pcd_fqs_count) { + keygen = port->dts_params.fman->keygen; + err = keygen_port_hashing_init(keygen, port->port_id, + port->cfg->pcd_base_fqid, + port->cfg->pcd_fqs_count); + if (err) + return err; + + fman_port_use_kg_hash(port, true); + } + kfree(port->cfg); port->cfg = NULL; @@ -1682,6 +1720,17 @@ u32 fman_port_get_qman_channel_id(struct fman_port *port) } EXPORT_SYMBOL(fman_port_get_qman_channel_id); +int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset) +{ + if (port->buffer_offsets.hash_result_offset == ILLEGAL_BASE) + return -EINVAL; + + *offset = port->buffer_offsets.hash_result_offset; + + return 0; +} +EXPORT_SYMBOL(fman_port_get_hash_result_offset); + static int fman_port_probe(struct platform_device *of_dev) { struct fman_port *port; @@ -1720,8 +1769,8 @@ static int fman_port_probe(struct platform_device *of_dev) err = of_property_read_u32(port_node, "cell-index", &val); if (err) { - dev_err(port->dev, "%s: reading cell-index for %s failed\n", - __func__, port_node->full_name); + dev_err(port->dev, "%s: reading cell-index for %pOF failed\n", + __func__, port_node); err = -EINVAL; goto return_err; } diff --git a/drivers/net/ethernet/freescale/fman/fman_port.h b/drivers/net/ethernet/freescale/fman/fman_port.h index 8ba901737048..e86ca6a34e4e 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.h +++ b/drivers/net/ethernet/freescale/fman/fman_port.h @@ -100,6 +100,9 @@ struct fman_port; struct fman_port_rx_params { u32 err_fqid; /* Error Queue Id. */ u32 dflt_fqid; /* Default Queue Id. */ + u32 pcd_base_fqid; /* PCD base Queue Id. */ + u32 pcd_fqs_count; /* Number of PCD FQs. */ + /* Which external buffer pools are used * (up to FMAN_PORT_MAX_EXT_POOLS_NUM), and their sizes. */ @@ -134,6 +137,8 @@ struct fman_port_params { int fman_port_config(struct fman_port *port, struct fman_port_params *params); +void fman_port_use_kg_hash(struct fman_port *port, bool enable); + int fman_port_init(struct fman_port *port); int fman_port_cfg_buf_prefix_content(struct fman_port *port, @@ -146,6 +151,8 @@ int fman_port_enable(struct fman_port *port); u32 fman_port_get_qman_channel_id(struct fman_port *port); +int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset); + struct fman_port *fman_port_bind(struct device *dev); #endif /* __FMAN_PORT_H */ diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 1c7da16ad0ff..387eb4a88b72 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -700,8 +700,8 @@ static int mac_probe(struct platform_device *_of_dev) priv->internal_phy_node = of_parse_phandle(mac_node, "pcsphy-handle", 0); } else { - dev_err(dev, "MAC node (%s) contains unsupported MAC\n", - mac_node->full_name); + dev_err(dev, "MAC node (%pOF) contains unsupported MAC\n", + mac_node); err = -EINVAL; goto _return; } @@ -714,16 +714,15 @@ static int mac_probe(struct platform_device *_of_dev) /* Get the FM node */ dev_node = of_get_parent(mac_node); if (!dev_node) { - dev_err(dev, "of_get_parent(%s) failed\n", - mac_node->full_name); + dev_err(dev, "of_get_parent(%pOF) failed\n", + mac_node); err = -EINVAL; goto _return_dev_set_drvdata; } of_dev = of_find_device_by_node(dev_node); if (!of_dev) { - dev_err(dev, "of_find_device_by_node(%s) failed\n", - dev_node->full_name); + dev_err(dev, "of_find_device_by_node(%pOF) failed\n", dev_node); err = -EINVAL; goto _return_of_node_put; } @@ -731,8 +730,7 @@ static int mac_probe(struct platform_device *_of_dev) /* Get the FMan cell-index */ err = of_property_read_u32(dev_node, "cell-index", &val); if (err) { - dev_err(dev, "failed to read cell-index for %s\n", - dev_node->full_name); + dev_err(dev, "failed to read cell-index for %pOF\n", dev_node); err = -EINVAL; goto _return_of_node_put; } @@ -741,7 +739,7 @@ static int mac_probe(struct platform_device *_of_dev) priv->fman = fman_bind(&of_dev->dev); if (!priv->fman) { - dev_err(dev, "fman_bind(%s) failed\n", dev_node->full_name); + dev_err(dev, "fman_bind(%pOF) failed\n", dev_node); err = -ENODEV; goto _return_of_node_put; } @@ -751,8 +749,8 @@ static int mac_probe(struct platform_device *_of_dev) /* Get the address of the memory mapped registers */ err = of_address_to_resource(mac_node, 0, &res); if (err < 0) { - dev_err(dev, "of_address_to_resource(%s) = %d\n", - mac_node->full_name, err); + dev_err(dev, "of_address_to_resource(%pOF) = %d\n", + mac_node, err); goto _return_dev_set_drvdata; } @@ -786,8 +784,7 @@ static int mac_probe(struct platform_device *_of_dev) /* Get the cell-index */ err = of_property_read_u32(mac_node, "cell-index", &val); if (err) { - dev_err(dev, "failed to read cell-index for %s\n", - mac_node->full_name); + dev_err(dev, "failed to read cell-index for %pOF\n", mac_node); err = -EINVAL; goto _return_dev_set_drvdata; } @@ -796,8 +793,7 @@ static int mac_probe(struct platform_device *_of_dev) /* Get the MAC address */ mac_addr = of_get_mac_address(mac_node); if (!mac_addr) { - dev_err(dev, "of_get_mac_address(%s) failed\n", - mac_node->full_name); + dev_err(dev, "of_get_mac_address(%pOF) failed\n", mac_node); err = -EINVAL; goto _return_dev_set_drvdata; } @@ -806,15 +802,15 @@ static int mac_probe(struct platform_device *_of_dev) /* Get the port handles */ nph = of_count_phandle_with_args(mac_node, "fsl,fman-ports", NULL); if (unlikely(nph < 0)) { - dev_err(dev, "of_count_phandle_with_args(%s, fsl,fman-ports) failed\n", - mac_node->full_name); + dev_err(dev, "of_count_phandle_with_args(%pOF, fsl,fman-ports) failed\n", + mac_node); err = nph; goto _return_dev_set_drvdata; } if (nph != ARRAY_SIZE(mac_dev->port)) { - dev_err(dev, "Not supported number of fman-ports handles of mac node %s from device tree\n", - mac_node->full_name); + dev_err(dev, "Not supported number of fman-ports handles of mac node %pOF from device tree\n", + mac_node); err = -EINVAL; goto _return_dev_set_drvdata; } @@ -823,24 +819,24 @@ static int mac_probe(struct platform_device *_of_dev) /* Find the port node */ dev_node = of_parse_phandle(mac_node, "fsl,fman-ports", i); if (!dev_node) { - dev_err(dev, "of_parse_phandle(%s, fsl,fman-ports) failed\n", - mac_node->full_name); + dev_err(dev, "of_parse_phandle(%pOF, fsl,fman-ports) failed\n", + mac_node); err = -EINVAL; goto _return_of_node_put; } of_dev = of_find_device_by_node(dev_node); if (!of_dev) { - dev_err(dev, "of_find_device_by_node(%s) failed\n", - dev_node->full_name); + dev_err(dev, "of_find_device_by_node(%pOF) failed\n", + dev_node); err = -EINVAL; goto _return_of_node_put; } mac_dev->port[i] = fman_port_bind(&of_dev->dev); if (!mac_dev->port[i]) { - dev_err(dev, "dev_get_drvdata(%s) failed\n", - dev_node->full_name); + dev_err(dev, "dev_get_drvdata(%pOF) failed\n", + dev_node); err = -EINVAL; goto _return_of_node_put; } @@ -851,8 +847,8 @@ static int mac_probe(struct platform_device *_of_dev) phy_if = of_get_phy_mode(mac_node); if (phy_if < 0) { dev_warn(dev, - "of_get_phy_mode() for %s failed. Defaulting to SGMII\n", - mac_node->full_name); + "of_get_phy_mode() for %pOF failed. Defaulting to SGMII\n", + mac_node); phy_if = PHY_INTERFACE_MODE_SGMII; } priv->phy_if = phy_if; diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c index 1f015edcca22..c8e5d889bd81 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c +++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c @@ -100,7 +100,7 @@ static inline void mdc(struct mdiobb_ctrl *ctrl, int what) in_be32(bitbang->dat); } -static struct mdiobb_ops bb_ops = { +static const struct mdiobb_ops bb_ops = { .owner = THIS_MODULE, .set_mdc = mdc, .set_mdio_dir = mdio_dir, diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index a10de1e9c157..80ad16acf0f1 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -267,8 +267,8 @@ static void ucc_configure(phys_addr_t start, phys_addr_t end) ret = of_address_to_resource(np, 0, &res); if (ret < 0) { - pr_debug("fsl-pq-mdio: no address range in node %s\n", - np->full_name); + pr_debug("fsl-pq-mdio: no address range in node %pOF\n", + np); continue; } @@ -280,8 +280,8 @@ static void ucc_configure(phys_addr_t start, phys_addr_t end) if (!iprop) { iprop = of_get_property(np, "device-id", NULL); if (!iprop) { - pr_debug("fsl-pq-mdio: no UCC ID in node %s\n", - np->full_name); + pr_debug("fsl-pq-mdio: no UCC ID in node %pOF\n", + np); continue; } } @@ -293,8 +293,8 @@ static void ucc_configure(phys_addr_t start, phys_addr_t end) * numbered from 1, not 0. */ if (ucc_set_qe_mux_mii_mng(id - 1) < 0) { - pr_debug("fsl-pq-mdio: invalid UCC ID in node %s\n", - np->full_name); + pr_debug("fsl-pq-mdio: invalid UCC ID in node %pOF\n", + np); continue; } @@ -442,8 +442,8 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) if (data->get_tbipa) { for_each_child_of_node(np, tbi) { if (strcmp(tbi->type, "tbi-phy") == 0) { - dev_dbg(&pdev->dev, "found TBI PHY node %s\n", - strrchr(tbi->full_name, '/') + 1); + dev_dbg(&pdev->dev, "found TBI PHY node %pOFP\n", + tbi); break; } } @@ -454,8 +454,8 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) if (!prop) { dev_err(&pdev->dev, - "missing 'reg' property in node %s\n", - tbi->full_name); + "missing 'reg' property in node %pOF\n", + tbi); err = -EBUSY; goto error; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index c4b4b0a1bbf0..5be52d89b182 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -3687,7 +3687,7 @@ static noinline void gfar_update_link_state(struct gfar_private *priv) u32 tempval1 = gfar_read(®s->maccfg1); u32 tempval = gfar_read(®s->maccfg2); u32 ecntrl = gfar_read(®s->ecntrl); - u32 tx_flow_oldval = (tempval & MACCFG1_TX_FLOW); + u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW); if (phydev->duplex != priv->oldduplex) { if (!(phydev->duplex)) diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c index 721be13081f9..544114281ea7 100644 --- a/drivers/net/ethernet/freescale/gianfar_ptp.c +++ b/drivers/net/ethernet/freescale/gianfar_ptp.c @@ -411,7 +411,7 @@ static int ptp_gianfar_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } -static struct ptp_clock_info ptp_gianfar_caps = { +static const struct ptp_clock_info ptp_gianfar_caps = { .owner = THIS_MODULE, .name = "gianfar clock", .max_adj = 512000, diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index d11287e11371..91c7bdb9b43c 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -76,4 +76,31 @@ config HNS_ENET This selects the general ethernet driver for HNS. This module make use of any HNS AE driver, such as HNS_DSAF +config HNS3 + tristate "Hisilicon Network Subsystem Support HNS3 (Framework)" + depends on PCI + ---help--- + This selects the framework support for Hisilicon Network Subsystem 3. + This layer facilitates clients like ENET, RoCE and user-space ethernet + drivers(like ODP)to register with HNAE devices and their associated + operations. + +config HNS3_HCLGE + tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support" + depends on PCI_MSI + depends on HNS3 + ---help--- + This selects the HNS3_HCLGE network acceleration engine & its hardware + compatibility layer. The engine would be used in Hisilicon hip08 family of + SoCs and further upcoming SoCs. + +config HNS3_ENET + tristate "Hisilicon HNS3 Ethernet Device Support" + depends on 64BIT && PCI + depends on HNS3 && HNS3_HCLGE + ---help--- + This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08 + family of SoCs. This module depends upon HNAE3 driver to access the HNAE3 + devices and their associated operations. + endif # NET_VENDOR_HISILICON diff --git a/drivers/net/ethernet/hisilicon/Makefile b/drivers/net/ethernet/hisilicon/Makefile index 8661695024dc..3828c435c18f 100644 --- a/drivers/net/ethernet/hisilicon/Makefile +++ b/drivers/net/ethernet/hisilicon/Makefile @@ -6,4 +6,5 @@ obj-$(CONFIG_HIX5HD2_GMAC) += hix5hd2_gmac.o obj-$(CONFIG_HIP04_ETH) += hip04_eth.o obj-$(CONFIG_HNS_MDIO) += hns_mdio.o obj-$(CONFIG_HNS) += hns/ +obj-$(CONFIG_HNS3) += hns3/ obj-$(CONFIG_HISI_FEMAC) += hisi_femac.o diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 9d9b6e6dd988..a051e582d541 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -202,6 +202,7 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags) ring->q = q; ring->flags = flags; spin_lock_init(&ring->lock); + ring->coal_param = q->handle->coal_param; assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr); /* not matter for tx or rx ring, the ntc and ntc start from 0 */ diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index 7ba653af19cb..3e62692af011 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -89,6 +89,10 @@ do { \ #define RCB_RING_NAME_LEN 16 +#define HNAE_LOWEST_LATENCY_COAL_PARAM 30 +#define HNAE_LOW_LATENCY_COAL_PARAM 80 +#define HNAE_BULK_LATENCY_COAL_PARAM 150 + enum hnae_led_state { HNAE_LED_INACTIVE, HNAE_LED_ACTIVE, @@ -292,6 +296,12 @@ struct hnae_ring { int flags; /* ring attribute */ int irq_init_flag; + + /* total rx bytes after last rx rate calucated */ + u64 coal_last_rx_bytes; + unsigned long coal_last_jiffies; + u32 coal_param; + u32 coal_rx_rate; /* rx rate in MB */ }; #define ring_ptr_move_fw(ring, p) \ @@ -548,8 +558,13 @@ struct hnae_handle { u32 if_support; int q_num; int vf_id; + unsigned long coal_last_jiffies; + u32 coal_param; /* self adapt coalesce param */ + /* the ring index of last ring that set coal param */ + u32 coal_ring_idx; u32 eport_id; u32 dport_id; /* v2 tx bd should fill the dport_id */ + bool coal_adapt_en; enum hnae_port_type port_type; enum hnae_media_type media_type; struct list_head node; /* list to hnae_ae_dev->handle_list */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index a37166ee577b..bd68379d2bea 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -99,6 +99,7 @@ struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, ae_handle->owner_dev = dsaf_dev->dev; ae_handle->dev = dev; ae_handle->q_num = qnum_per_vf; + ae_handle->coal_param = HNAE_LOWEST_LATENCY_COAL_PARAM; /* find ring pair, and set vf id*/ for (ae_handle->vf_id = 0; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 3987699f8fe6..36520634c96a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -812,6 +812,113 @@ static int hns_desc_unused(struct hnae_ring *ring) return ((ntc >= ntu) ? 0 : ring->desc_num) + ntc - ntu; } +#define HNS_LOWEST_LATENCY_RATE 27 /* 27 MB/s */ +#define HNS_LOW_LATENCY_RATE 80 /* 80 MB/s */ + +#define HNS_COAL_BDNUM 3 + +static u32 hns_coal_rx_bdnum(struct hnae_ring *ring) +{ + bool coal_enable = ring->q->handle->coal_adapt_en; + + if (coal_enable && + ring->coal_last_rx_bytes > HNS_LOWEST_LATENCY_RATE) + return HNS_COAL_BDNUM; + else + return 0; +} + +static void hns_update_rx_rate(struct hnae_ring *ring) +{ + bool coal_enable = ring->q->handle->coal_adapt_en; + u32 time_passed_ms; + u64 total_bytes; + + if (!coal_enable || + time_before(jiffies, ring->coal_last_jiffies + (HZ >> 4))) + return; + + /* ring->stats.rx_bytes overflowed */ + if (ring->coal_last_rx_bytes > ring->stats.rx_bytes) { + ring->coal_last_rx_bytes = ring->stats.rx_bytes; + ring->coal_last_jiffies = jiffies; + return; + } + + total_bytes = ring->stats.rx_bytes - ring->coal_last_rx_bytes; + time_passed_ms = jiffies_to_msecs(jiffies - ring->coal_last_jiffies); + do_div(total_bytes, time_passed_ms); + ring->coal_rx_rate = total_bytes >> 10; + + ring->coal_last_rx_bytes = ring->stats.rx_bytes; + ring->coal_last_jiffies = jiffies; +} + +/** + * smooth_alg - smoothing algrithm for adjusting coalesce parameter + **/ +static u32 smooth_alg(u32 new_param, u32 old_param) +{ + u32 gap = (new_param > old_param) ? new_param - old_param + : old_param - new_param; + + if (gap > 8) + gap >>= 3; + + if (new_param > old_param) + return old_param + gap; + else + return old_param - gap; +} + +/** + * hns_nic_adp_coalesce - self adapte coalesce according to rx rate + * @ring_data: pointer to hns_nic_ring_data + **/ +static void hns_nic_adpt_coalesce(struct hns_nic_ring_data *ring_data) +{ + struct hnae_ring *ring = ring_data->ring; + struct hnae_handle *handle = ring->q->handle; + u32 new_coal_param, old_coal_param = ring->coal_param; + + if (ring->coal_rx_rate < HNS_LOWEST_LATENCY_RATE) + new_coal_param = HNAE_LOWEST_LATENCY_COAL_PARAM; + else if (ring->coal_rx_rate < HNS_LOW_LATENCY_RATE) + new_coal_param = HNAE_LOW_LATENCY_COAL_PARAM; + else + new_coal_param = HNAE_BULK_LATENCY_COAL_PARAM; + + if (new_coal_param == old_coal_param && + new_coal_param == handle->coal_param) + return; + + new_coal_param = smooth_alg(new_coal_param, old_coal_param); + ring->coal_param = new_coal_param; + + /** + * Because all ring in one port has one coalesce param, when one ring + * calculate its own coalesce param, it cannot write to hardware at + * once. There are three conditions as follows: + * 1. current ring's coalesce param is larger than the hardware. + * 2. or ring which adapt last time can change again. + * 3. timeout. + */ + if (new_coal_param == handle->coal_param) { + handle->coal_last_jiffies = jiffies; + handle->coal_ring_idx = ring_data->queue_index; + } else if (new_coal_param > handle->coal_param || + handle->coal_ring_idx == ring_data->queue_index || + time_after(jiffies, handle->coal_last_jiffies + (HZ >> 4))) { + handle->dev->ops->set_coalesce_usecs(handle, + new_coal_param); + handle->dev->ops->set_coalesce_frames(handle, + 1, new_coal_param); + handle->coal_param = new_coal_param; + handle->coal_ring_idx = ring_data->queue_index; + handle->coal_last_jiffies = jiffies; + } +} + static int hns_nic_rx_poll_one(struct hns_nic_ring_data *ring_data, int budget, void *v) { @@ -868,20 +975,27 @@ static bool hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data) { struct hnae_ring *ring = ring_data->ring; int num = 0; + bool rx_stopped; - ring_data->ring->q->handle->dev->ops->toggle_ring_irq(ring, 0); + hns_update_rx_rate(ring); /* for hardware bug fixed */ + ring_data->ring->q->handle->dev->ops->toggle_ring_irq(ring, 0); num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM); - if (num > 0) { + if (num <= hns_coal_rx_bdnum(ring)) { + if (ring->q->handle->coal_adapt_en) + hns_nic_adpt_coalesce(ring_data); + + rx_stopped = true; + } else { ring_data->ring->q->handle->dev->ops->toggle_ring_irq( ring_data->ring, 1); - return false; - } else { - return true; + rx_stopped = false; } + + return rx_stopped; } static bool hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data) @@ -889,12 +1003,17 @@ static bool hns_nic_rx_fini_pro_v2(struct hns_nic_ring_data *ring_data) struct hnae_ring *ring = ring_data->ring; int num; + hns_update_rx_rate(ring); num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM); - if (!num) + if (num <= hns_coal_rx_bdnum(ring)) { + if (ring->q->handle->coal_adapt_en) + hns_nic_adpt_coalesce(ring_data); + return true; - else - return false; + } + + return false; } static inline void hns_nic_reclaim_one_desc(struct hnae_ring *ring, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h index 9cb4c7884201..26e9afcbdd50 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h @@ -38,7 +38,7 @@ struct hns_nic_ring_data { struct hnae_ring *ring; struct napi_struct napi; cpumask_t mask; /* affinity mask */ - int queue_index; + u32 queue_index; int (*poll_one)(struct hns_nic_ring_data *, int, void *); void (*ex_process)(struct hns_nic_ring_data *, struct sk_buff *); bool (*fini_process)(struct hns_nic_ring_data *); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index a8db27e86a11..7ea7f8a4aa2a 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -595,7 +595,7 @@ static void hns_nic_self_test(struct net_device *ndev, set_bit(NIC_STATE_TESTING, &priv->state); if (if_running) - (void)dev_close(ndev); + dev_close(ndev); for (i = 0; i < SELF_TEST_TPYE_NUM; i++) { if (!st_param[i][1]) @@ -735,8 +735,8 @@ static int hns_get_coalesce(struct net_device *net_dev, ops = priv->ae_handle->dev->ops; - ec->use_adaptive_rx_coalesce = 1; - ec->use_adaptive_tx_coalesce = 1; + ec->use_adaptive_rx_coalesce = priv->ae_handle->coal_adapt_en; + ec->use_adaptive_tx_coalesce = priv->ae_handle->coal_adapt_en; if ((!ops->get_coalesce_usecs) || (!ops->get_max_coalesced_frames)) @@ -787,6 +787,9 @@ static int hns_set_coalesce(struct net_device *net_dev, (!ops->set_coalesce_frames)) return -ESRCH; + if (ec->use_adaptive_rx_coalesce != priv->ae_handle->coal_adapt_en) + priv->ae_handle->coal_adapt_en = ec->use_adaptive_rx_coalesce; + rc1 = ops->set_coalesce_usecs(priv->ae_handle, ec->rx_coalesce_usecs); diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile new file mode 100644 index 000000000000..a9349e1f3e51 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the HISILICON network device drivers. +# + +obj-$(CONFIG_HNS3) += hns3pf/ + +obj-$(CONFIG_HNS3) += hnae3.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c new file mode 100644 index 000000000000..59efbd605416 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -0,0 +1,300 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include "hnae3.h" + +static LIST_HEAD(hnae3_ae_algo_list); +static LIST_HEAD(hnae3_client_list); +static LIST_HEAD(hnae3_ae_dev_list); + +/* we are keeping things simple and using single lock for all the + * list. This is a non-critical code so other updations, if happen + * in parallel, can wait. + */ +static DEFINE_MUTEX(hnae3_common_lock); + +static bool hnae3_client_match(enum hnae3_client_type client_type, + enum hnae3_dev_type dev_type) +{ + if ((dev_type == HNAE3_DEV_KNIC) && (client_type == HNAE3_CLIENT_KNIC || + client_type == HNAE3_CLIENT_ROCE)) + return true; + + if (dev_type == HNAE3_DEV_UNIC && client_type == HNAE3_CLIENT_UNIC) + return true; + + return false; +} + +static int hnae3_match_n_instantiate(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev, + bool is_reg, bool *matched) +{ + int ret; + + *matched = false; + + /* check if this client matches the type of ae_dev */ + if (!(hnae3_client_match(client->type, ae_dev->dev_type) && + hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) { + return 0; + } + /* there is a match of client and dev */ + *matched = true; + + /* now, (un-)instantiate client by calling lower layer */ + if (is_reg) { + ret = ae_dev->ops->init_client_instance(client, ae_dev); + if (ret) + dev_err(&ae_dev->pdev->dev, + "fail to instantiate client\n"); + return ret; + } + + ae_dev->ops->uninit_client_instance(client, ae_dev); + return 0; +} + +int hnae3_register_client(struct hnae3_client *client) +{ + struct hnae3_client *client_tmp; + struct hnae3_ae_dev *ae_dev; + bool matched; + int ret = 0; + + mutex_lock(&hnae3_common_lock); + /* one system should only have one client for every type */ + list_for_each_entry(client_tmp, &hnae3_client_list, node) { + if (client_tmp->type == client->type) + goto exit; + } + + list_add_tail(&client->node, &hnae3_client_list); + + /* initialize the client on every matched port */ + list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { + /* if the client could not be initialized on current port, for + * any error reasons, move on to next available port + */ + ret = hnae3_match_n_instantiate(client, ae_dev, true, &matched); + if (ret) + dev_err(&ae_dev->pdev->dev, + "match and instantiation failed for port\n"); + } + +exit: + mutex_unlock(&hnae3_common_lock); + + return ret; +} +EXPORT_SYMBOL(hnae3_register_client); + +void hnae3_unregister_client(struct hnae3_client *client) +{ + struct hnae3_ae_dev *ae_dev; + bool matched; + + mutex_lock(&hnae3_common_lock); + /* un-initialize the client on every matched port */ + list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { + hnae3_match_n_instantiate(client, ae_dev, false, &matched); + } + + list_del(&client->node); + mutex_unlock(&hnae3_common_lock); +} +EXPORT_SYMBOL(hnae3_unregister_client); + +/* hnae3_register_ae_algo - register a AE algorithm to hnae3 framework + * @ae_algo: AE algorithm + * NOTE: the duplicated name will not be checked + */ +int hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) +{ + const struct pci_device_id *id; + struct hnae3_ae_dev *ae_dev; + struct hnae3_client *client; + bool matched; + int ret = 0; + + mutex_lock(&hnae3_common_lock); + + list_add_tail(&ae_algo->node, &hnae3_ae_algo_list); + + /* Check if this algo/ops matches the list of ae_devs */ + list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { + id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); + if (!id) + continue; + + /* ae_dev init should set flag */ + ae_dev->ops = ae_algo->ops; + ret = ae_algo->ops->init_ae_dev(ae_dev); + if (ret) { + dev_err(&ae_dev->pdev->dev, "init ae_dev error.\n"); + continue; + } + + hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); + + /* check the client list for the match with this ae_dev type and + * initialize the figure out client instance + */ + list_for_each_entry(client, &hnae3_client_list, node) { + ret = hnae3_match_n_instantiate(client, ae_dev, true, + &matched); + if (ret) + dev_err(&ae_dev->pdev->dev, + "match and instantiation failed\n"); + if (matched) + break; + } + } + + mutex_unlock(&hnae3_common_lock); + + return ret; +} +EXPORT_SYMBOL(hnae3_register_ae_algo); + +/* hnae3_unregister_ae_algo - unregisters a AE algorithm + * @ae_algo: the AE algorithm to unregister + */ +void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo) +{ + const struct pci_device_id *id; + struct hnae3_ae_dev *ae_dev; + struct hnae3_client *client; + bool matched; + + mutex_lock(&hnae3_common_lock); + /* Check if there are matched ae_dev */ + list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { + id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); + if (!id) + continue; + + /* check the client list for the match with this ae_dev type and + * un-initialize the figure out client instance + */ + list_for_each_entry(client, &hnae3_client_list, node) { + hnae3_match_n_instantiate(client, ae_dev, false, + &matched); + if (matched) + break; + } + + ae_algo->ops->uninit_ae_dev(ae_dev); + hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); + } + + list_del(&ae_algo->node); + mutex_unlock(&hnae3_common_lock); +} +EXPORT_SYMBOL(hnae3_unregister_ae_algo); + +/* hnae3_register_ae_dev - registers a AE device to hnae3 framework + * @ae_dev: the AE device + * NOTE: the duplicated name will not be checked + */ +int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) +{ + const struct pci_device_id *id; + struct hnae3_ae_algo *ae_algo; + struct hnae3_client *client; + bool matched; + int ret = 0; + + mutex_lock(&hnae3_common_lock); + list_add_tail(&ae_dev->node, &hnae3_ae_dev_list); + + /* Check if there are matched ae_algo */ + list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) { + id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); + if (!id) + continue; + + ae_dev->ops = ae_algo->ops; + + if (!ae_dev->ops) { + dev_err(&ae_dev->pdev->dev, "ae_dev ops are null\n"); + goto out_err; + } + + /* ae_dev init should set flag */ + ret = ae_dev->ops->init_ae_dev(ae_dev); + if (ret) { + dev_err(&ae_dev->pdev->dev, "init ae_dev error\n"); + goto out_err; + } + + hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1); + break; + } + + /* check the client list for the match with this ae_dev type and + * initialize the figure out client instance + */ + list_for_each_entry(client, &hnae3_client_list, node) { + ret = hnae3_match_n_instantiate(client, ae_dev, true, + &matched); + if (ret) + dev_err(&ae_dev->pdev->dev, + "match and instantiation failed\n"); + if (matched) + break; + } + +out_err: + mutex_unlock(&hnae3_common_lock); + + return ret; +} +EXPORT_SYMBOL(hnae3_register_ae_dev); + +/* hnae3_unregister_ae_dev - unregisters a AE device + * @ae_dev: the AE device to unregister + */ +void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev) +{ + const struct pci_device_id *id; + struct hnae3_ae_algo *ae_algo; + struct hnae3_client *client; + bool matched; + + mutex_lock(&hnae3_common_lock); + /* Check if there are matched ae_algo */ + list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) { + id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev); + if (!id) + continue; + + list_for_each_entry(client, &hnae3_client_list, node) { + hnae3_match_n_instantiate(client, ae_dev, false, + &matched); + if (matched) + break; + } + + ae_algo->ops->uninit_ae_dev(ae_dev); + hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0); + } + + list_del(&ae_dev->node); + mutex_unlock(&hnae3_common_lock); +} +EXPORT_SYMBOL(hnae3_unregister_ae_dev); + +MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("HNAE3(Hisilicon Network Acceleration Engine) Framework"); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h new file mode 100644 index 000000000000..b2f28ae81273 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -0,0 +1,444 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HNAE3_H +#define __HNAE3_H + +/* Names used in this framework: + * ae handle (handle): + * a set of queues provided by AE + * ring buffer queue (rbq): + * the channel between upper layer and the AE, can do tx and rx + * ring: + * a tx or rx channel within a rbq + * ring description (desc): + * an element in the ring with packet information + * buffer: + * a memory region referred by desc with the full packet payload + * + * "num" means a static number set as a parameter, "count" mean a dynamic + * number set while running + * "cb" means control block + */ + +#include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/types.h> + +/* Device IDs */ +#define HNAE3_DEV_ID_GE 0xA220 +#define HNAE3_DEV_ID_25GE 0xA221 +#define HNAE3_DEV_ID_25GE_RDMA 0xA222 +#define HNAE3_DEV_ID_25GE_RDMA_MACSEC 0xA223 +#define HNAE3_DEV_ID_50GE_RDMA 0xA224 +#define HNAE3_DEV_ID_50GE_RDMA_MACSEC 0xA225 +#define HNAE3_DEV_ID_100G_RDMA_MACSEC 0xA226 +#define HNAE3_DEV_ID_100G_VF 0xA22E +#define HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF 0xA22F + +#define HNAE3_CLASS_NAME_SIZE 16 + +#define HNAE3_DEV_INITED_B 0x0 +#define HNAE_DEV_SUPPORT_ROCE_B 0x1 + +#define ring_ptr_move_fw(ring, p) \ + ((ring)->p = ((ring)->p + 1) % (ring)->desc_num) +#define ring_ptr_move_bw(ring, p) \ + ((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num) + +enum hns_desc_type { + DESC_TYPE_SKB, + DESC_TYPE_PAGE, +}; + +struct hnae3_handle; + +struct hnae3_queue { + void __iomem *io_base; + struct hnae3_ae_algo *ae_algo; + struct hnae3_handle *handle; + int tqp_index; /* index in a handle */ + u32 buf_size; /* size for hnae_desc->addr, preset by AE */ + u16 desc_num; /* total number of desc */ +}; + +/*hnae3 loop mode*/ +enum hnae3_loop { + HNAE3_MAC_INTER_LOOP_MAC, + HNAE3_MAC_INTER_LOOP_SERDES, + HNAE3_MAC_INTER_LOOP_PHY, + HNAE3_MAC_LOOP_NONE, +}; + +enum hnae3_client_type { + HNAE3_CLIENT_KNIC, + HNAE3_CLIENT_UNIC, + HNAE3_CLIENT_ROCE, +}; + +enum hnae3_dev_type { + HNAE3_DEV_KNIC, + HNAE3_DEV_UNIC, +}; + +/* mac media type */ +enum hnae3_media_type { + HNAE3_MEDIA_TYPE_UNKNOWN, + HNAE3_MEDIA_TYPE_FIBER, + HNAE3_MEDIA_TYPE_COPPER, + HNAE3_MEDIA_TYPE_BACKPLANE, +}; + +struct hnae3_vector_info { + u8 __iomem *io_addr; + int vector; +}; + +#define HNAE3_RING_TYPE_B 0 +#define HNAE3_RING_TYPE_TX 0 +#define HNAE3_RING_TYPE_RX 1 + +struct hnae3_ring_chain_node { + struct hnae3_ring_chain_node *next; + u32 tqp_index; + u32 flag; +}; + +#define HNAE3_IS_TX_RING(node) \ + (((node)->flag & (1 << HNAE3_RING_TYPE_B)) == HNAE3_RING_TYPE_TX) + +struct hnae3_client_ops { + int (*init_instance)(struct hnae3_handle *handle); + void (*uninit_instance)(struct hnae3_handle *handle, bool reset); + void (*link_status_change)(struct hnae3_handle *handle, bool state); +}; + +#define HNAE3_CLIENT_NAME_LENGTH 16 +struct hnae3_client { + char name[HNAE3_CLIENT_NAME_LENGTH]; + u16 version; + unsigned long state; + enum hnae3_client_type type; + const struct hnae3_client_ops *ops; + struct list_head node; +}; + +struct hnae3_ae_dev { + struct pci_dev *pdev; + const struct hnae3_ae_ops *ops; + struct list_head node; + u32 flag; + enum hnae3_dev_type dev_type; + void *priv; +}; + +/* This struct defines the operation on the handle. + * + * init_ae_dev(): (mandatory) + * Get PF configure from pci_dev and initialize PF hardware + * uninit_ae_dev() + * Disable PF device and release PF resource + * register_client + * Register client to ae_dev + * unregister_client() + * Unregister client from ae_dev + * start() + * Enable the hardware + * stop() + * Disable the hardware + * get_status() + * Get the carrier state of the back channel of the handle, 1 for ok, 0 for + * non-ok + * get_ksettings_an_result() + * Get negotiation status,speed and duplex + * update_speed_duplex_h() + * Update hardware speed and duplex + * get_media_type() + * Get media type of MAC + * adjust_link() + * Adjust link status + * set_loopback() + * Set loopback + * set_promisc_mode + * Set promisc mode + * set_mtu() + * set mtu + * get_pauseparam() + * get tx and rx of pause frame use + * set_pauseparam() + * set tx and rx of pause frame use + * set_autoneg() + * set auto autonegotiation of pause frame use + * get_autoneg() + * get auto autonegotiation of pause frame use + * get_coalesce_usecs() + * get usecs to delay a TX interrupt after a packet is sent + * get_rx_max_coalesced_frames() + * get Maximum number of packets to be sent before a TX interrupt. + * set_coalesce_usecs() + * set usecs to delay a TX interrupt after a packet is sent + * set_coalesce_frames() + * set Maximum number of packets to be sent before a TX interrupt. + * get_mac_addr() + * get mac address + * set_mac_addr() + * set mac address + * add_uc_addr + * Add unicast addr to mac table + * rm_uc_addr + * Remove unicast addr from mac table + * set_mc_addr() + * Set multicast address + * add_mc_addr + * Add multicast address to mac table + * rm_mc_addr + * Remove multicast address from mac table + * update_stats() + * Update Old network device statistics + * get_ethtool_stats() + * Get ethtool network device statistics + * get_strings() + * Get a set of strings that describe the requested objects + * get_sset_count() + * Get number of strings that @get_strings will write + * update_led_status() + * Update the led status + * set_led_id() + * Set led id + * get_regs() + * Get regs dump + * get_regs_len() + * Get the len of the regs dump + * get_rss_key_size() + * Get rss key size + * get_rss_indir_size() + * Get rss indirection table size + * get_rss() + * Get rss table + * set_rss() + * Set rss table + * get_tc_size() + * Get tc size of handle + * get_vector() + * Get vector number and vector information + * map_ring_to_vector() + * Map rings to vector + * unmap_ring_from_vector() + * Unmap rings from vector + * add_tunnel_udp() + * Add tunnel information to hardware + * del_tunnel_udp() + * Delete tunnel information from hardware + * reset_queue() + * Reset queue + * get_fw_version() + * Get firmware version + * get_mdix_mode() + * Get media typr of phy + * set_vlan_filter() + * Set vlan filter config of Ports + * set_vf_vlan_filter() + * Set vlan filter config of vf + */ +struct hnae3_ae_ops { + int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev); + void (*uninit_ae_dev)(struct hnae3_ae_dev *ae_dev); + + int (*init_client_instance)(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev); + void (*uninit_client_instance)(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev); + int (*start)(struct hnae3_handle *handle); + void (*stop)(struct hnae3_handle *handle); + int (*get_status)(struct hnae3_handle *handle); + void (*get_ksettings_an_result)(struct hnae3_handle *handle, + u8 *auto_neg, u32 *speed, u8 *duplex); + + int (*update_speed_duplex_h)(struct hnae3_handle *handle); + int (*cfg_mac_speed_dup_h)(struct hnae3_handle *handle, int speed, + u8 duplex); + + void (*get_media_type)(struct hnae3_handle *handle, u8 *media_type); + void (*adjust_link)(struct hnae3_handle *handle, int speed, int duplex); + int (*set_loopback)(struct hnae3_handle *handle, + enum hnae3_loop loop_mode, bool en); + + void (*set_promisc_mode)(struct hnae3_handle *handle, u32 en); + int (*set_mtu)(struct hnae3_handle *handle, int new_mtu); + + void (*get_pauseparam)(struct hnae3_handle *handle, + u32 *auto_neg, u32 *rx_en, u32 *tx_en); + int (*set_pauseparam)(struct hnae3_handle *handle, + u32 auto_neg, u32 rx_en, u32 tx_en); + + int (*set_autoneg)(struct hnae3_handle *handle, bool enable); + int (*get_autoneg)(struct hnae3_handle *handle); + + void (*get_coalesce_usecs)(struct hnae3_handle *handle, + u32 *tx_usecs, u32 *rx_usecs); + void (*get_rx_max_coalesced_frames)(struct hnae3_handle *handle, + u32 *tx_frames, u32 *rx_frames); + int (*set_coalesce_usecs)(struct hnae3_handle *handle, u32 timeout); + int (*set_coalesce_frames)(struct hnae3_handle *handle, + u32 coalesce_frames); + void (*get_coalesce_range)(struct hnae3_handle *handle, + u32 *tx_frames_low, u32 *rx_frames_low, + u32 *tx_frames_high, u32 *rx_frames_high, + u32 *tx_usecs_low, u32 *rx_usecs_low, + u32 *tx_usecs_high, u32 *rx_usecs_high); + + void (*get_mac_addr)(struct hnae3_handle *handle, u8 *p); + int (*set_mac_addr)(struct hnae3_handle *handle, void *p); + int (*add_uc_addr)(struct hnae3_handle *handle, + const unsigned char *addr); + int (*rm_uc_addr)(struct hnae3_handle *handle, + const unsigned char *addr); + int (*set_mc_addr)(struct hnae3_handle *handle, void *addr); + int (*add_mc_addr)(struct hnae3_handle *handle, + const unsigned char *addr); + int (*rm_mc_addr)(struct hnae3_handle *handle, + const unsigned char *addr); + + void (*set_tso_stats)(struct hnae3_handle *handle, int enable); + void (*update_stats)(struct hnae3_handle *handle, + struct net_device_stats *net_stats); + void (*get_stats)(struct hnae3_handle *handle, u64 *data); + + void (*get_strings)(struct hnae3_handle *handle, + u32 stringset, u8 *data); + int (*get_sset_count)(struct hnae3_handle *handle, int stringset); + + void (*get_regs)(struct hnae3_handle *handle, void *data); + int (*get_regs_len)(struct hnae3_handle *handle); + + u32 (*get_rss_key_size)(struct hnae3_handle *handle); + u32 (*get_rss_indir_size)(struct hnae3_handle *handle); + int (*get_rss)(struct hnae3_handle *handle, u32 *indir, u8 *key, + u8 *hfunc); + int (*set_rss)(struct hnae3_handle *handle, const u32 *indir, + const u8 *key, const u8 hfunc); + + int (*get_tc_size)(struct hnae3_handle *handle); + + int (*get_vector)(struct hnae3_handle *handle, u16 vector_num, + struct hnae3_vector_info *vector_info); + int (*map_ring_to_vector)(struct hnae3_handle *handle, + int vector_num, + struct hnae3_ring_chain_node *vr_chain); + int (*unmap_ring_from_vector)(struct hnae3_handle *handle, + int vector_num, + struct hnae3_ring_chain_node *vr_chain); + + int (*add_tunnel_udp)(struct hnae3_handle *handle, u16 port_num); + int (*del_tunnel_udp)(struct hnae3_handle *handle, u16 port_num); + + void (*reset_queue)(struct hnae3_handle *handle, u16 queue_id); + u32 (*get_fw_version)(struct hnae3_handle *handle); + void (*get_mdix_mode)(struct hnae3_handle *handle, + u8 *tp_mdix_ctrl, u8 *tp_mdix); + + int (*set_vlan_filter)(struct hnae3_handle *handle, __be16 proto, + u16 vlan_id, bool is_kill); + int (*set_vf_vlan_filter)(struct hnae3_handle *handle, int vfid, + u16 vlan, u8 qos, __be16 proto); +}; + +struct hnae3_ae_algo { + const struct hnae3_ae_ops *ops; + struct list_head node; + char name[HNAE3_CLASS_NAME_SIZE]; + const struct pci_device_id *pdev_id_table; +}; + +#define HNAE3_INT_NAME_LEN (IFNAMSIZ + 16) +#define HNAE3_ITR_COUNTDOWN_START 100 + +struct hnae3_tc_info { + u16 tqp_offset; /* TQP offset from base TQP */ + u16 tqp_count; /* Total TQPs */ + u8 up; /* user priority */ + u8 tc; /* TC index */ + bool enable; /* If this TC is enable or not */ +}; + +#define HNAE3_MAX_TC 8 +struct hnae3_knic_private_info { + struct net_device *netdev; /* Set by KNIC client when init instance */ + u16 rss_size; /* Allocated RSS queues */ + u16 rx_buf_len; + u16 num_desc; + + u8 num_tc; /* Total number of enabled TCs */ + struct hnae3_tc_info tc_info[HNAE3_MAX_TC]; /* Idx of array is HW TC */ + + u16 num_tqps; /* total number of TQPs in this handle */ + struct hnae3_queue **tqp; /* array base of all TQPs in this instance */ +}; + +struct hnae3_roce_private_info { + struct net_device *netdev; + void __iomem *roce_io_base; + int base_vector; + int num_vectors; +}; + +struct hnae3_unic_private_info { + struct net_device *netdev; + u16 rx_buf_len; + u16 num_desc; + u16 num_tqps; /* total number of tqps in this handle */ + struct hnae3_queue **tqp; /* array base of all TQPs of this instance */ +}; + +#define HNAE3_SUPPORT_MAC_LOOPBACK 1 +#define HNAE3_SUPPORT_PHY_LOOPBACK 2 +#define HNAE3_SUPPORT_SERDES_LOOPBACK 4 + +struct hnae3_handle { + struct hnae3_client *client; + struct pci_dev *pdev; + void *priv; + struct hnae3_ae_algo *ae_algo; /* the class who provides this handle */ + u64 flags; /* Indicate the capabilities for this handle*/ + + union { + struct net_device *netdev; /* first member */ + struct hnae3_knic_private_info kinfo; + struct hnae3_unic_private_info uinfo; + struct hnae3_roce_private_info rinfo; + }; + + u32 numa_node_mask; /* for multi-chip support */ +}; + +#define hnae_set_field(origin, mask, shift, val) \ + do { \ + (origin) &= (~(mask)); \ + (origin) |= ((val) << (shift)) & (mask); \ + } while (0) +#define hnae_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift)) + +#define hnae_set_bit(origin, shift, val) \ + hnae_set_field((origin), (0x1 << (shift)), (shift), (val)) +#define hnae_get_bit(origin, shift) \ + hnae_get_field((origin), (0x1 << (shift)), (shift)) + +int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev); +void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev); + +void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo); +int hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo); + +void hnae3_unregister_client(struct hnae3_client *client); +int hnae3_register_client(struct hnae3_client *client); +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile new file mode 100644 index 000000000000..162e8a42acd0 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile @@ -0,0 +1,11 @@ +# +# Makefile for the HISILICON network device drivers. +# + +ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3 + +obj-$(CONFIG_HNS3_HCLGE) += hclge.o +hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o + +obj-$(CONFIG_HNS3_ENET) += hns3.o +hns3-objs = hns3_enet.o hns3_ethtool.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c new file mode 100644 index 000000000000..8b511e6e0ce9 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -0,0 +1,356 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/dma-mapping.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/dma-direction.h> +#include "hclge_cmd.h" +#include "hnae3.h" +#include "hclge_main.h" + +#define hclge_is_csq(ring) ((ring)->flag & HCLGE_TYPE_CSQ) +#define hclge_ring_to_dma_dir(ring) (hclge_is_csq(ring) ? \ + DMA_TO_DEVICE : DMA_FROM_DEVICE) +#define cmq_ring_to_dev(ring) (&(ring)->dev->pdev->dev) + +static int hclge_ring_space(struct hclge_cmq_ring *ring) +{ + int ntu = ring->next_to_use; + int ntc = ring->next_to_clean; + int used = (ntu - ntc + ring->desc_num) % ring->desc_num; + + return ring->desc_num - used - 1; +} + +static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring) +{ + int size = ring->desc_num * sizeof(struct hclge_desc); + + ring->desc = kzalloc(size, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc, + size, DMA_BIDIRECTIONAL); + if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) { + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; + return -ENOMEM; + } + + return 0; +} + +static void hclge_free_cmd_desc(struct hclge_cmq_ring *ring) +{ + dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr, + ring->desc_num * sizeof(ring->desc[0]), + DMA_BIDIRECTIONAL); + + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; +} + +static int hclge_init_cmd_queue(struct hclge_dev *hdev, int ring_type) +{ + struct hclge_hw *hw = &hdev->hw; + struct hclge_cmq_ring *ring = + (ring_type == HCLGE_TYPE_CSQ) ? &hw->cmq.csq : &hw->cmq.crq; + int ret; + + ring->flag = ring_type; + ring->dev = hdev; + + ret = hclge_alloc_cmd_desc(ring); + if (ret) { + dev_err(&hdev->pdev->dev, "descriptor %s alloc error %d\n", + (ring_type == HCLGE_TYPE_CSQ) ? "CSQ" : "CRQ", ret); + return ret; + } + + ring->next_to_clean = 0; + ring->next_to_use = 0; + + return 0; +} + +void hclge_cmd_setup_basic_desc(struct hclge_desc *desc, + enum hclge_opcode_type opcode, bool is_read) +{ + memset((void *)desc, 0, sizeof(struct hclge_desc)); + desc->opcode = cpu_to_le16(opcode); + desc->flag = cpu_to_le16(HCLGE_CMD_FLAG_NO_INTR | HCLGE_CMD_FLAG_IN); + + if (is_read) + desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR); + else + desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); +} + +static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring) +{ + dma_addr_t dma = ring->desc_dma_addr; + struct hclge_dev *hdev = ring->dev; + struct hclge_hw *hw = &hdev->hw; + + if (ring->flag == HCLGE_TYPE_CSQ) { + hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG, + (u32)dma); + hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, + (ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) | + HCLGE_NIC_CMQ_ENABLE); + hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0); + } else { + hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG, + (u32)dma); + hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG, + (ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) | + HCLGE_NIC_CMQ_ENABLE); + hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0); + hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0); + } +} + +static void hclge_cmd_init_regs(struct hclge_hw *hw) +{ + hclge_cmd_config_regs(&hw->cmq.csq); + hclge_cmd_config_regs(&hw->cmq.crq); +} + +static int hclge_cmd_csq_clean(struct hclge_hw *hw) +{ + struct hclge_cmq_ring *csq = &hw->cmq.csq; + u16 ntc = csq->next_to_clean; + struct hclge_desc *desc; + int clean = 0; + u32 head; + + desc = &csq->desc[ntc]; + head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG); + + while (head != ntc) { + memset(desc, 0, sizeof(*desc)); + ntc++; + if (ntc == csq->desc_num) + ntc = 0; + desc = &csq->desc[ntc]; + clean++; + } + csq->next_to_clean = ntc; + + return clean; +} + +static int hclge_cmd_csq_done(struct hclge_hw *hw) +{ + u32 head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG); + return head == hw->cmq.csq.next_to_use; +} + +static bool hclge_is_special_opcode(u16 opcode) +{ + u16 spec_opcode[3] = {0x0030, 0x0031, 0x0032}; + int i; + + for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) { + if (spec_opcode[i] == opcode) + return true; + } + + return false; +} + +/** + * hclge_cmd_send - send command to command queue + * @hw: pointer to the hw struct + * @desc: prefilled descriptor for describing the command + * @num : the number of descriptors to be sent + * + * This is the main send command for command queue, it + * sends the queue, cleans the queue, etc + **/ +int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) +{ + struct hclge_dev *hdev = (struct hclge_dev *)hw->back; + struct hclge_desc *desc_to_use; + bool complete = false; + u32 timeout = 0; + int handle = 0; + int retval = 0; + u16 opcode, desc_ret; + int ntc; + + spin_lock_bh(&hw->cmq.csq.lock); + + if (num > hclge_ring_space(&hw->cmq.csq)) { + spin_unlock_bh(&hw->cmq.csq.lock); + return -EBUSY; + } + + /** + * Record the location of desc in the ring for this time + * which will be use for hardware to write back + */ + ntc = hw->cmq.csq.next_to_use; + opcode = desc[0].opcode; + while (handle < num) { + desc_to_use = &hw->cmq.csq.desc[hw->cmq.csq.next_to_use]; + *desc_to_use = desc[handle]; + (hw->cmq.csq.next_to_use)++; + if (hw->cmq.csq.next_to_use == hw->cmq.csq.desc_num) + hw->cmq.csq.next_to_use = 0; + handle++; + } + + /* Write to hardware */ + hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, hw->cmq.csq.next_to_use); + + /** + * If the command is sync, wait for the firmware to write back, + * if multi descriptors to be sent, use the first one to check + */ + if (HCLGE_SEND_SYNC(desc->flag)) { + do { + if (hclge_cmd_csq_done(hw)) + break; + udelay(1); + timeout++; + } while (timeout < hw->cmq.tx_timeout); + } + + if (hclge_cmd_csq_done(hw)) { + complete = true; + handle = 0; + while (handle < num) { + /* Get the result of hardware write back */ + desc_to_use = &hw->cmq.csq.desc[ntc]; + desc[handle] = *desc_to_use; + pr_debug("Get cmd desc:\n"); + + if (likely(!hclge_is_special_opcode(opcode))) + desc_ret = desc[handle].retval; + else + desc_ret = desc[0].retval; + + if ((enum hclge_cmd_return_status)desc_ret == + HCLGE_CMD_EXEC_SUCCESS) + retval = 0; + else + retval = -EIO; + hw->cmq.last_status = (enum hclge_cmd_status)desc_ret; + ntc++; + handle++; + if (ntc == hw->cmq.csq.desc_num) + ntc = 0; + } + } + + if (!complete) + retval = -EAGAIN; + + /* Clean the command send queue */ + handle = hclge_cmd_csq_clean(hw); + if (handle != num) { + dev_warn(&hdev->pdev->dev, + "cleaned %d, need to clean %d\n", handle, num); + } + + spin_unlock_bh(&hw->cmq.csq.lock); + + return retval; +} + +enum hclge_cmd_status hclge_cmd_query_firmware_version(struct hclge_hw *hw, + u32 *version) +{ + struct hclge_query_version *resp; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FW_VER, 1); + resp = (struct hclge_query_version *)desc.data; + + ret = hclge_cmd_send(hw, &desc, 1); + if (!ret) + *version = le32_to_cpu(resp->firmware); + + return ret; +} + +int hclge_cmd_init(struct hclge_dev *hdev) +{ + u32 version; + int ret; + + /* Setup the queue entries for use cmd queue */ + hdev->hw.cmq.csq.desc_num = HCLGE_NIC_CMQ_DESC_NUM; + hdev->hw.cmq.crq.desc_num = HCLGE_NIC_CMQ_DESC_NUM; + + /* Setup the lock for command queue */ + spin_lock_init(&hdev->hw.cmq.csq.lock); + spin_lock_init(&hdev->hw.cmq.crq.lock); + + /* Setup Tx write back timeout */ + hdev->hw.cmq.tx_timeout = HCLGE_CMDQ_TX_TIMEOUT; + + /* Setup queue rings */ + ret = hclge_init_cmd_queue(hdev, HCLGE_TYPE_CSQ); + if (ret) { + dev_err(&hdev->pdev->dev, + "CSQ ring setup error %d\n", ret); + return ret; + } + + ret = hclge_init_cmd_queue(hdev, HCLGE_TYPE_CRQ); + if (ret) { + dev_err(&hdev->pdev->dev, + "CRQ ring setup error %d\n", ret); + goto err_csq; + } + + hclge_cmd_init_regs(&hdev->hw); + + ret = hclge_cmd_query_firmware_version(&hdev->hw, &version); + if (ret) { + dev_err(&hdev->pdev->dev, + "firmware version query failed %d\n", ret); + return ret; + } + hdev->fw_version = version; + + dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version); + + return 0; +err_csq: + hclge_free_cmd_desc(&hdev->hw.cmq.csq); + return ret; +} + +static void hclge_destroy_queue(struct hclge_cmq_ring *ring) +{ + spin_lock_bh(&ring->lock); + hclge_free_cmd_desc(ring); + spin_unlock_bh(&ring->lock); +} + +void hclge_destroy_cmd_queue(struct hclge_hw *hw) +{ + hclge_destroy_queue(&hw->cmq.csq); + hclge_destroy_queue(&hw->cmq.crq); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h new file mode 100644 index 000000000000..91ae0135ee50 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -0,0 +1,740 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HCLGE_CMD_H +#define __HCLGE_CMD_H +#include <linux/types.h> +#include <linux/io.h> + +#define HCLGE_CMDQ_TX_TIMEOUT 1000 + +struct hclge_dev; +struct hclge_desc { + __le16 opcode; + +#define HCLGE_CMDQ_RX_INVLD_B 0 +#define HCLGE_CMDQ_RX_OUTVLD_B 1 + + __le16 flag; + __le16 retval; + __le16 rsv; + __le32 data[6]; +}; + +struct hclge_desc_cb { + dma_addr_t dma; + void *va; + u32 length; +}; + +struct hclge_cmq_ring { + dma_addr_t desc_dma_addr; + struct hclge_desc *desc; + struct hclge_desc_cb *desc_cb; + struct hclge_dev *dev; + u32 head; + u32 tail; + + u16 buf_size; + u16 desc_num; + int next_to_use; + int next_to_clean; + u8 flag; + spinlock_t lock; /* Command queue lock */ +}; + +enum hclge_cmd_return_status { + HCLGE_CMD_EXEC_SUCCESS = 0, + HCLGE_CMD_NO_AUTH = 1, + HCLGE_CMD_NOT_EXEC = 2, + HCLGE_CMD_QUEUE_FULL = 3, +}; + +enum hclge_cmd_status { + HCLGE_STATUS_SUCCESS = 0, + HCLGE_ERR_CSQ_FULL = -1, + HCLGE_ERR_CSQ_TIMEOUT = -2, + HCLGE_ERR_CSQ_ERROR = -3, +}; + +struct hclge_cmq { + struct hclge_cmq_ring csq; + struct hclge_cmq_ring crq; + u16 tx_timeout; /* Tx timeout */ + enum hclge_cmd_status last_status; +}; + +#define HCLGE_CMD_FLAG_IN_VALID_SHIFT 0 +#define HCLGE_CMD_FLAG_OUT_VALID_SHIFT 1 +#define HCLGE_CMD_FLAG_NEXT_SHIFT 2 +#define HCLGE_CMD_FLAG_WR_OR_RD_SHIFT 3 +#define HCLGE_CMD_FLAG_NO_INTR_SHIFT 4 +#define HCLGE_CMD_FLAG_ERR_INTR_SHIFT 5 + +#define HCLGE_CMD_FLAG_IN BIT(HCLGE_CMD_FLAG_IN_VALID_SHIFT) +#define HCLGE_CMD_FLAG_OUT BIT(HCLGE_CMD_FLAG_OUT_VALID_SHIFT) +#define HCLGE_CMD_FLAG_NEXT BIT(HCLGE_CMD_FLAG_NEXT_SHIFT) +#define HCLGE_CMD_FLAG_WR BIT(HCLGE_CMD_FLAG_WR_OR_RD_SHIFT) +#define HCLGE_CMD_FLAG_NO_INTR BIT(HCLGE_CMD_FLAG_NO_INTR_SHIFT) +#define HCLGE_CMD_FLAG_ERR_INTR BIT(HCLGE_CMD_FLAG_ERR_INTR_SHIFT) + +enum hclge_opcode_type { + /* Generic command */ + HCLGE_OPC_QUERY_FW_VER = 0x0001, + HCLGE_OPC_CFG_RST_TRIGGER = 0x0020, + HCLGE_OPC_GBL_RST_STATUS = 0x0021, + HCLGE_OPC_QUERY_FUNC_STATUS = 0x0022, + HCLGE_OPC_QUERY_PF_RSRC = 0x0023, + HCLGE_OPC_QUERY_VF_RSRC = 0x0024, + HCLGE_OPC_GET_CFG_PARAM = 0x0025, + + HCLGE_OPC_STATS_64_BIT = 0x0030, + HCLGE_OPC_STATS_32_BIT = 0x0031, + HCLGE_OPC_STATS_MAC = 0x0032, + /* Device management command */ + + /* MAC commond */ + HCLGE_OPC_CONFIG_MAC_MODE = 0x0301, + HCLGE_OPC_CONFIG_AN_MODE = 0x0304, + HCLGE_OPC_QUERY_AN_RESULT = 0x0306, + HCLGE_OPC_QUERY_LINK_STATUS = 0x0307, + HCLGE_OPC_CONFIG_MAX_FRM_SIZE = 0x0308, + HCLGE_OPC_CONFIG_SPEED_DUP = 0x0309, + /* MACSEC command */ + + /* PFC/Pause CMD*/ + HCLGE_OPC_CFG_MAC_PAUSE_EN = 0x0701, + HCLGE_OPC_CFG_PFC_PAUSE_EN = 0x0702, + HCLGE_OPC_CFG_MAC_PARA = 0x0703, + HCLGE_OPC_CFG_PFC_PARA = 0x0704, + HCLGE_OPC_QUERY_MAC_TX_PKT_CNT = 0x0705, + HCLGE_OPC_QUERY_MAC_RX_PKT_CNT = 0x0706, + HCLGE_OPC_QUERY_PFC_TX_PKT_CNT = 0x0707, + HCLGE_OPC_QUERY_PFC_RX_PKT_CNT = 0x0708, + HCLGE_OPC_PRI_TO_TC_MAPPING = 0x0709, + HCLGE_OPC_QOS_MAP = 0x070A, + + /* ETS/scheduler commands */ + HCLGE_OPC_TM_PG_TO_PRI_LINK = 0x0804, + HCLGE_OPC_TM_QS_TO_PRI_LINK = 0x0805, + HCLGE_OPC_TM_NQ_TO_QS_LINK = 0x0806, + HCLGE_OPC_TM_RQ_TO_QS_LINK = 0x0807, + HCLGE_OPC_TM_PORT_WEIGHT = 0x0808, + HCLGE_OPC_TM_PG_WEIGHT = 0x0809, + HCLGE_OPC_TM_QS_WEIGHT = 0x080A, + HCLGE_OPC_TM_PRI_WEIGHT = 0x080B, + HCLGE_OPC_TM_PRI_C_SHAPPING = 0x080C, + HCLGE_OPC_TM_PRI_P_SHAPPING = 0x080D, + HCLGE_OPC_TM_PG_C_SHAPPING = 0x080E, + HCLGE_OPC_TM_PG_P_SHAPPING = 0x080F, + HCLGE_OPC_TM_PORT_SHAPPING = 0x0810, + HCLGE_OPC_TM_PG_SCH_MODE_CFG = 0x0812, + HCLGE_OPC_TM_PRI_SCH_MODE_CFG = 0x0813, + HCLGE_OPC_TM_QS_SCH_MODE_CFG = 0x0814, + HCLGE_OPC_TM_BP_TO_QSET_MAPPING = 0x0815, + + /* Packet buffer allocate command */ + HCLGE_OPC_TX_BUFF_ALLOC = 0x0901, + HCLGE_OPC_RX_PRIV_BUFF_ALLOC = 0x0902, + HCLGE_OPC_RX_PRIV_WL_ALLOC = 0x0903, + HCLGE_OPC_RX_COM_THRD_ALLOC = 0x0904, + HCLGE_OPC_RX_COM_WL_ALLOC = 0x0905, + HCLGE_OPC_RX_GBL_PKT_CNT = 0x0906, + + /* PTP command */ + /* TQP management command */ + HCLGE_OPC_SET_TQP_MAP = 0x0A01, + + /* TQP command */ + HCLGE_OPC_CFG_TX_QUEUE = 0x0B01, + HCLGE_OPC_QUERY_TX_POINTER = 0x0B02, + HCLGE_OPC_QUERY_TX_STATUS = 0x0B03, + HCLGE_OPC_CFG_RX_QUEUE = 0x0B11, + HCLGE_OPC_QUERY_RX_POINTER = 0x0B12, + HCLGE_OPC_QUERY_RX_STATUS = 0x0B13, + HCLGE_OPC_STASH_RX_QUEUE_LRO = 0x0B16, + HCLGE_OPC_CFG_RX_QUEUE_LRO = 0x0B17, + HCLGE_OPC_CFG_COM_TQP_QUEUE = 0x0B20, + HCLGE_OPC_RESET_TQP_QUEUE = 0x0B22, + + /* TSO cmd */ + HCLGE_OPC_TSO_GENERIC_CONFIG = 0x0C01, + + /* RSS cmd */ + HCLGE_OPC_RSS_GENERIC_CONFIG = 0x0D01, + HCLGE_OPC_RSS_INDIR_TABLE = 0x0D07, + HCLGE_OPC_RSS_TC_MODE = 0x0D08, + HCLGE_OPC_RSS_INPUT_TUPLE = 0x0D02, + + /* Promisuous mode command */ + HCLGE_OPC_CFG_PROMISC_MODE = 0x0E01, + + /* Interrupts cmd */ + HCLGE_OPC_ADD_RING_TO_VECTOR = 0x1503, + HCLGE_OPC_DEL_RING_TO_VECTOR = 0x1504, + + /* MAC command */ + HCLGE_OPC_MAC_VLAN_ADD = 0x1000, + HCLGE_OPC_MAC_VLAN_REMOVE = 0x1001, + HCLGE_OPC_MAC_VLAN_TYPE_ID = 0x1002, + HCLGE_OPC_MAC_VLAN_INSERT = 0x1003, + HCLGE_OPC_MAC_ETHTYPE_ADD = 0x1010, + HCLGE_OPC_MAC_ETHTYPE_REMOVE = 0x1011, + + /* Multicast linear table cmd */ + HCLGE_OPC_MTA_MAC_MODE_CFG = 0x1020, + HCLGE_OPC_MTA_MAC_FUNC_CFG = 0x1021, + HCLGE_OPC_MTA_TBL_ITEM_CFG = 0x1022, + HCLGE_OPC_MTA_TBL_ITEM_QUERY = 0x1023, + + /* VLAN command */ + HCLGE_OPC_VLAN_FILTER_CTRL = 0x1100, + HCLGE_OPC_VLAN_FILTER_PF_CFG = 0x1101, + HCLGE_OPC_VLAN_FILTER_VF_CFG = 0x1102, + + /* MDIO command */ + HCLGE_OPC_MDIO_CONFIG = 0x1900, + + /* QCN command */ + HCLGE_OPC_QCN_MOD_CFG = 0x1A01, + HCLGE_OPC_QCN_GRP_TMPLT_CFG = 0x1A02, + HCLGE_OPC_QCN_SHAPPING_IR_CFG = 0x1A03, + HCLGE_OPC_QCN_SHAPPING_BS_CFG = 0x1A04, + HCLGE_OPC_QCN_QSET_LINK_CFG = 0x1A05, + HCLGE_OPC_QCN_RP_STATUS_GET = 0x1A06, + HCLGE_OPC_QCN_AJUST_INIT = 0x1A07, + HCLGE_OPC_QCN_DFX_CNT_STATUS = 0x1A08, + + /* Mailbox cmd */ + HCLGEVF_OPC_MBX_PF_TO_VF = 0x2000, +}; + +#define HCLGE_TQP_REG_OFFSET 0x80000 +#define HCLGE_TQP_REG_SIZE 0x200 + +#define HCLGE_RCB_INIT_QUERY_TIMEOUT 10 +#define HCLGE_RCB_INIT_FLAG_EN_B 0 +#define HCLGE_RCB_INIT_FLAG_FINI_B 8 +struct hclge_config_rcb_init { + __le16 rcb_init_flag; + u8 rsv[22]; +}; + +struct hclge_tqp_map { + __le16 tqp_id; /* Absolute tqp id for in this pf */ + u8 tqp_vf; /* VF id */ +#define HCLGE_TQP_MAP_TYPE_PF 0 +#define HCLGE_TQP_MAP_TYPE_VF 1 +#define HCLGE_TQP_MAP_TYPE_B 0 +#define HCLGE_TQP_MAP_EN_B 1 + u8 tqp_flag; /* Indicate it's pf or vf tqp */ + __le16 tqp_vid; /* Virtual id in this pf/vf */ + u8 rsv[18]; +}; + +#define HCLGE_VECTOR_ELEMENTS_PER_CMD 11 + +enum hclge_int_type { + HCLGE_INT_TX, + HCLGE_INT_RX, + HCLGE_INT_EVENT, +}; + +struct hclge_ctrl_vector_chain { + u8 int_vector_id; + u8 int_cause_num; +#define HCLGE_INT_TYPE_S 0 +#define HCLGE_INT_TYPE_M 0x3 +#define HCLGE_TQP_ID_S 2 +#define HCLGE_TQP_ID_M (0x3fff << HCLGE_TQP_ID_S) + __le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD]; +}; + +#define HCLGE_TC_NUM 8 +#define HCLGE_TC0_PRI_BUF_EN_B 15 /* Bit 15 indicate enable or not */ +#define HCLGE_BUF_UNIT_S 7 /* Buf size is united by 128 bytes */ +struct hclge_tx_buff_alloc { + __le16 tx_pkt_buff[HCLGE_TC_NUM]; + u8 tx_buff_rsv[8]; +}; + +struct hclge_rx_priv_buff { + __le16 buf_num[HCLGE_TC_NUM]; + u8 rsv[8]; +}; + +struct hclge_query_version { + __le32 firmware; + __le32 firmware_rsv[5]; +}; + +#define HCLGE_RX_PRIV_EN_B 15 +#define HCLGE_TC_NUM_ONE_DESC 4 +struct hclge_priv_wl { + __le16 high; + __le16 low; +}; + +struct hclge_rx_priv_wl_buf { + struct hclge_priv_wl tc_wl[HCLGE_TC_NUM_ONE_DESC]; +}; + +struct hclge_rx_com_thrd { + struct hclge_priv_wl com_thrd[HCLGE_TC_NUM_ONE_DESC]; +}; + +struct hclge_rx_com_wl { + struct hclge_priv_wl com_wl; +}; + +struct hclge_waterline { + u32 low; + u32 high; +}; + +struct hclge_tc_thrd { + u32 low; + u32 high; +}; + +struct hclge_priv_buf { + struct hclge_waterline wl; /* Waterline for low and high*/ + u32 buf_size; /* TC private buffer size */ + u32 enable; /* Enable TC private buffer or not */ +}; + +#define HCLGE_MAX_TC_NUM 8 +struct hclge_shared_buf { + struct hclge_waterline self; + struct hclge_tc_thrd tc_thrd[HCLGE_MAX_TC_NUM]; + u32 buf_size; +}; + +#define HCLGE_RX_COM_WL_EN_B 15 +struct hclge_rx_com_wl_buf { + __le16 high_wl; + __le16 low_wl; + u8 rsv[20]; +}; + +#define HCLGE_RX_PKT_EN_B 15 +struct hclge_rx_pkt_buf { + __le16 high_pkt; + __le16 low_pkt; + u8 rsv[20]; +}; + +#define HCLGE_PF_STATE_DONE_B 0 +#define HCLGE_PF_STATE_MAIN_B 1 +#define HCLGE_PF_STATE_BOND_B 2 +#define HCLGE_PF_STATE_MAC_N_B 6 +#define HCLGE_PF_MAC_NUM_MASK 0x3 +#define HCLGE_PF_STATE_MAIN BIT(HCLGE_PF_STATE_MAIN_B) +#define HCLGE_PF_STATE_DONE BIT(HCLGE_PF_STATE_DONE_B) +struct hclge_func_status { + __le32 vf_rst_state[4]; + u8 pf_state; + u8 mac_id; + u8 rsv1; + u8 pf_cnt_in_mac; + u8 pf_num; + u8 vf_num; + u8 rsv[2]; +}; + +struct hclge_pf_res { + __le16 tqp_num; + __le16 buf_size; + __le16 msixcap_localid_ba_nic; + __le16 msixcap_localid_ba_rocee; +#define HCLGE_PF_VEC_NUM_S 0 +#define HCLGE_PF_VEC_NUM_M (0xff << HCLGE_PF_VEC_NUM_S) + __le16 pf_intr_vector_number; + __le16 pf_own_fun_number; + __le32 rsv[3]; +}; + +#define HCLGE_CFG_OFFSET_S 0 +#define HCLGE_CFG_OFFSET_M 0xfffff /* Byte (8-10.3) */ +#define HCLGE_CFG_RD_LEN_S 24 +#define HCLGE_CFG_RD_LEN_M (0xf << HCLGE_CFG_RD_LEN_S) +#define HCLGE_CFG_RD_LEN_BYTES 16 +#define HCLGE_CFG_RD_LEN_UNIT 4 + +#define HCLGE_CFG_VMDQ_S 0 +#define HCLGE_CFG_VMDQ_M (0xff << HCLGE_CFG_VMDQ_S) +#define HCLGE_CFG_TC_NUM_S 8 +#define HCLGE_CFG_TC_NUM_M (0xff << HCLGE_CFG_TC_NUM_S) +#define HCLGE_CFG_TQP_DESC_N_S 16 +#define HCLGE_CFG_TQP_DESC_N_M (0xffff << HCLGE_CFG_TQP_DESC_N_S) +#define HCLGE_CFG_PHY_ADDR_S 0 +#define HCLGE_CFG_PHY_ADDR_M (0x1f << HCLGE_CFG_PHY_ADDR_S) +#define HCLGE_CFG_MEDIA_TP_S 8 +#define HCLGE_CFG_MEDIA_TP_M (0xff << HCLGE_CFG_MEDIA_TP_S) +#define HCLGE_CFG_RX_BUF_LEN_S 16 +#define HCLGE_CFG_RX_BUF_LEN_M (0xffff << HCLGE_CFG_RX_BUF_LEN_S) +#define HCLGE_CFG_MAC_ADDR_H_S 0 +#define HCLGE_CFG_MAC_ADDR_H_M (0xffff << HCLGE_CFG_MAC_ADDR_H_S) +#define HCLGE_CFG_DEFAULT_SPEED_S 16 +#define HCLGE_CFG_DEFAULT_SPEED_M (0xff << HCLGE_CFG_DEFAULT_SPEED_S) + +struct hclge_cfg_param { + __le32 offset; + __le32 rsv; + __le32 param[4]; +}; + +#define HCLGE_MAC_MODE 0x0 +#define HCLGE_DESC_NUM 0x40 + +#define HCLGE_ALLOC_VALID_B 0 +struct hclge_vf_num { + u8 alloc_valid; + u8 rsv[23]; +}; + +#define HCLGE_RSS_DEFAULT_OUTPORT_B 4 +#define HCLGE_RSS_HASH_KEY_OFFSET_B 4 +#define HCLGE_RSS_HASH_KEY_NUM 16 +struct hclge_rss_config { + u8 hash_config; + u8 rsv[7]; + u8 hash_key[HCLGE_RSS_HASH_KEY_NUM]; +}; + +struct hclge_rss_input_tuple { + u8 ipv4_tcp_en; + u8 ipv4_udp_en; + u8 ipv4_sctp_en; + u8 ipv4_fragment_en; + u8 ipv6_tcp_en; + u8 ipv6_udp_en; + u8 ipv6_sctp_en; + u8 ipv6_fragment_en; + u8 rsv[16]; +}; + +#define HCLGE_RSS_CFG_TBL_SIZE 16 + +struct hclge_rss_indirection_table { + u16 start_table_index; + u16 rss_set_bitmap; + u8 rsv[4]; + u8 rss_result[HCLGE_RSS_CFG_TBL_SIZE]; +}; + +#define HCLGE_RSS_TC_OFFSET_S 0 +#define HCLGE_RSS_TC_OFFSET_M (0x3ff << HCLGE_RSS_TC_OFFSET_S) +#define HCLGE_RSS_TC_SIZE_S 12 +#define HCLGE_RSS_TC_SIZE_M (0x7 << HCLGE_RSS_TC_SIZE_S) +#define HCLGE_RSS_TC_VALID_B 15 +struct hclge_rss_tc_mode { + u16 rss_tc_mode[HCLGE_MAX_TC_NUM]; + u8 rsv[8]; +}; + +#define HCLGE_LINK_STS_B 0 +#define HCLGE_LINK_STATUS BIT(HCLGE_LINK_STS_B) +struct hclge_link_status { + u8 status; + u8 rsv[23]; +}; + +struct hclge_promisc_param { + u8 vf_id; + u8 enable; +}; + +#define HCLGE_PROMISC_EN_B 1 +#define HCLGE_PROMISC_EN_ALL 0x7 +#define HCLGE_PROMISC_EN_UC 0x1 +#define HCLGE_PROMISC_EN_MC 0x2 +#define HCLGE_PROMISC_EN_BC 0x4 +struct hclge_promisc_cfg { + u8 flag; + u8 vf_id; + __le16 rsv0; + u8 rsv1[20]; +}; + +enum hclge_promisc_type { + HCLGE_UNICAST = 1, + HCLGE_MULTICAST = 2, + HCLGE_BROADCAST = 3, +}; + +#define HCLGE_MAC_TX_EN_B 6 +#define HCLGE_MAC_RX_EN_B 7 +#define HCLGE_MAC_PAD_TX_B 11 +#define HCLGE_MAC_PAD_RX_B 12 +#define HCLGE_MAC_1588_TX_B 13 +#define HCLGE_MAC_1588_RX_B 14 +#define HCLGE_MAC_APP_LP_B 15 +#define HCLGE_MAC_LINE_LP_B 16 +#define HCLGE_MAC_FCS_TX_B 17 +#define HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B 18 +#define HCLGE_MAC_RX_FCS_STRIP_B 19 +#define HCLGE_MAC_RX_FCS_B 20 +#define HCLGE_MAC_TX_UNDER_MIN_ERR_B 21 +#define HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B 22 + +struct hclge_config_mac_mode { + __le32 txrx_pad_fcs_loop_en; + u8 rsv[20]; +}; + +#define HCLGE_CFG_SPEED_S 0 +#define HCLGE_CFG_SPEED_M (0x3f << HCLGE_CFG_SPEED_S) + +#define HCLGE_CFG_DUPLEX_B 7 +#define HCLGE_CFG_DUPLEX_M BIT(HCLGE_CFG_DUPLEX_B) + +struct hclge_config_mac_speed_dup { + u8 speed_dup; + +#define HCLGE_CFG_MAC_SPEED_CHANGE_EN_B 0 + u8 mac_change_fec_en; + u8 rsv[22]; +}; + +#define HCLGE_QUERY_SPEED_S 3 +#define HCLGE_QUERY_AN_B 0 +#define HCLGE_QUERY_DUPLEX_B 2 + +#define HCLGE_QUERY_SPEED_M (0x1f << HCLGE_QUERY_SPEED_S) +#define HCLGE_QUERY_AN_M BIT(HCLGE_QUERY_AN_B) +#define HCLGE_QUERY_DUPLEX_M BIT(HCLGE_QUERY_DUPLEX_B) + +struct hclge_query_an_speed_dup { + u8 an_syn_dup_speed; + u8 pause; + u8 rsv[23]; +}; + +#define HCLGE_RING_ID_MASK 0x3ff +#define HCLGE_TQP_ENABLE_B 0 + +#define HCLGE_MAC_CFG_AN_EN_B 0 +#define HCLGE_MAC_CFG_AN_INT_EN_B 1 +#define HCLGE_MAC_CFG_AN_INT_MSK_B 2 +#define HCLGE_MAC_CFG_AN_INT_CLR_B 3 +#define HCLGE_MAC_CFG_AN_RST_B 4 + +#define HCLGE_MAC_CFG_AN_EN BIT(HCLGE_MAC_CFG_AN_EN_B) + +struct hclge_config_auto_neg { + __le32 cfg_an_cmd_flag; + u8 rsv[20]; +}; + +#define HCLGE_MAC_MIN_MTU 64 +#define HCLGE_MAC_MAX_MTU 9728 +#define HCLGE_MAC_UPLINK_PORT 0x100 + +struct hclge_config_max_frm_size { + __le16 max_frm_size; + u8 rsv[22]; +}; + +enum hclge_mac_vlan_tbl_opcode { + HCLGE_MAC_VLAN_ADD, /* Add new or modify mac_vlan */ + HCLGE_MAC_VLAN_UPDATE, /* Modify other fields of this table */ + HCLGE_MAC_VLAN_REMOVE, /* Remove a entry through mac_vlan key */ + HCLGE_MAC_VLAN_LKUP, /* Lookup a entry through mac_vlan key */ +}; + +#define HCLGE_MAC_VLAN_BIT0_EN_B 0x0 +#define HCLGE_MAC_VLAN_BIT1_EN_B 0x1 +#define HCLGE_MAC_EPORT_SW_EN_B 0xc +#define HCLGE_MAC_EPORT_TYPE_B 0xb +#define HCLGE_MAC_EPORT_VFID_S 0x3 +#define HCLGE_MAC_EPORT_VFID_M (0xff << HCLGE_MAC_EPORT_VFID_S) +#define HCLGE_MAC_EPORT_PFID_S 0x0 +#define HCLGE_MAC_EPORT_PFID_M (0x7 << HCLGE_MAC_EPORT_PFID_S) +struct hclge_mac_vlan_tbl_entry { + u8 flags; + u8 resp_code; + __le16 vlan_tag; + __le32 mac_addr_hi32; + __le16 mac_addr_lo16; + __le16 rsv1; + u8 entry_type; + u8 mc_mac_en; + __le16 egress_port; + __le16 egress_queue; + u8 rsv2[6]; +}; + +#define HCLGE_CFG_MTA_MAC_SEL_S 0x0 +#define HCLGE_CFG_MTA_MAC_SEL_M (0x3 << HCLGE_CFG_MTA_MAC_SEL_S) +#define HCLGE_CFG_MTA_MAC_EN_B 0x7 +struct hclge_mta_filter_mode { + u8 dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */ + u8 rsv[23]; +}; + +#define HCLGE_CFG_FUNC_MTA_ACCEPT_B 0x0 +struct hclge_cfg_func_mta_filter { + u8 accept; /* Only used lowest 1 bit */ + u8 function_id; + u8 rsv[22]; +}; + +#define HCLGE_CFG_MTA_ITEM_ACCEPT_B 0x0 +#define HCLGE_CFG_MTA_ITEM_IDX_S 0x0 +#define HCLGE_CFG_MTA_ITEM_IDX_M (0xfff << HCLGE_CFG_MTA_ITEM_IDX_S) +struct hclge_cfg_func_mta_item { + u16 item_idx; /* Only used lowest 12 bit */ + u8 accept; /* Only used lowest 1 bit */ + u8 rsv[21]; +}; + +struct hclge_mac_vlan_add { + __le16 flags; + __le16 mac_addr_hi16; + __le32 mac_addr_lo32; + __le32 mac_addr_msk_hi32; + __le16 mac_addr_msk_lo16; + __le16 vlan_tag; + __le16 ingress_port; + __le16 egress_port; + u8 rsv[4]; +}; + +#define HNS3_MAC_VLAN_CFG_FLAG_BIT 0 +struct hclge_mac_vlan_remove { + __le16 flags; + __le16 mac_addr_hi16; + __le32 mac_addr_lo32; + __le32 mac_addr_msk_hi32; + __le16 mac_addr_msk_lo16; + __le16 vlan_tag; + __le16 ingress_port; + __le16 egress_port; + u8 rsv[4]; +}; + +struct hclge_vlan_filter_ctrl { + u8 vlan_type; + u8 vlan_fe; + u8 rsv[22]; +}; + +struct hclge_vlan_filter_pf_cfg { + u8 vlan_offset; + u8 vlan_cfg; + u8 rsv[2]; + u8 vlan_offset_bitmap[20]; +}; + +struct hclge_vlan_filter_vf_cfg { + u16 vlan_id; + u8 resp_code; + u8 rsv; + u8 vlan_cfg; + u8 rsv1[3]; + u8 vf_bitmap[16]; +}; + +struct hclge_cfg_com_tqp_queue { + __le16 tqp_id; + __le16 stream_id; + u8 enable; + u8 rsv[19]; +}; + +struct hclge_cfg_tx_queue_pointer { + __le16 tqp_id; + __le16 tx_tail; + __le16 tx_head; + __le16 fbd_num; + __le16 ring_offset; + u8 rsv[14]; +}; + +#define HCLGE_TSO_MSS_MIN_S 0 +#define HCLGE_TSO_MSS_MIN_M (0x3FFF << HCLGE_TSO_MSS_MIN_S) + +#define HCLGE_TSO_MSS_MAX_S 16 +#define HCLGE_TSO_MSS_MAX_M (0x3FFF << HCLGE_TSO_MSS_MAX_S) + +struct hclge_cfg_tso_status { + __le16 tso_mss_min; + __le16 tso_mss_max; + u8 rsv[20]; +}; + +#define HCLGE_TSO_MSS_MIN 256 +#define HCLGE_TSO_MSS_MAX 9668 + +#define HCLGE_TQP_RESET_B 0 +struct hclge_reset_tqp_queue { + __le16 tqp_id; + u8 reset_req; + u8 ready_to_reset; + u8 rsv[20]; +}; + +#define HCLGE_DEFAULT_TX_BUF 0x4000 /* 16k bytes */ +#define HCLGE_TOTAL_PKT_BUF 0x108000 /* 1.03125M bytes */ +#define HCLGE_DEFAULT_DV 0xA000 /* 40k byte */ + +#define HCLGE_TYPE_CRQ 0 +#define HCLGE_TYPE_CSQ 1 +#define HCLGE_NIC_CSQ_BASEADDR_L_REG 0x27000 +#define HCLGE_NIC_CSQ_BASEADDR_H_REG 0x27004 +#define HCLGE_NIC_CSQ_DEPTH_REG 0x27008 +#define HCLGE_NIC_CSQ_TAIL_REG 0x27010 +#define HCLGE_NIC_CSQ_HEAD_REG 0x27014 +#define HCLGE_NIC_CRQ_BASEADDR_L_REG 0x27018 +#define HCLGE_NIC_CRQ_BASEADDR_H_REG 0x2701c +#define HCLGE_NIC_CRQ_DEPTH_REG 0x27020 +#define HCLGE_NIC_CRQ_TAIL_REG 0x27024 +#define HCLGE_NIC_CRQ_HEAD_REG 0x27028 +#define HCLGE_NIC_CMQ_EN_B 16 +#define HCLGE_NIC_CMQ_ENABLE BIT(HCLGE_NIC_CMQ_EN_B) +#define HCLGE_NIC_CMQ_DESC_NUM 1024 +#define HCLGE_NIC_CMQ_DESC_NUM_S 3 + +int hclge_cmd_init(struct hclge_dev *hdev); +static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value) +{ + writel(value, base + reg); +} + +#define hclge_write_dev(a, reg, value) \ + hclge_write_reg((a)->io_base, (reg), (value)) +#define hclge_read_dev(a, reg) \ + hclge_read_reg((a)->io_base, (reg)) + +static inline u32 hclge_read_reg(u8 __iomem *base, u32 reg) +{ + u8 __iomem *reg_addr = READ_ONCE(base); + + return readl(reg_addr + reg); +} + +#define HCLGE_SEND_SYNC(flag) \ + ((flag) & HCLGE_CMD_FLAG_NO_INTR) + +struct hclge_hw; +int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num); +void hclge_cmd_setup_basic_desc(struct hclge_desc *desc, + enum hclge_opcode_type opcode, bool is_read); + +int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, + struct hclge_promisc_param *param); + +enum hclge_cmd_status hclge_cmd_mdio_write(struct hclge_hw *hw, + struct hclge_desc *desc); +enum hclge_cmd_status hclge_cmd_mdio_read(struct hclge_hw *hw, + struct hclge_desc *desc); + +void hclge_destroy_cmd_queue(struct hclge_hw *hw); +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c new file mode 100644 index 000000000000..bb45365fb817 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -0,0 +1,4265 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/acpi.h> +#include <linux/device.h> +#include <linux/etherdevice.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include "hclge_cmd.h" +#include "hclge_main.h" +#include "hclge_mdio.h" +#include "hclge_tm.h" +#include "hnae3.h" + +#define HCLGE_NAME "hclge" +#define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset)))) +#define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f)) +#define HCLGE_64BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_64_bit_stats, f)) +#define HCLGE_32BIT_STATS_FIELD_OFF(f) (offsetof(struct hclge_32_bit_stats, f)) + +static int hclge_rss_init_hw(struct hclge_dev *hdev); +static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, + enum hclge_mta_dmac_sel_type mta_mac_sel, + bool enable); +static int hclge_init_vlan_config(struct hclge_dev *hdev); + +static struct hnae3_ae_algo ae_algo; + +static const struct pci_device_id ae_algo_pci_tbl[] = { + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_GE), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, + /* Required last entry */ + {0, } +}; + +static const struct pci_device_id roce_pci_tbl[] = { + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, + /* Required last entry */ + {0, } +}; + +static const char hns3_nic_test_strs[][ETH_GSTRING_LEN] = { + "Mac Loopback test", + "Serdes Loopback test", + "Phy Loopback test" +}; + +static const struct hclge_comm_stats_str g_all_64bit_stats_string[] = { + {"igu_rx_oversize_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_oversize_pkt)}, + {"igu_rx_undersize_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_undersize_pkt)}, + {"igu_rx_out_all_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_out_all_pkt)}, + {"igu_rx_uni_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_uni_pkt)}, + {"igu_rx_multi_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_multi_pkt)}, + {"igu_rx_broad_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(igu_rx_broad_pkt)}, + {"egu_tx_out_all_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_out_all_pkt)}, + {"egu_tx_uni_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_uni_pkt)}, + {"egu_tx_multi_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_multi_pkt)}, + {"egu_tx_broad_pkt", + HCLGE_64BIT_STATS_FIELD_OFF(egu_tx_broad_pkt)}, + {"ssu_ppp_mac_key_num", + HCLGE_64BIT_STATS_FIELD_OFF(ssu_ppp_mac_key_num)}, + {"ssu_ppp_host_key_num", + HCLGE_64BIT_STATS_FIELD_OFF(ssu_ppp_host_key_num)}, + {"ppp_ssu_mac_rlt_num", + HCLGE_64BIT_STATS_FIELD_OFF(ppp_ssu_mac_rlt_num)}, + {"ppp_ssu_host_rlt_num", + HCLGE_64BIT_STATS_FIELD_OFF(ppp_ssu_host_rlt_num)}, + {"ssu_tx_in_num", + HCLGE_64BIT_STATS_FIELD_OFF(ssu_tx_in_num)}, + {"ssu_tx_out_num", + HCLGE_64BIT_STATS_FIELD_OFF(ssu_tx_out_num)}, + {"ssu_rx_in_num", + HCLGE_64BIT_STATS_FIELD_OFF(ssu_rx_in_num)}, + {"ssu_rx_out_num", + HCLGE_64BIT_STATS_FIELD_OFF(ssu_rx_out_num)} +}; + +static const struct hclge_comm_stats_str g_all_32bit_stats_string[] = { + {"igu_rx_err_pkt", + HCLGE_32BIT_STATS_FIELD_OFF(igu_rx_err_pkt)}, + {"igu_rx_no_eof_pkt", + HCLGE_32BIT_STATS_FIELD_OFF(igu_rx_no_eof_pkt)}, + {"igu_rx_no_sof_pkt", + HCLGE_32BIT_STATS_FIELD_OFF(igu_rx_no_sof_pkt)}, + {"egu_tx_1588_pkt", + HCLGE_32BIT_STATS_FIELD_OFF(egu_tx_1588_pkt)}, + {"ssu_full_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(ssu_full_drop_num)}, + {"ssu_part_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(ssu_part_drop_num)}, + {"ppp_key_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(ppp_key_drop_num)}, + {"ppp_rlt_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(ppp_rlt_drop_num)}, + {"ssu_key_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(ssu_key_drop_num)}, + {"pkt_curr_buf_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_cnt)}, + {"qcn_fb_rcv_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(qcn_fb_rcv_cnt)}, + {"qcn_fb_drop_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(qcn_fb_drop_cnt)}, + {"qcn_fb_invaild_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(qcn_fb_invaild_cnt)}, + {"rx_packet_tc0_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc0_in_cnt)}, + {"rx_packet_tc1_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc1_in_cnt)}, + {"rx_packet_tc2_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc2_in_cnt)}, + {"rx_packet_tc3_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc3_in_cnt)}, + {"rx_packet_tc4_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc4_in_cnt)}, + {"rx_packet_tc5_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc5_in_cnt)}, + {"rx_packet_tc6_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc6_in_cnt)}, + {"rx_packet_tc7_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc7_in_cnt)}, + {"rx_packet_tc0_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc0_out_cnt)}, + {"rx_packet_tc1_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc1_out_cnt)}, + {"rx_packet_tc2_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc2_out_cnt)}, + {"rx_packet_tc3_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc3_out_cnt)}, + {"rx_packet_tc4_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc4_out_cnt)}, + {"rx_packet_tc5_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc5_out_cnt)}, + {"rx_packet_tc6_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc6_out_cnt)}, + {"rx_packet_tc7_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_packet_tc7_out_cnt)}, + {"tx_packet_tc0_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc0_in_cnt)}, + {"tx_packet_tc1_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc1_in_cnt)}, + {"tx_packet_tc2_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc2_in_cnt)}, + {"tx_packet_tc3_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc3_in_cnt)}, + {"tx_packet_tc4_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc4_in_cnt)}, + {"tx_packet_tc5_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc5_in_cnt)}, + {"tx_packet_tc6_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc6_in_cnt)}, + {"tx_packet_tc7_in_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc7_in_cnt)}, + {"tx_packet_tc0_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc0_out_cnt)}, + {"tx_packet_tc1_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc1_out_cnt)}, + {"tx_packet_tc2_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc2_out_cnt)}, + {"tx_packet_tc3_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc3_out_cnt)}, + {"tx_packet_tc4_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc4_out_cnt)}, + {"tx_packet_tc5_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc5_out_cnt)}, + {"tx_packet_tc6_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc6_out_cnt)}, + {"tx_packet_tc7_out_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_packet_tc7_out_cnt)}, + {"pkt_curr_buf_tc0_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc0_cnt)}, + {"pkt_curr_buf_tc1_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc1_cnt)}, + {"pkt_curr_buf_tc2_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc2_cnt)}, + {"pkt_curr_buf_tc3_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc3_cnt)}, + {"pkt_curr_buf_tc4_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc4_cnt)}, + {"pkt_curr_buf_tc5_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc5_cnt)}, + {"pkt_curr_buf_tc6_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc6_cnt)}, + {"pkt_curr_buf_tc7_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(pkt_curr_buf_tc7_cnt)}, + {"mb_uncopy_num", + HCLGE_32BIT_STATS_FIELD_OFF(mb_uncopy_num)}, + {"lo_pri_unicast_rlt_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(lo_pri_unicast_rlt_drop_num)}, + {"hi_pri_multicast_rlt_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(hi_pri_multicast_rlt_drop_num)}, + {"lo_pri_multicast_rlt_drop_num", + HCLGE_32BIT_STATS_FIELD_OFF(lo_pri_multicast_rlt_drop_num)}, + {"rx_oq_drop_pkt_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(rx_oq_drop_pkt_cnt)}, + {"tx_oq_drop_pkt_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(tx_oq_drop_pkt_cnt)}, + {"nic_l2_err_drop_pkt_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(nic_l2_err_drop_pkt_cnt)}, + {"roc_l2_err_drop_pkt_cnt", + HCLGE_32BIT_STATS_FIELD_OFF(roc_l2_err_drop_pkt_cnt)} +}; + +static const struct hclge_comm_stats_str g_mac_stats_string[] = { + {"mac_tx_mac_pause_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_mac_pause_num)}, + {"mac_rx_mac_pause_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_mac_pause_num)}, + {"mac_tx_pfc_pri0_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri0_pkt_num)}, + {"mac_tx_pfc_pri1_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri1_pkt_num)}, + {"mac_tx_pfc_pri2_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri2_pkt_num)}, + {"mac_tx_pfc_pri3_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri3_pkt_num)}, + {"mac_tx_pfc_pri4_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri4_pkt_num)}, + {"mac_tx_pfc_pri5_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri5_pkt_num)}, + {"mac_tx_pfc_pri6_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri6_pkt_num)}, + {"mac_tx_pfc_pri7_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri7_pkt_num)}, + {"mac_rx_pfc_pri0_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri0_pkt_num)}, + {"mac_rx_pfc_pri1_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri1_pkt_num)}, + {"mac_rx_pfc_pri2_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri2_pkt_num)}, + {"mac_rx_pfc_pri3_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri3_pkt_num)}, + {"mac_rx_pfc_pri4_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri4_pkt_num)}, + {"mac_rx_pfc_pri5_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri5_pkt_num)}, + {"mac_rx_pfc_pri6_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri6_pkt_num)}, + {"mac_rx_pfc_pri7_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri7_pkt_num)}, + {"mac_tx_total_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_total_pkt_num)}, + {"mac_tx_total_oct_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_total_oct_num)}, + {"mac_tx_good_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_good_pkt_num)}, + {"mac_tx_bad_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_bad_pkt_num)}, + {"mac_tx_good_oct_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_good_oct_num)}, + {"mac_tx_bad_oct_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_bad_oct_num)}, + {"mac_tx_uni_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_uni_pkt_num)}, + {"mac_tx_multi_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_multi_pkt_num)}, + {"mac_tx_broad_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_broad_pkt_num)}, + {"mac_tx_undersize_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_undersize_pkt_num)}, + {"mac_tx_overrsize_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_overrsize_pkt_num)}, + {"mac_tx_64_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_64_oct_pkt_num)}, + {"mac_tx_65_127_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_65_127_oct_pkt_num)}, + {"mac_tx_128_255_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_128_255_oct_pkt_num)}, + {"mac_tx_256_511_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_256_511_oct_pkt_num)}, + {"mac_tx_512_1023_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_512_1023_oct_pkt_num)}, + {"mac_tx_1024_1518_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_1024_1518_oct_pkt_num)}, + {"mac_tx_1519_max_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_tx_1519_max_oct_pkt_num)}, + {"mac_rx_total_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_total_pkt_num)}, + {"mac_rx_total_oct_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_total_oct_num)}, + {"mac_rx_good_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_good_pkt_num)}, + {"mac_rx_bad_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_bad_pkt_num)}, + {"mac_rx_good_oct_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_good_oct_num)}, + {"mac_rx_bad_oct_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_bad_oct_num)}, + {"mac_rx_uni_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_uni_pkt_num)}, + {"mac_rx_multi_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_multi_pkt_num)}, + {"mac_rx_broad_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_broad_pkt_num)}, + {"mac_rx_undersize_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_undersize_pkt_num)}, + {"mac_rx_overrsize_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_overrsize_pkt_num)}, + {"mac_rx_64_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_64_oct_pkt_num)}, + {"mac_rx_65_127_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_65_127_oct_pkt_num)}, + {"mac_rx_128_255_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_128_255_oct_pkt_num)}, + {"mac_rx_256_511_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_256_511_oct_pkt_num)}, + {"mac_rx_512_1023_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_512_1023_oct_pkt_num)}, + {"mac_rx_1024_1518_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_1024_1518_oct_pkt_num)}, + {"mac_rx_1519_max_oct_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rx_1519_max_oct_pkt_num)}, + + {"mac_trans_fragment_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_trans_fragment_pkt_num)}, + {"mac_trans_undermin_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_trans_undermin_pkt_num)}, + {"mac_trans_jabber_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_trans_jabber_pkt_num)}, + {"mac_trans_err_all_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_trans_err_all_pkt_num)}, + {"mac_trans_from_app_good_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_trans_from_app_good_pkt_num)}, + {"mac_trans_from_app_bad_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_trans_from_app_bad_pkt_num)}, + {"mac_rcv_fragment_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rcv_fragment_pkt_num)}, + {"mac_rcv_undermin_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rcv_undermin_pkt_num)}, + {"mac_rcv_jabber_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rcv_jabber_pkt_num)}, + {"mac_rcv_fcs_err_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rcv_fcs_err_pkt_num)}, + {"mac_rcv_send_app_good_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rcv_send_app_good_pkt_num)}, + {"mac_rcv_send_app_bad_pkt_num", + HCLGE_MAC_STATS_FIELD_OFF(mac_rcv_send_app_bad_pkt_num)} +}; + +static int hclge_64_bit_update_stats(struct hclge_dev *hdev) +{ +#define HCLGE_64_BIT_CMD_NUM 5 +#define HCLGE_64_BIT_RTN_DATANUM 4 + u64 *data = (u64 *)(&hdev->hw_stats.all_64_bit_stats); + struct hclge_desc desc[HCLGE_64_BIT_CMD_NUM]; + u64 *desc_data; + int i, k, n; + int ret; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_64_BIT, true); + ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_64_BIT_CMD_NUM); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get 64 bit pkt stats fail, status = %d.\n", ret); + return ret; + } + + for (i = 0; i < HCLGE_64_BIT_CMD_NUM; i++) { + if (unlikely(i == 0)) { + desc_data = (u64 *)(&desc[i].data[0]); + n = HCLGE_64_BIT_RTN_DATANUM - 1; + } else { + desc_data = (u64 *)(&desc[i]); + n = HCLGE_64_BIT_RTN_DATANUM; + } + for (k = 0; k < n; k++) { + *data++ += cpu_to_le64(*desc_data); + desc_data++; + } + } + + return 0; +} + +static void hclge_reset_partial_32bit_counter(struct hclge_32_bit_stats *stats) +{ + stats->pkt_curr_buf_cnt = 0; + stats->pkt_curr_buf_tc0_cnt = 0; + stats->pkt_curr_buf_tc1_cnt = 0; + stats->pkt_curr_buf_tc2_cnt = 0; + stats->pkt_curr_buf_tc3_cnt = 0; + stats->pkt_curr_buf_tc4_cnt = 0; + stats->pkt_curr_buf_tc5_cnt = 0; + stats->pkt_curr_buf_tc6_cnt = 0; + stats->pkt_curr_buf_tc7_cnt = 0; +} + +static int hclge_32_bit_update_stats(struct hclge_dev *hdev) +{ +#define HCLGE_32_BIT_CMD_NUM 8 +#define HCLGE_32_BIT_RTN_DATANUM 8 + + struct hclge_desc desc[HCLGE_32_BIT_CMD_NUM]; + struct hclge_32_bit_stats *all_32_bit_stats; + u32 *desc_data; + int i, k, n; + u64 *data; + int ret; + + all_32_bit_stats = &hdev->hw_stats.all_32_bit_stats; + data = (u64 *)(&all_32_bit_stats->egu_tx_1588_pkt); + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_32_BIT, true); + ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_32_BIT_CMD_NUM); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get 32 bit pkt stats fail, status = %d.\n", ret); + + return ret; + } + + hclge_reset_partial_32bit_counter(all_32_bit_stats); + for (i = 0; i < HCLGE_32_BIT_CMD_NUM; i++) { + if (unlikely(i == 0)) { + all_32_bit_stats->igu_rx_err_pkt += + cpu_to_le32(desc[i].data[0]); + all_32_bit_stats->igu_rx_no_eof_pkt += + cpu_to_le32(desc[i].data[1] & 0xffff); + all_32_bit_stats->igu_rx_no_sof_pkt += + cpu_to_le32((desc[i].data[1] >> 16) & 0xffff); + + desc_data = (u32 *)(&desc[i].data[2]); + n = HCLGE_32_BIT_RTN_DATANUM - 4; + } else { + desc_data = (u32 *)(&desc[i]); + n = HCLGE_32_BIT_RTN_DATANUM; + } + for (k = 0; k < n; k++) { + *data++ += cpu_to_le32(*desc_data); + desc_data++; + } + } + + return 0; +} + +static int hclge_mac_update_stats(struct hclge_dev *hdev) +{ +#define HCLGE_MAC_CMD_NUM 17 +#define HCLGE_RTN_DATA_NUM 4 + + u64 *data = (u64 *)(&hdev->hw_stats.mac_stats); + struct hclge_desc desc[HCLGE_MAC_CMD_NUM]; + u64 *desc_data; + int i, k, n; + int ret; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC, true); + ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_MAC_CMD_NUM); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get MAC pkt stats fail, status = %d.\n", ret); + + return ret; + } + + for (i = 0; i < HCLGE_MAC_CMD_NUM; i++) { + if (unlikely(i == 0)) { + desc_data = (u64 *)(&desc[i].data[0]); + n = HCLGE_RTN_DATA_NUM - 2; + } else { + desc_data = (u64 *)(&desc[i]); + n = HCLGE_RTN_DATA_NUM; + } + for (k = 0; k < n; k++) { + *data++ += cpu_to_le64(*desc_data); + desc_data++; + } + } + + return 0; +} + +static int hclge_tqps_update_stats(struct hnae3_handle *handle) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hnae3_queue *queue; + struct hclge_desc desc[1]; + struct hclge_tqp *tqp; + int ret, i; + + for (i = 0; i < kinfo->num_tqps; i++) { + queue = handle->kinfo.tqp[i]; + tqp = container_of(queue, struct hclge_tqp, q); + /* command : HCLGE_OPC_QUERY_IGU_STAT */ + hclge_cmd_setup_basic_desc(&desc[0], + HCLGE_OPC_QUERY_RX_STATUS, + true); + + desc[0].data[0] = (tqp->index & 0x1ff); + ret = hclge_cmd_send(&hdev->hw, desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query tqp stat fail, status = %d,queue = %d\n", + ret, i); + return ret; + } + tqp->tqp_stats.rcb_rx_ring_pktnum_rcd += + cpu_to_le32(desc[0].data[4]); + } + + for (i = 0; i < kinfo->num_tqps; i++) { + queue = handle->kinfo.tqp[i]; + tqp = container_of(queue, struct hclge_tqp, q); + /* command : HCLGE_OPC_QUERY_IGU_STAT */ + hclge_cmd_setup_basic_desc(&desc[0], + HCLGE_OPC_QUERY_TX_STATUS, + true); + + desc[0].data[0] = (tqp->index & 0x1ff); + ret = hclge_cmd_send(&hdev->hw, desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Query tqp stat fail, status = %d,queue = %d\n", + ret, i); + return ret; + } + tqp->tqp_stats.rcb_tx_ring_pktnum_rcd += + cpu_to_le32(desc[0].data[4]); + } + + return 0; +} + +static u64 *hclge_tqps_get_stats(struct hnae3_handle *handle, u64 *data) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_tqp *tqp; + u64 *buff = data; + int i; + + for (i = 0; i < kinfo->num_tqps; i++) { + tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q); + *buff++ = cpu_to_le64(tqp->tqp_stats.rcb_tx_ring_pktnum_rcd); + } + + for (i = 0; i < kinfo->num_tqps; i++) { + tqp = container_of(kinfo->tqp[i], struct hclge_tqp, q); + *buff++ = cpu_to_le64(tqp->tqp_stats.rcb_rx_ring_pktnum_rcd); + } + + return buff; +} + +static int hclge_tqps_get_sset_count(struct hnae3_handle *handle, int stringset) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + + return kinfo->num_tqps * (2); +} + +static u8 *hclge_tqps_get_strings(struct hnae3_handle *handle, u8 *data) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + u8 *buff = data; + int i = 0; + + for (i = 0; i < kinfo->num_tqps; i++) { + struct hclge_tqp *tqp = container_of(handle->kinfo.tqp[i], + struct hclge_tqp, q); + snprintf(buff, ETH_GSTRING_LEN, "rcb_q%d_tx_pktnum_rcd", + tqp->index); + buff = buff + ETH_GSTRING_LEN; + } + + for (i = 0; i < kinfo->num_tqps; i++) { + struct hclge_tqp *tqp = container_of(kinfo->tqp[i], + struct hclge_tqp, q); + snprintf(buff, ETH_GSTRING_LEN, "rcb_q%d_rx_pktnum_rcd", + tqp->index); + buff = buff + ETH_GSTRING_LEN; + } + + return buff; +} + +static u64 *hclge_comm_get_stats(void *comm_stats, + const struct hclge_comm_stats_str strs[], + int size, u64 *data) +{ + u64 *buf = data; + u32 i; + + for (i = 0; i < size; i++) + buf[i] = HCLGE_STATS_READ(comm_stats, strs[i].offset); + + return buf + size; +} + +static u8 *hclge_comm_get_strings(u32 stringset, + const struct hclge_comm_stats_str strs[], + int size, u8 *data) +{ + char *buff = (char *)data; + u32 i; + + if (stringset != ETH_SS_STATS) + return buff; + + for (i = 0; i < size; i++) { + snprintf(buff, ETH_GSTRING_LEN, + strs[i].desc); + buff = buff + ETH_GSTRING_LEN; + } + + return (u8 *)buff; +} + +static void hclge_update_netstat(struct hclge_hw_stats *hw_stats, + struct net_device_stats *net_stats) +{ + net_stats->tx_dropped = 0; + net_stats->rx_dropped = hw_stats->all_32_bit_stats.ssu_full_drop_num; + net_stats->rx_dropped += hw_stats->all_32_bit_stats.ppp_key_drop_num; + net_stats->rx_dropped += hw_stats->all_32_bit_stats.ssu_key_drop_num; + + net_stats->rx_errors = hw_stats->mac_stats.mac_rx_overrsize_pkt_num; + net_stats->rx_errors += hw_stats->mac_stats.mac_rx_undersize_pkt_num; + net_stats->rx_errors += hw_stats->all_32_bit_stats.igu_rx_err_pkt; + net_stats->rx_errors += hw_stats->all_32_bit_stats.igu_rx_no_eof_pkt; + net_stats->rx_errors += hw_stats->all_32_bit_stats.igu_rx_no_sof_pkt; + net_stats->rx_errors += hw_stats->mac_stats.mac_rcv_fcs_err_pkt_num; + + net_stats->multicast = hw_stats->mac_stats.mac_tx_multi_pkt_num; + net_stats->multicast += hw_stats->mac_stats.mac_rx_multi_pkt_num; + + net_stats->rx_crc_errors = hw_stats->mac_stats.mac_rcv_fcs_err_pkt_num; + net_stats->rx_length_errors = + hw_stats->mac_stats.mac_rx_undersize_pkt_num; + net_stats->rx_length_errors += + hw_stats->mac_stats.mac_rx_overrsize_pkt_num; + net_stats->rx_over_errors = + hw_stats->mac_stats.mac_rx_overrsize_pkt_num; +} + +static void hclge_update_stats_for_all(struct hclge_dev *hdev) +{ + struct hnae3_handle *handle; + int status; + + handle = &hdev->vport[0].nic; + if (handle->client) { + status = hclge_tqps_update_stats(handle); + if (status) { + dev_err(&hdev->pdev->dev, + "Update TQPS stats fail, status = %d.\n", + status); + } + } + + status = hclge_mac_update_stats(hdev); + if (status) + dev_err(&hdev->pdev->dev, + "Update MAC stats fail, status = %d.\n", status); + + status = hclge_32_bit_update_stats(hdev); + if (status) + dev_err(&hdev->pdev->dev, + "Update 32 bit stats fail, status = %d.\n", + status); + + hclge_update_netstat(&hdev->hw_stats, &handle->kinfo.netdev->stats); +} + +static void hclge_update_stats(struct hnae3_handle *handle, + struct net_device_stats *net_stats) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_hw_stats *hw_stats = &hdev->hw_stats; + int status; + + status = hclge_mac_update_stats(hdev); + if (status) + dev_err(&hdev->pdev->dev, + "Update MAC stats fail, status = %d.\n", + status); + + status = hclge_32_bit_update_stats(hdev); + if (status) + dev_err(&hdev->pdev->dev, + "Update 32 bit stats fail, status = %d.\n", + status); + + status = hclge_64_bit_update_stats(hdev); + if (status) + dev_err(&hdev->pdev->dev, + "Update 64 bit stats fail, status = %d.\n", + status); + + status = hclge_tqps_update_stats(handle); + if (status) + dev_err(&hdev->pdev->dev, + "Update TQPS stats fail, status = %d.\n", + status); + + hclge_update_netstat(hw_stats, net_stats); +} + +static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset) +{ +#define HCLGE_LOOPBACK_TEST_FLAGS 0x7 + + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int count = 0; + + /* Loopback test support rules: + * mac: only GE mode support + * serdes: all mac mode will support include GE/XGE/LGE/CGE + * phy: only support when phy device exist on board + */ + if (stringset == ETH_SS_TEST) { + /* clear loopback bit flags at first */ + handle->flags = (handle->flags & (~HCLGE_LOOPBACK_TEST_FLAGS)); + if (hdev->hw.mac.speed == HCLGE_MAC_SPEED_10M || + hdev->hw.mac.speed == HCLGE_MAC_SPEED_100M || + hdev->hw.mac.speed == HCLGE_MAC_SPEED_1G) { + count += 1; + handle->flags |= HNAE3_SUPPORT_MAC_LOOPBACK; + } else { + count = -EOPNOTSUPP; + } + } else if (stringset == ETH_SS_STATS) { + count = ARRAY_SIZE(g_mac_stats_string) + + ARRAY_SIZE(g_all_32bit_stats_string) + + ARRAY_SIZE(g_all_64bit_stats_string) + + hclge_tqps_get_sset_count(handle, stringset); + } + + return count; +} + +static void hclge_get_strings(struct hnae3_handle *handle, + u32 stringset, + u8 *data) +{ + u8 *p = (char *)data; + int size; + + if (stringset == ETH_SS_STATS) { + size = ARRAY_SIZE(g_mac_stats_string); + p = hclge_comm_get_strings(stringset, + g_mac_stats_string, + size, + p); + size = ARRAY_SIZE(g_all_32bit_stats_string); + p = hclge_comm_get_strings(stringset, + g_all_32bit_stats_string, + size, + p); + size = ARRAY_SIZE(g_all_64bit_stats_string); + p = hclge_comm_get_strings(stringset, + g_all_64bit_stats_string, + size, + p); + p = hclge_tqps_get_strings(handle, p); + } else if (stringset == ETH_SS_TEST) { + if (handle->flags & HNAE3_SUPPORT_MAC_LOOPBACK) { + memcpy(p, + hns3_nic_test_strs[HNAE3_MAC_INTER_LOOP_MAC], + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + if (handle->flags & HNAE3_SUPPORT_SERDES_LOOPBACK) { + memcpy(p, + hns3_nic_test_strs[HNAE3_MAC_INTER_LOOP_SERDES], + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + if (handle->flags & HNAE3_SUPPORT_PHY_LOOPBACK) { + memcpy(p, + hns3_nic_test_strs[HNAE3_MAC_INTER_LOOP_PHY], + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + } +} + +static void hclge_get_stats(struct hnae3_handle *handle, u64 *data) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u64 *p; + + p = hclge_comm_get_stats(&hdev->hw_stats.mac_stats, + g_mac_stats_string, + ARRAY_SIZE(g_mac_stats_string), + data); + p = hclge_comm_get_stats(&hdev->hw_stats.all_32_bit_stats, + g_all_32bit_stats_string, + ARRAY_SIZE(g_all_32bit_stats_string), + p); + p = hclge_comm_get_stats(&hdev->hw_stats.all_64_bit_stats, + g_all_64bit_stats_string, + ARRAY_SIZE(g_all_64bit_stats_string), + p); + p = hclge_tqps_get_stats(handle, p); +} + +static int hclge_parse_func_status(struct hclge_dev *hdev, + struct hclge_func_status *status) +{ + if (!(status->pf_state & HCLGE_PF_STATE_DONE)) + return -EINVAL; + + /* Set the pf to main pf */ + if (status->pf_state & HCLGE_PF_STATE_MAIN) + hdev->flag |= HCLGE_FLAG_MAIN; + else + hdev->flag &= ~HCLGE_FLAG_MAIN; + + hdev->num_req_vfs = status->vf_num / status->pf_num; + return 0; +} + +static int hclge_query_function_status(struct hclge_dev *hdev) +{ + struct hclge_func_status *req; + struct hclge_desc desc; + int timeout = 0; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_FUNC_STATUS, true); + req = (struct hclge_func_status *)desc.data; + + do { + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "query function status failed %d.\n", + ret); + + return ret; + } + + /* Check pf reset is done */ + if (req->pf_state) + break; + usleep_range(1000, 2000); + } while (timeout++ < 5); + + ret = hclge_parse_func_status(hdev, req); + + return ret; +} + +static int hclge_query_pf_resource(struct hclge_dev *hdev) +{ + struct hclge_pf_res *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_PF_RSRC, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "query pf resource failed %d.\n", ret); + return ret; + } + + req = (struct hclge_pf_res *)desc.data; + hdev->num_tqps = __le16_to_cpu(req->tqp_num); + hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S; + + if (hnae_get_bit(hdev->ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B)) { + hdev->num_roce_msix = + hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number), + HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); + + /* PF should have NIC vectors and Roce vectors, + * NIC vectors are queued before Roce vectors. + */ + hdev->num_msi = hdev->num_roce_msix + HCLGE_ROCE_VECTOR_OFFSET; + } else { + hdev->num_msi = + hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number), + HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); + } + + return 0; +} + +static int hclge_parse_speed(int speed_cmd, int *speed) +{ + switch (speed_cmd) { + case 6: + *speed = HCLGE_MAC_SPEED_10M; + break; + case 7: + *speed = HCLGE_MAC_SPEED_100M; + break; + case 0: + *speed = HCLGE_MAC_SPEED_1G; + break; + case 1: + *speed = HCLGE_MAC_SPEED_10G; + break; + case 2: + *speed = HCLGE_MAC_SPEED_25G; + break; + case 3: + *speed = HCLGE_MAC_SPEED_40G; + break; + case 4: + *speed = HCLGE_MAC_SPEED_50G; + break; + case 5: + *speed = HCLGE_MAC_SPEED_100G; + break; + default: + return -EINVAL; + } + + return 0; +} + +static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) +{ + struct hclge_cfg_param *req; + u64 mac_addr_tmp_high; + u64 mac_addr_tmp; + int i; + + req = (struct hclge_cfg_param *)desc[0].data; + + /* get the configuration */ + cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]), + HCLGE_CFG_VMDQ_M, + HCLGE_CFG_VMDQ_S); + cfg->tc_num = hnae_get_field(__le32_to_cpu(req->param[0]), + HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S); + cfg->tqp_desc_num = hnae_get_field(__le32_to_cpu(req->param[0]), + HCLGE_CFG_TQP_DESC_N_M, + HCLGE_CFG_TQP_DESC_N_S); + + cfg->phy_addr = hnae_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_PHY_ADDR_M, + HCLGE_CFG_PHY_ADDR_S); + cfg->media_type = hnae_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_MEDIA_TP_M, + HCLGE_CFG_MEDIA_TP_S); + cfg->rx_buf_len = hnae_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_RX_BUF_LEN_M, + HCLGE_CFG_RX_BUF_LEN_S); + /* get mac_address */ + mac_addr_tmp = __le32_to_cpu(req->param[2]); + mac_addr_tmp_high = hnae_get_field(__le32_to_cpu(req->param[3]), + HCLGE_CFG_MAC_ADDR_H_M, + HCLGE_CFG_MAC_ADDR_H_S); + + mac_addr_tmp |= (mac_addr_tmp_high << 31) << 1; + + cfg->default_speed = hnae_get_field(__le32_to_cpu(req->param[3]), + HCLGE_CFG_DEFAULT_SPEED_M, + HCLGE_CFG_DEFAULT_SPEED_S); + for (i = 0; i < ETH_ALEN; i++) + cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff; + + req = (struct hclge_cfg_param *)desc[1].data; + cfg->numa_node_map = __le32_to_cpu(req->param[0]); +} + +/* hclge_get_cfg: query the static parameter from flash + * @hdev: pointer to struct hclge_dev + * @hcfg: the config structure to be getted + */ +static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg) +{ + struct hclge_desc desc[HCLGE_PF_CFG_DESC_NUM]; + struct hclge_cfg_param *req; + int i, ret; + + for (i = 0; i < HCLGE_PF_CFG_DESC_NUM; i++) { + req = (struct hclge_cfg_param *)desc[i].data; + hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM, + true); + hnae_set_field(req->offset, HCLGE_CFG_OFFSET_M, + HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES); + /* Len should be united by 4 bytes when send to hardware */ + hnae_set_field(req->offset, HCLGE_CFG_RD_LEN_M, + HCLGE_CFG_RD_LEN_S, + HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT); + req->offset = cpu_to_le32(req->offset); + } + + ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_PF_CFG_DESC_NUM); + if (ret) { + dev_err(&hdev->pdev->dev, + "get config failed %d.\n", ret); + return ret; + } + + hclge_parse_cfg(hcfg, desc); + return 0; +} + +static int hclge_get_cap(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_query_function_status(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "query function status error %d.\n", ret); + return ret; + } + + /* get pf resource */ + ret = hclge_query_pf_resource(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "query pf resource error %d.\n", ret); + return ret; + } + + return 0; +} + +static int hclge_configure(struct hclge_dev *hdev) +{ + struct hclge_cfg cfg; + int ret, i; + + ret = hclge_get_cfg(hdev, &cfg); + if (ret) { + dev_err(&hdev->pdev->dev, "get mac mode error %d.\n", ret); + return ret; + } + + hdev->num_vmdq_vport = cfg.vmdq_vport_num; + hdev->base_tqp_pid = 0; + hdev->rss_size_max = 1; + hdev->rx_buf_len = cfg.rx_buf_len; + for (i = 0; i < ETH_ALEN; i++) + hdev->hw.mac.mac_addr[i] = cfg.mac_addr[i]; + hdev->hw.mac.media_type = cfg.media_type; + hdev->num_desc = cfg.tqp_desc_num; + hdev->tm_info.num_pg = 1; + hdev->tm_info.num_tc = cfg.tc_num; + hdev->tm_info.hw_pfc_map = 0; + + ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed); + if (ret) { + dev_err(&hdev->pdev->dev, "Get wrong speed ret=%d.\n", ret); + return ret; + } + + if ((hdev->tm_info.num_tc > HNAE3_MAX_TC) || + (hdev->tm_info.num_tc < 1)) { + dev_warn(&hdev->pdev->dev, "TC num = %d.\n", + hdev->tm_info.num_tc); + hdev->tm_info.num_tc = 1; + } + + /* Currently not support uncontiuous tc */ + for (i = 0; i < cfg.tc_num; i++) + hnae_set_bit(hdev->hw_tc_map, i, 1); + + if (!hdev->num_vmdq_vport && !hdev->num_req_vfs) + hdev->tx_sch_mode = HCLGE_FLAG_TC_BASE_SCH_MODE; + else + hdev->tx_sch_mode = HCLGE_FLAG_VNET_BASE_SCH_MODE; + + return ret; +} + +static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min, + int tso_mss_max) +{ + struct hclge_cfg_tso_status *req; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TSO_GENERIC_CONFIG, false); + + req = (struct hclge_cfg_tso_status *)desc.data; + hnae_set_field(req->tso_mss_min, HCLGE_TSO_MSS_MIN_M, + HCLGE_TSO_MSS_MIN_S, tso_mss_min); + hnae_set_field(req->tso_mss_max, HCLGE_TSO_MSS_MIN_M, + HCLGE_TSO_MSS_MIN_S, tso_mss_max); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_alloc_tqps(struct hclge_dev *hdev) +{ + struct hclge_tqp *tqp; + int i; + + hdev->htqp = devm_kcalloc(&hdev->pdev->dev, hdev->num_tqps, + sizeof(struct hclge_tqp), GFP_KERNEL); + if (!hdev->htqp) + return -ENOMEM; + + tqp = hdev->htqp; + + for (i = 0; i < hdev->num_tqps; i++) { + tqp->dev = &hdev->pdev->dev; + tqp->index = i; + + tqp->q.ae_algo = &ae_algo; + tqp->q.buf_size = hdev->rx_buf_len; + tqp->q.desc_num = hdev->num_desc; + tqp->q.io_base = hdev->hw.io_base + HCLGE_TQP_REG_OFFSET + + i * HCLGE_TQP_REG_SIZE; + + tqp++; + } + + return 0; +} + +static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id, + u16 tqp_pid, u16 tqp_vid, bool is_pf) +{ + struct hclge_tqp_map *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SET_TQP_MAP, false); + + req = (struct hclge_tqp_map *)desc.data; + req->tqp_id = cpu_to_le16(tqp_pid); + req->tqp_vf = cpu_to_le16(func_id); + req->tqp_flag = !is_pf << HCLGE_TQP_MAP_TYPE_B | + 1 << HCLGE_TQP_MAP_EN_B; + req->tqp_vid = cpu_to_le16(tqp_vid); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "TQP map failed %d.\n", + ret); + return ret; + } + + return 0; +} + +static int hclge_assign_tqp(struct hclge_vport *vport, + struct hnae3_queue **tqp, u16 num_tqps) +{ + struct hclge_dev *hdev = vport->back; + int i, alloced, func_id, ret; + bool is_pf; + + func_id = vport->vport_id; + is_pf = (vport->vport_id == 0) ? true : false; + + for (i = 0, alloced = 0; i < hdev->num_tqps && + alloced < num_tqps; i++) { + if (!hdev->htqp[i].alloced) { + hdev->htqp[i].q.handle = &vport->nic; + hdev->htqp[i].q.tqp_index = alloced; + tqp[alloced] = &hdev->htqp[i].q; + hdev->htqp[i].alloced = true; + ret = hclge_map_tqps_to_func(hdev, func_id, + hdev->htqp[i].index, + alloced, is_pf); + if (ret) + return ret; + + alloced++; + } + } + vport->alloc_tqps = num_tqps; + + return 0; +} + +static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps) +{ + struct hnae3_handle *nic = &vport->nic; + struct hnae3_knic_private_info *kinfo = &nic->kinfo; + struct hclge_dev *hdev = vport->back; + int i, ret; + + kinfo->num_desc = hdev->num_desc; + kinfo->rx_buf_len = hdev->rx_buf_len; + kinfo->num_tc = min_t(u16, num_tqps, hdev->tm_info.num_tc); + kinfo->rss_size + = min_t(u16, hdev->rss_size_max, num_tqps / kinfo->num_tc); + kinfo->num_tqps = kinfo->rss_size * kinfo->num_tc; + + for (i = 0; i < HNAE3_MAX_TC; i++) { + if (hdev->hw_tc_map & BIT(i)) { + kinfo->tc_info[i].enable = true; + kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size; + kinfo->tc_info[i].tqp_count = kinfo->rss_size; + kinfo->tc_info[i].tc = i; + } else { + /* Set to default queue if TC is disable */ + kinfo->tc_info[i].enable = false; + kinfo->tc_info[i].tqp_offset = 0; + kinfo->tc_info[i].tqp_count = 1; + kinfo->tc_info[i].tc = 0; + } + } + + kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps, + sizeof(struct hnae3_queue *), GFP_KERNEL); + if (!kinfo->tqp) + return -ENOMEM; + + ret = hclge_assign_tqp(vport, kinfo->tqp, kinfo->num_tqps); + if (ret) { + dev_err(&hdev->pdev->dev, "fail to assign TQPs %d.\n", ret); + return -EINVAL; + } + + return 0; +} + +static void hclge_unic_setup(struct hclge_vport *vport, u16 num_tqps) +{ + /* this would be initialized later */ +} + +static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps) +{ + struct hnae3_handle *nic = &vport->nic; + struct hclge_dev *hdev = vport->back; + int ret; + + nic->pdev = hdev->pdev; + nic->ae_algo = &ae_algo; + nic->numa_node_mask = hdev->numa_node_mask; + + if (hdev->ae_dev->dev_type == HNAE3_DEV_KNIC) { + ret = hclge_knic_setup(vport, num_tqps); + if (ret) { + dev_err(&hdev->pdev->dev, "knic setup failed %d\n", + ret); + return ret; + } + } else { + hclge_unic_setup(vport, num_tqps); + } + + return 0; +} + +static int hclge_alloc_vport(struct hclge_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + struct hclge_vport *vport; + u32 tqp_main_vport; + u32 tqp_per_vport; + int num_vport, i; + int ret; + + /* We need to alloc a vport for main NIC of PF */ + num_vport = hdev->num_vmdq_vport + hdev->num_req_vfs + 1; + + if (hdev->num_tqps < num_vport) + num_vport = hdev->num_tqps; + + /* Alloc the same number of TQPs for every vport */ + tqp_per_vport = hdev->num_tqps / num_vport; + tqp_main_vport = tqp_per_vport + hdev->num_tqps % num_vport; + + vport = devm_kcalloc(&pdev->dev, num_vport, sizeof(struct hclge_vport), + GFP_KERNEL); + if (!vport) + return -ENOMEM; + + hdev->vport = vport; + hdev->num_alloc_vport = num_vport; + +#ifdef CONFIG_PCI_IOV + /* Enable SRIOV */ + if (hdev->num_req_vfs) { + dev_info(&pdev->dev, "active VFs(%d) found, enabling SRIOV\n", + hdev->num_req_vfs); + ret = pci_enable_sriov(hdev->pdev, hdev->num_req_vfs); + if (ret) { + hdev->num_alloc_vfs = 0; + dev_err(&pdev->dev, "SRIOV enable failed %d\n", + ret); + return ret; + } + } + hdev->num_alloc_vfs = hdev->num_req_vfs; +#endif + + for (i = 0; i < num_vport; i++) { + vport->back = hdev; + vport->vport_id = i; + + if (i == 0) + ret = hclge_vport_setup(vport, tqp_main_vport); + else + ret = hclge_vport_setup(vport, tqp_per_vport); + if (ret) { + dev_err(&pdev->dev, + "vport setup failed for vport %d, %d\n", + i, ret); + return ret; + } + + vport++; + } + + return 0; +} + +static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, u16 buf_size) +{ +/* TX buffer size is unit by 128 byte */ +#define HCLGE_BUF_SIZE_UNIT_SHIFT 7 +#define HCLGE_BUF_SIZE_UPDATE_EN_MSK BIT(15) + struct hclge_tx_buff_alloc *req; + struct hclge_desc desc; + int ret; + u8 i; + + req = (struct hclge_tx_buff_alloc *)desc.data; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0); + for (i = 0; i < HCLGE_TC_NUM; i++) + req->tx_pkt_buff[i] = + cpu_to_le16((buf_size >> HCLGE_BUF_SIZE_UNIT_SHIFT) | + HCLGE_BUF_SIZE_UPDATE_EN_MSK); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "tx buffer alloc cmd failed %d.\n", + ret); + return ret; + } + + return 0; +} + +static int hclge_tx_buffer_alloc(struct hclge_dev *hdev, u32 buf_size) +{ + int ret = hclge_cmd_alloc_tx_buff(hdev, buf_size); + + if (ret) { + dev_err(&hdev->pdev->dev, + "tx buffer alloc failed %d\n", ret); + return ret; + } + + return 0; +} + +static int hclge_get_tc_num(struct hclge_dev *hdev) +{ + int i, cnt = 0; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) + if (hdev->hw_tc_map & BIT(i)) + cnt++; + return cnt; +} + +static int hclge_get_pfc_enalbe_num(struct hclge_dev *hdev) +{ + int i, cnt = 0; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) + if (hdev->hw_tc_map & BIT(i) && + hdev->tm_info.hw_pfc_map & BIT(i)) + cnt++; + return cnt; +} + +/* Get the number of pfc enabled TCs, which have private buffer */ +static int hclge_get_pfc_priv_num(struct hclge_dev *hdev) +{ + struct hclge_priv_buf *priv; + int i, cnt = 0; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + priv = &hdev->priv_buf[i]; + if ((hdev->tm_info.hw_pfc_map & BIT(i)) && + priv->enable) + cnt++; + } + + return cnt; +} + +/* Get the number of pfc disabled TCs, which have private buffer */ +static int hclge_get_no_pfc_priv_num(struct hclge_dev *hdev) +{ + struct hclge_priv_buf *priv; + int i, cnt = 0; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + priv = &hdev->priv_buf[i]; + if (hdev->hw_tc_map & BIT(i) && + !(hdev->tm_info.hw_pfc_map & BIT(i)) && + priv->enable) + cnt++; + } + + return cnt; +} + +static u32 hclge_get_rx_priv_buff_alloced(struct hclge_dev *hdev) +{ + struct hclge_priv_buf *priv; + u32 rx_priv = 0; + int i; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + priv = &hdev->priv_buf[i]; + if (priv->enable) + rx_priv += priv->buf_size; + } + return rx_priv; +} + +static bool hclge_is_rx_buf_ok(struct hclge_dev *hdev, u32 rx_all) +{ + u32 shared_buf_min, shared_buf_tc, shared_std; + int tc_num, pfc_enable_num; + u32 shared_buf; + u32 rx_priv; + int i; + + tc_num = hclge_get_tc_num(hdev); + pfc_enable_num = hclge_get_pfc_enalbe_num(hdev); + + shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV; + shared_buf_tc = pfc_enable_num * hdev->mps + + (tc_num - pfc_enable_num) * hdev->mps / 2 + + hdev->mps; + shared_std = max_t(u32, shared_buf_min, shared_buf_tc); + + rx_priv = hclge_get_rx_priv_buff_alloced(hdev); + if (rx_all <= rx_priv + shared_std) + return false; + + shared_buf = rx_all - rx_priv; + hdev->s_buf.buf_size = shared_buf; + hdev->s_buf.self.high = shared_buf; + hdev->s_buf.self.low = 2 * hdev->mps; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + if ((hdev->hw_tc_map & BIT(i)) && + (hdev->tm_info.hw_pfc_map & BIT(i))) { + hdev->s_buf.tc_thrd[i].low = hdev->mps; + hdev->s_buf.tc_thrd[i].high = 2 * hdev->mps; + } else { + hdev->s_buf.tc_thrd[i].low = 0; + hdev->s_buf.tc_thrd[i].high = hdev->mps; + } + } + + return true; +} + +/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs + * @hdev: pointer to struct hclge_dev + * @tx_size: the allocated tx buffer for all TCs + * @return: 0: calculate sucessful, negative: fail + */ +int hclge_rx_buffer_calc(struct hclge_dev *hdev, u32 tx_size) +{ + u32 rx_all = hdev->pkt_buf_size - tx_size; + int no_pfc_priv_num, pfc_priv_num; + struct hclge_priv_buf *priv; + int i; + + /* step 1, try to alloc private buffer for all enabled tc */ + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + priv = &hdev->priv_buf[i]; + if (hdev->hw_tc_map & BIT(i)) { + priv->enable = 1; + if (hdev->tm_info.hw_pfc_map & BIT(i)) { + priv->wl.low = hdev->mps; + priv->wl.high = priv->wl.low + hdev->mps; + priv->buf_size = priv->wl.high + + HCLGE_DEFAULT_DV; + } else { + priv->wl.low = 0; + priv->wl.high = 2 * hdev->mps; + priv->buf_size = priv->wl.high; + } + } + } + + if (hclge_is_rx_buf_ok(hdev, rx_all)) + return 0; + + /* step 2, try to decrease the buffer size of + * no pfc TC's private buffer + */ + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + priv = &hdev->priv_buf[i]; + + if (hdev->hw_tc_map & BIT(i)) + priv->enable = 1; + + if (hdev->tm_info.hw_pfc_map & BIT(i)) { + priv->wl.low = 128; + priv->wl.high = priv->wl.low + hdev->mps; + priv->buf_size = priv->wl.high + HCLGE_DEFAULT_DV; + } else { + priv->wl.low = 0; + priv->wl.high = hdev->mps; + priv->buf_size = priv->wl.high; + } + } + + if (hclge_is_rx_buf_ok(hdev, rx_all)) + return 0; + + /* step 3, try to reduce the number of pfc disabled TCs, + * which have private buffer + */ + /* get the total no pfc enable TC number, which have private buffer */ + no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev); + + /* let the last to be cleared first */ + for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) { + priv = &hdev->priv_buf[i]; + + if (hdev->hw_tc_map & BIT(i) && + !(hdev->tm_info.hw_pfc_map & BIT(i))) { + /* Clear the no pfc TC private buffer */ + priv->wl.low = 0; + priv->wl.high = 0; + priv->buf_size = 0; + priv->enable = 0; + no_pfc_priv_num--; + } + + if (hclge_is_rx_buf_ok(hdev, rx_all) || + no_pfc_priv_num == 0) + break; + } + + if (hclge_is_rx_buf_ok(hdev, rx_all)) + return 0; + + /* step 4, try to reduce the number of pfc enabled TCs + * which have private buffer. + */ + pfc_priv_num = hclge_get_pfc_priv_num(hdev); + + /* let the last to be cleared first */ + for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) { + priv = &hdev->priv_buf[i]; + + if (hdev->hw_tc_map & BIT(i) && + hdev->tm_info.hw_pfc_map & BIT(i)) { + /* Reduce the number of pfc TC with private buffer */ + priv->wl.low = 0; + priv->enable = 0; + priv->wl.high = 0; + priv->buf_size = 0; + pfc_priv_num--; + } + + if (hclge_is_rx_buf_ok(hdev, rx_all) || + pfc_priv_num == 0) + break; + } + if (hclge_is_rx_buf_ok(hdev, rx_all)) + return 0; + + return -ENOMEM; +} + +static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev) +{ + struct hclge_rx_priv_buff *req; + struct hclge_desc desc; + int ret; + int i; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_PRIV_BUFF_ALLOC, false); + req = (struct hclge_rx_priv_buff *)desc.data; + + /* Alloc private buffer TCs */ + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + struct hclge_priv_buf *priv = &hdev->priv_buf[i]; + + req->buf_num[i] = + cpu_to_le16(priv->buf_size >> HCLGE_BUF_UNIT_S); + req->buf_num[i] |= + cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B); + } + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "rx private buffer alloc cmd failed %d\n", ret); + return ret; + } + + return 0; +} + +#define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0) + +static int hclge_rx_priv_wl_config(struct hclge_dev *hdev) +{ + struct hclge_rx_priv_wl_buf *req; + struct hclge_priv_buf *priv; + struct hclge_desc desc[2]; + int i, j; + int ret; + + for (i = 0; i < 2; i++) { + hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_RX_PRIV_WL_ALLOC, + false); + req = (struct hclge_rx_priv_wl_buf *)desc[i].data; + + /* The first descriptor set the NEXT bit to 1 */ + if (i == 0) + desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + else + desc[i].flag &= ~cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + + for (j = 0; j < HCLGE_TC_NUM_ONE_DESC; j++) { + priv = &hdev->priv_buf[i * HCLGE_TC_NUM_ONE_DESC + j]; + req->tc_wl[j].high = + cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S); + req->tc_wl[j].high |= + cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.high) << + HCLGE_RX_PRIV_EN_B); + req->tc_wl[j].low = + cpu_to_le16(priv->wl.low >> HCLGE_BUF_UNIT_S); + req->tc_wl[j].low |= + cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.low) << + HCLGE_RX_PRIV_EN_B); + } + } + + /* Send 2 descriptor at one time */ + ret = hclge_cmd_send(&hdev->hw, desc, 2); + if (ret) { + dev_err(&hdev->pdev->dev, + "rx private waterline config cmd failed %d\n", + ret); + return ret; + } + return 0; +} + +static int hclge_common_thrd_config(struct hclge_dev *hdev) +{ + struct hclge_shared_buf *s_buf = &hdev->s_buf; + struct hclge_rx_com_thrd *req; + struct hclge_desc desc[2]; + struct hclge_tc_thrd *tc; + int i, j; + int ret; + + for (i = 0; i < 2; i++) { + hclge_cmd_setup_basic_desc(&desc[i], + HCLGE_OPC_RX_COM_THRD_ALLOC, false); + req = (struct hclge_rx_com_thrd *)&desc[i].data; + + /* The first descriptor set the NEXT bit to 1 */ + if (i == 0) + desc[i].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + else + desc[i].flag &= ~cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + + for (j = 0; j < HCLGE_TC_NUM_ONE_DESC; j++) { + tc = &s_buf->tc_thrd[i * HCLGE_TC_NUM_ONE_DESC + j]; + + req->com_thrd[j].high = + cpu_to_le16(tc->high >> HCLGE_BUF_UNIT_S); + req->com_thrd[j].high |= + cpu_to_le16(HCLGE_PRIV_ENABLE(tc->high) << + HCLGE_RX_PRIV_EN_B); + req->com_thrd[j].low = + cpu_to_le16(tc->low >> HCLGE_BUF_UNIT_S); + req->com_thrd[j].low |= + cpu_to_le16(HCLGE_PRIV_ENABLE(tc->low) << + HCLGE_RX_PRIV_EN_B); + } + } + + /* Send 2 descriptors at one time */ + ret = hclge_cmd_send(&hdev->hw, desc, 2); + if (ret) { + dev_err(&hdev->pdev->dev, + "common threshold config cmd failed %d\n", ret); + return ret; + } + return 0; +} + +static int hclge_common_wl_config(struct hclge_dev *hdev) +{ + struct hclge_shared_buf *buf = &hdev->s_buf; + struct hclge_rx_com_wl *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_COM_WL_ALLOC, false); + + req = (struct hclge_rx_com_wl *)desc.data; + req->com_wl.high = cpu_to_le16(buf->self.high >> HCLGE_BUF_UNIT_S); + req->com_wl.high |= + cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.high) << + HCLGE_RX_PRIV_EN_B); + + req->com_wl.low = cpu_to_le16(buf->self.low >> HCLGE_BUF_UNIT_S); + req->com_wl.low |= + cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.low) << + HCLGE_RX_PRIV_EN_B); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "common waterline config cmd failed %d\n", ret); + return ret; + } + + return 0; +} + +int hclge_buffer_alloc(struct hclge_dev *hdev) +{ + u32 tx_buf_size = HCLGE_DEFAULT_TX_BUF; + int ret; + + hdev->priv_buf = devm_kmalloc_array(&hdev->pdev->dev, HCLGE_MAX_TC_NUM, + sizeof(struct hclge_priv_buf), + GFP_KERNEL | __GFP_ZERO); + if (!hdev->priv_buf) + return -ENOMEM; + + ret = hclge_tx_buffer_alloc(hdev, tx_buf_size); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not alloc tx buffers %d\n", ret); + return ret; + } + + ret = hclge_rx_buffer_calc(hdev, tx_buf_size); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not calc rx priv buffer size for all TCs %d\n", + ret); + return ret; + } + + ret = hclge_rx_priv_buf_alloc(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, "could not alloc rx priv buffer %d\n", + ret); + return ret; + } + + ret = hclge_rx_priv_wl_config(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not configure rx private waterline %d\n", ret); + return ret; + } + + ret = hclge_common_thrd_config(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not configure common threshold %d\n", ret); + return ret; + } + + ret = hclge_common_wl_config(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not configure common waterline %d\n", ret); + return ret; + } + + return 0; +} + +static int hclge_init_roce_base_info(struct hclge_vport *vport) +{ + struct hnae3_handle *roce = &vport->roce; + struct hnae3_handle *nic = &vport->nic; + + roce->rinfo.num_vectors = vport->back->num_roce_msix; + + if (vport->back->num_msi_left < vport->roce.rinfo.num_vectors || + vport->back->num_msi_left == 0) + return -EINVAL; + + roce->rinfo.base_vector = vport->back->roce_base_vector; + + roce->rinfo.netdev = nic->kinfo.netdev; + roce->rinfo.roce_io_base = vport->back->hw.io_base; + + roce->pdev = nic->pdev; + roce->ae_algo = nic->ae_algo; + roce->numa_node_mask = nic->numa_node_mask; + + return 0; +} + +static int hclge_init_msix(struct hclge_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int ret, i; + + hdev->msix_entries = devm_kcalloc(&pdev->dev, hdev->num_msi, + sizeof(struct msix_entry), + GFP_KERNEL); + if (!hdev->msix_entries) + return -ENOMEM; + + hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi, + sizeof(u16), GFP_KERNEL); + if (!hdev->vector_status) + return -ENOMEM; + + for (i = 0; i < hdev->num_msi; i++) { + hdev->msix_entries[i].entry = i; + hdev->vector_status[i] = HCLGE_INVALID_VPORT; + } + + hdev->num_msi_left = hdev->num_msi; + hdev->base_msi_vector = hdev->pdev->irq; + hdev->roce_base_vector = hdev->base_msi_vector + + HCLGE_ROCE_VECTOR_OFFSET; + + ret = pci_enable_msix_range(hdev->pdev, hdev->msix_entries, + hdev->num_msi, hdev->num_msi); + if (ret < 0) { + dev_info(&hdev->pdev->dev, + "MSI-X vector alloc failed: %d\n", ret); + return ret; + } + + return 0; +} + +static int hclge_init_msi(struct hclge_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int vectors; + int i; + + hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi, + sizeof(u16), GFP_KERNEL); + if (!hdev->vector_status) + return -ENOMEM; + + for (i = 0; i < hdev->num_msi; i++) + hdev->vector_status[i] = HCLGE_INVALID_VPORT; + + vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi, PCI_IRQ_MSI); + if (vectors < 0) { + dev_err(&pdev->dev, "MSI vectors enable failed %d\n", vectors); + return -EINVAL; + } + hdev->num_msi = vectors; + hdev->num_msi_left = vectors; + hdev->base_msi_vector = pdev->irq; + hdev->roce_base_vector = hdev->base_msi_vector + + HCLGE_ROCE_VECTOR_OFFSET; + + return 0; +} + +static void hclge_check_speed_dup(struct hclge_dev *hdev, int duplex, int speed) +{ + struct hclge_mac *mac = &hdev->hw.mac; + + if ((speed == HCLGE_MAC_SPEED_10M) || (speed == HCLGE_MAC_SPEED_100M)) + mac->duplex = (u8)duplex; + else + mac->duplex = HCLGE_MAC_FULL; + + mac->speed = speed; +} + +int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) +{ + struct hclge_config_mac_speed_dup *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_config_mac_speed_dup *)desc.data; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false); + + hnae_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex); + + switch (speed) { + case HCLGE_MAC_SPEED_10M: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 6); + break; + case HCLGE_MAC_SPEED_100M: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 7); + break; + case HCLGE_MAC_SPEED_1G: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 0); + break; + case HCLGE_MAC_SPEED_10G: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 1); + break; + case HCLGE_MAC_SPEED_25G: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 2); + break; + case HCLGE_MAC_SPEED_40G: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 3); + break; + case HCLGE_MAC_SPEED_50G: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 4); + break; + case HCLGE_MAC_SPEED_100G: + hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M, + HCLGE_CFG_SPEED_S, 5); + break; + default: + dev_err(&hdev->pdev->dev, "invalid speed (%d)\n", speed); + return -EINVAL; + } + + hnae_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B, + 1); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "mac speed/duplex config cmd failed %d.\n", ret); + return ret; + } + + hclge_check_speed_dup(hdev, duplex, speed); + + return 0; +} + +static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, + u8 duplex) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + return hclge_cfg_mac_speed_dup(hdev, speed, duplex); +} + +static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed, + u8 *duplex) +{ + struct hclge_query_an_speed_dup *req; + struct hclge_desc desc; + int speed_tmp; + int ret; + + req = (struct hclge_query_an_speed_dup *)desc.data; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "mac speed/autoneg/duplex query cmd failed %d\n", + ret); + return ret; + } + + *duplex = hnae_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B); + speed_tmp = hnae_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M, + HCLGE_QUERY_SPEED_S); + + ret = hclge_parse_speed(speed_tmp, speed); + if (ret) { + dev_err(&hdev->pdev->dev, + "could not parse speed(=%d), %d\n", speed_tmp, ret); + return -EIO; + } + + return 0; +} + +static int hclge_query_autoneg_result(struct hclge_dev *hdev) +{ + struct hclge_mac *mac = &hdev->hw.mac; + struct hclge_query_an_speed_dup *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_query_an_speed_dup *)desc.data; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "autoneg result query cmd failed %d.\n", ret); + return ret; + } + + mac->autoneg = hnae_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_AN_B); + + return 0; +} + +static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) +{ + struct hclge_config_auto_neg *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false); + + req = (struct hclge_config_auto_neg *)desc.data; + hnae_set_bit(req->cfg_an_cmd_flag, HCLGE_MAC_CFG_AN_EN_B, !!enable); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "auto neg set cmd failed %d.\n", + ret); + return ret; + } + + return 0; +} + +static int hclge_set_autoneg(struct hnae3_handle *handle, bool enable) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + return hclge_set_autoneg_en(hdev, enable); +} + +static int hclge_get_autoneg(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + hclge_query_autoneg_result(hdev); + + return hdev->hw.mac.autoneg; +} + +static int hclge_mac_init(struct hclge_dev *hdev) +{ + struct hclge_mac *mac = &hdev->hw.mac; + int ret; + + ret = hclge_cfg_mac_speed_dup(hdev, hdev->hw.mac.speed, HCLGE_MAC_FULL); + if (ret) { + dev_err(&hdev->pdev->dev, + "Config mac speed dup fail ret=%d\n", ret); + return ret; + } + + mac->link = 0; + + ret = hclge_mac_mdio_config(hdev); + if (ret) { + dev_warn(&hdev->pdev->dev, + "mdio config fail ret=%d\n", ret); + return ret; + } + + /* Initialize the MTA table work mode */ + hdev->accept_mta_mc = true; + hdev->enable_mta = true; + hdev->mta_mac_sel_type = HCLGE_MAC_ADDR_47_36; + + ret = hclge_set_mta_filter_mode(hdev, + hdev->mta_mac_sel_type, + hdev->enable_mta); + if (ret) { + dev_err(&hdev->pdev->dev, "set mta filter mode failed %d\n", + ret); + return ret; + } + + return hclge_cfg_func_mta_filter(hdev, 0, hdev->accept_mta_mc); +} + +static void hclge_task_schedule(struct hclge_dev *hdev) +{ + if (!test_bit(HCLGE_STATE_DOWN, &hdev->state) && + !test_bit(HCLGE_STATE_REMOVING, &hdev->state) && + !test_and_set_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)) + (void)schedule_work(&hdev->service_task); +} + +static int hclge_get_mac_link_status(struct hclge_dev *hdev) +{ + struct hclge_link_status *req; + struct hclge_desc desc; + int link_status; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_LINK_STATUS, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "get link status cmd failed %d\n", + ret); + return ret; + } + + req = (struct hclge_link_status *)desc.data; + link_status = req->status & HCLGE_LINK_STATUS; + + return !!link_status; +} + +static int hclge_get_mac_phy_link(struct hclge_dev *hdev) +{ + int mac_state; + int link_stat; + + mac_state = hclge_get_mac_link_status(hdev); + + if (hdev->hw.mac.phydev) { + if (!genphy_read_status(hdev->hw.mac.phydev)) + link_stat = mac_state & + hdev->hw.mac.phydev->link; + else + link_stat = 0; + + } else { + link_stat = mac_state; + } + + return !!link_stat; +} + +static void hclge_update_link_status(struct hclge_dev *hdev) +{ + struct hnae3_client *client = hdev->nic_client; + struct hnae3_handle *handle; + int state; + int i; + + if (!client) + return; + state = hclge_get_mac_phy_link(hdev); + if (state != hdev->hw.mac.link) { + for (i = 0; i < hdev->num_vmdq_vport + 1; i++) { + handle = &hdev->vport[i].nic; + client->ops->link_status_change(handle, state); + } + hdev->hw.mac.link = state; + } +} + +static int hclge_update_speed_duplex(struct hclge_dev *hdev) +{ + struct hclge_mac mac = hdev->hw.mac; + u8 duplex; + int speed; + int ret; + + /* get the speed and duplex as autoneg'result from mac cmd when phy + * doesn't exit. + */ + if (mac.phydev) + return 0; + + /* update mac->antoneg. */ + ret = hclge_query_autoneg_result(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "autoneg result query failed %d\n", ret); + return ret; + } + + if (!mac.autoneg) + return 0; + + ret = hclge_query_mac_an_speed_dup(hdev, &speed, &duplex); + if (ret) { + dev_err(&hdev->pdev->dev, + "mac autoneg/speed/duplex query failed %d\n", ret); + return ret; + } + + if ((mac.speed != speed) || (mac.duplex != duplex)) { + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex); + if (ret) { + dev_err(&hdev->pdev->dev, + "mac speed/duplex config failed %d\n", ret); + return ret; + } + } + + return 0; +} + +static int hclge_update_speed_duplex_h(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + return hclge_update_speed_duplex(hdev); +} + +static int hclge_get_status(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + hclge_update_link_status(hdev); + + return hdev->hw.mac.link; +} + +static void hclge_service_timer(unsigned long data) +{ + struct hclge_dev *hdev = (struct hclge_dev *)data; + (void)mod_timer(&hdev->service_timer, jiffies + HZ); + + hclge_task_schedule(hdev); +} + +static void hclge_service_complete(struct hclge_dev *hdev) +{ + WARN_ON(!test_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)); + + /* Flush memory before next watchdog */ + smp_mb__before_atomic(); + clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); +} + +static void hclge_service_task(struct work_struct *work) +{ + struct hclge_dev *hdev = + container_of(work, struct hclge_dev, service_task); + + hclge_update_speed_duplex(hdev); + hclge_update_link_status(hdev); + hclge_update_stats_for_all(hdev); + hclge_service_complete(hdev); +} + +static void hclge_disable_sriov(struct hclge_dev *hdev) +{ + /* If our VFs are assigned we cannot shut down SR-IOV + * without causing issues, so just leave the hardware + * available but disabled + */ + if (pci_vfs_assigned(hdev->pdev)) { + dev_warn(&hdev->pdev->dev, + "disabling driver while VFs are assigned\n"); + return; + } + + pci_disable_sriov(hdev->pdev); +} + +struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle) +{ + /* VF handle has no client */ + if (!handle->client) + return container_of(handle, struct hclge_vport, nic); + else if (handle->client->type == HNAE3_CLIENT_ROCE) + return container_of(handle, struct hclge_vport, roce); + else + return container_of(handle, struct hclge_vport, nic); +} + +static int hclge_get_vector(struct hnae3_handle *handle, u16 vector_num, + struct hnae3_vector_info *vector_info) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hnae3_vector_info *vector = vector_info; + struct hclge_dev *hdev = vport->back; + int alloc = 0; + int i, j; + + vector_num = min(hdev->num_msi_left, vector_num); + + for (j = 0; j < vector_num; j++) { + for (i = 1; i < hdev->num_msi; i++) { + if (hdev->vector_status[i] == HCLGE_INVALID_VPORT) { + vector->vector = pci_irq_vector(hdev->pdev, i); + vector->io_addr = hdev->hw.io_base + + HCLGE_VECTOR_REG_BASE + + (i - 1) * HCLGE_VECTOR_REG_OFFSET + + vport->vport_id * + HCLGE_VECTOR_VF_OFFSET; + hdev->vector_status[i] = vport->vport_id; + + vector++; + alloc++; + + break; + } + } + } + hdev->num_msi_left -= alloc; + hdev->num_msi_used += alloc; + + return alloc; +} + +static int hclge_get_vector_index(struct hclge_dev *hdev, int vector) +{ + int i; + + for (i = 0; i < hdev->num_msi; i++) { + if (hdev->msix_entries) { + if (vector == hdev->msix_entries[i].vector) + return i; + } else { + if (vector == (hdev->base_msi_vector + i)) + return i; + } + } + return -EINVAL; +} + +static u32 hclge_get_rss_key_size(struct hnae3_handle *handle) +{ + return HCLGE_RSS_KEY_SIZE; +} + +static u32 hclge_get_rss_indir_size(struct hnae3_handle *handle) +{ + return HCLGE_RSS_IND_TBL_SIZE; +} + +static int hclge_get_rss_algo(struct hclge_dev *hdev) +{ + struct hclge_rss_config *req; + struct hclge_desc desc; + int rss_hash_algo; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_GENERIC_CONFIG, true); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get link status error, status =%d\n", ret); + return ret; + } + + req = (struct hclge_rss_config *)desc.data; + rss_hash_algo = (req->hash_config & HCLGE_RSS_HASH_ALGO_MASK); + + if (rss_hash_algo == HCLGE_RSS_HASH_ALGO_TOEPLITZ) + return ETH_RSS_HASH_TOP; + + return -EINVAL; +} + +static int hclge_set_rss_algo_key(struct hclge_dev *hdev, + const u8 hfunc, const u8 *key) +{ + struct hclge_rss_config *req; + struct hclge_desc desc; + int key_offset; + int key_size; + int ret; + + req = (struct hclge_rss_config *)desc.data; + + for (key_offset = 0; key_offset < 3; key_offset++) { + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_GENERIC_CONFIG, + false); + + req->hash_config |= (hfunc & HCLGE_RSS_HASH_ALGO_MASK); + req->hash_config |= (key_offset << HCLGE_RSS_HASH_KEY_OFFSET_B); + + if (key_offset == 2) + key_size = + HCLGE_RSS_KEY_SIZE - HCLGE_RSS_HASH_KEY_NUM * 2; + else + key_size = HCLGE_RSS_HASH_KEY_NUM; + + memcpy(req->hash_key, + key + key_offset * HCLGE_RSS_HASH_KEY_NUM, key_size); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Configure RSS config fail, status = %d\n", + ret); + return ret; + } + } + return 0; +} + +static int hclge_set_rss_indir_table(struct hclge_dev *hdev, const u32 *indir) +{ + struct hclge_rss_indirection_table *req; + struct hclge_desc desc; + int i, j; + int ret; + + req = (struct hclge_rss_indirection_table *)desc.data; + + for (i = 0; i < HCLGE_RSS_CFG_TBL_NUM; i++) { + hclge_cmd_setup_basic_desc + (&desc, HCLGE_OPC_RSS_INDIR_TABLE, false); + + req->start_table_index = i * HCLGE_RSS_CFG_TBL_SIZE; + req->rss_set_bitmap = HCLGE_RSS_SET_BITMAP_MSK; + + for (j = 0; j < HCLGE_RSS_CFG_TBL_SIZE; j++) + req->rss_result[j] = + indir[i * HCLGE_RSS_CFG_TBL_SIZE + j]; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Configure rss indir table fail,status = %d\n", + ret); + return ret; + } + } + return 0; +} + +static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid, + u16 *tc_size, u16 *tc_offset) +{ + struct hclge_rss_tc_mode *req; + struct hclge_desc desc; + int ret; + int i; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_TC_MODE, false); + req = (struct hclge_rss_tc_mode *)desc.data; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + hnae_set_bit(req->rss_tc_mode[i], HCLGE_RSS_TC_VALID_B, + (tc_valid[i] & 0x1)); + hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_SIZE_M, + HCLGE_RSS_TC_SIZE_S, tc_size[i]); + hnae_set_field(req->rss_tc_mode[i], HCLGE_RSS_TC_OFFSET_M, + HCLGE_RSS_TC_OFFSET_S, tc_offset[i]); + } + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Configure rss tc mode fail, status = %d\n", ret); + return ret; + } + + return 0; +} + +static int hclge_set_rss_input_tuple(struct hclge_dev *hdev) +{ +#define HCLGE_RSS_INPUT_TUPLE_OTHER 0xf +#define HCLGE_RSS_INPUT_TUPLE_SCTP 0x1f + struct hclge_rss_input_tuple *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RSS_INPUT_TUPLE, false); + + req = (struct hclge_rss_input_tuple *)desc.data; + req->ipv4_tcp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + req->ipv4_udp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + req->ipv4_sctp_en = HCLGE_RSS_INPUT_TUPLE_SCTP; + req->ipv4_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + req->ipv6_tcp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + req->ipv6_udp_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + req->ipv6_sctp_en = HCLGE_RSS_INPUT_TUPLE_SCTP; + req->ipv6_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Configure rss input fail, status = %d\n", ret); + return ret; + } + + return 0; +} + +static int hclge_get_rss(struct hnae3_handle *handle, u32 *indir, + u8 *key, u8 *hfunc) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int i; + + /* Get hash algorithm */ + if (hfunc) + *hfunc = hclge_get_rss_algo(hdev); + + /* Get the RSS Key required by the user */ + if (key) + memcpy(key, vport->rss_hash_key, HCLGE_RSS_KEY_SIZE); + + /* Get indirect table */ + if (indir) + for (i = 0; i < HCLGE_RSS_IND_TBL_SIZE; i++) + indir[i] = vport->rss_indirection_tbl[i]; + + return 0; +} + +static int hclge_set_rss(struct hnae3_handle *handle, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u8 hash_algo; + int ret, i; + + /* Set the RSS Hash Key if specififed by the user */ + if (key) { + /* Update the shadow RSS key with user specified qids */ + memcpy(vport->rss_hash_key, key, HCLGE_RSS_KEY_SIZE); + + if (hfunc == ETH_RSS_HASH_TOP || + hfunc == ETH_RSS_HASH_NO_CHANGE) + hash_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ; + else + return -EINVAL; + ret = hclge_set_rss_algo_key(hdev, hash_algo, key); + if (ret) + return ret; + } + + /* Update the shadow RSS table with user specified qids */ + for (i = 0; i < HCLGE_RSS_IND_TBL_SIZE; i++) + vport->rss_indirection_tbl[i] = indir[i]; + + /* Update the hardware */ + ret = hclge_set_rss_indir_table(hdev, indir); + return ret; +} + +static int hclge_get_tc_size(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + return hdev->rss_size_max; +} + +static int hclge_rss_init_hw(struct hclge_dev *hdev) +{ + const u8 hfunc = HCLGE_RSS_HASH_ALGO_TOEPLITZ; + struct hclge_vport *vport = hdev->vport; + u16 tc_offset[HCLGE_MAX_TC_NUM]; + u8 rss_key[HCLGE_RSS_KEY_SIZE]; + u16 tc_valid[HCLGE_MAX_TC_NUM]; + u16 tc_size[HCLGE_MAX_TC_NUM]; + u32 *rss_indir = NULL; + const u8 *key; + int i, ret, j; + + rss_indir = kcalloc(HCLGE_RSS_IND_TBL_SIZE, sizeof(u32), GFP_KERNEL); + if (!rss_indir) + return -ENOMEM; + + /* Get default RSS key */ + netdev_rss_key_fill(rss_key, HCLGE_RSS_KEY_SIZE); + + /* Initialize RSS indirect table for each vport */ + for (j = 0; j < hdev->num_vmdq_vport + 1; j++) { + for (i = 0; i < HCLGE_RSS_IND_TBL_SIZE; i++) { + vport[j].rss_indirection_tbl[i] = + i % hdev->rss_size_max; + rss_indir[i] = vport[j].rss_indirection_tbl[i]; + } + } + ret = hclge_set_rss_indir_table(hdev, rss_indir); + if (ret) + goto err; + + key = rss_key; + ret = hclge_set_rss_algo_key(hdev, hfunc, key); + if (ret) + goto err; + + ret = hclge_set_rss_input_tuple(hdev); + if (ret) + goto err; + + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { + if (hdev->hw_tc_map & BIT(i)) + tc_valid[i] = 1; + else + tc_valid[i] = 0; + + switch (hdev->rss_size_max) { + case HCLGE_RSS_TC_SIZE_0: + tc_size[i] = 0; + break; + case HCLGE_RSS_TC_SIZE_1: + tc_size[i] = 1; + break; + case HCLGE_RSS_TC_SIZE_2: + tc_size[i] = 2; + break; + case HCLGE_RSS_TC_SIZE_3: + tc_size[i] = 3; + break; + case HCLGE_RSS_TC_SIZE_4: + tc_size[i] = 4; + break; + case HCLGE_RSS_TC_SIZE_5: + tc_size[i] = 5; + break; + case HCLGE_RSS_TC_SIZE_6: + tc_size[i] = 6; + break; + case HCLGE_RSS_TC_SIZE_7: + tc_size[i] = 7; + break; + default: + break; + } + tc_offset[i] = hdev->rss_size_max * i; + } + ret = hclge_set_rss_tc_mode(hdev, tc_valid, tc_size, tc_offset); + +err: + kfree(rss_indir); + + return ret; +} + +int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector_id, + struct hnae3_ring_chain_node *ring_chain) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_ctrl_vector_chain *req; + struct hnae3_ring_chain_node *node; + struct hclge_desc desc; + int ret; + int i; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ADD_RING_TO_VECTOR, false); + + req = (struct hclge_ctrl_vector_chain *)desc.data; + req->int_vector_id = vector_id; + + i = 0; + for (node = ring_chain; node; node = node->next) { + hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M, + HCLGE_INT_TYPE_S, + hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); + hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, + HCLGE_TQP_ID_S, node->tqp_index); + req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + + if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { + req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Map TQP fail, status is %d.\n", + ret); + return ret; + } + i = 0; + + hclge_cmd_setup_basic_desc(&desc, + HCLGE_OPC_ADD_RING_TO_VECTOR, + false); + req->int_vector_id = vector_id; + } + } + + if (i > 0) { + req->int_cause_num = i; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Map TQP fail, status is %d.\n", ret); + return ret; + } + } + + return 0; +} + +int hclge_map_handle_ring_to_vector(struct hnae3_handle *handle, + int vector, + struct hnae3_ring_chain_node *ring_chain) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int vector_id; + + vector_id = hclge_get_vector_index(hdev, vector); + if (vector_id < 0) { + dev_err(&hdev->pdev->dev, + "Get vector index fail. ret =%d\n", vector_id); + return vector_id; + } + + return hclge_map_vport_ring_to_vector(vport, vector_id, ring_chain); +} + +static int hclge_unmap_ring_from_vector( + struct hnae3_handle *handle, int vector, + struct hnae3_ring_chain_node *ring_chain) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_ctrl_vector_chain *req; + struct hnae3_ring_chain_node *node; + struct hclge_desc desc; + int i, vector_id; + int ret; + + vector_id = hclge_get_vector_index(hdev, vector); + if (vector_id < 0) { + dev_err(&handle->pdev->dev, + "Get vector index fail. ret =%d\n", vector_id); + return vector_id; + } + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_DEL_RING_TO_VECTOR, false); + + req = (struct hclge_ctrl_vector_chain *)desc.data; + req->int_vector_id = vector_id; + + i = 0; + for (node = ring_chain; node; node = node->next) { + hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_TYPE_M, + HCLGE_INT_TYPE_S, + hnae_get_bit(node->flag, HNAE3_RING_TYPE_B)); + hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M, + HCLGE_TQP_ID_S, node->tqp_index); + + req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]); + + if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) { + req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Unmap TQP fail, status is %d.\n", + ret); + return ret; + } + i = 0; + hclge_cmd_setup_basic_desc(&desc, + HCLGE_OPC_ADD_RING_TO_VECTOR, + false); + req->int_vector_id = vector_id; + } + } + + if (i > 0) { + req->int_cause_num = i; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Unmap TQP fail, status is %d.\n", ret); + return ret; + } + } + + return 0; +} + +int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, + struct hclge_promisc_param *param) +{ + struct hclge_promisc_cfg *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_PROMISC_MODE, false); + + req = (struct hclge_promisc_cfg *)desc.data; + req->vf_id = param->vf_id; + req->flag = (param->enable << HCLGE_PROMISC_EN_B); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Set promisc mode fail, status is %d.\n", ret); + return ret; + } + return 0; +} + +void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc, + bool en_mc, bool en_bc, int vport_id) +{ + if (!param) + return; + + memset(param, 0, sizeof(struct hclge_promisc_param)); + if (en_uc) + param->enable = HCLGE_PROMISC_EN_UC; + if (en_mc) + param->enable |= HCLGE_PROMISC_EN_MC; + if (en_bc) + param->enable |= HCLGE_PROMISC_EN_BC; + param->vf_id = vport_id; +} + +static void hclge_set_promisc_mode(struct hnae3_handle *handle, u32 en) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_promisc_param param; + + hclge_promisc_param_init(¶m, en, en, true, vport->vport_id); + hclge_cmd_set_promisc_mode(hdev, ¶m); +} + +static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) +{ + struct hclge_desc desc; + struct hclge_config_mac_mode *req = + (struct hclge_config_mac_mode *)desc.data; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_TX_EN_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_EN_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_TX_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_PAD_RX_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_TX_B, 0); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_1588_RX_B, 0); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_APP_LP_B, 0); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_LINE_LP_B, 0); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_FCS_TX_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, HCLGE_MAC_RX_FCS_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, + HCLGE_MAC_RX_FCS_STRIP_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, + HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, + HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable); + hnae_set_bit(req->txrx_pad_fcs_loop_en, + HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "mac enable fail, ret =%d.\n", ret); +} + +static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id, + int stream_id, bool enable) +{ + struct hclge_desc desc; + struct hclge_cfg_com_tqp_queue *req = + (struct hclge_cfg_com_tqp_queue *)desc.data; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false); + req->tqp_id = cpu_to_le16(tqp_id & HCLGE_RING_ID_MASK); + req->stream_id = cpu_to_le16(stream_id); + req->enable |= enable << HCLGE_TQP_ENABLE_B; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "Tqp enable fail, status =%d.\n", ret); + return ret; +} + +static void hclge_reset_tqp_stats(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hnae3_queue *queue; + struct hclge_tqp *tqp; + int i; + + for (i = 0; i < vport->alloc_tqps; i++) { + queue = handle->kinfo.tqp[i]; + tqp = container_of(queue, struct hclge_tqp, q); + memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats)); + } +} + +static int hclge_ae_start(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int i, queue_id, ret; + + for (i = 0; i < vport->alloc_tqps; i++) { + /* todo clear interrupt */ + /* ring enable */ + queue_id = hclge_get_queue_id(handle->kinfo.tqp[i]); + if (queue_id < 0) { + dev_warn(&hdev->pdev->dev, + "Get invalid queue id, ignore it\n"); + continue; + } + + hclge_tqp_enable(hdev, queue_id, 0, true); + } + /* mac enable */ + hclge_cfg_mac_mode(hdev, true); + clear_bit(HCLGE_STATE_DOWN, &hdev->state); + (void)mod_timer(&hdev->service_timer, jiffies + HZ); + + ret = hclge_mac_start_phy(hdev); + if (ret) + return ret; + + /* reset tqp stats */ + hclge_reset_tqp_stats(handle); + + return 0; +} + +static void hclge_ae_stop(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int i, queue_id; + + for (i = 0; i < vport->alloc_tqps; i++) { + /* Ring disable */ + queue_id = hclge_get_queue_id(handle->kinfo.tqp[i]); + if (queue_id < 0) { + dev_warn(&hdev->pdev->dev, + "Get invalid queue id, ignore it\n"); + continue; + } + + hclge_tqp_enable(hdev, queue_id, 0, false); + } + /* Mac disable */ + hclge_cfg_mac_mode(hdev, false); + + hclge_mac_stop_phy(hdev); + + /* reset tqp stats */ + hclge_reset_tqp_stats(handle); +} + +static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport, + u16 cmdq_resp, u8 resp_code, + enum hclge_mac_vlan_tbl_opcode op) +{ + struct hclge_dev *hdev = vport->back; + int return_status = -EIO; + + if (cmdq_resp) { + dev_err(&hdev->pdev->dev, + "cmdq execute failed for get_mac_vlan_cmd_status,status=%d.\n", + cmdq_resp); + return -EIO; + } + + if (op == HCLGE_MAC_VLAN_ADD) { + if ((!resp_code) || (resp_code == 1)) { + return_status = 0; + } else if (resp_code == 2) { + return_status = -EIO; + dev_err(&hdev->pdev->dev, + "add mac addr failed for uc_overflow.\n"); + } else if (resp_code == 3) { + return_status = -EIO; + dev_err(&hdev->pdev->dev, + "add mac addr failed for mc_overflow.\n"); + } else { + dev_err(&hdev->pdev->dev, + "add mac addr failed for undefined, code=%d.\n", + resp_code); + } + } else if (op == HCLGE_MAC_VLAN_REMOVE) { + if (!resp_code) { + return_status = 0; + } else if (resp_code == 1) { + return_status = -EIO; + dev_dbg(&hdev->pdev->dev, + "remove mac addr failed for miss.\n"); + } else { + dev_err(&hdev->pdev->dev, + "remove mac addr failed for undefined, code=%d.\n", + resp_code); + } + } else if (op == HCLGE_MAC_VLAN_LKUP) { + if (!resp_code) { + return_status = 0; + } else if (resp_code == 1) { + return_status = -EIO; + dev_dbg(&hdev->pdev->dev, + "lookup mac addr failed for miss.\n"); + } else { + dev_err(&hdev->pdev->dev, + "lookup mac addr failed for undefined, code=%d.\n", + resp_code); + } + } else { + return_status = -EIO; + dev_err(&hdev->pdev->dev, + "unknown opcode for get_mac_vlan_cmd_status,opcode=%d.\n", + op); + } + + return return_status; +} + +static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr) +{ + int word_num; + int bit_num; + + if (vfid > 255 || vfid < 0) + return -EIO; + + if (vfid >= 0 && vfid <= 191) { + word_num = vfid / 32; + bit_num = vfid % 32; + if (clr) + desc[1].data[word_num] &= ~(1 << bit_num); + else + desc[1].data[word_num] |= (1 << bit_num); + } else { + word_num = (vfid - 192) / 32; + bit_num = vfid % 32; + if (clr) + desc[2].data[word_num] &= ~(1 << bit_num); + else + desc[2].data[word_num] |= (1 << bit_num); + } + + return 0; +} + +static bool hclge_is_all_function_id_zero(struct hclge_desc *desc) +{ +#define HCLGE_DESC_NUMBER 3 +#define HCLGE_FUNC_NUMBER_PER_DESC 6 + int i, j; + + for (i = 0; i < HCLGE_DESC_NUMBER; i++) + for (j = 0; j < HCLGE_FUNC_NUMBER_PER_DESC; j++) + if (desc[i].data[j]) + return false; + + return true; +} + +static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry *new_req, + const u8 *addr) +{ + const unsigned char *mac_addr = addr; + u32 high_val = mac_addr[2] << 16 | (mac_addr[3] << 24) | + (mac_addr[0]) | (mac_addr[1] << 8); + u32 low_val = mac_addr[4] | (mac_addr[5] << 8); + + new_req->mac_addr_hi32 = cpu_to_le32(high_val); + new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff); +} + +u16 hclge_get_mac_addr_to_mta_index(struct hclge_vport *vport, + const u8 *addr) +{ + u16 high_val = addr[1] | (addr[0] << 8); + struct hclge_dev *hdev = vport->back; + u32 rsh = 4 - hdev->mta_mac_sel_type; + u16 ret_val = (high_val >> rsh) & 0xfff; + + return ret_val; +} + +static int hclge_set_mta_filter_mode(struct hclge_dev *hdev, + enum hclge_mta_dmac_sel_type mta_mac_sel, + bool enable) +{ + struct hclge_mta_filter_mode *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_mta_filter_mode *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false); + + hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B, + enable); + hnae_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M, + HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Config mat filter mode failed for cmd_send, ret =%d.\n", + ret); + return ret; + } + + return 0; +} + +int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, + u8 func_id, + bool enable) +{ + struct hclge_cfg_func_mta_filter *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_cfg_func_mta_filter *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false); + + hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B, + enable); + req->function_id = func_id; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Config func_id enable failed for cmd_send, ret =%d.\n", + ret); + return ret; + } + + return 0; +} + +static int hclge_set_mta_table_item(struct hclge_vport *vport, + u16 idx, + bool enable) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_cfg_func_mta_item *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_cfg_func_mta_item *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false); + hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable); + + hnae_set_field(req->item_idx, HCLGE_CFG_MTA_ITEM_IDX_M, + HCLGE_CFG_MTA_ITEM_IDX_S, idx); + req->item_idx = cpu_to_le16(req->item_idx); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Config mta table item failed for cmd_send, ret =%d.\n", + ret); + return ret; + } + + return 0; +} + +static int hclge_remove_mac_vlan_tbl(struct hclge_vport *vport, + struct hclge_mac_vlan_tbl_entry *req) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_desc desc; + u8 resp_code; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_REMOVE, false); + + memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry)); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "del mac addr failed for cmd_send, ret =%d.\n", + ret); + return ret; + } + resp_code = (desc.data[0] >> 8) & 0xff; + + return hclge_get_mac_vlan_cmd_status(vport, desc.retval, resp_code, + HCLGE_MAC_VLAN_REMOVE); +} + +static int hclge_lookup_mac_vlan_tbl(struct hclge_vport *vport, + struct hclge_mac_vlan_tbl_entry *req, + struct hclge_desc *desc, + bool is_mc) +{ + struct hclge_dev *hdev = vport->back; + u8 resp_code; + int ret; + + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_MAC_VLAN_ADD, true); + if (is_mc) { + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + memcpy(desc[0].data, + req, + sizeof(struct hclge_mac_vlan_tbl_entry)); + hclge_cmd_setup_basic_desc(&desc[1], + HCLGE_OPC_MAC_VLAN_ADD, + true); + desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[2], + HCLGE_OPC_MAC_VLAN_ADD, + true); + ret = hclge_cmd_send(&hdev->hw, desc, 3); + } else { + memcpy(desc[0].data, + req, + sizeof(struct hclge_mac_vlan_tbl_entry)); + ret = hclge_cmd_send(&hdev->hw, desc, 1); + } + if (ret) { + dev_err(&hdev->pdev->dev, + "lookup mac addr failed for cmd_send, ret =%d.\n", + ret); + return ret; + } + resp_code = (desc[0].data[0] >> 8) & 0xff; + + return hclge_get_mac_vlan_cmd_status(vport, desc[0].retval, resp_code, + HCLGE_MAC_VLAN_LKUP); +} + +static int hclge_add_mac_vlan_tbl(struct hclge_vport *vport, + struct hclge_mac_vlan_tbl_entry *req, + struct hclge_desc *mc_desc) +{ + struct hclge_dev *hdev = vport->back; + int cfg_status; + u8 resp_code; + int ret; + + if (!mc_desc) { + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, + HCLGE_OPC_MAC_VLAN_ADD, + false); + memcpy(desc.data, req, sizeof(struct hclge_mac_vlan_tbl_entry)); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + resp_code = (desc.data[0] >> 8) & 0xff; + cfg_status = hclge_get_mac_vlan_cmd_status(vport, desc.retval, + resp_code, + HCLGE_MAC_VLAN_ADD); + } else { + mc_desc[0].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); + mc_desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + mc_desc[1].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); + mc_desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR); + mc_desc[2].flag &= cpu_to_le16(~HCLGE_CMD_FLAG_NEXT); + memcpy(mc_desc[0].data, req, + sizeof(struct hclge_mac_vlan_tbl_entry)); + ret = hclge_cmd_send(&hdev->hw, mc_desc, 3); + resp_code = (mc_desc[0].data[0] >> 8) & 0xff; + cfg_status = hclge_get_mac_vlan_cmd_status(vport, + mc_desc[0].retval, + resp_code, + HCLGE_MAC_VLAN_ADD); + } + + if (ret) { + dev_err(&hdev->pdev->dev, + "add mac addr failed for cmd_send, ret =%d.\n", + ret); + return ret; + } + + return cfg_status; +} + +static int hclge_add_uc_addr(struct hnae3_handle *handle, + const unsigned char *addr) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + + return hclge_add_uc_addr_common(vport, addr); +} + +int hclge_add_uc_addr_common(struct hclge_vport *vport, + const unsigned char *addr) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_mac_vlan_tbl_entry req; + enum hclge_cmd_status status; + + /* mac addr check */ + if (is_zero_ether_addr(addr) || + is_broadcast_ether_addr(addr) || + is_multicast_ether_addr(addr)) { + dev_err(&hdev->pdev->dev, + "Set_uc mac err! invalid mac:%pM. is_zero:%d,is_br=%d,is_mul=%d\n", + addr, + is_zero_ether_addr(addr), + is_broadcast_ether_addr(addr), + is_multicast_ether_addr(addr)); + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0); + hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae_set_bit(req.egress_port, + HCLGE_MAC_EPORT_SW_EN_B, 0); + hnae_set_bit(req.egress_port, + HCLGE_MAC_EPORT_TYPE_B, 0); + hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_VFID_M, + HCLGE_MAC_EPORT_VFID_S, vport->vport_id); + hnae_set_field(req.egress_port, HCLGE_MAC_EPORT_PFID_M, + HCLGE_MAC_EPORT_PFID_S, 0); + req.egress_port = cpu_to_le16(req.egress_port); + + hclge_prepare_mac_addr(&req, addr); + + status = hclge_add_mac_vlan_tbl(vport, &req, NULL); + + return status; +} + +static int hclge_rm_uc_addr(struct hnae3_handle *handle, + const unsigned char *addr) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + + return hclge_rm_uc_addr_common(vport, addr); +} + +int hclge_rm_uc_addr_common(struct hclge_vport *vport, + const unsigned char *addr) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_mac_vlan_tbl_entry req; + enum hclge_cmd_status status; + + /* mac addr check */ + if (is_zero_ether_addr(addr) || + is_broadcast_ether_addr(addr) || + is_multicast_ether_addr(addr)) { + dev_dbg(&hdev->pdev->dev, + "Remove mac err! invalid mac:%pM.\n", + addr); + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hclge_prepare_mac_addr(&req, addr); + status = hclge_remove_mac_vlan_tbl(vport, &req); + + return status; +} + +static int hclge_add_mc_addr(struct hnae3_handle *handle, + const unsigned char *addr) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + + return hclge_add_mc_addr_common(vport, addr); +} + +int hclge_add_mc_addr_common(struct hclge_vport *vport, + const unsigned char *addr) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_mac_vlan_tbl_entry req; + struct hclge_desc desc[3]; + u16 tbl_idx; + int status; + + /* mac addr check */ + if (!is_multicast_ether_addr(addr)) { + dev_err(&hdev->pdev->dev, + "Add mc mac err! invalid mac:%pM.\n", + addr); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); + hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); + hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hclge_prepare_mac_addr(&req, addr); + status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); + if (!status) { + /* This mac addr exist, update VFID for it */ + hclge_update_desc_vfid(desc, vport->vport_id, false); + status = hclge_add_mac_vlan_tbl(vport, &req, desc); + } else { + /* This mac addr do not exist, add new entry for it */ + memset(desc[0].data, 0, sizeof(desc[0].data)); + memset(desc[1].data, 0, sizeof(desc[0].data)); + memset(desc[2].data, 0, sizeof(desc[0].data)); + hclge_update_desc_vfid(desc, vport->vport_id, false); + status = hclge_add_mac_vlan_tbl(vport, &req, desc); + } + + /* Set MTA table for this MAC address */ + tbl_idx = hclge_get_mac_addr_to_mta_index(vport, addr); + status = hclge_set_mta_table_item(vport, tbl_idx, true); + + return status; +} + +static int hclge_rm_mc_addr(struct hnae3_handle *handle, + const unsigned char *addr) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + + return hclge_rm_mc_addr_common(vport, addr); +} + +int hclge_rm_mc_addr_common(struct hclge_vport *vport, + const unsigned char *addr) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_mac_vlan_tbl_entry req; + enum hclge_cmd_status status; + struct hclge_desc desc[3]; + u16 tbl_idx; + + /* mac addr check */ + if (!is_multicast_ether_addr(addr)) { + dev_dbg(&hdev->pdev->dev, + "Remove mc mac err! invalid mac:%pM.\n", + addr); + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); + hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hclge_prepare_mac_addr(&req, addr); + status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); + if (!status) { + /* This mac addr exist, remove this handle's VFID for it */ + hclge_update_desc_vfid(desc, vport->vport_id, true); + + if (hclge_is_all_function_id_zero(desc)) + /* All the vfid is zero, so need to delete this entry */ + status = hclge_remove_mac_vlan_tbl(vport, &req); + else + /* Not all the vfid is zero, update the vfid */ + status = hclge_add_mac_vlan_tbl(vport, &req, desc); + + } else { + /* This mac addr do not exist, can't delete it */ + dev_err(&hdev->pdev->dev, + "Rm multicast mac addr failed, ret = %d.\n", + status); + return -EIO; + } + + /* Set MTB table for this MAC address */ + tbl_idx = hclge_get_mac_addr_to_mta_index(vport, addr); + status = hclge_set_mta_table_item(vport, tbl_idx, false); + + return status; +} + +static void hclge_get_mac_addr(struct hnae3_handle *handle, u8 *p) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + ether_addr_copy(p, hdev->hw.mac.mac_addr); +} + +static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p) +{ + const unsigned char *new_addr = (const unsigned char *)p; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + /* mac addr check */ + if (is_zero_ether_addr(new_addr) || + is_broadcast_ether_addr(new_addr) || + is_multicast_ether_addr(new_addr)) { + dev_err(&hdev->pdev->dev, + "Change uc mac err! invalid mac:%p.\n", + new_addr); + return -EINVAL; + } + + hclge_rm_uc_addr(handle, hdev->hw.mac.mac_addr); + + if (!hclge_add_uc_addr(handle, new_addr)) { + ether_addr_copy(hdev->hw.mac.mac_addr, new_addr); + return 0; + } + + return -EIO; +} + +static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, + bool filter_en) +{ + struct hclge_vlan_filter_ctrl *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_CTRL, false); + + req = (struct hclge_vlan_filter_ctrl *)desc.data; + req->vlan_type = vlan_type; + req->vlan_fe = filter_en; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "set vlan filter fail, ret =%d.\n", + ret); + return ret; + } + + return 0; +} + +int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, + bool is_kill, u16 vlan, u8 qos, __be16 proto) +{ +#define HCLGE_MAX_VF_BYTES 16 + struct hclge_vlan_filter_vf_cfg *req0; + struct hclge_vlan_filter_vf_cfg *req1; + struct hclge_desc desc[2]; + u8 vf_byte_val; + u8 vf_byte_off; + int ret; + + hclge_cmd_setup_basic_desc(&desc[0], + HCLGE_OPC_VLAN_FILTER_VF_CFG, false); + hclge_cmd_setup_basic_desc(&desc[1], + HCLGE_OPC_VLAN_FILTER_VF_CFG, false); + + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + + vf_byte_off = vfid / 8; + vf_byte_val = 1 << (vfid % 8); + + req0 = (struct hclge_vlan_filter_vf_cfg *)desc[0].data; + req1 = (struct hclge_vlan_filter_vf_cfg *)desc[1].data; + + req0->vlan_id = vlan; + req0->vlan_cfg = is_kill; + + if (vf_byte_off < HCLGE_MAX_VF_BYTES) + req0->vf_bitmap[vf_byte_off] = vf_byte_val; + else + req1->vf_bitmap[vf_byte_off - HCLGE_MAX_VF_BYTES] = vf_byte_val; + + ret = hclge_cmd_send(&hdev->hw, desc, 2); + if (ret) { + dev_err(&hdev->pdev->dev, + "Send vf vlan command fail, ret =%d.\n", + ret); + return ret; + } + + if (!is_kill) { + if (!req0->resp_code || req0->resp_code == 1) + return 0; + + dev_err(&hdev->pdev->dev, + "Add vf vlan filter fail, ret =%d.\n", + req0->resp_code); + } else { + if (!req0->resp_code) + return 0; + + dev_err(&hdev->pdev->dev, + "Kill vf vlan filter fail, ret =%d.\n", + req0->resp_code); + } + + return -EIO; +} + +static int hclge_set_port_vlan_filter(struct hnae3_handle *handle, + __be16 proto, u16 vlan_id, + bool is_kill) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_vlan_filter_pf_cfg *req; + struct hclge_desc desc; + u8 vlan_offset_byte_val; + u8 vlan_offset_byte; + u8 vlan_offset_160; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_FILTER_PF_CFG, false); + + vlan_offset_160 = vlan_id / 160; + vlan_offset_byte = (vlan_id % 160) / 8; + vlan_offset_byte_val = 1 << (vlan_id % 8); + + req = (struct hclge_vlan_filter_pf_cfg *)desc.data; + req->vlan_offset = vlan_offset_160; + req->vlan_cfg = is_kill; + req->vlan_offset_bitmap[vlan_offset_byte] = vlan_offset_byte_val; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "port vlan command, send fail, ret =%d.\n", + ret); + return ret; + } + + ret = hclge_set_vf_vlan_common(hdev, 0, is_kill, vlan_id, 0, proto); + if (ret) { + dev_err(&hdev->pdev->dev, + "Set pf vlan filter config fail, ret =%d.\n", + ret); + return -EIO; + } + + return 0; +} + +static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, + u16 vlan, u8 qos, __be16 proto) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if ((vfid >= hdev->num_alloc_vfs) || (vlan > 4095) || (qos > 7)) + return -EINVAL; + if (proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + + return hclge_set_vf_vlan_common(hdev, vfid, false, vlan, qos, proto); +} + +static int hclge_init_vlan_config(struct hclge_dev *hdev) +{ +#define HCLGE_VLAN_TYPE_VF_TABLE 0 +#define HCLGE_VLAN_TYPE_PORT_TABLE 1 + int ret; + + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_VF_TABLE, + true); + if (ret) + return ret; + + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_PORT_TABLE, + true); + + return ret; +} + +static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_config_max_frm_size *req; + struct hclge_dev *hdev = vport->back; + struct hclge_desc desc; + int ret; + + if ((new_mtu < HCLGE_MAC_MIN_MTU) || (new_mtu > HCLGE_MAC_MAX_MTU)) + return -EINVAL; + + hdev->mps = new_mtu; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, false); + + req = (struct hclge_config_max_frm_size *)desc.data; + req->max_frm_size = cpu_to_le16(new_mtu); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "set mtu fail, ret =%d.\n", ret); + return ret; + } + + return 0; +} + +static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id, + bool enable) +{ + struct hclge_reset_tqp_queue *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, false); + + req = (struct hclge_reset_tqp_queue *)desc.data; + req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK); + hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Send tqp reset cmd error, status =%d\n", ret); + return ret; + } + + return 0; +} + +static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id) +{ + struct hclge_reset_tqp_queue *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RESET_TQP_QUEUE, true); + + req = (struct hclge_reset_tqp_queue *)desc.data; + req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get reset status error, status =%d\n", ret); + return ret; + } + + return hnae_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B); +} + +static void hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int reset_try_times = 0; + int reset_status; + int ret; + + ret = hclge_tqp_enable(hdev, queue_id, 0, false); + if (ret) { + dev_warn(&hdev->pdev->dev, "Disable tqp fail, ret = %d\n", ret); + return; + } + + ret = hclge_send_reset_tqp_cmd(hdev, queue_id, true); + if (ret) { + dev_warn(&hdev->pdev->dev, + "Send reset tqp cmd fail, ret = %d\n", ret); + return; + } + + reset_try_times = 0; + while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) { + /* Wait for tqp hw reset */ + msleep(20); + reset_status = hclge_get_reset_status(hdev, queue_id); + if (reset_status) + break; + } + + if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) { + dev_warn(&hdev->pdev->dev, "Reset TQP fail\n"); + return; + } + + ret = hclge_send_reset_tqp_cmd(hdev, queue_id, false); + if (ret) { + dev_warn(&hdev->pdev->dev, + "Deassert the soft reset fail, ret = %d\n", ret); + return; + } +} + +static u32 hclge_get_fw_version(struct hnae3_handle *handle) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + return hdev->fw_version; +} + +static void hclge_get_pauseparam(struct hnae3_handle *handle, u32 *auto_neg, + u32 *rx_en, u32 *tx_en) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + *auto_neg = hclge_get_autoneg(handle); + + if (hdev->tm_info.fc_mode == HCLGE_FC_PFC) { + *rx_en = 0; + *tx_en = 0; + return; + } + + if (hdev->tm_info.fc_mode == HCLGE_FC_RX_PAUSE) { + *rx_en = 1; + *tx_en = 0; + } else if (hdev->tm_info.fc_mode == HCLGE_FC_TX_PAUSE) { + *tx_en = 1; + *rx_en = 0; + } else if (hdev->tm_info.fc_mode == HCLGE_FC_FULL) { + *rx_en = 1; + *tx_en = 1; + } else { + *rx_en = 0; + *tx_en = 0; + } +} + +static void hclge_get_ksettings_an_result(struct hnae3_handle *handle, + u8 *auto_neg, u32 *speed, u8 *duplex) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if (speed) + *speed = hdev->hw.mac.speed; + if (duplex) + *duplex = hdev->hw.mac.duplex; + if (auto_neg) + *auto_neg = hdev->hw.mac.autoneg; +} + +static void hclge_get_media_type(struct hnae3_handle *handle, u8 *media_type) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if (media_type) + *media_type = hdev->hw.mac.media_type; +} + +static void hclge_get_mdix_mode(struct hnae3_handle *handle, + u8 *tp_mdix_ctrl, u8 *tp_mdix) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct phy_device *phydev = hdev->hw.mac.phydev; + int mdix_ctrl, mdix, retval, is_resolved; + + if (!phydev) { + *tp_mdix_ctrl = ETH_TP_MDI_INVALID; + *tp_mdix = ETH_TP_MDI_INVALID; + return; + } + + phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_MDIX); + + retval = phy_read(phydev, HCLGE_PHY_CSC_REG); + mdix_ctrl = hnae_get_field(retval, HCLGE_PHY_MDIX_CTRL_M, + HCLGE_PHY_MDIX_CTRL_S); + + retval = phy_read(phydev, HCLGE_PHY_CSS_REG); + mdix = hnae_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B); + is_resolved = hnae_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B); + + phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_COPPER); + + switch (mdix_ctrl) { + case 0x0: + *tp_mdix_ctrl = ETH_TP_MDI; + break; + case 0x1: + *tp_mdix_ctrl = ETH_TP_MDI_X; + break; + case 0x3: + *tp_mdix_ctrl = ETH_TP_MDI_AUTO; + break; + default: + *tp_mdix_ctrl = ETH_TP_MDI_INVALID; + break; + } + + if (!is_resolved) + *tp_mdix = ETH_TP_MDI_INVALID; + else if (mdix) + *tp_mdix = ETH_TP_MDI_X; + else + *tp_mdix = ETH_TP_MDI; +} + +static int hclge_init_client_instance(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev) +{ + struct hclge_dev *hdev = ae_dev->priv; + struct hclge_vport *vport; + int i, ret; + + for (i = 0; i < hdev->num_vmdq_vport + 1; i++) { + vport = &hdev->vport[i]; + + switch (client->type) { + case HNAE3_CLIENT_KNIC: + + hdev->nic_client = client; + vport->nic.client = client; + ret = client->ops->init_instance(&vport->nic); + if (ret) + goto err; + + if (hdev->roce_client && + hnae_get_bit(hdev->ae_dev->flag, + HNAE_DEV_SUPPORT_ROCE_B)) { + struct hnae3_client *rc = hdev->roce_client; + + ret = hclge_init_roce_base_info(vport); + if (ret) + goto err; + + ret = rc->ops->init_instance(&vport->roce); + if (ret) + goto err; + } + + break; + case HNAE3_CLIENT_UNIC: + hdev->nic_client = client; + vport->nic.client = client; + + ret = client->ops->init_instance(&vport->nic); + if (ret) + goto err; + + break; + case HNAE3_CLIENT_ROCE: + if (hnae_get_bit(hdev->ae_dev->flag, + HNAE_DEV_SUPPORT_ROCE_B)) { + hdev->roce_client = client; + vport->roce.client = client; + } + + if (hdev->roce_client) { + ret = hclge_init_roce_base_info(vport); + if (ret) + goto err; + + ret = client->ops->init_instance(&vport->roce); + if (ret) + goto err; + } + } + } + + return 0; +err: + return ret; +} + +static void hclge_uninit_client_instance(struct hnae3_client *client, + struct hnae3_ae_dev *ae_dev) +{ + struct hclge_dev *hdev = ae_dev->priv; + struct hclge_vport *vport; + int i; + + for (i = 0; i < hdev->num_vmdq_vport + 1; i++) { + vport = &hdev->vport[i]; + if (hdev->roce_client) + hdev->roce_client->ops->uninit_instance(&vport->roce, + 0); + if (client->type == HNAE3_CLIENT_ROCE) + return; + if (client->ops->uninit_instance) + client->ops->uninit_instance(&vport->nic, 0); + } +} + +static int hclge_pci_init(struct hclge_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + struct hclge_hw *hw; + int ret; + + ret = pci_enable_device(pdev); + if (ret) { + dev_err(&pdev->dev, "failed to enable PCI device\n"); + goto err_no_drvdata; + } + + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) { + ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (ret) { + dev_err(&pdev->dev, + "can't set consistent PCI DMA"); + goto err_disable_device; + } + dev_warn(&pdev->dev, "set DMA mask to 32 bits\n"); + } + + ret = pci_request_regions(pdev, HCLGE_DRIVER_NAME); + if (ret) { + dev_err(&pdev->dev, "PCI request regions failed %d\n", ret); + goto err_disable_device; + } + + pci_set_master(pdev); + hw = &hdev->hw; + hw->back = hdev; + hw->io_base = pcim_iomap(pdev, 2, 0); + if (!hw->io_base) { + dev_err(&pdev->dev, "Can't map configuration register space\n"); + ret = -ENOMEM; + goto err_clr_master; + } + + return 0; +err_clr_master: + pci_clear_master(pdev); + pci_release_regions(pdev); +err_disable_device: + pci_disable_device(pdev); +err_no_drvdata: + pci_set_drvdata(pdev, NULL); + + return ret; +} + +static void hclge_pci_uninit(struct hclge_dev *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + + if (hdev->flag & HCLGE_FLAG_USE_MSIX) { + pci_disable_msix(pdev); + devm_kfree(&pdev->dev, hdev->msix_entries); + hdev->msix_entries = NULL; + } else { + pci_disable_msi(pdev); + } + + pci_clear_master(pdev); + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} + +static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) +{ + struct pci_dev *pdev = ae_dev->pdev; + const struct pci_device_id *id; + struct hclge_dev *hdev; + int ret; + + hdev = devm_kzalloc(&pdev->dev, sizeof(*hdev), GFP_KERNEL); + if (!hdev) { + ret = -ENOMEM; + goto err_hclge_dev; + } + + hdev->flag |= HCLGE_FLAG_USE_MSIX; + hdev->pdev = pdev; + hdev->ae_dev = ae_dev; + ae_dev->priv = hdev; + + id = pci_match_id(roce_pci_tbl, ae_dev->pdev); + if (id) + hnae_set_bit(ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B, 1); + + ret = hclge_pci_init(hdev); + if (ret) { + dev_err(&pdev->dev, "PCI init failed\n"); + goto err_pci_init; + } + + /* Command queue initialize */ + ret = hclge_cmd_init(hdev); + if (ret) + goto err_cmd_init; + + ret = hclge_get_cap(hdev); + if (ret) { + dev_err(&pdev->dev, "get hw capability error, ret = %d.\n", + ret); + return ret; + } + + ret = hclge_configure(hdev); + if (ret) { + dev_err(&pdev->dev, "Configure dev error, ret = %d.\n", ret); + return ret; + } + + if (hdev->flag & HCLGE_FLAG_USE_MSIX) + ret = hclge_init_msix(hdev); + else + ret = hclge_init_msi(hdev); + if (ret) { + dev_err(&pdev->dev, "Init msix/msi error, ret = %d.\n", ret); + return ret; + } + + ret = hclge_alloc_tqps(hdev); + if (ret) { + dev_err(&pdev->dev, "Allocate TQPs error, ret = %d.\n", ret); + return ret; + } + + ret = hclge_alloc_vport(hdev); + if (ret) { + dev_err(&pdev->dev, "Allocate vport error, ret = %d.\n", ret); + return ret; + } + + ret = hclge_mac_init(hdev); + if (ret) { + dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret); + return ret; + } + ret = hclge_buffer_alloc(hdev); + if (ret) { + dev_err(&pdev->dev, "Buffer allocate fail, ret =%d\n", ret); + return ret; + } + + ret = hclge_config_tso(hdev, HCLGE_TSO_MSS_MIN, HCLGE_TSO_MSS_MAX); + if (ret) { + dev_err(&pdev->dev, "Enable tso fail, ret =%d\n", ret); + return ret; + } + + ret = hclge_rss_init_hw(hdev); + if (ret) { + dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret); + return ret; + } + + ret = hclge_init_vlan_config(hdev); + if (ret) { + dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret); + return ret; + } + + ret = hclge_tm_schd_init(hdev); + if (ret) { + dev_err(&pdev->dev, "tm schd init fail, ret =%d\n", ret); + return ret; + } + + setup_timer(&hdev->service_timer, hclge_service_timer, + (unsigned long)hdev); + INIT_WORK(&hdev->service_task, hclge_service_task); + + set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state); + set_bit(HCLGE_STATE_DOWN, &hdev->state); + + pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME); + return 0; + +err_cmd_init: + pci_release_regions(pdev); +err_pci_init: + pci_set_drvdata(pdev, NULL); +err_hclge_dev: + return ret; +} + +static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) +{ + struct hclge_dev *hdev = ae_dev->priv; + struct hclge_mac *mac = &hdev->hw.mac; + + set_bit(HCLGE_STATE_DOWN, &hdev->state); + + if (IS_ENABLED(CONFIG_PCI_IOV)) + hclge_disable_sriov(hdev); + + if (hdev->service_timer.data) + del_timer_sync(&hdev->service_timer); + if (hdev->service_task.func) + cancel_work_sync(&hdev->service_task); + + if (mac->phydev) + mdiobus_unregister(mac->mdio_bus); + + hclge_destroy_cmd_queue(&hdev->hw); + hclge_pci_uninit(hdev); + ae_dev->priv = NULL; +} + +static const struct hnae3_ae_ops hclge_ops = { + .init_ae_dev = hclge_init_ae_dev, + .uninit_ae_dev = hclge_uninit_ae_dev, + .init_client_instance = hclge_init_client_instance, + .uninit_client_instance = hclge_uninit_client_instance, + .map_ring_to_vector = hclge_map_handle_ring_to_vector, + .unmap_ring_from_vector = hclge_unmap_ring_from_vector, + .get_vector = hclge_get_vector, + .set_promisc_mode = hclge_set_promisc_mode, + .start = hclge_ae_start, + .stop = hclge_ae_stop, + .get_status = hclge_get_status, + .get_ksettings_an_result = hclge_get_ksettings_an_result, + .update_speed_duplex_h = hclge_update_speed_duplex_h, + .cfg_mac_speed_dup_h = hclge_cfg_mac_speed_dup_h, + .get_media_type = hclge_get_media_type, + .get_rss_key_size = hclge_get_rss_key_size, + .get_rss_indir_size = hclge_get_rss_indir_size, + .get_rss = hclge_get_rss, + .set_rss = hclge_set_rss, + .get_tc_size = hclge_get_tc_size, + .get_mac_addr = hclge_get_mac_addr, + .set_mac_addr = hclge_set_mac_addr, + .add_uc_addr = hclge_add_uc_addr, + .rm_uc_addr = hclge_rm_uc_addr, + .add_mc_addr = hclge_add_mc_addr, + .rm_mc_addr = hclge_rm_mc_addr, + .set_autoneg = hclge_set_autoneg, + .get_autoneg = hclge_get_autoneg, + .get_pauseparam = hclge_get_pauseparam, + .set_mtu = hclge_set_mtu, + .reset_queue = hclge_reset_tqp, + .get_stats = hclge_get_stats, + .update_stats = hclge_update_stats, + .get_strings = hclge_get_strings, + .get_sset_count = hclge_get_sset_count, + .get_fw_version = hclge_get_fw_version, + .get_mdix_mode = hclge_get_mdix_mode, + .set_vlan_filter = hclge_set_port_vlan_filter, + .set_vf_vlan_filter = hclge_set_vf_vlan_filter, +}; + +static struct hnae3_ae_algo ae_algo = { + .ops = &hclge_ops, + .name = HCLGE_NAME, + .pdev_id_table = ae_algo_pci_tbl, +}; + +static int hclge_init(void) +{ + pr_info("%s is initializing\n", HCLGE_NAME); + + return hnae3_register_ae_algo(&ae_algo); +} + +static void hclge_exit(void) +{ + hnae3_unregister_ae_algo(&ae_algo); +} +module_init(hclge_init); +module_exit(hclge_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +MODULE_DESCRIPTION("HCLGE Driver"); +MODULE_VERSION(HCLGE_MOD_VERSION); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h new file mode 100644 index 000000000000..edb10ad075eb --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -0,0 +1,519 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HCLGE_MAIN_H +#define __HCLGE_MAIN_H +#include <linux/fs.h> +#include <linux/types.h> +#include <linux/phy.h> +#include "hclge_cmd.h" +#include "hnae3.h" + +#define HCLGE_MOD_VERSION "v1.0" +#define HCLGE_DRIVER_NAME "hclge" + +#define HCLGE_INVALID_VPORT 0xffff + +#define HCLGE_ROCE_VECTOR_OFFSET 96 + +#define HCLGE_PF_CFG_BLOCK_SIZE 32 +#define HCLGE_PF_CFG_DESC_NUM \ + (HCLGE_PF_CFG_BLOCK_SIZE / HCLGE_CFG_RD_LEN_BYTES) + +#define HCLGE_VECTOR_REG_BASE 0x20000 + +#define HCLGE_VECTOR_REG_OFFSET 0x4 +#define HCLGE_VECTOR_VF_OFFSET 0x100000 + +#define HCLGE_RSS_IND_TBL_SIZE 512 +#define HCLGE_RSS_SET_BITMAP_MSK 0xffff +#define HCLGE_RSS_KEY_SIZE 40 +#define HCLGE_RSS_HASH_ALGO_TOEPLITZ 0 +#define HCLGE_RSS_HASH_ALGO_SIMPLE 1 +#define HCLGE_RSS_HASH_ALGO_SYMMETRIC 2 +#define HCLGE_RSS_HASH_ALGO_MASK 0xf +#define HCLGE_RSS_CFG_TBL_NUM \ + (HCLGE_RSS_IND_TBL_SIZE / HCLGE_RSS_CFG_TBL_SIZE) + +#define HCLGE_RSS_TC_SIZE_0 1 +#define HCLGE_RSS_TC_SIZE_1 2 +#define HCLGE_RSS_TC_SIZE_2 4 +#define HCLGE_RSS_TC_SIZE_3 8 +#define HCLGE_RSS_TC_SIZE_4 16 +#define HCLGE_RSS_TC_SIZE_5 32 +#define HCLGE_RSS_TC_SIZE_6 64 +#define HCLGE_RSS_TC_SIZE_7 128 + +#define HCLGE_TQP_RESET_TRY_TIMES 10 + +#define HCLGE_PHY_PAGE_MDIX 0 +#define HCLGE_PHY_PAGE_COPPER 0 + +/* Page Selection Reg. */ +#define HCLGE_PHY_PAGE_REG 22 + +/* Copper Specific Control Register */ +#define HCLGE_PHY_CSC_REG 16 + +/* Copper Specific Status Register */ +#define HCLGE_PHY_CSS_REG 17 + +#define HCLGE_PHY_MDIX_CTRL_S (5) +#define HCLGE_PHY_MDIX_CTRL_M (3 << HCLGE_PHY_MDIX_CTRL_S) + +#define HCLGE_PHY_MDIX_STATUS_B (6) +#define HCLGE_PHY_SPEED_DUP_RESOLVE_B (11) + +enum HCLGE_DEV_STATE { + HCLGE_STATE_REINITING, + HCLGE_STATE_DOWN, + HCLGE_STATE_DISABLED, + HCLGE_STATE_REMOVING, + HCLGE_STATE_SERVICE_INITED, + HCLGE_STATE_SERVICE_SCHED, + HCLGE_STATE_MBX_HANDLING, + HCLGE_STATE_MBX_IRQ, + HCLGE_STATE_MAX +}; + +#define HCLGE_MPF_ENBALE 1 +struct hclge_caps { + u16 num_tqp; + u16 num_buffer_cell; + u32 flag; + u16 vmdq; +}; + +enum HCLGE_MAC_SPEED { + HCLGE_MAC_SPEED_10M = 10, /* 10 Mbps */ + HCLGE_MAC_SPEED_100M = 100, /* 100 Mbps */ + HCLGE_MAC_SPEED_1G = 1000, /* 1000 Mbps = 1 Gbps */ + HCLGE_MAC_SPEED_10G = 10000, /* 10000 Mbps = 10 Gbps */ + HCLGE_MAC_SPEED_25G = 25000, /* 25000 Mbps = 25 Gbps */ + HCLGE_MAC_SPEED_40G = 40000, /* 40000 Mbps = 40 Gbps */ + HCLGE_MAC_SPEED_50G = 50000, /* 50000 Mbps = 50 Gbps */ + HCLGE_MAC_SPEED_100G = 100000 /* 100000 Mbps = 100 Gbps */ +}; + +enum HCLGE_MAC_DUPLEX { + HCLGE_MAC_HALF, + HCLGE_MAC_FULL +}; + +enum hclge_mta_dmac_sel_type { + HCLGE_MAC_ADDR_47_36, + HCLGE_MAC_ADDR_46_35, + HCLGE_MAC_ADDR_45_34, + HCLGE_MAC_ADDR_44_33, +}; + +struct hclge_mac { + u8 phy_addr; + u8 flag; + u8 media_type; + u8 mac_addr[ETH_ALEN]; + u8 autoneg; + u8 duplex; + u32 speed; + int link; /* store the link status of mac & phy (if phy exit)*/ + struct phy_device *phydev; + struct mii_bus *mdio_bus; + phy_interface_t phy_if; +}; + +struct hclge_hw { + void __iomem *io_base; + struct hclge_mac mac; + int num_vec; + struct hclge_cmq cmq; + struct hclge_caps caps; + void *back; +}; + +/* TQP stats */ +struct hlcge_tqp_stats { + /* query_tqp_tx_queue_statistics ,opcode id: 0x0B03 */ + u64 rcb_tx_ring_pktnum_rcd; /* 32bit */ + /* query_tqp_rx_queue_statistics ,opcode id: 0x0B13 */ + u64 rcb_rx_ring_pktnum_rcd; /* 32bit */ +}; + +struct hclge_tqp { + struct device *dev; /* Device for DMA mapping */ + struct hnae3_queue q; + struct hlcge_tqp_stats tqp_stats; + u16 index; /* Global index in a NIC controller */ + + bool alloced; +}; + +enum hclge_fc_mode { + HCLGE_FC_NONE, + HCLGE_FC_RX_PAUSE, + HCLGE_FC_TX_PAUSE, + HCLGE_FC_FULL, + HCLGE_FC_PFC, + HCLGE_FC_DEFAULT +}; + +#define HCLGE_PG_NUM 4 +#define HCLGE_SCH_MODE_SP 0 +#define HCLGE_SCH_MODE_DWRR 1 +struct hclge_pg_info { + u8 pg_id; + u8 pg_sch_mode; /* 0: sp; 1: dwrr */ + u8 tc_bit_map; + u32 bw_limit; + u8 tc_dwrr[HNAE3_MAX_TC]; +}; + +struct hclge_tc_info { + u8 tc_id; + u8 tc_sch_mode; /* 0: sp; 1: dwrr */ + u8 up; + u8 pgid; + u32 bw_limit; +}; + +struct hclge_cfg { + u8 vmdq_vport_num; + u8 tc_num; + u16 tqp_desc_num; + u16 rx_buf_len; + u8 phy_addr; + u8 media_type; + u8 mac_addr[ETH_ALEN]; + u8 default_speed; + u32 numa_node_map; +}; + +struct hclge_tm_info { + u8 num_tc; + u8 num_pg; /* It must be 1 if vNET-Base schd */ + u8 pg_dwrr[HCLGE_PG_NUM]; + struct hclge_pg_info pg_info[HCLGE_PG_NUM]; + struct hclge_tc_info tc_info[HNAE3_MAX_TC]; + enum hclge_fc_mode fc_mode; + u8 hw_pfc_map; /* Allow for packet drop or not on this TC */ +}; + +struct hclge_comm_stats_str { + char desc[ETH_GSTRING_LEN]; + unsigned long offset; +}; + +/* all 64bit stats, opcode id: 0x0030 */ +struct hclge_64_bit_stats { + /* query_igu_stat */ + u64 igu_rx_oversize_pkt; + u64 igu_rx_undersize_pkt; + u64 igu_rx_out_all_pkt; + u64 igu_rx_uni_pkt; + u64 igu_rx_multi_pkt; + u64 igu_rx_broad_pkt; + u64 rsv0; + + /* query_egu_stat */ + u64 egu_tx_out_all_pkt; + u64 egu_tx_uni_pkt; + u64 egu_tx_multi_pkt; + u64 egu_tx_broad_pkt; + + /* ssu_ppp packet stats */ + u64 ssu_ppp_mac_key_num; + u64 ssu_ppp_host_key_num; + u64 ppp_ssu_mac_rlt_num; + u64 ppp_ssu_host_rlt_num; + + /* ssu_tx_in_out_dfx_stats */ + u64 ssu_tx_in_num; + u64 ssu_tx_out_num; + /* ssu_rx_in_out_dfx_stats */ + u64 ssu_rx_in_num; + u64 ssu_rx_out_num; +}; + +/* all 32bit stats, opcode id: 0x0031 */ +struct hclge_32_bit_stats { + u64 igu_rx_err_pkt; + u64 igu_rx_no_eof_pkt; + u64 igu_rx_no_sof_pkt; + u64 egu_tx_1588_pkt; + u64 egu_tx_err_pkt; + u64 ssu_full_drop_num; + u64 ssu_part_drop_num; + u64 ppp_key_drop_num; + u64 ppp_rlt_drop_num; + u64 ssu_key_drop_num; + u64 pkt_curr_buf_cnt; + u64 qcn_fb_rcv_cnt; + u64 qcn_fb_drop_cnt; + u64 qcn_fb_invaild_cnt; + u64 rsv0; + u64 rx_packet_tc0_in_cnt; + u64 rx_packet_tc1_in_cnt; + u64 rx_packet_tc2_in_cnt; + u64 rx_packet_tc3_in_cnt; + u64 rx_packet_tc4_in_cnt; + u64 rx_packet_tc5_in_cnt; + u64 rx_packet_tc6_in_cnt; + u64 rx_packet_tc7_in_cnt; + u64 rx_packet_tc0_out_cnt; + u64 rx_packet_tc1_out_cnt; + u64 rx_packet_tc2_out_cnt; + u64 rx_packet_tc3_out_cnt; + u64 rx_packet_tc4_out_cnt; + u64 rx_packet_tc5_out_cnt; + u64 rx_packet_tc6_out_cnt; + u64 rx_packet_tc7_out_cnt; + + /* Tx packet level statistics */ + u64 tx_packet_tc0_in_cnt; + u64 tx_packet_tc1_in_cnt; + u64 tx_packet_tc2_in_cnt; + u64 tx_packet_tc3_in_cnt; + u64 tx_packet_tc4_in_cnt; + u64 tx_packet_tc5_in_cnt; + u64 tx_packet_tc6_in_cnt; + u64 tx_packet_tc7_in_cnt; + u64 tx_packet_tc0_out_cnt; + u64 tx_packet_tc1_out_cnt; + u64 tx_packet_tc2_out_cnt; + u64 tx_packet_tc3_out_cnt; + u64 tx_packet_tc4_out_cnt; + u64 tx_packet_tc5_out_cnt; + u64 tx_packet_tc6_out_cnt; + u64 tx_packet_tc7_out_cnt; + + /* packet buffer statistics */ + u64 pkt_curr_buf_tc0_cnt; + u64 pkt_curr_buf_tc1_cnt; + u64 pkt_curr_buf_tc2_cnt; + u64 pkt_curr_buf_tc3_cnt; + u64 pkt_curr_buf_tc4_cnt; + u64 pkt_curr_buf_tc5_cnt; + u64 pkt_curr_buf_tc6_cnt; + u64 pkt_curr_buf_tc7_cnt; + + u64 mb_uncopy_num; + u64 lo_pri_unicast_rlt_drop_num; + u64 hi_pri_multicast_rlt_drop_num; + u64 lo_pri_multicast_rlt_drop_num; + u64 rx_oq_drop_pkt_cnt; + u64 tx_oq_drop_pkt_cnt; + u64 nic_l2_err_drop_pkt_cnt; + u64 roc_l2_err_drop_pkt_cnt; +}; + +/* mac stats ,opcode id: 0x0032 */ +struct hclge_mac_stats { + u64 mac_tx_mac_pause_num; + u64 mac_rx_mac_pause_num; + u64 mac_tx_pfc_pri0_pkt_num; + u64 mac_tx_pfc_pri1_pkt_num; + u64 mac_tx_pfc_pri2_pkt_num; + u64 mac_tx_pfc_pri3_pkt_num; + u64 mac_tx_pfc_pri4_pkt_num; + u64 mac_tx_pfc_pri5_pkt_num; + u64 mac_tx_pfc_pri6_pkt_num; + u64 mac_tx_pfc_pri7_pkt_num; + u64 mac_rx_pfc_pri0_pkt_num; + u64 mac_rx_pfc_pri1_pkt_num; + u64 mac_rx_pfc_pri2_pkt_num; + u64 mac_rx_pfc_pri3_pkt_num; + u64 mac_rx_pfc_pri4_pkt_num; + u64 mac_rx_pfc_pri5_pkt_num; + u64 mac_rx_pfc_pri6_pkt_num; + u64 mac_rx_pfc_pri7_pkt_num; + u64 mac_tx_total_pkt_num; + u64 mac_tx_total_oct_num; + u64 mac_tx_good_pkt_num; + u64 mac_tx_bad_pkt_num; + u64 mac_tx_good_oct_num; + u64 mac_tx_bad_oct_num; + u64 mac_tx_uni_pkt_num; + u64 mac_tx_multi_pkt_num; + u64 mac_tx_broad_pkt_num; + u64 mac_tx_undersize_pkt_num; + u64 mac_tx_overrsize_pkt_num; + u64 mac_tx_64_oct_pkt_num; + u64 mac_tx_65_127_oct_pkt_num; + u64 mac_tx_128_255_oct_pkt_num; + u64 mac_tx_256_511_oct_pkt_num; + u64 mac_tx_512_1023_oct_pkt_num; + u64 mac_tx_1024_1518_oct_pkt_num; + u64 mac_tx_1519_max_oct_pkt_num; + u64 mac_rx_total_pkt_num; + u64 mac_rx_total_oct_num; + u64 mac_rx_good_pkt_num; + u64 mac_rx_bad_pkt_num; + u64 mac_rx_good_oct_num; + u64 mac_rx_bad_oct_num; + u64 mac_rx_uni_pkt_num; + u64 mac_rx_multi_pkt_num; + u64 mac_rx_broad_pkt_num; + u64 mac_rx_undersize_pkt_num; + u64 mac_rx_overrsize_pkt_num; + u64 mac_rx_64_oct_pkt_num; + u64 mac_rx_65_127_oct_pkt_num; + u64 mac_rx_128_255_oct_pkt_num; + u64 mac_rx_256_511_oct_pkt_num; + u64 mac_rx_512_1023_oct_pkt_num; + u64 mac_rx_1024_1518_oct_pkt_num; + u64 mac_rx_1519_max_oct_pkt_num; + + u64 mac_trans_fragment_pkt_num; + u64 mac_trans_undermin_pkt_num; + u64 mac_trans_jabber_pkt_num; + u64 mac_trans_err_all_pkt_num; + u64 mac_trans_from_app_good_pkt_num; + u64 mac_trans_from_app_bad_pkt_num; + u64 mac_rcv_fragment_pkt_num; + u64 mac_rcv_undermin_pkt_num; + u64 mac_rcv_jabber_pkt_num; + u64 mac_rcv_fcs_err_pkt_num; + u64 mac_rcv_send_app_good_pkt_num; + u64 mac_rcv_send_app_bad_pkt_num; +}; + +struct hclge_hw_stats { + struct hclge_mac_stats mac_stats; + struct hclge_64_bit_stats all_64_bit_stats; + struct hclge_32_bit_stats all_32_bit_stats; +}; + +struct hclge_dev { + struct pci_dev *pdev; + struct hnae3_ae_dev *ae_dev; + struct hclge_hw hw; + struct hclge_hw_stats hw_stats; + unsigned long state; + + u32 fw_version; + u16 num_vmdq_vport; /* Num vmdq vport this PF has set up */ + u16 num_tqps; /* Num task queue pairs of this PF */ + u16 num_req_vfs; /* Num VFs requested for this PF */ + + u16 num_roce_msix; /* Num of roce vectors for this PF */ + int roce_base_vector; + + /* Base task tqp physical id of this PF */ + u16 base_tqp_pid; + u16 alloc_rss_size; /* Allocated RSS task queue */ + u16 rss_size_max; /* HW defined max RSS task queue */ + + /* Num of guaranteed filters for this PF */ + u16 fdir_pf_filter_count; + u16 num_alloc_vport; /* Num vports this driver supports */ + u32 numa_node_mask; + u16 rx_buf_len; + u16 num_desc; + u8 hw_tc_map; + u8 tc_num_last_time; + enum hclge_fc_mode fc_mode_last_time; + +#define HCLGE_FLAG_TC_BASE_SCH_MODE 1 +#define HCLGE_FLAG_VNET_BASE_SCH_MODE 2 + u8 tx_sch_mode; + + u8 default_up; + struct hclge_tm_info tm_info; + + u16 num_msi; + u16 num_msi_left; + u16 num_msi_used; + u32 base_msi_vector; + struct msix_entry *msix_entries; + u16 *vector_status; + + u16 pending_udp_bitmap; + + u16 rx_itr_default; + u16 tx_itr_default; + + u16 adminq_work_limit; /* Num of admin receive queue desc to process */ + unsigned long service_timer_period; + unsigned long service_timer_previous; + struct timer_list service_timer; + struct work_struct service_task; + + bool cur_promisc; + int num_alloc_vfs; /* Actual number of VFs allocated */ + + struct hclge_tqp *htqp; + struct hclge_vport *vport; + + struct dentry *hclge_dbgfs; + + struct hnae3_client *nic_client; + struct hnae3_client *roce_client; + +#define HCLGE_FLAG_USE_MSI 0x00000001 +#define HCLGE_FLAG_USE_MSIX 0x00000002 +#define HCLGE_FLAG_MAIN 0x00000004 +#define HCLGE_FLAG_DCB_CAPABLE 0x00000008 +#define HCLGE_FLAG_DCB_ENABLE 0x00000010 + u32 flag; + + u32 pkt_buf_size; /* Total pf buf size for tx/rx */ + u32 mps; /* Max packet size */ + struct hclge_priv_buf *priv_buf; + struct hclge_shared_buf s_buf; + + enum hclge_mta_dmac_sel_type mta_mac_sel_type; + bool enable_mta; /* Mutilcast filter enable */ + bool accept_mta_mc; /* Whether accept mta filter multicast */ +}; + +struct hclge_vport { + u16 alloc_tqps; /* Allocated Tx/Rx queues */ + + u8 rss_hash_key[HCLGE_RSS_KEY_SIZE]; /* User configured hash keys */ + /* User configured lookup table entries */ + u8 rss_indirection_tbl[HCLGE_RSS_IND_TBL_SIZE]; + + u16 qs_offset; + u16 bw_limit; /* VSI BW Limit (0 = disabled) */ + u8 dwrr; + + int vport_id; + struct hclge_dev *back; /* Back reference to associated dev */ + struct hnae3_handle nic; + struct hnae3_handle roce; +}; + +void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc, + bool en_mc, bool en_bc, int vport_id); + +int hclge_add_uc_addr_common(struct hclge_vport *vport, + const unsigned char *addr); +int hclge_rm_uc_addr_common(struct hclge_vport *vport, + const unsigned char *addr); +int hclge_add_mc_addr_common(struct hclge_vport *vport, + const unsigned char *addr); +int hclge_rm_mc_addr_common(struct hclge_vport *vport, + const unsigned char *addr); + +int hclge_cfg_func_mta_filter(struct hclge_dev *hdev, + u8 func_id, + bool enable); +struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle); +int hclge_map_vport_ring_to_vector(struct hclge_vport *vport, int vector, + struct hnae3_ring_chain_node *ring_chain); +static inline int hclge_get_queue_id(struct hnae3_queue *queue) +{ + struct hclge_tqp *tqp = container_of(queue, struct hclge_tqp, q); + + return tqp->index; +} + +int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex); +int hclge_set_vf_vlan_common(struct hclge_dev *vport, int vfid, + bool is_kill, u16 vlan, u8 qos, __be16 proto); +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c new file mode 100644 index 000000000000..f32d719c4f77 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -0,0 +1,213 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/etherdevice.h> +#include <linux/kernel.h> + +#include "hclge_cmd.h" +#include "hclge_main.h" +#include "hclge_mdio.h" + +enum hclge_mdio_c22_op_seq { + HCLGE_MDIO_C22_WRITE = 1, + HCLGE_MDIO_C22_READ = 2 +}; + +#define HCLGE_MDIO_CTRL_START_B 0 +#define HCLGE_MDIO_CTRL_ST_S 1 +#define HCLGE_MDIO_CTRL_ST_M (0x3 << HCLGE_MDIO_CTRL_ST_S) +#define HCLGE_MDIO_CTRL_OP_S 3 +#define HCLGE_MDIO_CTRL_OP_M (0x3 << HCLGE_MDIO_CTRL_OP_S) + +#define HCLGE_MDIO_PHYID_S 0 +#define HCLGE_MDIO_PHYID_M (0x1f << HCLGE_MDIO_PHYID_S) + +#define HCLGE_MDIO_PHYREG_S 0 +#define HCLGE_MDIO_PHYREG_M (0x1f << HCLGE_MDIO_PHYREG_S) + +#define HCLGE_MDIO_STA_B 0 + +struct hclge_mdio_cfg_cmd { + u8 ctrl_bit; + u8 phyid; + u8 phyad; + u8 rsvd; + __le16 reserve; + __le16 data_wr; + __le16 data_rd; + __le16 sta; +}; + +static int hclge_mdio_write(struct mii_bus *bus, int phyid, int regnum, + u16 data) +{ + struct hclge_mdio_cfg_cmd *mdio_cmd; + struct hclge_dev *hdev = bus->priv; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, false); + + mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data; + + hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M, + HCLGE_MDIO_PHYID_S, phyid); + hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M, + HCLGE_MDIO_PHYREG_S, regnum); + + hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1); + hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M, + HCLGE_MDIO_CTRL_ST_S, 1); + hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M, + HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE); + + mdio_cmd->data_wr = cpu_to_le16(data); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "mdio write fail when sending cmd, status is %d.\n", + ret); + return ret; + } + + return 0; +} + +static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum) +{ + struct hclge_mdio_cfg_cmd *mdio_cmd; + struct hclge_dev *hdev = bus->priv; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, true); + + mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data; + + hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M, + HCLGE_MDIO_PHYID_S, phyid); + hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M, + HCLGE_MDIO_PHYREG_S, regnum); + + hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1); + hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M, + HCLGE_MDIO_CTRL_ST_S, 1); + hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M, + HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ); + + /* Read out phy data */ + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "mdio read fail when get data, status is %d.\n", + ret); + return ret; + } + + if (hnae_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) { + dev_err(&hdev->pdev->dev, "mdio read data error\n"); + return -EIO; + } + + return le16_to_cpu(mdio_cmd->data_rd); +} + +int hclge_mac_mdio_config(struct hclge_dev *hdev) +{ + struct hclge_mac *mac = &hdev->hw.mac; + struct phy_device *phydev; + struct mii_bus *mdio_bus; + int ret; + + if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) + return 0; + + mdio_bus = devm_mdiobus_alloc(&hdev->pdev->dev); + if (!mdio_bus) + return -ENOMEM; + + mdio_bus->name = "hisilicon MII bus"; + mdio_bus->read = hclge_mdio_read; + mdio_bus->write = hclge_mdio_write; + snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s-%s", "mii", + dev_name(&hdev->pdev->dev)); + + mdio_bus->parent = &hdev->pdev->dev; + mdio_bus->priv = hdev; + mdio_bus->phy_mask = ~(1 << mac->phy_addr); + ret = mdiobus_register(mdio_bus); + if (ret) { + dev_err(mdio_bus->parent, + "Failed to register MDIO bus ret = %#x\n", ret); + return ret; + } + + phydev = mdiobus_get_phy(mdio_bus, mac->phy_addr); + if (!phydev) { + dev_err(mdio_bus->parent, "Failed to get phy device\n"); + mdiobus_unregister(mdio_bus); + return -EIO; + } + + mac->phydev = phydev; + mac->mdio_bus = mdio_bus; + + return 0; +} + +static void hclge_mac_adjust_link(struct net_device *netdev) +{ + struct hnae3_handle *h = *((void **)netdev_priv(netdev)); + struct hclge_vport *vport = hclge_get_vport(h); + struct hclge_dev *hdev = vport->back; + int duplex, speed; + int ret; + + speed = netdev->phydev->speed; + duplex = netdev->phydev->duplex; + + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex); + if (ret) + netdev_err(netdev, "failed to adjust link.\n"); +} + +int hclge_mac_start_phy(struct hclge_dev *hdev) +{ + struct net_device *netdev = hdev->vport[0].nic.netdev; + struct phy_device *phydev = hdev->hw.mac.phydev; + int ret; + + if (!phydev) + return 0; + + ret = phy_connect_direct(netdev, phydev, + hclge_mac_adjust_link, + PHY_INTERFACE_MODE_SGMII); + if (ret) { + netdev_err(netdev, "phy_connect_direct err.\n"); + return ret; + } + + phy_start(phydev); + + return 0; +} + +void hclge_mac_stop_phy(struct hclge_dev *hdev) +{ + struct net_device *netdev = hdev->vport[0].nic.netdev; + struct phy_device *phydev = netdev->phydev; + + if (!phydev) + return; + + phy_stop(phydev); + phy_disconnect(phydev); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h new file mode 100644 index 000000000000..c5e91cfb8f2c --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h @@ -0,0 +1,17 @@ +/* + * Copyright (c) 2016-2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HCLGE_MDIO_H +#define __HCLGE_MDIO_H + +int hclge_mac_mdio_config(struct hclge_dev *hdev); +int hclge_mac_start_phy(struct hclge_dev *hdev); +void hclge_mac_stop_phy(struct hclge_dev *hdev); + +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c new file mode 100644 index 000000000000..1c577d268f00 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -0,0 +1,1015 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/etherdevice.h> + +#include "hclge_cmd.h" +#include "hclge_main.h" +#include "hclge_tm.h" + +enum hclge_shaper_level { + HCLGE_SHAPER_LVL_PRI = 0, + HCLGE_SHAPER_LVL_PG = 1, + HCLGE_SHAPER_LVL_PORT = 2, + HCLGE_SHAPER_LVL_QSET = 3, + HCLGE_SHAPER_LVL_CNT = 4, + HCLGE_SHAPER_LVL_VF = 0, + HCLGE_SHAPER_LVL_PF = 1, +}; + +#define HCLGE_SHAPER_BS_U_DEF 1 +#define HCLGE_SHAPER_BS_S_DEF 4 + +#define HCLGE_ETHER_MAX_RATE 100000 + +/* hclge_shaper_para_calc: calculate ir parameter for the shaper + * @ir: Rate to be config, its unit is Mbps + * @shaper_level: the shaper level. eg: port, pg, priority, queueset + * @ir_b: IR_B parameter of IR shaper + * @ir_u: IR_U parameter of IR shaper + * @ir_s: IR_S parameter of IR shaper + * + * the formula: + * + * IR_b * (2 ^ IR_u) * 8 + * IR(Mbps) = ------------------------- * CLOCK(1000Mbps) + * Tick * (2 ^ IR_s) + * + * @return: 0: calculate sucessful, negative: fail + */ +static int hclge_shaper_para_calc(u32 ir, u8 shaper_level, + u8 *ir_b, u8 *ir_u, u8 *ir_s) +{ + const u16 tick_array[HCLGE_SHAPER_LVL_CNT] = { + 6 * 256, /* Prioriy level */ + 6 * 32, /* Prioriy group level */ + 6 * 8, /* Port level */ + 6 * 256 /* Qset level */ + }; + u8 ir_u_calc = 0, ir_s_calc = 0; + u32 ir_calc; + u32 tick; + + /* Calc tick */ + if (shaper_level >= HCLGE_SHAPER_LVL_CNT) + return -EINVAL; + + tick = tick_array[shaper_level]; + + /** + * Calc the speed if ir_b = 126, ir_u = 0 and ir_s = 0 + * the formula is changed to: + * 126 * 1 * 8 + * ir_calc = ---------------- * 1000 + * tick * 1 + */ + ir_calc = (1008000 + (tick >> 1) - 1) / tick; + + if (ir_calc == ir) { + *ir_b = 126; + *ir_u = 0; + *ir_s = 0; + + return 0; + } else if (ir_calc > ir) { + /* Increasing the denominator to select ir_s value */ + while (ir_calc > ir) { + ir_s_calc++; + ir_calc = 1008000 / (tick * (1 << ir_s_calc)); + } + + if (ir_calc == ir) + *ir_b = 126; + else + *ir_b = (ir * tick * (1 << ir_s_calc) + 4000) / 8000; + } else { + /* Increasing the numerator to select ir_u value */ + u32 numerator; + + while (ir_calc < ir) { + ir_u_calc++; + numerator = 1008000 * (1 << ir_u_calc); + ir_calc = (numerator + (tick >> 1)) / tick; + } + + if (ir_calc == ir) { + *ir_b = 126; + } else { + u32 denominator = (8000 * (1 << --ir_u_calc)); + *ir_b = (ir * tick + (denominator >> 1)) / denominator; + } + } + + *ir_u = ir_u_calc; + *ir_s = ir_s_calc; + + return 0; +} + +static int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx) +{ + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PAUSE_EN, false); + + desc.data[0] = cpu_to_le32((tx ? HCLGE_TX_MAC_PAUSE_EN_MSK : 0) | + (rx ? HCLGE_RX_MAC_PAUSE_EN_MSK : 0)); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_fill_pri_array(struct hclge_dev *hdev, u8 *pri, u8 pri_id) +{ + u8 tc; + + for (tc = 0; tc < hdev->tm_info.num_tc; tc++) + if (hdev->tm_info.tc_info[tc].up == pri_id) + break; + + if (tc >= hdev->tm_info.num_tc) + return -EINVAL; + + /** + * the register for priority has four bytes, the first bytes includes + * priority0 and priority1, the higher 4bit stands for priority1 + * while the lower 4bit stands for priority0, as below: + * first byte: | pri_1 | pri_0 | + * second byte: | pri_3 | pri_2 | + * third byte: | pri_5 | pri_4 | + * fourth byte: | pri_7 | pri_6 | + */ + pri[pri_id >> 1] |= tc << ((pri_id & 1) * 4); + + return 0; +} + +static int hclge_up_to_tc_map(struct hclge_dev *hdev) +{ + struct hclge_desc desc; + u8 *pri = (u8 *)desc.data; + u8 pri_id; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, false); + + for (pri_id = 0; pri_id < hdev->tm_info.num_tc; pri_id++) { + ret = hclge_fill_pri_array(hdev, pri, pri_id); + if (ret) + return ret; + } + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_pg_to_pri_map_cfg(struct hclge_dev *hdev, + u8 pg_id, u8 pri_bit_map) +{ + struct hclge_pg_to_pri_link_cmd *map; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_TO_PRI_LINK, false); + + map = (struct hclge_pg_to_pri_link_cmd *)desc.data; + + map->pg_id = pg_id; + map->pri_bit_map = pri_bit_map; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_qs_to_pri_map_cfg(struct hclge_dev *hdev, + u16 qs_id, u8 pri) +{ + struct hclge_qs_to_pri_link_cmd *map; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_TO_PRI_LINK, false); + + map = (struct hclge_qs_to_pri_link_cmd *)desc.data; + + map->qs_id = cpu_to_le16(qs_id); + map->priority = pri; + map->link_vld = HCLGE_TM_QS_PRI_LINK_VLD_MSK; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_q_to_qs_map_cfg(struct hclge_dev *hdev, + u8 q_id, u16 qs_id) +{ + struct hclge_nq_to_qs_link_cmd *map; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NQ_TO_QS_LINK, false); + + map = (struct hclge_nq_to_qs_link_cmd *)desc.data; + + map->nq_id = cpu_to_le16(q_id); + map->qset_id = cpu_to_le16(qs_id | HCLGE_TM_Q_QS_LINK_VLD_MSK); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_pg_weight_cfg(struct hclge_dev *hdev, u8 pg_id, + u8 dwrr) +{ + struct hclge_pg_weight_cmd *weight; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_WEIGHT, false); + + weight = (struct hclge_pg_weight_cmd *)desc.data; + + weight->pg_id = pg_id; + weight->dwrr = dwrr; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_pri_weight_cfg(struct hclge_dev *hdev, u8 pri_id, + u8 dwrr) +{ + struct hclge_priority_weight_cmd *weight; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PRI_WEIGHT, false); + + weight = (struct hclge_priority_weight_cmd *)desc.data; + + weight->pri_id = pri_id; + weight->dwrr = dwrr; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_qs_weight_cfg(struct hclge_dev *hdev, u16 qs_id, + u8 dwrr) +{ + struct hclge_qs_weight_cmd *weight; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_WEIGHT, false); + + weight = (struct hclge_qs_weight_cmd *)desc.data; + + weight->qs_id = cpu_to_le16(qs_id); + weight->dwrr = dwrr; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_pg_shapping_cfg(struct hclge_dev *hdev, + enum hclge_shap_bucket bucket, u8 pg_id, + u8 ir_b, u8 ir_u, u8 ir_s, u8 bs_b, u8 bs_s) +{ + struct hclge_pg_shapping_cmd *shap_cfg_cmd; + enum hclge_opcode_type opcode; + struct hclge_desc desc; + + opcode = bucket ? HCLGE_OPC_TM_PG_P_SHAPPING : + HCLGE_OPC_TM_PG_C_SHAPPING; + hclge_cmd_setup_basic_desc(&desc, opcode, false); + + shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data; + + shap_cfg_cmd->pg_id = pg_id; + + hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b); + hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u); + hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s); + hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b); + hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_pri_shapping_cfg(struct hclge_dev *hdev, + enum hclge_shap_bucket bucket, u8 pri_id, + u8 ir_b, u8 ir_u, u8 ir_s, + u8 bs_b, u8 bs_s) +{ + struct hclge_pri_shapping_cmd *shap_cfg_cmd; + enum hclge_opcode_type opcode; + struct hclge_desc desc; + + opcode = bucket ? HCLGE_OPC_TM_PRI_P_SHAPPING : + HCLGE_OPC_TM_PRI_C_SHAPPING; + + hclge_cmd_setup_basic_desc(&desc, opcode, false); + + shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data; + + shap_cfg_cmd->pri_id = pri_id; + + hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b); + hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u); + hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s); + hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b); + hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_pg_schd_mode_cfg(struct hclge_dev *hdev, u8 pg_id) +{ + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_SCH_MODE_CFG, false); + + if (hdev->tm_info.pg_info[pg_id].pg_sch_mode == HCLGE_SCH_MODE_DWRR) + desc.data[1] = cpu_to_le32(HCLGE_TM_TX_SCHD_DWRR_MSK); + else + desc.data[1] = 0; + + desc.data[0] = cpu_to_le32(pg_id); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_pri_schd_mode_cfg(struct hclge_dev *hdev, u8 pri_id) +{ + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PRI_SCH_MODE_CFG, false); + + if (hdev->tm_info.tc_info[pri_id].tc_sch_mode == HCLGE_SCH_MODE_DWRR) + desc.data[1] = cpu_to_le32(HCLGE_TM_TX_SCHD_DWRR_MSK); + else + desc.data[1] = 0; + + desc.data[0] = cpu_to_le32(pri_id); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_qs_schd_mode_cfg(struct hclge_dev *hdev, u16 qs_id) +{ + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_QS_SCH_MODE_CFG, false); + + if (hdev->tm_info.tc_info[qs_id].tc_sch_mode == HCLGE_SCH_MODE_DWRR) + desc.data[1] = cpu_to_le32(HCLGE_TM_TX_SCHD_DWRR_MSK); + else + desc.data[1] = 0; + + desc.data[0] = cpu_to_le32(qs_id); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static int hclge_tm_qs_bp_cfg(struct hclge_dev *hdev, u8 tc) +{ + struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd; + struct hclge_desc desc; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_BP_TO_QSET_MAPPING, + false); + + bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data; + + bp_to_qs_map_cmd->tc_id = tc; + + /* Qset and tc is one by one mapping */ + bp_to_qs_map_cmd->qs_bit_map = cpu_to_le32(1 << tc); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + +static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) +{ + struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + struct hclge_dev *hdev = vport->back; + u8 i; + + kinfo = &vport->nic.kinfo; + vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit; + kinfo->num_tc = + min_t(u16, kinfo->num_tqps, hdev->tm_info.num_tc); + kinfo->rss_size + = min_t(u16, hdev->rss_size_max, + kinfo->num_tqps / kinfo->num_tc); + vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id; + vport->dwrr = 100; /* 100 percent as init */ + + for (i = 0; i < kinfo->num_tc; i++) { + if (hdev->hw_tc_map & BIT(i)) { + kinfo->tc_info[i].enable = true; + kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size; + kinfo->tc_info[i].tqp_count = kinfo->rss_size; + kinfo->tc_info[i].tc = i; + kinfo->tc_info[i].up = hdev->tm_info.tc_info[i].up; + } else { + /* Set to default queue if TC is disable */ + kinfo->tc_info[i].enable = false; + kinfo->tc_info[i].tqp_offset = 0; + kinfo->tc_info[i].tqp_count = 1; + kinfo->tc_info[i].tc = 0; + kinfo->tc_info[i].up = 0; + } + } +} + +static void hclge_tm_vport_info_update(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + u32 i; + + for (i = 0; i < hdev->num_alloc_vport; i++) { + hclge_tm_vport_tc_info_update(vport); + + vport++; + } +} + +static void hclge_tm_tc_info_init(struct hclge_dev *hdev) +{ + u8 i; + + for (i = 0; i < hdev->tm_info.num_tc; i++) { + hdev->tm_info.tc_info[i].tc_id = i; + hdev->tm_info.tc_info[i].tc_sch_mode = HCLGE_SCH_MODE_DWRR; + hdev->tm_info.tc_info[i].up = i; + hdev->tm_info.tc_info[i].pgid = 0; + hdev->tm_info.tc_info[i].bw_limit = + hdev->tm_info.pg_info[0].bw_limit; + } + + hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE; +} + +static void hclge_tm_pg_info_init(struct hclge_dev *hdev) +{ + u8 i; + + for (i = 0; i < hdev->tm_info.num_pg; i++) { + int k; + + hdev->tm_info.pg_dwrr[i] = i ? 0 : 100; + + hdev->tm_info.pg_info[i].pg_id = i; + hdev->tm_info.pg_info[i].pg_sch_mode = HCLGE_SCH_MODE_DWRR; + + hdev->tm_info.pg_info[i].bw_limit = HCLGE_ETHER_MAX_RATE; + + if (i != 0) + continue; + + hdev->tm_info.pg_info[i].tc_bit_map = hdev->hw_tc_map; + for (k = 0; k < hdev->tm_info.num_tc; k++) + hdev->tm_info.pg_info[i].tc_dwrr[k] = 100; + } +} + +static int hclge_tm_schd_info_init(struct hclge_dev *hdev) +{ + if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) && + (hdev->tm_info.num_pg != 1)) + return -EINVAL; + + hclge_tm_pg_info_init(hdev); + + hclge_tm_tc_info_init(hdev); + + hclge_tm_vport_info_update(hdev); + + hdev->tm_info.fc_mode = HCLGE_FC_NONE; + hdev->fc_mode_last_time = hdev->tm_info.fc_mode; + + return 0; +} + +static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev) +{ + int ret; + u32 i; + + if (hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) + return 0; + + for (i = 0; i < hdev->tm_info.num_pg; i++) { + /* Cfg mapping */ + ret = hclge_tm_pg_to_pri_map_cfg( + hdev, i, hdev->tm_info.pg_info[i].tc_bit_map); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_pg_shaper_cfg(struct hclge_dev *hdev) +{ + u8 ir_u, ir_b, ir_s; + int ret; + u32 i; + + /* Cfg pg schd */ + if (hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) + return 0; + + /* Pg to pri */ + for (i = 0; i < hdev->tm_info.num_pg; i++) { + /* Calc shaper para */ + ret = hclge_shaper_para_calc( + hdev->tm_info.pg_info[i].bw_limit, + HCLGE_SHAPER_LVL_PG, + &ir_b, &ir_u, &ir_s); + if (ret) + return ret; + + ret = hclge_tm_pg_shapping_cfg(hdev, + HCLGE_TM_SHAP_C_BUCKET, i, + 0, 0, 0, HCLGE_SHAPER_BS_U_DEF, + HCLGE_SHAPER_BS_S_DEF); + if (ret) + return ret; + + ret = hclge_tm_pg_shapping_cfg(hdev, + HCLGE_TM_SHAP_P_BUCKET, i, + ir_b, ir_u, ir_s, + HCLGE_SHAPER_BS_U_DEF, + HCLGE_SHAPER_BS_S_DEF); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_pg_dwrr_cfg(struct hclge_dev *hdev) +{ + int ret; + u32 i; + + /* cfg pg schd */ + if (hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) + return 0; + + /* pg to prio */ + for (i = 0; i < hdev->tm_info.num_pg; i++) { + /* Cfg dwrr */ + ret = hclge_tm_pg_weight_cfg(hdev, i, + hdev->tm_info.pg_dwrr[i]); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_vport_q_to_qs_map(struct hclge_dev *hdev, + struct hclge_vport *vport) +{ + struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + struct hnae3_queue **tqp = kinfo->tqp; + struct hnae3_tc_info *v_tc_info; + u32 i, j; + int ret; + + for (i = 0; i < kinfo->num_tc; i++) { + v_tc_info = &kinfo->tc_info[i]; + for (j = 0; j < v_tc_info->tqp_count; j++) { + struct hnae3_queue *q = tqp[v_tc_info->tqp_offset + j]; + + ret = hclge_tm_q_to_qs_map_cfg(hdev, + hclge_get_queue_id(q), + vport->qs_offset + i); + if (ret) + return ret; + } + } + + return 0; +} + +static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + int ret; + u32 i; + + if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) { + /* Cfg qs -> pri mapping, one by one mapping */ + for (i = 0; i < hdev->tm_info.num_tc; i++) { + ret = hclge_tm_qs_to_pri_map_cfg(hdev, i, i); + if (ret) + return ret; + } + } else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) { + int k; + /* Cfg qs -> pri mapping, qs = tc, pri = vf, 8 qs -> 1 pri */ + for (k = 0; k < hdev->num_alloc_vport; k++) + for (i = 0; i < HNAE3_MAX_TC; i++) { + ret = hclge_tm_qs_to_pri_map_cfg( + hdev, vport[k].qs_offset + i, k); + if (ret) + return ret; + } + } else { + return -EINVAL; + } + + /* Cfg q -> qs mapping */ + for (i = 0; i < hdev->num_alloc_vport; i++) { + ret = hclge_vport_q_to_qs_map(hdev, vport); + if (ret) + return ret; + + vport++; + } + + return 0; +} + +static int hclge_tm_pri_tc_base_shaper_cfg(struct hclge_dev *hdev) +{ + u8 ir_u, ir_b, ir_s; + int ret; + u32 i; + + for (i = 0; i < hdev->tm_info.num_tc; i++) { + ret = hclge_shaper_para_calc( + hdev->tm_info.tc_info[i].bw_limit, + HCLGE_SHAPER_LVL_PRI, + &ir_b, &ir_u, &ir_s); + if (ret) + return ret; + + ret = hclge_tm_pri_shapping_cfg( + hdev, HCLGE_TM_SHAP_C_BUCKET, i, + 0, 0, 0, HCLGE_SHAPER_BS_U_DEF, + HCLGE_SHAPER_BS_S_DEF); + if (ret) + return ret; + + ret = hclge_tm_pri_shapping_cfg( + hdev, HCLGE_TM_SHAP_P_BUCKET, i, + ir_b, ir_u, ir_s, HCLGE_SHAPER_BS_U_DEF, + HCLGE_SHAPER_BS_S_DEF); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_pri_vnet_base_shaper_pri_cfg(struct hclge_vport *vport) +{ + struct hclge_dev *hdev = vport->back; + u8 ir_u, ir_b, ir_s; + int ret; + + ret = hclge_shaper_para_calc(vport->bw_limit, HCLGE_SHAPER_LVL_VF, + &ir_b, &ir_u, &ir_s); + if (ret) + return ret; + + ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_C_BUCKET, + vport->vport_id, + 0, 0, 0, HCLGE_SHAPER_BS_U_DEF, + HCLGE_SHAPER_BS_S_DEF); + if (ret) + return ret; + + ret = hclge_tm_pri_shapping_cfg(hdev, HCLGE_TM_SHAP_P_BUCKET, + vport->vport_id, + ir_b, ir_u, ir_s, + HCLGE_SHAPER_BS_U_DEF, + HCLGE_SHAPER_BS_S_DEF); + if (ret) + return ret; + + return 0; +} + +static int hclge_tm_pri_vnet_base_shaper_qs_cfg(struct hclge_vport *vport) +{ + struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + struct hclge_dev *hdev = vport->back; + struct hnae3_tc_info *v_tc_info; + u8 ir_u, ir_b, ir_s; + u32 i; + int ret; + + for (i = 0; i < kinfo->num_tc; i++) { + v_tc_info = &kinfo->tc_info[i]; + ret = hclge_shaper_para_calc( + hdev->tm_info.tc_info[i].bw_limit, + HCLGE_SHAPER_LVL_QSET, + &ir_b, &ir_u, &ir_s); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_pri_vnet_base_shaper_cfg(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + int ret; + u32 i; + + /* Need config vport shaper */ + for (i = 0; i < hdev->num_alloc_vport; i++) { + ret = hclge_tm_pri_vnet_base_shaper_pri_cfg(vport); + if (ret) + return ret; + + ret = hclge_tm_pri_vnet_base_shaper_qs_cfg(vport); + if (ret) + return ret; + + vport++; + } + + return 0; +} + +static int hclge_tm_pri_shaper_cfg(struct hclge_dev *hdev) +{ + int ret; + + if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) { + ret = hclge_tm_pri_tc_base_shaper_cfg(hdev); + if (ret) + return ret; + } else { + ret = hclge_tm_pri_vnet_base_shaper_cfg(hdev); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev) +{ + struct hclge_pg_info *pg_info; + u8 dwrr; + int ret; + u32 i; + + for (i = 0; i < hdev->tm_info.num_tc; i++) { + pg_info = + &hdev->tm_info.pg_info[hdev->tm_info.tc_info[i].pgid]; + dwrr = pg_info->tc_dwrr[i]; + + ret = hclge_tm_pri_weight_cfg(hdev, i, dwrr); + if (ret) + return ret; + + ret = hclge_tm_qs_weight_cfg(hdev, i, dwrr); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_pri_vnet_base_dwrr_pri_cfg(struct hclge_vport *vport) +{ + struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + struct hclge_dev *hdev = vport->back; + int ret; + u8 i; + + /* Vf dwrr */ + ret = hclge_tm_pri_weight_cfg(hdev, vport->vport_id, vport->dwrr); + if (ret) + return ret; + + /* Qset dwrr */ + for (i = 0; i < kinfo->num_tc; i++) { + ret = hclge_tm_qs_weight_cfg( + hdev, vport->qs_offset + i, + hdev->tm_info.pg_info[0].tc_dwrr[i]); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_pri_vnet_base_dwrr_cfg(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + int ret; + u32 i; + + for (i = 0; i < hdev->num_alloc_vport; i++) { + ret = hclge_tm_pri_vnet_base_dwrr_pri_cfg(vport); + if (ret) + return ret; + + vport++; + } + + return 0; +} + +static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev) +{ + int ret; + + if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) { + ret = hclge_tm_pri_tc_base_dwrr_cfg(hdev); + if (ret) + return ret; + } else { + ret = hclge_tm_pri_vnet_base_dwrr_cfg(hdev); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_map_cfg(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_tm_pg_to_pri_map(hdev); + if (ret) + return ret; + + return hclge_tm_pri_q_qs_cfg(hdev); +} + +static int hclge_tm_shaper_cfg(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_tm_pg_shaper_cfg(hdev); + if (ret) + return ret; + + return hclge_tm_pri_shaper_cfg(hdev); +} + +int hclge_tm_dwrr_cfg(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_tm_pg_dwrr_cfg(hdev); + if (ret) + return ret; + + return hclge_tm_pri_dwrr_cfg(hdev); +} + +static int hclge_tm_lvl2_schd_mode_cfg(struct hclge_dev *hdev) +{ + int ret; + u8 i; + + /* Only being config on TC-Based scheduler mode */ + if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) + return 0; + + for (i = 0; i < hdev->tm_info.num_pg; i++) { + ret = hclge_tm_pg_schd_mode_cfg(hdev, i); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_schd_mode_vnet_base_cfg(struct hclge_vport *vport) +{ + struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + struct hclge_dev *hdev = vport->back; + int ret; + u8 i; + + ret = hclge_tm_pri_schd_mode_cfg(hdev, vport->vport_id); + if (ret) + return ret; + + for (i = 0; i < kinfo->num_tc; i++) { + ret = hclge_tm_qs_schd_mode_cfg(hdev, vport->qs_offset + i); + if (ret) + return ret; + } + + return 0; +} + +static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + int ret; + u8 i; + + if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) { + for (i = 0; i < hdev->tm_info.num_tc; i++) { + ret = hclge_tm_pri_schd_mode_cfg(hdev, i); + if (ret) + return ret; + + ret = hclge_tm_qs_schd_mode_cfg(hdev, i); + if (ret) + return ret; + } + } else { + for (i = 0; i < hdev->num_alloc_vport; i++) { + ret = hclge_tm_schd_mode_vnet_base_cfg(vport); + if (ret) + return ret; + + vport++; + } + } + + return 0; +} + +static int hclge_tm_schd_mode_hw(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_tm_lvl2_schd_mode_cfg(hdev); + if (ret) + return ret; + + return hclge_tm_lvl34_schd_mode_cfg(hdev); +} + +static int hclge_tm_schd_setup_hw(struct hclge_dev *hdev) +{ + int ret; + + /* Cfg tm mapping */ + ret = hclge_tm_map_cfg(hdev); + if (ret) + return ret; + + /* Cfg tm shaper */ + ret = hclge_tm_shaper_cfg(hdev); + if (ret) + return ret; + + /* Cfg dwrr */ + ret = hclge_tm_dwrr_cfg(hdev); + if (ret) + return ret; + + /* Cfg schd mode for each level schd */ + return hclge_tm_schd_mode_hw(hdev); +} + +int hclge_pause_setup_hw(struct hclge_dev *hdev) +{ + bool en = hdev->tm_info.fc_mode != HCLGE_FC_PFC; + int ret; + u8 i; + + ret = hclge_mac_pause_en_cfg(hdev, en, en); + if (ret) + return ret; + + for (i = 0; i < hdev->tm_info.num_tc; i++) { + ret = hclge_tm_qs_bp_cfg(hdev, i); + if (ret) + return ret; + } + + return hclge_up_to_tc_map(hdev); +} + +int hclge_tm_init_hw(struct hclge_dev *hdev) +{ + int ret; + + if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) && + (hdev->tx_sch_mode != HCLGE_FLAG_VNET_BASE_SCH_MODE)) + return -ENOTSUPP; + + ret = hclge_tm_schd_setup_hw(hdev); + if (ret) + return ret; + + ret = hclge_pause_setup_hw(hdev); + if (ret) + return ret; + + return 0; +} + +int hclge_tm_schd_init(struct hclge_dev *hdev) +{ + int ret = hclge_tm_schd_info_init(hdev); + + if (ret) + return ret; + + return hclge_tm_init_hw(hdev); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h new file mode 100644 index 000000000000..7e67337dfaf2 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -0,0 +1,106 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HCLGE_TM_H +#define __HCLGE_TM_H + +#include <linux/types.h> + +/* MAC Pause */ +#define HCLGE_TX_MAC_PAUSE_EN_MSK BIT(0) +#define HCLGE_RX_MAC_PAUSE_EN_MSK BIT(1) + +#define HCLGE_TM_PORT_BASE_MODE_MSK BIT(0) + +/* SP or DWRR */ +#define HCLGE_TM_TX_SCHD_DWRR_MSK BIT(0) +#define HCLGE_TM_TX_SCHD_SP_MSK (0xFE) + +struct hclge_pg_to_pri_link_cmd { + u8 pg_id; + u8 rsvd1[3]; + u8 pri_bit_map; +}; + +struct hclge_qs_to_pri_link_cmd { + __le16 qs_id; + __le16 rsvd; + u8 priority; +#define HCLGE_TM_QS_PRI_LINK_VLD_MSK BIT(0) + u8 link_vld; +}; + +struct hclge_nq_to_qs_link_cmd { + __le16 nq_id; + __le16 rsvd; +#define HCLGE_TM_Q_QS_LINK_VLD_MSK BIT(10) + __le16 qset_id; +}; + +struct hclge_pg_weight_cmd { + u8 pg_id; + u8 dwrr; +}; + +struct hclge_priority_weight_cmd { + u8 pri_id; + u8 dwrr; +}; + +struct hclge_qs_weight_cmd { + __le16 qs_id; + u8 dwrr; +}; + +#define HCLGE_TM_SHAP_IR_B_MSK GENMASK(7, 0) +#define HCLGE_TM_SHAP_IR_B_LSH 0 +#define HCLGE_TM_SHAP_IR_U_MSK GENMASK(11, 8) +#define HCLGE_TM_SHAP_IR_U_LSH 8 +#define HCLGE_TM_SHAP_IR_S_MSK GENMASK(15, 12) +#define HCLGE_TM_SHAP_IR_S_LSH 12 +#define HCLGE_TM_SHAP_BS_B_MSK GENMASK(20, 16) +#define HCLGE_TM_SHAP_BS_B_LSH 16 +#define HCLGE_TM_SHAP_BS_S_MSK GENMASK(25, 21) +#define HCLGE_TM_SHAP_BS_S_LSH 21 + +enum hclge_shap_bucket { + HCLGE_TM_SHAP_C_BUCKET = 0, + HCLGE_TM_SHAP_P_BUCKET, +}; + +struct hclge_pri_shapping_cmd { + u8 pri_id; + u8 rsvd[3]; + __le32 pri_shapping_para; +}; + +struct hclge_pg_shapping_cmd { + u8 pg_id; + u8 rsvd[3]; + __le32 pg_shapping_para; +}; + +struct hclge_bp_to_qs_map_cmd { + u8 tc_id; + u8 rsvd[2]; + u8 qs_group_id; + __le32 qs_bit_map; + u32 rsvd1; +}; + +#define hclge_tm_set_feild(dest, string, val) \ + hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \ + (HCLGE_TM_SHAP_##string##_LSH), val) +#define hclge_tm_get_feild(src, string) \ + hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \ + (HCLGE_TM_SHAP_##string##_LSH)) + +int hclge_tm_schd_init(struct hclge_dev *hdev); +int hclge_pause_setup_hw(struct hclge_dev *hdev); +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c new file mode 100644 index 000000000000..1c3e29447891 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c @@ -0,0 +1,2891 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/dma-mapping.h> +#include <linux/etherdevice.h> +#include <linux/interrupt.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/skbuff.h> +#include <linux/sctp.h> +#include <linux/vermagic.h> +#include <net/gre.h> +#include <net/vxlan.h> + +#include "hnae3.h" +#include "hns3_enet.h" + +const char hns3_driver_name[] = "hns3"; +const char hns3_driver_version[] = VERMAGIC_STRING; +static const char hns3_driver_string[] = + "Hisilicon Ethernet Network Driver for Hip08 Family"; +static const char hns3_copyright[] = "Copyright (c) 2017 Huawei Corporation."; +static struct hnae3_client client; + +/* hns3_pci_tbl - PCI Device ID Table + * + * Last entry must be all 0s + * + * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, + * Class, Class Mask, private data (not used) } + */ +static const struct pci_device_id hns3_pci_tbl[] = { + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_GE), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0}, + {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0}, + /* required last entry */ + {0, } +}; +MODULE_DEVICE_TABLE(pci, hns3_pci_tbl); + +static irqreturn_t hns3_irq_handle(int irq, void *dev) +{ + struct hns3_enet_tqp_vector *tqp_vector = dev; + + napi_schedule(&tqp_vector->napi); + + return IRQ_HANDLED; +} + +static void hns3_nic_uninit_irq(struct hns3_nic_priv *priv) +{ + struct hns3_enet_tqp_vector *tqp_vectors; + unsigned int i; + + for (i = 0; i < priv->vector_num; i++) { + tqp_vectors = &priv->tqp_vector[i]; + + if (tqp_vectors->irq_init_flag != HNS3_VECTOR_INITED) + continue; + + /* release the irq resource */ + free_irq(tqp_vectors->vector_irq, tqp_vectors); + tqp_vectors->irq_init_flag = HNS3_VECTOR_NOT_INITED; + } +} + +static int hns3_nic_init_irq(struct hns3_nic_priv *priv) +{ + struct hns3_enet_tqp_vector *tqp_vectors; + int txrx_int_idx = 0; + int rx_int_idx = 0; + int tx_int_idx = 0; + unsigned int i; + int ret; + + for (i = 0; i < priv->vector_num; i++) { + tqp_vectors = &priv->tqp_vector[i]; + + if (tqp_vectors->irq_init_flag == HNS3_VECTOR_INITED) + continue; + + if (tqp_vectors->tx_group.ring && tqp_vectors->rx_group.ring) { + snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1, + "%s-%s-%d", priv->netdev->name, "TxRx", + txrx_int_idx++); + txrx_int_idx++; + } else if (tqp_vectors->rx_group.ring) { + snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1, + "%s-%s-%d", priv->netdev->name, "Rx", + rx_int_idx++); + } else if (tqp_vectors->tx_group.ring) { + snprintf(tqp_vectors->name, HNAE3_INT_NAME_LEN - 1, + "%s-%s-%d", priv->netdev->name, "Tx", + tx_int_idx++); + } else { + /* Skip this unused q_vector */ + continue; + } + + tqp_vectors->name[HNAE3_INT_NAME_LEN - 1] = '\0'; + + ret = request_irq(tqp_vectors->vector_irq, hns3_irq_handle, 0, + tqp_vectors->name, + tqp_vectors); + if (ret) { + netdev_err(priv->netdev, "request irq(%d) fail\n", + tqp_vectors->vector_irq); + return ret; + } + + tqp_vectors->irq_init_flag = HNS3_VECTOR_INITED; + } + + return 0; +} + +static void hns3_mask_vector_irq(struct hns3_enet_tqp_vector *tqp_vector, + u32 mask_en) +{ + writel(mask_en, tqp_vector->mask_addr); +} + +static void hns3_vector_enable(struct hns3_enet_tqp_vector *tqp_vector) +{ + napi_enable(&tqp_vector->napi); + + /* enable vector */ + hns3_mask_vector_irq(tqp_vector, 1); +} + +static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector) +{ + /* disable vector */ + hns3_mask_vector_irq(tqp_vector, 0); + + disable_irq(tqp_vector->vector_irq); + napi_disable(&tqp_vector->napi); +} + +static void hns3_set_vector_coalesc_gl(struct hns3_enet_tqp_vector *tqp_vector, + u32 gl_value) +{ + /* this defines the configuration for GL (Interrupt Gap Limiter) + * GL defines inter interrupt gap. + * GL and RL(Rate Limiter) are 2 ways to acheive interrupt coalescing + */ + writel(gl_value, tqp_vector->mask_addr + HNS3_VECTOR_GL0_OFFSET); + writel(gl_value, tqp_vector->mask_addr + HNS3_VECTOR_GL1_OFFSET); + writel(gl_value, tqp_vector->mask_addr + HNS3_VECTOR_GL2_OFFSET); +} + +static void hns3_set_vector_coalesc_rl(struct hns3_enet_tqp_vector *tqp_vector, + u32 rl_value) +{ + /* this defines the configuration for RL (Interrupt Rate Limiter). + * Rl defines rate of interrupts i.e. number of interrupts-per-second + * GL and RL(Rate Limiter) are 2 ways to acheive interrupt coalescing + */ + writel(rl_value, tqp_vector->mask_addr + HNS3_VECTOR_RL_OFFSET); +} + +static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector) +{ + /* initialize the configuration for interrupt coalescing. + * 1. GL (Interrupt Gap Limiter) + * 2. RL (Interrupt Rate Limiter) + */ + + /* Default :enable interrupt coalesce */ + tqp_vector->rx_group.int_gl = HNS3_INT_GL_50K; + tqp_vector->tx_group.int_gl = HNS3_INT_GL_50K; + hns3_set_vector_coalesc_gl(tqp_vector, HNS3_INT_GL_50K); + /* for now we are disabling Interrupt RL - we + * will re-enable later + */ + hns3_set_vector_coalesc_rl(tqp_vector, 0); + tqp_vector->rx_group.flow_level = HNS3_FLOW_LOW; + tqp_vector->tx_group.flow_level = HNS3_FLOW_LOW; +} + +static int hns3_nic_net_up(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int i, j; + int ret; + + /* get irq resource for all vectors */ + ret = hns3_nic_init_irq(priv); + if (ret) { + netdev_err(netdev, "hns init irq failed! ret=%d\n", ret); + return ret; + } + + /* enable the vectors */ + for (i = 0; i < priv->vector_num; i++) + hns3_vector_enable(&priv->tqp_vector[i]); + + /* start the ae_dev */ + ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0; + if (ret) + goto out_start_err; + + return 0; + +out_start_err: + for (j = i - 1; j >= 0; j--) + hns3_vector_disable(&priv->tqp_vector[j]); + + hns3_nic_uninit_irq(priv); + + return ret; +} + +static int hns3_nic_net_open(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret; + + netif_carrier_off(netdev); + + ret = netif_set_real_num_tx_queues(netdev, h->kinfo.num_tqps); + if (ret) { + netdev_err(netdev, + "netif_set_real_num_tx_queues fail, ret=%d!\n", + ret); + return ret; + } + + ret = netif_set_real_num_rx_queues(netdev, h->kinfo.num_tqps); + if (ret) { + netdev_err(netdev, + "netif_set_real_num_rx_queues fail, ret=%d!\n", ret); + return ret; + } + + ret = hns3_nic_net_up(netdev); + if (ret) { + netdev_err(netdev, + "hns net up fail, ret=%d!\n", ret); + return ret; + } + + return 0; +} + +static void hns3_nic_net_down(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + const struct hnae3_ae_ops *ops; + int i; + + /* stop ae_dev */ + ops = priv->ae_handle->ae_algo->ops; + if (ops->stop) + ops->stop(priv->ae_handle); + + /* disable vectors */ + for (i = 0; i < priv->vector_num; i++) + hns3_vector_disable(&priv->tqp_vector[i]); + + /* free irq resources */ + hns3_nic_uninit_irq(priv); +} + +static int hns3_nic_net_stop(struct net_device *netdev) +{ + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); + + hns3_nic_net_down(netdev); + + return 0; +} + +void hns3_set_multicast_list(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + struct netdev_hw_addr *ha = NULL; + + if (h->ae_algo->ops->set_mc_addr) { + netdev_for_each_mc_addr(ha, netdev) + if (h->ae_algo->ops->set_mc_addr(h, ha->addr)) + netdev_err(netdev, "set multicast fail\n"); + } +} + +static int hns3_nic_uc_sync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->add_uc_addr) + return h->ae_algo->ops->add_uc_addr(h, addr); + + return 0; +} + +static int hns3_nic_uc_unsync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->rm_uc_addr) + return h->ae_algo->ops->rm_uc_addr(h, addr); + + return 0; +} + +static int hns3_nic_mc_sync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->add_mc_addr) + return h->ae_algo->ops->add_mc_addr(h, addr); + + return 0; +} + +static int hns3_nic_mc_unsync(struct net_device *netdev, + const unsigned char *addr) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->rm_mc_addr) + return h->ae_algo->ops->rm_mc_addr(h, addr); + + return 0; +} + +void hns3_nic_set_rx_mode(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo->ops->set_promisc_mode) { + if (netdev->flags & IFF_PROMISC) + h->ae_algo->ops->set_promisc_mode(h, 1); + else + h->ae_algo->ops->set_promisc_mode(h, 0); + } + if (__dev_uc_sync(netdev, hns3_nic_uc_sync, hns3_nic_uc_unsync)) + netdev_err(netdev, "sync uc address fail\n"); + if (netdev->flags & IFF_MULTICAST) + if (__dev_mc_sync(netdev, hns3_nic_mc_sync, hns3_nic_mc_unsync)) + netdev_err(netdev, "sync mc address fail\n"); +} + +static int hns3_set_tso(struct sk_buff *skb, u32 *paylen, + u16 *mss, u32 *type_cs_vlan_tso) +{ + u32 l4_offset, hdr_len; + union l3_hdr_info l3; + union l4_hdr_info l4; + u32 l4_paylen; + int ret; + + if (!skb_is_gso(skb)) + return 0; + + ret = skb_cow_head(skb, 0); + if (ret) + return ret; + + l3.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* Software should clear the IPv4's checksum field when tso is + * needed. + */ + if (l3.v4->version == 4) + l3.v4->check = 0; + + /* tunnel packet.*/ + if (skb_shinfo(skb)->gso_type & (SKB_GSO_GRE | + SKB_GSO_GRE_CSUM | + SKB_GSO_UDP_TUNNEL | + SKB_GSO_UDP_TUNNEL_CSUM)) { + if ((!(skb_shinfo(skb)->gso_type & + SKB_GSO_PARTIAL)) && + (skb_shinfo(skb)->gso_type & + SKB_GSO_UDP_TUNNEL_CSUM)) { + /* Software should clear the udp's checksum + * field when tso is needed. + */ + l4.udp->check = 0; + } + /* reset l3&l4 pointers from outer to inner headers */ + l3.hdr = skb_inner_network_header(skb); + l4.hdr = skb_inner_transport_header(skb); + + /* Software should clear the IPv4's checksum field when + * tso is needed. + */ + if (l3.v4->version == 4) + l3.v4->check = 0; + } + + /* normal or tunnel packet*/ + l4_offset = l4.hdr - skb->data; + hdr_len = (l4.tcp->doff * 4) + l4_offset; + + /* remove payload length from inner pseudo checksum when tso*/ + l4_paylen = skb->len - l4_offset; + csum_replace_by_diff(&l4.tcp->check, + (__force __wsum)htonl(l4_paylen)); + + /* find the txbd field values */ + *paylen = skb->len - hdr_len; + hnae_set_bit(*type_cs_vlan_tso, + HNS3_TXD_TSO_B, 1); + + /* get MSS for TSO */ + *mss = skb_shinfo(skb)->gso_size; + + return 0; +} + +static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto, + u8 *il4_proto) +{ + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } l3; + unsigned char *l4_hdr; + unsigned char *exthdr; + u8 l4_proto_tmp; + __be16 frag_off; + + /* find outer header point */ + l3.hdr = skb_network_header(skb); + l4_hdr = skb_inner_transport_header(skb); + + if (skb->protocol == htons(ETH_P_IPV6)) { + exthdr = l3.hdr + sizeof(*l3.v6); + l4_proto_tmp = l3.v6->nexthdr; + if (l4_hdr != exthdr) + ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto_tmp, &frag_off); + } else if (skb->protocol == htons(ETH_P_IP)) { + l4_proto_tmp = l3.v4->protocol; + } else { + return -EINVAL; + } + + *ol4_proto = l4_proto_tmp; + + /* tunnel packet */ + if (!skb->encapsulation) { + *il4_proto = 0; + return 0; + } + + /* find inner header point */ + l3.hdr = skb_inner_network_header(skb); + l4_hdr = skb_inner_transport_header(skb); + + if (l3.v6->version == 6) { + exthdr = l3.hdr + sizeof(*l3.v6); + l4_proto_tmp = l3.v6->nexthdr; + if (l4_hdr != exthdr) + ipv6_skip_exthdr(skb, exthdr - skb->data, + &l4_proto_tmp, &frag_off); + } else if (l3.v4->version == 4) { + l4_proto_tmp = l3.v4->protocol; + } + + *il4_proto = l4_proto_tmp; + + return 0; +} + +static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto, + u8 il4_proto, u32 *type_cs_vlan_tso, + u32 *ol_type_vlan_len_msec) +{ + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } l3; + union { + struct tcphdr *tcp; + struct udphdr *udp; + struct gre_base_hdr *gre; + unsigned char *hdr; + } l4; + unsigned char *l2_hdr; + u8 l4_proto = ol4_proto; + u32 ol2_len; + u32 ol3_len; + u32 ol4_len; + u32 l2_len; + u32 l3_len; + + l3.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + + /* compute L2 header size for normal packet, defined in 2 Bytes */ + l2_len = l3.hdr - skb->data; + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, l2_len >> 1); + + /* tunnel packet*/ + if (skb->encapsulation) { + /* compute OL2 header size, defined in 2 Bytes */ + ol2_len = l2_len; + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, ol2_len >> 1); + + /* compute OL3 header size, defined in 4 Bytes */ + ol3_len = l4.hdr - l3.hdr; + hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M, + HNS3_TXD_L3LEN_S, ol3_len >> 2); + + /* MAC in UDP, MAC in GRE (0x6558)*/ + if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) { + /* switch MAC header ptr from outer to inner header.*/ + l2_hdr = skb_inner_mac_header(skb); + + /* compute OL4 header size, defined in 4 Bytes. */ + ol4_len = l2_hdr - l4.hdr; + hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, ol4_len >> 2); + + /* switch IP header ptr from outer to inner header */ + l3.hdr = skb_inner_network_header(skb); + + /* compute inner l2 header size, defined in 2 Bytes. */ + l2_len = l3.hdr - l2_hdr; + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M, + HNS3_TXD_L2LEN_S, l2_len >> 1); + } else { + /* skb packet types not supported by hardware, + * txbd len fild doesn't be filled. + */ + return; + } + + /* switch L4 header pointer from outer to inner */ + l4.hdr = skb_inner_transport_header(skb); + + l4_proto = il4_proto; + } + + /* compute inner(/normal) L3 header size, defined in 4 Bytes */ + l3_len = l4.hdr - l3.hdr; + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M, + HNS3_TXD_L3LEN_S, l3_len >> 2); + + /* compute inner(/normal) L4 header size, defined in 4 Bytes */ + switch (l4_proto) { + case IPPROTO_TCP: + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, l4.tcp->doff); + break; + case IPPROTO_SCTP: + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, (sizeof(struct sctphdr) >> 2)); + break; + case IPPROTO_UDP: + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M, + HNS3_TXD_L4LEN_S, (sizeof(struct udphdr) >> 2)); + break; + default: + /* skb packet types not supported by hardware, + * txbd len fild doesn't be filled. + */ + return; + } +} + +static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto, + u8 il4_proto, u32 *type_cs_vlan_tso, + u32 *ol_type_vlan_len_msec) +{ + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } l3; + u32 l4_proto = ol4_proto; + + l3.hdr = skb_network_header(skb); + + /* define OL3 type and tunnel type(OL4).*/ + if (skb->encapsulation) { + /* define outer network header type.*/ + if (skb->protocol == htons(ETH_P_IP)) { + if (skb_is_gso(skb)) + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S, + HNS3_OL3T_IPV4_CSUM); + else + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S, + HNS3_OL3T_IPV4_NO_CSUM); + + } else if (skb->protocol == htons(ETH_P_IPV6)) { + hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M, + HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6); + } + + /* define tunnel type(OL4).*/ + switch (l4_proto) { + case IPPROTO_UDP: + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_TUNTYPE_M, + HNS3_TXD_TUNTYPE_S, + HNS3_TUN_MAC_IN_UDP); + break; + case IPPROTO_GRE: + hnae_set_field(*ol_type_vlan_len_msec, + HNS3_TXD_TUNTYPE_M, + HNS3_TXD_TUNTYPE_S, + HNS3_TUN_NVGRE); + break; + default: + /* drop the skb tunnel packet if hardware don't support, + * because hardware can't calculate csum when TSO. + */ + if (skb_is_gso(skb)) + return -EDOM; + + /* the stack computes the IP header already, + * driver calculate l4 checksum when not TSO. + */ + skb_checksum_help(skb); + return 0; + } + + l3.hdr = skb_inner_network_header(skb); + l4_proto = il4_proto; + } + + if (l3.v4->version == 4) { + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, + HNS3_TXD_L3T_S, HNS3_L3T_IPV4); + + /* the stack computes the IP header already, the only time we + * need the hardware to recompute it is in the case of TSO. + */ + if (skb_is_gso(skb)) + hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1); + + hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); + } else if (l3.v6->version == 6) { + hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M, + HNS3_TXD_L3T_S, HNS3_L3T_IPV6); + hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1); + } + + switch (l4_proto) { + case IPPROTO_TCP: + hnae_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_TCP); + break; + case IPPROTO_UDP: + hnae_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_UDP); + break; + case IPPROTO_SCTP: + hnae_set_field(*type_cs_vlan_tso, + HNS3_TXD_L4T_M, + HNS3_TXD_L4T_S, + HNS3_L4T_SCTP); + break; + default: + /* drop the skb tunnel packet if hardware don't support, + * because hardware can't calculate csum when TSO. + */ + if (skb_is_gso(skb)) + return -EDOM; + + /* the stack computes the IP header already, + * driver calculate l4 checksum when not TSO. + */ + skb_checksum_help(skb); + return 0; + } + + return 0; +} + +static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end) +{ + /* Config bd buffer end */ + hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M, + HNS3_TXD_BDTYPE_M, 0); + hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end); + hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1); + hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 1); +} + +static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + enum hns_desc_type type) +{ + struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; + struct hns3_desc *desc = &ring->desc[ring->next_to_use]; + u32 ol_type_vlan_len_msec = 0; + u16 bdtp_fe_sc_vld_ra_ri = 0; + u32 type_cs_vlan_tso = 0; + struct sk_buff *skb; + u32 paylen = 0; + u16 mss = 0; + __be16 protocol; + u8 ol4_proto; + u8 il4_proto; + int ret; + + /* The txbd's baseinfo of DESC_TYPE_PAGE & DESC_TYPE_SKB */ + desc_cb->priv = priv; + desc_cb->length = size; + desc_cb->dma = dma; + desc_cb->type = type; + + /* now, fill the descriptor */ + desc->addr = cpu_to_le64(dma); + desc->tx.send_size = cpu_to_le16((u16)size); + hns3_set_txbd_baseinfo(&bdtp_fe_sc_vld_ra_ri, frag_end); + desc->tx.bdtp_fe_sc_vld_ra_ri = cpu_to_le16(bdtp_fe_sc_vld_ra_ri); + + if (type == DESC_TYPE_SKB) { + skb = (struct sk_buff *)priv; + paylen = cpu_to_le16(skb->len); + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + skb_reset_mac_len(skb); + protocol = skb->protocol; + + /* vlan packet*/ + if (protocol == htons(ETH_P_8021Q)) { + protocol = vlan_get_protocol(skb); + skb->protocol = protocol; + } + ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); + if (ret) + return ret; + hns3_set_l2l3l4_len(skb, ol4_proto, il4_proto, + &type_cs_vlan_tso, + &ol_type_vlan_len_msec); + ret = hns3_set_l3l4_type_csum(skb, ol4_proto, il4_proto, + &type_cs_vlan_tso, + &ol_type_vlan_len_msec); + if (ret) + return ret; + + ret = hns3_set_tso(skb, &paylen, &mss, + &type_cs_vlan_tso); + if (ret) + return ret; + } + + /* Set txbd */ + desc->tx.ol_type_vlan_len_msec = + cpu_to_le32(ol_type_vlan_len_msec); + desc->tx.type_cs_vlan_tso_len = + cpu_to_le32(type_cs_vlan_tso); + desc->tx.paylen = cpu_to_le16(paylen); + desc->tx.mss = cpu_to_le16(mss); + } + + /* move ring pointer to next.*/ + ring_ptr_move_fw(ring, next_to_use); + + return 0; +} + +static int hns3_fill_desc_tso(struct hns3_enet_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + enum hns_desc_type type) +{ + unsigned int frag_buf_num; + unsigned int k; + int sizeoflast; + int ret; + + frag_buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE; + sizeoflast = size % HNS3_MAX_BD_SIZE; + sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE; + + /* When the frag size is bigger than hardware, split this frag */ + for (k = 0; k < frag_buf_num; k++) { + ret = hns3_fill_desc(ring, priv, + (k == frag_buf_num - 1) ? + sizeoflast : HNS3_MAX_BD_SIZE, + dma + HNS3_MAX_BD_SIZE * k, + frag_end && (k == frag_buf_num - 1) ? 1 : 0, + (type == DESC_TYPE_SKB && !k) ? + DESC_TYPE_SKB : DESC_TYPE_PAGE); + if (ret) + return ret; + } + + return 0; +} + +static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum, + struct hns3_enet_ring *ring) +{ + struct sk_buff *skb = *out_skb; + struct skb_frag_struct *frag; + int bdnum_for_frag; + int frag_num; + int buf_num; + int size; + int i; + + size = skb_headlen(skb); + buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE; + + frag_num = skb_shinfo(skb)->nr_frags; + for (i = 0; i < frag_num; i++) { + frag = &skb_shinfo(skb)->frags[i]; + size = skb_frag_size(frag); + bdnum_for_frag = + (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE; + if (bdnum_for_frag > HNS3_MAX_BD_PER_FRAG) + return -ENOMEM; + + buf_num += bdnum_for_frag; + } + + if (buf_num > ring_space(ring)) + return -EBUSY; + + *bnum = buf_num; + return 0; +} + +static int hns3_nic_maybe_stop_tx(struct sk_buff **out_skb, int *bnum, + struct hns3_enet_ring *ring) +{ + struct sk_buff *skb = *out_skb; + int buf_num; + + /* No. of segments (plus a header) */ + buf_num = skb_shinfo(skb)->nr_frags + 1; + + if (buf_num > ring_space(ring)) + return -EBUSY; + + *bnum = buf_num; + + return 0; +} + +static void hns_nic_dma_unmap(struct hns3_enet_ring *ring, int next_to_use_orig) +{ + struct device *dev = ring_to_dev(ring); + unsigned int i; + + for (i = 0; i < ring->desc_num; i++) { + /* check if this is where we started */ + if (ring->next_to_use == next_to_use_orig) + break; + + /* unmap the descriptor dma address */ + if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB) + dma_unmap_single(dev, + ring->desc_cb[ring->next_to_use].dma, + ring->desc_cb[ring->next_to_use].length, + DMA_TO_DEVICE); + else + dma_unmap_page(dev, + ring->desc_cb[ring->next_to_use].dma, + ring->desc_cb[ring->next_to_use].length, + DMA_TO_DEVICE); + + /* rollback one */ + ring_ptr_move_bw(ring, next_to_use); + } +} + +static netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_nic_ring_data *ring_data = + &tx_ring_data(priv, skb->queue_mapping); + struct hns3_enet_ring *ring = ring_data->ring; + struct device *dev = priv->dev; + struct netdev_queue *dev_queue; + struct skb_frag_struct *frag; + int next_to_use_head; + int next_to_use_frag; + dma_addr_t dma; + int buf_num; + int seg_num; + int size; + int ret; + int i; + + /* Prefetch the data used later */ + prefetch(skb->data); + + switch (priv->ops.maybe_stop_tx(&skb, &buf_num, ring)) { + case -EBUSY: + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_busy++; + u64_stats_update_end(&ring->syncp); + + goto out_net_tx_busy; + case -ENOMEM: + u64_stats_update_begin(&ring->syncp); + ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); + netdev_err(netdev, "no memory to xmit!\n"); + + goto out_err_tx_ok; + default: + break; + } + + /* No. of segments (plus a header) */ + seg_num = skb_shinfo(skb)->nr_frags + 1; + /* Fill the first part */ + size = skb_headlen(skb); + + next_to_use_head = ring->next_to_use; + + dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) { + netdev_err(netdev, "TX head DMA map failed\n"); + ring->stats.sw_err_cnt++; + goto out_err_tx_ok; + } + + ret = priv->ops.fill_desc(ring, skb, size, dma, seg_num == 1 ? 1 : 0, + DESC_TYPE_SKB); + if (ret) + goto head_dma_map_err; + + next_to_use_frag = ring->next_to_use; + /* Fill the fragments */ + for (i = 1; i < seg_num; i++) { + frag = &skb_shinfo(skb)->frags[i - 1]; + size = skb_frag_size(frag); + dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) { + netdev_err(netdev, "TX frag(%d) DMA map failed\n", i); + ring->stats.sw_err_cnt++; + goto frag_dma_map_err; + } + ret = priv->ops.fill_desc(ring, skb_frag_page(frag), size, dma, + seg_num - 1 == i ? 1 : 0, + DESC_TYPE_PAGE); + + if (ret) + goto frag_dma_map_err; + } + + /* Complete translate all packets */ + dev_queue = netdev_get_tx_queue(netdev, ring_data->queue_index); + netdev_tx_sent_queue(dev_queue, skb->len); + + wmb(); /* Commit all data before submit */ + + hnae_queue_xmit(ring->tqp, buf_num); + + return NETDEV_TX_OK; + +frag_dma_map_err: + hns_nic_dma_unmap(ring, next_to_use_frag); + +head_dma_map_err: + hns_nic_dma_unmap(ring, next_to_use_head); + +out_err_tx_ok: + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + +out_net_tx_busy: + netif_stop_subqueue(netdev, ring_data->queue_index); + smp_mb(); /* Commit all data before submit */ + + return NETDEV_TX_BUSY; +} + +static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + struct sockaddr *mac_addr = p; + int ret; + + if (!mac_addr || !is_valid_ether_addr((const u8 *)mac_addr->sa_data)) + return -EADDRNOTAVAIL; + + ret = h->ae_algo->ops->set_mac_addr(h, mac_addr->sa_data); + if (ret) { + netdev_err(netdev, "set_mac_address fail, ret=%d!\n", ret); + return ret; + } + + ether_addr_copy(netdev->dev_addr, mac_addr->sa_data); + + return 0; +} + +static int hns3_nic_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + + if (features & (NETIF_F_TSO | NETIF_F_TSO6)) { + priv->ops.fill_desc = hns3_fill_desc_tso; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tso; + } else { + priv->ops.fill_desc = hns3_fill_desc; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx; + } + + netdev->features = features; + return 0; +} + +static void +hns3_nic_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + int queue_num = priv->ae_handle->kinfo.num_tqps; + struct hns3_enet_ring *ring; + unsigned int start; + unsigned int idx; + u64 tx_bytes = 0; + u64 rx_bytes = 0; + u64 tx_pkts = 0; + u64 rx_pkts = 0; + + for (idx = 0; idx < queue_num; idx++) { + /* fetch the tx stats */ + ring = priv->ring_data[idx].ring; + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + tx_bytes += ring->stats.tx_bytes; + tx_pkts += ring->stats.tx_pkts; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + + /* fetch the rx stats */ + ring = priv->ring_data[idx + queue_num].ring; + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + rx_bytes += ring->stats.rx_bytes; + rx_pkts += ring->stats.rx_pkts; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + } + + stats->tx_bytes = tx_bytes; + stats->tx_packets = tx_pkts; + stats->rx_bytes = rx_bytes; + stats->rx_packets = rx_pkts; + + stats->rx_errors = netdev->stats.rx_errors; + stats->multicast = netdev->stats.multicast; + stats->rx_length_errors = netdev->stats.rx_length_errors; + stats->rx_crc_errors = netdev->stats.rx_crc_errors; + stats->rx_missed_errors = netdev->stats.rx_missed_errors; + + stats->tx_errors = netdev->stats.tx_errors; + stats->rx_dropped = netdev->stats.rx_dropped; + stats->tx_dropped = netdev->stats.tx_dropped; + stats->collisions = netdev->stats.collisions; + stats->rx_over_errors = netdev->stats.rx_over_errors; + stats->rx_frame_errors = netdev->stats.rx_frame_errors; + stats->rx_fifo_errors = netdev->stats.rx_fifo_errors; + stats->tx_aborted_errors = netdev->stats.tx_aborted_errors; + stats->tx_carrier_errors = netdev->stats.tx_carrier_errors; + stats->tx_fifo_errors = netdev->stats.tx_fifo_errors; + stats->tx_heartbeat_errors = netdev->stats.tx_heartbeat_errors; + stats->tx_window_errors = netdev->stats.tx_window_errors; + stats->rx_compressed = netdev->stats.rx_compressed; + stats->tx_compressed = netdev->stats.tx_compressed; +} + +static void hns3_add_tunnel_port(struct net_device *netdev, u16 port, + enum hns3_udp_tnl_type type) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type]; + struct hnae3_handle *h = priv->ae_handle; + + if (udp_tnl->used && udp_tnl->dst_port == port) { + udp_tnl->used++; + return; + } + + if (udp_tnl->used) { + netdev_warn(netdev, + "UDP tunnel [%d], port [%d] offload\n", type, port); + return; + } + + udp_tnl->dst_port = port; + udp_tnl->used = 1; + /* TBD send command to hardware to add port */ + if (h->ae_algo->ops->add_tunnel_udp) + h->ae_algo->ops->add_tunnel_udp(h, port); +} + +static void hns3_del_tunnel_port(struct net_device *netdev, u16 port, + enum hns3_udp_tnl_type type) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type]; + struct hnae3_handle *h = priv->ae_handle; + + if (!udp_tnl->used || udp_tnl->dst_port != port) { + netdev_warn(netdev, + "Invalid UDP tunnel port %d\n", port); + return; + } + + udp_tnl->used--; + if (udp_tnl->used) + return; + + udp_tnl->dst_port = 0; + /* TBD send command to hardware to del port */ + if (h->ae_algo->ops->del_tunnel_udp) + h->ae_algo->ops->del_tunnel_udp(h, port); +} + +/* hns3_nic_udp_tunnel_add - Get notifiacetion about UDP tunnel ports + * @netdev: This physical ports's netdev + * @ti: Tunnel information + */ +static void hns3_nic_udp_tunnel_add(struct net_device *netdev, + struct udp_tunnel_info *ti) +{ + u16 port_n = ntohs(ti->port); + + switch (ti->type) { + case UDP_TUNNEL_TYPE_VXLAN: + hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN); + break; + case UDP_TUNNEL_TYPE_GENEVE: + hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE); + break; + default: + netdev_err(netdev, "unsupported tunnel type %d\n", ti->type); + break; + } +} + +static void hns3_nic_udp_tunnel_del(struct net_device *netdev, + struct udp_tunnel_info *ti) +{ + u16 port_n = ntohs(ti->port); + + switch (ti->type) { + case UDP_TUNNEL_TYPE_VXLAN: + hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN); + break; + case UDP_TUNNEL_TYPE_GENEVE: + hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE); + break; + default: + break; + } +} + +static int hns3_setup_tc(struct net_device *netdev, u8 tc) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + struct hnae3_knic_private_info *kinfo = &h->kinfo; + unsigned int i; + int ret; + + if (tc > HNAE3_MAX_TC) + return -EINVAL; + + if (kinfo->num_tc == tc) + return 0; + + if (!netdev) + return -EINVAL; + + if (!tc) { + netdev_reset_tc(netdev); + return 0; + } + + /* Set num_tc for netdev */ + ret = netdev_set_num_tc(netdev, tc); + if (ret) + return ret; + + /* Set per TC queues for the VSI */ + for (i = 0; i < HNAE3_MAX_TC; i++) { + if (kinfo->tc_info[i].enable) + netdev_set_tc_queue(netdev, + kinfo->tc_info[i].tc, + kinfo->tc_info[i].tqp_count, + kinfo->tc_info[i].tqp_offset); + } + + return 0; +} + +static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct tc_mqprio_qopt *mqprio = type_data; + + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; + + return hns3_setup_tc(dev, mqprio->num_tc); +} + +static int hns3_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret = -EIO; + + if (h->ae_algo->ops->set_vlan_filter) + ret = h->ae_algo->ops->set_vlan_filter(h, proto, vid, false); + + return ret; +} + +static int hns3_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret = -EIO; + + if (h->ae_algo->ops->set_vlan_filter) + ret = h->ae_algo->ops->set_vlan_filter(h, proto, vid, true); + + return ret; +} + +static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, + u8 qos, __be16 vlan_proto) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int ret = -EIO; + + if (h->ae_algo->ops->set_vf_vlan_filter) + ret = h->ae_algo->ops->set_vf_vlan_filter(h, vf, vlan, + qos, vlan_proto); + + return ret; +} + +static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + bool if_running = netif_running(netdev); + int ret; + + if (!h->ae_algo->ops->set_mtu) + return -EOPNOTSUPP; + + /* if this was called with netdev up then bring netdevice down */ + if (if_running) { + (void)hns3_nic_net_stop(netdev); + msleep(100); + } + + ret = h->ae_algo->ops->set_mtu(h, new_mtu); + if (ret) { + netdev_err(netdev, "failed to change MTU in hardware %d\n", + ret); + return ret; + } + + /* if the netdev was running earlier, bring it up again */ + if (if_running && hns3_nic_net_open(netdev)) + ret = -EINVAL; + + return ret; +} + +static const struct net_device_ops hns3_nic_netdev_ops = { + .ndo_open = hns3_nic_net_open, + .ndo_stop = hns3_nic_net_stop, + .ndo_start_xmit = hns3_nic_net_xmit, + .ndo_set_mac_address = hns3_nic_net_set_mac_address, + .ndo_change_mtu = hns3_nic_change_mtu, + .ndo_set_features = hns3_nic_set_features, + .ndo_get_stats64 = hns3_nic_get_stats64, + .ndo_setup_tc = hns3_nic_setup_tc, + .ndo_set_rx_mode = hns3_nic_set_rx_mode, + .ndo_udp_tunnel_add = hns3_nic_udp_tunnel_add, + .ndo_udp_tunnel_del = hns3_nic_udp_tunnel_del, + .ndo_vlan_rx_add_vid = hns3_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = hns3_vlan_rx_kill_vid, + .ndo_set_vf_vlan = hns3_ndo_set_vf_vlan, +}; + +/* hns3_probe - Device initialization routine + * @pdev: PCI device information struct + * @ent: entry in hns3_pci_tbl + * + * hns3_probe initializes a PF identified by a pci_dev structure. + * The OS initialization, configuring of the PF private structure, + * and a hardware reset occur. + * + * Returns 0 on success, negative on failure + */ +static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct hnae3_ae_dev *ae_dev; + int ret; + + ae_dev = devm_kzalloc(&pdev->dev, sizeof(*ae_dev), + GFP_KERNEL); + if (!ae_dev) { + ret = -ENOMEM; + return ret; + } + + ae_dev->pdev = pdev; + ae_dev->dev_type = HNAE3_DEV_KNIC; + pci_set_drvdata(pdev, ae_dev); + + return hnae3_register_ae_dev(ae_dev); +} + +/* hns3_remove - Device removal routine + * @pdev: PCI device information struct + */ +static void hns3_remove(struct pci_dev *pdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); + + hnae3_unregister_ae_dev(ae_dev); + + devm_kfree(&pdev->dev, ae_dev); + + pci_set_drvdata(pdev, NULL); +} + +static struct pci_driver hns3_driver = { + .name = hns3_driver_name, + .id_table = hns3_pci_tbl, + .probe = hns3_probe, + .remove = hns3_remove, +}; + +/* set default feature to hns3 */ +static void hns3_set_default_feature(struct net_device *netdev) +{ + netdev->priv_flags |= IFF_UNICAST_FLT; + + netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; + + netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; + + netdev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->vlan_features |= + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | + NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | + NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; +} + +static int hns3_alloc_buffer(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + unsigned int order = hnae_page_order(ring); + struct page *p; + + p = dev_alloc_pages(order); + if (!p) + return -ENOMEM; + + cb->priv = p; + cb->page_offset = 0; + cb->reuse_flag = 0; + cb->buf = page_address(p); + cb->length = hnae_page_size(ring); + cb->type = DESC_TYPE_PAGE; + + memset(cb->buf, 0, cb->length); + + return 0; +} + +static void hns3_free_buffer(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + if (cb->type == DESC_TYPE_SKB) + dev_kfree_skb_any((struct sk_buff *)cb->priv); + else if (!HNAE3_IS_TX_RING(ring)) + put_page((struct page *)cb->priv); + memset(cb, 0, sizeof(*cb)); +} + +static int hns3_map_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) +{ + cb->dma = dma_map_page(ring_to_dev(ring), cb->priv, 0, + cb->length, ring_to_dma_dir(ring)); + + if (dma_mapping_error(ring_to_dev(ring), cb->dma)) + return -EIO; + + return 0; +} + +static void hns3_unmap_buffer(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + if (cb->type == DESC_TYPE_SKB) + dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length, + ring_to_dma_dir(ring)); + else + dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length, + ring_to_dma_dir(ring)); +} + +static void hns3_buffer_detach(struct hns3_enet_ring *ring, int i) +{ + hns3_unmap_buffer(ring, &ring->desc_cb[i]); + ring->desc[i].addr = 0; +} + +static void hns3_free_buffer_detach(struct hns3_enet_ring *ring, int i) +{ + struct hns3_desc_cb *cb = &ring->desc_cb[i]; + + if (!ring->desc_cb[i].dma) + return; + + hns3_buffer_detach(ring, i); + hns3_free_buffer(ring, cb); +} + +static void hns3_free_buffers(struct hns3_enet_ring *ring) +{ + int i; + + for (i = 0; i < ring->desc_num; i++) + hns3_free_buffer_detach(ring, i); +} + +/* free desc along with its attached buffer */ +static void hns3_free_desc(struct hns3_enet_ring *ring) +{ + hns3_free_buffers(ring); + + dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr, + ring->desc_num * sizeof(ring->desc[0]), + DMA_BIDIRECTIONAL); + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; +} + +static int hns3_alloc_desc(struct hns3_enet_ring *ring) +{ + int size = ring->desc_num * sizeof(ring->desc[0]); + + ring->desc = kzalloc(size, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_dma_addr = dma_map_single(ring_to_dev(ring), ring->desc, + size, DMA_BIDIRECTIONAL); + if (dma_mapping_error(ring_to_dev(ring), ring->desc_dma_addr)) { + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; + return -ENOMEM; + } + + return 0; +} + +static int hns3_reserve_buffer_map(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + int ret; + + ret = hns3_alloc_buffer(ring, cb); + if (ret) + goto out; + + ret = hns3_map_buffer(ring, cb); + if (ret) + goto out_with_buf; + + return 0; + +out_with_buf: + hns3_free_buffers(ring); +out: + return ret; +} + +static int hns3_alloc_buffer_attach(struct hns3_enet_ring *ring, int i) +{ + int ret = hns3_reserve_buffer_map(ring, &ring->desc_cb[i]); + + if (ret) + return ret; + + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma); + + return 0; +} + +/* Allocate memory for raw pkg, and map with dma */ +static int hns3_alloc_ring_buffers(struct hns3_enet_ring *ring) +{ + int i, j, ret; + + for (i = 0; i < ring->desc_num; i++) { + ret = hns3_alloc_buffer_attach(ring, i); + if (ret) + goto out_buffer_fail; + } + + return 0; + +out_buffer_fail: + for (j = i - 1; j >= 0; j--) + hns3_free_buffer_detach(ring, j); + return ret; +} + +/* detach a in-used buffer and replace with a reserved one */ +static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i, + struct hns3_desc_cb *res_cb) +{ + hns3_map_buffer(ring, &ring->desc_cb[i]); + ring->desc_cb[i] = *res_cb; + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma); +} + +static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i) +{ + ring->desc_cb[i].reuse_flag = 0; + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma + + ring->desc_cb[i].page_offset); +} + +static void hns3_nic_reclaim_one_desc(struct hns3_enet_ring *ring, int *bytes, + int *pkts) +{ + struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean]; + + (*pkts) += (desc_cb->type == DESC_TYPE_SKB); + (*bytes) += desc_cb->length; + /* desc_cb will be cleaned, after hnae_free_buffer_detach*/ + hns3_free_buffer_detach(ring, ring->next_to_clean); + + ring_ptr_move_fw(ring, next_to_clean); +} + +static int is_valid_clean_head(struct hns3_enet_ring *ring, int h) +{ + int u = ring->next_to_use; + int c = ring->next_to_clean; + + if (unlikely(h > ring->desc_num)) + return 0; + + return u > c ? (h > c && h <= u) : (h > c || h <= u); +} + +int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget) +{ + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + struct netdev_queue *dev_queue; + int bytes, pkts; + int head; + + head = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_HEAD_REG); + rmb(); /* Make sure head is ready before touch any data */ + + if (is_ring_empty(ring) || head == ring->next_to_clean) + return 0; /* no data to poll */ + + if (!is_valid_clean_head(ring, head)) { + netdev_err(netdev, "wrong head (%d, %d-%d)\n", head, + ring->next_to_use, ring->next_to_clean); + + u64_stats_update_begin(&ring->syncp); + ring->stats.io_err_cnt++; + u64_stats_update_end(&ring->syncp); + return -EIO; + } + + bytes = 0; + pkts = 0; + while (head != ring->next_to_clean && budget) { + hns3_nic_reclaim_one_desc(ring, &bytes, &pkts); + /* Issue prefetch for next Tx descriptor */ + prefetch(&ring->desc_cb[ring->next_to_clean]); + budget--; + } + + ring->tqp_vector->tx_group.total_bytes += bytes; + ring->tqp_vector->tx_group.total_packets += pkts; + + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_bytes += bytes; + ring->stats.tx_pkts += pkts; + u64_stats_update_end(&ring->syncp); + + dev_queue = netdev_get_tx_queue(netdev, ring->tqp->tqp_index); + netdev_tx_completed_queue(dev_queue, pkts, bytes); + + if (unlikely(pkts && netif_carrier_ok(netdev) && + (ring_space(ring) > HNS3_MAX_BD_PER_PKT))) { + /* Make sure that anybody stopping the queue after this + * sees the new next_to_clean. + */ + smp_mb(); + if (netif_tx_queue_stopped(dev_queue)) { + netif_tx_wake_queue(dev_queue); + ring->stats.restart_queue++; + } + } + + return !!budget; +} + +static int hns3_desc_unused(struct hns3_enet_ring *ring) +{ + int ntc = ring->next_to_clean; + int ntu = ring->next_to_use; + + return ((ntc >= ntu) ? 0 : ring->desc_num) + ntc - ntu; +} + +static void +hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, int cleand_count) +{ + struct hns3_desc_cb *desc_cb; + struct hns3_desc_cb res_cbs; + int i, ret; + + for (i = 0; i < cleand_count; i++) { + desc_cb = &ring->desc_cb[ring->next_to_use]; + if (desc_cb->reuse_flag) { + u64_stats_update_begin(&ring->syncp); + ring->stats.reuse_pg_cnt++; + u64_stats_update_end(&ring->syncp); + + hns3_reuse_buffer(ring, ring->next_to_use); + } else { + ret = hns3_reserve_buffer_map(ring, &res_cbs); + if (ret) { + u64_stats_update_begin(&ring->syncp); + ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); + + netdev_err(ring->tqp->handle->kinfo.netdev, + "hnae reserve buffer map failed.\n"); + break; + } + hns3_replace_buffer(ring, ring->next_to_use, &res_cbs); + } + + ring_ptr_move_fw(ring, next_to_use); + } + + wmb(); /* Make all data has been write before submit */ + writel_relaxed(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG); +} + +/* hns3_nic_get_headlen - determine size of header for LRO/GRO + * @data: pointer to the start of the headers + * @max: total length of section to find headers in + * + * This function is meant to determine the length of headers that will + * be recognized by hardware for LRO, GRO, and RSC offloads. The main + * motivation of doing this is to only perform one pull for IPv4 TCP + * packets so that we can do basic things like calculating the gso_size + * based on the average data per packet. + */ +static unsigned int hns3_nic_get_headlen(unsigned char *data, u32 flag, + unsigned int max_size) +{ + unsigned char *network; + u8 hlen; + + /* This should never happen, but better safe than sorry */ + if (max_size < ETH_HLEN) + return max_size; + + /* Initialize network frame pointer */ + network = data; + + /* Set first protocol and move network header forward */ + network += ETH_HLEN; + + /* Handle any vlan tag if present */ + if (hnae_get_field(flag, HNS3_RXD_VLAN_M, HNS3_RXD_VLAN_S) + == HNS3_RX_FLAG_VLAN_PRESENT) { + if ((typeof(max_size))(network - data) > (max_size - VLAN_HLEN)) + return max_size; + + network += VLAN_HLEN; + } + + /* Handle L3 protocols */ + if (hnae_get_field(flag, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S) + == HNS3_RX_FLAG_L3ID_IPV4) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct iphdr))) + return max_size; + + /* Access ihl as a u8 to avoid unaligned access on ia64 */ + hlen = (network[0] & 0x0F) << 2; + + /* Verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct iphdr)) + return network - data; + + /* Record next protocol if header is present */ + } else if (hnae_get_field(flag, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S) + == HNS3_RX_FLAG_L3ID_IPV6) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct ipv6hdr))) + return max_size; + + /* Record next protocol */ + hlen = sizeof(struct ipv6hdr); + } else { + return network - data; + } + + /* Relocate pointer to start of L4 header */ + network += hlen; + + /* Finally sort out TCP/UDP */ + if (hnae_get_field(flag, HNS3_RXD_L4ID_M, HNS3_RXD_L4ID_S) + == HNS3_RX_FLAG_L4ID_TCP) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct tcphdr))) + return max_size; + + /* Access doff as a u8 to avoid unaligned access on ia64 */ + hlen = (network[12] & 0xF0) >> 2; + + /* Verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct tcphdr)) + return network - data; + + network += hlen; + } else if (hnae_get_field(flag, HNS3_RXD_L4ID_M, HNS3_RXD_L4ID_S) + == HNS3_RX_FLAG_L4ID_UDP) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct udphdr))) + return max_size; + + network += sizeof(struct udphdr); + } + + /* If everything has gone correctly network should be the + * data section of the packet and will be the end of the header. + * If not then it probably represents the end of the last recognized + * header. + */ + if ((typeof(max_size))(network - data) < max_size) + return network - data; + else + return max_size; +} + +static void hns3_nic_reuse_page(struct sk_buff *skb, int i, + struct hns3_enet_ring *ring, int pull_len, + struct hns3_desc_cb *desc_cb) +{ + struct hns3_desc *desc; + int truesize, size; + int last_offset; + bool twobufs; + + twobufs = ((PAGE_SIZE < 8192) && + hnae_buf_size(ring) == HNS3_BUFFER_SIZE_2048); + + desc = &ring->desc[ring->next_to_clean]; + size = le16_to_cpu(desc->rx.size); + + if (twobufs) { + truesize = hnae_buf_size(ring); + } else { + truesize = ALIGN(size, L1_CACHE_BYTES); + last_offset = hnae_page_size(ring) - hnae_buf_size(ring); + } + + skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, + size - pull_len, truesize - pull_len); + + /* Avoid re-using remote pages,flag default unreuse */ + if (unlikely(page_to_nid(desc_cb->priv) != numa_node_id())) + return; + + if (twobufs) { + /* If we are only owner of page we can reuse it */ + if (likely(page_count(desc_cb->priv) == 1)) { + /* Flip page offset to other buffer */ + desc_cb->page_offset ^= truesize; + + desc_cb->reuse_flag = 1; + /* bump ref count on page before it is given*/ + get_page(desc_cb->priv); + } + return; + } + + /* Move offset up to the next cache line */ + desc_cb->page_offset += truesize; + + if (desc_cb->page_offset <= last_offset) { + desc_cb->reuse_flag = 1; + /* Bump ref count on page before it is given*/ + get_page(desc_cb->priv); + } +} + +static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, + struct hns3_desc *desc) +{ + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + int l3_type, l4_type; + u32 bd_base_info; + int ol4_type; + u32 l234info; + + bd_base_info = le32_to_cpu(desc->rx.bd_base_info); + l234info = le32_to_cpu(desc->rx.l234_info); + + skb->ip_summed = CHECKSUM_NONE; + + skb_checksum_none_assert(skb); + + if (!(netdev->features & NETIF_F_RXCSUM)) + return; + + /* check if hardware has done checksum */ + if (!hnae_get_bit(bd_base_info, HNS3_RXD_L3L4P_B)) + return; + + if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L3E_B) || + hnae_get_bit(l234info, HNS3_RXD_L4E_B) || + hnae_get_bit(l234info, HNS3_RXD_OL3E_B) || + hnae_get_bit(l234info, HNS3_RXD_OL4E_B))) { + netdev_err(netdev, "L3/L4 error pkt\n"); + u64_stats_update_begin(&ring->syncp); + ring->stats.l3l4_csum_err++; + u64_stats_update_end(&ring->syncp); + + return; + } + + l3_type = hnae_get_field(l234info, HNS3_RXD_L3ID_M, + HNS3_RXD_L3ID_S); + l4_type = hnae_get_field(l234info, HNS3_RXD_L4ID_M, + HNS3_RXD_L4ID_S); + + ol4_type = hnae_get_field(l234info, HNS3_RXD_OL4ID_M, HNS3_RXD_OL4ID_S); + switch (ol4_type) { + case HNS3_OL4_TYPE_MAC_IN_UDP: + case HNS3_OL4_TYPE_NVGRE: + skb->csum_level = 1; + case HNS3_OL4_TYPE_NO_TUN: + /* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */ + if (l3_type == HNS3_L3_TYPE_IPV4 || + (l3_type == HNS3_L3_TYPE_IPV6 && + (l4_type == HNS3_L4_TYPE_UDP || + l4_type == HNS3_L4_TYPE_TCP || + l4_type == HNS3_L4_TYPE_SCTP))) + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } +} + +static int hns3_handle_rx_bd(struct hns3_enet_ring *ring, + struct sk_buff **out_skb, int *out_bnum) +{ + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + struct hns3_desc_cb *desc_cb; + struct hns3_desc *desc; + struct sk_buff *skb; + unsigned char *va; + u32 bd_base_info; + int pull_len; + u32 l234info; + int length; + int bnum; + + desc = &ring->desc[ring->next_to_clean]; + desc_cb = &ring->desc_cb[ring->next_to_clean]; + + prefetch(desc); + + length = le16_to_cpu(desc->rx.pkt_len); + bd_base_info = le32_to_cpu(desc->rx.bd_base_info); + l234info = le32_to_cpu(desc->rx.l234_info); + + /* Check valid BD */ + if (!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B)) + return -EFAULT; + + va = (unsigned char *)desc_cb->buf + desc_cb->page_offset; + + /* Prefetch first cache line of first page + * Idea is to cache few bytes of the header of the packet. Our L1 Cache + * line size is 64B so need to prefetch twice to make it 128B. But in + * actual we can have greater size of caches with 128B Level 1 cache + * lines. In such a case, single fetch would suffice to cache in the + * relevant part of the header. + */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + skb = *out_skb = napi_alloc_skb(&ring->tqp_vector->napi, + HNS3_RX_HEAD_SIZE); + if (unlikely(!skb)) { + netdev_err(netdev, "alloc rx skb fail\n"); + + u64_stats_update_begin(&ring->syncp); + ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); + + return -ENOMEM; + } + + prefetchw(skb->data); + + bnum = 1; + if (length <= HNS3_RX_HEAD_SIZE) { + memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long))); + + /* We can reuse buffer as-is, just make sure it is local */ + if (likely(page_to_nid(desc_cb->priv) == numa_node_id())) + desc_cb->reuse_flag = 1; + else /* This page cannot be reused so discard it */ + put_page(desc_cb->priv); + + ring_ptr_move_fw(ring, next_to_clean); + } else { + u64_stats_update_begin(&ring->syncp); + ring->stats.seg_pkt_cnt++; + u64_stats_update_end(&ring->syncp); + + pull_len = hns3_nic_get_headlen(va, l234info, + HNS3_RX_HEAD_SIZE); + memcpy(__skb_put(skb, pull_len), va, + ALIGN(pull_len, sizeof(long))); + + hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb); + ring_ptr_move_fw(ring, next_to_clean); + + while (!hnae_get_bit(bd_base_info, HNS3_RXD_FE_B)) { + desc = &ring->desc[ring->next_to_clean]; + desc_cb = &ring->desc_cb[ring->next_to_clean]; + bd_base_info = le32_to_cpu(desc->rx.bd_base_info); + hns3_nic_reuse_page(skb, bnum, ring, 0, desc_cb); + ring_ptr_move_fw(ring, next_to_clean); + bnum++; + } + } + + *out_bnum = bnum; + + if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))) { + netdev_err(netdev, "no valid bd,%016llx,%016llx\n", + ((u64 *)desc)[0], ((u64 *)desc)[1]); + u64_stats_update_begin(&ring->syncp); + ring->stats.non_vld_descs++; + u64_stats_update_end(&ring->syncp); + + dev_kfree_skb_any(skb); + return -EINVAL; + } + + if (unlikely((!desc->rx.pkt_len) || + hnae_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) { + netdev_err(netdev, "truncated pkt\n"); + u64_stats_update_begin(&ring->syncp); + ring->stats.err_pkt_len++; + u64_stats_update_end(&ring->syncp); + + dev_kfree_skb_any(skb); + return -EFAULT; + } + + if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L2E_B))) { + netdev_err(netdev, "L2 error pkt\n"); + u64_stats_update_begin(&ring->syncp); + ring->stats.l2_err++; + u64_stats_update_end(&ring->syncp); + + dev_kfree_skb_any(skb); + return -EFAULT; + } + + u64_stats_update_begin(&ring->syncp); + ring->stats.rx_pkts++; + ring->stats.rx_bytes += skb->len; + u64_stats_update_end(&ring->syncp); + + ring->tqp_vector->rx_group.total_bytes += skb->len; + + hns3_rx_checksum(ring, skb, desc); + return 0; +} + +static int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget) +{ +#define RCB_NOF_ALLOC_RX_BUFF_ONCE 16 + struct net_device *netdev = ring->tqp->handle->kinfo.netdev; + int recv_pkts, recv_bds, clean_count, err; + int unused_count = hns3_desc_unused(ring); + struct sk_buff *skb = NULL; + int num, bnum = 0; + + num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG); + rmb(); /* Make sure num taken effect before the other data is touched */ + + recv_pkts = 0, recv_bds = 0, clean_count = 0; + num -= unused_count; + + while (recv_pkts < budget && recv_bds < num) { + /* Reuse or realloc buffers */ + if (clean_count + unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { + hns3_nic_alloc_rx_buffers(ring, + clean_count + unused_count); + clean_count = 0; + unused_count = hns3_desc_unused(ring); + } + + /* Poll one pkt */ + err = hns3_handle_rx_bd(ring, &skb, &bnum); + if (unlikely(!skb)) /* This fault cannot be repaired */ + goto out; + + recv_bds += bnum; + clean_count += bnum; + if (unlikely(err)) { /* Do jump the err */ + recv_pkts++; + continue; + } + + /* Do update ip stack process */ + skb->protocol = eth_type_trans(skb, netdev); + (void)napi_gro_receive(&ring->tqp_vector->napi, skb); + + recv_pkts++; + } + +out: + /* Make all data has been write before submit */ + if (clean_count + unused_count > 0) + hns3_nic_alloc_rx_buffers(ring, + clean_count + unused_count); + + return recv_pkts; +} + +static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group) +{ +#define HNS3_RX_ULTRA_PACKET_RATE 40000 + enum hns3_flow_level_range new_flow_level; + struct hns3_enet_tqp_vector *tqp_vector; + int packets_per_secs; + int bytes_per_usecs; + u16 new_int_gl; + int usecs; + + if (!ring_group->int_gl) + return false; + + if (ring_group->total_packets == 0) { + ring_group->int_gl = HNS3_INT_GL_50K; + ring_group->flow_level = HNS3_FLOW_LOW; + return true; + } + + /* Simple throttlerate management + * 0-10MB/s lower (50000 ints/s) + * 10-20MB/s middle (20000 ints/s) + * 20-1249MB/s high (18000 ints/s) + * > 40000pps ultra (8000 ints/s) + */ + new_flow_level = ring_group->flow_level; + new_int_gl = ring_group->int_gl; + tqp_vector = ring_group->ring->tqp_vector; + usecs = (ring_group->int_gl << 1); + bytes_per_usecs = ring_group->total_bytes / usecs; + /* 1000000 microseconds */ + packets_per_secs = ring_group->total_packets * 1000000 / usecs; + + switch (new_flow_level) { + case HNS3_FLOW_LOW: + if (bytes_per_usecs > 10) + new_flow_level = HNS3_FLOW_MID; + break; + case HNS3_FLOW_MID: + if (bytes_per_usecs > 20) + new_flow_level = HNS3_FLOW_HIGH; + else if (bytes_per_usecs <= 10) + new_flow_level = HNS3_FLOW_LOW; + break; + case HNS3_FLOW_HIGH: + case HNS3_FLOW_ULTRA: + default: + if (bytes_per_usecs <= 20) + new_flow_level = HNS3_FLOW_MID; + break; + } + + if ((packets_per_secs > HNS3_RX_ULTRA_PACKET_RATE) && + (&tqp_vector->rx_group == ring_group)) + new_flow_level = HNS3_FLOW_ULTRA; + + switch (new_flow_level) { + case HNS3_FLOW_LOW: + new_int_gl = HNS3_INT_GL_50K; + break; + case HNS3_FLOW_MID: + new_int_gl = HNS3_INT_GL_20K; + break; + case HNS3_FLOW_HIGH: + new_int_gl = HNS3_INT_GL_18K; + break; + case HNS3_FLOW_ULTRA: + new_int_gl = HNS3_INT_GL_8K; + break; + default: + break; + } + + ring_group->total_bytes = 0; + ring_group->total_packets = 0; + ring_group->flow_level = new_flow_level; + if (new_int_gl != ring_group->int_gl) { + ring_group->int_gl = new_int_gl; + return true; + } + return false; +} + +static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector) +{ + u16 rx_int_gl, tx_int_gl; + bool rx, tx; + + rx = hns3_get_new_int_gl(&tqp_vector->rx_group); + tx = hns3_get_new_int_gl(&tqp_vector->tx_group); + rx_int_gl = tqp_vector->rx_group.int_gl; + tx_int_gl = tqp_vector->tx_group.int_gl; + if (rx && tx) { + if (rx_int_gl > tx_int_gl) { + tqp_vector->tx_group.int_gl = rx_int_gl; + tqp_vector->tx_group.flow_level = + tqp_vector->rx_group.flow_level; + hns3_set_vector_coalesc_gl(tqp_vector, rx_int_gl); + } else { + tqp_vector->rx_group.int_gl = tx_int_gl; + tqp_vector->rx_group.flow_level = + tqp_vector->tx_group.flow_level; + hns3_set_vector_coalesc_gl(tqp_vector, tx_int_gl); + } + } +} + +static int hns3_nic_common_poll(struct napi_struct *napi, int budget) +{ + struct hns3_enet_ring *ring; + int rx_pkt_total = 0; + + struct hns3_enet_tqp_vector *tqp_vector = + container_of(napi, struct hns3_enet_tqp_vector, napi); + bool clean_complete = true; + int rx_budget; + + /* Since the actual Tx work is minimal, we can give the Tx a larger + * budget and be more aggressive about cleaning up the Tx descriptors. + */ + hns3_for_each_ring(ring, tqp_vector->tx_group) { + if (!hns3_clean_tx_ring(ring, budget)) + clean_complete = false; + } + + /* make sure rx ring budget not smaller than 1 */ + rx_budget = max(budget / tqp_vector->num_tqps, 1); + + hns3_for_each_ring(ring, tqp_vector->rx_group) { + int rx_cleaned = hns3_clean_rx_ring(ring, rx_budget); + + if (rx_cleaned >= rx_budget) + clean_complete = false; + + rx_pkt_total += rx_cleaned; + } + + tqp_vector->rx_group.total_packets += rx_pkt_total; + + if (!clean_complete) + return budget; + + napi_complete(napi); + hns3_update_new_int_gl(tqp_vector); + hns3_mask_vector_irq(tqp_vector, 1); + + return rx_pkt_total; +} + +static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, + struct hnae3_ring_chain_node *head) +{ + struct pci_dev *pdev = tqp_vector->handle->pdev; + struct hnae3_ring_chain_node *cur_chain = head; + struct hnae3_ring_chain_node *chain; + struct hns3_enet_ring *tx_ring; + struct hns3_enet_ring *rx_ring; + + tx_ring = tqp_vector->tx_group.ring; + if (tx_ring) { + cur_chain->tqp_index = tx_ring->tqp->tqp_index; + hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_TX); + + cur_chain->next = NULL; + + while (tx_ring->next) { + tx_ring = tx_ring->next; + + chain = devm_kzalloc(&pdev->dev, sizeof(*chain), + GFP_KERNEL); + if (!chain) + return -ENOMEM; + + cur_chain->next = chain; + chain->tqp_index = tx_ring->tqp->tqp_index; + hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_TX); + + cur_chain = chain; + } + } + + rx_ring = tqp_vector->rx_group.ring; + if (!tx_ring && rx_ring) { + cur_chain->next = NULL; + cur_chain->tqp_index = rx_ring->tqp->tqp_index; + hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_RX); + + rx_ring = rx_ring->next; + } + + while (rx_ring) { + chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL); + if (!chain) + return -ENOMEM; + + cur_chain->next = chain; + chain->tqp_index = rx_ring->tqp->tqp_index; + hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B, + HNAE3_RING_TYPE_RX); + cur_chain = chain; + + rx_ring = rx_ring->next; + } + + return 0; +} + +static void hns3_free_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, + struct hnae3_ring_chain_node *head) +{ + struct pci_dev *pdev = tqp_vector->handle->pdev; + struct hnae3_ring_chain_node *chain_tmp, *chain; + + chain = head->next; + + while (chain) { + chain_tmp = chain->next; + devm_kfree(&pdev->dev, chain); + chain = chain_tmp; + } +} + +static void hns3_add_ring_to_group(struct hns3_enet_ring_group *group, + struct hns3_enet_ring *ring) +{ + ring->next = group->ring; + group->ring = ring; + + group->count++; +} + +static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) +{ + struct hnae3_ring_chain_node vector_ring_chain; + struct hnae3_handle *h = priv->ae_handle; + struct hns3_enet_tqp_vector *tqp_vector; + struct hnae3_vector_info *vector; + struct pci_dev *pdev = h->pdev; + u16 tqp_num = h->kinfo.num_tqps; + u16 vector_num; + int ret = 0; + u16 i; + + /* RSS size, cpu online and vector_num should be the same */ + /* Should consider 2p/4p later */ + vector_num = min_t(u16, num_online_cpus(), tqp_num); + vector = devm_kcalloc(&pdev->dev, vector_num, sizeof(*vector), + GFP_KERNEL); + if (!vector) + return -ENOMEM; + + vector_num = h->ae_algo->ops->get_vector(h, vector_num, vector); + + priv->vector_num = vector_num; + priv->tqp_vector = (struct hns3_enet_tqp_vector *) + devm_kcalloc(&pdev->dev, vector_num, sizeof(*priv->tqp_vector), + GFP_KERNEL); + if (!priv->tqp_vector) + return -ENOMEM; + + for (i = 0; i < tqp_num; i++) { + u16 vector_i = i % vector_num; + + tqp_vector = &priv->tqp_vector[vector_i]; + + hns3_add_ring_to_group(&tqp_vector->tx_group, + priv->ring_data[i].ring); + + hns3_add_ring_to_group(&tqp_vector->rx_group, + priv->ring_data[i + tqp_num].ring); + + tqp_vector->idx = vector_i; + tqp_vector->mask_addr = vector[vector_i].io_addr; + tqp_vector->vector_irq = vector[vector_i].vector; + tqp_vector->num_tqps++; + + priv->ring_data[i].ring->tqp_vector = tqp_vector; + priv->ring_data[i + tqp_num].ring->tqp_vector = tqp_vector; + } + + for (i = 0; i < vector_num; i++) { + tqp_vector = &priv->tqp_vector[i]; + + tqp_vector->rx_group.total_bytes = 0; + tqp_vector->rx_group.total_packets = 0; + tqp_vector->tx_group.total_bytes = 0; + tqp_vector->tx_group.total_packets = 0; + hns3_vector_gl_rl_init(tqp_vector); + tqp_vector->handle = h; + + ret = hns3_get_vector_ring_chain(tqp_vector, + &vector_ring_chain); + if (ret) + goto out; + + ret = h->ae_algo->ops->map_ring_to_vector(h, + tqp_vector->vector_irq, &vector_ring_chain); + if (ret) + goto out; + + hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain); + + netif_napi_add(priv->netdev, &tqp_vector->napi, + hns3_nic_common_poll, NAPI_POLL_WEIGHT); + } + +out: + devm_kfree(&pdev->dev, vector); + return ret; +} + +static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv) +{ + struct hnae3_ring_chain_node vector_ring_chain; + struct hnae3_handle *h = priv->ae_handle; + struct hns3_enet_tqp_vector *tqp_vector; + struct pci_dev *pdev = h->pdev; + int i, ret; + + for (i = 0; i < priv->vector_num; i++) { + tqp_vector = &priv->tqp_vector[i]; + + ret = hns3_get_vector_ring_chain(tqp_vector, + &vector_ring_chain); + if (ret) + return ret; + + ret = h->ae_algo->ops->unmap_ring_from_vector(h, + tqp_vector->vector_irq, &vector_ring_chain); + if (ret) + return ret; + + hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain); + + if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) { + (void)irq_set_affinity_hint( + priv->tqp_vector[i].vector_irq, + NULL); + devm_free_irq(&pdev->dev, + priv->tqp_vector[i].vector_irq, + &priv->tqp_vector[i]); + } + + priv->ring_data[i].ring->irq_init_flag = HNS3_VECTOR_NOT_INITED; + + netif_napi_del(&priv->tqp_vector[i].napi); + } + + devm_kfree(&pdev->dev, priv->tqp_vector); + + return 0; +} + +static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, + int ring_type) +{ + struct hns3_nic_ring_data *ring_data = priv->ring_data; + int queue_num = priv->ae_handle->kinfo.num_tqps; + struct pci_dev *pdev = priv->ae_handle->pdev; + struct hns3_enet_ring *ring; + + ring = devm_kzalloc(&pdev->dev, sizeof(*ring), GFP_KERNEL); + if (!ring) + return -ENOMEM; + + if (ring_type == HNAE3_RING_TYPE_TX) { + ring_data[q->tqp_index].ring = ring; + ring->io_base = (u8 __iomem *)q->io_base + HNS3_TX_REG_OFFSET; + } else { + ring_data[q->tqp_index + queue_num].ring = ring; + ring->io_base = q->io_base; + } + + hnae_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type); + + ring_data[q->tqp_index].queue_index = q->tqp_index; + + ring->tqp = q; + ring->desc = NULL; + ring->desc_cb = NULL; + ring->dev = priv->dev; + ring->desc_dma_addr = 0; + ring->buf_size = q->buf_size; + ring->desc_num = q->desc_num; + ring->next_to_use = 0; + ring->next_to_clean = 0; + + return 0; +} + +static int hns3_queue_to_ring(struct hnae3_queue *tqp, + struct hns3_nic_priv *priv) +{ + int ret; + + ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_TX); + if (ret) + return ret; + + ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_RX); + if (ret) + return ret; + + return 0; +} + +static int hns3_get_ring_config(struct hns3_nic_priv *priv) +{ + struct hnae3_handle *h = priv->ae_handle; + struct pci_dev *pdev = h->pdev; + int i, ret; + + priv->ring_data = devm_kzalloc(&pdev->dev, h->kinfo.num_tqps * + sizeof(*priv->ring_data) * 2, + GFP_KERNEL); + if (!priv->ring_data) + return -ENOMEM; + + for (i = 0; i < h->kinfo.num_tqps; i++) { + ret = hns3_queue_to_ring(h->kinfo.tqp[i], priv); + if (ret) + goto err; + } + + return 0; +err: + devm_kfree(&pdev->dev, priv->ring_data); + return ret; +} + +static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring) +{ + int ret; + + if (ring->desc_num <= 0 || ring->buf_size <= 0) + return -EINVAL; + + ring->desc_cb = kcalloc(ring->desc_num, sizeof(ring->desc_cb[0]), + GFP_KERNEL); + if (!ring->desc_cb) { + ret = -ENOMEM; + goto out; + } + + ret = hns3_alloc_desc(ring); + if (ret) + goto out_with_desc_cb; + + if (!HNAE3_IS_TX_RING(ring)) { + ret = hns3_alloc_ring_buffers(ring); + if (ret) + goto out_with_desc; + } + + return 0; + +out_with_desc: + hns3_free_desc(ring); +out_with_desc_cb: + kfree(ring->desc_cb); + ring->desc_cb = NULL; +out: + return ret; +} + +static void hns3_fini_ring(struct hns3_enet_ring *ring) +{ + hns3_free_desc(ring); + kfree(ring->desc_cb); + ring->desc_cb = NULL; + ring->next_to_clean = 0; + ring->next_to_use = 0; +} + +int hns3_buf_size2type(u32 buf_size) +{ + int bd_size_type; + + switch (buf_size) { + case 512: + bd_size_type = HNS3_BD_SIZE_512_TYPE; + break; + case 1024: + bd_size_type = HNS3_BD_SIZE_1024_TYPE; + break; + case 2048: + bd_size_type = HNS3_BD_SIZE_2048_TYPE; + break; + case 4096: + bd_size_type = HNS3_BD_SIZE_4096_TYPE; + break; + default: + bd_size_type = HNS3_BD_SIZE_2048_TYPE; + } + + return bd_size_type; +} + +static void hns3_init_ring_hw(struct hns3_enet_ring *ring) +{ + dma_addr_t dma = ring->desc_dma_addr; + struct hnae3_queue *q = ring->tqp; + + if (!HNAE3_IS_TX_RING(ring)) { + hns3_write_dev(q, HNS3_RING_RX_RING_BASEADDR_L_REG, + (u32)dma); + hns3_write_dev(q, HNS3_RING_RX_RING_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + + hns3_write_dev(q, HNS3_RING_RX_RING_BD_LEN_REG, + hns3_buf_size2type(ring->buf_size)); + hns3_write_dev(q, HNS3_RING_RX_RING_BD_NUM_REG, + ring->desc_num / 8 - 1); + + } else { + hns3_write_dev(q, HNS3_RING_TX_RING_BASEADDR_L_REG, + (u32)dma); + hns3_write_dev(q, HNS3_RING_TX_RING_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + + hns3_write_dev(q, HNS3_RING_TX_RING_BD_LEN_REG, + hns3_buf_size2type(ring->buf_size)); + hns3_write_dev(q, HNS3_RING_TX_RING_BD_NUM_REG, + ring->desc_num / 8 - 1); + } +} + +static int hns3_init_all_ring(struct hns3_nic_priv *priv) +{ + struct hnae3_handle *h = priv->ae_handle; + int ring_num = h->kinfo.num_tqps * 2; + int i, j; + int ret; + + for (i = 0; i < ring_num; i++) { + ret = hns3_alloc_ring_memory(priv->ring_data[i].ring); + if (ret) { + dev_err(priv->dev, + "Alloc ring memory fail! ret=%d\n", ret); + goto out_when_alloc_ring_memory; + } + + hns3_init_ring_hw(priv->ring_data[i].ring); + + u64_stats_init(&priv->ring_data[i].ring->syncp); + } + + return 0; + +out_when_alloc_ring_memory: + for (j = i - 1; j >= 0; j--) + hns3_fini_ring(priv->ring_data[i].ring); + + return -ENOMEM; +} + +static int hns3_uninit_all_ring(struct hns3_nic_priv *priv) +{ + struct hnae3_handle *h = priv->ae_handle; + int i; + + for (i = 0; i < h->kinfo.num_tqps; i++) { + if (h->ae_algo->ops->reset_queue) + h->ae_algo->ops->reset_queue(h, i); + + hns3_fini_ring(priv->ring_data[i].ring); + hns3_fini_ring(priv->ring_data[i + h->kinfo.num_tqps].ring); + } + + return 0; +} + +/* Set mac addr if it is configured. or leave it to the AE driver */ +static void hns3_init_mac_addr(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + u8 mac_addr_temp[ETH_ALEN]; + + if (h->ae_algo->ops->get_mac_addr) { + h->ae_algo->ops->get_mac_addr(h, mac_addr_temp); + ether_addr_copy(netdev->dev_addr, mac_addr_temp); + } + + /* Check if the MAC address is valid, if not get a random one */ + if (!is_valid_ether_addr(netdev->dev_addr)) { + eth_hw_addr_random(netdev); + dev_warn(priv->dev, "using random MAC address %pM\n", + netdev->dev_addr); + /* Also copy this new MAC address into hdev */ + if (h->ae_algo->ops->set_mac_addr) + h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr); + } +} + +static void hns3_nic_set_priv_ops(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + + if ((netdev->features & NETIF_F_TSO) || + (netdev->features & NETIF_F_TSO6)) { + priv->ops.fill_desc = hns3_fill_desc_tso; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tso; + } else { + priv->ops.fill_desc = hns3_fill_desc; + priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx; + } +} + +static int hns3_client_init(struct hnae3_handle *handle) +{ + struct pci_dev *pdev = handle->pdev; + struct hns3_nic_priv *priv; + struct net_device *netdev; + int ret; + + netdev = alloc_etherdev_mq(sizeof(struct hns3_nic_priv), + handle->kinfo.num_tqps); + if (!netdev) + return -ENOMEM; + + priv = netdev_priv(netdev); + priv->dev = &pdev->dev; + priv->netdev = netdev; + priv->ae_handle = handle; + + handle->kinfo.netdev = netdev; + handle->priv = (void *)priv; + + hns3_init_mac_addr(netdev); + + hns3_set_default_feature(netdev); + + netdev->watchdog_timeo = HNS3_TX_TIMEOUT; + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->netdev_ops = &hns3_nic_netdev_ops; + SET_NETDEV_DEV(netdev, &pdev->dev); + hns3_ethtool_set_ops(netdev); + hns3_nic_set_priv_ops(netdev); + + /* Carrier off reporting is important to ethtool even BEFORE open */ + netif_carrier_off(netdev); + + ret = hns3_get_ring_config(priv); + if (ret) { + ret = -ENOMEM; + goto out_get_ring_cfg; + } + + ret = hns3_nic_init_vector_data(priv); + if (ret) { + ret = -ENOMEM; + goto out_init_vector_data; + } + + ret = hns3_init_all_ring(priv); + if (ret) { + ret = -ENOMEM; + goto out_init_ring_data; + } + + ret = register_netdev(netdev); + if (ret) { + dev_err(priv->dev, "probe register netdev fail!\n"); + goto out_reg_netdev_fail; + } + + /* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */ + netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); + + return ret; + +out_reg_netdev_fail: +out_init_ring_data: + (void)hns3_nic_uninit_vector_data(priv); + priv->ring_data = NULL; +out_init_vector_data: +out_get_ring_cfg: + priv->ae_handle = NULL; + free_netdev(netdev); + return ret; +} + +static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) +{ + struct net_device *netdev = handle->kinfo.netdev; + struct hns3_nic_priv *priv = netdev_priv(netdev); + int ret; + + if (netdev->reg_state != NETREG_UNINITIALIZED) + unregister_netdev(netdev); + + ret = hns3_nic_uninit_vector_data(priv); + if (ret) + netdev_err(netdev, "uninit vector error\n"); + + ret = hns3_uninit_all_ring(priv); + if (ret) + netdev_err(netdev, "uninit ring error\n"); + + priv->ring_data = NULL; + + free_netdev(netdev); +} + +static void hns3_link_status_change(struct hnae3_handle *handle, bool linkup) +{ + struct net_device *netdev = handle->kinfo.netdev; + + if (!netdev) + return; + + if (linkup) { + netif_carrier_on(netdev); + netif_tx_wake_all_queues(netdev); + netdev_info(netdev, "link up\n"); + } else { + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + netdev_info(netdev, "link down\n"); + } +} + +const struct hnae3_client_ops client_ops = { + .init_instance = hns3_client_init, + .uninit_instance = hns3_client_uninit, + .link_status_change = hns3_link_status_change, +}; + +/* hns3_init_module - Driver registration routine + * hns3_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + */ +static int __init hns3_init_module(void) +{ + int ret; + + pr_info("%s: %s - version\n", hns3_driver_name, hns3_driver_string); + pr_info("%s: %s\n", hns3_driver_name, hns3_copyright); + + client.type = HNAE3_CLIENT_KNIC; + snprintf(client.name, HNAE3_CLIENT_NAME_LENGTH - 1, "%s", + hns3_driver_name); + + client.ops = &client_ops; + + ret = hnae3_register_client(&client); + if (ret) + return ret; + + ret = pci_register_driver(&hns3_driver); + if (ret) + hnae3_unregister_client(&client); + + return ret; +} +module_init(hns3_init_module); + +/* hns3_exit_module - Driver exit cleanup routine + * hns3_exit_module is called just before the driver is removed + * from memory. + */ +static void __exit hns3_exit_module(void) +{ + pci_unregister_driver(&hns3_driver); + hnae3_unregister_client(&client); +} +module_exit(hns3_exit_module); + +MODULE_DESCRIPTION("HNS3: Hisilicon Ethernet Driver"); +MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("pci:hns-nic"); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h new file mode 100644 index 000000000000..7e8746189747 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.h @@ -0,0 +1,593 @@ +/* + * Copyright (c) 2016 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HNS3_ENET_H +#define __HNS3_ENET_H + +#include "hnae3.h" + +extern const char hns3_driver_version[]; + +enum hns3_nic_state { + HNS3_NIC_STATE_TESTING, + HNS3_NIC_STATE_RESETTING, + HNS3_NIC_STATE_REINITING, + HNS3_NIC_STATE_DOWN, + HNS3_NIC_STATE_DISABLED, + HNS3_NIC_STATE_REMOVING, + HNS3_NIC_STATE_SERVICE_INITED, + HNS3_NIC_STATE_SERVICE_SCHED, + HNS3_NIC_STATE2_RESET_REQUESTED, + HNS3_NIC_STATE_MAX +}; + +#define HNS3_RING_RX_RING_BASEADDR_L_REG 0x00000 +#define HNS3_RING_RX_RING_BASEADDR_H_REG 0x00004 +#define HNS3_RING_RX_RING_BD_NUM_REG 0x00008 +#define HNS3_RING_RX_RING_BD_LEN_REG 0x0000C +#define HNS3_RING_RX_RING_TAIL_REG 0x00018 +#define HNS3_RING_RX_RING_HEAD_REG 0x0001C +#define HNS3_RING_RX_RING_FBDNUM_REG 0x00020 +#define HNS3_RING_RX_RING_PKTNUM_RECORD_REG 0x0002C + +#define HNS3_RING_TX_RING_BASEADDR_L_REG 0x00040 +#define HNS3_RING_TX_RING_BASEADDR_H_REG 0x00044 +#define HNS3_RING_TX_RING_BD_NUM_REG 0x00048 +#define HNS3_RING_TX_RING_BD_LEN_REG 0x0004C +#define HNS3_RING_TX_RING_TAIL_REG 0x00058 +#define HNS3_RING_TX_RING_HEAD_REG 0x0005C +#define HNS3_RING_TX_RING_FBDNUM_REG 0x00060 +#define HNS3_RING_TX_RING_OFFSET_REG 0x00064 +#define HNS3_RING_TX_RING_PKTNUM_RECORD_REG 0x0006C + +#define HNS3_RING_PREFETCH_EN_REG 0x0007C +#define HNS3_RING_CFG_VF_NUM_REG 0x00080 +#define HNS3_RING_ASID_REG 0x0008C +#define HNS3_RING_RX_VM_REG 0x00090 +#define HNS3_RING_T0_BE_RST 0x00094 +#define HNS3_RING_COULD_BE_RST 0x00098 +#define HNS3_RING_WRR_WEIGHT_REG 0x0009c + +#define HNS3_RING_INTMSK_RXWL_REG 0x000A0 +#define HNS3_RING_INTSTS_RX_RING_REG 0x000A4 +#define HNS3_RX_RING_INT_STS_REG 0x000A8 +#define HNS3_RING_INTMSK_TXWL_REG 0x000AC +#define HNS3_RING_INTSTS_TX_RING_REG 0x000B0 +#define HNS3_TX_RING_INT_STS_REG 0x000B4 +#define HNS3_RING_INTMSK_RX_OVERTIME_REG 0x000B8 +#define HNS3_RING_INTSTS_RX_OVERTIME_REG 0x000BC +#define HNS3_RING_INTMSK_TX_OVERTIME_REG 0x000C4 +#define HNS3_RING_INTSTS_TX_OVERTIME_REG 0x000C8 + +#define HNS3_RING_MB_CTRL_REG 0x00100 +#define HNS3_RING_MB_DATA_BASE_REG 0x00200 + +#define HNS3_TX_REG_OFFSET 0x40 + +#define HNS3_RX_HEAD_SIZE 256 + +#define HNS3_TX_TIMEOUT (5 * HZ) +#define HNS3_RING_NAME_LEN 16 +#define HNS3_BUFFER_SIZE_2048 2048 +#define HNS3_RING_MAX_PENDING 32768 +#define HNS3_MAX_MTU 9728 + +#define HNS3_BD_SIZE_512_TYPE 0 +#define HNS3_BD_SIZE_1024_TYPE 1 +#define HNS3_BD_SIZE_2048_TYPE 2 +#define HNS3_BD_SIZE_4096_TYPE 3 + +#define HNS3_RX_FLAG_VLAN_PRESENT 0x1 +#define HNS3_RX_FLAG_L3ID_IPV4 0x0 +#define HNS3_RX_FLAG_L3ID_IPV6 0x1 +#define HNS3_RX_FLAG_L4ID_UDP 0x0 +#define HNS3_RX_FLAG_L4ID_TCP 0x1 + +#define HNS3_RXD_DMAC_S 0 +#define HNS3_RXD_DMAC_M (0x3 << HNS3_RXD_DMAC_S) +#define HNS3_RXD_VLAN_S 2 +#define HNS3_RXD_VLAN_M (0x3 << HNS3_RXD_VLAN_S) +#define HNS3_RXD_L3ID_S 4 +#define HNS3_RXD_L3ID_M (0xf << HNS3_RXD_L3ID_S) +#define HNS3_RXD_L4ID_S 8 +#define HNS3_RXD_L4ID_M (0xf << HNS3_RXD_L4ID_S) +#define HNS3_RXD_FRAG_B 12 +#define HNS3_RXD_L2E_B 16 +#define HNS3_RXD_L3E_B 17 +#define HNS3_RXD_L4E_B 18 +#define HNS3_RXD_TRUNCAT_B 19 +#define HNS3_RXD_HOI_B 20 +#define HNS3_RXD_DOI_B 21 +#define HNS3_RXD_OL3E_B 22 +#define HNS3_RXD_OL4E_B 23 + +#define HNS3_RXD_ODMAC_S 0 +#define HNS3_RXD_ODMAC_M (0x3 << HNS3_RXD_ODMAC_S) +#define HNS3_RXD_OVLAN_S 2 +#define HNS3_RXD_OVLAN_M (0x3 << HNS3_RXD_OVLAN_S) +#define HNS3_RXD_OL3ID_S 4 +#define HNS3_RXD_OL3ID_M (0xf << HNS3_RXD_OL3ID_S) +#define HNS3_RXD_OL4ID_S 8 +#define HNS3_RXD_OL4ID_M (0xf << HNS3_RXD_OL4ID_S) +#define HNS3_RXD_FBHI_S 12 +#define HNS3_RXD_FBHI_M (0x3 << HNS3_RXD_FBHI_S) +#define HNS3_RXD_FBLI_S 14 +#define HNS3_RXD_FBLI_M (0x3 << HNS3_RXD_FBLI_S) + +#define HNS3_RXD_BDTYPE_S 0 +#define HNS3_RXD_BDTYPE_M (0xf << HNS3_RXD_BDTYPE_S) +#define HNS3_RXD_VLD_B 4 +#define HNS3_RXD_UDP0_B 5 +#define HNS3_RXD_EXTEND_B 7 +#define HNS3_RXD_FE_B 8 +#define HNS3_RXD_LUM_B 9 +#define HNS3_RXD_CRCP_B 10 +#define HNS3_RXD_L3L4P_B 11 +#define HNS3_RXD_TSIND_S 12 +#define HNS3_RXD_TSIND_M (0x7 << HNS3_RXD_TSIND_S) +#define HNS3_RXD_LKBK_B 15 +#define HNS3_RXD_HDL_S 16 +#define HNS3_RXD_HDL_M (0x7ff << HNS3_RXD_HDL_S) +#define HNS3_RXD_HSIND_B 31 + +#define HNS3_TXD_L3T_S 0 +#define HNS3_TXD_L3T_M (0x3 << HNS3_TXD_L3T_S) +#define HNS3_TXD_L4T_S 2 +#define HNS3_TXD_L4T_M (0x3 << HNS3_TXD_L4T_S) +#define HNS3_TXD_L3CS_B 4 +#define HNS3_TXD_L4CS_B 5 +#define HNS3_TXD_VLAN_B 6 +#define HNS3_TXD_TSO_B 7 + +#define HNS3_TXD_L2LEN_S 8 +#define HNS3_TXD_L2LEN_M (0xff << HNS3_TXD_L2LEN_S) +#define HNS3_TXD_L3LEN_S 16 +#define HNS3_TXD_L3LEN_M (0xff << HNS3_TXD_L3LEN_S) +#define HNS3_TXD_L4LEN_S 24 +#define HNS3_TXD_L4LEN_M (0xff << HNS3_TXD_L4LEN_S) + +#define HNS3_TXD_OL3T_S 0 +#define HNS3_TXD_OL3T_M (0x3 << HNS3_TXD_OL3T_S) +#define HNS3_TXD_OVLAN_B 2 +#define HNS3_TXD_MACSEC_B 3 +#define HNS3_TXD_TUNTYPE_S 4 +#define HNS3_TXD_TUNTYPE_M (0xf << HNS3_TXD_TUNTYPE_S) + +#define HNS3_TXD_BDTYPE_S 0 +#define HNS3_TXD_BDTYPE_M (0xf << HNS3_TXD_BDTYPE_S) +#define HNS3_TXD_FE_B 4 +#define HNS3_TXD_SC_S 5 +#define HNS3_TXD_SC_M (0x3 << HNS3_TXD_SC_S) +#define HNS3_TXD_EXTEND_B 7 +#define HNS3_TXD_VLD_B 8 +#define HNS3_TXD_RI_B 9 +#define HNS3_TXD_RA_B 10 +#define HNS3_TXD_TSYN_B 11 +#define HNS3_TXD_DECTTL_S 12 +#define HNS3_TXD_DECTTL_M (0xf << HNS3_TXD_DECTTL_S) + +#define HNS3_TXD_MSS_S 0 +#define HNS3_TXD_MSS_M (0x3fff << HNS3_TXD_MSS_S) + +#define HNS3_VECTOR_TX_IRQ BIT_ULL(0) +#define HNS3_VECTOR_RX_IRQ BIT_ULL(1) + +#define HNS3_VECTOR_NOT_INITED 0 +#define HNS3_VECTOR_INITED 1 + +#define HNS3_MAX_BD_SIZE 65535 +#define HNS3_MAX_BD_PER_FRAG 8 +#define HNS3_MAX_BD_PER_PKT MAX_SKB_FRAGS + +#define HNS3_VECTOR_GL0_OFFSET 0x100 +#define HNS3_VECTOR_GL1_OFFSET 0x200 +#define HNS3_VECTOR_GL2_OFFSET 0x300 +#define HNS3_VECTOR_RL_OFFSET 0x900 +#define HNS3_VECTOR_RL_EN_B 6 + +enum hns3_pkt_l3t_type { + HNS3_L3T_NONE, + HNS3_L3T_IPV6, + HNS3_L3T_IPV4, + HNS3_L3T_RESERVED +}; + +enum hns3_pkt_l4t_type { + HNS3_L4T_UNKNOWN, + HNS3_L4T_TCP, + HNS3_L4T_UDP, + HNS3_L4T_SCTP +}; + +enum hns3_pkt_ol3t_type { + HNS3_OL3T_NONE, + HNS3_OL3T_IPV6, + HNS3_OL3T_IPV4_NO_CSUM, + HNS3_OL3T_IPV4_CSUM +}; + +enum hns3_pkt_tun_type { + HNS3_TUN_NONE, + HNS3_TUN_MAC_IN_UDP, + HNS3_TUN_NVGRE, + HNS3_TUN_OTHER +}; + +/* hardware spec ring buffer format */ +struct __packed hns3_desc { + __le64 addr; + union { + struct { + __le16 vlan_tag; + __le16 send_size; + union { + __le32 type_cs_vlan_tso_len; + struct { + __u8 type_cs_vlan_tso; + __u8 l2_len; + __u8 l3_len; + __u8 l4_len; + }; + }; + __le16 outer_vlan_tag; + __le16 tv; + + union { + __le32 ol_type_vlan_len_msec; + struct { + __u8 ol_type_vlan_msec; + __u8 ol2_len; + __u8 ol3_len; + __u8 ol4_len; + }; + }; + + __le32 paylen; + __le16 bdtp_fe_sc_vld_ra_ri; + __le16 mss; + } tx; + + struct { + __le32 l234_info; + __le16 pkt_len; + __le16 size; + + __le32 rss_hash; + __le16 fd_id; + __le16 vlan_tag; + + union { + __le32 ol_info; + struct { + __le16 o_dm_vlan_id_fb; + __le16 ot_vlan_tag; + }; + }; + + __le32 bd_base_info; + } rx; + }; +}; + +struct hns3_desc_cb { + dma_addr_t dma; /* dma address of this desc */ + void *buf; /* cpu addr for a desc */ + + /* priv data for the desc, e.g. skb when use with ip stack*/ + void *priv; + u16 page_offset; + u16 reuse_flag; + + u16 length; /* length of the buffer */ + + /* desc type, used by the ring user to mark the type of the priv data */ + u16 type; +}; + +enum hns3_pkt_l3type { + HNS3_L3_TYPE_IPV4, + HNS3_L3_TYPE_IPV6, + HNS3_L3_TYPE_ARP, + HNS3_L3_TYPE_RARP, + HNS3_L3_TYPE_IPV4_OPT, + HNS3_L3_TYPE_IPV6_EXT, + HNS3_L3_TYPE_LLDP, + HNS3_L3_TYPE_BPDU, + HNS3_L3_TYPE_MAC_PAUSE, + HNS3_L3_TYPE_PFC_PAUSE,/* 0x9*/ + + /* reserved for 0xA~0xB*/ + + HNS3_L3_TYPE_CNM = 0xc, + + /* reserved for 0xD~0xE*/ + + HNS3_L3_TYPE_PARSE_FAIL = 0xf /* must be last */ +}; + +enum hns3_pkt_l4type { + HNS3_L4_TYPE_UDP, + HNS3_L4_TYPE_TCP, + HNS3_L4_TYPE_GRE, + HNS3_L4_TYPE_SCTP, + HNS3_L4_TYPE_IGMP, + HNS3_L4_TYPE_ICMP, + + /* reserved for 0x6~0xE */ + + HNS3_L4_TYPE_PARSE_FAIL = 0xf /* must be last */ +}; + +enum hns3_pkt_ol3type { + HNS3_OL3_TYPE_IPV4 = 0, + HNS3_OL3_TYPE_IPV6, + /* reserved for 0x2~0x3 */ + HNS3_OL3_TYPE_IPV4_OPT = 4, + HNS3_OL3_TYPE_IPV6_EXT, + + /* reserved for 0x6~0xE*/ + + HNS3_OL3_TYPE_PARSE_FAIL = 0xf /* must be last */ +}; + +enum hns3_pkt_ol4type { + HNS3_OL4_TYPE_NO_TUN, + HNS3_OL4_TYPE_MAC_IN_UDP, + HNS3_OL4_TYPE_NVGRE, + HNS3_OL4_TYPE_UNKNOWN +}; + +struct ring_stats { + u64 io_err_cnt; + u64 sw_err_cnt; + u64 seg_pkt_cnt; + union { + struct { + u64 tx_pkts; + u64 tx_bytes; + u64 tx_err_cnt; + u64 restart_queue; + u64 tx_busy; + }; + struct { + u64 rx_pkts; + u64 rx_bytes; + u64 rx_err_cnt; + u64 reuse_pg_cnt; + u64 err_pkt_len; + u64 non_vld_descs; + u64 err_bd_num; + u64 l2_err; + u64 l3l4_csum_err; + }; + }; +}; + +struct hns3_enet_ring { + u8 __iomem *io_base; /* base io address for the ring */ + struct hns3_desc *desc; /* dma map address space */ + struct hns3_desc_cb *desc_cb; + struct hns3_enet_ring *next; + struct hns3_enet_tqp_vector *tqp_vector; + struct hnae3_queue *tqp; + char ring_name[HNS3_RING_NAME_LEN]; + struct device *dev; /* will be used for DMA mapping of descriptors */ + + /* statistic */ + struct ring_stats stats; + struct u64_stats_sync syncp; + + dma_addr_t desc_dma_addr; + u32 buf_size; /* size for hnae_desc->addr, preset by AE */ + u16 desc_num; /* total number of desc */ + u16 max_desc_num_per_pkt; + u16 max_raw_data_sz_per_desc; + u16 max_pkt_size; + int next_to_use; /* idx of next spare desc */ + + /* idx of lastest sent desc, the ring is empty when equal to + * next_to_use + */ + int next_to_clean; + + u32 flag; /* ring attribute */ + int irq_init_flag; + + int numa_node; + cpumask_t affinity_mask; +}; + +struct hns_queue; + +struct hns3_nic_ring_data { + struct hns3_enet_ring *ring; + struct napi_struct napi; + int queue_index; + int (*poll_one)(struct hns3_nic_ring_data *, int, void *); + void (*ex_process)(struct hns3_nic_ring_data *, struct sk_buff *); + void (*fini_process)(struct hns3_nic_ring_data *); +}; + +struct hns3_nic_ops { + int (*fill_desc)(struct hns3_enet_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + enum hns_desc_type type); + int (*maybe_stop_tx)(struct sk_buff **out_skb, + int *bnum, struct hns3_enet_ring *ring); + void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum); +}; + +enum hns3_flow_level_range { + HNS3_FLOW_LOW = 0, + HNS3_FLOW_MID = 1, + HNS3_FLOW_HIGH = 2, + HNS3_FLOW_ULTRA = 3, +}; + +enum hns3_link_mode_bits { + HNS3_LM_FIBRE_BIT = BIT(0), + HNS3_LM_AUTONEG_BIT = BIT(1), + HNS3_LM_TP_BIT = BIT(2), + HNS3_LM_PAUSE_BIT = BIT(3), + HNS3_LM_BACKPLANE_BIT = BIT(4), + HNS3_LM_10BASET_HALF_BIT = BIT(5), + HNS3_LM_10BASET_FULL_BIT = BIT(6), + HNS3_LM_100BASET_HALF_BIT = BIT(7), + HNS3_LM_100BASET_FULL_BIT = BIT(8), + HNS3_LM_1000BASET_FULL_BIT = BIT(9), + HNS3_LM_10000BASEKR_FULL_BIT = BIT(10), + HNS3_LM_25000BASEKR_FULL_BIT = BIT(11), + HNS3_LM_40000BASELR4_FULL_BIT = BIT(12), + HNS3_LM_50000BASEKR2_FULL_BIT = BIT(13), + HNS3_LM_100000BASEKR4_FULL_BIT = BIT(14), + HNS3_LM_COUNT = 15 +}; + +#define HNS3_INT_GL_50K 0x000A +#define HNS3_INT_GL_20K 0x0019 +#define HNS3_INT_GL_18K 0x001B +#define HNS3_INT_GL_8K 0x003E + +struct hns3_enet_ring_group { + /* array of pointers to rings */ + struct hns3_enet_ring *ring; + u64 total_bytes; /* total bytes processed this group */ + u64 total_packets; /* total packets processed this group */ + u16 count; + enum hns3_flow_level_range flow_level; + u16 int_gl; +}; + +struct hns3_enet_tqp_vector { + struct hnae3_handle *handle; + u8 __iomem *mask_addr; + int vector_irq; + int irq_init_flag; + + u16 idx; /* index in the TQP vector array per handle. */ + + struct napi_struct napi; + + struct hns3_enet_ring_group rx_group; + struct hns3_enet_ring_group tx_group; + + u16 num_tqps; /* total number of tqps in TQP vector */ + + cpumask_t affinity_mask; + char name[HNAE3_INT_NAME_LEN]; + + /* when 0 should adjust interrupt coalesce parameter */ + u8 int_adapt_down; +} ____cacheline_internodealigned_in_smp; + +enum hns3_udp_tnl_type { + HNS3_UDP_TNL_VXLAN, + HNS3_UDP_TNL_GENEVE, + HNS3_UDP_TNL_MAX, +}; + +struct hns3_udp_tunnel { + u16 dst_port; + int used; +}; + +struct hns3_nic_priv { + struct hnae3_handle *ae_handle; + u32 enet_ver; + u32 port_id; + struct net_device *netdev; + struct device *dev; + struct hns3_nic_ops ops; + + /** + * the cb for nic to manage the ring buffer, the first half of the + * array is for tx_ring and vice versa for the second half + */ + struct hns3_nic_ring_data *ring_data; + struct hns3_enet_tqp_vector *tqp_vector; + u16 vector_num; + + /* The most recently read link state */ + int link; + u64 tx_timeout_count; + + unsigned long state; + + struct timer_list service_timer; + + struct work_struct service_task; + + struct notifier_block notifier_block; + /* Vxlan/Geneve information */ + struct hns3_udp_tunnel udp_tnl[HNS3_UDP_TNL_MAX]; +}; + +union l3_hdr_info { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; +}; + +union l4_hdr_info { + struct tcphdr *tcp; + struct udphdr *udp; + unsigned char *hdr; +}; + +/* the distance between [begin, end) in a ring buffer + * note: there is a unuse slot between the begin and the end + */ +static inline int ring_dist(struct hns3_enet_ring *ring, int begin, int end) +{ + return (end - begin + ring->desc_num) % ring->desc_num; +} + +static inline int ring_space(struct hns3_enet_ring *ring) +{ + return ring->desc_num - + ring_dist(ring, ring->next_to_clean, ring->next_to_use) - 1; +} + +static inline int is_ring_empty(struct hns3_enet_ring *ring) +{ + return ring->next_to_use == ring->next_to_clean; +} + +static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value) +{ + u8 __iomem *reg_addr = READ_ONCE(base); + + writel(value, reg_addr + reg); +} + +#define hns3_write_dev(a, reg, value) \ + hns3_write_reg((a)->io_base, (reg), (value)) + +#define hnae_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \ + (tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG) + +#define ring_to_dev(ring) (&(ring)->tqp->handle->pdev->dev) + +#define ring_to_dma_dir(ring) (HNAE3_IS_TX_RING(ring) ? \ + DMA_TO_DEVICE : DMA_FROM_DEVICE) + +#define tx_ring_data(priv, idx) ((priv)->ring_data[idx]) + +#define hnae_buf_size(_ring) ((_ring)->buf_size) +#define hnae_page_order(_ring) (get_order(hnae_buf_size(_ring))) +#define hnae_page_size(_ring) (PAGE_SIZE << hnae_page_order(_ring)) + +/* iterator for handling rings in ring group */ +#define hns3_for_each_ring(pos, head) \ + for (pos = (head).ring; pos; pos = pos->next) + +void hns3_ethtool_set_ops(struct net_device *netdev); + +int hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget); +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c new file mode 100644 index 000000000000..d636399232fb --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_ethtool.c @@ -0,0 +1,493 @@ +/* + * Copyright (c) 2016~2017 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/etherdevice.h> +#include <linux/string.h> + +#include "hns3_enet.h" + +struct hns3_stats { + char stats_string[ETH_GSTRING_LEN]; + int stats_size; + int stats_offset; +}; + +/* tqp related stats */ +#define HNS3_TQP_STAT(_string, _member) { \ + .stats_string = _string, \ + .stats_size = FIELD_SIZEOF(struct ring_stats, _member), \ + .stats_offset = offsetof(struct hns3_enet_ring, stats), \ +} \ + +static const struct hns3_stats hns3_txq_stats[] = { + /* Tx per-queue statistics */ + HNS3_TQP_STAT("tx_io_err_cnt", io_err_cnt), + HNS3_TQP_STAT("tx_sw_err_cnt", sw_err_cnt), + HNS3_TQP_STAT("tx_seg_pkt_cnt", seg_pkt_cnt), + HNS3_TQP_STAT("tx_pkts", tx_pkts), + HNS3_TQP_STAT("tx_bytes", tx_bytes), + HNS3_TQP_STAT("tx_err_cnt", tx_err_cnt), + HNS3_TQP_STAT("tx_restart_queue", restart_queue), + HNS3_TQP_STAT("tx_busy", tx_busy), +}; + +#define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats) + +static const struct hns3_stats hns3_rxq_stats[] = { + /* Rx per-queue statistics */ + HNS3_TQP_STAT("rx_io_err_cnt", io_err_cnt), + HNS3_TQP_STAT("rx_sw_err_cnt", sw_err_cnt), + HNS3_TQP_STAT("rx_seg_pkt_cnt", seg_pkt_cnt), + HNS3_TQP_STAT("rx_pkts", rx_pkts), + HNS3_TQP_STAT("rx_bytes", rx_bytes), + HNS3_TQP_STAT("rx_err_cnt", rx_err_cnt), + HNS3_TQP_STAT("rx_reuse_pg_cnt", reuse_pg_cnt), + HNS3_TQP_STAT("rx_err_pkt_len", err_pkt_len), + HNS3_TQP_STAT("rx_non_vld_descs", non_vld_descs), + HNS3_TQP_STAT("rx_err_bd_num", err_bd_num), + HNS3_TQP_STAT("rx_l2_err", l2_err), + HNS3_TQP_STAT("rx_l3l4_csum_err", l3l4_csum_err), +}; + +#define HNS3_RXQ_STATS_COUNT ARRAY_SIZE(hns3_rxq_stats) + +#define HNS3_TQP_STATS_COUNT (HNS3_TXQ_STATS_COUNT + HNS3_RXQ_STATS_COUNT) + +struct hns3_link_mode_mapping { + u32 hns3_link_mode; + u32 ethtool_link_mode; +}; + +static const struct hns3_link_mode_mapping hns3_lm_map[] = { + {HNS3_LM_FIBRE_BIT, ETHTOOL_LINK_MODE_FIBRE_BIT}, + {HNS3_LM_AUTONEG_BIT, ETHTOOL_LINK_MODE_Autoneg_BIT}, + {HNS3_LM_TP_BIT, ETHTOOL_LINK_MODE_TP_BIT}, + {HNS3_LM_PAUSE_BIT, ETHTOOL_LINK_MODE_Pause_BIT}, + {HNS3_LM_BACKPLANE_BIT, ETHTOOL_LINK_MODE_Backplane_BIT}, + {HNS3_LM_10BASET_HALF_BIT, ETHTOOL_LINK_MODE_10baseT_Half_BIT}, + {HNS3_LM_10BASET_FULL_BIT, ETHTOOL_LINK_MODE_10baseT_Full_BIT}, + {HNS3_LM_100BASET_HALF_BIT, ETHTOOL_LINK_MODE_100baseT_Half_BIT}, + {HNS3_LM_100BASET_FULL_BIT, ETHTOOL_LINK_MODE_100baseT_Full_BIT}, + {HNS3_LM_1000BASET_FULL_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT}, +}; + +static void hns3_driv_to_eth_caps(u32 caps, struct ethtool_link_ksettings *cmd, + bool is_advertised) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(hns3_lm_map); i++) { + if (!(caps & hns3_lm_map[i].hns3_link_mode)) + continue; + + if (is_advertised) { + ethtool_link_ksettings_zero_link_mode(cmd, + advertising); + __set_bit(hns3_lm_map[i].ethtool_link_mode, + cmd->link_modes.advertising); + } else { + ethtool_link_ksettings_zero_link_mode(cmd, + supported); + __set_bit(hns3_lm_map[i].ethtool_link_mode, + cmd->link_modes.supported); + } + } +} + +static int hns3_get_sset_count(struct net_device *netdev, int stringset) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + const struct hnae3_ae_ops *ops = h->ae_algo->ops; + + if (!ops->get_sset_count) + return -EOPNOTSUPP; + + switch (stringset) { + case ETH_SS_STATS: + return ((HNS3_TQP_STATS_COUNT * h->kinfo.num_tqps) + + ops->get_sset_count(h, stringset)); + + case ETH_SS_TEST: + return ops->get_sset_count(h, stringset); + } + + return 0; +} + +static void *hns3_update_strings(u8 *data, const struct hns3_stats *stats, + u32 stat_count, u32 num_tqps) +{ +#define MAX_PREFIX_SIZE (8 + 4) + u32 size_left; + u32 i, j; + u32 n1; + + for (i = 0; i < num_tqps; i++) { + for (j = 0; j < stat_count; j++) { + data[ETH_GSTRING_LEN - 1] = '\0'; + + /* first, prepend the prefix string */ + n1 = snprintf(data, MAX_PREFIX_SIZE, "rcb_q%d_", i); + n1 = min_t(uint, n1, MAX_PREFIX_SIZE - 1); + size_left = (ETH_GSTRING_LEN - 1) - n1; + + /* now, concatenate the stats string to it */ + strncat(data, stats[j].stats_string, size_left); + data += ETH_GSTRING_LEN; + } + } + + return data; +} + +static u8 *hns3_get_strings_tqps(struct hnae3_handle *handle, u8 *data) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + + /* get strings for Tx */ + data = hns3_update_strings(data, hns3_txq_stats, HNS3_TXQ_STATS_COUNT, + kinfo->num_tqps); + + /* get strings for Rx */ + data = hns3_update_strings(data, hns3_rxq_stats, HNS3_RXQ_STATS_COUNT, + kinfo->num_tqps); + + return data; +} + +static void hns3_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + const struct hnae3_ae_ops *ops = h->ae_algo->ops; + char *buff = (char *)data; + + if (!ops->get_strings) + return; + + switch (stringset) { + case ETH_SS_STATS: + buff = hns3_get_strings_tqps(h, buff); + h->ae_algo->ops->get_strings(h, stringset, (u8 *)buff); + break; + case ETH_SS_TEST: + ops->get_strings(h, stringset, data); + break; + } +} + +static u64 *hns3_get_stats_tqps(struct hnae3_handle *handle, u64 *data) +{ + struct hns3_nic_priv *nic_priv = (struct hns3_nic_priv *)handle->priv; + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hns3_enet_ring *ring; + u8 *stat; + u32 i; + + /* get stats for Tx */ + for (i = 0; i < kinfo->num_tqps; i++) { + ring = nic_priv->ring_data[i].ring; + for (i = 0; i < HNS3_TXQ_STATS_COUNT; i++) { + stat = (u8 *)ring + hns3_txq_stats[i].stats_offset; + *data++ = *(u64 *)stat; + } + } + + /* get stats for Rx */ + for (i = 0; i < kinfo->num_tqps; i++) { + ring = nic_priv->ring_data[i + kinfo->num_tqps].ring; + for (i = 0; i < HNS3_RXQ_STATS_COUNT; i++) { + stat = (u8 *)ring + hns3_rxq_stats[i].stats_offset; + *data++ = *(u64 *)stat; + } + } + + return data; +} + +/* hns3_get_stats - get detail statistics. + * @netdev: net device + * @stats: statistics info. + * @data: statistics data. + */ +void hns3_get_stats(struct net_device *netdev, struct ethtool_stats *stats, + u64 *data) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + u64 *p = data; + + if (!h->ae_algo->ops->get_stats || !h->ae_algo->ops->update_stats) { + netdev_err(netdev, "could not get any statistics\n"); + return; + } + + h->ae_algo->ops->update_stats(h, &netdev->stats); + + /* get per-queue stats */ + p = hns3_get_stats_tqps(h, p); + + /* get MAC & other misc hardware stats */ + h->ae_algo->ops->get_stats(h, p); +} + +static void hns3_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + strncpy(drvinfo->version, hns3_driver_version, + sizeof(drvinfo->version)); + drvinfo->version[sizeof(drvinfo->version) - 1] = '\0'; + + strncpy(drvinfo->driver, h->pdev->driver->name, + sizeof(drvinfo->driver)); + drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; + + strncpy(drvinfo->bus_info, pci_name(h->pdev), + sizeof(drvinfo->bus_info)); + drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; + + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "0x%08x", + priv->ae_handle->ae_algo->ops->get_fw_version(h)); +} + +static u32 hns3_get_link(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h; + + h = priv->ae_handle; + + if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_status) + return h->ae_algo->ops->get_status(h); + else + return 0; +} + +static void hns3_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *param) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + int queue_num = priv->ae_handle->kinfo.num_tqps; + + param->tx_max_pending = HNS3_RING_MAX_PENDING; + param->rx_max_pending = HNS3_RING_MAX_PENDING; + + param->tx_pending = priv->ring_data[0].ring->desc_num; + param->rx_pending = priv->ring_data[queue_num].ring->desc_num; +} + +static void hns3_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *param) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (h->ae_algo && h->ae_algo->ops && h->ae_algo->ops->get_pauseparam) + h->ae_algo->ops->get_pauseparam(h, ¶m->autoneg, + ¶m->rx_pause, ¶m->tx_pause); +} + +static int hns3_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + u32 supported_caps; + u32 advertised_caps; + u8 media_type = HNAE3_MEDIA_TYPE_UNKNOWN; + u8 link_stat; + u8 auto_neg; + u8 duplex; + u32 speed; + + if (!h->ae_algo || !h->ae_algo->ops) + return -EOPNOTSUPP; + + /* 1.auto_neg & speed & duplex from cmd */ + if (h->ae_algo->ops->get_ksettings_an_result) { + h->ae_algo->ops->get_ksettings_an_result(h, &auto_neg, + &speed, &duplex); + cmd->base.autoneg = auto_neg; + cmd->base.speed = speed; + cmd->base.duplex = duplex; + + link_stat = hns3_get_link(netdev); + if (!link_stat) { + cmd->base.speed = (u32)SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + } + } + + /* 2.media_type get from bios parameter block */ + if (h->ae_algo->ops->get_media_type) { + h->ae_algo->ops->get_media_type(h, &media_type); + + switch (media_type) { + case HNAE3_MEDIA_TYPE_FIBER: + cmd->base.port = PORT_FIBRE; + supported_caps = HNS3_LM_FIBRE_BIT | + HNS3_LM_AUTONEG_BIT | + HNS3_LM_PAUSE_BIT | + HNS3_LM_1000BASET_FULL_BIT; + + advertised_caps = supported_caps; + break; + case HNAE3_MEDIA_TYPE_COPPER: + cmd->base.port = PORT_TP; + supported_caps = HNS3_LM_TP_BIT | + HNS3_LM_AUTONEG_BIT | + HNS3_LM_PAUSE_BIT | + HNS3_LM_1000BASET_FULL_BIT | + HNS3_LM_100BASET_FULL_BIT | + HNS3_LM_100BASET_HALF_BIT | + HNS3_LM_10BASET_FULL_BIT | + HNS3_LM_10BASET_HALF_BIT; + advertised_caps = supported_caps; + break; + case HNAE3_MEDIA_TYPE_BACKPLANE: + cmd->base.port = PORT_NONE; + supported_caps = HNS3_LM_BACKPLANE_BIT | + HNS3_LM_PAUSE_BIT | + HNS3_LM_AUTONEG_BIT | + HNS3_LM_1000BASET_FULL_BIT | + HNS3_LM_100BASET_FULL_BIT | + HNS3_LM_100BASET_HALF_BIT | + HNS3_LM_10BASET_FULL_BIT | + HNS3_LM_10BASET_HALF_BIT; + + advertised_caps = supported_caps; + break; + case HNAE3_MEDIA_TYPE_UNKNOWN: + default: + cmd->base.port = PORT_OTHER; + supported_caps = 0; + advertised_caps = 0; + break; + } + + /* now, map driver link modes to ethtool link modes */ + hns3_driv_to_eth_caps(supported_caps, cmd, false); + hns3_driv_to_eth_caps(advertised_caps, cmd, true); + } + + /* 3.mdix_ctrl&mdix get from phy reg */ + if (h->ae_algo->ops->get_mdix_mode) + h->ae_algo->ops->get_mdix_mode(h, &cmd->base.eth_tp_mdix_ctrl, + &cmd->base.eth_tp_mdix); + /* 4.mdio_support */ + cmd->base.mdio_support = ETH_MDIO_SUPPORTS_C22; + + return 0; +} + +static u32 hns3_get_rss_key_size(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (!h->ae_algo || !h->ae_algo->ops || + !h->ae_algo->ops->get_rss_key_size) + return -EOPNOTSUPP; + + return h->ae_algo->ops->get_rss_key_size(h); +} + +static u32 hns3_get_rss_indir_size(struct net_device *netdev) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (!h->ae_algo || !h->ae_algo->ops || + !h->ae_algo->ops->get_rss_indir_size) + return -EOPNOTSUPP; + + return h->ae_algo->ops->get_rss_indir_size(h); +} + +static int hns3_get_rss(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_rss) + return -EOPNOTSUPP; + + return h->ae_algo->ops->get_rss(h, indir, key, hfunc); +} + +static int hns3_set_rss(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->set_rss) + return -EOPNOTSUPP; + + /* currently we only support Toeplitz hash */ + if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_TOP)) { + netdev_err(netdev, + "hash func not supported (only Toeplitz hash)\n"); + return -EOPNOTSUPP; + } + if (!indir) { + netdev_err(netdev, + "set rss failed for indir is empty\n"); + return -EOPNOTSUPP; + } + + return h->ae_algo->ops->set_rss(h, indir, key, hfunc); +} + +static int hns3_get_rxnfc(struct net_device *netdev, + struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + + if (!h->ae_algo || !h->ae_algo->ops || !h->ae_algo->ops->get_tc_size) + return -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = h->ae_algo->ops->get_tc_size(h); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static const struct ethtool_ops hns3_ethtool_ops = { + .get_drvinfo = hns3_get_drvinfo, + .get_link = hns3_get_link, + .get_ringparam = hns3_get_ringparam, + .get_pauseparam = hns3_get_pauseparam, + .get_strings = hns3_get_strings, + .get_ethtool_stats = hns3_get_stats, + .get_sset_count = hns3_get_sset_count, + .get_rxnfc = hns3_get_rxnfc, + .get_rxfh_key_size = hns3_get_rss_key_size, + .get_rxfh_indir_size = hns3_get_rss_indir_size, + .get_rxfh = hns3_get_rss, + .set_rxfh = hns3_set_rss, + .get_link_ksettings = hns3_get_link_ksettings, +}; + +void hns3_ethtool_set_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &hns3_ethtool_ops; +} diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index c6164a98f257..c8c7ad2eff77 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -194,7 +194,7 @@ static const char *hp100_isa_tbl[] = { }; #endif -static struct eisa_device_id hp100_eisa_tbl[] = { +static const struct eisa_device_id hp100_eisa_tbl[] = { { "HWPF180" }, /* HP J2577 rev A */ { "HWP1920" }, /* HP 27248B */ { "HWP1940" }, /* HP J2577 */ diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig new file mode 100644 index 000000000000..c1a95ae4058b --- /dev/null +++ b/drivers/net/ethernet/huawei/Kconfig @@ -0,0 +1,19 @@ +# +# Huawei driver configuration +# + +config NET_VENDOR_HUAWEI + bool "Huawei devices" + default y + ---help--- + If you have a network (Ethernet) card belonging to this class, say Y. + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Huawei cards. If you say Y, you will be asked + for your specific card in the following questions. + +if NET_VENDOR_HUAWEI + +source "drivers/net/ethernet/huawei/hinic/Kconfig" + +endif # NET_VENDOR_HUAWEI diff --git a/drivers/net/ethernet/huawei/Makefile b/drivers/net/ethernet/huawei/Makefile new file mode 100644 index 000000000000..5c37cc8fc1bc --- /dev/null +++ b/drivers/net/ethernet/huawei/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the Huawei device drivers. +# + +obj-$(CONFIG_HINIC) += hinic/ diff --git a/drivers/net/ethernet/huawei/hinic/Kconfig b/drivers/net/ethernet/huawei/hinic/Kconfig new file mode 100644 index 000000000000..08db24954f7e --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/Kconfig @@ -0,0 +1,12 @@ +# +# Huawei driver configuration +# + +config HINIC + tristate "Huawei Intelligent PCIE Network Interface Card" + depends on (PCI_MSI && X86) + ---help--- + This driver supports HiNIC PCIE Ethernet cards. + To compile this driver as part of the kernel, choose Y here. + If unsure, choose N. + The default is compiled as module. diff --git a/drivers/net/ethernet/huawei/hinic/Makefile b/drivers/net/ethernet/huawei/hinic/Makefile new file mode 100644 index 000000000000..289ce88bb2d0 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/Makefile @@ -0,0 +1,6 @@ +obj-$(CONFIG_HINIC) += hinic.o + +hinic-y := hinic_main.o hinic_tx.o hinic_rx.o hinic_port.o hinic_hw_dev.o \ + hinic_hw_io.o hinic_hw_qp.o hinic_hw_cmdq.o hinic_hw_wq.o \ + hinic_hw_mgmt.o hinic_hw_api_cmd.o hinic_hw_eqs.o hinic_hw_if.o \ + hinic_common.o diff --git a/drivers/net/ethernet/huawei/hinic/hinic_common.c b/drivers/net/ethernet/huawei/hinic/hinic_common.c new file mode 100644 index 000000000000..02c74fd8380e --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_common.c @@ -0,0 +1,80 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <asm/byteorder.h> + +#include "hinic_common.h" + +/** + * hinic_cpu_to_be32 - convert data to big endian 32 bit format + * @data: the data to convert + * @len: length of data to convert + **/ +void hinic_cpu_to_be32(void *data, int len) +{ + u32 *mem = data; + int i; + + len = len / sizeof(u32); + + for (i = 0; i < len; i++) { + *mem = cpu_to_be32(*mem); + mem++; + } +} + +/** + * hinic_be32_to_cpu - convert data from big endian 32 bit format + * @data: the data to convert + * @len: length of data to convert + **/ +void hinic_be32_to_cpu(void *data, int len) +{ + u32 *mem = data; + int i; + + len = len / sizeof(u32); + + for (i = 0; i < len; i++) { + *mem = be32_to_cpu(*mem); + mem++; + } +} + +/** + * hinic_set_sge - set dma area in scatter gather entry + * @sge: scatter gather entry + * @addr: dma address + * @len: length of relevant data in the dma address + **/ +void hinic_set_sge(struct hinic_sge *sge, dma_addr_t addr, int len) +{ + sge->hi_addr = upper_32_bits(addr); + sge->lo_addr = lower_32_bits(addr); + sge->len = len; +} + +/** + * hinic_sge_to_dma - get dma address from scatter gather entry + * @sge: scatter gather entry + * + * Return dma address of sg entry + **/ +dma_addr_t hinic_sge_to_dma(struct hinic_sge *sge) +{ + return (dma_addr_t)((((u64)sge->hi_addr) << 32) | sge->lo_addr); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_common.h b/drivers/net/ethernet/huawei/hinic/hinic_common.h new file mode 100644 index 000000000000..2c06b76e94a1 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_common.h @@ -0,0 +1,38 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_COMMON_H +#define HINIC_COMMON_H + +#include <linux/types.h> + +#define UPPER_8_BITS(data) (((data) >> 8) & 0xFF) +#define LOWER_8_BITS(data) ((data) & 0xFF) + +struct hinic_sge { + u32 hi_addr; + u32 lo_addr; + u32 len; +}; + +void hinic_cpu_to_be32(void *data, int len); + +void hinic_be32_to_cpu(void *data, int len); + +void hinic_set_sge(struct hinic_sge *sge, dma_addr_t addr, int len); + +dma_addr_t hinic_sge_to_dma(struct hinic_sge *sge); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_dev.h new file mode 100644 index 000000000000..5186cc9023aa --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_dev.h @@ -0,0 +1,64 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_DEV_H +#define HINIC_DEV_H + +#include <linux/netdevice.h> +#include <linux/types.h> +#include <linux/semaphore.h> +#include <linux/workqueue.h> +#include <linux/bitops.h> + +#include "hinic_hw_dev.h" +#include "hinic_tx.h" +#include "hinic_rx.h" + +#define HINIC_DRV_NAME "hinic" + +enum hinic_flags { + HINIC_LINK_UP = BIT(0), + HINIC_INTF_UP = BIT(1), +}; + +struct hinic_rx_mode_work { + struct work_struct work; + u32 rx_mode; +}; + +struct hinic_dev { + struct net_device *netdev; + struct hinic_hwdev *hwdev; + + u32 msg_enable; + unsigned int tx_weight; + unsigned int rx_weight; + + unsigned int flags; + + struct semaphore mgmt_lock; + unsigned long *vlan_bitmap; + + struct hinic_rx_mode_work rx_mode_work; + struct workqueue_struct *workq; + + struct hinic_txq *txqs; + struct hinic_rxq *rxqs; + + struct hinic_txq_stats tx_stats; + struct hinic_rxq_stats rx_stats; +}; + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c new file mode 100644 index 000000000000..c40603a183df --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c @@ -0,0 +1,978 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/slab.h> +#include <linux/dma-mapping.h> +#include <linux/bitops.h> +#include <linux/err.h> +#include <linux/jiffies.h> +#include <linux/delay.h> +#include <linux/log2.h> +#include <linux/semaphore.h> +#include <asm/byteorder.h> +#include <asm/barrier.h> + +#include "hinic_hw_csr.h" +#include "hinic_hw_if.h" +#include "hinic_hw_api_cmd.h" + +#define API_CHAIN_NUM_CELLS 32 + +#define API_CMD_CELL_SIZE_SHIFT 6 +#define API_CMD_CELL_SIZE_MIN (BIT(API_CMD_CELL_SIZE_SHIFT)) + +#define API_CMD_CELL_SIZE(cell_size) \ + (((cell_size) >= API_CMD_CELL_SIZE_MIN) ? \ + (1 << (fls(cell_size - 1))) : API_CMD_CELL_SIZE_MIN) + +#define API_CMD_CELL_SIZE_VAL(size) \ + ilog2((size) >> API_CMD_CELL_SIZE_SHIFT) + +#define API_CMD_BUF_SIZE 2048 + +/* Sizes of the members in hinic_api_cmd_cell */ +#define API_CMD_CELL_DESC_SIZE 8 +#define API_CMD_CELL_DATA_ADDR_SIZE 8 + +#define API_CMD_CELL_ALIGNMENT 8 + +#define API_CMD_TIMEOUT 1000 + +#define MASKED_IDX(chain, idx) ((idx) & ((chain)->num_cells - 1)) + +#define SIZE_8BYTES(size) (ALIGN((size), 8) >> 3) +#define SIZE_4BYTES(size) (ALIGN((size), 4) >> 2) + +#define RD_DMA_ATTR_DEFAULT 0 +#define WR_DMA_ATTR_DEFAULT 0 + +enum api_cmd_data_format { + SGE_DATA = 1, /* cell data is passed by hw address */ +}; + +enum api_cmd_type { + API_CMD_WRITE = 0, +}; + +enum api_cmd_bypass { + NO_BYPASS = 0, + BYPASS = 1, +}; + +enum api_cmd_xor_chk_level { + XOR_CHK_DIS = 0, + + XOR_CHK_ALL = 3, +}; + +static u8 xor_chksum_set(void *data) +{ + int idx; + u8 *val, checksum = 0; + + val = data; + + for (idx = 0; idx < 7; idx++) + checksum ^= val[idx]; + + return checksum; +} + +static void set_prod_idx(struct hinic_api_cmd_chain *chain) +{ + enum hinic_api_cmd_chain_type chain_type = chain->chain_type; + struct hinic_hwif *hwif = chain->hwif; + u32 addr, prod_idx; + + addr = HINIC_CSR_API_CMD_CHAIN_PI_ADDR(chain_type); + prod_idx = hinic_hwif_read_reg(hwif, addr); + + prod_idx = HINIC_API_CMD_PI_CLEAR(prod_idx, IDX); + + prod_idx |= HINIC_API_CMD_PI_SET(chain->prod_idx, IDX); + + hinic_hwif_write_reg(hwif, addr, prod_idx); +} + +static u32 get_hw_cons_idx(struct hinic_api_cmd_chain *chain) +{ + u32 addr, val; + + addr = HINIC_CSR_API_CMD_STATUS_ADDR(chain->chain_type); + val = hinic_hwif_read_reg(chain->hwif, addr); + + return HINIC_API_CMD_STATUS_GET(val, CONS_IDX); +} + +/** + * chain_busy - check if the chain is still processing last requests + * @chain: chain to check + * + * Return 0 - Success, negative - Failure + **/ +static int chain_busy(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + u32 prod_idx; + + switch (chain->chain_type) { + case HINIC_API_CMD_WRITE_TO_MGMT_CPU: + chain->cons_idx = get_hw_cons_idx(chain); + prod_idx = chain->prod_idx; + + /* check for a space for a new command */ + if (chain->cons_idx == MASKED_IDX(chain, prod_idx + 1)) { + dev_err(&pdev->dev, "API CMD chain %d is busy\n", + chain->chain_type); + return -EBUSY; + } + break; + + default: + dev_err(&pdev->dev, "Unknown API CMD Chain type\n"); + break; + } + + return 0; +} + +/** + * get_cell_data_size - get the data size of a specific cell type + * @type: chain type + * + * Return the data(Desc + Address) size in the cell + **/ +static u8 get_cell_data_size(enum hinic_api_cmd_chain_type type) +{ + u8 cell_data_size = 0; + + switch (type) { + case HINIC_API_CMD_WRITE_TO_MGMT_CPU: + cell_data_size = ALIGN(API_CMD_CELL_DESC_SIZE + + API_CMD_CELL_DATA_ADDR_SIZE, + API_CMD_CELL_ALIGNMENT); + break; + default: + break; + } + + return cell_data_size; +} + +/** + * prepare_cell_ctrl - prepare the ctrl of the cell for the command + * @cell_ctrl: the control of the cell to set the control value into it + * @data_size: the size of the data in the cell + **/ +static void prepare_cell_ctrl(u64 *cell_ctrl, u16 data_size) +{ + u8 chksum; + u64 ctrl; + + ctrl = HINIC_API_CMD_CELL_CTRL_SET(SIZE_8BYTES(data_size), DATA_SZ) | + HINIC_API_CMD_CELL_CTRL_SET(RD_DMA_ATTR_DEFAULT, RD_DMA_ATTR) | + HINIC_API_CMD_CELL_CTRL_SET(WR_DMA_ATTR_DEFAULT, WR_DMA_ATTR); + + chksum = xor_chksum_set(&ctrl); + + ctrl |= HINIC_API_CMD_CELL_CTRL_SET(chksum, XOR_CHKSUM); + + /* The data in the HW should be in Big Endian Format */ + *cell_ctrl = cpu_to_be64(ctrl); +} + +/** + * prepare_api_cmd - prepare API CMD command + * @chain: chain for the command + * @dest: destination node on the card that will receive the command + * @cmd: command data + * @cmd_size: the command size + **/ +static void prepare_api_cmd(struct hinic_api_cmd_chain *chain, + enum hinic_node_id dest, + void *cmd, u16 cmd_size) +{ + struct hinic_api_cmd_cell *cell = chain->curr_node; + struct hinic_api_cmd_cell_ctxt *cell_ctxt; + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + + cell_ctxt = &chain->cell_ctxt[chain->prod_idx]; + + switch (chain->chain_type) { + case HINIC_API_CMD_WRITE_TO_MGMT_CPU: + cell->desc = HINIC_API_CMD_DESC_SET(SGE_DATA, API_TYPE) | + HINIC_API_CMD_DESC_SET(API_CMD_WRITE, RD_WR) | + HINIC_API_CMD_DESC_SET(NO_BYPASS, MGMT_BYPASS); + break; + + default: + dev_err(&pdev->dev, "unknown Chain type\n"); + return; + } + + cell->desc |= HINIC_API_CMD_DESC_SET(dest, DEST) | + HINIC_API_CMD_DESC_SET(SIZE_4BYTES(cmd_size), SIZE); + + cell->desc |= HINIC_API_CMD_DESC_SET(xor_chksum_set(&cell->desc), + XOR_CHKSUM); + + /* The data in the HW should be in Big Endian Format */ + cell->desc = cpu_to_be64(cell->desc); + + memcpy(cell_ctxt->api_cmd_vaddr, cmd, cmd_size); +} + +/** + * prepare_cell - prepare cell ctrl and cmd in the current cell + * @chain: chain for the command + * @dest: destination node on the card that will receive the command + * @cmd: command data + * @cmd_size: the command size + * + * Return 0 - Success, negative - Failure + **/ +static void prepare_cell(struct hinic_api_cmd_chain *chain, + enum hinic_node_id dest, + void *cmd, u16 cmd_size) +{ + struct hinic_api_cmd_cell *curr_node = chain->curr_node; + u16 data_size = get_cell_data_size(chain->chain_type); + + prepare_cell_ctrl(&curr_node->ctrl, data_size); + prepare_api_cmd(chain, dest, cmd, cmd_size); +} + +static inline void cmd_chain_prod_idx_inc(struct hinic_api_cmd_chain *chain) +{ + chain->prod_idx = MASKED_IDX(chain, chain->prod_idx + 1); +} + +/** + * api_cmd_status_update - update the status in the chain struct + * @chain: chain to update + **/ +static void api_cmd_status_update(struct hinic_api_cmd_chain *chain) +{ + enum hinic_api_cmd_chain_type chain_type; + struct hinic_api_cmd_status *wb_status; + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + u64 status_header; + u32 status; + + wb_status = chain->wb_status; + status_header = be64_to_cpu(wb_status->header); + + status = be32_to_cpu(wb_status->status); + if (HINIC_API_CMD_STATUS_GET(status, CHKSUM_ERR)) { + dev_err(&pdev->dev, "API CMD status: Xor check error\n"); + return; + } + + chain_type = HINIC_API_CMD_STATUS_HEADER_GET(status_header, CHAIN_ID); + if (chain_type >= HINIC_API_CMD_MAX) { + dev_err(&pdev->dev, "unknown API CMD Chain %d\n", chain_type); + return; + } + + chain->cons_idx = HINIC_API_CMD_STATUS_GET(status, CONS_IDX); +} + +/** + * wait_for_status_poll - wait for write to api cmd command to complete + * @chain: the chain of the command + * + * Return 0 - Success, negative - Failure + **/ +static int wait_for_status_poll(struct hinic_api_cmd_chain *chain) +{ + int err = -ETIMEDOUT; + unsigned long end; + + end = jiffies + msecs_to_jiffies(API_CMD_TIMEOUT); + do { + api_cmd_status_update(chain); + + /* wait for CI to be updated - sign for completion */ + if (chain->cons_idx == chain->prod_idx) { + err = 0; + break; + } + + msleep(20); + } while (time_before(jiffies, end)); + + return err; +} + +/** + * wait_for_api_cmd_completion - wait for command to complete + * @chain: chain for the command + * + * Return 0 - Success, negative - Failure + **/ +static int wait_for_api_cmd_completion(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + int err; + + switch (chain->chain_type) { + case HINIC_API_CMD_WRITE_TO_MGMT_CPU: + err = wait_for_status_poll(chain); + if (err) { + dev_err(&pdev->dev, "API CMD Poll status timeout\n"); + break; + } + break; + + default: + dev_err(&pdev->dev, "unknown API CMD Chain type\n"); + err = -EINVAL; + break; + } + + return err; +} + +/** + * api_cmd - API CMD command + * @chain: chain for the command + * @dest: destination node on the card that will receive the command + * @cmd: command data + * @size: the command size + * + * Return 0 - Success, negative - Failure + **/ +static int api_cmd(struct hinic_api_cmd_chain *chain, + enum hinic_node_id dest, u8 *cmd, u16 cmd_size) +{ + struct hinic_api_cmd_cell_ctxt *ctxt; + int err; + + down(&chain->sem); + if (chain_busy(chain)) { + up(&chain->sem); + return -EBUSY; + } + + prepare_cell(chain, dest, cmd, cmd_size); + cmd_chain_prod_idx_inc(chain); + + wmb(); /* inc pi before issue the command */ + + set_prod_idx(chain); /* issue the command */ + + ctxt = &chain->cell_ctxt[chain->prod_idx]; + + chain->curr_node = ctxt->cell_vaddr; + + err = wait_for_api_cmd_completion(chain); + + up(&chain->sem); + return err; +} + +/** + * hinic_api_cmd_write - Write API CMD command + * @chain: chain for write command + * @dest: destination node on the card that will receive the command + * @cmd: command data + * @size: the command size + * + * Return 0 - Success, negative - Failure + **/ +int hinic_api_cmd_write(struct hinic_api_cmd_chain *chain, + enum hinic_node_id dest, u8 *cmd, u16 size) +{ + /* Verify the chain type */ + if (chain->chain_type == HINIC_API_CMD_WRITE_TO_MGMT_CPU) + return api_cmd(chain, dest, cmd, size); + + return -EINVAL; +} + +/** + * api_cmd_hw_restart - restart the chain in the HW + * @chain: the API CMD specific chain to restart + * + * Return 0 - Success, negative - Failure + **/ +static int api_cmd_hw_restart(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + int err = -ETIMEDOUT; + unsigned long end; + u32 reg_addr, val; + + /* Read Modify Write */ + reg_addr = HINIC_CSR_API_CMD_CHAIN_REQ_ADDR(chain->chain_type); + val = hinic_hwif_read_reg(hwif, reg_addr); + + val = HINIC_API_CMD_CHAIN_REQ_CLEAR(val, RESTART); + val |= HINIC_API_CMD_CHAIN_REQ_SET(1, RESTART); + + hinic_hwif_write_reg(hwif, reg_addr, val); + + end = jiffies + msecs_to_jiffies(API_CMD_TIMEOUT); + do { + val = hinic_hwif_read_reg(hwif, reg_addr); + + if (!HINIC_API_CMD_CHAIN_REQ_GET(val, RESTART)) { + err = 0; + break; + } + + msleep(20); + } while (time_before(jiffies, end)); + + return err; +} + +/** + * api_cmd_ctrl_init - set the control register of a chain + * @chain: the API CMD specific chain to set control register for + **/ +static void api_cmd_ctrl_init(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + u32 addr, ctrl; + u16 cell_size; + + /* Read Modify Write */ + addr = HINIC_CSR_API_CMD_CHAIN_CTRL_ADDR(chain->chain_type); + + cell_size = API_CMD_CELL_SIZE_VAL(chain->cell_size); + + ctrl = hinic_hwif_read_reg(hwif, addr); + + ctrl = HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, RESTART_WB_STAT) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_ERR) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, AEQE_EN) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_CHK_EN) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, CELL_SIZE); + + ctrl |= HINIC_API_CMD_CHAIN_CTRL_SET(1, XOR_ERR) | + HINIC_API_CMD_CHAIN_CTRL_SET(XOR_CHK_ALL, XOR_CHK_EN) | + HINIC_API_CMD_CHAIN_CTRL_SET(cell_size, CELL_SIZE); + + hinic_hwif_write_reg(hwif, addr, ctrl); +} + +/** + * api_cmd_set_status_addr - set the status address of a chain in the HW + * @chain: the API CMD specific chain to set in HW status address for + **/ +static void api_cmd_set_status_addr(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + u32 addr, val; + + addr = HINIC_CSR_API_CMD_STATUS_HI_ADDR(chain->chain_type); + val = upper_32_bits(chain->wb_status_paddr); + hinic_hwif_write_reg(hwif, addr, val); + + addr = HINIC_CSR_API_CMD_STATUS_LO_ADDR(chain->chain_type); + val = lower_32_bits(chain->wb_status_paddr); + hinic_hwif_write_reg(hwif, addr, val); +} + +/** + * api_cmd_set_num_cells - set the number cells of a chain in the HW + * @chain: the API CMD specific chain to set in HW the number of cells for + **/ +static void api_cmd_set_num_cells(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + u32 addr, val; + + addr = HINIC_CSR_API_CMD_CHAIN_NUM_CELLS_ADDR(chain->chain_type); + val = chain->num_cells; + hinic_hwif_write_reg(hwif, addr, val); +} + +/** + * api_cmd_head_init - set the head of a chain in the HW + * @chain: the API CMD specific chain to set in HW the head for + **/ +static void api_cmd_head_init(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + u32 addr, val; + + addr = HINIC_CSR_API_CMD_CHAIN_HEAD_HI_ADDR(chain->chain_type); + val = upper_32_bits(chain->head_cell_paddr); + hinic_hwif_write_reg(hwif, addr, val); + + addr = HINIC_CSR_API_CMD_CHAIN_HEAD_LO_ADDR(chain->chain_type); + val = lower_32_bits(chain->head_cell_paddr); + hinic_hwif_write_reg(hwif, addr, val); +} + +/** + * api_cmd_chain_hw_clean - clean the HW + * @chain: the API CMD specific chain + **/ +static void api_cmd_chain_hw_clean(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + u32 addr, ctrl; + + addr = HINIC_CSR_API_CMD_CHAIN_CTRL_ADDR(chain->chain_type); + + ctrl = hinic_hwif_read_reg(hwif, addr); + ctrl = HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, RESTART_WB_STAT) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_ERR) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, AEQE_EN) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, XOR_CHK_EN) & + HINIC_API_CMD_CHAIN_CTRL_CLEAR(ctrl, CELL_SIZE); + + hinic_hwif_write_reg(hwif, addr, ctrl); +} + +/** + * api_cmd_chain_hw_init - initialize the chain in the HW + * @chain: the API CMD specific chain to initialize in HW + * + * Return 0 - Success, negative - Failure + **/ +static int api_cmd_chain_hw_init(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + int err; + + api_cmd_chain_hw_clean(chain); + + api_cmd_set_status_addr(chain); + + err = api_cmd_hw_restart(chain); + if (err) { + dev_err(&pdev->dev, "Failed to restart API CMD HW\n"); + return err; + } + + api_cmd_ctrl_init(chain); + api_cmd_set_num_cells(chain); + api_cmd_head_init(chain); + return 0; +} + +/** + * free_cmd_buf - free the dma buffer of API CMD command + * @chain: the API CMD specific chain of the cmd + * @cell_idx: the cell index of the cmd + **/ +static void free_cmd_buf(struct hinic_api_cmd_chain *chain, int cell_idx) +{ + struct hinic_api_cmd_cell_ctxt *cell_ctxt; + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + + cell_ctxt = &chain->cell_ctxt[cell_idx]; + + dma_free_coherent(&pdev->dev, API_CMD_BUF_SIZE, + cell_ctxt->api_cmd_vaddr, + cell_ctxt->api_cmd_paddr); +} + +/** + * alloc_cmd_buf - allocate a dma buffer for API CMD command + * @chain: the API CMD specific chain for the cmd + * @cell: the cell in the HW for the cmd + * @cell_idx: the index of the cell + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_cmd_buf(struct hinic_api_cmd_chain *chain, + struct hinic_api_cmd_cell *cell, int cell_idx) +{ + struct hinic_api_cmd_cell_ctxt *cell_ctxt; + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + dma_addr_t cmd_paddr; + u8 *cmd_vaddr; + int err = 0; + + cmd_vaddr = dma_zalloc_coherent(&pdev->dev, API_CMD_BUF_SIZE, + &cmd_paddr, GFP_KERNEL); + if (!cmd_vaddr) { + dev_err(&pdev->dev, "Failed to allocate API CMD DMA memory\n"); + return -ENOMEM; + } + + cell_ctxt = &chain->cell_ctxt[cell_idx]; + + cell_ctxt->api_cmd_vaddr = cmd_vaddr; + cell_ctxt->api_cmd_paddr = cmd_paddr; + + /* set the cmd DMA address in the cell */ + switch (chain->chain_type) { + case HINIC_API_CMD_WRITE_TO_MGMT_CPU: + /* The data in the HW should be in Big Endian Format */ + cell->write.hw_cmd_paddr = cpu_to_be64(cmd_paddr); + break; + + default: + dev_err(&pdev->dev, "Unsupported API CMD chain type\n"); + free_cmd_buf(chain, cell_idx); + err = -EINVAL; + break; + } + + return err; +} + +/** + * api_cmd_create_cell - create API CMD cell for specific chain + * @chain: the API CMD specific chain to create its cell + * @cell_idx: the index of the cell to create + * @pre_node: previous cell + * @node_vaddr: the returned virt addr of the cell + * + * Return 0 - Success, negative - Failure + **/ +static int api_cmd_create_cell(struct hinic_api_cmd_chain *chain, + int cell_idx, + struct hinic_api_cmd_cell *pre_node, + struct hinic_api_cmd_cell **node_vaddr) +{ + struct hinic_api_cmd_cell_ctxt *cell_ctxt; + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_api_cmd_cell *node; + dma_addr_t node_paddr; + int err; + + node = dma_zalloc_coherent(&pdev->dev, chain->cell_size, + &node_paddr, GFP_KERNEL); + if (!node) { + dev_err(&pdev->dev, "Failed to allocate dma API CMD cell\n"); + return -ENOMEM; + } + + node->read.hw_wb_resp_paddr = 0; + + cell_ctxt = &chain->cell_ctxt[cell_idx]; + cell_ctxt->cell_vaddr = node; + cell_ctxt->cell_paddr = node_paddr; + + if (!pre_node) { + chain->head_cell_paddr = node_paddr; + chain->head_node = node; + } else { + /* The data in the HW should be in Big Endian Format */ + pre_node->next_cell_paddr = cpu_to_be64(node_paddr); + } + + switch (chain->chain_type) { + case HINIC_API_CMD_WRITE_TO_MGMT_CPU: + err = alloc_cmd_buf(chain, node, cell_idx); + if (err) { + dev_err(&pdev->dev, "Failed to allocate cmd buffer\n"); + goto err_alloc_cmd_buf; + } + break; + + default: + dev_err(&pdev->dev, "Unsupported API CMD chain type\n"); + err = -EINVAL; + goto err_alloc_cmd_buf; + } + + *node_vaddr = node; + return 0; + +err_alloc_cmd_buf: + dma_free_coherent(&pdev->dev, chain->cell_size, node, node_paddr); + return err; +} + +/** + * api_cmd_destroy_cell - destroy API CMD cell of specific chain + * @chain: the API CMD specific chain to destroy its cell + * @cell_idx: the cell to destroy + **/ +static void api_cmd_destroy_cell(struct hinic_api_cmd_chain *chain, + int cell_idx) +{ + struct hinic_api_cmd_cell_ctxt *cell_ctxt; + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_api_cmd_cell *node; + dma_addr_t node_paddr; + size_t node_size; + + cell_ctxt = &chain->cell_ctxt[cell_idx]; + + node = cell_ctxt->cell_vaddr; + node_paddr = cell_ctxt->cell_paddr; + node_size = chain->cell_size; + + if (cell_ctxt->api_cmd_vaddr) { + switch (chain->chain_type) { + case HINIC_API_CMD_WRITE_TO_MGMT_CPU: + free_cmd_buf(chain, cell_idx); + break; + default: + dev_err(&pdev->dev, "Unsupported API CMD chain type\n"); + break; + } + + dma_free_coherent(&pdev->dev, node_size, node, + node_paddr); + } +} + +/** + * api_cmd_destroy_cells - destroy API CMD cells of specific chain + * @chain: the API CMD specific chain to destroy its cells + * @num_cells: number of cells to destroy + **/ +static void api_cmd_destroy_cells(struct hinic_api_cmd_chain *chain, + int num_cells) +{ + int cell_idx; + + for (cell_idx = 0; cell_idx < num_cells; cell_idx++) + api_cmd_destroy_cell(chain, cell_idx); +} + +/** + * api_cmd_create_cells - create API CMD cells for specific chain + * @chain: the API CMD specific chain + * + * Return 0 - Success, negative - Failure + **/ +static int api_cmd_create_cells(struct hinic_api_cmd_chain *chain) +{ + struct hinic_api_cmd_cell *node = NULL, *pre_node = NULL; + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + int err, cell_idx; + + for (cell_idx = 0; cell_idx < chain->num_cells; cell_idx++) { + err = api_cmd_create_cell(chain, cell_idx, pre_node, &node); + if (err) { + dev_err(&pdev->dev, "Failed to create API CMD cell\n"); + goto err_create_cell; + } + + pre_node = node; + } + + /* set the Final node to point on the start */ + node->next_cell_paddr = cpu_to_be64(chain->head_cell_paddr); + + /* set the current node to be the head */ + chain->curr_node = chain->head_node; + return 0; + +err_create_cell: + api_cmd_destroy_cells(chain, cell_idx); + return err; +} + +/** + * api_chain_init - initialize API CMD specific chain + * @chain: the API CMD specific chain to initialize + * @attr: attributes to set in the chain + * + * Return 0 - Success, negative - Failure + **/ +static int api_chain_init(struct hinic_api_cmd_chain *chain, + struct hinic_api_cmd_chain_attr *attr) +{ + struct hinic_hwif *hwif = attr->hwif; + struct pci_dev *pdev = hwif->pdev; + size_t cell_ctxt_size; + + chain->hwif = hwif; + chain->chain_type = attr->chain_type; + chain->num_cells = attr->num_cells; + chain->cell_size = attr->cell_size; + + chain->prod_idx = 0; + chain->cons_idx = 0; + + sema_init(&chain->sem, 1); + + cell_ctxt_size = chain->num_cells * sizeof(*chain->cell_ctxt); + chain->cell_ctxt = devm_kzalloc(&pdev->dev, cell_ctxt_size, GFP_KERNEL); + if (!chain->cell_ctxt) + return -ENOMEM; + + chain->wb_status = dma_zalloc_coherent(&pdev->dev, + sizeof(*chain->wb_status), + &chain->wb_status_paddr, + GFP_KERNEL); + if (!chain->wb_status) { + dev_err(&pdev->dev, "Failed to allocate DMA wb status\n"); + return -ENOMEM; + } + + return 0; +} + +/** + * api_chain_free - free API CMD specific chain + * @chain: the API CMD specific chain to free + **/ +static void api_chain_free(struct hinic_api_cmd_chain *chain) +{ + struct hinic_hwif *hwif = chain->hwif; + struct pci_dev *pdev = hwif->pdev; + + dma_free_coherent(&pdev->dev, sizeof(*chain->wb_status), + chain->wb_status, chain->wb_status_paddr); +} + +/** + * api_cmd_create_chain - create API CMD specific chain + * @attr: attributes to set the chain + * + * Return the created chain + **/ +static struct hinic_api_cmd_chain * + api_cmd_create_chain(struct hinic_api_cmd_chain_attr *attr) +{ + struct hinic_hwif *hwif = attr->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_api_cmd_chain *chain; + int err; + + if (attr->num_cells & (attr->num_cells - 1)) { + dev_err(&pdev->dev, "Invalid number of cells, must be power of 2\n"); + return ERR_PTR(-EINVAL); + } + + chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL); + if (!chain) + return ERR_PTR(-ENOMEM); + + err = api_chain_init(chain, attr); + if (err) { + dev_err(&pdev->dev, "Failed to initialize chain\n"); + return ERR_PTR(err); + } + + err = api_cmd_create_cells(chain); + if (err) { + dev_err(&pdev->dev, "Failed to create cells for API CMD chain\n"); + goto err_create_cells; + } + + err = api_cmd_chain_hw_init(chain); + if (err) { + dev_err(&pdev->dev, "Failed to initialize chain HW\n"); + goto err_chain_hw_init; + } + + return chain; + +err_chain_hw_init: + api_cmd_destroy_cells(chain, chain->num_cells); + +err_create_cells: + api_chain_free(chain); + return ERR_PTR(err); +} + +/** + * api_cmd_destroy_chain - destroy API CMD specific chain + * @chain: the API CMD specific chain to destroy + **/ +static void api_cmd_destroy_chain(struct hinic_api_cmd_chain *chain) +{ + api_cmd_chain_hw_clean(chain); + api_cmd_destroy_cells(chain, chain->num_cells); + api_chain_free(chain); +} + +/** + * hinic_api_cmd_init - Initialize all the API CMD chains + * @chain: the API CMD chains that are initialized + * @hwif: the hardware interface of a pci function device + * + * Return 0 - Success, negative - Failure + **/ +int hinic_api_cmd_init(struct hinic_api_cmd_chain **chain, + struct hinic_hwif *hwif) +{ + enum hinic_api_cmd_chain_type type, chain_type; + struct hinic_api_cmd_chain_attr attr; + struct pci_dev *pdev = hwif->pdev; + size_t hw_cell_sz; + int err; + + hw_cell_sz = sizeof(struct hinic_api_cmd_cell); + + attr.hwif = hwif; + attr.num_cells = API_CHAIN_NUM_CELLS; + attr.cell_size = API_CMD_CELL_SIZE(hw_cell_sz); + + chain_type = HINIC_API_CMD_WRITE_TO_MGMT_CPU; + for ( ; chain_type < HINIC_API_CMD_MAX; chain_type++) { + attr.chain_type = chain_type; + + if (chain_type != HINIC_API_CMD_WRITE_TO_MGMT_CPU) + continue; + + chain[chain_type] = api_cmd_create_chain(&attr); + if (IS_ERR(chain[chain_type])) { + dev_err(&pdev->dev, "Failed to create chain %d\n", + chain_type); + err = PTR_ERR(chain[chain_type]); + goto err_create_chain; + } + } + + return 0; + +err_create_chain: + type = HINIC_API_CMD_WRITE_TO_MGMT_CPU; + for ( ; type < chain_type; type++) { + if (type != HINIC_API_CMD_WRITE_TO_MGMT_CPU) + continue; + + api_cmd_destroy_chain(chain[type]); + } + + return err; +} + +/** + * hinic_api_cmd_free - free the API CMD chains + * @chain: the API CMD chains that are freed + **/ +void hinic_api_cmd_free(struct hinic_api_cmd_chain **chain) +{ + enum hinic_api_cmd_chain_type chain_type; + + chain_type = HINIC_API_CMD_WRITE_TO_MGMT_CPU; + for ( ; chain_type < HINIC_API_CMD_MAX; chain_type++) { + if (chain_type != HINIC_API_CMD_WRITE_TO_MGMT_CPU) + continue; + + api_cmd_destroy_chain(chain[chain_type]); + } +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h new file mode 100644 index 000000000000..31b94d5d47f7 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.h @@ -0,0 +1,208 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_API_CMD_H +#define HINIC_HW_API_CMD_H + +#include <linux/types.h> +#include <linux/semaphore.h> + +#include "hinic_hw_if.h" + +#define HINIC_API_CMD_PI_IDX_SHIFT 0 + +#define HINIC_API_CMD_PI_IDX_MASK 0xFFFFFF + +#define HINIC_API_CMD_PI_SET(val, member) \ + (((u32)(val) & HINIC_API_CMD_PI_##member##_MASK) << \ + HINIC_API_CMD_PI_##member##_SHIFT) + +#define HINIC_API_CMD_PI_CLEAR(val, member) \ + ((val) & (~(HINIC_API_CMD_PI_##member##_MASK \ + << HINIC_API_CMD_PI_##member##_SHIFT))) + +#define HINIC_API_CMD_CHAIN_REQ_RESTART_SHIFT 1 + +#define HINIC_API_CMD_CHAIN_REQ_RESTART_MASK 0x1 + +#define HINIC_API_CMD_CHAIN_REQ_SET(val, member) \ + (((u32)(val) & HINIC_API_CMD_CHAIN_REQ_##member##_MASK) << \ + HINIC_API_CMD_CHAIN_REQ_##member##_SHIFT) + +#define HINIC_API_CMD_CHAIN_REQ_GET(val, member) \ + (((val) >> HINIC_API_CMD_CHAIN_REQ_##member##_SHIFT) & \ + HINIC_API_CMD_CHAIN_REQ_##member##_MASK) + +#define HINIC_API_CMD_CHAIN_REQ_CLEAR(val, member) \ + ((val) & (~(HINIC_API_CMD_CHAIN_REQ_##member##_MASK \ + << HINIC_API_CMD_CHAIN_REQ_##member##_SHIFT))) + +#define HINIC_API_CMD_CHAIN_CTRL_RESTART_WB_STAT_SHIFT 1 +#define HINIC_API_CMD_CHAIN_CTRL_XOR_ERR_SHIFT 2 +#define HINIC_API_CMD_CHAIN_CTRL_AEQE_EN_SHIFT 4 +#define HINIC_API_CMD_CHAIN_CTRL_AEQ_ID_SHIFT 8 +#define HINIC_API_CMD_CHAIN_CTRL_XOR_CHK_EN_SHIFT 28 +#define HINIC_API_CMD_CHAIN_CTRL_CELL_SIZE_SHIFT 30 + +#define HINIC_API_CMD_CHAIN_CTRL_RESTART_WB_STAT_MASK 0x1 +#define HINIC_API_CMD_CHAIN_CTRL_XOR_ERR_MASK 0x1 +#define HINIC_API_CMD_CHAIN_CTRL_AEQE_EN_MASK 0x1 +#define HINIC_API_CMD_CHAIN_CTRL_AEQ_ID_MASK 0x3 +#define HINIC_API_CMD_CHAIN_CTRL_XOR_CHK_EN_MASK 0x3 +#define HINIC_API_CMD_CHAIN_CTRL_CELL_SIZE_MASK 0x3 + +#define HINIC_API_CMD_CHAIN_CTRL_SET(val, member) \ + (((u32)(val) & HINIC_API_CMD_CHAIN_CTRL_##member##_MASK) << \ + HINIC_API_CMD_CHAIN_CTRL_##member##_SHIFT) + +#define HINIC_API_CMD_CHAIN_CTRL_CLEAR(val, member) \ + ((val) & (~(HINIC_API_CMD_CHAIN_CTRL_##member##_MASK \ + << HINIC_API_CMD_CHAIN_CTRL_##member##_SHIFT))) + +#define HINIC_API_CMD_CELL_CTRL_DATA_SZ_SHIFT 0 +#define HINIC_API_CMD_CELL_CTRL_RD_DMA_ATTR_SHIFT 16 +#define HINIC_API_CMD_CELL_CTRL_WR_DMA_ATTR_SHIFT 24 +#define HINIC_API_CMD_CELL_CTRL_XOR_CHKSUM_SHIFT 56 + +#define HINIC_API_CMD_CELL_CTRL_DATA_SZ_MASK 0x3F +#define HINIC_API_CMD_CELL_CTRL_RD_DMA_ATTR_MASK 0x3F +#define HINIC_API_CMD_CELL_CTRL_WR_DMA_ATTR_MASK 0x3F +#define HINIC_API_CMD_CELL_CTRL_XOR_CHKSUM_MASK 0xFF + +#define HINIC_API_CMD_CELL_CTRL_SET(val, member) \ + ((((u64)val) & HINIC_API_CMD_CELL_CTRL_##member##_MASK) << \ + HINIC_API_CMD_CELL_CTRL_##member##_SHIFT) + +#define HINIC_API_CMD_DESC_API_TYPE_SHIFT 0 +#define HINIC_API_CMD_DESC_RD_WR_SHIFT 1 +#define HINIC_API_CMD_DESC_MGMT_BYPASS_SHIFT 2 +#define HINIC_API_CMD_DESC_DEST_SHIFT 32 +#define HINIC_API_CMD_DESC_SIZE_SHIFT 40 +#define HINIC_API_CMD_DESC_XOR_CHKSUM_SHIFT 56 + +#define HINIC_API_CMD_DESC_API_TYPE_MASK 0x1 +#define HINIC_API_CMD_DESC_RD_WR_MASK 0x1 +#define HINIC_API_CMD_DESC_MGMT_BYPASS_MASK 0x1 +#define HINIC_API_CMD_DESC_DEST_MASK 0x1F +#define HINIC_API_CMD_DESC_SIZE_MASK 0x7FF +#define HINIC_API_CMD_DESC_XOR_CHKSUM_MASK 0xFF + +#define HINIC_API_CMD_DESC_SET(val, member) \ + ((((u64)val) & HINIC_API_CMD_DESC_##member##_MASK) << \ + HINIC_API_CMD_DESC_##member##_SHIFT) + +#define HINIC_API_CMD_STATUS_HEADER_CHAIN_ID_SHIFT 16 + +#define HINIC_API_CMD_STATUS_HEADER_CHAIN_ID_MASK 0xFF + +#define HINIC_API_CMD_STATUS_HEADER_GET(val, member) \ + (((val) >> HINIC_API_CMD_STATUS_HEADER_##member##_SHIFT) & \ + HINIC_API_CMD_STATUS_HEADER_##member##_MASK) + +#define HINIC_API_CMD_STATUS_CONS_IDX_SHIFT 0 +#define HINIC_API_CMD_STATUS_CHKSUM_ERR_SHIFT 28 + +#define HINIC_API_CMD_STATUS_CONS_IDX_MASK 0xFFFFFF +#define HINIC_API_CMD_STATUS_CHKSUM_ERR_MASK 0x3 + +#define HINIC_API_CMD_STATUS_GET(val, member) \ + (((val) >> HINIC_API_CMD_STATUS_##member##_SHIFT) & \ + HINIC_API_CMD_STATUS_##member##_MASK) + +enum hinic_api_cmd_chain_type { + HINIC_API_CMD_WRITE_TO_MGMT_CPU = 2, + + HINIC_API_CMD_MAX, +}; + +struct hinic_api_cmd_chain_attr { + struct hinic_hwif *hwif; + enum hinic_api_cmd_chain_type chain_type; + + u32 num_cells; + u16 cell_size; +}; + +struct hinic_api_cmd_status { + u64 header; + u32 status; + u32 rsvd0; + u32 rsvd1; + u32 rsvd2; + u64 rsvd3; +}; + +/* HW struct */ +struct hinic_api_cmd_cell { + u64 ctrl; + + /* address is 64 bit in HW struct */ + u64 next_cell_paddr; + + u64 desc; + + /* HW struct */ + union { + struct { + u64 hw_cmd_paddr; + } write; + + struct { + u64 hw_wb_resp_paddr; + u64 hw_cmd_paddr; + } read; + }; +}; + +struct hinic_api_cmd_cell_ctxt { + dma_addr_t cell_paddr; + struct hinic_api_cmd_cell *cell_vaddr; + + dma_addr_t api_cmd_paddr; + u8 *api_cmd_vaddr; +}; + +struct hinic_api_cmd_chain { + struct hinic_hwif *hwif; + enum hinic_api_cmd_chain_type chain_type; + + u32 num_cells; + u16 cell_size; + + /* HW members in 24 bit format */ + u32 prod_idx; + u32 cons_idx; + + struct semaphore sem; + + struct hinic_api_cmd_cell_ctxt *cell_ctxt; + + dma_addr_t wb_status_paddr; + struct hinic_api_cmd_status *wb_status; + + dma_addr_t head_cell_paddr; + struct hinic_api_cmd_cell *head_node; + struct hinic_api_cmd_cell *curr_node; +}; + +int hinic_api_cmd_write(struct hinic_api_cmd_chain *chain, + enum hinic_node_id dest, u8 *cmd, u16 size); + +int hinic_api_cmd_init(struct hinic_api_cmd_chain **chain, + struct hinic_hwif *hwif); + +void hinic_api_cmd_free(struct hinic_api_cmd_chain **chain); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c new file mode 100644 index 000000000000..7d95f0866fb0 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c @@ -0,0 +1,946 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/spinlock.h> +#include <linux/sizes.h> +#include <linux/atomic.h> +#include <linux/log2.h> +#include <linux/io.h> +#include <linux/completion.h> +#include <linux/err.h> +#include <asm/byteorder.h> +#include <asm/barrier.h> + +#include "hinic_common.h" +#include "hinic_hw_if.h" +#include "hinic_hw_eqs.h" +#include "hinic_hw_mgmt.h" +#include "hinic_hw_wqe.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_cmdq.h" +#include "hinic_hw_io.h" +#include "hinic_hw_dev.h" + +#define CMDQ_CEQE_TYPE_SHIFT 0 + +#define CMDQ_CEQE_TYPE_MASK 0x7 + +#define CMDQ_CEQE_GET(val, member) \ + (((val) >> CMDQ_CEQE_##member##_SHIFT) \ + & CMDQ_CEQE_##member##_MASK) + +#define CMDQ_WQE_ERRCODE_VAL_SHIFT 20 + +#define CMDQ_WQE_ERRCODE_VAL_MASK 0xF + +#define CMDQ_WQE_ERRCODE_GET(val, member) \ + (((val) >> CMDQ_WQE_ERRCODE_##member##_SHIFT) \ + & CMDQ_WQE_ERRCODE_##member##_MASK) + +#define CMDQ_DB_PI_OFF(pi) (((u16)LOWER_8_BITS(pi)) << 3) + +#define CMDQ_DB_ADDR(db_base, pi) ((db_base) + CMDQ_DB_PI_OFF(pi)) + +#define CMDQ_WQE_HEADER(wqe) ((struct hinic_cmdq_header *)(wqe)) + +#define CMDQ_WQE_COMPLETED(ctrl_info) \ + HINIC_CMDQ_CTRL_GET(ctrl_info, HW_BUSY_BIT) + +#define FIRST_DATA_TO_WRITE_LAST sizeof(u64) + +#define CMDQ_DB_OFF SZ_2K + +#define CMDQ_WQEBB_SIZE 64 +#define CMDQ_WQE_SIZE 64 +#define CMDQ_DEPTH SZ_4K + +#define CMDQ_WQ_PAGE_SIZE SZ_4K + +#define WQE_LCMD_SIZE 64 +#define WQE_SCMD_SIZE 64 + +#define COMPLETE_LEN 3 + +#define CMDQ_TIMEOUT 1000 + +#define CMDQ_PFN(addr, page_size) ((addr) >> (ilog2(page_size))) + +#define cmdq_to_cmdqs(cmdq) container_of((cmdq) - (cmdq)->cmdq_type, \ + struct hinic_cmdqs, cmdq[0]) + +#define cmdqs_to_func_to_io(cmdqs) container_of(cmdqs, \ + struct hinic_func_to_io, \ + cmdqs) + +enum cmdq_wqe_type { + WQE_LCMD_TYPE = 0, + WQE_SCMD_TYPE = 1, +}; + +enum completion_format { + COMPLETE_DIRECT = 0, + COMPLETE_SGE = 1, +}; + +enum data_format { + DATA_SGE = 0, + DATA_DIRECT = 1, +}; + +enum bufdesc_len { + BUFDESC_LCMD_LEN = 2, /* 16 bytes - 2(8 byte unit) */ + BUFDESC_SCMD_LEN = 3, /* 24 bytes - 3(8 byte unit) */ +}; + +enum ctrl_sect_len { + CTRL_SECT_LEN = 1, /* 4 bytes (ctrl) - 1(8 byte unit) */ + CTRL_DIRECT_SECT_LEN = 2, /* 12 bytes (ctrl + rsvd) - 2(8 byte unit) */ +}; + +enum cmdq_scmd_type { + CMDQ_SET_ARM_CMD = 2, +}; + +enum cmdq_cmd_type { + CMDQ_CMD_SYNC_DIRECT_RESP = 0, + CMDQ_CMD_SYNC_SGE_RESP = 1, +}; + +enum completion_request { + NO_CEQ = 0, + CEQ_SET = 1, +}; + +/** + * hinic_alloc_cmdq_buf - alloc buffer for sending command + * @cmdqs: the cmdqs + * @cmdq_buf: the buffer returned in this struct + * + * Return 0 - Success, negative - Failure + **/ +int hinic_alloc_cmdq_buf(struct hinic_cmdqs *cmdqs, + struct hinic_cmdq_buf *cmdq_buf) +{ + struct hinic_hwif *hwif = cmdqs->hwif; + struct pci_dev *pdev = hwif->pdev; + + cmdq_buf->buf = pci_pool_alloc(cmdqs->cmdq_buf_pool, GFP_KERNEL, + &cmdq_buf->dma_addr); + if (!cmdq_buf->buf) { + dev_err(&pdev->dev, "Failed to allocate cmd from the pool\n"); + return -ENOMEM; + } + + return 0; +} + +/** + * hinic_free_cmdq_buf - free buffer + * @cmdqs: the cmdqs + * @cmdq_buf: the buffer to free that is in this struct + **/ +void hinic_free_cmdq_buf(struct hinic_cmdqs *cmdqs, + struct hinic_cmdq_buf *cmdq_buf) +{ + pci_pool_free(cmdqs->cmdq_buf_pool, cmdq_buf->buf, cmdq_buf->dma_addr); +} + +static unsigned int cmdq_wqe_size_from_bdlen(enum bufdesc_len len) +{ + unsigned int wqe_size = 0; + + switch (len) { + case BUFDESC_LCMD_LEN: + wqe_size = WQE_LCMD_SIZE; + break; + case BUFDESC_SCMD_LEN: + wqe_size = WQE_SCMD_SIZE; + break; + } + + return wqe_size; +} + +static void cmdq_set_sge_completion(struct hinic_cmdq_completion *completion, + struct hinic_cmdq_buf *buf_out) +{ + struct hinic_sge_resp *sge_resp = &completion->sge_resp; + + hinic_set_sge(&sge_resp->sge, buf_out->dma_addr, buf_out->size); +} + +static void cmdq_prepare_wqe_ctrl(struct hinic_cmdq_wqe *wqe, int wrapped, + enum hinic_cmd_ack_type ack_type, + enum hinic_mod_type mod, u8 cmd, u16 prod_idx, + enum completion_format complete_format, + enum data_format data_format, + enum bufdesc_len buf_len) +{ + struct hinic_cmdq_wqe_lcmd *wqe_lcmd; + struct hinic_cmdq_wqe_scmd *wqe_scmd; + enum ctrl_sect_len ctrl_len; + struct hinic_ctrl *ctrl; + u32 saved_data; + + if (data_format == DATA_SGE) { + wqe_lcmd = &wqe->wqe_lcmd; + + wqe_lcmd->status.status_info = 0; + ctrl = &wqe_lcmd->ctrl; + ctrl_len = CTRL_SECT_LEN; + } else { + wqe_scmd = &wqe->direct_wqe.wqe_scmd; + + wqe_scmd->status.status_info = 0; + ctrl = &wqe_scmd->ctrl; + ctrl_len = CTRL_DIRECT_SECT_LEN; + } + + ctrl->ctrl_info = HINIC_CMDQ_CTRL_SET(prod_idx, PI) | + HINIC_CMDQ_CTRL_SET(cmd, CMD) | + HINIC_CMDQ_CTRL_SET(mod, MOD) | + HINIC_CMDQ_CTRL_SET(ack_type, ACK_TYPE); + + CMDQ_WQE_HEADER(wqe)->header_info = + HINIC_CMDQ_WQE_HEADER_SET(buf_len, BUFDESC_LEN) | + HINIC_CMDQ_WQE_HEADER_SET(complete_format, COMPLETE_FMT) | + HINIC_CMDQ_WQE_HEADER_SET(data_format, DATA_FMT) | + HINIC_CMDQ_WQE_HEADER_SET(CEQ_SET, COMPLETE_REQ) | + HINIC_CMDQ_WQE_HEADER_SET(COMPLETE_LEN, COMPLETE_SECT_LEN) | + HINIC_CMDQ_WQE_HEADER_SET(ctrl_len, CTRL_LEN) | + HINIC_CMDQ_WQE_HEADER_SET(wrapped, TOGGLED_WRAPPED); + + saved_data = CMDQ_WQE_HEADER(wqe)->saved_data; + saved_data = HINIC_SAVED_DATA_CLEAR(saved_data, ARM); + + if ((cmd == CMDQ_SET_ARM_CMD) && (mod == HINIC_MOD_COMM)) + CMDQ_WQE_HEADER(wqe)->saved_data |= + HINIC_SAVED_DATA_SET(1, ARM); + else + CMDQ_WQE_HEADER(wqe)->saved_data = saved_data; +} + +static void cmdq_set_lcmd_bufdesc(struct hinic_cmdq_wqe_lcmd *wqe_lcmd, + struct hinic_cmdq_buf *buf_in) +{ + hinic_set_sge(&wqe_lcmd->buf_desc.sge, buf_in->dma_addr, buf_in->size); +} + +static void cmdq_set_direct_wqe_data(struct hinic_cmdq_direct_wqe *wqe, + void *buf_in, u32 in_size) +{ + struct hinic_cmdq_wqe_scmd *wqe_scmd = &wqe->wqe_scmd; + + wqe_scmd->buf_desc.buf_len = in_size; + memcpy(wqe_scmd->buf_desc.data, buf_in, in_size); +} + +static void cmdq_set_lcmd_wqe(struct hinic_cmdq_wqe *wqe, + enum cmdq_cmd_type cmd_type, + struct hinic_cmdq_buf *buf_in, + struct hinic_cmdq_buf *buf_out, int wrapped, + enum hinic_cmd_ack_type ack_type, + enum hinic_mod_type mod, u8 cmd, u16 prod_idx) +{ + struct hinic_cmdq_wqe_lcmd *wqe_lcmd = &wqe->wqe_lcmd; + enum completion_format complete_format; + + switch (cmd_type) { + case CMDQ_CMD_SYNC_SGE_RESP: + complete_format = COMPLETE_SGE; + cmdq_set_sge_completion(&wqe_lcmd->completion, buf_out); + break; + case CMDQ_CMD_SYNC_DIRECT_RESP: + complete_format = COMPLETE_DIRECT; + wqe_lcmd->completion.direct_resp = 0; + break; + } + + cmdq_prepare_wqe_ctrl(wqe, wrapped, ack_type, mod, cmd, + prod_idx, complete_format, DATA_SGE, + BUFDESC_LCMD_LEN); + + cmdq_set_lcmd_bufdesc(wqe_lcmd, buf_in); +} + +static void cmdq_set_direct_wqe(struct hinic_cmdq_wqe *wqe, + enum cmdq_cmd_type cmd_type, + void *buf_in, u16 in_size, + struct hinic_cmdq_buf *buf_out, int wrapped, + enum hinic_cmd_ack_type ack_type, + enum hinic_mod_type mod, u8 cmd, u16 prod_idx) +{ + struct hinic_cmdq_direct_wqe *direct_wqe = &wqe->direct_wqe; + enum completion_format complete_format; + struct hinic_cmdq_wqe_scmd *wqe_scmd; + + wqe_scmd = &direct_wqe->wqe_scmd; + + switch (cmd_type) { + case CMDQ_CMD_SYNC_SGE_RESP: + complete_format = COMPLETE_SGE; + cmdq_set_sge_completion(&wqe_scmd->completion, buf_out); + break; + case CMDQ_CMD_SYNC_DIRECT_RESP: + complete_format = COMPLETE_DIRECT; + wqe_scmd->completion.direct_resp = 0; + break; + } + + cmdq_prepare_wqe_ctrl(wqe, wrapped, ack_type, mod, cmd, prod_idx, + complete_format, DATA_DIRECT, BUFDESC_SCMD_LEN); + + cmdq_set_direct_wqe_data(direct_wqe, buf_in, in_size); +} + +static void cmdq_wqe_fill(void *dst, void *src) +{ + memcpy(dst + FIRST_DATA_TO_WRITE_LAST, src + FIRST_DATA_TO_WRITE_LAST, + CMDQ_WQE_SIZE - FIRST_DATA_TO_WRITE_LAST); + + wmb(); /* The first 8 bytes should be written last */ + + *(u64 *)dst = *(u64 *)src; +} + +static void cmdq_fill_db(u32 *db_info, + enum hinic_cmdq_type cmdq_type, u16 prod_idx) +{ + *db_info = HINIC_CMDQ_DB_INFO_SET(UPPER_8_BITS(prod_idx), HI_PROD_IDX) | + HINIC_CMDQ_DB_INFO_SET(HINIC_CTRL_PATH, PATH) | + HINIC_CMDQ_DB_INFO_SET(cmdq_type, CMDQ_TYPE) | + HINIC_CMDQ_DB_INFO_SET(HINIC_DB_CMDQ_TYPE, DB_TYPE); +} + +static void cmdq_set_db(struct hinic_cmdq *cmdq, + enum hinic_cmdq_type cmdq_type, u16 prod_idx) +{ + u32 db_info; + + cmdq_fill_db(&db_info, cmdq_type, prod_idx); + + /* The data that is written to HW should be in Big Endian Format */ + db_info = cpu_to_be32(db_info); + + wmb(); /* write all before the doorbell */ + + writel(db_info, CMDQ_DB_ADDR(cmdq->db_base, prod_idx)); +} + +static int cmdq_sync_cmd_direct_resp(struct hinic_cmdq *cmdq, + enum hinic_mod_type mod, u8 cmd, + struct hinic_cmdq_buf *buf_in, + u64 *resp) +{ + struct hinic_cmdq_wqe *curr_cmdq_wqe, cmdq_wqe; + u16 curr_prod_idx, next_prod_idx; + int errcode, wrapped, num_wqebbs; + struct hinic_wq *wq = cmdq->wq; + struct hinic_hw_wqe *hw_wqe; + struct completion done; + + /* Keep doorbell index correct. bh - for tasklet(ceq). */ + spin_lock_bh(&cmdq->cmdq_lock); + + /* WQE_SIZE = WQEBB_SIZE, we will get the wq element and not shadow*/ + hw_wqe = hinic_get_wqe(wq, WQE_LCMD_SIZE, &curr_prod_idx); + if (IS_ERR(hw_wqe)) { + spin_unlock_bh(&cmdq->cmdq_lock); + return -EBUSY; + } + + curr_cmdq_wqe = &hw_wqe->cmdq_wqe; + + wrapped = cmdq->wrapped; + + num_wqebbs = ALIGN(WQE_LCMD_SIZE, wq->wqebb_size) / wq->wqebb_size; + next_prod_idx = curr_prod_idx + num_wqebbs; + if (next_prod_idx >= wq->q_depth) { + cmdq->wrapped = !cmdq->wrapped; + next_prod_idx -= wq->q_depth; + } + + cmdq->errcode[curr_prod_idx] = &errcode; + + init_completion(&done); + cmdq->done[curr_prod_idx] = &done; + + cmdq_set_lcmd_wqe(&cmdq_wqe, CMDQ_CMD_SYNC_DIRECT_RESP, buf_in, NULL, + wrapped, HINIC_CMD_ACK_TYPE_CMDQ, mod, cmd, + curr_prod_idx); + + /* The data that is written to HW should be in Big Endian Format */ + hinic_cpu_to_be32(&cmdq_wqe, WQE_LCMD_SIZE); + + /* CMDQ WQE is not shadow, therefore wqe will be written to wq */ + cmdq_wqe_fill(curr_cmdq_wqe, &cmdq_wqe); + + cmdq_set_db(cmdq, HINIC_CMDQ_SYNC, next_prod_idx); + + spin_unlock_bh(&cmdq->cmdq_lock); + + if (!wait_for_completion_timeout(&done, CMDQ_TIMEOUT)) { + spin_lock_bh(&cmdq->cmdq_lock); + + if (cmdq->errcode[curr_prod_idx] == &errcode) + cmdq->errcode[curr_prod_idx] = NULL; + + if (cmdq->done[curr_prod_idx] == &done) + cmdq->done[curr_prod_idx] = NULL; + + spin_unlock_bh(&cmdq->cmdq_lock); + + return -ETIMEDOUT; + } + + smp_rmb(); /* read error code after completion */ + + if (resp) { + struct hinic_cmdq_wqe_lcmd *wqe_lcmd = &curr_cmdq_wqe->wqe_lcmd; + + *resp = cpu_to_be64(wqe_lcmd->completion.direct_resp); + } + + if (errcode != 0) + return -EFAULT; + + return 0; +} + +static int cmdq_set_arm_bit(struct hinic_cmdq *cmdq, void *buf_in, + u16 in_size) +{ + struct hinic_cmdq_wqe *curr_cmdq_wqe, cmdq_wqe; + u16 curr_prod_idx, next_prod_idx; + struct hinic_wq *wq = cmdq->wq; + struct hinic_hw_wqe *hw_wqe; + int wrapped, num_wqebbs; + + /* Keep doorbell index correct */ + spin_lock(&cmdq->cmdq_lock); + + /* WQE_SIZE = WQEBB_SIZE, we will get the wq element and not shadow*/ + hw_wqe = hinic_get_wqe(wq, WQE_SCMD_SIZE, &curr_prod_idx); + if (IS_ERR(hw_wqe)) { + spin_unlock(&cmdq->cmdq_lock); + return -EBUSY; + } + + curr_cmdq_wqe = &hw_wqe->cmdq_wqe; + + wrapped = cmdq->wrapped; + + num_wqebbs = ALIGN(WQE_SCMD_SIZE, wq->wqebb_size) / wq->wqebb_size; + next_prod_idx = curr_prod_idx + num_wqebbs; + if (next_prod_idx >= wq->q_depth) { + cmdq->wrapped = !cmdq->wrapped; + next_prod_idx -= wq->q_depth; + } + + cmdq_set_direct_wqe(&cmdq_wqe, CMDQ_CMD_SYNC_DIRECT_RESP, buf_in, + in_size, NULL, wrapped, HINIC_CMD_ACK_TYPE_CMDQ, + HINIC_MOD_COMM, CMDQ_SET_ARM_CMD, curr_prod_idx); + + /* The data that is written to HW should be in Big Endian Format */ + hinic_cpu_to_be32(&cmdq_wqe, WQE_SCMD_SIZE); + + /* cmdq wqe is not shadow, therefore wqe will be written to wq */ + cmdq_wqe_fill(curr_cmdq_wqe, &cmdq_wqe); + + cmdq_set_db(cmdq, HINIC_CMDQ_SYNC, next_prod_idx); + + spin_unlock(&cmdq->cmdq_lock); + return 0; +} + +static int cmdq_params_valid(struct hinic_cmdq_buf *buf_in) +{ + if (buf_in->size > HINIC_CMDQ_MAX_DATA_SIZE) + return -EINVAL; + + return 0; +} + +/** + * hinic_cmdq_direct_resp - send command with direct data as resp + * @cmdqs: the cmdqs + * @mod: module on the card that will handle the command + * @cmd: the command + * @buf_in: the buffer for the command + * @resp: the response to return + * + * Return 0 - Success, negative - Failure + **/ +int hinic_cmdq_direct_resp(struct hinic_cmdqs *cmdqs, + enum hinic_mod_type mod, u8 cmd, + struct hinic_cmdq_buf *buf_in, u64 *resp) +{ + struct hinic_hwif *hwif = cmdqs->hwif; + struct pci_dev *pdev = hwif->pdev; + int err; + + err = cmdq_params_valid(buf_in); + if (err) { + dev_err(&pdev->dev, "Invalid CMDQ parameters\n"); + return err; + } + + return cmdq_sync_cmd_direct_resp(&cmdqs->cmdq[HINIC_CMDQ_SYNC], + mod, cmd, buf_in, resp); +} + +/** + * hinic_set_arm_bit - set arm bit for enable interrupt again + * @cmdqs: the cmdqs + * @q_type: type of queue to set the arm bit for + * @q_id: the queue number + * + * Return 0 - Success, negative - Failure + **/ +int hinic_set_arm_bit(struct hinic_cmdqs *cmdqs, + enum hinic_set_arm_qtype q_type, u32 q_id) +{ + struct hinic_cmdq *cmdq = &cmdqs->cmdq[HINIC_CMDQ_SYNC]; + struct hinic_hwif *hwif = cmdqs->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_cmdq_arm_bit arm_bit; + int err; + + arm_bit.q_type = q_type; + arm_bit.q_id = q_id; + + err = cmdq_set_arm_bit(cmdq, &arm_bit, sizeof(arm_bit)); + if (err) { + dev_err(&pdev->dev, "Failed to set arm for qid %d\n", q_id); + return err; + } + + return 0; +} + +static void clear_wqe_complete_bit(struct hinic_cmdq *cmdq, + struct hinic_cmdq_wqe *wqe) +{ + u32 header_info = be32_to_cpu(CMDQ_WQE_HEADER(wqe)->header_info); + unsigned int bufdesc_len, wqe_size; + struct hinic_ctrl *ctrl; + + bufdesc_len = HINIC_CMDQ_WQE_HEADER_GET(header_info, BUFDESC_LEN); + wqe_size = cmdq_wqe_size_from_bdlen(bufdesc_len); + if (wqe_size == WQE_LCMD_SIZE) { + struct hinic_cmdq_wqe_lcmd *wqe_lcmd = &wqe->wqe_lcmd; + + ctrl = &wqe_lcmd->ctrl; + } else { + struct hinic_cmdq_direct_wqe *direct_wqe = &wqe->direct_wqe; + struct hinic_cmdq_wqe_scmd *wqe_scmd; + + wqe_scmd = &direct_wqe->wqe_scmd; + ctrl = &wqe_scmd->ctrl; + } + + /* clear HW busy bit */ + ctrl->ctrl_info = 0; + + wmb(); /* verify wqe is clear */ +} + +/** + * cmdq_arm_ceq_handler - cmdq completion event handler for arm command + * @cmdq: the cmdq of the arm command + * @wqe: the wqe of the arm command + * + * Return 0 - Success, negative - Failure + **/ +static int cmdq_arm_ceq_handler(struct hinic_cmdq *cmdq, + struct hinic_cmdq_wqe *wqe) +{ + struct hinic_cmdq_direct_wqe *direct_wqe = &wqe->direct_wqe; + struct hinic_cmdq_wqe_scmd *wqe_scmd; + struct hinic_ctrl *ctrl; + u32 ctrl_info; + + wqe_scmd = &direct_wqe->wqe_scmd; + ctrl = &wqe_scmd->ctrl; + ctrl_info = be32_to_cpu(ctrl->ctrl_info); + + /* HW should toggle the HW BUSY BIT */ + if (!CMDQ_WQE_COMPLETED(ctrl_info)) + return -EBUSY; + + clear_wqe_complete_bit(cmdq, wqe); + + hinic_put_wqe(cmdq->wq, WQE_SCMD_SIZE); + return 0; +} + +static void cmdq_update_errcode(struct hinic_cmdq *cmdq, u16 prod_idx, + int errcode) +{ + if (cmdq->errcode[prod_idx]) + *cmdq->errcode[prod_idx] = errcode; +} + +/** + * cmdq_arm_ceq_handler - cmdq completion event handler for sync command + * @cmdq: the cmdq of the command + * @cons_idx: the consumer index to update the error code for + * @errcode: the error code + **/ +static void cmdq_sync_cmd_handler(struct hinic_cmdq *cmdq, u16 cons_idx, + int errcode) +{ + u16 prod_idx = cons_idx; + + spin_lock(&cmdq->cmdq_lock); + cmdq_update_errcode(cmdq, prod_idx, errcode); + + wmb(); /* write all before update for the command request */ + + if (cmdq->done[prod_idx]) + complete(cmdq->done[prod_idx]); + spin_unlock(&cmdq->cmdq_lock); +} + +static int cmdq_cmd_ceq_handler(struct hinic_cmdq *cmdq, u16 ci, + struct hinic_cmdq_wqe *cmdq_wqe) +{ + struct hinic_cmdq_wqe_lcmd *wqe_lcmd = &cmdq_wqe->wqe_lcmd; + struct hinic_status *status = &wqe_lcmd->status; + struct hinic_ctrl *ctrl = &wqe_lcmd->ctrl; + int errcode; + + if (!CMDQ_WQE_COMPLETED(be32_to_cpu(ctrl->ctrl_info))) + return -EBUSY; + + errcode = CMDQ_WQE_ERRCODE_GET(be32_to_cpu(status->status_info), VAL); + + cmdq_sync_cmd_handler(cmdq, ci, errcode); + + clear_wqe_complete_bit(cmdq, cmdq_wqe); + hinic_put_wqe(cmdq->wq, WQE_LCMD_SIZE); + return 0; +} + +/** + * cmdq_ceq_handler - cmdq completion event handler + * @handle: private data for the handler(cmdqs) + * @ceqe_data: ceq element data + **/ +static void cmdq_ceq_handler(void *handle, u32 ceqe_data) +{ + enum hinic_cmdq_type cmdq_type = CMDQ_CEQE_GET(ceqe_data, TYPE); + struct hinic_cmdqs *cmdqs = (struct hinic_cmdqs *)handle; + struct hinic_cmdq *cmdq = &cmdqs->cmdq[cmdq_type]; + struct hinic_cmdq_header *header; + struct hinic_hw_wqe *hw_wqe; + int err, set_arm = 0; + u32 saved_data; + u16 ci; + + /* Read the smallest wqe size for getting wqe size */ + while ((hw_wqe = hinic_read_wqe(cmdq->wq, WQE_SCMD_SIZE, &ci))) { + if (IS_ERR(hw_wqe)) + break; + + header = CMDQ_WQE_HEADER(&hw_wqe->cmdq_wqe); + saved_data = be32_to_cpu(header->saved_data); + + if (HINIC_SAVED_DATA_GET(saved_data, ARM)) { + /* arm_bit was set until here */ + set_arm = 0; + + if (cmdq_arm_ceq_handler(cmdq, &hw_wqe->cmdq_wqe)) + break; + } else { + set_arm = 1; + + hw_wqe = hinic_read_wqe(cmdq->wq, WQE_LCMD_SIZE, &ci); + if (IS_ERR(hw_wqe)) + break; + + if (cmdq_cmd_ceq_handler(cmdq, ci, &hw_wqe->cmdq_wqe)) + break; + } + } + + if (set_arm) { + struct hinic_hwif *hwif = cmdqs->hwif; + struct pci_dev *pdev = hwif->pdev; + + err = hinic_set_arm_bit(cmdqs, HINIC_SET_ARM_CMDQ, cmdq_type); + if (err) + dev_err(&pdev->dev, "Failed to set arm for CMDQ\n"); + } +} + +/** + * cmdq_init_queue_ctxt - init the queue ctxt of a cmdq + * @cmdq_ctxt: cmdq ctxt to initialize + * @cmdq: the cmdq + * @cmdq_pages: the memory of the queue + **/ +static void cmdq_init_queue_ctxt(struct hinic_cmdq_ctxt *cmdq_ctxt, + struct hinic_cmdq *cmdq, + struct hinic_cmdq_pages *cmdq_pages) +{ + struct hinic_cmdq_ctxt_info *ctxt_info = &cmdq_ctxt->ctxt_info; + u64 wq_first_page_paddr, cmdq_first_block_paddr, pfn; + struct hinic_cmdqs *cmdqs = cmdq_to_cmdqs(cmdq); + struct hinic_wq *wq = cmdq->wq; + + /* The data in the HW is in Big Endian Format */ + wq_first_page_paddr = be64_to_cpu(*wq->block_vaddr); + + pfn = CMDQ_PFN(wq_first_page_paddr, wq->wq_page_size); + + ctxt_info->curr_wqe_page_pfn = + HINIC_CMDQ_CTXT_PAGE_INFO_SET(pfn, CURR_WQE_PAGE_PFN) | + HINIC_CMDQ_CTXT_PAGE_INFO_SET(HINIC_CEQ_ID_CMDQ, EQ_ID) | + HINIC_CMDQ_CTXT_PAGE_INFO_SET(1, CEQ_ARM) | + HINIC_CMDQ_CTXT_PAGE_INFO_SET(1, CEQ_EN) | + HINIC_CMDQ_CTXT_PAGE_INFO_SET(cmdq->wrapped, WRAPPED); + + /* block PFN - Read Modify Write */ + cmdq_first_block_paddr = cmdq_pages->page_paddr; + + pfn = CMDQ_PFN(cmdq_first_block_paddr, wq->wq_page_size); + + ctxt_info->wq_block_pfn = + HINIC_CMDQ_CTXT_BLOCK_INFO_SET(pfn, WQ_BLOCK_PFN) | + HINIC_CMDQ_CTXT_BLOCK_INFO_SET(atomic_read(&wq->cons_idx), CI); + + cmdq_ctxt->func_idx = HINIC_HWIF_FUNC_IDX(cmdqs->hwif); + cmdq_ctxt->cmdq_type = cmdq->cmdq_type; +} + +/** + * init_cmdq - initialize cmdq + * @cmdq: the cmdq + * @wq: the wq attaced to the cmdq + * @q_type: the cmdq type of the cmdq + * @db_area: doorbell area for the cmdq + * + * Return 0 - Success, negative - Failure + **/ +static int init_cmdq(struct hinic_cmdq *cmdq, struct hinic_wq *wq, + enum hinic_cmdq_type q_type, void __iomem *db_area) +{ + int err; + + cmdq->wq = wq; + cmdq->cmdq_type = q_type; + cmdq->wrapped = 1; + + spin_lock_init(&cmdq->cmdq_lock); + + cmdq->done = vzalloc(wq->q_depth * sizeof(*cmdq->done)); + if (!cmdq->done) + return -ENOMEM; + + cmdq->errcode = vzalloc(wq->q_depth * sizeof(*cmdq->errcode)); + if (!cmdq->errcode) { + err = -ENOMEM; + goto err_errcode; + } + + cmdq->db_base = db_area + CMDQ_DB_OFF; + return 0; + +err_errcode: + vfree(cmdq->done); + return err; +} + +/** + * free_cmdq - Free cmdq + * @cmdq: the cmdq to free + **/ +static void free_cmdq(struct hinic_cmdq *cmdq) +{ + vfree(cmdq->errcode); + vfree(cmdq->done); +} + +/** + * init_cmdqs_ctxt - write the cmdq ctxt to HW after init all cmdq + * @hwdev: the NIC HW device + * @cmdqs: cmdqs to write the ctxts for + * &db_area: db_area for all the cmdqs + * + * Return 0 - Success, negative - Failure + **/ +static int init_cmdqs_ctxt(struct hinic_hwdev *hwdev, + struct hinic_cmdqs *cmdqs, void __iomem **db_area) +{ + struct hinic_hwif *hwif = hwdev->hwif; + enum hinic_cmdq_type type, cmdq_type; + struct hinic_cmdq_ctxt *cmdq_ctxts; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + size_t cmdq_ctxts_size; + int err; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI function type\n"); + return -EINVAL; + } + + cmdq_ctxts_size = HINIC_MAX_CMDQ_TYPES * sizeof(*cmdq_ctxts); + cmdq_ctxts = devm_kzalloc(&pdev->dev, cmdq_ctxts_size, GFP_KERNEL); + if (!cmdq_ctxts) + return -ENOMEM; + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + cmdq_type = HINIC_CMDQ_SYNC; + for (; cmdq_type < HINIC_MAX_CMDQ_TYPES; cmdq_type++) { + err = init_cmdq(&cmdqs->cmdq[cmdq_type], + &cmdqs->saved_wqs[cmdq_type], cmdq_type, + db_area[cmdq_type]); + if (err) { + dev_err(&pdev->dev, "Failed to initialize cmdq\n"); + goto err_init_cmdq; + } + + cmdq_init_queue_ctxt(&cmdq_ctxts[cmdq_type], + &cmdqs->cmdq[cmdq_type], + &cmdqs->cmdq_pages); + } + + /* Write the CMDQ ctxts */ + cmdq_type = HINIC_CMDQ_SYNC; + for (; cmdq_type < HINIC_MAX_CMDQ_TYPES; cmdq_type++) { + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + HINIC_COMM_CMD_CMDQ_CTXT_SET, + &cmdq_ctxts[cmdq_type], + sizeof(cmdq_ctxts[cmdq_type]), + NULL, NULL, HINIC_MGMT_MSG_SYNC); + if (err) { + dev_err(&pdev->dev, "Failed to set CMDQ CTXT type = %d\n", + cmdq_type); + goto err_write_cmdq_ctxt; + } + } + + devm_kfree(&pdev->dev, cmdq_ctxts); + return 0; + +err_write_cmdq_ctxt: + cmdq_type = HINIC_MAX_CMDQ_TYPES; + +err_init_cmdq: + for (type = HINIC_CMDQ_SYNC; type < cmdq_type; type++) + free_cmdq(&cmdqs->cmdq[type]); + + devm_kfree(&pdev->dev, cmdq_ctxts); + return err; +} + +/** + * hinic_init_cmdqs - init all cmdqs + * @cmdqs: cmdqs to init + * @hwif: HW interface for accessing cmdqs + * @db_area: doorbell areas for all the cmdqs + * + * Return 0 - Success, negative - Failure + **/ +int hinic_init_cmdqs(struct hinic_cmdqs *cmdqs, struct hinic_hwif *hwif, + void __iomem **db_area) +{ + struct hinic_func_to_io *func_to_io = cmdqs_to_func_to_io(cmdqs); + struct pci_dev *pdev = hwif->pdev; + struct hinic_hwdev *hwdev; + size_t saved_wqs_size; + u16 max_wqe_size; + int err; + + cmdqs->hwif = hwif; + cmdqs->cmdq_buf_pool = pci_pool_create("hinic_cmdq", pdev, + HINIC_CMDQ_BUF_SIZE, + HINIC_CMDQ_BUF_SIZE, 0); + if (!cmdqs->cmdq_buf_pool) + return -ENOMEM; + + saved_wqs_size = HINIC_MAX_CMDQ_TYPES * sizeof(struct hinic_wq); + cmdqs->saved_wqs = devm_kzalloc(&pdev->dev, saved_wqs_size, GFP_KERNEL); + if (!cmdqs->saved_wqs) { + err = -ENOMEM; + goto err_saved_wqs; + } + + max_wqe_size = WQE_LCMD_SIZE; + err = hinic_wqs_cmdq_alloc(&cmdqs->cmdq_pages, cmdqs->saved_wqs, hwif, + HINIC_MAX_CMDQ_TYPES, CMDQ_WQEBB_SIZE, + CMDQ_WQ_PAGE_SIZE, CMDQ_DEPTH, max_wqe_size); + if (err) { + dev_err(&pdev->dev, "Failed to allocate CMDQ wqs\n"); + goto err_cmdq_wqs; + } + + hwdev = container_of(func_to_io, struct hinic_hwdev, func_to_io); + err = init_cmdqs_ctxt(hwdev, cmdqs, db_area); + if (err) { + dev_err(&pdev->dev, "Failed to write cmdq ctxt\n"); + goto err_cmdq_ctxt; + } + + hinic_ceq_register_cb(&func_to_io->ceqs, HINIC_CEQ_CMDQ, cmdqs, + cmdq_ceq_handler); + return 0; + +err_cmdq_ctxt: + hinic_wqs_cmdq_free(&cmdqs->cmdq_pages, cmdqs->saved_wqs, + HINIC_MAX_CMDQ_TYPES); + +err_cmdq_wqs: + devm_kfree(&pdev->dev, cmdqs->saved_wqs); + +err_saved_wqs: + pci_pool_destroy(cmdqs->cmdq_buf_pool); + return err; +} + +/** + * hinic_free_cmdqs - free all cmdqs + * @cmdqs: cmdqs to free + **/ +void hinic_free_cmdqs(struct hinic_cmdqs *cmdqs) +{ + struct hinic_func_to_io *func_to_io = cmdqs_to_func_to_io(cmdqs); + struct hinic_hwif *hwif = cmdqs->hwif; + struct pci_dev *pdev = hwif->pdev; + enum hinic_cmdq_type cmdq_type; + + hinic_ceq_unregister_cb(&func_to_io->ceqs, HINIC_CEQ_CMDQ); + + cmdq_type = HINIC_CMDQ_SYNC; + for (; cmdq_type < HINIC_MAX_CMDQ_TYPES; cmdq_type++) + free_cmdq(&cmdqs->cmdq[cmdq_type]); + + hinic_wqs_cmdq_free(&cmdqs->cmdq_pages, cmdqs->saved_wqs, + HINIC_MAX_CMDQ_TYPES); + + devm_kfree(&pdev->dev, cmdqs->saved_wqs); + + pci_pool_destroy(cmdqs->cmdq_buf_pool); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h new file mode 100644 index 000000000000..b35583400cb6 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.h @@ -0,0 +1,187 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_CMDQ_H +#define HINIC_CMDQ_H + +#include <linux/types.h> +#include <linux/spinlock.h> +#include <linux/completion.h> +#include <linux/pci.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_wq.h" + +#define HINIC_CMDQ_CTXT_CURR_WQE_PAGE_PFN_SHIFT 0 +#define HINIC_CMDQ_CTXT_EQ_ID_SHIFT 56 +#define HINIC_CMDQ_CTXT_CEQ_ARM_SHIFT 61 +#define HINIC_CMDQ_CTXT_CEQ_EN_SHIFT 62 +#define HINIC_CMDQ_CTXT_WRAPPED_SHIFT 63 + +#define HINIC_CMDQ_CTXT_CURR_WQE_PAGE_PFN_MASK 0xFFFFFFFFFFFFF +#define HINIC_CMDQ_CTXT_EQ_ID_MASK 0x1F +#define HINIC_CMDQ_CTXT_CEQ_ARM_MASK 0x1 +#define HINIC_CMDQ_CTXT_CEQ_EN_MASK 0x1 +#define HINIC_CMDQ_CTXT_WRAPPED_MASK 0x1 + +#define HINIC_CMDQ_CTXT_PAGE_INFO_SET(val, member) \ + (((u64)(val) & HINIC_CMDQ_CTXT_##member##_MASK) \ + << HINIC_CMDQ_CTXT_##member##_SHIFT) + +#define HINIC_CMDQ_CTXT_PAGE_INFO_CLEAR(val, member) \ + ((val) & (~((u64)HINIC_CMDQ_CTXT_##member##_MASK \ + << HINIC_CMDQ_CTXT_##member##_SHIFT))) + +#define HINIC_CMDQ_CTXT_WQ_BLOCK_PFN_SHIFT 0 +#define HINIC_CMDQ_CTXT_CI_SHIFT 52 + +#define HINIC_CMDQ_CTXT_WQ_BLOCK_PFN_MASK 0xFFFFFFFFFFFFF +#define HINIC_CMDQ_CTXT_CI_MASK 0xFFF + +#define HINIC_CMDQ_CTXT_BLOCK_INFO_SET(val, member) \ + (((u64)(val) & HINIC_CMDQ_CTXT_##member##_MASK) \ + << HINIC_CMDQ_CTXT_##member##_SHIFT) + +#define HINIC_CMDQ_CTXT_BLOCK_INFO_CLEAR(val, member) \ + ((val) & (~((u64)HINIC_CMDQ_CTXT_##member##_MASK \ + << HINIC_CMDQ_CTXT_##member##_SHIFT))) + +#define HINIC_SAVED_DATA_ARM_SHIFT 31 + +#define HINIC_SAVED_DATA_ARM_MASK 0x1 + +#define HINIC_SAVED_DATA_SET(val, member) \ + (((u32)(val) & HINIC_SAVED_DATA_##member##_MASK) \ + << HINIC_SAVED_DATA_##member##_SHIFT) + +#define HINIC_SAVED_DATA_GET(val, member) \ + (((val) >> HINIC_SAVED_DATA_##member##_SHIFT) \ + & HINIC_SAVED_DATA_##member##_MASK) + +#define HINIC_SAVED_DATA_CLEAR(val, member) \ + ((val) & (~(HINIC_SAVED_DATA_##member##_MASK \ + << HINIC_SAVED_DATA_##member##_SHIFT))) + +#define HINIC_CMDQ_DB_INFO_HI_PROD_IDX_SHIFT 0 +#define HINIC_CMDQ_DB_INFO_PATH_SHIFT 23 +#define HINIC_CMDQ_DB_INFO_CMDQ_TYPE_SHIFT 24 +#define HINIC_CMDQ_DB_INFO_DB_TYPE_SHIFT 27 + +#define HINIC_CMDQ_DB_INFO_HI_PROD_IDX_MASK 0xFF +#define HINIC_CMDQ_DB_INFO_PATH_MASK 0x1 +#define HINIC_CMDQ_DB_INFO_CMDQ_TYPE_MASK 0x7 +#define HINIC_CMDQ_DB_INFO_DB_TYPE_MASK 0x1F + +#define HINIC_CMDQ_DB_INFO_SET(val, member) \ + (((u32)(val) & HINIC_CMDQ_DB_INFO_##member##_MASK) \ + << HINIC_CMDQ_DB_INFO_##member##_SHIFT) + +#define HINIC_CMDQ_BUF_SIZE 2048 + +#define HINIC_CMDQ_BUF_HW_RSVD 8 +#define HINIC_CMDQ_MAX_DATA_SIZE (HINIC_CMDQ_BUF_SIZE - \ + HINIC_CMDQ_BUF_HW_RSVD) + +enum hinic_cmdq_type { + HINIC_CMDQ_SYNC, + + HINIC_MAX_CMDQ_TYPES, +}; + +enum hinic_set_arm_qtype { + HINIC_SET_ARM_CMDQ, +}; + +enum hinic_cmd_ack_type { + HINIC_CMD_ACK_TYPE_CMDQ, +}; + +struct hinic_cmdq_buf { + void *buf; + dma_addr_t dma_addr; + size_t size; +}; + +struct hinic_cmdq_arm_bit { + u32 q_type; + u32 q_id; +}; + +struct hinic_cmdq_ctxt_info { + u64 curr_wqe_page_pfn; + u64 wq_block_pfn; +}; + +struct hinic_cmdq_ctxt { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 cmdq_type; + u8 rsvd1[1]; + + u8 rsvd2[4]; + + struct hinic_cmdq_ctxt_info ctxt_info; +}; + +struct hinic_cmdq { + struct hinic_wq *wq; + + enum hinic_cmdq_type cmdq_type; + int wrapped; + + /* Lock for keeping the doorbell order */ + spinlock_t cmdq_lock; + + struct completion **done; + int **errcode; + + /* doorbell area */ + void __iomem *db_base; +}; + +struct hinic_cmdqs { + struct hinic_hwif *hwif; + + struct pci_pool *cmdq_buf_pool; + + struct hinic_wq *saved_wqs; + + struct hinic_cmdq_pages cmdq_pages; + + struct hinic_cmdq cmdq[HINIC_MAX_CMDQ_TYPES]; +}; + +int hinic_alloc_cmdq_buf(struct hinic_cmdqs *cmdqs, + struct hinic_cmdq_buf *cmdq_buf); + +void hinic_free_cmdq_buf(struct hinic_cmdqs *cmdqs, + struct hinic_cmdq_buf *cmdq_buf); + +int hinic_cmdq_direct_resp(struct hinic_cmdqs *cmdqs, + enum hinic_mod_type mod, u8 cmd, + struct hinic_cmdq_buf *buf_in, u64 *out_param); + +int hinic_set_arm_bit(struct hinic_cmdqs *cmdqs, + enum hinic_set_arm_qtype q_type, u32 q_id); + +int hinic_init_cmdqs(struct hinic_cmdqs *cmdqs, struct hinic_hwif *hwif, + void __iomem **db_area); + +void hinic_free_cmdqs(struct hinic_cmdqs *cmdqs); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h new file mode 100644 index 000000000000..f39b184f674d --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_csr.h @@ -0,0 +1,149 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_CSR_H +#define HINIC_HW_CSR_H + +/* HW interface registers */ +#define HINIC_CSR_FUNC_ATTR0_ADDR 0x0 +#define HINIC_CSR_FUNC_ATTR1_ADDR 0x4 + +#define HINIC_CSR_FUNC_ATTR4_ADDR 0x10 +#define HINIC_CSR_FUNC_ATTR5_ADDR 0x14 + +#define HINIC_DMA_ATTR_BASE 0xC80 +#define HINIC_ELECTION_BASE 0x4200 + +#define HINIC_DMA_ATTR_STRIDE 0x4 +#define HINIC_CSR_DMA_ATTR_ADDR(idx) \ + (HINIC_DMA_ATTR_BASE + (idx) * HINIC_DMA_ATTR_STRIDE) + +#define HINIC_PPF_ELECTION_STRIDE 0x4 +#define HINIC_CSR_MAX_PORTS 4 + +#define HINIC_CSR_PPF_ELECTION_ADDR(idx) \ + (HINIC_ELECTION_BASE + (idx) * HINIC_PPF_ELECTION_STRIDE) + +/* API CMD registers */ +#define HINIC_CSR_API_CMD_BASE 0xF000 + +#define HINIC_CSR_API_CMD_STRIDE 0x100 + +#define HINIC_CSR_API_CMD_CHAIN_HEAD_HI_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x0 + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_CHAIN_HEAD_LO_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x4 + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_STATUS_HI_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x8 + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_STATUS_LO_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0xC + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_CHAIN_NUM_CELLS_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x10 + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_CHAIN_CTRL_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x14 + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_CHAIN_PI_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x1C + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_CHAIN_REQ_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x20 + (idx) * HINIC_CSR_API_CMD_STRIDE) + +#define HINIC_CSR_API_CMD_STATUS_ADDR(idx) \ + (HINIC_CSR_API_CMD_BASE + 0x30 + (idx) * HINIC_CSR_API_CMD_STRIDE) + +/* MSI-X registers */ +#define HINIC_CSR_MSIX_CTRL_BASE 0x2000 +#define HINIC_CSR_MSIX_CNT_BASE 0x2004 + +#define HINIC_CSR_MSIX_STRIDE 0x8 + +#define HINIC_CSR_MSIX_CTRL_ADDR(idx) \ + (HINIC_CSR_MSIX_CTRL_BASE + (idx) * HINIC_CSR_MSIX_STRIDE) + +#define HINIC_CSR_MSIX_CNT_ADDR(idx) \ + (HINIC_CSR_MSIX_CNT_BASE + (idx) * HINIC_CSR_MSIX_STRIDE) + +/* EQ registers */ +#define HINIC_AEQ_MTT_OFF_BASE_ADDR 0x200 +#define HINIC_CEQ_MTT_OFF_BASE_ADDR 0x400 + +#define HINIC_EQ_MTT_OFF_STRIDE 0x40 + +#define HINIC_CSR_AEQ_MTT_OFF(id) \ + (HINIC_AEQ_MTT_OFF_BASE_ADDR + (id) * HINIC_EQ_MTT_OFF_STRIDE) + +#define HINIC_CSR_CEQ_MTT_OFF(id) \ + (HINIC_CEQ_MTT_OFF_BASE_ADDR + (id) * HINIC_EQ_MTT_OFF_STRIDE) + +#define HINIC_CSR_EQ_PAGE_OFF_STRIDE 8 + +#define HINIC_CSR_AEQ_HI_PHYS_ADDR_REG(q_id, pg_num) \ + (HINIC_CSR_AEQ_MTT_OFF(q_id) + \ + (pg_num) * HINIC_CSR_EQ_PAGE_OFF_STRIDE) + +#define HINIC_CSR_CEQ_HI_PHYS_ADDR_REG(q_id, pg_num) \ + (HINIC_CSR_CEQ_MTT_OFF(q_id) + \ + (pg_num) * HINIC_CSR_EQ_PAGE_OFF_STRIDE) + +#define HINIC_CSR_AEQ_LO_PHYS_ADDR_REG(q_id, pg_num) \ + (HINIC_CSR_AEQ_MTT_OFF(q_id) + \ + (pg_num) * HINIC_CSR_EQ_PAGE_OFF_STRIDE + 4) + +#define HINIC_CSR_CEQ_LO_PHYS_ADDR_REG(q_id, pg_num) \ + (HINIC_CSR_CEQ_MTT_OFF(q_id) + \ + (pg_num) * HINIC_CSR_EQ_PAGE_OFF_STRIDE + 4) + +#define HINIC_AEQ_CTRL_0_ADDR_BASE 0xE00 +#define HINIC_AEQ_CTRL_1_ADDR_BASE 0xE04 +#define HINIC_AEQ_CONS_IDX_ADDR_BASE 0xE08 +#define HINIC_AEQ_PROD_IDX_ADDR_BASE 0xE0C + +#define HINIC_CEQ_CTRL_0_ADDR_BASE 0x1000 +#define HINIC_CEQ_CTRL_1_ADDR_BASE 0x1004 +#define HINIC_CEQ_CONS_IDX_ADDR_BASE 0x1008 +#define HINIC_CEQ_PROD_IDX_ADDR_BASE 0x100C + +#define HINIC_EQ_OFF_STRIDE 0x80 + +#define HINIC_CSR_AEQ_CTRL_0_ADDR(idx) \ + (HINIC_AEQ_CTRL_0_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#define HINIC_CSR_AEQ_CTRL_1_ADDR(idx) \ + (HINIC_AEQ_CTRL_1_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#define HINIC_CSR_AEQ_CONS_IDX_ADDR(idx) \ + (HINIC_AEQ_CONS_IDX_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#define HINIC_CSR_AEQ_PROD_IDX_ADDR(idx) \ + (HINIC_AEQ_PROD_IDX_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#define HINIC_CSR_CEQ_CTRL_0_ADDR(idx) \ + (HINIC_CEQ_CTRL_0_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#define HINIC_CSR_CEQ_CTRL_1_ADDR(idx) \ + (HINIC_CEQ_CTRL_1_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#define HINIC_CSR_CEQ_CONS_IDX_ADDR(idx) \ + (HINIC_CEQ_CONS_IDX_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#define HINIC_CSR_CEQ_PROD_IDX_ADDR(idx) \ + (HINIC_CEQ_PROD_IDX_ADDR_BASE + (idx) * HINIC_EQ_OFF_STRIDE) + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c new file mode 100644 index 000000000000..79b567447084 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -0,0 +1,1013 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/bitops.h> +#include <linux/delay.h> +#include <linux/jiffies.h> +#include <linux/log2.h> +#include <linux/err.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_eqs.h" +#include "hinic_hw_mgmt.h" +#include "hinic_hw_qp_ctxt.h" +#include "hinic_hw_qp.h" +#include "hinic_hw_io.h" +#include "hinic_hw_dev.h" + +#define IO_STATUS_TIMEOUT 100 +#define OUTBOUND_STATE_TIMEOUT 100 +#define DB_STATE_TIMEOUT 100 + +#define MAX_IRQS(max_qps, num_aeqs, num_ceqs) \ + (2 * (max_qps) + (num_aeqs) + (num_ceqs)) + +#define ADDR_IN_4BYTES(addr) ((addr) >> 2) + +enum intr_type { + INTR_MSIX_TYPE, +}; + +enum io_status { + IO_STOPPED = 0, + IO_RUNNING = 1, +}; + +enum hw_ioctxt_set_cmdq_depth { + HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT, +}; + +/* HW struct */ +struct hinic_dev_cap { + u8 status; + u8 version; + u8 rsvd0[6]; + + u8 rsvd1[5]; + u8 intr_type; + u8 rsvd2[66]; + u16 max_sqs; + u16 max_rqs; + u8 rsvd3[208]; +}; + +/** + * get_capability - convert device capabilities to NIC capabilities + * @hwdev: the HW device to set and convert device capabilities for + * @dev_cap: device capabilities from FW + * + * Return 0 - Success, negative - Failure + **/ +static int get_capability(struct hinic_hwdev *hwdev, + struct hinic_dev_cap *dev_cap) +{ + struct hinic_cap *nic_cap = &hwdev->nic_cap; + int num_aeqs, num_ceqs, num_irqs; + + if (!HINIC_IS_PF(hwdev->hwif) && !HINIC_IS_PPF(hwdev->hwif)) + return -EINVAL; + + if (dev_cap->intr_type != INTR_MSIX_TYPE) + return -EFAULT; + + num_aeqs = HINIC_HWIF_NUM_AEQS(hwdev->hwif); + num_ceqs = HINIC_HWIF_NUM_CEQS(hwdev->hwif); + num_irqs = HINIC_HWIF_NUM_IRQS(hwdev->hwif); + + /* Each QP has its own (SQ + RQ) interrupts */ + nic_cap->num_qps = (num_irqs - (num_aeqs + num_ceqs)) / 2; + + if (nic_cap->num_qps > HINIC_Q_CTXT_MAX) + nic_cap->num_qps = HINIC_Q_CTXT_MAX; + + /* num_qps must be power of 2 */ + nic_cap->num_qps = BIT(fls(nic_cap->num_qps) - 1); + + nic_cap->max_qps = dev_cap->max_sqs + 1; + if (nic_cap->max_qps != (dev_cap->max_rqs + 1)) + return -EFAULT; + + if (nic_cap->num_qps > nic_cap->max_qps) + nic_cap->num_qps = nic_cap->max_qps; + + return 0; +} + +/** + * get_cap_from_fw - get device capabilities from FW + * @pfhwdev: the PF HW device to get capabilities for + * + * Return 0 - Success, negative - Failure + **/ +static int get_cap_from_fw(struct hinic_pfhwdev *pfhwdev) +{ + struct hinic_hwdev *hwdev = &pfhwdev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_dev_cap dev_cap; + u16 in_len, out_len; + int err; + + in_len = 0; + out_len = sizeof(dev_cap); + + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_CFGM, + HINIC_CFG_NIC_CAP, &dev_cap, in_len, &dev_cap, + &out_len, HINIC_MGMT_MSG_SYNC); + if (err) { + dev_err(&pdev->dev, "Failed to get capability from FW\n"); + return err; + } + + return get_capability(hwdev, &dev_cap); +} + +/** + * get_dev_cap - get device capabilities + * @hwdev: the NIC HW device to get capabilities for + * + * Return 0 - Success, negative - Failure + **/ +static int get_dev_cap(struct hinic_hwdev *hwdev) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + int err; + + switch (HINIC_FUNC_TYPE(hwif)) { + case HINIC_PPF: + case HINIC_PF: + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + err = get_cap_from_fw(pfhwdev); + if (err) { + dev_err(&pdev->dev, "Failed to get capability from FW\n"); + return err; + } + break; + + default: + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + return -EINVAL; + } + + return 0; +} + +/** + * init_msix - enable the msix and save the entries + * @hwdev: the NIC HW device + * + * Return 0 - Success, negative - Failure + **/ +static int init_msix(struct hinic_hwdev *hwdev) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + int nr_irqs, num_aeqs, num_ceqs; + size_t msix_entries_size; + int i, err; + + num_aeqs = HINIC_HWIF_NUM_AEQS(hwif); + num_ceqs = HINIC_HWIF_NUM_CEQS(hwif); + nr_irqs = MAX_IRQS(HINIC_MAX_QPS, num_aeqs, num_ceqs); + if (nr_irqs > HINIC_HWIF_NUM_IRQS(hwif)) + nr_irqs = HINIC_HWIF_NUM_IRQS(hwif); + + msix_entries_size = nr_irqs * sizeof(*hwdev->msix_entries); + hwdev->msix_entries = devm_kzalloc(&pdev->dev, msix_entries_size, + GFP_KERNEL); + if (!hwdev->msix_entries) + return -ENOMEM; + + for (i = 0; i < nr_irqs; i++) + hwdev->msix_entries[i].entry = i; + + err = pci_enable_msix_exact(pdev, hwdev->msix_entries, nr_irqs); + if (err) { + dev_err(&pdev->dev, "Failed to enable pci msix\n"); + return err; + } + + return 0; +} + +/** + * disable_msix - disable the msix + * @hwdev: the NIC HW device + **/ +static void disable_msix(struct hinic_hwdev *hwdev) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + + pci_disable_msix(pdev); +} + +/** + * hinic_port_msg_cmd - send port msg to mgmt + * @hwdev: the NIC HW device + * @cmd: the port command + * @buf_in: input buffer + * @in_size: input size + * @buf_out: output buffer + * @out_size: returned output size + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd, + void *buf_in, u16 in_size, void *buf_out, u16 *out_size) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "unsupported PCI Function type\n"); + return -EINVAL; + } + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, cmd, + buf_in, in_size, buf_out, out_size, + HINIC_MGMT_MSG_SYNC); +} + +/** + * init_fw_ctxt- Init Firmware tables before network mgmt and io operations + * @hwdev: the NIC HW device + * + * Return 0 - Success, negative - Failure + **/ +static int init_fw_ctxt(struct hinic_hwdev *hwdev) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_cmd_fw_ctxt fw_ctxt; + struct hinic_pfhwdev *pfhwdev; + u16 out_size; + int err; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + return -EINVAL; + } + + fw_ctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + fw_ctxt.rx_buf_sz = HINIC_RX_BUF_SZ; + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_FWCTXT_INIT, + &fw_ctxt, sizeof(fw_ctxt), + &fw_ctxt, &out_size); + if (err || (out_size != sizeof(fw_ctxt)) || fw_ctxt.status) { + dev_err(&pdev->dev, "Failed to init FW ctxt, ret = %d\n", + fw_ctxt.status); + return -EFAULT; + } + + return 0; +} + +/** + * set_hw_ioctxt - set the shape of the IO queues in FW + * @hwdev: the NIC HW device + * @rq_depth: rq depth + * @sq_depth: sq depth + * + * Return 0 - Success, negative - Failure + **/ +static int set_hw_ioctxt(struct hinic_hwdev *hwdev, unsigned int rq_depth, + unsigned int sq_depth) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct hinic_cmd_hw_ioctxt hw_ioctxt; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + return -EINVAL; + } + + hw_ioctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + hw_ioctxt.set_cmdq_depth = HW_IOCTXT_SET_CMDQ_DEPTH_DEFAULT; + hw_ioctxt.cmdq_depth = 0; + + hw_ioctxt.rq_depth = ilog2(rq_depth); + + hw_ioctxt.rx_buf_sz_idx = HINIC_RX_BUF_SZ_IDX; + + hw_ioctxt.sq_depth = ilog2(sq_depth); + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + HINIC_COMM_CMD_HWCTXT_SET, + &hw_ioctxt, sizeof(hw_ioctxt), NULL, + NULL, HINIC_MGMT_MSG_SYNC); +} + +static int wait_for_outbound_state(struct hinic_hwdev *hwdev) +{ + enum hinic_outbound_state outbound_state; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + unsigned long end; + + end = jiffies + msecs_to_jiffies(OUTBOUND_STATE_TIMEOUT); + do { + outbound_state = hinic_outbound_state_get(hwif); + + if (outbound_state == HINIC_OUTBOUND_ENABLE) + return 0; + + msleep(20); + } while (time_before(jiffies, end)); + + dev_err(&pdev->dev, "Wait for OUTBOUND - Timeout\n"); + return -EFAULT; +} + +static int wait_for_db_state(struct hinic_hwdev *hwdev) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + enum hinic_db_state db_state; + unsigned long end; + + end = jiffies + msecs_to_jiffies(DB_STATE_TIMEOUT); + do { + db_state = hinic_db_state_get(hwif); + + if (db_state == HINIC_DB_ENABLE) + return 0; + + msleep(20); + } while (time_before(jiffies, end)); + + dev_err(&pdev->dev, "Wait for DB - Timeout\n"); + return -EFAULT; +} + +static int wait_for_io_stopped(struct hinic_hwdev *hwdev) +{ + struct hinic_cmd_io_status cmd_io_status; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + unsigned long end; + u16 out_size; + int err; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + return -EINVAL; + } + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + cmd_io_status.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + end = jiffies + msecs_to_jiffies(IO_STATUS_TIMEOUT); + do { + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + HINIC_COMM_CMD_IO_STATUS_GET, + &cmd_io_status, sizeof(cmd_io_status), + &cmd_io_status, &out_size, + HINIC_MGMT_MSG_SYNC); + if ((err) || (out_size != sizeof(cmd_io_status))) { + dev_err(&pdev->dev, "Failed to get IO status, ret = %d\n", + err); + return err; + } + + if (cmd_io_status.status == IO_STOPPED) { + dev_info(&pdev->dev, "IO stopped\n"); + return 0; + } + + msleep(20); + } while (time_before(jiffies, end)); + + dev_err(&pdev->dev, "Wait for IO stopped - Timeout\n"); + return -ETIMEDOUT; +} + +/** + * clear_io_resource - set the IO resources as not active in the NIC + * @hwdev: the NIC HW device + * + * Return 0 - Success, negative - Failure + **/ +static int clear_io_resources(struct hinic_hwdev *hwdev) +{ + struct hinic_cmd_clear_io_res cmd_clear_io_res; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + int err; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + return -EINVAL; + } + + err = wait_for_io_stopped(hwdev); + if (err) { + dev_err(&pdev->dev, "IO has not stopped yet\n"); + return err; + } + + cmd_clear_io_res.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM, + HINIC_COMM_CMD_IO_RES_CLEAR, &cmd_clear_io_res, + sizeof(cmd_clear_io_res), NULL, NULL, + HINIC_MGMT_MSG_SYNC); + if (err) { + dev_err(&pdev->dev, "Failed to clear IO resources\n"); + return err; + } + + return 0; +} + +/** + * set_resources_state - set the state of the resources in the NIC + * @hwdev: the NIC HW device + * @state: the state to set + * + * Return 0 - Success, negative - Failure + **/ +static int set_resources_state(struct hinic_hwdev *hwdev, + enum hinic_res_state state) +{ + struct hinic_cmd_set_res_state res_state; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + return -EINVAL; + } + + res_state.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + res_state.state = state; + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, + HINIC_MOD_COMM, + HINIC_COMM_CMD_RES_STATE_SET, + &res_state, sizeof(res_state), NULL, + NULL, HINIC_MGMT_MSG_SYNC); +} + +/** + * get_base_qpn - get the first qp number + * @hwdev: the NIC HW device + * @base_qpn: returned qp number + * + * Return 0 - Success, negative - Failure + **/ +static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn) +{ + struct hinic_cmd_base_qpn cmd_base_qpn; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + u16 out_size; + int err; + + cmd_base_qpn.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_GLOBAL_QPN, + &cmd_base_qpn, sizeof(cmd_base_qpn), + &cmd_base_qpn, &out_size); + if (err || (out_size != sizeof(cmd_base_qpn)) || cmd_base_qpn.status) { + dev_err(&pdev->dev, "Failed to get base qpn, status = %d\n", + cmd_base_qpn.status); + return -EFAULT; + } + + *base_qpn = cmd_base_qpn.qpn; + return 0; +} + +/** + * hinic_hwdev_ifup - Preparing the HW for passing IO + * @hwdev: the NIC HW device + * + * Return 0 - Success, negative - Failure + **/ +int hinic_hwdev_ifup(struct hinic_hwdev *hwdev) +{ + struct hinic_func_to_io *func_to_io = &hwdev->func_to_io; + struct hinic_cap *nic_cap = &hwdev->nic_cap; + struct hinic_hwif *hwif = hwdev->hwif; + int err, num_aeqs, num_ceqs, num_qps; + struct msix_entry *ceq_msix_entries; + struct msix_entry *sq_msix_entries; + struct msix_entry *rq_msix_entries; + struct pci_dev *pdev = hwif->pdev; + u16 base_qpn; + + err = get_base_qpn(hwdev, &base_qpn); + if (err) { + dev_err(&pdev->dev, "Failed to get global base qp number\n"); + return err; + } + + num_aeqs = HINIC_HWIF_NUM_AEQS(hwif); + num_ceqs = HINIC_HWIF_NUM_CEQS(hwif); + + ceq_msix_entries = &hwdev->msix_entries[num_aeqs]; + + err = hinic_io_init(func_to_io, hwif, nic_cap->max_qps, num_ceqs, + ceq_msix_entries); + if (err) { + dev_err(&pdev->dev, "Failed to init IO channel\n"); + return err; + } + + num_qps = nic_cap->num_qps; + sq_msix_entries = &hwdev->msix_entries[num_aeqs + num_ceqs]; + rq_msix_entries = &hwdev->msix_entries[num_aeqs + num_ceqs + num_qps]; + + err = hinic_io_create_qps(func_to_io, base_qpn, num_qps, + sq_msix_entries, rq_msix_entries); + if (err) { + dev_err(&pdev->dev, "Failed to create QPs\n"); + goto err_create_qps; + } + + err = wait_for_db_state(hwdev); + if (err) { + dev_warn(&pdev->dev, "db - disabled, try again\n"); + hinic_db_state_set(hwif, HINIC_DB_ENABLE); + } + + err = set_hw_ioctxt(hwdev, HINIC_SQ_DEPTH, HINIC_RQ_DEPTH); + if (err) { + dev_err(&pdev->dev, "Failed to set HW IO ctxt\n"); + goto err_hw_ioctxt; + } + + return 0; + +err_hw_ioctxt: + hinic_io_destroy_qps(func_to_io, num_qps); + +err_create_qps: + hinic_io_free(func_to_io); + return err; +} + +/** + * hinic_hwdev_ifdown - Closing the HW for passing IO + * @hwdev: the NIC HW device + * + **/ +void hinic_hwdev_ifdown(struct hinic_hwdev *hwdev) +{ + struct hinic_func_to_io *func_to_io = &hwdev->func_to_io; + struct hinic_cap *nic_cap = &hwdev->nic_cap; + + clear_io_resources(hwdev); + + hinic_io_destroy_qps(func_to_io, nic_cap->num_qps); + hinic_io_free(func_to_io); +} + +/** + * hinic_hwdev_cb_register - register callback handler for MGMT events + * @hwdev: the NIC HW device + * @cmd: the mgmt event + * @handle: private data for the handler + * @handler: event handler + **/ +void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev, + enum hinic_mgmt_msg_cmd cmd, void *handle, + void (*handler)(void *handle, void *buf_in, + u16 in_size, void *buf_out, + u16 *out_size)) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + struct hinic_nic_cb *nic_cb; + u8 cmd_cb; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "unsupported PCI Function type\n"); + return; + } + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + cmd_cb = cmd - HINIC_MGMT_MSG_CMD_BASE; + nic_cb = &pfhwdev->nic_cb[cmd_cb]; + + nic_cb->handler = handler; + nic_cb->handle = handle; + nic_cb->cb_state = HINIC_CB_ENABLED; +} + +/** + * hinic_hwdev_cb_unregister - unregister callback handler for MGMT events + * @hwdev: the NIC HW device + * @cmd: the mgmt event + **/ +void hinic_hwdev_cb_unregister(struct hinic_hwdev *hwdev, + enum hinic_mgmt_msg_cmd cmd) +{ + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + struct hinic_nic_cb *nic_cb; + u8 cmd_cb; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "unsupported PCI Function type\n"); + return; + } + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + + cmd_cb = cmd - HINIC_MGMT_MSG_CMD_BASE; + nic_cb = &pfhwdev->nic_cb[cmd_cb]; + + nic_cb->cb_state &= ~HINIC_CB_ENABLED; + + while (nic_cb->cb_state & HINIC_CB_RUNNING) + schedule(); + + nic_cb->handler = NULL; +} + +/** + * nic_mgmt_msg_handler - nic mgmt event handler + * @handle: private data for the handler + * @buf_in: input buffer + * @in_size: input size + * @buf_out: output buffer + * @out_size: returned output size + **/ +static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in, + u16 in_size, void *buf_out, u16 *out_size) +{ + struct hinic_pfhwdev *pfhwdev = handle; + enum hinic_cb_state cb_state; + struct hinic_nic_cb *nic_cb; + struct hinic_hwdev *hwdev; + struct hinic_hwif *hwif; + struct pci_dev *pdev; + u8 cmd_cb; + + hwdev = &pfhwdev->hwdev; + hwif = hwdev->hwif; + pdev = hwif->pdev; + + if ((cmd < HINIC_MGMT_MSG_CMD_BASE) || + (cmd >= HINIC_MGMT_MSG_CMD_MAX)) { + dev_err(&pdev->dev, "unknown L2NIC event, cmd = %d\n", cmd); + return; + } + + cmd_cb = cmd - HINIC_MGMT_MSG_CMD_BASE; + + nic_cb = &pfhwdev->nic_cb[cmd_cb]; + + cb_state = cmpxchg(&nic_cb->cb_state, + HINIC_CB_ENABLED, + HINIC_CB_ENABLED | HINIC_CB_RUNNING); + + if ((cb_state == HINIC_CB_ENABLED) && (nic_cb->handler)) + nic_cb->handler(nic_cb->handle, buf_in, + in_size, buf_out, out_size); + else + dev_err(&pdev->dev, "Unhandled NIC Event %d\n", cmd); + + nic_cb->cb_state &= ~HINIC_CB_RUNNING; +} + +/** + * init_pfhwdev - Initialize the extended components of PF + * @pfhwdev: the HW device for PF + * + * Return 0 - success, negative - failure + **/ +static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev) +{ + struct hinic_hwdev *hwdev = &pfhwdev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + int err; + + err = hinic_pf_to_mgmt_init(&pfhwdev->pf_to_mgmt, hwif); + if (err) { + dev_err(&pdev->dev, "Failed to initialize PF to MGMT channel\n"); + return err; + } + + hinic_register_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC, + pfhwdev, nic_mgmt_msg_handler); + + hinic_set_pf_action(hwif, HINIC_PF_MGMT_ACTIVE); + return 0; +} + +/** + * free_pfhwdev - Free the extended components of PF + * @pfhwdev: the HW device for PF + **/ +static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev) +{ + struct hinic_hwdev *hwdev = &pfhwdev->hwdev; + + hinic_set_pf_action(hwdev->hwif, HINIC_PF_MGMT_INIT); + + hinic_unregister_mgmt_msg_cb(&pfhwdev->pf_to_mgmt, HINIC_MOD_L2NIC); + + hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); +} + +/** + * hinic_init_hwdev - Initialize the NIC HW + * @pdev: the NIC pci device + * + * Return initialized NIC HW device + * + * Initialize the NIC HW device and return a pointer to it + **/ +struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev) +{ + struct hinic_pfhwdev *pfhwdev; + struct hinic_hwdev *hwdev; + struct hinic_hwif *hwif; + int err, num_aeqs; + + hwif = devm_kzalloc(&pdev->dev, sizeof(*hwif), GFP_KERNEL); + if (!hwif) + return ERR_PTR(-ENOMEM); + + err = hinic_init_hwif(hwif, pdev); + if (err) { + dev_err(&pdev->dev, "Failed to init HW interface\n"); + return ERR_PTR(err); + } + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + err = -EFAULT; + goto err_func_type; + } + + pfhwdev = devm_kzalloc(&pdev->dev, sizeof(*pfhwdev), GFP_KERNEL); + if (!pfhwdev) { + err = -ENOMEM; + goto err_pfhwdev_alloc; + } + + hwdev = &pfhwdev->hwdev; + hwdev->hwif = hwif; + + err = init_msix(hwdev); + if (err) { + dev_err(&pdev->dev, "Failed to init msix\n"); + goto err_init_msix; + } + + err = wait_for_outbound_state(hwdev); + if (err) { + dev_warn(&pdev->dev, "outbound - disabled, try again\n"); + hinic_outbound_state_set(hwif, HINIC_OUTBOUND_ENABLE); + } + + num_aeqs = HINIC_HWIF_NUM_AEQS(hwif); + + err = hinic_aeqs_init(&hwdev->aeqs, hwif, num_aeqs, + HINIC_DEFAULT_AEQ_LEN, HINIC_EQ_PAGE_SIZE, + hwdev->msix_entries); + if (err) { + dev_err(&pdev->dev, "Failed to init async event queues\n"); + goto err_aeqs_init; + } + + err = init_pfhwdev(pfhwdev); + if (err) { + dev_err(&pdev->dev, "Failed to init PF HW device\n"); + goto err_init_pfhwdev; + } + + err = get_dev_cap(hwdev); + if (err) { + dev_err(&pdev->dev, "Failed to get device capabilities\n"); + goto err_dev_cap; + } + + err = init_fw_ctxt(hwdev); + if (err) { + dev_err(&pdev->dev, "Failed to init function table\n"); + goto err_init_fw_ctxt; + } + + err = set_resources_state(hwdev, HINIC_RES_ACTIVE); + if (err) { + dev_err(&pdev->dev, "Failed to set resources state\n"); + goto err_resources_state; + } + + return hwdev; + +err_resources_state: +err_init_fw_ctxt: +err_dev_cap: + free_pfhwdev(pfhwdev); + +err_init_pfhwdev: + hinic_aeqs_free(&hwdev->aeqs); + +err_aeqs_init: + disable_msix(hwdev); + +err_init_msix: +err_pfhwdev_alloc: +err_func_type: + hinic_free_hwif(hwif); + return ERR_PTR(err); +} + +/** + * hinic_free_hwdev - Free the NIC HW device + * @hwdev: the NIC HW device + **/ +void hinic_free_hwdev(struct hinic_hwdev *hwdev) +{ + struct hinic_pfhwdev *pfhwdev = container_of(hwdev, + struct hinic_pfhwdev, + hwdev); + + set_resources_state(hwdev, HINIC_RES_CLEAN); + + free_pfhwdev(pfhwdev); + + hinic_aeqs_free(&hwdev->aeqs); + + disable_msix(hwdev); + + hinic_free_hwif(hwdev->hwif); +} + +/** + * hinic_hwdev_num_qps - return the number QPs available for use + * @hwdev: the NIC HW device + * + * Return number QPs available for use + **/ +int hinic_hwdev_num_qps(struct hinic_hwdev *hwdev) +{ + struct hinic_cap *nic_cap = &hwdev->nic_cap; + + return nic_cap->num_qps; +} + +/** + * hinic_hwdev_get_sq - get SQ + * @hwdev: the NIC HW device + * @i: the position of the SQ + * + * Return: the SQ in the i position + **/ +struct hinic_sq *hinic_hwdev_get_sq(struct hinic_hwdev *hwdev, int i) +{ + struct hinic_func_to_io *func_to_io = &hwdev->func_to_io; + struct hinic_qp *qp = &func_to_io->qps[i]; + + if (i >= hinic_hwdev_num_qps(hwdev)) + return NULL; + + return &qp->sq; +} + +/** + * hinic_hwdev_get_sq - get RQ + * @hwdev: the NIC HW device + * @i: the position of the RQ + * + * Return: the RQ in the i position + **/ +struct hinic_rq *hinic_hwdev_get_rq(struct hinic_hwdev *hwdev, int i) +{ + struct hinic_func_to_io *func_to_io = &hwdev->func_to_io; + struct hinic_qp *qp = &func_to_io->qps[i]; + + if (i >= hinic_hwdev_num_qps(hwdev)) + return NULL; + + return &qp->rq; +} + +/** + * hinic_hwdev_msix_cnt_set - clear message attribute counters for msix entry + * @hwdev: the NIC HW device + * @msix_index: msix_index + * + * Return 0 - Success, negative - Failure + **/ +int hinic_hwdev_msix_cnt_set(struct hinic_hwdev *hwdev, u16 msix_index) +{ + return hinic_msix_attr_cnt_clear(hwdev->hwif, msix_index); +} + +/** + * hinic_hwdev_msix_set - set message attribute for msix entry + * @hwdev: the NIC HW device + * @msix_index: msix_index + * @pending_limit: the maximum pending interrupt events (unit 8) + * @coalesc_timer: coalesc period for interrupt (unit 8 us) + * @lli_timer: replenishing period for low latency credit (unit 8 us) + * @lli_credit_limit: maximum credits for low latency msix messages (unit 8) + * @resend_timer: maximum wait for resending msix (unit coalesc period) + * + * Return 0 - Success, negative - Failure + **/ +int hinic_hwdev_msix_set(struct hinic_hwdev *hwdev, u16 msix_index, + u8 pending_limit, u8 coalesc_timer, + u8 lli_timer_cfg, u8 lli_credit_limit, + u8 resend_timer) +{ + return hinic_msix_attr_set(hwdev->hwif, msix_index, + pending_limit, coalesc_timer, + lli_timer_cfg, lli_credit_limit, + resend_timer); +} + +/** + * hinic_hwdev_hw_ci_addr_set - set cons idx addr and attributes in HW for sq + * @hwdev: the NIC HW device + * @sq: send queue + * @pending_limit: the maximum pending update ci events (unit 8) + * @coalesc_timer: coalesc period for update ci (unit 8 us) + * + * Return 0 - Success, negative - Failure + **/ +int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq, + u8 pending_limit, u8 coalesc_timer) +{ + struct hinic_qp *qp = container_of(sq, struct hinic_qp, sq); + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_pfhwdev *pfhwdev; + struct hinic_cmd_hw_ci hw_ci; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "Unsupported PCI Function type\n"); + return -EINVAL; + } + + hw_ci.dma_attr_off = 0; + hw_ci.pending_limit = pending_limit; + hw_ci.coalesc_timer = coalesc_timer; + + hw_ci.msix_en = 1; + hw_ci.msix_entry_idx = sq->msix_entry; + + hw_ci.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + hw_ci.sq_id = qp->q_id; + + hw_ci.ci_addr = ADDR_IN_4BYTES(sq->hw_ci_dma_addr); + + pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev); + return hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, + HINIC_MOD_COMM, + HINIC_COMM_CMD_SQ_HI_CI_SET, + &hw_ci, sizeof(hw_ci), NULL, + NULL, HINIC_MGMT_MSG_SYNC); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h new file mode 100644 index 000000000000..0f5563f3b779 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -0,0 +1,239 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_DEV_H +#define HINIC_HW_DEV_H + +#include <linux/pci.h> +#include <linux/types.h> +#include <linux/bitops.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_eqs.h" +#include "hinic_hw_mgmt.h" +#include "hinic_hw_qp.h" +#include "hinic_hw_io.h" + +#define HINIC_MAX_QPS 32 + +#define HINIC_MGMT_NUM_MSG_CMD (HINIC_MGMT_MSG_CMD_MAX - \ + HINIC_MGMT_MSG_CMD_BASE) + +struct hinic_cap { + u16 max_qps; + u16 num_qps; +}; + +enum hinic_port_cmd { + HINIC_PORT_CMD_CHANGE_MTU = 2, + + HINIC_PORT_CMD_ADD_VLAN = 3, + HINIC_PORT_CMD_DEL_VLAN = 4, + + HINIC_PORT_CMD_SET_MAC = 9, + HINIC_PORT_CMD_GET_MAC = 10, + HINIC_PORT_CMD_DEL_MAC = 11, + + HINIC_PORT_CMD_SET_RX_MODE = 12, + + HINIC_PORT_CMD_GET_LINK_STATE = 24, + + HINIC_PORT_CMD_SET_PORT_STATE = 41, + + HINIC_PORT_CMD_FWCTXT_INIT = 69, + + HINIC_PORT_CMD_SET_FUNC_STATE = 93, + + HINIC_PORT_CMD_GET_GLOBAL_QPN = 102, + + HINIC_PORT_CMD_GET_CAP = 170, +}; + +enum hinic_mgmt_msg_cmd { + HINIC_MGMT_MSG_CMD_BASE = 160, + + HINIC_MGMT_MSG_CMD_LINK_STATUS = 160, + + HINIC_MGMT_MSG_CMD_MAX, +}; + +enum hinic_cb_state { + HINIC_CB_ENABLED = BIT(0), + HINIC_CB_RUNNING = BIT(1), +}; + +enum hinic_res_state { + HINIC_RES_CLEAN = 0, + HINIC_RES_ACTIVE = 1, +}; + +struct hinic_cmd_fw_ctxt { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 rx_buf_sz; + + u32 rsvd1; +}; + +struct hinic_cmd_hw_ioctxt { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + + u16 rsvd1; + + u8 set_cmdq_depth; + u8 cmdq_depth; + + u8 rsvd2; + u8 rsvd3; + u8 rsvd4; + u8 rsvd5; + + u16 rq_depth; + u16 rx_buf_sz_idx; + u16 sq_depth; +}; + +struct hinic_cmd_io_status { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 rsvd1; + u8 rsvd2; + u32 io_status; +}; + +struct hinic_cmd_clear_io_res { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 rsvd1; + u8 rsvd2; +}; + +struct hinic_cmd_set_res_state { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 state; + u8 rsvd1; + u32 rsvd2; +}; + +struct hinic_cmd_base_qpn { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 qpn; +}; + +struct hinic_cmd_hw_ci { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + + u8 dma_attr_off; + u8 pending_limit; + u8 coalesc_timer; + + u8 msix_en; + u16 msix_entry_idx; + + u32 sq_id; + u32 rsvd1; + u64 ci_addr; +}; + +struct hinic_hwdev { + struct hinic_hwif *hwif; + struct msix_entry *msix_entries; + + struct hinic_aeqs aeqs; + struct hinic_func_to_io func_to_io; + + struct hinic_cap nic_cap; +}; + +struct hinic_nic_cb { + void (*handler)(void *handle, void *buf_in, + u16 in_size, void *buf_out, + u16 *out_size); + + void *handle; + unsigned long cb_state; +}; + +struct hinic_pfhwdev { + struct hinic_hwdev hwdev; + + struct hinic_pf_to_mgmt pf_to_mgmt; + + struct hinic_nic_cb nic_cb[HINIC_MGMT_NUM_MSG_CMD]; +}; + +void hinic_hwdev_cb_register(struct hinic_hwdev *hwdev, + enum hinic_mgmt_msg_cmd cmd, void *handle, + void (*handler)(void *handle, void *buf_in, + u16 in_size, void *buf_out, + u16 *out_size)); + +void hinic_hwdev_cb_unregister(struct hinic_hwdev *hwdev, + enum hinic_mgmt_msg_cmd cmd); + +int hinic_port_msg_cmd(struct hinic_hwdev *hwdev, enum hinic_port_cmd cmd, + void *buf_in, u16 in_size, void *buf_out, + u16 *out_size); + +int hinic_hwdev_ifup(struct hinic_hwdev *hwdev); + +void hinic_hwdev_ifdown(struct hinic_hwdev *hwdev); + +struct hinic_hwdev *hinic_init_hwdev(struct pci_dev *pdev); + +void hinic_free_hwdev(struct hinic_hwdev *hwdev); + +int hinic_hwdev_num_qps(struct hinic_hwdev *hwdev); + +struct hinic_sq *hinic_hwdev_get_sq(struct hinic_hwdev *hwdev, int i); + +struct hinic_rq *hinic_hwdev_get_rq(struct hinic_hwdev *hwdev, int i); + +int hinic_hwdev_msix_cnt_set(struct hinic_hwdev *hwdev, u16 msix_index); + +int hinic_hwdev_msix_set(struct hinic_hwdev *hwdev, u16 msix_index, + u8 pending_limit, u8 coalesc_timer, + u8 lli_timer_cfg, u8 lli_credit_limit, + u8 resend_timer); + +int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq, + u8 pending_limit, u8 coalesc_timer); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c new file mode 100644 index 000000000000..7cb8b9b94726 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c @@ -0,0 +1,886 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/workqueue.h> +#include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/dma-mapping.h> +#include <linux/log2.h> +#include <asm/byteorder.h> +#include <asm/barrier.h> + +#include "hinic_hw_csr.h" +#include "hinic_hw_if.h" +#include "hinic_hw_eqs.h" + +#define HINIC_EQS_WQ_NAME "hinic_eqs" + +#define GET_EQ_NUM_PAGES(eq, pg_size) \ + (ALIGN((eq)->q_len * (eq)->elem_size, pg_size) / (pg_size)) + +#define GET_EQ_NUM_ELEMS_IN_PG(eq, pg_size) ((pg_size) / (eq)->elem_size) + +#define EQ_CONS_IDX_REG_ADDR(eq) (((eq)->type == HINIC_AEQ) ? \ + HINIC_CSR_AEQ_CONS_IDX_ADDR((eq)->q_id) : \ + HINIC_CSR_CEQ_CONS_IDX_ADDR((eq)->q_id)) + +#define EQ_PROD_IDX_REG_ADDR(eq) (((eq)->type == HINIC_AEQ) ? \ + HINIC_CSR_AEQ_PROD_IDX_ADDR((eq)->q_id) : \ + HINIC_CSR_CEQ_PROD_IDX_ADDR((eq)->q_id)) + +#define EQ_HI_PHYS_ADDR_REG(eq, pg_num) (((eq)->type == HINIC_AEQ) ? \ + HINIC_CSR_AEQ_HI_PHYS_ADDR_REG((eq)->q_id, pg_num) : \ + HINIC_CSR_CEQ_HI_PHYS_ADDR_REG((eq)->q_id, pg_num)) + +#define EQ_LO_PHYS_ADDR_REG(eq, pg_num) (((eq)->type == HINIC_AEQ) ? \ + HINIC_CSR_AEQ_LO_PHYS_ADDR_REG((eq)->q_id, pg_num) : \ + HINIC_CSR_CEQ_LO_PHYS_ADDR_REG((eq)->q_id, pg_num)) + +#define GET_EQ_ELEMENT(eq, idx) \ + ((eq)->virt_addr[(idx) / (eq)->num_elem_in_pg] + \ + (((idx) & ((eq)->num_elem_in_pg - 1)) * (eq)->elem_size)) + +#define GET_AEQ_ELEM(eq, idx) ((struct hinic_aeq_elem *) \ + GET_EQ_ELEMENT(eq, idx)) + +#define GET_CEQ_ELEM(eq, idx) ((u32 *) \ + GET_EQ_ELEMENT(eq, idx)) + +#define GET_CURR_AEQ_ELEM(eq) GET_AEQ_ELEM(eq, (eq)->cons_idx) + +#define GET_CURR_CEQ_ELEM(eq) GET_CEQ_ELEM(eq, (eq)->cons_idx) + +#define PAGE_IN_4K(page_size) ((page_size) >> 12) +#define EQ_SET_HW_PAGE_SIZE_VAL(eq) (ilog2(PAGE_IN_4K((eq)->page_size))) + +#define ELEMENT_SIZE_IN_32B(eq) (((eq)->elem_size) >> 5) +#define EQ_SET_HW_ELEM_SIZE_VAL(eq) (ilog2(ELEMENT_SIZE_IN_32B(eq))) + +#define EQ_MAX_PAGES 8 + +#define CEQE_TYPE_SHIFT 23 +#define CEQE_TYPE_MASK 0x7 + +#define CEQE_TYPE(ceqe) (((ceqe) >> CEQE_TYPE_SHIFT) & \ + CEQE_TYPE_MASK) + +#define CEQE_DATA_MASK 0x3FFFFFF +#define CEQE_DATA(ceqe) ((ceqe) & CEQE_DATA_MASK) + +#define aeq_to_aeqs(eq) \ + container_of((eq) - (eq)->q_id, struct hinic_aeqs, aeq[0]) + +#define ceq_to_ceqs(eq) \ + container_of((eq) - (eq)->q_id, struct hinic_ceqs, ceq[0]) + +#define work_to_aeq_work(work) \ + container_of(work, struct hinic_eq_work, work) + +#define DMA_ATTR_AEQ_DEFAULT 0 +#define DMA_ATTR_CEQ_DEFAULT 0 + +/* No coalescence */ +#define THRESH_CEQ_DEFAULT 0 + +enum eq_int_mode { + EQ_INT_MODE_ARMED, + EQ_INT_MODE_ALWAYS +}; + +enum eq_arm_state { + EQ_NOT_ARMED, + EQ_ARMED +}; + +/** + * hinic_aeq_register_hw_cb - register AEQ callback for specific event + * @aeqs: pointer to Async eqs of the chip + * @event: aeq event to register callback for it + * @handle: private data will be used by the callback + * @hw_handler: callback function + **/ +void hinic_aeq_register_hw_cb(struct hinic_aeqs *aeqs, + enum hinic_aeq_type event, void *handle, + void (*hwe_handler)(void *handle, void *data, + u8 size)) +{ + struct hinic_hw_event_cb *hwe_cb = &aeqs->hwe_cb[event]; + + hwe_cb->hwe_handler = hwe_handler; + hwe_cb->handle = handle; + hwe_cb->hwe_state = HINIC_EQE_ENABLED; +} + +/** + * hinic_aeq_unregister_hw_cb - unregister the AEQ callback for specific event + * @aeqs: pointer to Async eqs of the chip + * @event: aeq event to unregister callback for it + **/ +void hinic_aeq_unregister_hw_cb(struct hinic_aeqs *aeqs, + enum hinic_aeq_type event) +{ + struct hinic_hw_event_cb *hwe_cb = &aeqs->hwe_cb[event]; + + hwe_cb->hwe_state &= ~HINIC_EQE_ENABLED; + + while (hwe_cb->hwe_state & HINIC_EQE_RUNNING) + schedule(); + + hwe_cb->hwe_handler = NULL; +} + +/** + * hinic_ceq_register_cb - register CEQ callback for specific event + * @ceqs: pointer to Completion eqs part of the chip + * @event: ceq event to register callback for it + * @handle: private data will be used by the callback + * @handler: callback function + **/ +void hinic_ceq_register_cb(struct hinic_ceqs *ceqs, + enum hinic_ceq_type event, void *handle, + void (*handler)(void *handle, u32 ceqe_data)) +{ + struct hinic_ceq_cb *ceq_cb = &ceqs->ceq_cb[event]; + + ceq_cb->handler = handler; + ceq_cb->handle = handle; + ceq_cb->ceqe_state = HINIC_EQE_ENABLED; +} + +/** + * hinic_ceq_unregister_cb - unregister the CEQ callback for specific event + * @ceqs: pointer to Completion eqs part of the chip + * @event: ceq event to unregister callback for it + **/ +void hinic_ceq_unregister_cb(struct hinic_ceqs *ceqs, + enum hinic_ceq_type event) +{ + struct hinic_ceq_cb *ceq_cb = &ceqs->ceq_cb[event]; + + ceq_cb->ceqe_state &= ~HINIC_EQE_ENABLED; + + while (ceq_cb->ceqe_state & HINIC_EQE_RUNNING) + schedule(); + + ceq_cb->handler = NULL; +} + +static u8 eq_cons_idx_checksum_set(u32 val) +{ + u8 checksum = 0; + int idx; + + for (idx = 0; idx < 32; idx += 4) + checksum ^= ((val >> idx) & 0xF); + + return (checksum & 0xF); +} + +/** + * eq_update_ci - update the HW cons idx of event queue + * @eq: the event queue to update the cons idx for + **/ +static void eq_update_ci(struct hinic_eq *eq) +{ + u32 val, addr = EQ_CONS_IDX_REG_ADDR(eq); + + /* Read Modify Write */ + val = hinic_hwif_read_reg(eq->hwif, addr); + + val = HINIC_EQ_CI_CLEAR(val, IDX) & + HINIC_EQ_CI_CLEAR(val, WRAPPED) & + HINIC_EQ_CI_CLEAR(val, INT_ARMED) & + HINIC_EQ_CI_CLEAR(val, XOR_CHKSUM); + + val |= HINIC_EQ_CI_SET(eq->cons_idx, IDX) | + HINIC_EQ_CI_SET(eq->wrapped, WRAPPED) | + HINIC_EQ_CI_SET(EQ_ARMED, INT_ARMED); + + val |= HINIC_EQ_CI_SET(eq_cons_idx_checksum_set(val), XOR_CHKSUM); + + hinic_hwif_write_reg(eq->hwif, addr, val); +} + +/** + * aeq_irq_handler - handler for the AEQ event + * @eq: the Async Event Queue that received the event + **/ +static void aeq_irq_handler(struct hinic_eq *eq) +{ + struct hinic_aeqs *aeqs = aeq_to_aeqs(eq); + struct hinic_hwif *hwif = aeqs->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_aeq_elem *aeqe_curr; + struct hinic_hw_event_cb *hwe_cb; + enum hinic_aeq_type event; + unsigned long eqe_state; + u32 aeqe_desc; + int i, size; + + for (i = 0; i < eq->q_len; i++) { + aeqe_curr = GET_CURR_AEQ_ELEM(eq); + + /* Data in HW is in Big endian Format */ + aeqe_desc = be32_to_cpu(aeqe_curr->desc); + + /* HW toggles the wrapped bit, when it adds eq element */ + if (HINIC_EQ_ELEM_DESC_GET(aeqe_desc, WRAPPED) == eq->wrapped) + break; + + event = HINIC_EQ_ELEM_DESC_GET(aeqe_desc, TYPE); + if (event >= HINIC_MAX_AEQ_EVENTS) { + dev_err(&pdev->dev, "Unknown AEQ Event %d\n", event); + return; + } + + if (!HINIC_EQ_ELEM_DESC_GET(aeqe_desc, SRC)) { + hwe_cb = &aeqs->hwe_cb[event]; + + size = HINIC_EQ_ELEM_DESC_GET(aeqe_desc, SIZE); + + eqe_state = cmpxchg(&hwe_cb->hwe_state, + HINIC_EQE_ENABLED, + HINIC_EQE_ENABLED | + HINIC_EQE_RUNNING); + if ((eqe_state == HINIC_EQE_ENABLED) && + (hwe_cb->hwe_handler)) + hwe_cb->hwe_handler(hwe_cb->handle, + aeqe_curr->data, size); + else + dev_err(&pdev->dev, "Unhandled AEQ Event %d\n", + event); + + hwe_cb->hwe_state &= ~HINIC_EQE_RUNNING; + } + + eq->cons_idx++; + + if (eq->cons_idx == eq->q_len) { + eq->cons_idx = 0; + eq->wrapped = !eq->wrapped; + } + } +} + +/** + * ceq_event_handler - handler for the ceq events + * @ceqs: ceqs part of the chip + * @ceqe: ceq element that describes the event + **/ +static void ceq_event_handler(struct hinic_ceqs *ceqs, u32 ceqe) +{ + struct hinic_hwif *hwif = ceqs->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_ceq_cb *ceq_cb; + enum hinic_ceq_type event; + unsigned long eqe_state; + + event = CEQE_TYPE(ceqe); + if (event >= HINIC_MAX_CEQ_EVENTS) { + dev_err(&pdev->dev, "Unknown CEQ event, event = %d\n", event); + return; + } + + ceq_cb = &ceqs->ceq_cb[event]; + + eqe_state = cmpxchg(&ceq_cb->ceqe_state, + HINIC_EQE_ENABLED, + HINIC_EQE_ENABLED | HINIC_EQE_RUNNING); + + if ((eqe_state == HINIC_EQE_ENABLED) && (ceq_cb->handler)) + ceq_cb->handler(ceq_cb->handle, CEQE_DATA(ceqe)); + else + dev_err(&pdev->dev, "Unhandled CEQ Event %d\n", event); + + ceq_cb->ceqe_state &= ~HINIC_EQE_RUNNING; +} + +/** + * ceq_irq_handler - handler for the CEQ event + * @eq: the Completion Event Queue that received the event + **/ +static void ceq_irq_handler(struct hinic_eq *eq) +{ + struct hinic_ceqs *ceqs = ceq_to_ceqs(eq); + u32 ceqe; + int i; + + for (i = 0; i < eq->q_len; i++) { + ceqe = *(GET_CURR_CEQ_ELEM(eq)); + + /* Data in HW is in Big endian Format */ + ceqe = be32_to_cpu(ceqe); + + /* HW toggles the wrapped bit, when it adds eq element event */ + if (HINIC_EQ_ELEM_DESC_GET(ceqe, WRAPPED) == eq->wrapped) + break; + + ceq_event_handler(ceqs, ceqe); + + eq->cons_idx++; + + if (eq->cons_idx == eq->q_len) { + eq->cons_idx = 0; + eq->wrapped = !eq->wrapped; + } + } +} + +/** + * eq_irq_handler - handler for the EQ event + * @data: the Event Queue that received the event + **/ +static void eq_irq_handler(void *data) +{ + struct hinic_eq *eq = data; + + if (eq->type == HINIC_AEQ) + aeq_irq_handler(eq); + else if (eq->type == HINIC_CEQ) + ceq_irq_handler(eq); + + eq_update_ci(eq); +} + +/** + * eq_irq_work - the work of the EQ that received the event + * @work: the work struct that is associated with the EQ + **/ +static void eq_irq_work(struct work_struct *work) +{ + struct hinic_eq_work *aeq_work = work_to_aeq_work(work); + struct hinic_eq *aeq; + + aeq = aeq_work->data; + eq_irq_handler(aeq); +} + +/** + * ceq_tasklet - the tasklet of the EQ that received the event + * @ceq_data: the eq + **/ +static void ceq_tasklet(unsigned long ceq_data) +{ + struct hinic_eq *ceq = (struct hinic_eq *)ceq_data; + + eq_irq_handler(ceq); +} + +/** + * aeq_interrupt - aeq interrupt handler + * @irq: irq number + * @data: the Async Event Queue that collected the event + **/ +static irqreturn_t aeq_interrupt(int irq, void *data) +{ + struct hinic_eq_work *aeq_work; + struct hinic_eq *aeq = data; + struct hinic_aeqs *aeqs; + + /* clear resend timer cnt register */ + hinic_msix_attr_cnt_clear(aeq->hwif, aeq->msix_entry.entry); + + aeq_work = &aeq->aeq_work; + aeq_work->data = aeq; + + aeqs = aeq_to_aeqs(aeq); + queue_work(aeqs->workq, &aeq_work->work); + + return IRQ_HANDLED; +} + +/** + * ceq_interrupt - ceq interrupt handler + * @irq: irq number + * @data: the Completion Event Queue that collected the event + **/ +static irqreturn_t ceq_interrupt(int irq, void *data) +{ + struct hinic_eq *ceq = data; + + /* clear resend timer cnt register */ + hinic_msix_attr_cnt_clear(ceq->hwif, ceq->msix_entry.entry); + + tasklet_schedule(&ceq->ceq_tasklet); + + return IRQ_HANDLED; +} + +static void set_ctrl0(struct hinic_eq *eq) +{ + struct msix_entry *msix_entry = &eq->msix_entry; + enum hinic_eq_type type = eq->type; + u32 addr, val, ctrl0; + + if (type == HINIC_AEQ) { + /* RMW Ctrl0 */ + addr = HINIC_CSR_AEQ_CTRL_0_ADDR(eq->q_id); + + val = hinic_hwif_read_reg(eq->hwif, addr); + + val = HINIC_AEQ_CTRL_0_CLEAR(val, INT_IDX) & + HINIC_AEQ_CTRL_0_CLEAR(val, DMA_ATTR) & + HINIC_AEQ_CTRL_0_CLEAR(val, PCI_INTF_IDX) & + HINIC_AEQ_CTRL_0_CLEAR(val, INT_MODE); + + ctrl0 = HINIC_AEQ_CTRL_0_SET(msix_entry->entry, INT_IDX) | + HINIC_AEQ_CTRL_0_SET(DMA_ATTR_AEQ_DEFAULT, DMA_ATTR) | + HINIC_AEQ_CTRL_0_SET(HINIC_HWIF_PCI_INTF(eq->hwif), + PCI_INTF_IDX) | + HINIC_AEQ_CTRL_0_SET(EQ_INT_MODE_ARMED, INT_MODE); + + val |= ctrl0; + + hinic_hwif_write_reg(eq->hwif, addr, val); + } else if (type == HINIC_CEQ) { + /* RMW Ctrl0 */ + addr = HINIC_CSR_CEQ_CTRL_0_ADDR(eq->q_id); + + val = hinic_hwif_read_reg(eq->hwif, addr); + + val = HINIC_CEQ_CTRL_0_CLEAR(val, INTR_IDX) & + HINIC_CEQ_CTRL_0_CLEAR(val, DMA_ATTR) & + HINIC_CEQ_CTRL_0_CLEAR(val, KICK_THRESH) & + HINIC_CEQ_CTRL_0_CLEAR(val, PCI_INTF_IDX) & + HINIC_CEQ_CTRL_0_CLEAR(val, INTR_MODE); + + ctrl0 = HINIC_CEQ_CTRL_0_SET(msix_entry->entry, INTR_IDX) | + HINIC_CEQ_CTRL_0_SET(DMA_ATTR_CEQ_DEFAULT, DMA_ATTR) | + HINIC_CEQ_CTRL_0_SET(THRESH_CEQ_DEFAULT, KICK_THRESH) | + HINIC_CEQ_CTRL_0_SET(HINIC_HWIF_PCI_INTF(eq->hwif), + PCI_INTF_IDX) | + HINIC_CEQ_CTRL_0_SET(EQ_INT_MODE_ARMED, INTR_MODE); + + val |= ctrl0; + + hinic_hwif_write_reg(eq->hwif, addr, val); + } +} + +static void set_ctrl1(struct hinic_eq *eq) +{ + enum hinic_eq_type type = eq->type; + u32 page_size_val, elem_size; + u32 addr, val, ctrl1; + + if (type == HINIC_AEQ) { + /* RMW Ctrl1 */ + addr = HINIC_CSR_AEQ_CTRL_1_ADDR(eq->q_id); + + page_size_val = EQ_SET_HW_PAGE_SIZE_VAL(eq); + elem_size = EQ_SET_HW_ELEM_SIZE_VAL(eq); + + val = hinic_hwif_read_reg(eq->hwif, addr); + + val = HINIC_AEQ_CTRL_1_CLEAR(val, LEN) & + HINIC_AEQ_CTRL_1_CLEAR(val, ELEM_SIZE) & + HINIC_AEQ_CTRL_1_CLEAR(val, PAGE_SIZE); + + ctrl1 = HINIC_AEQ_CTRL_1_SET(eq->q_len, LEN) | + HINIC_AEQ_CTRL_1_SET(elem_size, ELEM_SIZE) | + HINIC_AEQ_CTRL_1_SET(page_size_val, PAGE_SIZE); + + val |= ctrl1; + + hinic_hwif_write_reg(eq->hwif, addr, val); + } else if (type == HINIC_CEQ) { + /* RMW Ctrl1 */ + addr = HINIC_CSR_CEQ_CTRL_1_ADDR(eq->q_id); + + page_size_val = EQ_SET_HW_PAGE_SIZE_VAL(eq); + + val = hinic_hwif_read_reg(eq->hwif, addr); + + val = HINIC_CEQ_CTRL_1_CLEAR(val, LEN) & + HINIC_CEQ_CTRL_1_CLEAR(val, PAGE_SIZE); + + ctrl1 = HINIC_CEQ_CTRL_1_SET(eq->q_len, LEN) | + HINIC_CEQ_CTRL_1_SET(page_size_val, PAGE_SIZE); + + val |= ctrl1; + + hinic_hwif_write_reg(eq->hwif, addr, val); + } +} + +/** + * set_eq_ctrls - setting eq's ctrl registers + * @eq: the Event Queue for setting + **/ +static void set_eq_ctrls(struct hinic_eq *eq) +{ + set_ctrl0(eq); + set_ctrl1(eq); +} + +/** + * aeq_elements_init - initialize all the elements in the aeq + * @eq: the Async Event Queue + * @init_val: value to initialize the elements with it + **/ +static void aeq_elements_init(struct hinic_eq *eq, u32 init_val) +{ + struct hinic_aeq_elem *aeqe; + int i; + + for (i = 0; i < eq->q_len; i++) { + aeqe = GET_AEQ_ELEM(eq, i); + aeqe->desc = cpu_to_be32(init_val); + } + + wmb(); /* Write the initilzation values */ +} + +/** + * ceq_elements_init - Initialize all the elements in the ceq + * @eq: the event queue + * @init_val: value to init with it the elements + **/ +static void ceq_elements_init(struct hinic_eq *eq, u32 init_val) +{ + u32 *ceqe; + int i; + + for (i = 0; i < eq->q_len; i++) { + ceqe = GET_CEQ_ELEM(eq, i); + *(ceqe) = cpu_to_be32(init_val); + } + + wmb(); /* Write the initilzation values */ +} + +/** + * alloc_eq_pages - allocate the pages for the queue + * @eq: the event queue + * + * Return 0 - Success, Negative - Failure + **/ +static int alloc_eq_pages(struct hinic_eq *eq) +{ + struct hinic_hwif *hwif = eq->hwif; + struct pci_dev *pdev = hwif->pdev; + u32 init_val, addr, val; + size_t addr_size; + int err, pg; + + addr_size = eq->num_pages * sizeof(*eq->dma_addr); + eq->dma_addr = devm_kzalloc(&pdev->dev, addr_size, GFP_KERNEL); + if (!eq->dma_addr) + return -ENOMEM; + + addr_size = eq->num_pages * sizeof(*eq->virt_addr); + eq->virt_addr = devm_kzalloc(&pdev->dev, addr_size, GFP_KERNEL); + if (!eq->virt_addr) { + err = -ENOMEM; + goto err_virt_addr_alloc; + } + + for (pg = 0; pg < eq->num_pages; pg++) { + eq->virt_addr[pg] = dma_zalloc_coherent(&pdev->dev, + eq->page_size, + &eq->dma_addr[pg], + GFP_KERNEL); + if (!eq->virt_addr[pg]) { + err = -ENOMEM; + goto err_dma_alloc; + } + + addr = EQ_HI_PHYS_ADDR_REG(eq, pg); + val = upper_32_bits(eq->dma_addr[pg]); + + hinic_hwif_write_reg(hwif, addr, val); + + addr = EQ_LO_PHYS_ADDR_REG(eq, pg); + val = lower_32_bits(eq->dma_addr[pg]); + + hinic_hwif_write_reg(hwif, addr, val); + } + + init_val = HINIC_EQ_ELEM_DESC_SET(eq->wrapped, WRAPPED); + + if (eq->type == HINIC_AEQ) + aeq_elements_init(eq, init_val); + else if (eq->type == HINIC_CEQ) + ceq_elements_init(eq, init_val); + + return 0; + +err_dma_alloc: + while (--pg >= 0) + dma_free_coherent(&pdev->dev, eq->page_size, + eq->virt_addr[pg], + eq->dma_addr[pg]); + + devm_kfree(&pdev->dev, eq->virt_addr); + +err_virt_addr_alloc: + devm_kfree(&pdev->dev, eq->dma_addr); + return err; +} + +/** + * free_eq_pages - free the pages of the queue + * @eq: the Event Queue + **/ +static void free_eq_pages(struct hinic_eq *eq) +{ + struct hinic_hwif *hwif = eq->hwif; + struct pci_dev *pdev = hwif->pdev; + int pg; + + for (pg = 0; pg < eq->num_pages; pg++) + dma_free_coherent(&pdev->dev, eq->page_size, + eq->virt_addr[pg], + eq->dma_addr[pg]); + + devm_kfree(&pdev->dev, eq->virt_addr); + devm_kfree(&pdev->dev, eq->dma_addr); +} + +/** + * init_eq - initialize Event Queue + * @eq: the event queue + * @hwif: the HW interface of a PCI function device + * @type: the type of the event queue, aeq or ceq + * @q_id: Queue id number + * @q_len: the number of EQ elements + * @page_size: the page size of the pages in the event queue + * @entry: msix entry associated with the event queue + * + * Return 0 - Success, Negative - Failure + **/ +static int init_eq(struct hinic_eq *eq, struct hinic_hwif *hwif, + enum hinic_eq_type type, int q_id, u32 q_len, u32 page_size, + struct msix_entry entry) +{ + struct pci_dev *pdev = hwif->pdev; + int err; + + eq->hwif = hwif; + eq->type = type; + eq->q_id = q_id; + eq->q_len = q_len; + eq->page_size = page_size; + + /* Clear PI and CI, also clear the ARM bit */ + hinic_hwif_write_reg(eq->hwif, EQ_CONS_IDX_REG_ADDR(eq), 0); + hinic_hwif_write_reg(eq->hwif, EQ_PROD_IDX_REG_ADDR(eq), 0); + + eq->cons_idx = 0; + eq->wrapped = 0; + + if (type == HINIC_AEQ) { + eq->elem_size = HINIC_AEQE_SIZE; + } else if (type == HINIC_CEQ) { + eq->elem_size = HINIC_CEQE_SIZE; + } else { + dev_err(&pdev->dev, "Invalid EQ type\n"); + return -EINVAL; + } + + eq->num_pages = GET_EQ_NUM_PAGES(eq, page_size); + eq->num_elem_in_pg = GET_EQ_NUM_ELEMS_IN_PG(eq, page_size); + + eq->msix_entry = entry; + + if (eq->num_elem_in_pg & (eq->num_elem_in_pg - 1)) { + dev_err(&pdev->dev, "num elements in eq page != power of 2\n"); + return -EINVAL; + } + + if (eq->num_pages > EQ_MAX_PAGES) { + dev_err(&pdev->dev, "too many pages for eq\n"); + return -EINVAL; + } + + set_eq_ctrls(eq); + eq_update_ci(eq); + + err = alloc_eq_pages(eq); + if (err) { + dev_err(&pdev->dev, "Failed to allocate pages for eq\n"); + return err; + } + + if (type == HINIC_AEQ) { + struct hinic_eq_work *aeq_work = &eq->aeq_work; + + INIT_WORK(&aeq_work->work, eq_irq_work); + } else if (type == HINIC_CEQ) { + tasklet_init(&eq->ceq_tasklet, ceq_tasklet, + (unsigned long)eq); + } + + /* set the attributes of the msix entry */ + hinic_msix_attr_set(eq->hwif, eq->msix_entry.entry, + HINIC_EQ_MSIX_PENDING_LIMIT_DEFAULT, + HINIC_EQ_MSIX_COALESC_TIMER_DEFAULT, + HINIC_EQ_MSIX_LLI_TIMER_DEFAULT, + HINIC_EQ_MSIX_LLI_CREDIT_LIMIT_DEFAULT, + HINIC_EQ_MSIX_RESEND_TIMER_DEFAULT); + + if (type == HINIC_AEQ) + err = request_irq(entry.vector, aeq_interrupt, 0, + "hinic_aeq", eq); + else if (type == HINIC_CEQ) + err = request_irq(entry.vector, ceq_interrupt, 0, + "hinic_ceq", eq); + + if (err) { + dev_err(&pdev->dev, "Failed to request irq for the EQ\n"); + goto err_req_irq; + } + + return 0; + +err_req_irq: + free_eq_pages(eq); + return err; +} + +/** + * remove_eq - remove Event Queue + * @eq: the event queue + **/ +static void remove_eq(struct hinic_eq *eq) +{ + struct msix_entry *entry = &eq->msix_entry; + + free_irq(entry->vector, eq); + + if (eq->type == HINIC_AEQ) { + struct hinic_eq_work *aeq_work = &eq->aeq_work; + + cancel_work_sync(&aeq_work->work); + } else if (eq->type == HINIC_CEQ) { + tasklet_kill(&eq->ceq_tasklet); + } + + free_eq_pages(eq); +} + +/** + * hinic_aeqs_init - initialize all the aeqs + * @aeqs: pointer to Async eqs of the chip + * @hwif: the HW interface of a PCI function device + * @num_aeqs: number of AEQs + * @q_len: number of EQ elements + * @page_size: the page size of the pages in the event queue + * @msix_entries: msix entries associated with the event queues + * + * Return 0 - Success, negative - Failure + **/ +int hinic_aeqs_init(struct hinic_aeqs *aeqs, struct hinic_hwif *hwif, + int num_aeqs, u32 q_len, u32 page_size, + struct msix_entry *msix_entries) +{ + struct pci_dev *pdev = hwif->pdev; + int err, i, q_id; + + aeqs->workq = create_singlethread_workqueue(HINIC_EQS_WQ_NAME); + if (!aeqs->workq) + return -ENOMEM; + + aeqs->hwif = hwif; + aeqs->num_aeqs = num_aeqs; + + for (q_id = 0; q_id < num_aeqs; q_id++) { + err = init_eq(&aeqs->aeq[q_id], hwif, HINIC_AEQ, q_id, q_len, + page_size, msix_entries[q_id]); + if (err) { + dev_err(&pdev->dev, "Failed to init aeq %d\n", q_id); + goto err_init_aeq; + } + } + + return 0; + +err_init_aeq: + for (i = 0; i < q_id; i++) + remove_eq(&aeqs->aeq[i]); + + destroy_workqueue(aeqs->workq); + return err; +} + +/** + * hinic_aeqs_free - free all the aeqs + * @aeqs: pointer to Async eqs of the chip + **/ +void hinic_aeqs_free(struct hinic_aeqs *aeqs) +{ + int q_id; + + for (q_id = 0; q_id < aeqs->num_aeqs ; q_id++) + remove_eq(&aeqs->aeq[q_id]); + + destroy_workqueue(aeqs->workq); +} + +/** + * hinic_ceqs_init - init all the ceqs + * @ceqs: ceqs part of the chip + * @hwif: the hardware interface of a pci function device + * @num_ceqs: number of CEQs + * @q_len: number of EQ elements + * @page_size: the page size of the event queue + * @msix_entries: msix entries associated with the event queues + * + * Return 0 - Success, Negative - Failure + **/ +int hinic_ceqs_init(struct hinic_ceqs *ceqs, struct hinic_hwif *hwif, + int num_ceqs, u32 q_len, u32 page_size, + struct msix_entry *msix_entries) +{ + struct pci_dev *pdev = hwif->pdev; + int i, q_id, err; + + ceqs->hwif = hwif; + ceqs->num_ceqs = num_ceqs; + + for (q_id = 0; q_id < num_ceqs; q_id++) { + err = init_eq(&ceqs->ceq[q_id], hwif, HINIC_CEQ, q_id, q_len, + page_size, msix_entries[q_id]); + if (err) { + dev_err(&pdev->dev, "Failed to init ceq %d\n", q_id); + goto err_init_ceq; + } + } + + return 0; + +err_init_ceq: + for (i = 0; i < q_id; i++) + remove_eq(&ceqs->ceq[i]); + + return err; +} + +/** + * hinic_ceqs_free - free all the ceqs + * @ceqs: ceqs part of the chip + **/ +void hinic_ceqs_free(struct hinic_ceqs *ceqs) +{ + int q_id; + + for (q_id = 0; q_id < ceqs->num_ceqs; q_id++) + remove_eq(&ceqs->ceq[q_id]); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h new file mode 100644 index 000000000000..ecb9c2bc6dc8 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.h @@ -0,0 +1,265 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_EQS_H +#define HINIC_HW_EQS_H + +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/pci.h> +#include <linux/sizes.h> +#include <linux/bitops.h> +#include <linux/interrupt.h> + +#include "hinic_hw_if.h" + +#define HINIC_AEQ_CTRL_0_INT_IDX_SHIFT 0 +#define HINIC_AEQ_CTRL_0_DMA_ATTR_SHIFT 12 +#define HINIC_AEQ_CTRL_0_PCI_INTF_IDX_SHIFT 20 +#define HINIC_AEQ_CTRL_0_INT_MODE_SHIFT 31 + +#define HINIC_AEQ_CTRL_0_INT_IDX_MASK 0x3FF +#define HINIC_AEQ_CTRL_0_DMA_ATTR_MASK 0x3F +#define HINIC_AEQ_CTRL_0_PCI_INTF_IDX_MASK 0x3 +#define HINIC_AEQ_CTRL_0_INT_MODE_MASK 0x1 + +#define HINIC_AEQ_CTRL_0_SET(val, member) \ + (((u32)(val) & HINIC_AEQ_CTRL_0_##member##_MASK) << \ + HINIC_AEQ_CTRL_0_##member##_SHIFT) + +#define HINIC_AEQ_CTRL_0_CLEAR(val, member) \ + ((val) & (~(HINIC_AEQ_CTRL_0_##member##_MASK \ + << HINIC_AEQ_CTRL_0_##member##_SHIFT))) + +#define HINIC_AEQ_CTRL_1_LEN_SHIFT 0 +#define HINIC_AEQ_CTRL_1_ELEM_SIZE_SHIFT 24 +#define HINIC_AEQ_CTRL_1_PAGE_SIZE_SHIFT 28 + +#define HINIC_AEQ_CTRL_1_LEN_MASK 0x1FFFFF +#define HINIC_AEQ_CTRL_1_ELEM_SIZE_MASK 0x3 +#define HINIC_AEQ_CTRL_1_PAGE_SIZE_MASK 0xF + +#define HINIC_AEQ_CTRL_1_SET(val, member) \ + (((u32)(val) & HINIC_AEQ_CTRL_1_##member##_MASK) << \ + HINIC_AEQ_CTRL_1_##member##_SHIFT) + +#define HINIC_AEQ_CTRL_1_CLEAR(val, member) \ + ((val) & (~(HINIC_AEQ_CTRL_1_##member##_MASK \ + << HINIC_AEQ_CTRL_1_##member##_SHIFT))) + +#define HINIC_CEQ_CTRL_0_INTR_IDX_SHIFT 0 +#define HINIC_CEQ_CTRL_0_DMA_ATTR_SHIFT 12 +#define HINIC_CEQ_CTRL_0_KICK_THRESH_SHIFT 20 +#define HINIC_CEQ_CTRL_0_PCI_INTF_IDX_SHIFT 24 +#define HINIC_CEQ_CTRL_0_INTR_MODE_SHIFT 31 + +#define HINIC_CEQ_CTRL_0_INTR_IDX_MASK 0x3FF +#define HINIC_CEQ_CTRL_0_DMA_ATTR_MASK 0x3F +#define HINIC_CEQ_CTRL_0_KICK_THRESH_MASK 0xF +#define HINIC_CEQ_CTRL_0_PCI_INTF_IDX_MASK 0x3 +#define HINIC_CEQ_CTRL_0_INTR_MODE_MASK 0x1 + +#define HINIC_CEQ_CTRL_0_SET(val, member) \ + (((u32)(val) & HINIC_CEQ_CTRL_0_##member##_MASK) << \ + HINIC_CEQ_CTRL_0_##member##_SHIFT) + +#define HINIC_CEQ_CTRL_0_CLEAR(val, member) \ + ((val) & (~(HINIC_CEQ_CTRL_0_##member##_MASK \ + << HINIC_CEQ_CTRL_0_##member##_SHIFT))) + +#define HINIC_CEQ_CTRL_1_LEN_SHIFT 0 +#define HINIC_CEQ_CTRL_1_PAGE_SIZE_SHIFT 28 + +#define HINIC_CEQ_CTRL_1_LEN_MASK 0x1FFFFF +#define HINIC_CEQ_CTRL_1_PAGE_SIZE_MASK 0xF + +#define HINIC_CEQ_CTRL_1_SET(val, member) \ + (((u32)(val) & HINIC_CEQ_CTRL_1_##member##_MASK) << \ + HINIC_CEQ_CTRL_1_##member##_SHIFT) + +#define HINIC_CEQ_CTRL_1_CLEAR(val, member) \ + ((val) & (~(HINIC_CEQ_CTRL_1_##member##_MASK \ + << HINIC_CEQ_CTRL_1_##member##_SHIFT))) + +#define HINIC_EQ_ELEM_DESC_TYPE_SHIFT 0 +#define HINIC_EQ_ELEM_DESC_SRC_SHIFT 7 +#define HINIC_EQ_ELEM_DESC_SIZE_SHIFT 8 +#define HINIC_EQ_ELEM_DESC_WRAPPED_SHIFT 31 + +#define HINIC_EQ_ELEM_DESC_TYPE_MASK 0x7F +#define HINIC_EQ_ELEM_DESC_SRC_MASK 0x1 +#define HINIC_EQ_ELEM_DESC_SIZE_MASK 0xFF +#define HINIC_EQ_ELEM_DESC_WRAPPED_MASK 0x1 + +#define HINIC_EQ_ELEM_DESC_SET(val, member) \ + (((u32)(val) & HINIC_EQ_ELEM_DESC_##member##_MASK) << \ + HINIC_EQ_ELEM_DESC_##member##_SHIFT) + +#define HINIC_EQ_ELEM_DESC_GET(val, member) \ + (((val) >> HINIC_EQ_ELEM_DESC_##member##_SHIFT) & \ + HINIC_EQ_ELEM_DESC_##member##_MASK) + +#define HINIC_EQ_CI_IDX_SHIFT 0 +#define HINIC_EQ_CI_WRAPPED_SHIFT 20 +#define HINIC_EQ_CI_XOR_CHKSUM_SHIFT 24 +#define HINIC_EQ_CI_INT_ARMED_SHIFT 31 + +#define HINIC_EQ_CI_IDX_MASK 0xFFFFF +#define HINIC_EQ_CI_WRAPPED_MASK 0x1 +#define HINIC_EQ_CI_XOR_CHKSUM_MASK 0xF +#define HINIC_EQ_CI_INT_ARMED_MASK 0x1 + +#define HINIC_EQ_CI_SET(val, member) \ + (((u32)(val) & HINIC_EQ_CI_##member##_MASK) << \ + HINIC_EQ_CI_##member##_SHIFT) + +#define HINIC_EQ_CI_CLEAR(val, member) \ + ((val) & (~(HINIC_EQ_CI_##member##_MASK \ + << HINIC_EQ_CI_##member##_SHIFT))) + +#define HINIC_MAX_AEQS 4 +#define HINIC_MAX_CEQS 32 + +#define HINIC_AEQE_SIZE 64 +#define HINIC_CEQE_SIZE 4 + +#define HINIC_AEQE_DESC_SIZE 4 +#define HINIC_AEQE_DATA_SIZE \ + (HINIC_AEQE_SIZE - HINIC_AEQE_DESC_SIZE) + +#define HINIC_DEFAULT_AEQ_LEN 64 +#define HINIC_DEFAULT_CEQ_LEN 1024 + +#define HINIC_EQ_PAGE_SIZE SZ_4K + +#define HINIC_CEQ_ID_CMDQ 0 + +enum hinic_eq_type { + HINIC_AEQ, + HINIC_CEQ, +}; + +enum hinic_aeq_type { + HINIC_MSG_FROM_MGMT_CPU = 2, + + HINIC_MAX_AEQ_EVENTS, +}; + +enum hinic_ceq_type { + HINIC_CEQ_CMDQ = 3, + + HINIC_MAX_CEQ_EVENTS, +}; + +enum hinic_eqe_state { + HINIC_EQE_ENABLED = BIT(0), + HINIC_EQE_RUNNING = BIT(1), +}; + +struct hinic_aeq_elem { + u8 data[HINIC_AEQE_DATA_SIZE]; + u32 desc; +}; + +struct hinic_eq_work { + struct work_struct work; + void *data; +}; + +struct hinic_eq { + struct hinic_hwif *hwif; + + enum hinic_eq_type type; + int q_id; + u32 q_len; + u32 page_size; + + u32 cons_idx; + int wrapped; + + size_t elem_size; + int num_pages; + int num_elem_in_pg; + + struct msix_entry msix_entry; + + dma_addr_t *dma_addr; + void **virt_addr; + + struct hinic_eq_work aeq_work; + + struct tasklet_struct ceq_tasklet; +}; + +struct hinic_hw_event_cb { + void (*hwe_handler)(void *handle, void *data, u8 size); + void *handle; + unsigned long hwe_state; +}; + +struct hinic_aeqs { + struct hinic_hwif *hwif; + + struct hinic_eq aeq[HINIC_MAX_AEQS]; + int num_aeqs; + + struct hinic_hw_event_cb hwe_cb[HINIC_MAX_AEQ_EVENTS]; + + struct workqueue_struct *workq; +}; + +struct hinic_ceq_cb { + void (*handler)(void *handle, u32 ceqe_data); + void *handle; + enum hinic_eqe_state ceqe_state; +}; + +struct hinic_ceqs { + struct hinic_hwif *hwif; + + struct hinic_eq ceq[HINIC_MAX_CEQS]; + int num_ceqs; + + struct hinic_ceq_cb ceq_cb[HINIC_MAX_CEQ_EVENTS]; +}; + +void hinic_aeq_register_hw_cb(struct hinic_aeqs *aeqs, + enum hinic_aeq_type event, void *handle, + void (*hwe_handler)(void *handle, void *data, + u8 size)); + +void hinic_aeq_unregister_hw_cb(struct hinic_aeqs *aeqs, + enum hinic_aeq_type event); + +void hinic_ceq_register_cb(struct hinic_ceqs *ceqs, + enum hinic_ceq_type event, void *handle, + void (*ceq_cb)(void *handle, u32 ceqe_data)); + +void hinic_ceq_unregister_cb(struct hinic_ceqs *ceqs, + enum hinic_ceq_type event); + +int hinic_aeqs_init(struct hinic_aeqs *aeqs, struct hinic_hwif *hwif, + int num_aeqs, u32 q_len, u32 page_size, + struct msix_entry *msix_entries); + +void hinic_aeqs_free(struct hinic_aeqs *aeqs); + +int hinic_ceqs_init(struct hinic_ceqs *ceqs, struct hinic_hwif *hwif, + int num_ceqs, u32 q_len, u32 page_size, + struct msix_entry *msix_entries); + +void hinic_ceqs_free(struct hinic_ceqs *ceqs); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c new file mode 100644 index 000000000000..823a17061a97 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c @@ -0,0 +1,351 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/types.h> +#include <linux/bitops.h> + +#include "hinic_hw_csr.h" +#include "hinic_hw_if.h" + +#define PCIE_ATTR_ENTRY 0 + +#define VALID_MSIX_IDX(attr, msix_index) ((msix_index) < (attr)->num_irqs) + +/** + * hinic_msix_attr_set - set message attribute for msix entry + * @hwif: the HW interface of a pci function device + * @msix_index: msix_index + * @pending_limit: the maximum pending interrupt events (unit 8) + * @coalesc_timer: coalesc period for interrupt (unit 8 us) + * @lli_timer: replenishing period for low latency credit (unit 8 us) + * @lli_credit_limit: maximum credits for low latency msix messages (unit 8) + * @resend_timer: maximum wait for resending msix (unit coalesc period) + * + * Return 0 - Success, negative - Failure + **/ +int hinic_msix_attr_set(struct hinic_hwif *hwif, u16 msix_index, + u8 pending_limit, u8 coalesc_timer, + u8 lli_timer, u8 lli_credit_limit, + u8 resend_timer) +{ + u32 msix_ctrl, addr; + + if (!VALID_MSIX_IDX(&hwif->attr, msix_index)) + return -EINVAL; + + msix_ctrl = HINIC_MSIX_ATTR_SET(pending_limit, PENDING_LIMIT) | + HINIC_MSIX_ATTR_SET(coalesc_timer, COALESC_TIMER) | + HINIC_MSIX_ATTR_SET(lli_timer, LLI_TIMER) | + HINIC_MSIX_ATTR_SET(lli_credit_limit, LLI_CREDIT) | + HINIC_MSIX_ATTR_SET(resend_timer, RESEND_TIMER); + + addr = HINIC_CSR_MSIX_CTRL_ADDR(msix_index); + + hinic_hwif_write_reg(hwif, addr, msix_ctrl); + return 0; +} + +/** + * hinic_msix_attr_get - get message attribute of msix entry + * @hwif: the HW interface of a pci function device + * @msix_index: msix_index + * @pending_limit: the maximum pending interrupt events (unit 8) + * @coalesc_timer: coalesc period for interrupt (unit 8 us) + * @lli_timer: replenishing period for low latency credit (unit 8 us) + * @lli_credit_limit: maximum credits for low latency msix messages (unit 8) + * @resend_timer: maximum wait for resending msix (unit coalesc period) + * + * Return 0 - Success, negative - Failure + **/ +int hinic_msix_attr_get(struct hinic_hwif *hwif, u16 msix_index, + u8 *pending_limit, u8 *coalesc_timer, + u8 *lli_timer, u8 *lli_credit_limit, + u8 *resend_timer) +{ + u32 addr, val; + + if (!VALID_MSIX_IDX(&hwif->attr, msix_index)) + return -EINVAL; + + addr = HINIC_CSR_MSIX_CTRL_ADDR(msix_index); + val = hinic_hwif_read_reg(hwif, addr); + + *pending_limit = HINIC_MSIX_ATTR_GET(val, PENDING_LIMIT); + *coalesc_timer = HINIC_MSIX_ATTR_GET(val, COALESC_TIMER); + *lli_timer = HINIC_MSIX_ATTR_GET(val, LLI_TIMER); + *lli_credit_limit = HINIC_MSIX_ATTR_GET(val, LLI_CREDIT); + *resend_timer = HINIC_MSIX_ATTR_GET(val, RESEND_TIMER); + return 0; +} + +/** + * hinic_msix_attr_cnt_clear - clear message attribute counters for msix entry + * @hwif: the HW interface of a pci function device + * @msix_index: msix_index + * + * Return 0 - Success, negative - Failure + **/ +int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index) +{ + u32 msix_ctrl, addr; + + if (!VALID_MSIX_IDX(&hwif->attr, msix_index)) + return -EINVAL; + + msix_ctrl = HINIC_MSIX_CNT_SET(1, RESEND_TIMER); + addr = HINIC_CSR_MSIX_CNT_ADDR(msix_index); + + hinic_hwif_write_reg(hwif, addr, msix_ctrl); + return 0; +} + +/** + * hinic_set_pf_action - set action on pf channel + * @hwif: the HW interface of a pci function device + * @action: action on pf channel + * + * Return 0 - Success, negative - Failure + **/ +void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action) +{ + u32 attr5 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR); + + attr5 = HINIC_FA5_CLEAR(attr5, PF_ACTION); + attr5 |= HINIC_FA5_SET(action, PF_ACTION); + + hinic_hwif_write_reg(hwif, HINIC_CSR_FUNC_ATTR5_ADDR, attr5); +} + +enum hinic_outbound_state hinic_outbound_state_get(struct hinic_hwif *hwif) +{ + u32 attr4 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR); + + return HINIC_FA4_GET(attr4, OUTBOUND_STATE); +} + +void hinic_outbound_state_set(struct hinic_hwif *hwif, + enum hinic_outbound_state outbound_state) +{ + u32 attr4 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR); + + attr4 = HINIC_FA4_CLEAR(attr4, OUTBOUND_STATE); + attr4 |= HINIC_FA4_SET(outbound_state, OUTBOUND_STATE); + + hinic_hwif_write_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR, attr4); +} + +enum hinic_db_state hinic_db_state_get(struct hinic_hwif *hwif) +{ + u32 attr4 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR); + + return HINIC_FA4_GET(attr4, DB_STATE); +} + +void hinic_db_state_set(struct hinic_hwif *hwif, + enum hinic_db_state db_state) +{ + u32 attr4 = hinic_hwif_read_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR); + + attr4 = HINIC_FA4_CLEAR(attr4, DB_STATE); + attr4 |= HINIC_FA4_SET(db_state, DB_STATE); + + hinic_hwif_write_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR, attr4); +} + +/** + * hwif_ready - test if the HW is ready for use + * @hwif: the HW interface of a pci function device + * + * Return 0 - Success, negative - Failure + **/ +static int hwif_ready(struct hinic_hwif *hwif) +{ + struct pci_dev *pdev = hwif->pdev; + u32 addr, attr1; + + addr = HINIC_CSR_FUNC_ATTR1_ADDR; + attr1 = hinic_hwif_read_reg(hwif, addr); + + if (!HINIC_FA1_GET(attr1, INIT_STATUS)) { + dev_err(&pdev->dev, "hwif status is not ready\n"); + return -EFAULT; + } + + return 0; +} + +/** + * set_hwif_attr - set the attributes in the relevant members in hwif + * @hwif: the HW interface of a pci function device + * @attr0: the first attribute that was read from the hw + * @attr1: the second attribute that was read from the hw + **/ +static void set_hwif_attr(struct hinic_hwif *hwif, u32 attr0, u32 attr1) +{ + hwif->attr.func_idx = HINIC_FA0_GET(attr0, FUNC_IDX); + hwif->attr.pf_idx = HINIC_FA0_GET(attr0, PF_IDX); + hwif->attr.pci_intf_idx = HINIC_FA0_GET(attr0, PCI_INTF_IDX); + hwif->attr.func_type = HINIC_FA0_GET(attr0, FUNC_TYPE); + + hwif->attr.num_aeqs = BIT(HINIC_FA1_GET(attr1, AEQS_PER_FUNC)); + hwif->attr.num_ceqs = BIT(HINIC_FA1_GET(attr1, CEQS_PER_FUNC)); + hwif->attr.num_irqs = BIT(HINIC_FA1_GET(attr1, IRQS_PER_FUNC)); + hwif->attr.num_dma_attr = BIT(HINIC_FA1_GET(attr1, DMA_ATTR_PER_FUNC)); +} + +/** + * read_hwif_attr - read the attributes and set members in hwif + * @hwif: the HW interface of a pci function device + **/ +static void read_hwif_attr(struct hinic_hwif *hwif) +{ + u32 addr, attr0, attr1; + + addr = HINIC_CSR_FUNC_ATTR0_ADDR; + attr0 = hinic_hwif_read_reg(hwif, addr); + + addr = HINIC_CSR_FUNC_ATTR1_ADDR; + attr1 = hinic_hwif_read_reg(hwif, addr); + + set_hwif_attr(hwif, attr0, attr1); +} + +/** + * set_ppf - try to set hwif as ppf and set the type of hwif in this case + * @hwif: the HW interface of a pci function device + **/ +static void set_ppf(struct hinic_hwif *hwif) +{ + struct hinic_func_attr *attr = &hwif->attr; + u32 addr, val, ppf_election; + + /* Read Modify Write */ + addr = HINIC_CSR_PPF_ELECTION_ADDR(HINIC_HWIF_PCI_INTF(hwif)); + + val = hinic_hwif_read_reg(hwif, addr); + val = HINIC_PPF_ELECTION_CLEAR(val, IDX); + + ppf_election = HINIC_PPF_ELECTION_SET(HINIC_HWIF_FUNC_IDX(hwif), IDX); + + val |= ppf_election; + hinic_hwif_write_reg(hwif, addr, val); + + /* check PPF */ + val = hinic_hwif_read_reg(hwif, addr); + + attr->ppf_idx = HINIC_PPF_ELECTION_GET(val, IDX); + if (attr->ppf_idx == HINIC_HWIF_FUNC_IDX(hwif)) + attr->func_type = HINIC_PPF; +} + +/** + * set_dma_attr - set the dma attributes in the HW + * @hwif: the HW interface of a pci function device + * @entry_idx: the entry index in the dma table + * @st: PCIE TLP steering tag + * @at: PCIE TLP AT field + * @ph: PCIE TLP Processing Hint field + * @no_snooping: PCIE TLP No snooping + * @tph_en: PCIE TLP Processing Hint Enable + **/ +static void set_dma_attr(struct hinic_hwif *hwif, u32 entry_idx, + u8 st, u8 at, u8 ph, + enum hinic_pcie_nosnoop no_snooping, + enum hinic_pcie_tph tph_en) +{ + u32 addr, val, dma_attr_entry; + + /* Read Modify Write */ + addr = HINIC_CSR_DMA_ATTR_ADDR(entry_idx); + + val = hinic_hwif_read_reg(hwif, addr); + val = HINIC_DMA_ATTR_CLEAR(val, ST) & + HINIC_DMA_ATTR_CLEAR(val, AT) & + HINIC_DMA_ATTR_CLEAR(val, PH) & + HINIC_DMA_ATTR_CLEAR(val, NO_SNOOPING) & + HINIC_DMA_ATTR_CLEAR(val, TPH_EN); + + dma_attr_entry = HINIC_DMA_ATTR_SET(st, ST) | + HINIC_DMA_ATTR_SET(at, AT) | + HINIC_DMA_ATTR_SET(ph, PH) | + HINIC_DMA_ATTR_SET(no_snooping, NO_SNOOPING) | + HINIC_DMA_ATTR_SET(tph_en, TPH_EN); + + val |= dma_attr_entry; + hinic_hwif_write_reg(hwif, addr, val); +} + +/** + * dma_attr_table_init - initialize the the default dma attributes + * @hwif: the HW interface of a pci function device + **/ +static void dma_attr_init(struct hinic_hwif *hwif) +{ + set_dma_attr(hwif, PCIE_ATTR_ENTRY, HINIC_PCIE_ST_DISABLE, + HINIC_PCIE_AT_DISABLE, HINIC_PCIE_PH_DISABLE, + HINIC_PCIE_SNOOP, HINIC_PCIE_TPH_DISABLE); +} + +/** + * hinic_init_hwif - initialize the hw interface + * @hwif: the HW interface of a pci function device + * @pdev: the pci device for acessing PCI resources + * + * Return 0 - Success, negative - Failure + **/ +int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev) +{ + int err; + + hwif->pdev = pdev; + + hwif->cfg_regs_bar = pci_ioremap_bar(pdev, HINIC_PCI_CFG_REGS_BAR); + if (!hwif->cfg_regs_bar) { + dev_err(&pdev->dev, "Failed to map configuration regs\n"); + return -ENOMEM; + } + + err = hwif_ready(hwif); + if (err) { + dev_err(&pdev->dev, "HW interface is not ready\n"); + goto err_hwif_ready; + } + + read_hwif_attr(hwif); + + if (HINIC_IS_PF(hwif)) + set_ppf(hwif); + + /* No transactionss before DMA is initialized */ + dma_attr_init(hwif); + return 0; + +err_hwif_ready: + iounmap(hwif->cfg_regs_bar); + return err; +} + +/** + * hinic_free_hwif - free the HW interface + * @hwif: the HW interface of a pci function device + **/ +void hinic_free_hwif(struct hinic_hwif *hwif) +{ + iounmap(hwif->cfg_regs_bar); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h new file mode 100644 index 000000000000..5b4760c0e9f5 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h @@ -0,0 +1,272 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_IF_H +#define HINIC_HW_IF_H + +#include <linux/pci.h> +#include <linux/io.h> +#include <linux/types.h> +#include <asm/byteorder.h> + +#define HINIC_DMA_ATTR_ST_SHIFT 0 +#define HINIC_DMA_ATTR_AT_SHIFT 8 +#define HINIC_DMA_ATTR_PH_SHIFT 10 +#define HINIC_DMA_ATTR_NO_SNOOPING_SHIFT 12 +#define HINIC_DMA_ATTR_TPH_EN_SHIFT 13 + +#define HINIC_DMA_ATTR_ST_MASK 0xFF +#define HINIC_DMA_ATTR_AT_MASK 0x3 +#define HINIC_DMA_ATTR_PH_MASK 0x3 +#define HINIC_DMA_ATTR_NO_SNOOPING_MASK 0x1 +#define HINIC_DMA_ATTR_TPH_EN_MASK 0x1 + +#define HINIC_DMA_ATTR_SET(val, member) \ + (((u32)(val) & HINIC_DMA_ATTR_##member##_MASK) << \ + HINIC_DMA_ATTR_##member##_SHIFT) + +#define HINIC_DMA_ATTR_CLEAR(val, member) \ + ((val) & (~(HINIC_DMA_ATTR_##member##_MASK \ + << HINIC_DMA_ATTR_##member##_SHIFT))) + +#define HINIC_FA0_FUNC_IDX_SHIFT 0 +#define HINIC_FA0_PF_IDX_SHIFT 10 +#define HINIC_FA0_PCI_INTF_IDX_SHIFT 14 +/* reserved members - off 16 */ +#define HINIC_FA0_FUNC_TYPE_SHIFT 24 + +#define HINIC_FA0_FUNC_IDX_MASK 0x3FF +#define HINIC_FA0_PF_IDX_MASK 0xF +#define HINIC_FA0_PCI_INTF_IDX_MASK 0x3 +#define HINIC_FA0_FUNC_TYPE_MASK 0x1 + +#define HINIC_FA0_GET(val, member) \ + (((val) >> HINIC_FA0_##member##_SHIFT) & HINIC_FA0_##member##_MASK) + +#define HINIC_FA1_AEQS_PER_FUNC_SHIFT 8 +/* reserved members - off 10 */ +#define HINIC_FA1_CEQS_PER_FUNC_SHIFT 12 +/* reserved members - off 15 */ +#define HINIC_FA1_IRQS_PER_FUNC_SHIFT 20 +#define HINIC_FA1_DMA_ATTR_PER_FUNC_SHIFT 24 +/* reserved members - off 27 */ +#define HINIC_FA1_INIT_STATUS_SHIFT 30 + +#define HINIC_FA1_AEQS_PER_FUNC_MASK 0x3 +#define HINIC_FA1_CEQS_PER_FUNC_MASK 0x7 +#define HINIC_FA1_IRQS_PER_FUNC_MASK 0xF +#define HINIC_FA1_DMA_ATTR_PER_FUNC_MASK 0x7 +#define HINIC_FA1_INIT_STATUS_MASK 0x1 + +#define HINIC_FA1_GET(val, member) \ + (((val) >> HINIC_FA1_##member##_SHIFT) & HINIC_FA1_##member##_MASK) + +#define HINIC_FA4_OUTBOUND_STATE_SHIFT 0 +#define HINIC_FA4_DB_STATE_SHIFT 1 + +#define HINIC_FA4_OUTBOUND_STATE_MASK 0x1 +#define HINIC_FA4_DB_STATE_MASK 0x1 + +#define HINIC_FA4_GET(val, member) \ + (((val) >> HINIC_FA4_##member##_SHIFT) & HINIC_FA4_##member##_MASK) + +#define HINIC_FA4_SET(val, member) \ + ((((u32)val) & HINIC_FA4_##member##_MASK) << HINIC_FA4_##member##_SHIFT) + +#define HINIC_FA4_CLEAR(val, member) \ + ((val) & (~(HINIC_FA4_##member##_MASK << HINIC_FA4_##member##_SHIFT))) + +#define HINIC_FA5_PF_ACTION_SHIFT 0 +#define HINIC_FA5_PF_ACTION_MASK 0xFFFF + +#define HINIC_FA5_SET(val, member) \ + (((u32)(val) & HINIC_FA5_##member##_MASK) << HINIC_FA5_##member##_SHIFT) + +#define HINIC_FA5_CLEAR(val, member) \ + ((val) & (~(HINIC_FA5_##member##_MASK << HINIC_FA5_##member##_SHIFT))) + +#define HINIC_PPF_ELECTION_IDX_SHIFT 0 +#define HINIC_PPF_ELECTION_IDX_MASK 0x1F + +#define HINIC_PPF_ELECTION_SET(val, member) \ + (((u32)(val) & HINIC_PPF_ELECTION_##member##_MASK) << \ + HINIC_PPF_ELECTION_##member##_SHIFT) + +#define HINIC_PPF_ELECTION_GET(val, member) \ + (((val) >> HINIC_PPF_ELECTION_##member##_SHIFT) & \ + HINIC_PPF_ELECTION_##member##_MASK) + +#define HINIC_PPF_ELECTION_CLEAR(val, member) \ + ((val) & (~(HINIC_PPF_ELECTION_##member##_MASK \ + << HINIC_PPF_ELECTION_##member##_SHIFT))) + +#define HINIC_MSIX_PENDING_LIMIT_SHIFT 0 +#define HINIC_MSIX_COALESC_TIMER_SHIFT 8 +#define HINIC_MSIX_LLI_TIMER_SHIFT 16 +#define HINIC_MSIX_LLI_CREDIT_SHIFT 24 +#define HINIC_MSIX_RESEND_TIMER_SHIFT 29 + +#define HINIC_MSIX_PENDING_LIMIT_MASK 0xFF +#define HINIC_MSIX_COALESC_TIMER_MASK 0xFF +#define HINIC_MSIX_LLI_TIMER_MASK 0xFF +#define HINIC_MSIX_LLI_CREDIT_MASK 0x1F +#define HINIC_MSIX_RESEND_TIMER_MASK 0x7 + +#define HINIC_MSIX_ATTR_SET(val, member) \ + (((u32)(val) & HINIC_MSIX_##member##_MASK) << \ + HINIC_MSIX_##member##_SHIFT) + +#define HINIC_MSIX_ATTR_GET(val, member) \ + (((val) >> HINIC_MSIX_##member##_SHIFT) & \ + HINIC_MSIX_##member##_MASK) + +#define HINIC_MSIX_CNT_RESEND_TIMER_SHIFT 29 + +#define HINIC_MSIX_CNT_RESEND_TIMER_MASK 0x1 + +#define HINIC_MSIX_CNT_SET(val, member) \ + (((u32)(val) & HINIC_MSIX_CNT_##member##_MASK) << \ + HINIC_MSIX_CNT_##member##_SHIFT) + +#define HINIC_HWIF_NUM_AEQS(hwif) ((hwif)->attr.num_aeqs) +#define HINIC_HWIF_NUM_CEQS(hwif) ((hwif)->attr.num_ceqs) +#define HINIC_HWIF_NUM_IRQS(hwif) ((hwif)->attr.num_irqs) +#define HINIC_HWIF_FUNC_IDX(hwif) ((hwif)->attr.func_idx) +#define HINIC_HWIF_PCI_INTF(hwif) ((hwif)->attr.pci_intf_idx) +#define HINIC_HWIF_PF_IDX(hwif) ((hwif)->attr.pf_idx) + +#define HINIC_FUNC_TYPE(hwif) ((hwif)->attr.func_type) +#define HINIC_IS_PF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PF) +#define HINIC_IS_PPF(hwif) (HINIC_FUNC_TYPE(hwif) == HINIC_PPF) + +#define HINIC_PCI_CFG_REGS_BAR 0 +#define HINIC_PCI_DB_BAR 4 + +#define HINIC_PCIE_ST_DISABLE 0 +#define HINIC_PCIE_AT_DISABLE 0 +#define HINIC_PCIE_PH_DISABLE 0 + +#define HINIC_EQ_MSIX_PENDING_LIMIT_DEFAULT 0 /* Disabled */ +#define HINIC_EQ_MSIX_COALESC_TIMER_DEFAULT 0xFF /* max */ +#define HINIC_EQ_MSIX_LLI_TIMER_DEFAULT 0 /* Disabled */ +#define HINIC_EQ_MSIX_LLI_CREDIT_LIMIT_DEFAULT 0 /* Disabled */ +#define HINIC_EQ_MSIX_RESEND_TIMER_DEFAULT 7 /* max */ + +enum hinic_pcie_nosnoop { + HINIC_PCIE_SNOOP = 0, + HINIC_PCIE_NO_SNOOP = 1, +}; + +enum hinic_pcie_tph { + HINIC_PCIE_TPH_DISABLE = 0, + HINIC_PCIE_TPH_ENABLE = 1, +}; + +enum hinic_func_type { + HINIC_PF = 0, + HINIC_PPF = 2, +}; + +enum hinic_mod_type { + HINIC_MOD_COMM = 0, /* HW communication module */ + HINIC_MOD_L2NIC = 1, /* L2NIC module */ + HINIC_MOD_CFGM = 7, /* Configuration module */ + + HINIC_MOD_MAX = 15 +}; + +enum hinic_node_id { + HINIC_NODE_ID_MGMT = 21, +}; + +enum hinic_pf_action { + HINIC_PF_MGMT_INIT = 0x0, + + HINIC_PF_MGMT_ACTIVE = 0x11, +}; + +enum hinic_outbound_state { + HINIC_OUTBOUND_ENABLE = 0, + HINIC_OUTBOUND_DISABLE = 1, +}; + +enum hinic_db_state { + HINIC_DB_ENABLE = 0, + HINIC_DB_DISABLE = 1, +}; + +struct hinic_func_attr { + u16 func_idx; + u8 pf_idx; + u8 pci_intf_idx; + + enum hinic_func_type func_type; + + u8 ppf_idx; + + u16 num_irqs; + u8 num_aeqs; + u8 num_ceqs; + + u8 num_dma_attr; +}; + +struct hinic_hwif { + struct pci_dev *pdev; + void __iomem *cfg_regs_bar; + + struct hinic_func_attr attr; +}; + +static inline u32 hinic_hwif_read_reg(struct hinic_hwif *hwif, u32 reg) +{ + return be32_to_cpu(readl(hwif->cfg_regs_bar + reg)); +} + +static inline void hinic_hwif_write_reg(struct hinic_hwif *hwif, u32 reg, + u32 val) +{ + writel(cpu_to_be32(val), hwif->cfg_regs_bar + reg); +} + +int hinic_msix_attr_set(struct hinic_hwif *hwif, u16 msix_index, + u8 pending_limit, u8 coalesc_timer, + u8 lli_timer_cfg, u8 lli_credit_limit, + u8 resend_timer); + +int hinic_msix_attr_get(struct hinic_hwif *hwif, u16 msix_index, + u8 *pending_limit, u8 *coalesc_timer_cfg, + u8 *lli_timer, u8 *lli_credit_limit, + u8 *resend_timer); + +int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index); + +void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action); + +enum hinic_outbound_state hinic_outbound_state_get(struct hinic_hwif *hwif); + +void hinic_outbound_state_set(struct hinic_hwif *hwif, + enum hinic_outbound_state outbound_state); + +enum hinic_db_state hinic_db_state_get(struct hinic_hwif *hwif); + +void hinic_db_state_set(struct hinic_hwif *hwif, + enum hinic_db_state db_state); + +int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev); + +void hinic_free_hwif(struct hinic_hwif *hwif); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c new file mode 100644 index 000000000000..8e5897669a3a --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c @@ -0,0 +1,533 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/semaphore.h> +#include <linux/dma-mapping.h> +#include <linux/io.h> +#include <linux/err.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_eqs.h" +#include "hinic_hw_wqe.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_cmdq.h" +#include "hinic_hw_qp_ctxt.h" +#include "hinic_hw_qp.h" +#include "hinic_hw_io.h" + +#define CI_Q_ADDR_SIZE sizeof(u32) + +#define CI_ADDR(base_addr, q_id) ((base_addr) + \ + (q_id) * CI_Q_ADDR_SIZE) + +#define CI_TABLE_SIZE(num_qps) ((num_qps) * CI_Q_ADDR_SIZE) + +#define DB_IDX(db, db_base) \ + (((unsigned long)(db) - (unsigned long)(db_base)) / HINIC_DB_PAGE_SIZE) + +enum io_cmd { + IO_CMD_MODIFY_QUEUE_CTXT = 0, +}; + +static void init_db_area_idx(struct hinic_free_db_area *free_db_area) +{ + int i; + + for (i = 0; i < HINIC_DB_MAX_AREAS; i++) + free_db_area->db_idx[i] = i; + + free_db_area->alloc_pos = 0; + free_db_area->return_pos = HINIC_DB_MAX_AREAS; + + free_db_area->num_free = HINIC_DB_MAX_AREAS; + + sema_init(&free_db_area->idx_lock, 1); +} + +static void __iomem *get_db_area(struct hinic_func_to_io *func_to_io) +{ + struct hinic_free_db_area *free_db_area = &func_to_io->free_db_area; + int pos, idx; + + down(&free_db_area->idx_lock); + + free_db_area->num_free--; + + if (free_db_area->num_free < 0) { + free_db_area->num_free++; + up(&free_db_area->idx_lock); + return ERR_PTR(-ENOMEM); + } + + pos = free_db_area->alloc_pos++; + pos &= HINIC_DB_MAX_AREAS - 1; + + idx = free_db_area->db_idx[pos]; + + free_db_area->db_idx[pos] = -1; + + up(&free_db_area->idx_lock); + + return func_to_io->db_base + idx * HINIC_DB_PAGE_SIZE; +} + +static void return_db_area(struct hinic_func_to_io *func_to_io, + void __iomem *db_base) +{ + struct hinic_free_db_area *free_db_area = &func_to_io->free_db_area; + int pos, idx = DB_IDX(db_base, func_to_io->db_base); + + down(&free_db_area->idx_lock); + + pos = free_db_area->return_pos++; + pos &= HINIC_DB_MAX_AREAS - 1; + + free_db_area->db_idx[pos] = idx; + + free_db_area->num_free++; + + up(&free_db_area->idx_lock); +} + +static int write_sq_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn, + u16 num_sqs) +{ + struct hinic_hwif *hwif = func_to_io->hwif; + struct hinic_sq_ctxt_block *sq_ctxt_block; + struct pci_dev *pdev = hwif->pdev; + struct hinic_cmdq_buf cmdq_buf; + struct hinic_sq_ctxt *sq_ctxt; + struct hinic_qp *qp; + u64 out_param; + int err, i; + + err = hinic_alloc_cmdq_buf(&func_to_io->cmdqs, &cmdq_buf); + if (err) { + dev_err(&pdev->dev, "Failed to allocate cmdq buf\n"); + return err; + } + + sq_ctxt_block = cmdq_buf.buf; + sq_ctxt = sq_ctxt_block->sq_ctxt; + + hinic_qp_prepare_header(&sq_ctxt_block->hdr, HINIC_QP_CTXT_TYPE_SQ, + num_sqs, func_to_io->max_qps); + for (i = 0; i < num_sqs; i++) { + qp = &func_to_io->qps[i]; + + hinic_sq_prepare_ctxt(&sq_ctxt[i], &qp->sq, + base_qpn + qp->q_id); + } + + cmdq_buf.size = HINIC_SQ_CTXT_SIZE(num_sqs); + + err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC, + IO_CMD_MODIFY_QUEUE_CTXT, &cmdq_buf, + &out_param); + if ((err) || (out_param != 0)) { + dev_err(&pdev->dev, "Failed to set SQ ctxts\n"); + err = -EFAULT; + } + + hinic_free_cmdq_buf(&func_to_io->cmdqs, &cmdq_buf); + return err; +} + +static int write_rq_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn, + u16 num_rqs) +{ + struct hinic_hwif *hwif = func_to_io->hwif; + struct hinic_rq_ctxt_block *rq_ctxt_block; + struct pci_dev *pdev = hwif->pdev; + struct hinic_cmdq_buf cmdq_buf; + struct hinic_rq_ctxt *rq_ctxt; + struct hinic_qp *qp; + u64 out_param; + int err, i; + + err = hinic_alloc_cmdq_buf(&func_to_io->cmdqs, &cmdq_buf); + if (err) { + dev_err(&pdev->dev, "Failed to allocate cmdq buf\n"); + return err; + } + + rq_ctxt_block = cmdq_buf.buf; + rq_ctxt = rq_ctxt_block->rq_ctxt; + + hinic_qp_prepare_header(&rq_ctxt_block->hdr, HINIC_QP_CTXT_TYPE_RQ, + num_rqs, func_to_io->max_qps); + for (i = 0; i < num_rqs; i++) { + qp = &func_to_io->qps[i]; + + hinic_rq_prepare_ctxt(&rq_ctxt[i], &qp->rq, + base_qpn + qp->q_id); + } + + cmdq_buf.size = HINIC_RQ_CTXT_SIZE(num_rqs); + + err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC, + IO_CMD_MODIFY_QUEUE_CTXT, &cmdq_buf, + &out_param); + if ((err) || (out_param != 0)) { + dev_err(&pdev->dev, "Failed to set RQ ctxts\n"); + err = -EFAULT; + } + + hinic_free_cmdq_buf(&func_to_io->cmdqs, &cmdq_buf); + return err; +} + +/** + * write_qp_ctxts - write the qp ctxt to HW + * @func_to_io: func to io channel that holds the IO components + * @base_qpn: first qp number + * @num_qps: number of qps to write + * + * Return 0 - Success, negative - Failure + **/ +static int write_qp_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn, + u16 num_qps) +{ + return (write_sq_ctxts(func_to_io, base_qpn, num_qps) || + write_rq_ctxts(func_to_io, base_qpn, num_qps)); +} + +/** + * init_qp - Initialize a Queue Pair + * @func_to_io: func to io channel that holds the IO components + * @qp: pointer to the qp to initialize + * @q_id: the id of the qp + * @sq_msix_entry: msix entry for sq + * @rq_msix_entry: msix entry for rq + * + * Return 0 - Success, negative - Failure + **/ +static int init_qp(struct hinic_func_to_io *func_to_io, + struct hinic_qp *qp, int q_id, + struct msix_entry *sq_msix_entry, + struct msix_entry *rq_msix_entry) +{ + struct hinic_hwif *hwif = func_to_io->hwif; + struct pci_dev *pdev = hwif->pdev; + void __iomem *db_base; + int err; + + qp->q_id = q_id; + + err = hinic_wq_allocate(&func_to_io->wqs, &func_to_io->sq_wq[q_id], + HINIC_SQ_WQEBB_SIZE, HINIC_SQ_PAGE_SIZE, + HINIC_SQ_DEPTH, HINIC_SQ_WQE_MAX_SIZE); + if (err) { + dev_err(&pdev->dev, "Failed to allocate WQ for SQ\n"); + return err; + } + + err = hinic_wq_allocate(&func_to_io->wqs, &func_to_io->rq_wq[q_id], + HINIC_RQ_WQEBB_SIZE, HINIC_RQ_PAGE_SIZE, + HINIC_RQ_DEPTH, HINIC_RQ_WQE_SIZE); + if (err) { + dev_err(&pdev->dev, "Failed to allocate WQ for RQ\n"); + goto err_rq_alloc; + } + + db_base = get_db_area(func_to_io); + if (IS_ERR(db_base)) { + dev_err(&pdev->dev, "Failed to get DB area for SQ\n"); + err = PTR_ERR(db_base); + goto err_get_db; + } + + func_to_io->sq_db[q_id] = db_base; + + err = hinic_init_sq(&qp->sq, hwif, &func_to_io->sq_wq[q_id], + sq_msix_entry, + CI_ADDR(func_to_io->ci_addr_base, q_id), + CI_ADDR(func_to_io->ci_dma_base, q_id), db_base); + if (err) { + dev_err(&pdev->dev, "Failed to init SQ\n"); + goto err_sq_init; + } + + err = hinic_init_rq(&qp->rq, hwif, &func_to_io->rq_wq[q_id], + rq_msix_entry); + if (err) { + dev_err(&pdev->dev, "Failed to init RQ\n"); + goto err_rq_init; + } + + return 0; + +err_rq_init: + hinic_clean_sq(&qp->sq); + +err_sq_init: + return_db_area(func_to_io, db_base); + +err_get_db: + hinic_wq_free(&func_to_io->wqs, &func_to_io->rq_wq[q_id]); + +err_rq_alloc: + hinic_wq_free(&func_to_io->wqs, &func_to_io->sq_wq[q_id]); + return err; +} + +/** + * destroy_qp - Clean the resources of a Queue Pair + * @func_to_io: func to io channel that holds the IO components + * @qp: pointer to the qp to clean + **/ +static void destroy_qp(struct hinic_func_to_io *func_to_io, + struct hinic_qp *qp) +{ + int q_id = qp->q_id; + + hinic_clean_rq(&qp->rq); + hinic_clean_sq(&qp->sq); + + return_db_area(func_to_io, func_to_io->sq_db[q_id]); + + hinic_wq_free(&func_to_io->wqs, &func_to_io->rq_wq[q_id]); + hinic_wq_free(&func_to_io->wqs, &func_to_io->sq_wq[q_id]); +} + +/** + * hinic_io_create_qps - Create Queue Pairs + * @func_to_io: func to io channel that holds the IO components + * @base_qpn: base qp number + * @num_qps: number queue pairs to create + * @sq_msix_entry: msix entries for sq + * @rq_msix_entry: msix entries for rq + * + * Return 0 - Success, negative - Failure + **/ +int hinic_io_create_qps(struct hinic_func_to_io *func_to_io, + u16 base_qpn, int num_qps, + struct msix_entry *sq_msix_entries, + struct msix_entry *rq_msix_entries) +{ + struct hinic_hwif *hwif = func_to_io->hwif; + struct pci_dev *pdev = hwif->pdev; + size_t qps_size, wq_size, db_size; + void *ci_addr_base; + int i, j, err; + + qps_size = num_qps * sizeof(*func_to_io->qps); + func_to_io->qps = devm_kzalloc(&pdev->dev, qps_size, GFP_KERNEL); + if (!func_to_io->qps) + return -ENOMEM; + + wq_size = num_qps * sizeof(*func_to_io->sq_wq); + func_to_io->sq_wq = devm_kzalloc(&pdev->dev, wq_size, GFP_KERNEL); + if (!func_to_io->sq_wq) { + err = -ENOMEM; + goto err_sq_wq; + } + + wq_size = num_qps * sizeof(*func_to_io->rq_wq); + func_to_io->rq_wq = devm_kzalloc(&pdev->dev, wq_size, GFP_KERNEL); + if (!func_to_io->rq_wq) { + err = -ENOMEM; + goto err_rq_wq; + } + + db_size = num_qps * sizeof(*func_to_io->sq_db); + func_to_io->sq_db = devm_kzalloc(&pdev->dev, db_size, GFP_KERNEL); + if (!func_to_io->sq_db) { + err = -ENOMEM; + goto err_sq_db; + } + + ci_addr_base = dma_zalloc_coherent(&pdev->dev, CI_TABLE_SIZE(num_qps), + &func_to_io->ci_dma_base, + GFP_KERNEL); + if (!ci_addr_base) { + dev_err(&pdev->dev, "Failed to allocate CI area\n"); + err = -ENOMEM; + goto err_ci_base; + } + + func_to_io->ci_addr_base = ci_addr_base; + + for (i = 0; i < num_qps; i++) { + err = init_qp(func_to_io, &func_to_io->qps[i], i, + &sq_msix_entries[i], &rq_msix_entries[i]); + if (err) { + dev_err(&pdev->dev, "Failed to create QP %d\n", i); + goto err_init_qp; + } + } + + err = write_qp_ctxts(func_to_io, base_qpn, num_qps); + if (err) { + dev_err(&pdev->dev, "Failed to init QP ctxts\n"); + goto err_write_qp_ctxts; + } + + return 0; + +err_write_qp_ctxts: +err_init_qp: + for (j = 0; j < i; j++) + destroy_qp(func_to_io, &func_to_io->qps[j]); + + dma_free_coherent(&pdev->dev, CI_TABLE_SIZE(num_qps), + func_to_io->ci_addr_base, func_to_io->ci_dma_base); + +err_ci_base: + devm_kfree(&pdev->dev, func_to_io->sq_db); + +err_sq_db: + devm_kfree(&pdev->dev, func_to_io->rq_wq); + +err_rq_wq: + devm_kfree(&pdev->dev, func_to_io->sq_wq); + +err_sq_wq: + devm_kfree(&pdev->dev, func_to_io->qps); + return err; +} + +/** + * hinic_io_destroy_qps - Destroy the IO Queue Pairs + * @func_to_io: func to io channel that holds the IO components + * @num_qps: number queue pairs to destroy + **/ +void hinic_io_destroy_qps(struct hinic_func_to_io *func_to_io, int num_qps) +{ + struct hinic_hwif *hwif = func_to_io->hwif; + struct pci_dev *pdev = hwif->pdev; + size_t ci_table_size; + int i; + + ci_table_size = CI_TABLE_SIZE(num_qps); + + for (i = 0; i < num_qps; i++) + destroy_qp(func_to_io, &func_to_io->qps[i]); + + dma_free_coherent(&pdev->dev, ci_table_size, func_to_io->ci_addr_base, + func_to_io->ci_dma_base); + + devm_kfree(&pdev->dev, func_to_io->sq_db); + + devm_kfree(&pdev->dev, func_to_io->rq_wq); + devm_kfree(&pdev->dev, func_to_io->sq_wq); + + devm_kfree(&pdev->dev, func_to_io->qps); +} + +/** + * hinic_io_init - Initialize the IO components + * @func_to_io: func to io channel that holds the IO components + * @hwif: HW interface for accessing IO + * @max_qps: maximum QPs in HW + * @num_ceqs: number completion event queues + * @ceq_msix_entries: msix entries for ceqs + * + * Return 0 - Success, negative - Failure + **/ +int hinic_io_init(struct hinic_func_to_io *func_to_io, + struct hinic_hwif *hwif, u16 max_qps, int num_ceqs, + struct msix_entry *ceq_msix_entries) +{ + struct pci_dev *pdev = hwif->pdev; + enum hinic_cmdq_type cmdq, type; + void __iomem *db_area; + int err; + + func_to_io->hwif = hwif; + func_to_io->qps = NULL; + func_to_io->max_qps = max_qps; + + err = hinic_ceqs_init(&func_to_io->ceqs, hwif, num_ceqs, + HINIC_DEFAULT_CEQ_LEN, HINIC_EQ_PAGE_SIZE, + ceq_msix_entries); + if (err) { + dev_err(&pdev->dev, "Failed to init CEQs\n"); + return err; + } + + err = hinic_wqs_alloc(&func_to_io->wqs, 2 * max_qps, hwif); + if (err) { + dev_err(&pdev->dev, "Failed to allocate WQS for IO\n"); + goto err_wqs_alloc; + } + + func_to_io->db_base = pci_ioremap_bar(pdev, HINIC_PCI_DB_BAR); + if (!func_to_io->db_base) { + dev_err(&pdev->dev, "Failed to remap IO DB area\n"); + err = -ENOMEM; + goto err_db_ioremap; + } + + init_db_area_idx(&func_to_io->free_db_area); + + for (cmdq = HINIC_CMDQ_SYNC; cmdq < HINIC_MAX_CMDQ_TYPES; cmdq++) { + db_area = get_db_area(func_to_io); + if (IS_ERR(db_area)) { + dev_err(&pdev->dev, "Failed to get cmdq db area\n"); + err = PTR_ERR(db_area); + goto err_db_area; + } + + func_to_io->cmdq_db_area[cmdq] = db_area; + } + + err = hinic_init_cmdqs(&func_to_io->cmdqs, hwif, + func_to_io->cmdq_db_area); + if (err) { + dev_err(&pdev->dev, "Failed to initialize cmdqs\n"); + goto err_init_cmdqs; + } + + return 0; + +err_init_cmdqs: +err_db_area: + for (type = HINIC_CMDQ_SYNC; type < cmdq; type++) + return_db_area(func_to_io, func_to_io->cmdq_db_area[type]); + + iounmap(func_to_io->db_base); + +err_db_ioremap: + hinic_wqs_free(&func_to_io->wqs); + +err_wqs_alloc: + hinic_ceqs_free(&func_to_io->ceqs); + return err; +} + +/** + * hinic_io_free - Free the IO components + * @func_to_io: func to io channel that holds the IO components + **/ +void hinic_io_free(struct hinic_func_to_io *func_to_io) +{ + enum hinic_cmdq_type cmdq; + + hinic_free_cmdqs(&func_to_io->cmdqs); + + for (cmdq = HINIC_CMDQ_SYNC; cmdq < HINIC_MAX_CMDQ_TYPES; cmdq++) + return_db_area(func_to_io, func_to_io->cmdq_db_area[cmdq]); + + iounmap(func_to_io->db_base); + hinic_wqs_free(&func_to_io->wqs); + hinic_ceqs_free(&func_to_io->ceqs); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h new file mode 100644 index 000000000000..adb64179d47d --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.h @@ -0,0 +1,97 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_IO_H +#define HINIC_HW_IO_H + +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/semaphore.h> +#include <linux/sizes.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_eqs.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_cmdq.h" +#include "hinic_hw_qp.h" + +#define HINIC_DB_PAGE_SIZE SZ_4K +#define HINIC_DB_SIZE SZ_4M + +#define HINIC_DB_MAX_AREAS (HINIC_DB_SIZE / HINIC_DB_PAGE_SIZE) + +enum hinic_db_type { + HINIC_DB_CMDQ_TYPE, + HINIC_DB_SQ_TYPE, +}; + +enum hinic_io_path { + HINIC_CTRL_PATH, + HINIC_DATA_PATH, +}; + +struct hinic_free_db_area { + int db_idx[HINIC_DB_MAX_AREAS]; + + int alloc_pos; + int return_pos; + + int num_free; + + /* Lock for getting db area */ + struct semaphore idx_lock; +}; + +struct hinic_func_to_io { + struct hinic_hwif *hwif; + + struct hinic_ceqs ceqs; + + struct hinic_wqs wqs; + + struct hinic_wq *sq_wq; + struct hinic_wq *rq_wq; + + struct hinic_qp *qps; + u16 max_qps; + + void __iomem **sq_db; + void __iomem *db_base; + + void *ci_addr_base; + dma_addr_t ci_dma_base; + + struct hinic_free_db_area free_db_area; + + void __iomem *cmdq_db_area[HINIC_MAX_CMDQ_TYPES]; + + struct hinic_cmdqs cmdqs; +}; + +int hinic_io_create_qps(struct hinic_func_to_io *func_to_io, + u16 base_qpn, int num_qps, + struct msix_entry *sq_msix_entries, + struct msix_entry *rq_msix_entries); + +void hinic_io_destroy_qps(struct hinic_func_to_io *func_to_io, + int num_qps); + +int hinic_io_init(struct hinic_func_to_io *func_to_io, + struct hinic_hwif *hwif, u16 max_qps, int num_ceqs, + struct msix_entry *ceq_msix_entries); + +void hinic_io_free(struct hinic_func_to_io *func_to_io); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c new file mode 100644 index 000000000000..278dc13f3dae --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -0,0 +1,597 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/semaphore.h> +#include <linux/completion.h> +#include <linux/slab.h> +#include <asm/barrier.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_eqs.h" +#include "hinic_hw_api_cmd.h" +#include "hinic_hw_mgmt.h" +#include "hinic_hw_dev.h" + +#define SYNC_MSG_ID_MASK 0x1FF + +#define SYNC_MSG_ID(pf_to_mgmt) ((pf_to_mgmt)->sync_msg_id) + +#define SYNC_MSG_ID_INC(pf_to_mgmt) (SYNC_MSG_ID(pf_to_mgmt) = \ + ((SYNC_MSG_ID(pf_to_mgmt) + 1) & \ + SYNC_MSG_ID_MASK)) + +#define MSG_SZ_IS_VALID(in_size) ((in_size) <= MAX_MSG_LEN) + +#define MGMT_MSG_LEN_MIN 20 +#define MGMT_MSG_LEN_STEP 16 +#define MGMT_MSG_RSVD_FOR_DEV 8 + +#define SEGMENT_LEN 48 + +#define MAX_PF_MGMT_BUF_SIZE 2048 + +/* Data should be SEG LEN size aligned */ +#define MAX_MSG_LEN 2016 + +#define MSG_NOT_RESP 0xFFFF + +#define MGMT_MSG_TIMEOUT 1000 + +#define mgmt_to_pfhwdev(pf_mgmt) \ + container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt) + +enum msg_segment_type { + NOT_LAST_SEGMENT = 0, + LAST_SEGMENT = 1, +}; + +enum mgmt_direction_type { + MGMT_DIRECT_SEND = 0, + MGMT_RESP = 1, +}; + +enum msg_ack_type { + MSG_ACK = 0, + MSG_NO_ACK = 1, +}; + +/** + * hinic_register_mgmt_msg_cb - register msg handler for a msg from a module + * @pf_to_mgmt: PF to MGMT channel + * @mod: module in the chip that this handler will handle its messages + * @handle: private data for the callback + * @callback: the handler that will handle messages + **/ +void hinic_register_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod, + void *handle, + void (*callback)(void *handle, + u8 cmd, void *buf_in, + u16 in_size, void *buf_out, + u16 *out_size)) +{ + struct hinic_mgmt_cb *mgmt_cb = &pf_to_mgmt->mgmt_cb[mod]; + + mgmt_cb->cb = callback; + mgmt_cb->handle = handle; + mgmt_cb->state = HINIC_MGMT_CB_ENABLED; +} + +/** + * hinic_unregister_mgmt_msg_cb - unregister msg handler for a msg from a module + * @pf_to_mgmt: PF to MGMT channel + * @mod: module in the chip that this handler handles its messages + **/ +void hinic_unregister_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod) +{ + struct hinic_mgmt_cb *mgmt_cb = &pf_to_mgmt->mgmt_cb[mod]; + + mgmt_cb->state &= ~HINIC_MGMT_CB_ENABLED; + + while (mgmt_cb->state & HINIC_MGMT_CB_RUNNING) + schedule(); + + mgmt_cb->cb = NULL; +} + +/** + * prepare_header - prepare the header of the message + * @pf_to_mgmt: PF to MGMT channel + * @msg_len: the length of the message + * @mod: module in the chip that will get the message + * @ack_type: ask for response + * @direction: the direction of the message + * @cmd: command of the message + * @msg_id: message id + * + * Return the prepared header value + **/ +static u64 prepare_header(struct hinic_pf_to_mgmt *pf_to_mgmt, + u16 msg_len, enum hinic_mod_type mod, + enum msg_ack_type ack_type, + enum mgmt_direction_type direction, + u16 cmd, u16 msg_id) +{ + struct hinic_hwif *hwif = pf_to_mgmt->hwif; + + return HINIC_MSG_HEADER_SET(msg_len, MSG_LEN) | + HINIC_MSG_HEADER_SET(mod, MODULE) | + HINIC_MSG_HEADER_SET(SEGMENT_LEN, SEG_LEN) | + HINIC_MSG_HEADER_SET(ack_type, NO_ACK) | + HINIC_MSG_HEADER_SET(0, ASYNC_MGMT_TO_PF) | + HINIC_MSG_HEADER_SET(0, SEQID) | + HINIC_MSG_HEADER_SET(LAST_SEGMENT, LAST) | + HINIC_MSG_HEADER_SET(direction, DIRECTION) | + HINIC_MSG_HEADER_SET(cmd, CMD) | + HINIC_MSG_HEADER_SET(HINIC_HWIF_PCI_INTF(hwif), PCI_INTF) | + HINIC_MSG_HEADER_SET(HINIC_HWIF_PF_IDX(hwif), PF_IDX) | + HINIC_MSG_HEADER_SET(msg_id, MSG_ID); +} + +/** + * prepare_mgmt_cmd - prepare the mgmt command + * @mgmt_cmd: pointer to the command to prepare + * @header: pointer of the header for the message + * @msg: the data of the message + * @msg_len: the length of the message + **/ +static void prepare_mgmt_cmd(u8 *mgmt_cmd, u64 *header, u8 *msg, u16 msg_len) +{ + memset(mgmt_cmd, 0, MGMT_MSG_RSVD_FOR_DEV); + + mgmt_cmd += MGMT_MSG_RSVD_FOR_DEV; + memcpy(mgmt_cmd, header, sizeof(*header)); + + mgmt_cmd += sizeof(*header); + memcpy(mgmt_cmd, msg, msg_len); +} + +/** + * mgmt_msg_len - calculate the total message length + * @msg_data_len: the length of the message data + * + * Return the total message length + **/ +static u16 mgmt_msg_len(u16 msg_data_len) +{ + /* RSVD + HEADER_SIZE + DATA_LEN */ + u16 msg_len = MGMT_MSG_RSVD_FOR_DEV + sizeof(u64) + msg_data_len; + + if (msg_len > MGMT_MSG_LEN_MIN) + msg_len = MGMT_MSG_LEN_MIN + + ALIGN((msg_len - MGMT_MSG_LEN_MIN), + MGMT_MSG_LEN_STEP); + else + msg_len = MGMT_MSG_LEN_MIN; + + return msg_len; +} + +/** + * send_msg_to_mgmt - send message to mgmt by API CMD + * @pf_to_mgmt: PF to MGMT channel + * @mod: module in the chip that will get the message + * @cmd: command of the message + * @data: the msg data + * @data_len: the msg data length + * @ack_type: ask for response + * @direction: the direction of the original message + * @resp_msg_id: msg id to response for + * + * Return 0 - Success, negative - Failure + **/ +static int send_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod, u8 cmd, + u8 *data, u16 data_len, + enum msg_ack_type ack_type, + enum mgmt_direction_type direction, + u16 resp_msg_id) +{ + struct hinic_api_cmd_chain *chain; + u64 header; + u16 msg_id; + + msg_id = SYNC_MSG_ID(pf_to_mgmt); + + if (direction == MGMT_RESP) { + header = prepare_header(pf_to_mgmt, data_len, mod, ack_type, + direction, cmd, resp_msg_id); + } else { + SYNC_MSG_ID_INC(pf_to_mgmt); + header = prepare_header(pf_to_mgmt, data_len, mod, ack_type, + direction, cmd, msg_id); + } + + prepare_mgmt_cmd(pf_to_mgmt->sync_msg_buf, &header, data, data_len); + + chain = pf_to_mgmt->cmd_chain[HINIC_API_CMD_WRITE_TO_MGMT_CPU]; + return hinic_api_cmd_write(chain, HINIC_NODE_ID_MGMT, + pf_to_mgmt->sync_msg_buf, + mgmt_msg_len(data_len)); +} + +/** + * msg_to_mgmt_sync - send sync message to mgmt + * @pf_to_mgmt: PF to MGMT channel + * @mod: module in the chip that will get the message + * @cmd: command of the message + * @buf_in: the msg data + * @in_size: the msg data length + * @buf_out: response + * @out_size: response length + * @direction: the direction of the original message + * @resp_msg_id: msg id to response for + * + * Return 0 - Success, negative - Failure + **/ +static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod, u8 cmd, + u8 *buf_in, u16 in_size, + u8 *buf_out, u16 *out_size, + enum mgmt_direction_type direction, + u16 resp_msg_id) +{ + struct hinic_hwif *hwif = pf_to_mgmt->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_recv_msg *recv_msg; + struct completion *recv_done; + u16 msg_id; + int err; + + /* Lock the sync_msg_buf */ + down(&pf_to_mgmt->sync_msg_lock); + + recv_msg = &pf_to_mgmt->recv_resp_msg_from_mgmt; + recv_done = &recv_msg->recv_done; + + if (resp_msg_id == MSG_NOT_RESP) + msg_id = SYNC_MSG_ID(pf_to_mgmt); + else + msg_id = resp_msg_id; + + init_completion(recv_done); + + err = send_msg_to_mgmt(pf_to_mgmt, mod, cmd, buf_in, in_size, + MSG_ACK, direction, resp_msg_id); + if (err) { + dev_err(&pdev->dev, "Failed to send sync msg to mgmt\n"); + goto unlock_sync_msg; + } + + if (!wait_for_completion_timeout(recv_done, MGMT_MSG_TIMEOUT)) { + dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id); + err = -ETIMEDOUT; + goto unlock_sync_msg; + } + + smp_rmb(); /* verify reading after completion */ + + if (recv_msg->msg_id != msg_id) { + dev_err(&pdev->dev, "incorrect MSG for id = %d\n", msg_id); + err = -EFAULT; + goto unlock_sync_msg; + } + + if ((buf_out) && (recv_msg->msg_len <= MAX_PF_MGMT_BUF_SIZE)) { + memcpy(buf_out, recv_msg->msg, recv_msg->msg_len); + *out_size = recv_msg->msg_len; + } + +unlock_sync_msg: + up(&pf_to_mgmt->sync_msg_lock); + return err; +} + +/** + * msg_to_mgmt_async - send message to mgmt without response + * @pf_to_mgmt: PF to MGMT channel + * @mod: module in the chip that will get the message + * @cmd: command of the message + * @buf_in: the msg data + * @in_size: the msg data length + * @direction: the direction of the original message + * @resp_msg_id: msg id to response for + * + * Return 0 - Success, negative - Failure + **/ +static int msg_to_mgmt_async(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod, u8 cmd, + u8 *buf_in, u16 in_size, + enum mgmt_direction_type direction, + u16 resp_msg_id) +{ + int err; + + /* Lock the sync_msg_buf */ + down(&pf_to_mgmt->sync_msg_lock); + + err = send_msg_to_mgmt(pf_to_mgmt, mod, cmd, buf_in, in_size, + MSG_NO_ACK, direction, resp_msg_id); + + up(&pf_to_mgmt->sync_msg_lock); + return err; +} + +/** + * hinic_msg_to_mgmt - send message to mgmt + * @pf_to_mgmt: PF to MGMT channel + * @mod: module in the chip that will get the message + * @cmd: command of the message + * @buf_in: the msg data + * @in_size: the msg data length + * @buf_out: response + * @out_size: returned response length + * @sync: sync msg or async msg + * + * Return 0 - Success, negative - Failure + **/ +int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod, u8 cmd, + void *buf_in, u16 in_size, void *buf_out, u16 *out_size, + enum hinic_mgmt_msg_type sync) +{ + struct hinic_hwif *hwif = pf_to_mgmt->hwif; + struct pci_dev *pdev = hwif->pdev; + + if (sync != HINIC_MGMT_MSG_SYNC) { + dev_err(&pdev->dev, "Invalid MGMT msg type\n"); + return -EINVAL; + } + + if (!MSG_SZ_IS_VALID(in_size)) { + dev_err(&pdev->dev, "Invalid MGMT msg buffer size\n"); + return -EINVAL; + } + + return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, + buf_out, out_size, MGMT_DIRECT_SEND, + MSG_NOT_RESP); +} + +/** + * mgmt_recv_msg_handler - handler for message from mgmt cpu + * @pf_to_mgmt: PF to MGMT channel + * @recv_msg: received message details + **/ +static void mgmt_recv_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt, + struct hinic_recv_msg *recv_msg) +{ + struct hinic_hwif *hwif = pf_to_mgmt->hwif; + struct pci_dev *pdev = hwif->pdev; + u8 *buf_out = recv_msg->buf_out; + struct hinic_mgmt_cb *mgmt_cb; + unsigned long cb_state; + u16 out_size = 0; + + if (recv_msg->mod >= HINIC_MOD_MAX) { + dev_err(&pdev->dev, "Unknown MGMT MSG module = %d\n", + recv_msg->mod); + return; + } + + mgmt_cb = &pf_to_mgmt->mgmt_cb[recv_msg->mod]; + + cb_state = cmpxchg(&mgmt_cb->state, + HINIC_MGMT_CB_ENABLED, + HINIC_MGMT_CB_ENABLED | HINIC_MGMT_CB_RUNNING); + + if ((cb_state == HINIC_MGMT_CB_ENABLED) && (mgmt_cb->cb)) + mgmt_cb->cb(mgmt_cb->handle, recv_msg->cmd, + recv_msg->msg, recv_msg->msg_len, + buf_out, &out_size); + else + dev_err(&pdev->dev, "No MGMT msg handler, mod = %d\n", + recv_msg->mod); + + mgmt_cb->state &= ~HINIC_MGMT_CB_RUNNING; + + if (!recv_msg->async_mgmt_to_pf) + /* MGMT sent sync msg, send the response */ + msg_to_mgmt_async(pf_to_mgmt, recv_msg->mod, recv_msg->cmd, + buf_out, out_size, MGMT_RESP, + recv_msg->msg_id); +} + +/** + * mgmt_resp_msg_handler - handler for a response message from mgmt cpu + * @pf_to_mgmt: PF to MGMT channel + * @recv_msg: received message details + **/ +static void mgmt_resp_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt, + struct hinic_recv_msg *recv_msg) +{ + wmb(); /* verify writing all, before reading */ + + complete(&recv_msg->recv_done); +} + +/** + * recv_mgmt_msg_handler - handler for a message from mgmt cpu + * @pf_to_mgmt: PF to MGMT channel + * @header: the header of the message + * @recv_msg: received message details + **/ +static void recv_mgmt_msg_handler(struct hinic_pf_to_mgmt *pf_to_mgmt, + u64 *header, struct hinic_recv_msg *recv_msg) +{ + struct hinic_hwif *hwif = pf_to_mgmt->hwif; + struct pci_dev *pdev = hwif->pdev; + int seq_id, seg_len; + u8 *msg_body; + + seq_id = HINIC_MSG_HEADER_GET(*header, SEQID); + seg_len = HINIC_MSG_HEADER_GET(*header, SEG_LEN); + + if (seq_id >= (MAX_MSG_LEN / SEGMENT_LEN)) { + dev_err(&pdev->dev, "recv big mgmt msg\n"); + return; + } + + msg_body = (u8 *)header + sizeof(*header); + memcpy(recv_msg->msg + seq_id * SEGMENT_LEN, msg_body, seg_len); + + if (!HINIC_MSG_HEADER_GET(*header, LAST)) + return; + + recv_msg->cmd = HINIC_MSG_HEADER_GET(*header, CMD); + recv_msg->mod = HINIC_MSG_HEADER_GET(*header, MODULE); + recv_msg->async_mgmt_to_pf = HINIC_MSG_HEADER_GET(*header, + ASYNC_MGMT_TO_PF); + recv_msg->msg_len = HINIC_MSG_HEADER_GET(*header, MSG_LEN); + recv_msg->msg_id = HINIC_MSG_HEADER_GET(*header, MSG_ID); + + if (HINIC_MSG_HEADER_GET(*header, DIRECTION) == MGMT_RESP) + mgmt_resp_msg_handler(pf_to_mgmt, recv_msg); + else + mgmt_recv_msg_handler(pf_to_mgmt, recv_msg); +} + +/** + * mgmt_msg_aeqe_handler - handler for a mgmt message event + * @handle: PF to MGMT channel + * @data: the header of the message + * @size: unused + **/ +static void mgmt_msg_aeqe_handler(void *handle, void *data, u8 size) +{ + struct hinic_pf_to_mgmt *pf_to_mgmt = handle; + struct hinic_recv_msg *recv_msg; + u64 *header = (u64 *)data; + + recv_msg = HINIC_MSG_HEADER_GET(*header, DIRECTION) == + MGMT_DIRECT_SEND ? + &pf_to_mgmt->recv_msg_from_mgmt : + &pf_to_mgmt->recv_resp_msg_from_mgmt; + + recv_mgmt_msg_handler(pf_to_mgmt, header, recv_msg); +} + +/** + * alloc_recv_msg - allocate receive message memory + * @pf_to_mgmt: PF to MGMT channel + * @recv_msg: pointer that will hold the allocated data + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_recv_msg(struct hinic_pf_to_mgmt *pf_to_mgmt, + struct hinic_recv_msg *recv_msg) +{ + struct hinic_hwif *hwif = pf_to_mgmt->hwif; + struct pci_dev *pdev = hwif->pdev; + + recv_msg->msg = devm_kzalloc(&pdev->dev, MAX_PF_MGMT_BUF_SIZE, + GFP_KERNEL); + if (!recv_msg->msg) + return -ENOMEM; + + recv_msg->buf_out = devm_kzalloc(&pdev->dev, MAX_PF_MGMT_BUF_SIZE, + GFP_KERNEL); + if (!recv_msg->buf_out) + return -ENOMEM; + + return 0; +} + +/** + * alloc_msg_buf - allocate all the message buffers of PF to MGMT channel + * @pf_to_mgmt: PF to MGMT channel + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_msg_buf(struct hinic_pf_to_mgmt *pf_to_mgmt) +{ + struct hinic_hwif *hwif = pf_to_mgmt->hwif; + struct pci_dev *pdev = hwif->pdev; + int err; + + err = alloc_recv_msg(pf_to_mgmt, + &pf_to_mgmt->recv_msg_from_mgmt); + if (err) { + dev_err(&pdev->dev, "Failed to allocate recv msg\n"); + return err; + } + + err = alloc_recv_msg(pf_to_mgmt, + &pf_to_mgmt->recv_resp_msg_from_mgmt); + if (err) { + dev_err(&pdev->dev, "Failed to allocate resp recv msg\n"); + return err; + } + + pf_to_mgmt->sync_msg_buf = devm_kzalloc(&pdev->dev, + MAX_PF_MGMT_BUF_SIZE, + GFP_KERNEL); + if (!pf_to_mgmt->sync_msg_buf) + return -ENOMEM; + + return 0; +} + +/** + * hinic_pf_to_mgmt_init - initialize PF to MGMT channel + * @pf_to_mgmt: PF to MGMT channel + * @hwif: HW interface the PF to MGMT will use for accessing HW + * + * Return 0 - Success, negative - Failure + **/ +int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt, + struct hinic_hwif *hwif) +{ + struct hinic_pfhwdev *pfhwdev = mgmt_to_pfhwdev(pf_to_mgmt); + struct hinic_hwdev *hwdev = &pfhwdev->hwdev; + struct pci_dev *pdev = hwif->pdev; + int err; + + pf_to_mgmt->hwif = hwif; + + sema_init(&pf_to_mgmt->sync_msg_lock, 1); + pf_to_mgmt->sync_msg_id = 0; + + err = alloc_msg_buf(pf_to_mgmt); + if (err) { + dev_err(&pdev->dev, "Failed to allocate msg buffers\n"); + return err; + } + + err = hinic_api_cmd_init(pf_to_mgmt->cmd_chain, hwif); + if (err) { + dev_err(&pdev->dev, "Failed to initialize cmd chains\n"); + return err; + } + + hinic_aeq_register_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU, + pf_to_mgmt, + mgmt_msg_aeqe_handler); + return 0; +} + +/** + * hinic_pf_to_mgmt_free - free PF to MGMT channel + * @pf_to_mgmt: PF to MGMT channel + **/ +void hinic_pf_to_mgmt_free(struct hinic_pf_to_mgmt *pf_to_mgmt) +{ + struct hinic_pfhwdev *pfhwdev = mgmt_to_pfhwdev(pf_to_mgmt); + struct hinic_hwdev *hwdev = &pfhwdev->hwdev; + + hinic_aeq_unregister_hw_cb(&hwdev->aeqs, HINIC_MSG_FROM_MGMT_CPU); + hinic_api_cmd_free(pf_to_mgmt->cmd_chain); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h new file mode 100644 index 000000000000..320711e8dee6 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.h @@ -0,0 +1,153 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_MGMT_H +#define HINIC_HW_MGMT_H + +#include <linux/types.h> +#include <linux/semaphore.h> +#include <linux/completion.h> +#include <linux/bitops.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_api_cmd.h" + +#define HINIC_MSG_HEADER_MSG_LEN_SHIFT 0 +#define HINIC_MSG_HEADER_MODULE_SHIFT 11 +#define HINIC_MSG_HEADER_SEG_LEN_SHIFT 16 +#define HINIC_MSG_HEADER_NO_ACK_SHIFT 22 +#define HINIC_MSG_HEADER_ASYNC_MGMT_TO_PF_SHIFT 23 +#define HINIC_MSG_HEADER_SEQID_SHIFT 24 +#define HINIC_MSG_HEADER_LAST_SHIFT 30 +#define HINIC_MSG_HEADER_DIRECTION_SHIFT 31 +#define HINIC_MSG_HEADER_CMD_SHIFT 32 +#define HINIC_MSG_HEADER_ZEROS_SHIFT 40 +#define HINIC_MSG_HEADER_PCI_INTF_SHIFT 48 +#define HINIC_MSG_HEADER_PF_IDX_SHIFT 50 +#define HINIC_MSG_HEADER_MSG_ID_SHIFT 54 + +#define HINIC_MSG_HEADER_MSG_LEN_MASK 0x7FF +#define HINIC_MSG_HEADER_MODULE_MASK 0x1F +#define HINIC_MSG_HEADER_SEG_LEN_MASK 0x3F +#define HINIC_MSG_HEADER_NO_ACK_MASK 0x1 +#define HINIC_MSG_HEADER_ASYNC_MGMT_TO_PF_MASK 0x1 +#define HINIC_MSG_HEADER_SEQID_MASK 0x3F +#define HINIC_MSG_HEADER_LAST_MASK 0x1 +#define HINIC_MSG_HEADER_DIRECTION_MASK 0x1 +#define HINIC_MSG_HEADER_CMD_MASK 0xFF +#define HINIC_MSG_HEADER_ZEROS_MASK 0xFF +#define HINIC_MSG_HEADER_PCI_INTF_MASK 0x3 +#define HINIC_MSG_HEADER_PF_IDX_MASK 0xF +#define HINIC_MSG_HEADER_MSG_ID_MASK 0x3FF + +#define HINIC_MSG_HEADER_SET(val, member) \ + ((u64)((val) & HINIC_MSG_HEADER_##member##_MASK) << \ + HINIC_MSG_HEADER_##member##_SHIFT) + +#define HINIC_MSG_HEADER_GET(val, member) \ + (((val) >> HINIC_MSG_HEADER_##member##_SHIFT) & \ + HINIC_MSG_HEADER_##member##_MASK) + +enum hinic_mgmt_msg_type { + HINIC_MGMT_MSG_SYNC = 1, +}; + +enum hinic_cfg_cmd { + HINIC_CFG_NIC_CAP = 0, +}; + +enum hinic_comm_cmd { + HINIC_COMM_CMD_IO_STATUS_GET = 0x3, + + HINIC_COMM_CMD_CMDQ_CTXT_SET = 0x10, + HINIC_COMM_CMD_CMDQ_CTXT_GET = 0x11, + + HINIC_COMM_CMD_HWCTXT_SET = 0x12, + HINIC_COMM_CMD_HWCTXT_GET = 0x13, + + HINIC_COMM_CMD_SQ_HI_CI_SET = 0x14, + + HINIC_COMM_CMD_RES_STATE_SET = 0x24, + + HINIC_COMM_CMD_IO_RES_CLEAR = 0x29, + + HINIC_COMM_CMD_MAX = 0x32, +}; + +enum hinic_mgmt_cb_state { + HINIC_MGMT_CB_ENABLED = BIT(0), + HINIC_MGMT_CB_RUNNING = BIT(1), +}; + +struct hinic_recv_msg { + u8 *msg; + u8 *buf_out; + + struct completion recv_done; + + u16 cmd; + enum hinic_mod_type mod; + int async_mgmt_to_pf; + + u16 msg_len; + u16 msg_id; +}; + +struct hinic_mgmt_cb { + void (*cb)(void *handle, u8 cmd, + void *buf_in, u16 in_size, + void *buf_out, u16 *out_size); + + void *handle; + unsigned long state; +}; + +struct hinic_pf_to_mgmt { + struct hinic_hwif *hwif; + + struct semaphore sync_msg_lock; + u16 sync_msg_id; + u8 *sync_msg_buf; + + struct hinic_recv_msg recv_resp_msg_from_mgmt; + struct hinic_recv_msg recv_msg_from_mgmt; + + struct hinic_api_cmd_chain *cmd_chain[HINIC_API_CMD_MAX]; + + struct hinic_mgmt_cb mgmt_cb[HINIC_MOD_MAX]; +}; + +void hinic_register_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod, + void *handle, + void (*callback)(void *handle, + u8 cmd, void *buf_in, + u16 in_size, void *buf_out, + u16 *out_size)); + +void hinic_unregister_mgmt_msg_cb(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod); + +int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, + enum hinic_mod_type mod, u8 cmd, + void *buf_in, u16 in_size, void *buf_out, u16 *out_size, + enum hinic_mgmt_msg_type sync); + +int hinic_pf_to_mgmt_init(struct hinic_pf_to_mgmt *pf_to_mgmt, + struct hinic_hwif *hwif); + +void hinic_pf_to_mgmt_free(struct hinic_pf_to_mgmt *pf_to_mgmt); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c new file mode 100644 index 000000000000..b9db6d649743 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c @@ -0,0 +1,887 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/dma-mapping.h> +#include <linux/vmalloc.h> +#include <linux/errno.h> +#include <linux/sizes.h> +#include <linux/atomic.h> +#include <linux/skbuff.h> +#include <linux/io.h> +#include <asm/barrier.h> +#include <asm/byteorder.h> + +#include "hinic_common.h" +#include "hinic_hw_if.h" +#include "hinic_hw_wqe.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_qp_ctxt.h" +#include "hinic_hw_qp.h" +#include "hinic_hw_io.h" + +#define SQ_DB_OFF SZ_2K + +/* The number of cache line to prefetch Until threshold state */ +#define WQ_PREFETCH_MAX 2 +/* The number of cache line to prefetch After threshold state */ +#define WQ_PREFETCH_MIN 1 +/* Threshold state */ +#define WQ_PREFETCH_THRESHOLD 256 + +/* sizes of the SQ/RQ ctxt */ +#define Q_CTXT_SIZE 48 +#define CTXT_RSVD 240 + +#define SQ_CTXT_OFFSET(max_sqs, max_rqs, q_id) \ + (((max_rqs) + (max_sqs)) * CTXT_RSVD + (q_id) * Q_CTXT_SIZE) + +#define RQ_CTXT_OFFSET(max_sqs, max_rqs, q_id) \ + (((max_rqs) + (max_sqs)) * CTXT_RSVD + \ + (max_sqs + (q_id)) * Q_CTXT_SIZE) + +#define SIZE_16BYTES(size) (ALIGN(size, 16) >> 4) +#define SIZE_8BYTES(size) (ALIGN(size, 8) >> 3) +#define SECT_SIZE_FROM_8BYTES(size) ((size) << 3) + +#define SQ_DB_PI_HI_SHIFT 8 +#define SQ_DB_PI_HI(prod_idx) ((prod_idx) >> SQ_DB_PI_HI_SHIFT) + +#define SQ_DB_PI_LOW_MASK 0xFF +#define SQ_DB_PI_LOW(prod_idx) ((prod_idx) & SQ_DB_PI_LOW_MASK) + +#define SQ_DB_ADDR(sq, pi) ((u64 *)((sq)->db_base) + SQ_DB_PI_LOW(pi)) + +#define SQ_MASKED_IDX(sq, idx) ((idx) & (sq)->wq->mask) +#define RQ_MASKED_IDX(rq, idx) ((idx) & (rq)->wq->mask) + +#define TX_MAX_MSS_DEFAULT 0x3E00 + +enum sq_wqe_type { + SQ_NORMAL_WQE = 0, +}; + +enum rq_completion_fmt { + RQ_COMPLETE_SGE = 1 +}; + +void hinic_qp_prepare_header(struct hinic_qp_ctxt_header *qp_ctxt_hdr, + enum hinic_qp_ctxt_type ctxt_type, + u16 num_queues, u16 max_queues) +{ + u16 max_sqs = max_queues; + u16 max_rqs = max_queues; + + qp_ctxt_hdr->num_queues = num_queues; + qp_ctxt_hdr->queue_type = ctxt_type; + + if (ctxt_type == HINIC_QP_CTXT_TYPE_SQ) + qp_ctxt_hdr->addr_offset = SQ_CTXT_OFFSET(max_sqs, max_rqs, 0); + else + qp_ctxt_hdr->addr_offset = RQ_CTXT_OFFSET(max_sqs, max_rqs, 0); + + qp_ctxt_hdr->addr_offset = SIZE_16BYTES(qp_ctxt_hdr->addr_offset); + + hinic_cpu_to_be32(qp_ctxt_hdr, sizeof(*qp_ctxt_hdr)); +} + +void hinic_sq_prepare_ctxt(struct hinic_sq_ctxt *sq_ctxt, + struct hinic_sq *sq, u16 global_qid) +{ + u32 wq_page_pfn_hi, wq_page_pfn_lo, wq_block_pfn_hi, wq_block_pfn_lo; + u64 wq_page_addr, wq_page_pfn, wq_block_pfn; + u16 pi_start, ci_start; + struct hinic_wq *wq; + + wq = sq->wq; + ci_start = atomic_read(&wq->cons_idx); + pi_start = atomic_read(&wq->prod_idx); + + /* Read the first page paddr from the WQ page paddr ptrs */ + wq_page_addr = be64_to_cpu(*wq->block_vaddr); + + wq_page_pfn = HINIC_WQ_PAGE_PFN(wq_page_addr); + wq_page_pfn_hi = upper_32_bits(wq_page_pfn); + wq_page_pfn_lo = lower_32_bits(wq_page_pfn); + + wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq->block_paddr); + wq_block_pfn_hi = upper_32_bits(wq_block_pfn); + wq_block_pfn_lo = lower_32_bits(wq_block_pfn); + + sq_ctxt->ceq_attr = HINIC_SQ_CTXT_CEQ_ATTR_SET(global_qid, + GLOBAL_SQ_ID) | + HINIC_SQ_CTXT_CEQ_ATTR_SET(0, EN); + + sq_ctxt->ci_wrapped = HINIC_SQ_CTXT_CI_SET(ci_start, IDX) | + HINIC_SQ_CTXT_CI_SET(1, WRAPPED); + + sq_ctxt->wq_hi_pfn_pi = + HINIC_SQ_CTXT_WQ_PAGE_SET(wq_page_pfn_hi, HI_PFN) | + HINIC_SQ_CTXT_WQ_PAGE_SET(pi_start, PI); + + sq_ctxt->wq_lo_pfn = wq_page_pfn_lo; + + sq_ctxt->pref_cache = + HINIC_SQ_CTXT_PREF_SET(WQ_PREFETCH_MIN, CACHE_MIN) | + HINIC_SQ_CTXT_PREF_SET(WQ_PREFETCH_MAX, CACHE_MAX) | + HINIC_SQ_CTXT_PREF_SET(WQ_PREFETCH_THRESHOLD, CACHE_THRESHOLD); + + sq_ctxt->pref_wrapped = 1; + + sq_ctxt->pref_wq_hi_pfn_ci = + HINIC_SQ_CTXT_PREF_SET(ci_start, CI) | + HINIC_SQ_CTXT_PREF_SET(wq_page_pfn_hi, WQ_HI_PFN); + + sq_ctxt->pref_wq_lo_pfn = wq_page_pfn_lo; + + sq_ctxt->wq_block_hi_pfn = + HINIC_SQ_CTXT_WQ_BLOCK_SET(wq_block_pfn_hi, HI_PFN); + + sq_ctxt->wq_block_lo_pfn = wq_block_pfn_lo; + + hinic_cpu_to_be32(sq_ctxt, sizeof(*sq_ctxt)); +} + +void hinic_rq_prepare_ctxt(struct hinic_rq_ctxt *rq_ctxt, + struct hinic_rq *rq, u16 global_qid) +{ + u32 wq_page_pfn_hi, wq_page_pfn_lo, wq_block_pfn_hi, wq_block_pfn_lo; + u64 wq_page_addr, wq_page_pfn, wq_block_pfn; + u16 pi_start, ci_start; + struct hinic_wq *wq; + + wq = rq->wq; + ci_start = atomic_read(&wq->cons_idx); + pi_start = atomic_read(&wq->prod_idx); + + /* Read the first page paddr from the WQ page paddr ptrs */ + wq_page_addr = be64_to_cpu(*wq->block_vaddr); + + wq_page_pfn = HINIC_WQ_PAGE_PFN(wq_page_addr); + wq_page_pfn_hi = upper_32_bits(wq_page_pfn); + wq_page_pfn_lo = lower_32_bits(wq_page_pfn); + + wq_block_pfn = HINIC_WQ_BLOCK_PFN(wq->block_paddr); + wq_block_pfn_hi = upper_32_bits(wq_block_pfn); + wq_block_pfn_lo = lower_32_bits(wq_block_pfn); + + rq_ctxt->ceq_attr = HINIC_RQ_CTXT_CEQ_ATTR_SET(0, EN) | + HINIC_RQ_CTXT_CEQ_ATTR_SET(1, WRAPPED); + + rq_ctxt->pi_intr_attr = HINIC_RQ_CTXT_PI_SET(pi_start, IDX) | + HINIC_RQ_CTXT_PI_SET(rq->msix_entry, INTR); + + rq_ctxt->wq_hi_pfn_ci = HINIC_RQ_CTXT_WQ_PAGE_SET(wq_page_pfn_hi, + HI_PFN) | + HINIC_RQ_CTXT_WQ_PAGE_SET(ci_start, CI); + + rq_ctxt->wq_lo_pfn = wq_page_pfn_lo; + + rq_ctxt->pref_cache = + HINIC_RQ_CTXT_PREF_SET(WQ_PREFETCH_MIN, CACHE_MIN) | + HINIC_RQ_CTXT_PREF_SET(WQ_PREFETCH_MAX, CACHE_MAX) | + HINIC_RQ_CTXT_PREF_SET(WQ_PREFETCH_THRESHOLD, CACHE_THRESHOLD); + + rq_ctxt->pref_wrapped = 1; + + rq_ctxt->pref_wq_hi_pfn_ci = + HINIC_RQ_CTXT_PREF_SET(wq_page_pfn_hi, WQ_HI_PFN) | + HINIC_RQ_CTXT_PREF_SET(ci_start, CI); + + rq_ctxt->pref_wq_lo_pfn = wq_page_pfn_lo; + + rq_ctxt->pi_paddr_hi = upper_32_bits(rq->pi_dma_addr); + rq_ctxt->pi_paddr_lo = lower_32_bits(rq->pi_dma_addr); + + rq_ctxt->wq_block_hi_pfn = + HINIC_RQ_CTXT_WQ_BLOCK_SET(wq_block_pfn_hi, HI_PFN); + + rq_ctxt->wq_block_lo_pfn = wq_block_pfn_lo; + + hinic_cpu_to_be32(rq_ctxt, sizeof(*rq_ctxt)); +} + +/** + * alloc_sq_skb_arr - allocate sq array for saved skb + * @sq: HW Send Queue + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_sq_skb_arr(struct hinic_sq *sq) +{ + struct hinic_wq *wq = sq->wq; + size_t skb_arr_size; + + skb_arr_size = wq->q_depth * sizeof(*sq->saved_skb); + sq->saved_skb = vzalloc(skb_arr_size); + if (!sq->saved_skb) + return -ENOMEM; + + return 0; +} + +/** + * free_sq_skb_arr - free sq array for saved skb + * @sq: HW Send Queue + **/ +static void free_sq_skb_arr(struct hinic_sq *sq) +{ + vfree(sq->saved_skb); +} + +/** + * alloc_rq_skb_arr - allocate rq array for saved skb + * @rq: HW Receive Queue + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_rq_skb_arr(struct hinic_rq *rq) +{ + struct hinic_wq *wq = rq->wq; + size_t skb_arr_size; + + skb_arr_size = wq->q_depth * sizeof(*rq->saved_skb); + rq->saved_skb = vzalloc(skb_arr_size); + if (!rq->saved_skb) + return -ENOMEM; + + return 0; +} + +/** + * free_rq_skb_arr - free rq array for saved skb + * @rq: HW Receive Queue + **/ +static void free_rq_skb_arr(struct hinic_rq *rq) +{ + vfree(rq->saved_skb); +} + +/** + * hinic_init_sq - Initialize HW Send Queue + * @sq: HW Send Queue + * @hwif: HW Interface for accessing HW + * @wq: Work Queue for the data of the SQ + * @entry: msix entry for sq + * @ci_addr: address for reading the current HW consumer index + * @ci_dma_addr: dma address for reading the current HW consumer index + * @db_base: doorbell base address + * + * Return 0 - Success, negative - Failure + **/ +int hinic_init_sq(struct hinic_sq *sq, struct hinic_hwif *hwif, + struct hinic_wq *wq, struct msix_entry *entry, + void *ci_addr, dma_addr_t ci_dma_addr, + void __iomem *db_base) +{ + sq->hwif = hwif; + + sq->wq = wq; + + sq->irq = entry->vector; + sq->msix_entry = entry->entry; + + sq->hw_ci_addr = ci_addr; + sq->hw_ci_dma_addr = ci_dma_addr; + + sq->db_base = db_base + SQ_DB_OFF; + + return alloc_sq_skb_arr(sq); +} + +/** + * hinic_clean_sq - Clean HW Send Queue's Resources + * @sq: Send Queue + **/ +void hinic_clean_sq(struct hinic_sq *sq) +{ + free_sq_skb_arr(sq); +} + +/** + * alloc_rq_cqe - allocate rq completion queue elements + * @rq: HW Receive Queue + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_rq_cqe(struct hinic_rq *rq) +{ + struct hinic_hwif *hwif = rq->hwif; + struct pci_dev *pdev = hwif->pdev; + size_t cqe_dma_size, cqe_size; + struct hinic_wq *wq = rq->wq; + int j, i; + + cqe_size = wq->q_depth * sizeof(*rq->cqe); + rq->cqe = vzalloc(cqe_size); + if (!rq->cqe) + return -ENOMEM; + + cqe_dma_size = wq->q_depth * sizeof(*rq->cqe_dma); + rq->cqe_dma = vzalloc(cqe_dma_size); + if (!rq->cqe_dma) + goto err_cqe_dma_arr_alloc; + + for (i = 0; i < wq->q_depth; i++) { + rq->cqe[i] = dma_zalloc_coherent(&pdev->dev, + sizeof(*rq->cqe[i]), + &rq->cqe_dma[i], GFP_KERNEL); + if (!rq->cqe[i]) + goto err_cqe_alloc; + } + + return 0; + +err_cqe_alloc: + for (j = 0; j < i; j++) + dma_free_coherent(&pdev->dev, sizeof(*rq->cqe[j]), rq->cqe[j], + rq->cqe_dma[j]); + + vfree(rq->cqe_dma); + +err_cqe_dma_arr_alloc: + vfree(rq->cqe); + return -ENOMEM; +} + +/** + * free_rq_cqe - free rq completion queue elements + * @rq: HW Receive Queue + **/ +static void free_rq_cqe(struct hinic_rq *rq) +{ + struct hinic_hwif *hwif = rq->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_wq *wq = rq->wq; + int i; + + for (i = 0; i < wq->q_depth; i++) + dma_free_coherent(&pdev->dev, sizeof(*rq->cqe[i]), rq->cqe[i], + rq->cqe_dma[i]); + + vfree(rq->cqe_dma); + vfree(rq->cqe); +} + +/** + * hinic_init_rq - Initialize HW Receive Queue + * @rq: HW Receive Queue + * @hwif: HW Interface for accessing HW + * @wq: Work Queue for the data of the RQ + * @entry: msix entry for rq + * + * Return 0 - Success, negative - Failure + **/ +int hinic_init_rq(struct hinic_rq *rq, struct hinic_hwif *hwif, + struct hinic_wq *wq, struct msix_entry *entry) +{ + struct pci_dev *pdev = hwif->pdev; + size_t pi_size; + int err; + + rq->hwif = hwif; + + rq->wq = wq; + + rq->irq = entry->vector; + rq->msix_entry = entry->entry; + + rq->buf_sz = HINIC_RX_BUF_SZ; + + err = alloc_rq_skb_arr(rq); + if (err) { + dev_err(&pdev->dev, "Failed to allocate rq priv data\n"); + return err; + } + + err = alloc_rq_cqe(rq); + if (err) { + dev_err(&pdev->dev, "Failed to allocate rq cqe\n"); + goto err_alloc_rq_cqe; + } + + /* HW requirements: Must be at least 32 bit */ + pi_size = ALIGN(sizeof(*rq->pi_virt_addr), sizeof(u32)); + rq->pi_virt_addr = dma_zalloc_coherent(&pdev->dev, pi_size, + &rq->pi_dma_addr, GFP_KERNEL); + if (!rq->pi_virt_addr) { + dev_err(&pdev->dev, "Failed to allocate PI address\n"); + err = -ENOMEM; + goto err_pi_virt; + } + + return 0; + +err_pi_virt: + free_rq_cqe(rq); + +err_alloc_rq_cqe: + free_rq_skb_arr(rq); + return err; +} + +/** + * hinic_clean_rq - Clean HW Receive Queue's Resources + * @rq: HW Receive Queue + **/ +void hinic_clean_rq(struct hinic_rq *rq) +{ + struct hinic_hwif *hwif = rq->hwif; + struct pci_dev *pdev = hwif->pdev; + size_t pi_size; + + pi_size = ALIGN(sizeof(*rq->pi_virt_addr), sizeof(u32)); + dma_free_coherent(&pdev->dev, pi_size, rq->pi_virt_addr, + rq->pi_dma_addr); + + free_rq_cqe(rq); + free_rq_skb_arr(rq); +} + +/** + * hinic_get_sq_free_wqebbs - return number of free wqebbs for use + * @sq: send queue + * + * Return number of free wqebbs + **/ +int hinic_get_sq_free_wqebbs(struct hinic_sq *sq) +{ + struct hinic_wq *wq = sq->wq; + + return atomic_read(&wq->delta) - 1; +} + +/** + * hinic_get_rq_free_wqebbs - return number of free wqebbs for use + * @rq: recv queue + * + * Return number of free wqebbs + **/ +int hinic_get_rq_free_wqebbs(struct hinic_rq *rq) +{ + struct hinic_wq *wq = rq->wq; + + return atomic_read(&wq->delta) - 1; +} + +static void sq_prepare_ctrl(struct hinic_sq_ctrl *ctrl, u16 prod_idx, + int nr_descs) +{ + u32 ctrl_size, task_size, bufdesc_size; + + ctrl_size = SIZE_8BYTES(sizeof(struct hinic_sq_ctrl)); + task_size = SIZE_8BYTES(sizeof(struct hinic_sq_task)); + bufdesc_size = nr_descs * sizeof(struct hinic_sq_bufdesc); + bufdesc_size = SIZE_8BYTES(bufdesc_size); + + ctrl->ctrl_info = HINIC_SQ_CTRL_SET(bufdesc_size, BUFDESC_SECT_LEN) | + HINIC_SQ_CTRL_SET(task_size, TASKSECT_LEN) | + HINIC_SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) | + HINIC_SQ_CTRL_SET(ctrl_size, LEN); + + ctrl->queue_info = HINIC_SQ_CTRL_SET(TX_MAX_MSS_DEFAULT, + QUEUE_INFO_MSS); +} + +static void sq_prepare_task(struct hinic_sq_task *task) +{ + task->pkt_info0 = + HINIC_SQ_TASK_INFO0_SET(0, L2HDR_LEN) | + HINIC_SQ_TASK_INFO0_SET(HINIC_L4_OFF_DISABLE, L4_OFFLOAD) | + HINIC_SQ_TASK_INFO0_SET(HINIC_OUTER_L3TYPE_UNKNOWN, + INNER_L3TYPE) | + HINIC_SQ_TASK_INFO0_SET(HINIC_VLAN_OFF_DISABLE, + VLAN_OFFLOAD) | + HINIC_SQ_TASK_INFO0_SET(HINIC_PKT_NOT_PARSED, PARSE_FLAG); + + task->pkt_info1 = + HINIC_SQ_TASK_INFO1_SET(HINIC_MEDIA_UNKNOWN, MEDIA_TYPE) | + HINIC_SQ_TASK_INFO1_SET(0, INNER_L4_LEN) | + HINIC_SQ_TASK_INFO1_SET(0, INNER_L3_LEN); + + task->pkt_info2 = + HINIC_SQ_TASK_INFO2_SET(0, TUNNEL_L4_LEN) | + HINIC_SQ_TASK_INFO2_SET(0, OUTER_L3_LEN) | + HINIC_SQ_TASK_INFO2_SET(HINIC_TUNNEL_L4TYPE_UNKNOWN, + TUNNEL_L4TYPE) | + HINIC_SQ_TASK_INFO2_SET(HINIC_OUTER_L3TYPE_UNKNOWN, + OUTER_L3TYPE); + + task->ufo_v6_identify = 0; + + task->pkt_info4 = HINIC_SQ_TASK_INFO4_SET(HINIC_L2TYPE_ETH, L2TYPE); + + task->zero_pad = 0; +} + +/** + * hinic_sq_prepare_wqe - prepare wqe before insert to the queue + * @sq: send queue + * @prod_idx: pi value + * @sq_wqe: wqe to prepare + * @sges: sges for use by the wqe for send for buf addresses + * @nr_sges: number of sges + **/ +void hinic_sq_prepare_wqe(struct hinic_sq *sq, u16 prod_idx, + struct hinic_sq_wqe *sq_wqe, struct hinic_sge *sges, + int nr_sges) +{ + int i; + + sq_prepare_ctrl(&sq_wqe->ctrl, prod_idx, nr_sges); + + sq_prepare_task(&sq_wqe->task); + + for (i = 0; i < nr_sges; i++) + sq_wqe->buf_descs[i].sge = sges[i]; +} + +/** + * sq_prepare_db - prepare doorbell to write + * @sq: send queue + * @prod_idx: pi value for the doorbell + * @cos: cos of the doorbell + * + * Return db value + **/ +static u32 sq_prepare_db(struct hinic_sq *sq, u16 prod_idx, unsigned int cos) +{ + struct hinic_qp *qp = container_of(sq, struct hinic_qp, sq); + u8 hi_prod_idx = SQ_DB_PI_HI(SQ_MASKED_IDX(sq, prod_idx)); + + /* Data should be written to HW in Big Endian Format */ + return cpu_to_be32(HINIC_SQ_DB_INFO_SET(hi_prod_idx, PI_HI) | + HINIC_SQ_DB_INFO_SET(HINIC_DB_SQ_TYPE, TYPE) | + HINIC_SQ_DB_INFO_SET(HINIC_DATA_PATH, PATH) | + HINIC_SQ_DB_INFO_SET(cos, COS) | + HINIC_SQ_DB_INFO_SET(qp->q_id, QID)); +} + +/** + * hinic_sq_write_db- write doorbell + * @sq: send queue + * @prod_idx: pi value for the doorbell + * @wqe_size: wqe size + * @cos: cos of the wqe + **/ +void hinic_sq_write_db(struct hinic_sq *sq, u16 prod_idx, unsigned int wqe_size, + unsigned int cos) +{ + struct hinic_wq *wq = sq->wq; + + /* increment prod_idx to the next */ + prod_idx += ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size; + + wmb(); /* Write all before the doorbell */ + + writel(sq_prepare_db(sq, prod_idx, cos), SQ_DB_ADDR(sq, prod_idx)); +} + +/** + * hinic_sq_get_wqe - get wqe ptr in the current pi and update the pi + * @sq: sq to get wqe from + * @wqe_size: wqe size + * @prod_idx: returned pi + * + * Return wqe pointer + **/ +struct hinic_sq_wqe *hinic_sq_get_wqe(struct hinic_sq *sq, + unsigned int wqe_size, u16 *prod_idx) +{ + struct hinic_hw_wqe *hw_wqe = hinic_get_wqe(sq->wq, wqe_size, + prod_idx); + + if (IS_ERR(hw_wqe)) + return NULL; + + return &hw_wqe->sq_wqe; +} + +/** + * hinic_sq_write_wqe - write the wqe to the sq + * @sq: send queue + * @prod_idx: pi of the wqe + * @sq_wqe: the wqe to write + * @skb: skb to save + * @wqe_size: the size of the wqe + **/ +void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx, + struct hinic_sq_wqe *sq_wqe, + struct sk_buff *skb, unsigned int wqe_size) +{ + struct hinic_hw_wqe *hw_wqe = (struct hinic_hw_wqe *)sq_wqe; + + sq->saved_skb[prod_idx] = skb; + + /* The data in the HW should be in Big Endian Format */ + hinic_cpu_to_be32(sq_wqe, wqe_size); + + hinic_write_wqe(sq->wq, hw_wqe, wqe_size); +} + +/** + * hinic_sq_read_wqe - read wqe ptr in the current ci and update the ci + * @sq: send queue + * @skb: return skb that was saved + * @wqe_size: the size of the wqe + * @cons_idx: consumer index of the wqe + * + * Return wqe in ci position + **/ +struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq, + struct sk_buff **skb, + unsigned int *wqe_size, u16 *cons_idx) +{ + struct hinic_hw_wqe *hw_wqe; + struct hinic_sq_wqe *sq_wqe; + struct hinic_sq_ctrl *ctrl; + unsigned int buf_sect_len; + u32 ctrl_info; + + /* read the ctrl section for getting wqe size */ + hw_wqe = hinic_read_wqe(sq->wq, sizeof(*ctrl), cons_idx); + if (IS_ERR(hw_wqe)) + return NULL; + + sq_wqe = &hw_wqe->sq_wqe; + ctrl = &sq_wqe->ctrl; + ctrl_info = be32_to_cpu(ctrl->ctrl_info); + buf_sect_len = HINIC_SQ_CTRL_GET(ctrl_info, BUFDESC_SECT_LEN); + + *wqe_size = sizeof(*ctrl) + sizeof(sq_wqe->task); + *wqe_size += SECT_SIZE_FROM_8BYTES(buf_sect_len); + + *skb = sq->saved_skb[*cons_idx]; + + /* using the real wqe size to read wqe again */ + hw_wqe = hinic_read_wqe(sq->wq, *wqe_size, cons_idx); + + return &hw_wqe->sq_wqe; +} + +/** + * hinic_sq_put_wqe - release the ci for new wqes + * @sq: send queue + * @wqe_size: the size of the wqe + **/ +void hinic_sq_put_wqe(struct hinic_sq *sq, unsigned int wqe_size) +{ + hinic_put_wqe(sq->wq, wqe_size); +} + +/** + * hinic_sq_get_sges - get sges from the wqe + * @sq_wqe: wqe to get the sges from its buffer addresses + * @sges: returned sges + * @nr_sges: number sges to return + **/ +void hinic_sq_get_sges(struct hinic_sq_wqe *sq_wqe, struct hinic_sge *sges, + int nr_sges) +{ + int i; + + for (i = 0; i < nr_sges && i < HINIC_MAX_SQ_BUFDESCS; i++) { + sges[i] = sq_wqe->buf_descs[i].sge; + hinic_be32_to_cpu(&sges[i], sizeof(sges[i])); + } +} + +/** + * hinic_rq_get_wqe - get wqe ptr in the current pi and update the pi + * @rq: rq to get wqe from + * @wqe_size: wqe size + * @prod_idx: returned pi + * + * Return wqe pointer + **/ +struct hinic_rq_wqe *hinic_rq_get_wqe(struct hinic_rq *rq, + unsigned int wqe_size, u16 *prod_idx) +{ + struct hinic_hw_wqe *hw_wqe = hinic_get_wqe(rq->wq, wqe_size, + prod_idx); + + if (IS_ERR(hw_wqe)) + return NULL; + + return &hw_wqe->rq_wqe; +} + +/** + * hinic_rq_write_wqe - write the wqe to the rq + * @rq: recv queue + * @prod_idx: pi of the wqe + * @rq_wqe: the wqe to write + * @skb: skb to save + **/ +void hinic_rq_write_wqe(struct hinic_rq *rq, u16 prod_idx, + struct hinic_rq_wqe *rq_wqe, struct sk_buff *skb) +{ + struct hinic_hw_wqe *hw_wqe = (struct hinic_hw_wqe *)rq_wqe; + + rq->saved_skb[prod_idx] = skb; + + /* The data in the HW should be in Big Endian Format */ + hinic_cpu_to_be32(rq_wqe, sizeof(*rq_wqe)); + + hinic_write_wqe(rq->wq, hw_wqe, sizeof(*rq_wqe)); +} + +/** + * hinic_rq_read_wqe - read wqe ptr in the current ci and update the ci + * @rq: recv queue + * @wqe_size: the size of the wqe + * @skb: return saved skb + * @cons_idx: consumer index of the wqe + * + * Return wqe in ci position + **/ +struct hinic_rq_wqe *hinic_rq_read_wqe(struct hinic_rq *rq, + unsigned int wqe_size, + struct sk_buff **skb, u16 *cons_idx) +{ + struct hinic_hw_wqe *hw_wqe; + struct hinic_rq_cqe *cqe; + int rx_done; + u32 status; + + hw_wqe = hinic_read_wqe(rq->wq, wqe_size, cons_idx); + if (IS_ERR(hw_wqe)) + return NULL; + + cqe = rq->cqe[*cons_idx]; + + status = be32_to_cpu(cqe->status); + + rx_done = HINIC_RQ_CQE_STATUS_GET(status, RXDONE); + if (!rx_done) + return NULL; + + *skb = rq->saved_skb[*cons_idx]; + + return &hw_wqe->rq_wqe; +} + +/** + * hinic_rq_read_next_wqe - increment ci and read the wqe in ci position + * @rq: recv queue + * @wqe_size: the size of the wqe + * @skb: return saved skb + * @cons_idx: consumer index in the wq + * + * Return wqe in incremented ci position + **/ +struct hinic_rq_wqe *hinic_rq_read_next_wqe(struct hinic_rq *rq, + unsigned int wqe_size, + struct sk_buff **skb, + u16 *cons_idx) +{ + struct hinic_wq *wq = rq->wq; + struct hinic_hw_wqe *hw_wqe; + unsigned int num_wqebbs; + + wqe_size = ALIGN(wqe_size, wq->wqebb_size); + num_wqebbs = wqe_size / wq->wqebb_size; + + *cons_idx = RQ_MASKED_IDX(rq, *cons_idx + num_wqebbs); + + *skb = rq->saved_skb[*cons_idx]; + + hw_wqe = hinic_read_wqe_direct(wq, *cons_idx); + + return &hw_wqe->rq_wqe; +} + +/** + * hinic_put_wqe - release the ci for new wqes + * @rq: recv queue + * @cons_idx: consumer index of the wqe + * @wqe_size: the size of the wqe + **/ +void hinic_rq_put_wqe(struct hinic_rq *rq, u16 cons_idx, + unsigned int wqe_size) +{ + struct hinic_rq_cqe *cqe = rq->cqe[cons_idx]; + u32 status = be32_to_cpu(cqe->status); + + status = HINIC_RQ_CQE_STATUS_CLEAR(status, RXDONE); + + /* Rx WQE size is 1 WQEBB, no wq shadow*/ + cqe->status = cpu_to_be32(status); + + wmb(); /* clear done flag */ + + hinic_put_wqe(rq->wq, wqe_size); +} + +/** + * hinic_rq_get_sge - get sge from the wqe + * @rq: recv queue + * @rq_wqe: wqe to get the sge from its buf address + * @cons_idx: consumer index + * @sge: returned sge + **/ +void hinic_rq_get_sge(struct hinic_rq *rq, struct hinic_rq_wqe *rq_wqe, + u16 cons_idx, struct hinic_sge *sge) +{ + struct hinic_rq_cqe *cqe = rq->cqe[cons_idx]; + u32 len = be32_to_cpu(cqe->len); + + sge->hi_addr = be32_to_cpu(rq_wqe->buf_desc.hi_addr); + sge->lo_addr = be32_to_cpu(rq_wqe->buf_desc.lo_addr); + sge->len = HINIC_RQ_CQE_SGE_GET(len, LEN); +} + +/** + * hinic_rq_prepare_wqe - prepare wqe before insert to the queue + * @rq: recv queue + * @prod_idx: pi value + * @rq_wqe: the wqe + * @sge: sge for use by the wqe for recv buf address + **/ +void hinic_rq_prepare_wqe(struct hinic_rq *rq, u16 prod_idx, + struct hinic_rq_wqe *rq_wqe, struct hinic_sge *sge) +{ + struct hinic_rq_cqe_sect *cqe_sect = &rq_wqe->cqe_sect; + struct hinic_rq_bufdesc *buf_desc = &rq_wqe->buf_desc; + struct hinic_rq_cqe *cqe = rq->cqe[prod_idx]; + struct hinic_rq_ctrl *ctrl = &rq_wqe->ctrl; + dma_addr_t cqe_dma = rq->cqe_dma[prod_idx]; + + ctrl->ctrl_info = + HINIC_RQ_CTRL_SET(SIZE_8BYTES(sizeof(*ctrl)), LEN) | + HINIC_RQ_CTRL_SET(SIZE_8BYTES(sizeof(*cqe_sect)), + COMPLETE_LEN) | + HINIC_RQ_CTRL_SET(SIZE_8BYTES(sizeof(*buf_desc)), + BUFDESC_SECT_LEN) | + HINIC_RQ_CTRL_SET(RQ_COMPLETE_SGE, COMPLETE_FORMAT); + + hinic_set_sge(&cqe_sect->sge, cqe_dma, sizeof(*cqe)); + + buf_desc->hi_addr = sge->hi_addr; + buf_desc->lo_addr = sge->lo_addr; +} + +/** + * hinic_rq_update - update pi of the rq + * @rq: recv queue + * @prod_idx: pi value + **/ +void hinic_rq_update(struct hinic_rq *rq, u16 prod_idx) +{ + *rq->pi_virt_addr = cpu_to_be16(RQ_MASKED_IDX(rq, prod_idx + 1)); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h new file mode 100644 index 000000000000..df729a1587e9 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -0,0 +1,201 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_QP_H +#define HINIC_HW_QP_H + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/sizes.h> +#include <linux/pci.h> +#include <linux/skbuff.h> + +#include "hinic_common.h" +#include "hinic_hw_if.h" +#include "hinic_hw_wqe.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_qp_ctxt.h" + +#define HINIC_SQ_DB_INFO_PI_HI_SHIFT 0 +#define HINIC_SQ_DB_INFO_QID_SHIFT 8 +#define HINIC_SQ_DB_INFO_PATH_SHIFT 23 +#define HINIC_SQ_DB_INFO_COS_SHIFT 24 +#define HINIC_SQ_DB_INFO_TYPE_SHIFT 27 + +#define HINIC_SQ_DB_INFO_PI_HI_MASK 0xFF +#define HINIC_SQ_DB_INFO_QID_MASK 0x3FF +#define HINIC_SQ_DB_INFO_PATH_MASK 0x1 +#define HINIC_SQ_DB_INFO_COS_MASK 0x7 +#define HINIC_SQ_DB_INFO_TYPE_MASK 0x1F + +#define HINIC_SQ_DB_INFO_SET(val, member) \ + (((u32)(val) & HINIC_SQ_DB_INFO_##member##_MASK) \ + << HINIC_SQ_DB_INFO_##member##_SHIFT) + +#define HINIC_SQ_WQEBB_SIZE 64 +#define HINIC_RQ_WQEBB_SIZE 32 + +#define HINIC_SQ_PAGE_SIZE SZ_4K +#define HINIC_RQ_PAGE_SIZE SZ_4K + +#define HINIC_SQ_DEPTH SZ_4K +#define HINIC_RQ_DEPTH SZ_4K + +/* In any change to HINIC_RX_BUF_SZ, HINIC_RX_BUF_SZ_IDX must be changed */ +#define HINIC_RX_BUF_SZ 2048 +#define HINIC_RX_BUF_SZ_IDX HINIC_RX_BUF_SZ_2048_IDX + +#define HINIC_MIN_TX_WQE_SIZE(wq) \ + ALIGN(HINIC_SQ_WQE_SIZE(1), (wq)->wqebb_size) + +#define HINIC_MIN_TX_NUM_WQEBBS(sq) \ + (HINIC_MIN_TX_WQE_SIZE((sq)->wq) / (sq)->wq->wqebb_size) + +enum hinic_rx_buf_sz_idx { + HINIC_RX_BUF_SZ_32_IDX, + HINIC_RX_BUF_SZ_64_IDX, + HINIC_RX_BUF_SZ_96_IDX, + HINIC_RX_BUF_SZ_128_IDX, + HINIC_RX_BUF_SZ_192_IDX, + HINIC_RX_BUF_SZ_256_IDX, + HINIC_RX_BUF_SZ_384_IDX, + HINIC_RX_BUF_SZ_512_IDX, + HINIC_RX_BUF_SZ_768_IDX, + HINIC_RX_BUF_SZ_1024_IDX, + HINIC_RX_BUF_SZ_1536_IDX, + HINIC_RX_BUF_SZ_2048_IDX, + HINIC_RX_BUF_SZ_3072_IDX, + HINIC_RX_BUF_SZ_4096_IDX, + HINIC_RX_BUF_SZ_8192_IDX, + HINIC_RX_BUF_SZ_16384_IDX, +}; + +struct hinic_sq { + struct hinic_hwif *hwif; + + struct hinic_wq *wq; + + u32 irq; + u16 msix_entry; + + void *hw_ci_addr; + dma_addr_t hw_ci_dma_addr; + + void __iomem *db_base; + + struct sk_buff **saved_skb; +}; + +struct hinic_rq { + struct hinic_hwif *hwif; + + struct hinic_wq *wq; + + u32 irq; + u16 msix_entry; + + size_t buf_sz; + + struct sk_buff **saved_skb; + + struct hinic_rq_cqe **cqe; + dma_addr_t *cqe_dma; + + u16 *pi_virt_addr; + dma_addr_t pi_dma_addr; +}; + +struct hinic_qp { + struct hinic_sq sq; + struct hinic_rq rq; + + u16 q_id; +}; + +void hinic_qp_prepare_header(struct hinic_qp_ctxt_header *qp_ctxt_hdr, + enum hinic_qp_ctxt_type ctxt_type, + u16 num_queues, u16 max_queues); + +void hinic_sq_prepare_ctxt(struct hinic_sq_ctxt *sq_ctxt, + struct hinic_sq *sq, u16 global_qid); + +void hinic_rq_prepare_ctxt(struct hinic_rq_ctxt *rq_ctxt, + struct hinic_rq *rq, u16 global_qid); + +int hinic_init_sq(struct hinic_sq *sq, struct hinic_hwif *hwif, + struct hinic_wq *wq, struct msix_entry *entry, void *ci_addr, + dma_addr_t ci_dma_addr, void __iomem *db_base); + +void hinic_clean_sq(struct hinic_sq *sq); + +int hinic_init_rq(struct hinic_rq *rq, struct hinic_hwif *hwif, + struct hinic_wq *wq, struct msix_entry *entry); + +void hinic_clean_rq(struct hinic_rq *rq); + +int hinic_get_sq_free_wqebbs(struct hinic_sq *sq); + +int hinic_get_rq_free_wqebbs(struct hinic_rq *rq); + +void hinic_sq_prepare_wqe(struct hinic_sq *sq, u16 prod_idx, + struct hinic_sq_wqe *wqe, struct hinic_sge *sges, + int nr_sges); + +void hinic_sq_write_db(struct hinic_sq *sq, u16 prod_idx, unsigned int wqe_size, + unsigned int cos); + +struct hinic_sq_wqe *hinic_sq_get_wqe(struct hinic_sq *sq, + unsigned int wqe_size, u16 *prod_idx); + +void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx, + struct hinic_sq_wqe *wqe, struct sk_buff *skb, + unsigned int wqe_size); + +struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq, + struct sk_buff **skb, + unsigned int *wqe_size, u16 *cons_idx); + +void hinic_sq_put_wqe(struct hinic_sq *sq, unsigned int wqe_size); + +void hinic_sq_get_sges(struct hinic_sq_wqe *wqe, struct hinic_sge *sges, + int nr_sges); + +struct hinic_rq_wqe *hinic_rq_get_wqe(struct hinic_rq *rq, + unsigned int wqe_size, u16 *prod_idx); + +void hinic_rq_write_wqe(struct hinic_rq *rq, u16 prod_idx, + struct hinic_rq_wqe *wqe, struct sk_buff *skb); + +struct hinic_rq_wqe *hinic_rq_read_wqe(struct hinic_rq *rq, + unsigned int wqe_size, + struct sk_buff **skb, u16 *cons_idx); + +struct hinic_rq_wqe *hinic_rq_read_next_wqe(struct hinic_rq *rq, + unsigned int wqe_size, + struct sk_buff **skb, + u16 *cons_idx); + +void hinic_rq_put_wqe(struct hinic_rq *rq, u16 cons_idx, + unsigned int wqe_size); + +void hinic_rq_get_sge(struct hinic_rq *rq, struct hinic_rq_wqe *wqe, + u16 cons_idx, struct hinic_sge *sge); + +void hinic_rq_prepare_wqe(struct hinic_rq *rq, u16 prod_idx, + struct hinic_rq_wqe *wqe, struct hinic_sge *sge); + +void hinic_rq_update(struct hinic_rq *rq, u16 prod_idx); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h new file mode 100644 index 000000000000..376abf00762b --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp_ctxt.h @@ -0,0 +1,214 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_QP_CTXT_H +#define HINIC_HW_QP_CTXT_H + +#include <linux/types.h> + +#include "hinic_hw_cmdq.h" + +#define HINIC_SQ_CTXT_CEQ_ATTR_GLOBAL_SQ_ID_SHIFT 13 +#define HINIC_SQ_CTXT_CEQ_ATTR_EN_SHIFT 23 + +#define HINIC_SQ_CTXT_CEQ_ATTR_GLOBAL_SQ_ID_MASK 0x3FF +#define HINIC_SQ_CTXT_CEQ_ATTR_EN_MASK 0x1 + +#define HINIC_SQ_CTXT_CEQ_ATTR_SET(val, member) \ + (((u32)(val) & HINIC_SQ_CTXT_CEQ_ATTR_##member##_MASK) \ + << HINIC_SQ_CTXT_CEQ_ATTR_##member##_SHIFT) + +#define HINIC_SQ_CTXT_CI_IDX_SHIFT 11 +#define HINIC_SQ_CTXT_CI_WRAPPED_SHIFT 23 + +#define HINIC_SQ_CTXT_CI_IDX_MASK 0xFFF +#define HINIC_SQ_CTXT_CI_WRAPPED_MASK 0x1 + +#define HINIC_SQ_CTXT_CI_SET(val, member) \ + (((u32)(val) & HINIC_SQ_CTXT_CI_##member##_MASK) \ + << HINIC_SQ_CTXT_CI_##member##_SHIFT) + +#define HINIC_SQ_CTXT_WQ_PAGE_HI_PFN_SHIFT 0 +#define HINIC_SQ_CTXT_WQ_PAGE_PI_SHIFT 20 + +#define HINIC_SQ_CTXT_WQ_PAGE_HI_PFN_MASK 0xFFFFF +#define HINIC_SQ_CTXT_WQ_PAGE_PI_MASK 0xFFF + +#define HINIC_SQ_CTXT_WQ_PAGE_SET(val, member) \ + (((u32)(val) & HINIC_SQ_CTXT_WQ_PAGE_##member##_MASK) \ + << HINIC_SQ_CTXT_WQ_PAGE_##member##_SHIFT) + +#define HINIC_SQ_CTXT_PREF_CACHE_THRESHOLD_SHIFT 0 +#define HINIC_SQ_CTXT_PREF_CACHE_MAX_SHIFT 14 +#define HINIC_SQ_CTXT_PREF_CACHE_MIN_SHIFT 25 + +#define HINIC_SQ_CTXT_PREF_CACHE_THRESHOLD_MASK 0x3FFF +#define HINIC_SQ_CTXT_PREF_CACHE_MAX_MASK 0x7FF +#define HINIC_SQ_CTXT_PREF_CACHE_MIN_MASK 0x7F + +#define HINIC_SQ_CTXT_PREF_WQ_HI_PFN_SHIFT 0 +#define HINIC_SQ_CTXT_PREF_CI_SHIFT 20 + +#define HINIC_SQ_CTXT_PREF_WQ_HI_PFN_MASK 0xFFFFF +#define HINIC_SQ_CTXT_PREF_CI_MASK 0xFFF + +#define HINIC_SQ_CTXT_PREF_SET(val, member) \ + (((u32)(val) & HINIC_SQ_CTXT_PREF_##member##_MASK) \ + << HINIC_SQ_CTXT_PREF_##member##_SHIFT) + +#define HINIC_SQ_CTXT_WQ_BLOCK_HI_PFN_SHIFT 0 + +#define HINIC_SQ_CTXT_WQ_BLOCK_HI_PFN_MASK 0x7FFFFF + +#define HINIC_SQ_CTXT_WQ_BLOCK_SET(val, member) \ + (((u32)(val) & HINIC_SQ_CTXT_WQ_BLOCK_##member##_MASK) \ + << HINIC_SQ_CTXT_WQ_BLOCK_##member##_SHIFT) + +#define HINIC_RQ_CTXT_CEQ_ATTR_EN_SHIFT 0 +#define HINIC_RQ_CTXT_CEQ_ATTR_WRAPPED_SHIFT 1 + +#define HINIC_RQ_CTXT_CEQ_ATTR_EN_MASK 0x1 +#define HINIC_RQ_CTXT_CEQ_ATTR_WRAPPED_MASK 0x1 + +#define HINIC_RQ_CTXT_CEQ_ATTR_SET(val, member) \ + (((u32)(val) & HINIC_RQ_CTXT_CEQ_ATTR_##member##_MASK) \ + << HINIC_RQ_CTXT_CEQ_ATTR_##member##_SHIFT) + +#define HINIC_RQ_CTXT_PI_IDX_SHIFT 0 +#define HINIC_RQ_CTXT_PI_INTR_SHIFT 22 + +#define HINIC_RQ_CTXT_PI_IDX_MASK 0xFFF +#define HINIC_RQ_CTXT_PI_INTR_MASK 0x3FF + +#define HINIC_RQ_CTXT_PI_SET(val, member) \ + (((u32)(val) & HINIC_RQ_CTXT_PI_##member##_MASK) << \ + HINIC_RQ_CTXT_PI_##member##_SHIFT) + +#define HINIC_RQ_CTXT_WQ_PAGE_HI_PFN_SHIFT 0 +#define HINIC_RQ_CTXT_WQ_PAGE_CI_SHIFT 20 + +#define HINIC_RQ_CTXT_WQ_PAGE_HI_PFN_MASK 0xFFFFF +#define HINIC_RQ_CTXT_WQ_PAGE_CI_MASK 0xFFF + +#define HINIC_RQ_CTXT_WQ_PAGE_SET(val, member) \ + (((u32)(val) & HINIC_RQ_CTXT_WQ_PAGE_##member##_MASK) << \ + HINIC_RQ_CTXT_WQ_PAGE_##member##_SHIFT) + +#define HINIC_RQ_CTXT_PREF_CACHE_THRESHOLD_SHIFT 0 +#define HINIC_RQ_CTXT_PREF_CACHE_MAX_SHIFT 14 +#define HINIC_RQ_CTXT_PREF_CACHE_MIN_SHIFT 25 + +#define HINIC_RQ_CTXT_PREF_CACHE_THRESHOLD_MASK 0x3FFF +#define HINIC_RQ_CTXT_PREF_CACHE_MAX_MASK 0x7FF +#define HINIC_RQ_CTXT_PREF_CACHE_MIN_MASK 0x7F + +#define HINIC_RQ_CTXT_PREF_WQ_HI_PFN_SHIFT 0 +#define HINIC_RQ_CTXT_PREF_CI_SHIFT 20 + +#define HINIC_RQ_CTXT_PREF_WQ_HI_PFN_MASK 0xFFFFF +#define HINIC_RQ_CTXT_PREF_CI_MASK 0xFFF + +#define HINIC_RQ_CTXT_PREF_SET(val, member) \ + (((u32)(val) & HINIC_RQ_CTXT_PREF_##member##_MASK) << \ + HINIC_RQ_CTXT_PREF_##member##_SHIFT) + +#define HINIC_RQ_CTXT_WQ_BLOCK_HI_PFN_SHIFT 0 + +#define HINIC_RQ_CTXT_WQ_BLOCK_HI_PFN_MASK 0x7FFFFF + +#define HINIC_RQ_CTXT_WQ_BLOCK_SET(val, member) \ + (((u32)(val) & HINIC_RQ_CTXT_WQ_BLOCK_##member##_MASK) << \ + HINIC_RQ_CTXT_WQ_BLOCK_##member##_SHIFT) + +#define HINIC_SQ_CTXT_SIZE(num_sqs) (sizeof(struct hinic_qp_ctxt_header) \ + + (num_sqs) * sizeof(struct hinic_sq_ctxt)) + +#define HINIC_RQ_CTXT_SIZE(num_rqs) (sizeof(struct hinic_qp_ctxt_header) \ + + (num_rqs) * sizeof(struct hinic_rq_ctxt)) + +#define HINIC_WQ_PAGE_PFN_SHIFT 12 +#define HINIC_WQ_BLOCK_PFN_SHIFT 9 + +#define HINIC_WQ_PAGE_PFN(page_addr) ((page_addr) >> HINIC_WQ_PAGE_PFN_SHIFT) +#define HINIC_WQ_BLOCK_PFN(page_addr) ((page_addr) >> \ + HINIC_WQ_BLOCK_PFN_SHIFT) + +#define HINIC_Q_CTXT_MAX \ + ((HINIC_CMDQ_BUF_SIZE - sizeof(struct hinic_qp_ctxt_header)) \ + / sizeof(struct hinic_sq_ctxt)) + +enum hinic_qp_ctxt_type { + HINIC_QP_CTXT_TYPE_SQ, + HINIC_QP_CTXT_TYPE_RQ +}; + +struct hinic_qp_ctxt_header { + u16 num_queues; + u16 queue_type; + u32 addr_offset; +}; + +struct hinic_sq_ctxt { + u32 ceq_attr; + + u32 ci_wrapped; + + u32 wq_hi_pfn_pi; + u32 wq_lo_pfn; + + u32 pref_cache; + u32 pref_wrapped; + u32 pref_wq_hi_pfn_ci; + u32 pref_wq_lo_pfn; + + u32 rsvd0; + u32 rsvd1; + + u32 wq_block_hi_pfn; + u32 wq_block_lo_pfn; +}; + +struct hinic_rq_ctxt { + u32 ceq_attr; + + u32 pi_intr_attr; + + u32 wq_hi_pfn_ci; + u32 wq_lo_pfn; + + u32 pref_cache; + u32 pref_wrapped; + + u32 pref_wq_hi_pfn_ci; + u32 pref_wq_lo_pfn; + + u32 pi_paddr_hi; + u32 pi_paddr_lo; + + u32 wq_block_hi_pfn; + u32 wq_block_lo_pfn; +}; + +struct hinic_sq_ctxt_block { + struct hinic_qp_ctxt_header hdr; + struct hinic_sq_ctxt sq_ctxt[HINIC_Q_CTXT_MAX]; +}; + +struct hinic_rq_ctxt_block { + struct hinic_qp_ctxt_header hdr; + struct hinic_rq_ctxt rq_ctxt[HINIC_Q_CTXT_MAX]; +}; + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c new file mode 100644 index 000000000000..3e3181c089bd --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c @@ -0,0 +1,878 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/dma-mapping.h> +#include <linux/slab.h> +#include <linux/atomic.h> +#include <linux/semaphore.h> +#include <linux/errno.h> +#include <linux/vmalloc.h> +#include <linux/err.h> +#include <asm/byteorder.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_wqe.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_cmdq.h" + +#define WQS_BLOCKS_PER_PAGE 4 + +#define WQ_BLOCK_SIZE 4096 +#define WQS_PAGE_SIZE (WQS_BLOCKS_PER_PAGE * WQ_BLOCK_SIZE) + +#define WQS_MAX_NUM_BLOCKS 128 +#define WQS_FREE_BLOCKS_SIZE(wqs) (WQS_MAX_NUM_BLOCKS * \ + sizeof((wqs)->free_blocks[0])) + +#define WQ_SIZE(wq) ((wq)->q_depth * (wq)->wqebb_size) + +#define WQ_PAGE_ADDR_SIZE sizeof(u64) +#define WQ_MAX_PAGES (WQ_BLOCK_SIZE / WQ_PAGE_ADDR_SIZE) + +#define CMDQ_BLOCK_SIZE 512 +#define CMDQ_PAGE_SIZE 4096 + +#define CMDQ_WQ_MAX_PAGES (CMDQ_BLOCK_SIZE / WQ_PAGE_ADDR_SIZE) + +#define WQ_BASE_VADDR(wqs, wq) \ + ((void *)((wqs)->page_vaddr[(wq)->page_idx]) \ + + (wq)->block_idx * WQ_BLOCK_SIZE) + +#define WQ_BASE_PADDR(wqs, wq) \ + ((wqs)->page_paddr[(wq)->page_idx] \ + + (wq)->block_idx * WQ_BLOCK_SIZE) + +#define WQ_BASE_ADDR(wqs, wq) \ + ((void *)((wqs)->shadow_page_vaddr[(wq)->page_idx]) \ + + (wq)->block_idx * WQ_BLOCK_SIZE) + +#define CMDQ_BASE_VADDR(cmdq_pages, wq) \ + ((void *)((cmdq_pages)->page_vaddr) \ + + (wq)->block_idx * CMDQ_BLOCK_SIZE) + +#define CMDQ_BASE_PADDR(cmdq_pages, wq) \ + ((cmdq_pages)->page_paddr \ + + (wq)->block_idx * CMDQ_BLOCK_SIZE) + +#define CMDQ_BASE_ADDR(cmdq_pages, wq) \ + ((void *)((cmdq_pages)->shadow_page_vaddr) \ + + (wq)->block_idx * CMDQ_BLOCK_SIZE) + +#define WQE_PAGE_OFF(wq, idx) (((idx) & ((wq)->num_wqebbs_per_page - 1)) * \ + (wq)->wqebb_size) + +#define WQE_PAGE_NUM(wq, idx) (((idx) / ((wq)->num_wqebbs_per_page)) \ + & ((wq)->num_q_pages - 1)) + +#define WQ_PAGE_ADDR(wq, idx) \ + ((wq)->shadow_block_vaddr[WQE_PAGE_NUM(wq, idx)]) + +#define MASKED_WQE_IDX(wq, idx) ((idx) & (wq)->mask) + +#define WQE_IN_RANGE(wqe, start, end) \ + (((unsigned long)(wqe) >= (unsigned long)(start)) && \ + ((unsigned long)(wqe) < (unsigned long)(end))) + +#define WQE_SHADOW_PAGE(wq, wqe) \ + (((unsigned long)(wqe) - (unsigned long)(wq)->shadow_wqe) \ + / (wq)->max_wqe_size) + +/** + * queue_alloc_page - allocate page for Queue + * @hwif: HW interface for allocating DMA + * @vaddr: virtual address will be returned in this address + * @paddr: physical address will be returned in this address + * @shadow_vaddr: VM area will be return here for holding WQ page addresses + * @page_sz: page size of each WQ page + * + * Return 0 - Success, negative - Failure + **/ +static int queue_alloc_page(struct hinic_hwif *hwif, u64 **vaddr, u64 *paddr, + void ***shadow_vaddr, size_t page_sz) +{ + struct pci_dev *pdev = hwif->pdev; + dma_addr_t dma_addr; + + *vaddr = dma_zalloc_coherent(&pdev->dev, page_sz, &dma_addr, + GFP_KERNEL); + if (!*vaddr) { + dev_err(&pdev->dev, "Failed to allocate dma for wqs page\n"); + return -ENOMEM; + } + + *paddr = (u64)dma_addr; + + /* use vzalloc for big mem */ + *shadow_vaddr = vzalloc(page_sz); + if (!*shadow_vaddr) + goto err_shadow_vaddr; + + return 0; + +err_shadow_vaddr: + dma_free_coherent(&pdev->dev, page_sz, *vaddr, dma_addr); + return -ENOMEM; +} + +/** + * wqs_allocate_page - allocate page for WQ set + * @wqs: Work Queue Set + * @page_idx: the page index of the page will be allocated + * + * Return 0 - Success, negative - Failure + **/ +static int wqs_allocate_page(struct hinic_wqs *wqs, int page_idx) +{ + return queue_alloc_page(wqs->hwif, &wqs->page_vaddr[page_idx], + &wqs->page_paddr[page_idx], + &wqs->shadow_page_vaddr[page_idx], + WQS_PAGE_SIZE); +} + +/** + * wqs_free_page - free page of WQ set + * @wqs: Work Queue Set + * @page_idx: the page index of the page will be freed + **/ +static void wqs_free_page(struct hinic_wqs *wqs, int page_idx) +{ + struct hinic_hwif *hwif = wqs->hwif; + struct pci_dev *pdev = hwif->pdev; + + dma_free_coherent(&pdev->dev, WQS_PAGE_SIZE, + wqs->page_vaddr[page_idx], + (dma_addr_t)wqs->page_paddr[page_idx]); + vfree(wqs->shadow_page_vaddr[page_idx]); +} + +/** + * cmdq_allocate_page - allocate page for cmdq + * @cmdq_pages: the pages of the cmdq queue struct to hold the page + * + * Return 0 - Success, negative - Failure + **/ +static int cmdq_allocate_page(struct hinic_cmdq_pages *cmdq_pages) +{ + return queue_alloc_page(cmdq_pages->hwif, &cmdq_pages->page_vaddr, + &cmdq_pages->page_paddr, + &cmdq_pages->shadow_page_vaddr, + CMDQ_PAGE_SIZE); +} + +/** + * cmdq_free_page - free page from cmdq + * @cmdq_pages: the pages of the cmdq queue struct that hold the page + * + * Return 0 - Success, negative - Failure + **/ +static void cmdq_free_page(struct hinic_cmdq_pages *cmdq_pages) +{ + struct hinic_hwif *hwif = cmdq_pages->hwif; + struct pci_dev *pdev = hwif->pdev; + + dma_free_coherent(&pdev->dev, CMDQ_PAGE_SIZE, + cmdq_pages->page_vaddr, + (dma_addr_t)cmdq_pages->page_paddr); + vfree(cmdq_pages->shadow_page_vaddr); +} + +static int alloc_page_arrays(struct hinic_wqs *wqs) +{ + struct hinic_hwif *hwif = wqs->hwif; + struct pci_dev *pdev = hwif->pdev; + size_t size; + + size = wqs->num_pages * sizeof(*wqs->page_paddr); + wqs->page_paddr = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!wqs->page_paddr) + return -ENOMEM; + + size = wqs->num_pages * sizeof(*wqs->page_vaddr); + wqs->page_vaddr = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!wqs->page_vaddr) + goto err_page_vaddr; + + size = wqs->num_pages * sizeof(*wqs->shadow_page_vaddr); + wqs->shadow_page_vaddr = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!wqs->shadow_page_vaddr) + goto err_page_shadow_vaddr; + + return 0; + +err_page_shadow_vaddr: + devm_kfree(&pdev->dev, wqs->page_vaddr); + +err_page_vaddr: + devm_kfree(&pdev->dev, wqs->page_paddr); + return -ENOMEM; +} + +static void free_page_arrays(struct hinic_wqs *wqs) +{ + struct hinic_hwif *hwif = wqs->hwif; + struct pci_dev *pdev = hwif->pdev; + + devm_kfree(&pdev->dev, wqs->shadow_page_vaddr); + devm_kfree(&pdev->dev, wqs->page_vaddr); + devm_kfree(&pdev->dev, wqs->page_paddr); +} + +static int wqs_next_block(struct hinic_wqs *wqs, int *page_idx, + int *block_idx) +{ + int pos; + + down(&wqs->alloc_blocks_lock); + + wqs->num_free_blks--; + + if (wqs->num_free_blks < 0) { + wqs->num_free_blks++; + up(&wqs->alloc_blocks_lock); + return -ENOMEM; + } + + pos = wqs->alloc_blk_pos++; + pos &= WQS_MAX_NUM_BLOCKS - 1; + + *page_idx = wqs->free_blocks[pos].page_idx; + *block_idx = wqs->free_blocks[pos].block_idx; + + wqs->free_blocks[pos].page_idx = -1; + wqs->free_blocks[pos].block_idx = -1; + + up(&wqs->alloc_blocks_lock); + return 0; +} + +static void wqs_return_block(struct hinic_wqs *wqs, int page_idx, + int block_idx) +{ + int pos; + + down(&wqs->alloc_blocks_lock); + + pos = wqs->return_blk_pos++; + pos &= WQS_MAX_NUM_BLOCKS - 1; + + wqs->free_blocks[pos].page_idx = page_idx; + wqs->free_blocks[pos].block_idx = block_idx; + + wqs->num_free_blks++; + + up(&wqs->alloc_blocks_lock); +} + +static void init_wqs_blocks_arr(struct hinic_wqs *wqs) +{ + int page_idx, blk_idx, pos = 0; + + for (page_idx = 0; page_idx < wqs->num_pages; page_idx++) { + for (blk_idx = 0; blk_idx < WQS_BLOCKS_PER_PAGE; blk_idx++) { + wqs->free_blocks[pos].page_idx = page_idx; + wqs->free_blocks[pos].block_idx = blk_idx; + pos++; + } + } + + wqs->alloc_blk_pos = 0; + wqs->return_blk_pos = pos; + wqs->num_free_blks = pos; + + sema_init(&wqs->alloc_blocks_lock, 1); +} + +/** + * hinic_wqs_alloc - allocate Work Queues set + * @wqs: Work Queue Set + * @max_wqs: maximum wqs to allocate + * @hwif: HW interface for use for the allocation + * + * Return 0 - Success, negative - Failure + **/ +int hinic_wqs_alloc(struct hinic_wqs *wqs, int max_wqs, + struct hinic_hwif *hwif) +{ + struct pci_dev *pdev = hwif->pdev; + int err, i, page_idx; + + max_wqs = ALIGN(max_wqs, WQS_BLOCKS_PER_PAGE); + if (max_wqs > WQS_MAX_NUM_BLOCKS) { + dev_err(&pdev->dev, "Invalid max_wqs = %d\n", max_wqs); + return -EINVAL; + } + + wqs->hwif = hwif; + wqs->num_pages = max_wqs / WQS_BLOCKS_PER_PAGE; + + if (alloc_page_arrays(wqs)) { + dev_err(&pdev->dev, + "Failed to allocate mem for page addresses\n"); + return -ENOMEM; + } + + for (page_idx = 0; page_idx < wqs->num_pages; page_idx++) { + err = wqs_allocate_page(wqs, page_idx); + if (err) { + dev_err(&pdev->dev, "Failed wq page allocation\n"); + goto err_wq_allocate_page; + } + } + + wqs->free_blocks = devm_kzalloc(&pdev->dev, WQS_FREE_BLOCKS_SIZE(wqs), + GFP_KERNEL); + if (!wqs->free_blocks) { + err = -ENOMEM; + goto err_alloc_blocks; + } + + init_wqs_blocks_arr(wqs); + return 0; + +err_alloc_blocks: +err_wq_allocate_page: + for (i = 0; i < page_idx; i++) + wqs_free_page(wqs, i); + + free_page_arrays(wqs); + return err; +} + +/** + * hinic_wqs_free - free Work Queues set + * @wqs: Work Queue Set + **/ +void hinic_wqs_free(struct hinic_wqs *wqs) +{ + struct hinic_hwif *hwif = wqs->hwif; + struct pci_dev *pdev = hwif->pdev; + int page_idx; + + devm_kfree(&pdev->dev, wqs->free_blocks); + + for (page_idx = 0; page_idx < wqs->num_pages; page_idx++) + wqs_free_page(wqs, page_idx); + + free_page_arrays(wqs); +} + +/** + * alloc_wqes_shadow - allocate WQE shadows for WQ + * @wq: WQ to allocate shadows for + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_wqes_shadow(struct hinic_wq *wq) +{ + struct hinic_hwif *hwif = wq->hwif; + struct pci_dev *pdev = hwif->pdev; + size_t size; + + size = wq->num_q_pages * wq->max_wqe_size; + wq->shadow_wqe = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!wq->shadow_wqe) + return -ENOMEM; + + size = wq->num_q_pages * sizeof(wq->prod_idx); + wq->shadow_idx = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!wq->shadow_idx) + goto err_shadow_idx; + + return 0; + +err_shadow_idx: + devm_kfree(&pdev->dev, wq->shadow_wqe); + return -ENOMEM; +} + +/** + * free_wqes_shadow - free WQE shadows of WQ + * @wq: WQ to free shadows from + **/ +static void free_wqes_shadow(struct hinic_wq *wq) +{ + struct hinic_hwif *hwif = wq->hwif; + struct pci_dev *pdev = hwif->pdev; + + devm_kfree(&pdev->dev, wq->shadow_idx); + devm_kfree(&pdev->dev, wq->shadow_wqe); +} + +/** + * free_wq_pages - free pages of WQ + * @hwif: HW interface for releasing dma addresses + * @wq: WQ to free pages from + * @num_q_pages: number pages to free + **/ +static void free_wq_pages(struct hinic_wq *wq, struct hinic_hwif *hwif, + int num_q_pages) +{ + struct pci_dev *pdev = hwif->pdev; + int i; + + for (i = 0; i < num_q_pages; i++) { + void **vaddr = &wq->shadow_block_vaddr[i]; + u64 *paddr = &wq->block_vaddr[i]; + dma_addr_t dma_addr; + + dma_addr = (dma_addr_t)be64_to_cpu(*paddr); + dma_free_coherent(&pdev->dev, wq->wq_page_size, *vaddr, + dma_addr); + } + + free_wqes_shadow(wq); +} + +/** + * alloc_wq_pages - alloc pages for WQ + * @hwif: HW interface for allocating dma addresses + * @wq: WQ to allocate pages for + * @max_pages: maximum pages allowed + * + * Return 0 - Success, negative - Failure + **/ +static int alloc_wq_pages(struct hinic_wq *wq, struct hinic_hwif *hwif, + int max_pages) +{ + struct pci_dev *pdev = hwif->pdev; + int i, err, num_q_pages; + + num_q_pages = ALIGN(WQ_SIZE(wq), wq->wq_page_size) / wq->wq_page_size; + if (num_q_pages > max_pages) { + dev_err(&pdev->dev, "Number wq pages exceeds the limit\n"); + return -EINVAL; + } + + if (num_q_pages & (num_q_pages - 1)) { + dev_err(&pdev->dev, "Number wq pages must be power of 2\n"); + return -EINVAL; + } + + wq->num_q_pages = num_q_pages; + + err = alloc_wqes_shadow(wq); + if (err) { + dev_err(&pdev->dev, "Failed to allocate wqe shadow\n"); + return err; + } + + for (i = 0; i < num_q_pages; i++) { + void **vaddr = &wq->shadow_block_vaddr[i]; + u64 *paddr = &wq->block_vaddr[i]; + dma_addr_t dma_addr; + + *vaddr = dma_zalloc_coherent(&pdev->dev, wq->wq_page_size, + &dma_addr, GFP_KERNEL); + if (!*vaddr) { + dev_err(&pdev->dev, "Failed to allocate wq page\n"); + goto err_alloc_wq_pages; + } + + /* HW uses Big Endian Format */ + *paddr = cpu_to_be64(dma_addr); + } + + return 0; + +err_alloc_wq_pages: + free_wq_pages(wq, hwif, i); + return -ENOMEM; +} + +/** + * hinic_wq_allocate - Allocate the WQ resources from the WQS + * @wqs: WQ set from which to allocate the WQ resources + * @wq: WQ to allocate resources for it from the WQ set + * @wqebb_size: Work Queue Block Byte Size + * @wq_page_size: the page size in the Work Queue + * @q_depth: number of wqebbs in WQ + * @max_wqe_size: maximum WQE size that will be used in the WQ + * + * Return 0 - Success, negative - Failure + **/ +int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq, + u16 wqebb_size, u16 wq_page_size, u16 q_depth, + u16 max_wqe_size) +{ + struct hinic_hwif *hwif = wqs->hwif; + struct pci_dev *pdev = hwif->pdev; + u16 num_wqebbs_per_page; + int err; + + if (wqebb_size == 0) { + dev_err(&pdev->dev, "wqebb_size must be > 0\n"); + return -EINVAL; + } + + if (wq_page_size == 0) { + dev_err(&pdev->dev, "wq_page_size must be > 0\n"); + return -EINVAL; + } + + if (q_depth & (q_depth - 1)) { + dev_err(&pdev->dev, "WQ q_depth must be power of 2\n"); + return -EINVAL; + } + + num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size) / wqebb_size; + + if (num_wqebbs_per_page & (num_wqebbs_per_page - 1)) { + dev_err(&pdev->dev, "num wqebbs per page must be power of 2\n"); + return -EINVAL; + } + + wq->hwif = hwif; + + err = wqs_next_block(wqs, &wq->page_idx, &wq->block_idx); + if (err) { + dev_err(&pdev->dev, "Failed to get free wqs next block\n"); + return err; + } + + wq->wqebb_size = wqebb_size; + wq->wq_page_size = wq_page_size; + wq->q_depth = q_depth; + wq->max_wqe_size = max_wqe_size; + wq->num_wqebbs_per_page = num_wqebbs_per_page; + + wq->block_vaddr = WQ_BASE_VADDR(wqs, wq); + wq->shadow_block_vaddr = WQ_BASE_ADDR(wqs, wq); + wq->block_paddr = WQ_BASE_PADDR(wqs, wq); + + err = alloc_wq_pages(wq, wqs->hwif, WQ_MAX_PAGES); + if (err) { + dev_err(&pdev->dev, "Failed to allocate wq pages\n"); + goto err_alloc_wq_pages; + } + + atomic_set(&wq->cons_idx, 0); + atomic_set(&wq->prod_idx, 0); + atomic_set(&wq->delta, q_depth); + wq->mask = q_depth - 1; + + return 0; + +err_alloc_wq_pages: + wqs_return_block(wqs, wq->page_idx, wq->block_idx); + return err; +} + +/** + * hinic_wq_free - Free the WQ resources to the WQS + * @wqs: WQ set to free the WQ resources to it + * @wq: WQ to free its resources to the WQ set resources + **/ +void hinic_wq_free(struct hinic_wqs *wqs, struct hinic_wq *wq) +{ + free_wq_pages(wq, wqs->hwif, wq->num_q_pages); + + wqs_return_block(wqs, wq->page_idx, wq->block_idx); +} + +/** + * hinic_wqs_cmdq_alloc - Allocate wqs for cmdqs + * @cmdq_pages: will hold the pages of the cmdq + * @wq: returned wqs + * @hwif: HW interface + * @cmdq_blocks: number of cmdq blocks/wq to allocate + * @wqebb_size: Work Queue Block Byte Size + * @wq_page_size: the page size in the Work Queue + * @q_depth: number of wqebbs in WQ + * @max_wqe_size: maximum WQE size that will be used in the WQ + * + * Return 0 - Success, negative - Failure + **/ +int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages, + struct hinic_wq *wq, struct hinic_hwif *hwif, + int cmdq_blocks, u16 wqebb_size, u16 wq_page_size, + u16 q_depth, u16 max_wqe_size) +{ + struct pci_dev *pdev = hwif->pdev; + u16 num_wqebbs_per_page; + int i, j, err = -ENOMEM; + + if (wqebb_size == 0) { + dev_err(&pdev->dev, "wqebb_size must be > 0\n"); + return -EINVAL; + } + + if (wq_page_size == 0) { + dev_err(&pdev->dev, "wq_page_size must be > 0\n"); + return -EINVAL; + } + + if (q_depth & (q_depth - 1)) { + dev_err(&pdev->dev, "WQ q_depth must be power of 2\n"); + return -EINVAL; + } + + num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size) / wqebb_size; + + if (num_wqebbs_per_page & (num_wqebbs_per_page - 1)) { + dev_err(&pdev->dev, "num wqebbs per page must be power of 2\n"); + return -EINVAL; + } + + cmdq_pages->hwif = hwif; + + err = cmdq_allocate_page(cmdq_pages); + if (err) { + dev_err(&pdev->dev, "Failed to allocate CMDQ page\n"); + return err; + } + + for (i = 0; i < cmdq_blocks; i++) { + wq[i].hwif = hwif; + wq[i].page_idx = 0; + wq[i].block_idx = i; + + wq[i].wqebb_size = wqebb_size; + wq[i].wq_page_size = wq_page_size; + wq[i].q_depth = q_depth; + wq[i].max_wqe_size = max_wqe_size; + wq[i].num_wqebbs_per_page = num_wqebbs_per_page; + + wq[i].block_vaddr = CMDQ_BASE_VADDR(cmdq_pages, &wq[i]); + wq[i].shadow_block_vaddr = CMDQ_BASE_ADDR(cmdq_pages, &wq[i]); + wq[i].block_paddr = CMDQ_BASE_PADDR(cmdq_pages, &wq[i]); + + err = alloc_wq_pages(&wq[i], cmdq_pages->hwif, + CMDQ_WQ_MAX_PAGES); + if (err) { + dev_err(&pdev->dev, "Failed to alloc CMDQ blocks\n"); + goto err_cmdq_block; + } + + atomic_set(&wq[i].cons_idx, 0); + atomic_set(&wq[i].prod_idx, 0); + atomic_set(&wq[i].delta, q_depth); + wq[i].mask = q_depth - 1; + } + + return 0; + +err_cmdq_block: + for (j = 0; j < i; j++) + free_wq_pages(&wq[j], cmdq_pages->hwif, wq[j].num_q_pages); + + cmdq_free_page(cmdq_pages); + return err; +} + +/** + * hinic_wqs_cmdq_free - Free wqs from cmdqs + * @cmdq_pages: hold the pages of the cmdq + * @wq: wqs to free + * @cmdq_blocks: number of wqs to free + **/ +void hinic_wqs_cmdq_free(struct hinic_cmdq_pages *cmdq_pages, + struct hinic_wq *wq, int cmdq_blocks) +{ + int i; + + for (i = 0; i < cmdq_blocks; i++) + free_wq_pages(&wq[i], cmdq_pages->hwif, wq[i].num_q_pages); + + cmdq_free_page(cmdq_pages); +} + +static void copy_wqe_to_shadow(struct hinic_wq *wq, void *shadow_addr, + int num_wqebbs, u16 idx) +{ + void *wqebb_addr; + int i; + + for (i = 0; i < num_wqebbs; i++, idx++) { + idx = MASKED_WQE_IDX(wq, idx); + wqebb_addr = WQ_PAGE_ADDR(wq, idx) + + WQE_PAGE_OFF(wq, idx); + + memcpy(shadow_addr, wqebb_addr, wq->wqebb_size); + + shadow_addr += wq->wqebb_size; + } +} + +static void copy_wqe_from_shadow(struct hinic_wq *wq, void *shadow_addr, + int num_wqebbs, u16 idx) +{ + void *wqebb_addr; + int i; + + for (i = 0; i < num_wqebbs; i++, idx++) { + idx = MASKED_WQE_IDX(wq, idx); + wqebb_addr = WQ_PAGE_ADDR(wq, idx) + + WQE_PAGE_OFF(wq, idx); + + memcpy(wqebb_addr, shadow_addr, wq->wqebb_size); + shadow_addr += wq->wqebb_size; + } +} + +/** + * hinic_get_wqe - get wqe ptr in the current pi and update the pi + * @wq: wq to get wqe from + * @wqe_size: wqe size + * @prod_idx: returned pi + * + * Return wqe pointer + **/ +struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size, + u16 *prod_idx) +{ + int curr_pg, end_pg, num_wqebbs; + u16 curr_prod_idx, end_prod_idx; + + *prod_idx = MASKED_WQE_IDX(wq, atomic_read(&wq->prod_idx)); + + num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size; + + if (atomic_sub_return(num_wqebbs, &wq->delta) <= 0) { + atomic_add(num_wqebbs, &wq->delta); + return ERR_PTR(-EBUSY); + } + + end_prod_idx = atomic_add_return(num_wqebbs, &wq->prod_idx); + + end_prod_idx = MASKED_WQE_IDX(wq, end_prod_idx); + curr_prod_idx = end_prod_idx - num_wqebbs; + curr_prod_idx = MASKED_WQE_IDX(wq, curr_prod_idx); + + /* end prod index points to the next wqebb, therefore minus 1 */ + end_prod_idx = MASKED_WQE_IDX(wq, end_prod_idx - 1); + + curr_pg = WQE_PAGE_NUM(wq, curr_prod_idx); + end_pg = WQE_PAGE_NUM(wq, end_prod_idx); + + *prod_idx = curr_prod_idx; + + if (curr_pg != end_pg) { + void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; + + copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *prod_idx); + + wq->shadow_idx[curr_pg] = *prod_idx; + return shadow_addr; + } + + return WQ_PAGE_ADDR(wq, *prod_idx) + WQE_PAGE_OFF(wq, *prod_idx); +} + +/** + * hinic_put_wqe - return the wqe place to use for a new wqe + * @wq: wq to return wqe + * @wqe_size: wqe size + **/ +void hinic_put_wqe(struct hinic_wq *wq, unsigned int wqe_size) +{ + int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size; + + atomic_add(num_wqebbs, &wq->cons_idx); + + atomic_add(num_wqebbs, &wq->delta); +} + +/** + * hinic_read_wqe - read wqe ptr in the current ci + * @wq: wq to get read from + * @wqe_size: wqe size + * @cons_idx: returned ci + * + * Return wqe pointer + **/ +struct hinic_hw_wqe *hinic_read_wqe(struct hinic_wq *wq, unsigned int wqe_size, + u16 *cons_idx) +{ + int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size; + u16 curr_cons_idx, end_cons_idx; + int curr_pg, end_pg; + + if ((atomic_read(&wq->delta) + num_wqebbs) > wq->q_depth) + return ERR_PTR(-EBUSY); + + curr_cons_idx = atomic_read(&wq->cons_idx); + + curr_cons_idx = MASKED_WQE_IDX(wq, curr_cons_idx); + end_cons_idx = MASKED_WQE_IDX(wq, curr_cons_idx + num_wqebbs - 1); + + curr_pg = WQE_PAGE_NUM(wq, curr_cons_idx); + end_pg = WQE_PAGE_NUM(wq, end_cons_idx); + + *cons_idx = curr_cons_idx; + + if (curr_pg != end_pg) { + void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; + + copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *cons_idx); + return shadow_addr; + } + + return WQ_PAGE_ADDR(wq, *cons_idx) + WQE_PAGE_OFF(wq, *cons_idx); +} + +/** + * hinic_read_wqe_direct - read wqe directly from ci position + * @wq: wq + * @cons_idx: ci position + * + * Return wqe + **/ +struct hinic_hw_wqe *hinic_read_wqe_direct(struct hinic_wq *wq, u16 cons_idx) +{ + return WQ_PAGE_ADDR(wq, cons_idx) + WQE_PAGE_OFF(wq, cons_idx); +} + +/** + * wqe_shadow - check if a wqe is shadow + * @wq: wq of the wqe + * @wqe: the wqe for shadow checking + * + * Return true - shadow, false - Not shadow + **/ +static inline bool wqe_shadow(struct hinic_wq *wq, struct hinic_hw_wqe *wqe) +{ + size_t wqe_shadow_size = wq->num_q_pages * wq->max_wqe_size; + + return WQE_IN_RANGE(wqe, wq->shadow_wqe, + &wq->shadow_wqe[wqe_shadow_size]); +} + +/** + * hinic_write_wqe - write the wqe to the wq + * @wq: wq to write wqe to + * @wqe: wqe to write + * @wqe_size: wqe size + **/ +void hinic_write_wqe(struct hinic_wq *wq, struct hinic_hw_wqe *wqe, + unsigned int wqe_size) +{ + int curr_pg, num_wqebbs; + void *shadow_addr; + u16 prod_idx; + + if (wqe_shadow(wq, wqe)) { + curr_pg = WQE_SHADOW_PAGE(wq, wqe); + + prod_idx = wq->shadow_idx[curr_pg]; + num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size; + shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size]; + + copy_wqe_from_shadow(wq, shadow_addr, num_wqebbs, prod_idx); + } +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h new file mode 100644 index 000000000000..9c030a0f035e --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h @@ -0,0 +1,117 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_WQ_H +#define HINIC_HW_WQ_H + +#include <linux/types.h> +#include <linux/semaphore.h> +#include <linux/atomic.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_wqe.h" + +struct hinic_free_block { + int page_idx; + int block_idx; +}; + +struct hinic_wq { + struct hinic_hwif *hwif; + + int page_idx; + int block_idx; + + u16 wqebb_size; + u16 wq_page_size; + u16 q_depth; + u16 max_wqe_size; + u16 num_wqebbs_per_page; + + /* The addresses are 64 bit in the HW */ + u64 block_paddr; + void **shadow_block_vaddr; + u64 *block_vaddr; + + int num_q_pages; + u8 *shadow_wqe; + u16 *shadow_idx; + + atomic_t cons_idx; + atomic_t prod_idx; + atomic_t delta; + u16 mask; +}; + +struct hinic_wqs { + struct hinic_hwif *hwif; + int num_pages; + + /* The addresses are 64 bit in the HW */ + u64 *page_paddr; + u64 **page_vaddr; + void ***shadow_page_vaddr; + + struct hinic_free_block *free_blocks; + int alloc_blk_pos; + int return_blk_pos; + int num_free_blks; + + /* Lock for getting a free block from the WQ set */ + struct semaphore alloc_blocks_lock; +}; + +struct hinic_cmdq_pages { + /* The addresses are 64 bit in the HW */ + u64 page_paddr; + u64 *page_vaddr; + void **shadow_page_vaddr; + + struct hinic_hwif *hwif; +}; + +int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages, + struct hinic_wq *wq, struct hinic_hwif *hwif, + int cmdq_blocks, u16 wqebb_size, u16 wq_page_size, + u16 q_depth, u16 max_wqe_size); + +void hinic_wqs_cmdq_free(struct hinic_cmdq_pages *cmdq_pages, + struct hinic_wq *wq, int cmdq_blocks); + +int hinic_wqs_alloc(struct hinic_wqs *wqs, int num_wqs, + struct hinic_hwif *hwif); + +void hinic_wqs_free(struct hinic_wqs *wqs); + +int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq, + u16 wqebb_size, u16 wq_page_size, u16 q_depth, + u16 max_wqe_size); + +void hinic_wq_free(struct hinic_wqs *wqs, struct hinic_wq *wq); + +struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size, + u16 *prod_idx); + +void hinic_put_wqe(struct hinic_wq *wq, unsigned int wqe_size); + +struct hinic_hw_wqe *hinic_read_wqe(struct hinic_wq *wq, unsigned int wqe_size, + u16 *cons_idx); + +struct hinic_hw_wqe *hinic_read_wqe_direct(struct hinic_wq *wq, u16 cons_idx); + +void hinic_write_wqe(struct hinic_wq *wq, struct hinic_hw_wqe *wqe, + unsigned int wqe_size); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h new file mode 100644 index 000000000000..bc73485483c5 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h @@ -0,0 +1,368 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_HW_WQE_H +#define HINIC_HW_WQE_H + +#include "hinic_common.h" + +#define HINIC_CMDQ_CTRL_PI_SHIFT 0 +#define HINIC_CMDQ_CTRL_CMD_SHIFT 16 +#define HINIC_CMDQ_CTRL_MOD_SHIFT 24 +#define HINIC_CMDQ_CTRL_ACK_TYPE_SHIFT 29 +#define HINIC_CMDQ_CTRL_HW_BUSY_BIT_SHIFT 31 + +#define HINIC_CMDQ_CTRL_PI_MASK 0xFFFF +#define HINIC_CMDQ_CTRL_CMD_MASK 0xFF +#define HINIC_CMDQ_CTRL_MOD_MASK 0x1F +#define HINIC_CMDQ_CTRL_ACK_TYPE_MASK 0x3 +#define HINIC_CMDQ_CTRL_HW_BUSY_BIT_MASK 0x1 + +#define HINIC_CMDQ_CTRL_SET(val, member) \ + (((u32)(val) & HINIC_CMDQ_CTRL_##member##_MASK) \ + << HINIC_CMDQ_CTRL_##member##_SHIFT) + +#define HINIC_CMDQ_CTRL_GET(val, member) \ + (((val) >> HINIC_CMDQ_CTRL_##member##_SHIFT) \ + & HINIC_CMDQ_CTRL_##member##_MASK) + +#define HINIC_CMDQ_WQE_HEADER_BUFDESC_LEN_SHIFT 0 +#define HINIC_CMDQ_WQE_HEADER_COMPLETE_FMT_SHIFT 15 +#define HINIC_CMDQ_WQE_HEADER_DATA_FMT_SHIFT 22 +#define HINIC_CMDQ_WQE_HEADER_COMPLETE_REQ_SHIFT 23 +#define HINIC_CMDQ_WQE_HEADER_COMPLETE_SECT_LEN_SHIFT 27 +#define HINIC_CMDQ_WQE_HEADER_CTRL_LEN_SHIFT 29 +#define HINIC_CMDQ_WQE_HEADER_TOGGLED_WRAPPED_SHIFT 31 + +#define HINIC_CMDQ_WQE_HEADER_BUFDESC_LEN_MASK 0xFF +#define HINIC_CMDQ_WQE_HEADER_COMPLETE_FMT_MASK 0x1 +#define HINIC_CMDQ_WQE_HEADER_DATA_FMT_MASK 0x1 +#define HINIC_CMDQ_WQE_HEADER_COMPLETE_REQ_MASK 0x1 +#define HINIC_CMDQ_WQE_HEADER_COMPLETE_SECT_LEN_MASK 0x3 +#define HINIC_CMDQ_WQE_HEADER_CTRL_LEN_MASK 0x3 +#define HINIC_CMDQ_WQE_HEADER_TOGGLED_WRAPPED_MASK 0x1 + +#define HINIC_CMDQ_WQE_HEADER_SET(val, member) \ + (((u32)(val) & HINIC_CMDQ_WQE_HEADER_##member##_MASK) \ + << HINIC_CMDQ_WQE_HEADER_##member##_SHIFT) + +#define HINIC_CMDQ_WQE_HEADER_GET(val, member) \ + (((val) >> HINIC_CMDQ_WQE_HEADER_##member##_SHIFT) \ + & HINIC_CMDQ_WQE_HEADER_##member##_MASK) + +#define HINIC_SQ_CTRL_BUFDESC_SECT_LEN_SHIFT 0 +#define HINIC_SQ_CTRL_TASKSECT_LEN_SHIFT 16 +#define HINIC_SQ_CTRL_DATA_FORMAT_SHIFT 22 +#define HINIC_SQ_CTRL_LEN_SHIFT 29 + +#define HINIC_SQ_CTRL_BUFDESC_SECT_LEN_MASK 0xFF +#define HINIC_SQ_CTRL_TASKSECT_LEN_MASK 0x1F +#define HINIC_SQ_CTRL_DATA_FORMAT_MASK 0x1 +#define HINIC_SQ_CTRL_LEN_MASK 0x3 + +#define HINIC_SQ_CTRL_QUEUE_INFO_MSS_SHIFT 13 + +#define HINIC_SQ_CTRL_QUEUE_INFO_MSS_MASK 0x3FFF + +#define HINIC_SQ_CTRL_SET(val, member) \ + (((u32)(val) & HINIC_SQ_CTRL_##member##_MASK) \ + << HINIC_SQ_CTRL_##member##_SHIFT) + +#define HINIC_SQ_CTRL_GET(val, member) \ + (((val) >> HINIC_SQ_CTRL_##member##_SHIFT) \ + & HINIC_SQ_CTRL_##member##_MASK) + +#define HINIC_SQ_TASK_INFO0_L2HDR_LEN_SHIFT 0 +#define HINIC_SQ_TASK_INFO0_L4_OFFLOAD_SHIFT 8 +#define HINIC_SQ_TASK_INFO0_INNER_L3TYPE_SHIFT 10 +#define HINIC_SQ_TASK_INFO0_VLAN_OFFLOAD_SHIFT 12 +#define HINIC_SQ_TASK_INFO0_PARSE_FLAG_SHIFT 13 +/* 1 bit reserved */ +#define HINIC_SQ_TASK_INFO0_TSO_FLAG_SHIFT 15 +#define HINIC_SQ_TASK_INFO0_VLAN_TAG_SHIFT 16 + +#define HINIC_SQ_TASK_INFO0_L2HDR_LEN_MASK 0xFF +#define HINIC_SQ_TASK_INFO0_L4_OFFLOAD_MASK 0x3 +#define HINIC_SQ_TASK_INFO0_INNER_L3TYPE_MASK 0x3 +#define HINIC_SQ_TASK_INFO0_VLAN_OFFLOAD_MASK 0x1 +#define HINIC_SQ_TASK_INFO0_PARSE_FLAG_MASK 0x1 +/* 1 bit reserved */ +#define HINIC_SQ_TASK_INFO0_TSO_FLAG_MASK 0x1 +#define HINIC_SQ_TASK_INFO0_VLAN_TAG_MASK 0xFFFF + +#define HINIC_SQ_TASK_INFO0_SET(val, member) \ + (((u32)(val) & HINIC_SQ_TASK_INFO0_##member##_MASK) << \ + HINIC_SQ_TASK_INFO0_##member##_SHIFT) + +/* 8 bits reserved */ +#define HINIC_SQ_TASK_INFO1_MEDIA_TYPE_SHIFT 8 +#define HINIC_SQ_TASK_INFO1_INNER_L4_LEN_SHIFT 16 +#define HINIC_SQ_TASK_INFO1_INNER_L3_LEN_SHIFT 24 + +/* 8 bits reserved */ +#define HINIC_SQ_TASK_INFO1_MEDIA_TYPE_MASK 0xFF +#define HINIC_SQ_TASK_INFO1_INNER_L4_LEN_MASK 0xFF +#define HINIC_SQ_TASK_INFO1_INNER_L3_LEN_MASK 0xFF + +#define HINIC_SQ_TASK_INFO1_SET(val, member) \ + (((u32)(val) & HINIC_SQ_TASK_INFO1_##member##_MASK) << \ + HINIC_SQ_TASK_INFO1_##member##_SHIFT) + +#define HINIC_SQ_TASK_INFO2_TUNNEL_L4_LEN_SHIFT 0 +#define HINIC_SQ_TASK_INFO2_OUTER_L3_LEN_SHIFT 12 +#define HINIC_SQ_TASK_INFO2_TUNNEL_L4TYPE_SHIFT 19 +/* 1 bit reserved */ +#define HINIC_SQ_TASK_INFO2_OUTER_L3TYPE_SHIFT 22 +/* 8 bits reserved */ + +#define HINIC_SQ_TASK_INFO2_TUNNEL_L4_LEN_MASK 0xFFF +#define HINIC_SQ_TASK_INFO2_OUTER_L3_LEN_MASK 0x7F +#define HINIC_SQ_TASK_INFO2_TUNNEL_L4TYPE_MASK 0x3 +/* 1 bit reserved */ +#define HINIC_SQ_TASK_INFO2_OUTER_L3TYPE_MASK 0x3 +/* 8 bits reserved */ + +#define HINIC_SQ_TASK_INFO2_SET(val, member) \ + (((u32)(val) & HINIC_SQ_TASK_INFO2_##member##_MASK) << \ + HINIC_SQ_TASK_INFO2_##member##_SHIFT) + +/* 31 bits reserved */ +#define HINIC_SQ_TASK_INFO4_L2TYPE_SHIFT 31 + +/* 31 bits reserved */ +#define HINIC_SQ_TASK_INFO4_L2TYPE_MASK 0x1 + +#define HINIC_SQ_TASK_INFO4_SET(val, member) \ + (((u32)(val) & HINIC_SQ_TASK_INFO4_##member##_MASK) << \ + HINIC_SQ_TASK_INFO4_##member##_SHIFT) + +#define HINIC_RQ_CQE_STATUS_RXDONE_SHIFT 31 + +#define HINIC_RQ_CQE_STATUS_RXDONE_MASK 0x1 + +#define HINIC_RQ_CQE_STATUS_GET(val, member) \ + (((val) >> HINIC_RQ_CQE_STATUS_##member##_SHIFT) & \ + HINIC_RQ_CQE_STATUS_##member##_MASK) + +#define HINIC_RQ_CQE_STATUS_CLEAR(val, member) \ + ((val) & (~(HINIC_RQ_CQE_STATUS_##member##_MASK << \ + HINIC_RQ_CQE_STATUS_##member##_SHIFT))) + +#define HINIC_RQ_CQE_SGE_LEN_SHIFT 16 + +#define HINIC_RQ_CQE_SGE_LEN_MASK 0xFFFF + +#define HINIC_RQ_CQE_SGE_GET(val, member) \ + (((val) >> HINIC_RQ_CQE_SGE_##member##_SHIFT) & \ + HINIC_RQ_CQE_SGE_##member##_MASK) + +#define HINIC_RQ_CTRL_BUFDESC_SECT_LEN_SHIFT 0 +#define HINIC_RQ_CTRL_COMPLETE_FORMAT_SHIFT 15 +#define HINIC_RQ_CTRL_COMPLETE_LEN_SHIFT 27 +#define HINIC_RQ_CTRL_LEN_SHIFT 29 + +#define HINIC_RQ_CTRL_BUFDESC_SECT_LEN_MASK 0xFF +#define HINIC_RQ_CTRL_COMPLETE_FORMAT_MASK 0x1 +#define HINIC_RQ_CTRL_COMPLETE_LEN_MASK 0x3 +#define HINIC_RQ_CTRL_LEN_MASK 0x3 + +#define HINIC_RQ_CTRL_SET(val, member) \ + (((u32)(val) & HINIC_RQ_CTRL_##member##_MASK) << \ + HINIC_RQ_CTRL_##member##_SHIFT) + +#define HINIC_SQ_WQE_SIZE(nr_sges) \ + (sizeof(struct hinic_sq_ctrl) + \ + sizeof(struct hinic_sq_task) + \ + (nr_sges) * sizeof(struct hinic_sq_bufdesc)) + +#define HINIC_SCMD_DATA_LEN 16 + +#define HINIC_MAX_SQ_BUFDESCS 17 + +#define HINIC_SQ_WQE_MAX_SIZE 320 +#define HINIC_RQ_WQE_SIZE 32 + +enum hinic_l4offload_type { + HINIC_L4_OFF_DISABLE = 0, + HINIC_TCP_OFFLOAD_ENABLE = 1, + HINIC_SCTP_OFFLOAD_ENABLE = 2, + HINIC_UDP_OFFLOAD_ENABLE = 3, +}; + +enum hinic_vlan_offload { + HINIC_VLAN_OFF_DISABLE = 0, + HINIC_VLAN_OFF_ENABLE = 1, +}; + +enum hinic_pkt_parsed { + HINIC_PKT_NOT_PARSED = 0, + HINIC_PKT_PARSED = 1, +}; + +enum hinic_outer_l3type { + HINIC_OUTER_L3TYPE_UNKNOWN = 0, + HINIC_OUTER_L3TYPE_IPV6 = 1, + HINIC_OUTER_L3TYPE_IPV4_NO_CHKSUM = 2, + HINIC_OUTER_L3TYPE_IPV4_CHKSUM = 3, +}; + +enum hinic_media_type { + HINIC_MEDIA_UNKNOWN = 0, +}; + +enum hinic_l2type { + HINIC_L2TYPE_ETH = 0, +}; + +enum hinc_tunnel_l4type { + HINIC_TUNNEL_L4TYPE_UNKNOWN = 0, +}; + +struct hinic_cmdq_header { + u32 header_info; + u32 saved_data; +}; + +struct hinic_status { + u32 status_info; +}; + +struct hinic_ctrl { + u32 ctrl_info; +}; + +struct hinic_sge_resp { + struct hinic_sge sge; + u32 rsvd; +}; + +struct hinic_cmdq_completion { + /* HW Format */ + union { + struct hinic_sge_resp sge_resp; + u64 direct_resp; + }; +}; + +struct hinic_scmd_bufdesc { + u32 buf_len; + u32 rsvd; + u8 data[HINIC_SCMD_DATA_LEN]; +}; + +struct hinic_lcmd_bufdesc { + struct hinic_sge sge; + u32 rsvd1; + u64 rsvd2; + u64 rsvd3; +}; + +struct hinic_cmdq_wqe_scmd { + struct hinic_cmdq_header header; + u64 rsvd; + struct hinic_status status; + struct hinic_ctrl ctrl; + struct hinic_cmdq_completion completion; + struct hinic_scmd_bufdesc buf_desc; +}; + +struct hinic_cmdq_wqe_lcmd { + struct hinic_cmdq_header header; + struct hinic_status status; + struct hinic_ctrl ctrl; + struct hinic_cmdq_completion completion; + struct hinic_lcmd_bufdesc buf_desc; +}; + +struct hinic_cmdq_direct_wqe { + struct hinic_cmdq_wqe_scmd wqe_scmd; +}; + +struct hinic_cmdq_wqe { + /* HW Format */ + union { + struct hinic_cmdq_direct_wqe direct_wqe; + struct hinic_cmdq_wqe_lcmd wqe_lcmd; + }; +}; + +struct hinic_sq_ctrl { + u32 ctrl_info; + u32 queue_info; +}; + +struct hinic_sq_task { + u32 pkt_info0; + u32 pkt_info1; + u32 pkt_info2; + u32 ufo_v6_identify; + u32 pkt_info4; + u32 zero_pad; +}; + +struct hinic_sq_bufdesc { + struct hinic_sge sge; + u32 rsvd; +}; + +struct hinic_sq_wqe { + struct hinic_sq_ctrl ctrl; + struct hinic_sq_task task; + struct hinic_sq_bufdesc buf_descs[HINIC_MAX_SQ_BUFDESCS]; +}; + +struct hinic_rq_cqe { + u32 status; + u32 len; + + u32 rsvd2; + u32 rsvd3; + u32 rsvd4; + u32 rsvd5; + u32 rsvd6; + u32 rsvd7; +}; + +struct hinic_rq_ctrl { + u32 ctrl_info; +}; + +struct hinic_rq_cqe_sect { + struct hinic_sge sge; + u32 rsvd; +}; + +struct hinic_rq_bufdesc { + u32 hi_addr; + u32 lo_addr; +}; + +struct hinic_rq_wqe { + struct hinic_rq_ctrl ctrl; + u32 rsvd; + struct hinic_rq_cqe_sect cqe_sect; + struct hinic_rq_bufdesc buf_desc; +}; + +struct hinic_hw_wqe { + /* HW Format */ + union { + struct hinic_cmdq_wqe cmdq_wqe; + struct hinic_sq_wqe sq_wqe; + struct hinic_rq_wqe rq_wqe; + }; +}; + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c new file mode 100644 index 000000000000..eb53bd93065e --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -0,0 +1,1112 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/etherdevice.h> +#include <linux/netdevice.h> +#include <linux/slab.h> +#include <linux/if_vlan.h> +#include <linux/semaphore.h> +#include <linux/workqueue.h> +#include <net/ip.h> +#include <linux/bitops.h> +#include <linux/bitmap.h> +#include <linux/delay.h> +#include <linux/err.h> + +#include "hinic_hw_qp.h" +#include "hinic_hw_dev.h" +#include "hinic_port.h" +#include "hinic_tx.h" +#include "hinic_rx.h" +#include "hinic_dev.h" + +MODULE_AUTHOR("Huawei Technologies CO., Ltd"); +MODULE_DESCRIPTION("Huawei Intelligent NIC driver"); +MODULE_LICENSE("GPL"); + +static unsigned int tx_weight = 64; +module_param(tx_weight, uint, 0644); +MODULE_PARM_DESC(tx_weight, "Number Tx packets for NAPI budget (default=64)"); + +static unsigned int rx_weight = 64; +module_param(rx_weight, uint, 0644); +MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)"); + +#define PCI_DEVICE_ID_HI1822_PF 0x1822 + +#define HINIC_WQ_NAME "hinic_dev" + +#define MSG_ENABLE_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \ + NETIF_MSG_IFUP | \ + NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR) + +#define VLAN_BITMAP_SIZE(nic_dev) (ALIGN(VLAN_N_VID, 8) / 8) + +#define work_to_rx_mode_work(work) \ + container_of(work, struct hinic_rx_mode_work, work) + +#define rx_mode_work_to_nic_dev(rx_mode_work) \ + container_of(rx_mode_work, struct hinic_dev, rx_mode_work) + +static int change_mac_addr(struct net_device *netdev, const u8 *addr); + +static void set_link_speed(struct ethtool_link_ksettings *link_ksettings, + enum hinic_speed speed) +{ + switch (speed) { + case HINIC_SPEED_10MB_LINK: + link_ksettings->base.speed = SPEED_10; + break; + + case HINIC_SPEED_100MB_LINK: + link_ksettings->base.speed = SPEED_100; + break; + + case HINIC_SPEED_1000MB_LINK: + link_ksettings->base.speed = SPEED_1000; + break; + + case HINIC_SPEED_10GB_LINK: + link_ksettings->base.speed = SPEED_10000; + break; + + case HINIC_SPEED_25GB_LINK: + link_ksettings->base.speed = SPEED_25000; + break; + + case HINIC_SPEED_40GB_LINK: + link_ksettings->base.speed = SPEED_40000; + break; + + case HINIC_SPEED_100GB_LINK: + link_ksettings->base.speed = SPEED_100000; + break; + + default: + link_ksettings->base.speed = SPEED_UNKNOWN; + break; + } +} + +static int hinic_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings + *link_ksettings) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + enum hinic_port_link_state link_state; + struct hinic_port_cap port_cap; + int err; + + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + ethtool_link_ksettings_add_link_mode(link_ksettings, supported, + Autoneg); + + link_ksettings->base.speed = SPEED_UNKNOWN; + link_ksettings->base.autoneg = AUTONEG_DISABLE; + link_ksettings->base.duplex = DUPLEX_UNKNOWN; + + err = hinic_port_get_cap(nic_dev, &port_cap); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to get port capabilities\n"); + return err; + } + + err = hinic_port_link_state(nic_dev, &link_state); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to get port link state\n"); + return err; + } + + if (link_state != HINIC_LINK_STATE_UP) { + netif_info(nic_dev, drv, netdev, "No link\n"); + return err; + } + + set_link_speed(link_ksettings, port_cap.speed); + + if (!!(port_cap.autoneg_cap & HINIC_AUTONEG_SUPPORTED)) + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, Autoneg); + + if (port_cap.autoneg_state == HINIC_AUTONEG_ACTIVE) + link_ksettings->base.autoneg = AUTONEG_ENABLE; + + link_ksettings->base.duplex = (port_cap.duplex == HINIC_DUPLEX_FULL) ? + DUPLEX_FULL : DUPLEX_HALF; + return 0; +} + +static void hinic_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *info) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + + strlcpy(info->driver, HINIC_DRV_NAME, sizeof(info->driver)); + strlcpy(info->bus_info, pci_name(hwif->pdev), sizeof(info->bus_info)); +} + +static void hinic_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + ring->rx_max_pending = HINIC_RQ_DEPTH; + ring->tx_max_pending = HINIC_SQ_DEPTH; + ring->rx_pending = HINIC_RQ_DEPTH; + ring->tx_pending = HINIC_SQ_DEPTH; +} + +static void hinic_get_channels(struct net_device *netdev, + struct ethtool_channels *channels) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_hwdev *hwdev = nic_dev->hwdev; + + channels->max_rx = hwdev->nic_cap.max_qps; + channels->max_tx = hwdev->nic_cap.max_qps; + channels->max_other = 0; + channels->max_combined = 0; + channels->rx_count = hinic_hwdev_num_qps(hwdev); + channels->tx_count = hinic_hwdev_num_qps(hwdev); + channels->other_count = 0; + channels->combined_count = 0; +} + +static const struct ethtool_ops hinic_ethtool_ops = { + .get_link_ksettings = hinic_get_link_ksettings, + .get_drvinfo = hinic_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_ringparam = hinic_get_ringparam, + .get_channels = hinic_get_channels, +}; + +static void update_rx_stats(struct hinic_dev *nic_dev, struct hinic_rxq *rxq) +{ + struct hinic_rxq_stats *nic_rx_stats = &nic_dev->rx_stats; + struct hinic_rxq_stats rx_stats; + + u64_stats_init(&rx_stats.syncp); + + hinic_rxq_get_stats(rxq, &rx_stats); + + u64_stats_update_begin(&nic_rx_stats->syncp); + nic_rx_stats->bytes += rx_stats.bytes; + nic_rx_stats->pkts += rx_stats.pkts; + u64_stats_update_end(&nic_rx_stats->syncp); + + hinic_rxq_clean_stats(rxq); +} + +static void update_tx_stats(struct hinic_dev *nic_dev, struct hinic_txq *txq) +{ + struct hinic_txq_stats *nic_tx_stats = &nic_dev->tx_stats; + struct hinic_txq_stats tx_stats; + + u64_stats_init(&tx_stats.syncp); + + hinic_txq_get_stats(txq, &tx_stats); + + u64_stats_update_begin(&nic_tx_stats->syncp); + nic_tx_stats->bytes += tx_stats.bytes; + nic_tx_stats->pkts += tx_stats.pkts; + nic_tx_stats->tx_busy += tx_stats.tx_busy; + nic_tx_stats->tx_wake += tx_stats.tx_wake; + nic_tx_stats->tx_dropped += tx_stats.tx_dropped; + u64_stats_update_end(&nic_tx_stats->syncp); + + hinic_txq_clean_stats(txq); +} + +static void update_nic_stats(struct hinic_dev *nic_dev) +{ + int i, num_qps = hinic_hwdev_num_qps(nic_dev->hwdev); + + for (i = 0; i < num_qps; i++) + update_rx_stats(nic_dev, &nic_dev->rxqs[i]); + + for (i = 0; i < num_qps; i++) + update_tx_stats(nic_dev, &nic_dev->txqs[i]); +} + +/** + * create_txqs - Create the Logical Tx Queues of specific NIC device + * @nic_dev: the specific NIC device + * + * Return 0 - Success, negative - Failure + **/ +static int create_txqs(struct hinic_dev *nic_dev) +{ + int err, i, j, num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev); + struct net_device *netdev = nic_dev->netdev; + size_t txq_size; + + if (nic_dev->txqs) + return -EINVAL; + + txq_size = num_txqs * sizeof(*nic_dev->txqs); + nic_dev->txqs = devm_kzalloc(&netdev->dev, txq_size, GFP_KERNEL); + if (!nic_dev->txqs) + return -ENOMEM; + + for (i = 0; i < num_txqs; i++) { + struct hinic_sq *sq = hinic_hwdev_get_sq(nic_dev->hwdev, i); + + err = hinic_init_txq(&nic_dev->txqs[i], sq, netdev); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to init Txq\n"); + goto err_init_txq; + } + } + + return 0; + +err_init_txq: + for (j = 0; j < i; j++) + hinic_clean_txq(&nic_dev->txqs[j]); + + devm_kfree(&netdev->dev, nic_dev->txqs); + return err; +} + +/** + * free_txqs - Free the Logical Tx Queues of specific NIC device + * @nic_dev: the specific NIC device + **/ +static void free_txqs(struct hinic_dev *nic_dev) +{ + int i, num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev); + struct net_device *netdev = nic_dev->netdev; + + if (!nic_dev->txqs) + return; + + for (i = 0; i < num_txqs; i++) + hinic_clean_txq(&nic_dev->txqs[i]); + + devm_kfree(&netdev->dev, nic_dev->txqs); + nic_dev->txqs = NULL; +} + +/** + * create_txqs - Create the Logical Rx Queues of specific NIC device + * @nic_dev: the specific NIC device + * + * Return 0 - Success, negative - Failure + **/ +static int create_rxqs(struct hinic_dev *nic_dev) +{ + int err, i, j, num_rxqs = hinic_hwdev_num_qps(nic_dev->hwdev); + struct net_device *netdev = nic_dev->netdev; + size_t rxq_size; + + if (nic_dev->rxqs) + return -EINVAL; + + rxq_size = num_rxqs * sizeof(*nic_dev->rxqs); + nic_dev->rxqs = devm_kzalloc(&netdev->dev, rxq_size, GFP_KERNEL); + if (!nic_dev->rxqs) + return -ENOMEM; + + for (i = 0; i < num_rxqs; i++) { + struct hinic_rq *rq = hinic_hwdev_get_rq(nic_dev->hwdev, i); + + err = hinic_init_rxq(&nic_dev->rxqs[i], rq, netdev); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to init rxq\n"); + goto err_init_rxq; + } + } + + return 0; + +err_init_rxq: + for (j = 0; j < i; j++) + hinic_clean_rxq(&nic_dev->rxqs[j]); + + devm_kfree(&netdev->dev, nic_dev->rxqs); + return err; +} + +/** + * free_txqs - Free the Logical Rx Queues of specific NIC device + * @nic_dev: the specific NIC device + **/ +static void free_rxqs(struct hinic_dev *nic_dev) +{ + int i, num_rxqs = hinic_hwdev_num_qps(nic_dev->hwdev); + struct net_device *netdev = nic_dev->netdev; + + if (!nic_dev->rxqs) + return; + + for (i = 0; i < num_rxqs; i++) + hinic_clean_rxq(&nic_dev->rxqs[i]); + + devm_kfree(&netdev->dev, nic_dev->rxqs); + nic_dev->rxqs = NULL; +} + +static int hinic_open(struct net_device *netdev) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + enum hinic_port_link_state link_state; + int err, ret, num_qps; + + if (!(nic_dev->flags & HINIC_INTF_UP)) { + err = hinic_hwdev_ifup(nic_dev->hwdev); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed - HW interface up\n"); + return err; + } + } + + err = create_txqs(nic_dev); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to create Tx queues\n"); + goto err_create_txqs; + } + + err = create_rxqs(nic_dev); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to create Rx queues\n"); + goto err_create_rxqs; + } + + num_qps = hinic_hwdev_num_qps(nic_dev->hwdev); + netif_set_real_num_tx_queues(netdev, num_qps); + netif_set_real_num_rx_queues(netdev, num_qps); + + err = hinic_port_set_state(nic_dev, HINIC_PORT_ENABLE); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to set port state\n"); + goto err_port_state; + } + + err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_ENABLE); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to set func port state\n"); + goto err_func_port_state; + } + + /* Wait up to 3 sec between port enable to link state */ + msleep(3000); + + down(&nic_dev->mgmt_lock); + + err = hinic_port_link_state(nic_dev, &link_state); + if (err) { + netif_err(nic_dev, drv, netdev, "Failed to get link state\n"); + goto err_port_link; + } + + if (link_state == HINIC_LINK_STATE_UP) + nic_dev->flags |= HINIC_LINK_UP; + + nic_dev->flags |= HINIC_INTF_UP; + + if ((nic_dev->flags & (HINIC_LINK_UP | HINIC_INTF_UP)) == + (HINIC_LINK_UP | HINIC_INTF_UP)) { + netif_info(nic_dev, drv, netdev, "link + intf UP\n"); + netif_carrier_on(netdev); + netif_tx_wake_all_queues(netdev); + } + + up(&nic_dev->mgmt_lock); + + netif_info(nic_dev, drv, netdev, "HINIC_INTF is UP\n"); + return 0; + +err_port_link: + up(&nic_dev->mgmt_lock); + ret = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); + if (ret) + netif_warn(nic_dev, drv, netdev, + "Failed to revert func port state\n"); + +err_func_port_state: + ret = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); + if (ret) + netif_warn(nic_dev, drv, netdev, + "Failed to revert port state\n"); + +err_port_state: + free_rxqs(nic_dev); + +err_create_rxqs: + free_txqs(nic_dev); + +err_create_txqs: + if (!(nic_dev->flags & HINIC_INTF_UP)) + hinic_hwdev_ifdown(nic_dev->hwdev); + return err; +} + +static int hinic_close(struct net_device *netdev) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + unsigned int flags; + int err; + + down(&nic_dev->mgmt_lock); + + flags = nic_dev->flags; + nic_dev->flags &= ~HINIC_INTF_UP; + + netif_carrier_off(netdev); + netif_tx_disable(netdev); + + update_nic_stats(nic_dev); + + up(&nic_dev->mgmt_lock); + + err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to set func port state\n"); + nic_dev->flags |= (flags & HINIC_INTF_UP); + return err; + } + + err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); + if (err) { + netif_err(nic_dev, drv, netdev, "Failed to set port state\n"); + nic_dev->flags |= (flags & HINIC_INTF_UP); + return err; + } + + free_rxqs(nic_dev); + free_txqs(nic_dev); + + if (flags & HINIC_INTF_UP) + hinic_hwdev_ifdown(nic_dev->hwdev); + + netif_info(nic_dev, drv, netdev, "HINIC_INTF is DOWN\n"); + return 0; +} + +static int hinic_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + int err; + + netif_info(nic_dev, drv, netdev, "set_mtu = %d\n", new_mtu); + + err = hinic_port_set_mtu(nic_dev, new_mtu); + if (err) + netif_err(nic_dev, drv, netdev, "Failed to set port mtu\n"); + else + netdev->mtu = new_mtu; + + return err; +} + +/** + * change_mac_addr - change the main mac address of network device + * @netdev: network device + * @addr: mac address to set + * + * Return 0 - Success, negative - Failure + **/ +static int change_mac_addr(struct net_device *netdev, const u8 *addr) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + u16 vid = 0; + int err; + + if (!is_valid_ether_addr(addr)) + return -EADDRNOTAVAIL; + + netif_info(nic_dev, drv, netdev, "change mac addr = %02x %02x %02x %02x %02x %02x\n", + addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); + + down(&nic_dev->mgmt_lock); + + do { + err = hinic_port_del_mac(nic_dev, netdev->dev_addr, vid); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to delete mac\n"); + break; + } + + err = hinic_port_add_mac(nic_dev, addr, vid); + if (err) { + netif_err(nic_dev, drv, netdev, "Failed to add mac\n"); + break; + } + + vid = find_next_bit(nic_dev->vlan_bitmap, VLAN_N_VID, vid + 1); + } while (vid != VLAN_N_VID); + + up(&nic_dev->mgmt_lock); + return err; +} + +static int hinic_set_mac_addr(struct net_device *netdev, void *addr) +{ + unsigned char new_mac[ETH_ALEN]; + struct sockaddr *saddr = addr; + int err; + + memcpy(new_mac, saddr->sa_data, ETH_ALEN); + + err = change_mac_addr(netdev, new_mac); + if (!err) + memcpy(netdev->dev_addr, new_mac, ETH_ALEN); + + return err; +} + +/** + * add_mac_addr - add mac address to network device + * @netdev: network device + * @addr: mac address to add + * + * Return 0 - Success, negative - Failure + **/ +static int add_mac_addr(struct net_device *netdev, const u8 *addr) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + u16 vid = 0; + int err; + + if (!is_valid_ether_addr(addr)) + return -EADDRNOTAVAIL; + + netif_info(nic_dev, drv, netdev, "set mac addr = %02x %02x %02x %02x %02x %02x\n", + addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); + + down(&nic_dev->mgmt_lock); + + do { + err = hinic_port_add_mac(nic_dev, addr, vid); + if (err) { + netif_err(nic_dev, drv, netdev, "Failed to add mac\n"); + break; + } + + vid = find_next_bit(nic_dev->vlan_bitmap, VLAN_N_VID, vid + 1); + } while (vid != VLAN_N_VID); + + up(&nic_dev->mgmt_lock); + return err; +} + +/** + * remove_mac_addr - remove mac address from network device + * @netdev: network device + * @addr: mac address to remove + * + * Return 0 - Success, negative - Failure + **/ +static int remove_mac_addr(struct net_device *netdev, const u8 *addr) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + u16 vid = 0; + int err; + + if (!is_valid_ether_addr(addr)) + return -EADDRNOTAVAIL; + + netif_info(nic_dev, drv, netdev, "remove mac addr = %02x %02x %02x %02x %02x %02x\n", + addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); + + down(&nic_dev->mgmt_lock); + + do { + err = hinic_port_del_mac(nic_dev, addr, vid); + if (err) { + netif_err(nic_dev, drv, netdev, + "Failed to delete mac\n"); + break; + } + + vid = find_next_bit(nic_dev->vlan_bitmap, VLAN_N_VID, vid + 1); + } while (vid != VLAN_N_VID); + + up(&nic_dev->mgmt_lock); + return err; +} + +static int hinic_vlan_rx_add_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + int ret, err; + + netif_info(nic_dev, drv, netdev, "add vid = %d\n", vid); + + down(&nic_dev->mgmt_lock); + + err = hinic_port_add_vlan(nic_dev, vid); + if (err) { + netif_err(nic_dev, drv, netdev, "Failed to add vlan\n"); + goto err_vlan_add; + } + + err = hinic_port_add_mac(nic_dev, netdev->dev_addr, vid); + if (err) { + netif_err(nic_dev, drv, netdev, "Failed to set mac\n"); + goto err_add_mac; + } + + bitmap_set(nic_dev->vlan_bitmap, vid, 1); + + up(&nic_dev->mgmt_lock); + return 0; + +err_add_mac: + ret = hinic_port_del_vlan(nic_dev, vid); + if (ret) + netif_err(nic_dev, drv, netdev, + "Failed to revert by removing vlan\n"); + +err_vlan_add: + up(&nic_dev->mgmt_lock); + return err; +} + +static int hinic_vlan_rx_kill_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + int err; + + netif_info(nic_dev, drv, netdev, "remove vid = %d\n", vid); + + down(&nic_dev->mgmt_lock); + + err = hinic_port_del_vlan(nic_dev, vid); + if (err) { + netif_err(nic_dev, drv, netdev, "Failed to delete vlan\n"); + goto err_del_vlan; + } + + bitmap_clear(nic_dev->vlan_bitmap, vid, 1); + + up(&nic_dev->mgmt_lock); + return 0; + +err_del_vlan: + up(&nic_dev->mgmt_lock); + return err; +} + +static void set_rx_mode(struct work_struct *work) +{ + struct hinic_rx_mode_work *rx_mode_work = work_to_rx_mode_work(work); + struct hinic_dev *nic_dev = rx_mode_work_to_nic_dev(rx_mode_work); + + netif_info(nic_dev, drv, nic_dev->netdev, "set rx mode work\n"); + + hinic_port_set_rx_mode(nic_dev, rx_mode_work->rx_mode); + + __dev_uc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr); + __dev_mc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr); +} + +static void hinic_set_rx_mode(struct net_device *netdev) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_rx_mode_work *rx_mode_work; + u32 rx_mode; + + rx_mode_work = &nic_dev->rx_mode_work; + + rx_mode = HINIC_RX_MODE_UC | + HINIC_RX_MODE_MC | + HINIC_RX_MODE_BC; + + if (netdev->flags & IFF_PROMISC) + rx_mode |= HINIC_RX_MODE_PROMISC; + else if (netdev->flags & IFF_ALLMULTI) + rx_mode |= HINIC_RX_MODE_MC_ALL; + + rx_mode_work->rx_mode = rx_mode; + + queue_work(nic_dev->workq, &rx_mode_work->work); +} + +static void hinic_tx_timeout(struct net_device *netdev) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + + netif_err(nic_dev, drv, netdev, "Tx timeout\n"); +} + +static void hinic_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_rxq_stats *nic_rx_stats; + struct hinic_txq_stats *nic_tx_stats; + + nic_rx_stats = &nic_dev->rx_stats; + nic_tx_stats = &nic_dev->tx_stats; + + down(&nic_dev->mgmt_lock); + + if (nic_dev->flags & HINIC_INTF_UP) + update_nic_stats(nic_dev); + + up(&nic_dev->mgmt_lock); + + stats->rx_bytes = nic_rx_stats->bytes; + stats->rx_packets = nic_rx_stats->pkts; + + stats->tx_bytes = nic_tx_stats->bytes; + stats->tx_packets = nic_tx_stats->pkts; + stats->tx_errors = nic_tx_stats->tx_dropped; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void hinic_netpoll(struct net_device *netdev) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + int i, num_qps; + + num_qps = hinic_hwdev_num_qps(nic_dev->hwdev); + for (i = 0; i < num_qps; i++) { + struct hinic_txq *txq = &nic_dev->txqs[i]; + struct hinic_rxq *rxq = &nic_dev->rxqs[i]; + + napi_schedule(&txq->napi); + napi_schedule(&rxq->napi); + } +} +#endif + +static const struct net_device_ops hinic_netdev_ops = { + .ndo_open = hinic_open, + .ndo_stop = hinic_close, + .ndo_change_mtu = hinic_change_mtu, + .ndo_set_mac_address = hinic_set_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_vlan_rx_add_vid = hinic_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = hinic_vlan_rx_kill_vid, + .ndo_set_rx_mode = hinic_set_rx_mode, + .ndo_start_xmit = hinic_xmit_frame, + .ndo_tx_timeout = hinic_tx_timeout, + .ndo_get_stats64 = hinic_get_stats64, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = hinic_netpoll, +#endif +}; + +static void netdev_features_init(struct net_device *netdev) +{ + netdev->hw_features = NETIF_F_SG | NETIF_F_HIGHDMA; + + netdev->vlan_features = netdev->hw_features; + + netdev->features = netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; +} + +/** + * link_status_event_handler - link event handler + * @handle: nic device for the handler + * @buf_in: input buffer + * @in_size: input size + * @buf_in: output buffer + * @out_size: returned output size + * + * Return 0 - Success, negative - Failure + **/ +static void link_status_event_handler(void *handle, void *buf_in, u16 in_size, + void *buf_out, u16 *out_size) +{ + struct hinic_port_link_status *link_status, *ret_link_status; + struct hinic_dev *nic_dev = handle; + + link_status = buf_in; + + if (link_status->link == HINIC_LINK_STATE_UP) { + down(&nic_dev->mgmt_lock); + + nic_dev->flags |= HINIC_LINK_UP; + + if ((nic_dev->flags & (HINIC_LINK_UP | HINIC_INTF_UP)) == + (HINIC_LINK_UP | HINIC_INTF_UP)) { + netif_carrier_on(nic_dev->netdev); + netif_tx_wake_all_queues(nic_dev->netdev); + } + + up(&nic_dev->mgmt_lock); + + netif_info(nic_dev, drv, nic_dev->netdev, "HINIC_Link is UP\n"); + } else { + down(&nic_dev->mgmt_lock); + + nic_dev->flags &= ~HINIC_LINK_UP; + + netif_carrier_off(nic_dev->netdev); + netif_tx_disable(nic_dev->netdev); + + up(&nic_dev->mgmt_lock); + + netif_info(nic_dev, drv, nic_dev->netdev, "HINIC_Link is DOWN\n"); + } + + ret_link_status = buf_out; + ret_link_status->status = 0; + + *out_size = sizeof(*ret_link_status); +} + +/** + * nic_dev_init - Initialize the NIC device + * @pdev: the NIC pci device + * + * Return 0 - Success, negative - Failure + **/ +static int nic_dev_init(struct pci_dev *pdev) +{ + struct hinic_rx_mode_work *rx_mode_work; + struct hinic_txq_stats *tx_stats; + struct hinic_rxq_stats *rx_stats; + struct hinic_dev *nic_dev; + struct net_device *netdev; + struct hinic_hwdev *hwdev; + int err, num_qps; + + hwdev = hinic_init_hwdev(pdev); + if (IS_ERR(hwdev)) { + dev_err(&pdev->dev, "Failed to initialize HW device\n"); + return PTR_ERR(hwdev); + } + + num_qps = hinic_hwdev_num_qps(hwdev); + if (num_qps <= 0) { + dev_err(&pdev->dev, "Invalid number of QPS\n"); + err = -EINVAL; + goto err_num_qps; + } + + netdev = alloc_etherdev_mq(sizeof(*nic_dev), num_qps); + if (!netdev) { + dev_err(&pdev->dev, "Failed to allocate Ethernet device\n"); + err = -ENOMEM; + goto err_alloc_etherdev; + } + + netdev->netdev_ops = &hinic_netdev_ops; + netdev->ethtool_ops = &hinic_ethtool_ops; + netdev->max_mtu = ETH_MAX_MTU; + + nic_dev = netdev_priv(netdev); + nic_dev->netdev = netdev; + nic_dev->hwdev = hwdev; + nic_dev->msg_enable = MSG_ENABLE_DEFAULT; + nic_dev->flags = 0; + nic_dev->txqs = NULL; + nic_dev->rxqs = NULL; + nic_dev->tx_weight = tx_weight; + nic_dev->rx_weight = rx_weight; + + sema_init(&nic_dev->mgmt_lock, 1); + + tx_stats = &nic_dev->tx_stats; + rx_stats = &nic_dev->rx_stats; + + u64_stats_init(&tx_stats->syncp); + u64_stats_init(&rx_stats->syncp); + + nic_dev->vlan_bitmap = devm_kzalloc(&pdev->dev, + VLAN_BITMAP_SIZE(nic_dev), + GFP_KERNEL); + if (!nic_dev->vlan_bitmap) { + err = -ENOMEM; + goto err_vlan_bitmap; + } + + nic_dev->workq = create_singlethread_workqueue(HINIC_WQ_NAME); + if (!nic_dev->workq) { + err = -ENOMEM; + goto err_workq; + } + + pci_set_drvdata(pdev, netdev); + + err = hinic_port_get_mac(nic_dev, netdev->dev_addr); + if (err) + dev_warn(&pdev->dev, "Failed to get mac address\n"); + + err = hinic_port_add_mac(nic_dev, netdev->dev_addr, 0); + if (err) { + dev_err(&pdev->dev, "Failed to add mac\n"); + goto err_add_mac; + } + + err = hinic_port_set_mtu(nic_dev, netdev->mtu); + if (err) { + dev_err(&pdev->dev, "Failed to set mtu\n"); + goto err_set_mtu; + } + + rx_mode_work = &nic_dev->rx_mode_work; + INIT_WORK(&rx_mode_work->work, set_rx_mode); + + netdev_features_init(netdev); + + netif_carrier_off(netdev); + + hinic_hwdev_cb_register(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS, + nic_dev, link_status_event_handler); + + err = register_netdev(netdev); + if (err) { + dev_err(&pdev->dev, "Failed to register netdev\n"); + goto err_reg_netdev; + } + + return 0; + +err_reg_netdev: + hinic_hwdev_cb_unregister(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_LINK_STATUS); + cancel_work_sync(&rx_mode_work->work); + +err_set_mtu: +err_add_mac: + pci_set_drvdata(pdev, NULL); + destroy_workqueue(nic_dev->workq); + +err_workq: +err_vlan_bitmap: + free_netdev(netdev); + +err_alloc_etherdev: +err_num_qps: + hinic_free_hwdev(hwdev); + return err; +} + +static int hinic_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + int err = pci_enable_device(pdev); + + if (err) { + dev_err(&pdev->dev, "Failed to enable PCI device\n"); + return err; + } + + err = pci_request_regions(pdev, HINIC_DRV_NAME); + if (err) { + dev_err(&pdev->dev, "Failed to request PCI regions\n"); + goto err_pci_regions; + } + + pci_set_master(pdev); + + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (err) { + dev_warn(&pdev->dev, "Couldn't set 64-bit DMA mask\n"); + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, "Failed to set DMA mask\n"); + goto err_dma_mask; + } + } + + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + if (err) { + dev_warn(&pdev->dev, + "Couldn't set 64-bit consistent DMA mask\n"); + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, + "Failed to set consistent DMA mask\n"); + goto err_dma_consistent_mask; + } + } + + err = nic_dev_init(pdev); + if (err) { + dev_err(&pdev->dev, "Failed to initialize NIC device\n"); + goto err_nic_dev_init; + } + + dev_info(&pdev->dev, "HiNIC driver - probed\n"); + return 0; + +err_nic_dev_init: +err_dma_consistent_mask: +err_dma_mask: + pci_release_regions(pdev); + +err_pci_regions: + pci_disable_device(pdev); + return err; +} + +static void hinic_remove(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_rx_mode_work *rx_mode_work; + + unregister_netdev(netdev); + + hinic_hwdev_cb_unregister(nic_dev->hwdev, + HINIC_MGMT_MSG_CMD_LINK_STATUS); + + rx_mode_work = &nic_dev->rx_mode_work; + cancel_work_sync(&rx_mode_work->work); + + pci_set_drvdata(pdev, NULL); + + destroy_workqueue(nic_dev->workq); + + hinic_free_hwdev(nic_dev->hwdev); + + free_netdev(netdev); + + pci_release_regions(pdev); + pci_disable_device(pdev); + + dev_info(&pdev->dev, "HiNIC driver - removed\n"); +} + +static const struct pci_device_id hinic_pci_table[] = { + { PCI_VDEVICE(HUAWEI, PCI_DEVICE_ID_HI1822_PF), 0}, + { 0, 0} +}; +MODULE_DEVICE_TABLE(pci, hinic_pci_table); + +static struct pci_driver hinic_driver = { + .name = HINIC_DRV_NAME, + .id_table = hinic_pci_table, + .probe = hinic_probe, + .remove = hinic_remove, +}; + +module_pci_driver(hinic_driver); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c new file mode 100644 index 000000000000..4d4e3f05fb5f --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -0,0 +1,379 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/if_vlan.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/errno.h> + +#include "hinic_hw_if.h" +#include "hinic_hw_dev.h" +#include "hinic_port.h" +#include "hinic_dev.h" + +#define HINIC_MIN_MTU_SIZE 256 +#define HINIC_MAX_JUMBO_FRAME_SIZE 15872 + +enum mac_op { + MAC_DEL, + MAC_SET, +}; + +/** + * change_mac - change(add or delete) mac address + * @nic_dev: nic device + * @addr: mac address + * @vlan_id: vlan number to set with the mac + * @op: add or delete the mac + * + * Return 0 - Success, negative - Failure + **/ +static int change_mac(struct hinic_dev *nic_dev, const u8 *addr, + u16 vlan_id, enum mac_op op) +{ + struct net_device *netdev = nic_dev->netdev; + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_port_mac_cmd port_mac_cmd; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + enum hinic_port_cmd cmd; + u16 out_size; + int err; + + if (vlan_id >= VLAN_N_VID) { + netif_err(nic_dev, drv, netdev, "Invalid VLAN number\n"); + return -EINVAL; + } + + if (op == MAC_SET) + cmd = HINIC_PORT_CMD_SET_MAC; + else + cmd = HINIC_PORT_CMD_DEL_MAC; + + port_mac_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + port_mac_cmd.vlan_id = vlan_id; + memcpy(port_mac_cmd.mac, addr, ETH_ALEN); + + err = hinic_port_msg_cmd(hwdev, cmd, &port_mac_cmd, + sizeof(port_mac_cmd), + &port_mac_cmd, &out_size); + if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) { + dev_err(&pdev->dev, "Failed to change MAC, ret = %d\n", + port_mac_cmd.status); + return -EFAULT; + } + + return 0; +} + +/** + * hinic_port_add_mac - add mac address + * @nic_dev: nic device + * @addr: mac address + * @vlan_id: vlan number to set with the mac + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_add_mac(struct hinic_dev *nic_dev, + const u8 *addr, u16 vlan_id) +{ + return change_mac(nic_dev, addr, vlan_id, MAC_SET); +} + +/** + * hinic_port_del_mac - remove mac address + * @nic_dev: nic device + * @addr: mac address + * @vlan_id: vlan number that is connected to the mac + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_del_mac(struct hinic_dev *nic_dev, const u8 *addr, + u16 vlan_id) +{ + return change_mac(nic_dev, addr, vlan_id, MAC_DEL); +} + +/** + * hinic_port_get_mac - get the mac address of the nic device + * @nic_dev: nic device + * @addr: returned mac address + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_port_mac_cmd port_mac_cmd; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + u16 out_size; + int err; + + port_mac_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_MAC, + &port_mac_cmd, sizeof(port_mac_cmd), + &port_mac_cmd, &out_size); + if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) { + dev_err(&pdev->dev, "Failed to get mac, ret = %d\n", + port_mac_cmd.status); + return -EFAULT; + } + + memcpy(addr, port_mac_cmd.mac, ETH_ALEN); + return 0; +} + +/** + * hinic_port_set_mtu - set mtu + * @nic_dev: nic device + * @new_mtu: new mtu + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu) +{ + struct net_device *netdev = nic_dev->netdev; + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_port_mtu_cmd port_mtu_cmd; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + int err, max_frame; + u16 out_size; + + if (new_mtu < HINIC_MIN_MTU_SIZE) { + netif_err(nic_dev, drv, netdev, "mtu < MIN MTU size"); + return -EINVAL; + } + + max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; + if (max_frame > HINIC_MAX_JUMBO_FRAME_SIZE) { + netif_err(nic_dev, drv, netdev, "mtu > MAX MTU size"); + return -EINVAL; + } + + port_mtu_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + port_mtu_cmd.mtu = new_mtu; + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_CHANGE_MTU, + &port_mtu_cmd, sizeof(port_mtu_cmd), + &port_mtu_cmd, &out_size); + if (err || (out_size != sizeof(port_mtu_cmd)) || port_mtu_cmd.status) { + dev_err(&pdev->dev, "Failed to set mtu, ret = %d\n", + port_mtu_cmd.status); + return -EFAULT; + } + + return 0; +} + +/** + * hinic_port_add_vlan - add vlan to the nic device + * @nic_dev: nic device + * @vlan_id: the vlan number to add + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_add_vlan(struct hinic_dev *nic_dev, u16 vlan_id) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_port_vlan_cmd port_vlan_cmd; + + port_vlan_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwdev->hwif); + port_vlan_cmd.vlan_id = vlan_id; + + return hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_ADD_VLAN, + &port_vlan_cmd, sizeof(port_vlan_cmd), + NULL, NULL); +} + +/** + * hinic_port_del_vlan - delete vlan from the nic device + * @nic_dev: nic device + * @vlan_id: the vlan number to delete + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_del_vlan(struct hinic_dev *nic_dev, u16 vlan_id) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_port_vlan_cmd port_vlan_cmd; + + port_vlan_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwdev->hwif); + port_vlan_cmd.vlan_id = vlan_id; + + return hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_DEL_VLAN, + &port_vlan_cmd, sizeof(port_vlan_cmd), + NULL, NULL); +} + +/** + * hinic_port_set_rx_mode - set rx mode in the nic device + * @nic_dev: nic device + * @rx_mode: the rx mode to set + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_set_rx_mode(struct hinic_dev *nic_dev, u32 rx_mode) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_port_rx_mode_cmd rx_mode_cmd; + + rx_mode_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwdev->hwif); + rx_mode_cmd.rx_mode = rx_mode; + + return hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RX_MODE, + &rx_mode_cmd, sizeof(rx_mode_cmd), + NULL, NULL); +} + +/** + * hinic_port_link_state - get the link state + * @nic_dev: nic device + * @link_state: the returned link state + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_link_state(struct hinic_dev *nic_dev, + enum hinic_port_link_state *link_state) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct hinic_port_link_cmd link_cmd; + struct pci_dev *pdev = hwif->pdev; + u16 out_size; + int err; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "unsupported PCI Function type\n"); + return -EINVAL; + } + + link_cmd.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_LINK_STATE, + &link_cmd, sizeof(link_cmd), + &link_cmd, &out_size); + if (err || (out_size != sizeof(link_cmd)) || link_cmd.status) { + dev_err(&pdev->dev, "Failed to get link state, ret = %d\n", + link_cmd.status); + return -EINVAL; + } + + *link_state = link_cmd.state; + return 0; +} + +/** + * hinic_port_set_state - set port state + * @nic_dev: nic device + * @state: the state to set + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_port_state_cmd port_state; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + u16 out_size; + int err; + + if (!HINIC_IS_PF(hwif) && !HINIC_IS_PPF(hwif)) { + dev_err(&pdev->dev, "unsupported PCI Function type\n"); + return -EINVAL; + } + + port_state.state = state; + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_PORT_STATE, + &port_state, sizeof(port_state), + &port_state, &out_size); + if (err || (out_size != sizeof(port_state)) || port_state.status) { + dev_err(&pdev->dev, "Failed to set port state, ret = %d\n", + port_state.status); + return -EFAULT; + } + + return 0; +} + +/** + * hinic_port_set_func_state- set func device state + * @nic_dev: nic device + * @state: the state to set + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_set_func_state(struct hinic_dev *nic_dev, + enum hinic_func_port_state state) +{ + struct hinic_port_func_state_cmd func_state; + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + u16 out_size; + int err; + + func_state.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + func_state.state = state; + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_FUNC_STATE, + &func_state, sizeof(func_state), + &func_state, &out_size); + if (err || (out_size != sizeof(func_state)) || func_state.status) { + dev_err(&pdev->dev, "Failed to set port func state, ret = %d\n", + func_state.status); + return -EFAULT; + } + + return 0; +} + +/** + * hinic_port_get_cap - get port capabilities + * @nic_dev: nic device + * @port_cap: returned port capabilities + * + * Return 0 - Success, negative - Failure + **/ +int hinic_port_get_cap(struct hinic_dev *nic_dev, + struct hinic_port_cap *port_cap) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + u16 out_size; + int err; + + port_cap->func_idx = HINIC_HWIF_FUNC_IDX(hwif); + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_CAP, + port_cap, sizeof(*port_cap), + port_cap, &out_size); + if (err || (out_size != sizeof(*port_cap)) || port_cap->status) { + dev_err(&pdev->dev, + "Failed to get port capabilities, ret = %d\n", + port_cap->status); + return -EINVAL; + } + + return 0; +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h new file mode 100644 index 000000000000..9404365195dd --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h @@ -0,0 +1,198 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_PORT_H +#define HINIC_PORT_H + +#include <linux/types.h> +#include <linux/etherdevice.h> +#include <linux/bitops.h> + +#include "hinic_dev.h" + +enum hinic_rx_mode { + HINIC_RX_MODE_UC = BIT(0), + HINIC_RX_MODE_MC = BIT(1), + HINIC_RX_MODE_BC = BIT(2), + HINIC_RX_MODE_MC_ALL = BIT(3), + HINIC_RX_MODE_PROMISC = BIT(4), +}; + +enum hinic_port_link_state { + HINIC_LINK_STATE_DOWN, + HINIC_LINK_STATE_UP, +}; + +enum hinic_port_state { + HINIC_PORT_DISABLE = 0, + HINIC_PORT_ENABLE = 3, +}; + +enum hinic_func_port_state { + HINIC_FUNC_PORT_DISABLE = 0, + HINIC_FUNC_PORT_ENABLE = 2, +}; + +enum hinic_autoneg_cap { + HINIC_AUTONEG_UNSUPPORTED, + HINIC_AUTONEG_SUPPORTED, +}; + +enum hinic_autoneg_state { + HINIC_AUTONEG_DISABLED, + HINIC_AUTONEG_ACTIVE, +}; + +enum hinic_duplex { + HINIC_DUPLEX_HALF, + HINIC_DUPLEX_FULL, +}; + +enum hinic_speed { + HINIC_SPEED_10MB_LINK = 0, + HINIC_SPEED_100MB_LINK, + HINIC_SPEED_1000MB_LINK, + HINIC_SPEED_10GB_LINK, + HINIC_SPEED_25GB_LINK, + HINIC_SPEED_40GB_LINK, + HINIC_SPEED_100GB_LINK, + + HINIC_SPEED_UNKNOWN = 0xFF, +}; + +struct hinic_port_mac_cmd { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 vlan_id; + u16 rsvd1; + unsigned char mac[ETH_ALEN]; +}; + +struct hinic_port_mtu_cmd { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 rsvd1; + u32 mtu; +}; + +struct hinic_port_vlan_cmd { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 vlan_id; +}; + +struct hinic_port_rx_mode_cmd { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 rsvd; + u32 rx_mode; +}; + +struct hinic_port_link_cmd { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 state; + u8 rsvd1; +}; + +struct hinic_port_state_cmd { + u8 status; + u8 version; + u8 rsvd0[6]; + + u8 state; + u8 rsvd1[3]; +}; + +struct hinic_port_link_status { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 rsvd1; + u8 link; + u8 rsvd2; +}; + +struct hinic_port_func_state_cmd { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 rsvd1; + u8 state; + u8 rsvd2[3]; +}; + +struct hinic_port_cap { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u16 rsvd1; + u8 port_type; + u8 autoneg_cap; + u8 autoneg_state; + u8 duplex; + u8 speed; + u8 rsvd2[3]; +}; + +int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr, + u16 vlan_id); + +int hinic_port_del_mac(struct hinic_dev *nic_dev, const u8 *addr, + u16 vlan_id); + +int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr); + +int hinic_port_set_mtu(struct hinic_dev *nic_dev, int new_mtu); + +int hinic_port_add_vlan(struct hinic_dev *nic_dev, u16 vlan_id); + +int hinic_port_del_vlan(struct hinic_dev *nic_dev, u16 vlan_id); + +int hinic_port_set_rx_mode(struct hinic_dev *nic_dev, u32 rx_mode); + +int hinic_port_link_state(struct hinic_dev *nic_dev, + enum hinic_port_link_state *link_state); + +int hinic_port_set_state(struct hinic_dev *nic_dev, + enum hinic_port_state state); + +int hinic_port_set_func_state(struct hinic_dev *nic_dev, + enum hinic_func_port_state state); + +int hinic_port_get_cap(struct hinic_dev *nic_dev, + struct hinic_port_cap *port_cap); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c new file mode 100644 index 000000000000..1d4f712b15a8 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -0,0 +1,509 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/u64_stats_sync.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/skbuff.h> +#include <linux/dma-mapping.h> +#include <linux/prefetch.h> +#include <asm/barrier.h> + +#include "hinic_common.h" +#include "hinic_hw_if.h" +#include "hinic_hw_wqe.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_qp.h" +#include "hinic_hw_dev.h" +#include "hinic_rx.h" +#include "hinic_dev.h" + +#define RX_IRQ_NO_PENDING 0 +#define RX_IRQ_NO_COALESC 0 +#define RX_IRQ_NO_LLI_TIMER 0 +#define RX_IRQ_NO_CREDIT 0 +#define RX_IRQ_NO_RESEND_TIMER 0 + +/** + * hinic_rxq_clean_stats - Clean the statistics of specific queue + * @rxq: Logical Rx Queue + **/ +void hinic_rxq_clean_stats(struct hinic_rxq *rxq) +{ + struct hinic_rxq_stats *rxq_stats = &rxq->rxq_stats; + + u64_stats_update_begin(&rxq_stats->syncp); + rxq_stats->pkts = 0; + rxq_stats->bytes = 0; + u64_stats_update_end(&rxq_stats->syncp); +} + +/** + * hinic_rxq_get_stats - get statistics of Rx Queue + * @rxq: Logical Rx Queue + * @stats: return updated stats here + **/ +void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats) +{ + struct hinic_rxq_stats *rxq_stats = &rxq->rxq_stats; + unsigned int start; + + u64_stats_update_begin(&stats->syncp); + do { + start = u64_stats_fetch_begin(&rxq_stats->syncp); + stats->pkts = rxq_stats->pkts; + stats->bytes = rxq_stats->bytes; + } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); + u64_stats_update_end(&stats->syncp); +} + +/** + * rxq_stats_init - Initialize the statistics of specific queue + * @rxq: Logical Rx Queue + **/ +static void rxq_stats_init(struct hinic_rxq *rxq) +{ + struct hinic_rxq_stats *rxq_stats = &rxq->rxq_stats; + + u64_stats_init(&rxq_stats->syncp); + hinic_rxq_clean_stats(rxq); +} + +/** + * rx_alloc_skb - allocate skb and map it to dma address + * @rxq: rx queue + * @dma_addr: returned dma address for the skb + * + * Return skb + **/ +static struct sk_buff *rx_alloc_skb(struct hinic_rxq *rxq, + dma_addr_t *dma_addr) +{ + struct hinic_dev *nic_dev = netdev_priv(rxq->netdev); + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct sk_buff *skb; + dma_addr_t addr; + int err; + + skb = netdev_alloc_skb_ip_align(rxq->netdev, rxq->rq->buf_sz); + if (!skb) { + netdev_err(rxq->netdev, "Failed to allocate Rx SKB\n"); + return NULL; + } + + addr = dma_map_single(&pdev->dev, skb->data, rxq->rq->buf_sz, + DMA_FROM_DEVICE); + err = dma_mapping_error(&pdev->dev, addr); + if (err) { + dev_err(&pdev->dev, "Failed to map Rx DMA, err = %d\n", err); + goto err_rx_map; + } + + *dma_addr = addr; + return skb; + +err_rx_map: + dev_kfree_skb_any(skb); + return NULL; +} + +/** + * rx_unmap_skb - unmap the dma address of the skb + * @rxq: rx queue + * @dma_addr: dma address of the skb + **/ +static void rx_unmap_skb(struct hinic_rxq *rxq, dma_addr_t dma_addr) +{ + struct hinic_dev *nic_dev = netdev_priv(rxq->netdev); + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + + dma_unmap_single(&pdev->dev, dma_addr, rxq->rq->buf_sz, + DMA_FROM_DEVICE); +} + +/** + * rx_free_skb - unmap and free skb + * @rxq: rx queue + * @skb: skb to free + * @dma_addr: dma address of the skb + **/ +static void rx_free_skb(struct hinic_rxq *rxq, struct sk_buff *skb, + dma_addr_t dma_addr) +{ + rx_unmap_skb(rxq, dma_addr); + dev_kfree_skb_any(skb); +} + +/** + * rx_alloc_pkts - allocate pkts in rx queue + * @rxq: rx queue + * + * Return number of skbs allocated + **/ +static int rx_alloc_pkts(struct hinic_rxq *rxq) +{ + struct hinic_dev *nic_dev = netdev_priv(rxq->netdev); + struct hinic_rq_wqe *rq_wqe; + unsigned int free_wqebbs; + struct hinic_sge sge; + dma_addr_t dma_addr; + struct sk_buff *skb; + int i, alloc_more; + u16 prod_idx; + + free_wqebbs = hinic_get_rq_free_wqebbs(rxq->rq); + alloc_more = 0; + + /* Limit the allocation chunks */ + if (free_wqebbs > nic_dev->rx_weight) + free_wqebbs = nic_dev->rx_weight; + + for (i = 0; i < free_wqebbs; i++) { + skb = rx_alloc_skb(rxq, &dma_addr); + if (!skb) { + netdev_err(rxq->netdev, "Failed to alloc Rx skb\n"); + alloc_more = 1; + goto skb_out; + } + + hinic_set_sge(&sge, dma_addr, skb->len); + + rq_wqe = hinic_rq_get_wqe(rxq->rq, HINIC_RQ_WQE_SIZE, + &prod_idx); + if (!rq_wqe) { + rx_free_skb(rxq, skb, dma_addr); + alloc_more = 1; + goto skb_out; + } + + hinic_rq_prepare_wqe(rxq->rq, prod_idx, rq_wqe, &sge); + + hinic_rq_write_wqe(rxq->rq, prod_idx, rq_wqe, skb); + } + +skb_out: + if (i) { + wmb(); /* write all the wqes before update PI */ + + hinic_rq_update(rxq->rq, prod_idx); + } + + if (alloc_more) + tasklet_schedule(&rxq->rx_task); + + return i; +} + +/** + * free_all_rx_skbs - free all skbs in rx queue + * @rxq: rx queue + **/ +static void free_all_rx_skbs(struct hinic_rxq *rxq) +{ + struct hinic_rq *rq = rxq->rq; + struct hinic_hw_wqe *hw_wqe; + struct hinic_sge sge; + u16 ci; + + while ((hw_wqe = hinic_read_wqe(rq->wq, HINIC_RQ_WQE_SIZE, &ci))) { + if (IS_ERR(hw_wqe)) + break; + + hinic_rq_get_sge(rq, &hw_wqe->rq_wqe, ci, &sge); + + hinic_put_wqe(rq->wq, HINIC_RQ_WQE_SIZE); + + rx_free_skb(rxq, rq->saved_skb[ci], hinic_sge_to_dma(&sge)); + } +} + +/** + * rx_alloc_task - tasklet for queue allocation + * @data: rx queue + **/ +static void rx_alloc_task(unsigned long data) +{ + struct hinic_rxq *rxq = (struct hinic_rxq *)data; + + (void)rx_alloc_pkts(rxq); +} + +/** + * rx_recv_jumbo_pkt - Rx handler for jumbo pkt + * @rxq: rx queue + * @head_skb: the first skb in the list + * @left_pkt_len: left size of the pkt exclude head skb + * @ci: consumer index + * + * Return number of wqes that used for the left of the pkt + **/ +static int rx_recv_jumbo_pkt(struct hinic_rxq *rxq, struct sk_buff *head_skb, + unsigned int left_pkt_len, u16 ci) +{ + struct sk_buff *skb, *curr_skb = head_skb; + struct hinic_rq_wqe *rq_wqe; + unsigned int curr_len; + struct hinic_sge sge; + int num_wqes = 0; + + while (left_pkt_len > 0) { + rq_wqe = hinic_rq_read_next_wqe(rxq->rq, HINIC_RQ_WQE_SIZE, + &skb, &ci); + + num_wqes++; + + hinic_rq_get_sge(rxq->rq, rq_wqe, ci, &sge); + + rx_unmap_skb(rxq, hinic_sge_to_dma(&sge)); + + prefetch(skb->data); + + curr_len = (left_pkt_len > HINIC_RX_BUF_SZ) ? HINIC_RX_BUF_SZ : + left_pkt_len; + + left_pkt_len -= curr_len; + + __skb_put(skb, curr_len); + + if (curr_skb == head_skb) + skb_shinfo(head_skb)->frag_list = skb; + else + curr_skb->next = skb; + + head_skb->len += skb->len; + head_skb->data_len += skb->len; + head_skb->truesize += skb->truesize; + + curr_skb = skb; + } + + return num_wqes; +} + +/** + * rxq_recv - Rx handler + * @rxq: rx queue + * @budget: maximum pkts to process + * + * Return number of pkts received + **/ +static int rxq_recv(struct hinic_rxq *rxq, int budget) +{ + struct hinic_qp *qp = container_of(rxq->rq, struct hinic_qp, rq); + u64 pkt_len = 0, rx_bytes = 0; + struct hinic_rq_wqe *rq_wqe; + int num_wqes, pkts = 0; + struct hinic_sge sge; + struct sk_buff *skb; + u16 ci; + + while (pkts < budget) { + num_wqes = 0; + + rq_wqe = hinic_rq_read_wqe(rxq->rq, HINIC_RQ_WQE_SIZE, &skb, + &ci); + if (!rq_wqe) + break; + + hinic_rq_get_sge(rxq->rq, rq_wqe, ci, &sge); + + rx_unmap_skb(rxq, hinic_sge_to_dma(&sge)); + + prefetch(skb->data); + + pkt_len = sge.len; + + if (pkt_len <= HINIC_RX_BUF_SZ) { + __skb_put(skb, pkt_len); + } else { + __skb_put(skb, HINIC_RX_BUF_SZ); + num_wqes = rx_recv_jumbo_pkt(rxq, skb, pkt_len - + HINIC_RX_BUF_SZ, ci); + } + + hinic_rq_put_wqe(rxq->rq, ci, + (num_wqes + 1) * HINIC_RQ_WQE_SIZE); + + skb_record_rx_queue(skb, qp->q_id); + skb->protocol = eth_type_trans(skb, rxq->netdev); + + napi_gro_receive(&rxq->napi, skb); + + pkts++; + rx_bytes += pkt_len; + } + + if (pkts) + tasklet_schedule(&rxq->rx_task); /* hinic_rx_alloc_pkts */ + + u64_stats_update_begin(&rxq->rxq_stats.syncp); + rxq->rxq_stats.pkts += pkts; + rxq->rxq_stats.bytes += rx_bytes; + u64_stats_update_end(&rxq->rxq_stats.syncp); + + return pkts; +} + +static int rx_poll(struct napi_struct *napi, int budget) +{ + struct hinic_rxq *rxq = container_of(napi, struct hinic_rxq, napi); + struct hinic_rq *rq = rxq->rq; + int pkts; + + pkts = rxq_recv(rxq, budget); + if (pkts >= budget) + return budget; + + napi_complete(napi); + enable_irq(rq->irq); + return pkts; +} + +static void rx_add_napi(struct hinic_rxq *rxq) +{ + struct hinic_dev *nic_dev = netdev_priv(rxq->netdev); + + netif_napi_add(rxq->netdev, &rxq->napi, rx_poll, nic_dev->rx_weight); + napi_enable(&rxq->napi); +} + +static void rx_del_napi(struct hinic_rxq *rxq) +{ + napi_disable(&rxq->napi); + netif_napi_del(&rxq->napi); +} + +static irqreturn_t rx_irq(int irq, void *data) +{ + struct hinic_rxq *rxq = (struct hinic_rxq *)data; + struct hinic_rq *rq = rxq->rq; + struct hinic_dev *nic_dev; + + /* Disable the interrupt until napi will be completed */ + disable_irq_nosync(rq->irq); + + nic_dev = netdev_priv(rxq->netdev); + hinic_hwdev_msix_cnt_set(nic_dev->hwdev, rq->msix_entry); + + napi_schedule(&rxq->napi); + return IRQ_HANDLED; +} + +static int rx_request_irq(struct hinic_rxq *rxq) +{ + struct hinic_dev *nic_dev = netdev_priv(rxq->netdev); + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_rq *rq = rxq->rq; + int err; + + rx_add_napi(rxq); + + hinic_hwdev_msix_set(hwdev, rq->msix_entry, + RX_IRQ_NO_PENDING, RX_IRQ_NO_COALESC, + RX_IRQ_NO_LLI_TIMER, RX_IRQ_NO_CREDIT, + RX_IRQ_NO_RESEND_TIMER); + + err = request_irq(rq->irq, rx_irq, 0, rxq->irq_name, rxq); + if (err) { + rx_del_napi(rxq); + return err; + } + + return 0; +} + +static void rx_free_irq(struct hinic_rxq *rxq) +{ + struct hinic_rq *rq = rxq->rq; + + free_irq(rq->irq, rxq); + rx_del_napi(rxq); +} + +/** + * hinic_init_rxq - Initialize the Rx Queue + * @rxq: Logical Rx Queue + * @rq: Hardware Rx Queue to connect the Logical queue with + * @netdev: network device to connect the Logical queue with + * + * Return 0 - Success, negative - Failure + **/ +int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq, + struct net_device *netdev) +{ + struct hinic_qp *qp = container_of(rq, struct hinic_qp, rq); + int err, pkts, irqname_len; + + rxq->netdev = netdev; + rxq->rq = rq; + + rxq_stats_init(rxq); + + irqname_len = snprintf(NULL, 0, "hinic_rxq%d", qp->q_id) + 1; + rxq->irq_name = devm_kzalloc(&netdev->dev, irqname_len, GFP_KERNEL); + if (!rxq->irq_name) + return -ENOMEM; + + sprintf(rxq->irq_name, "hinic_rxq%d", qp->q_id); + + tasklet_init(&rxq->rx_task, rx_alloc_task, (unsigned long)rxq); + + pkts = rx_alloc_pkts(rxq); + if (!pkts) { + err = -ENOMEM; + goto err_rx_pkts; + } + + err = rx_request_irq(rxq); + if (err) { + netdev_err(netdev, "Failed to request Rx irq\n"); + goto err_req_rx_irq; + } + + return 0; + +err_req_rx_irq: +err_rx_pkts: + tasklet_kill(&rxq->rx_task); + free_all_rx_skbs(rxq); + devm_kfree(&netdev->dev, rxq->irq_name); + return err; +} + +/** + * hinic_clean_rxq - Clean the Rx Queue + * @rxq: Logical Rx Queue + **/ +void hinic_clean_rxq(struct hinic_rxq *rxq) +{ + struct net_device *netdev = rxq->netdev; + + rx_free_irq(rxq); + + tasklet_kill(&rxq->rx_task); + free_all_rx_skbs(rxq); + devm_kfree(&netdev->dev, rxq->irq_name); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.h b/drivers/net/ethernet/huawei/hinic/hinic_rx.h new file mode 100644 index 000000000000..27c9af4b1c12 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.h @@ -0,0 +1,55 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_RX_H +#define HINIC_RX_H + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <linux/u64_stats_sync.h> +#include <linux/interrupt.h> + +#include "hinic_hw_qp.h" + +struct hinic_rxq_stats { + u64 pkts; + u64 bytes; + + struct u64_stats_sync syncp; +}; + +struct hinic_rxq { + struct net_device *netdev; + struct hinic_rq *rq; + + struct hinic_rxq_stats rxq_stats; + + char *irq_name; + + struct tasklet_struct rx_task; + + struct napi_struct napi; +}; + +void hinic_rxq_clean_stats(struct hinic_rxq *rxq); + +void hinic_rxq_get_stats(struct hinic_rxq *rxq, struct hinic_rxq_stats *stats); + +int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq, + struct net_device *netdev); + +void hinic_clean_rxq(struct hinic_rxq *rxq); + +#endif diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c new file mode 100644 index 000000000000..abe3e38cd342 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -0,0 +1,504 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/u64_stats_sync.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/pci.h> +#include <linux/device.h> +#include <linux/dma-mapping.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/skbuff.h> +#include <linux/smp.h> +#include <asm/byteorder.h> + +#include "hinic_common.h" +#include "hinic_hw_if.h" +#include "hinic_hw_wqe.h" +#include "hinic_hw_wq.h" +#include "hinic_hw_qp.h" +#include "hinic_hw_dev.h" +#include "hinic_dev.h" +#include "hinic_tx.h" + +#define TX_IRQ_NO_PENDING 0 +#define TX_IRQ_NO_COALESC 0 +#define TX_IRQ_NO_LLI_TIMER 0 +#define TX_IRQ_NO_CREDIT 0 +#define TX_IRQ_NO_RESEND_TIMER 0 + +#define CI_UPDATE_NO_PENDING 0 +#define CI_UPDATE_NO_COALESC 0 + +#define HW_CONS_IDX(sq) be16_to_cpu(*(u16 *)((sq)->hw_ci_addr)) + +#define MIN_SKB_LEN 64 + +/** + * hinic_txq_clean_stats - Clean the statistics of specific queue + * @txq: Logical Tx Queue + **/ +void hinic_txq_clean_stats(struct hinic_txq *txq) +{ + struct hinic_txq_stats *txq_stats = &txq->txq_stats; + + u64_stats_update_begin(&txq_stats->syncp); + txq_stats->pkts = 0; + txq_stats->bytes = 0; + txq_stats->tx_busy = 0; + txq_stats->tx_wake = 0; + txq_stats->tx_dropped = 0; + u64_stats_update_end(&txq_stats->syncp); +} + +/** + * hinic_txq_get_stats - get statistics of Tx Queue + * @txq: Logical Tx Queue + * @stats: return updated stats here + **/ +void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats) +{ + struct hinic_txq_stats *txq_stats = &txq->txq_stats; + unsigned int start; + + u64_stats_update_begin(&stats->syncp); + do { + start = u64_stats_fetch_begin(&txq_stats->syncp); + stats->pkts = txq_stats->pkts; + stats->bytes = txq_stats->bytes; + stats->tx_busy = txq_stats->tx_busy; + stats->tx_wake = txq_stats->tx_wake; + stats->tx_dropped = txq_stats->tx_dropped; + } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); + u64_stats_update_end(&stats->syncp); +} + +/** + * txq_stats_init - Initialize the statistics of specific queue + * @txq: Logical Tx Queue + **/ +static void txq_stats_init(struct hinic_txq *txq) +{ + struct hinic_txq_stats *txq_stats = &txq->txq_stats; + + u64_stats_init(&txq_stats->syncp); + hinic_txq_clean_stats(txq); +} + +/** + * tx_map_skb - dma mapping for skb and return sges + * @nic_dev: nic device + * @skb: the skb + * @sges: returned sges + * + * Return 0 - Success, negative - Failure + **/ +static int tx_map_skb(struct hinic_dev *nic_dev, struct sk_buff *skb, + struct hinic_sge *sges) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct skb_frag_struct *frag; + dma_addr_t dma_addr; + int i, j; + + dma_addr = dma_map_single(&pdev->dev, skb->data, skb_headlen(skb), + DMA_TO_DEVICE); + if (dma_mapping_error(&pdev->dev, dma_addr)) { + dev_err(&pdev->dev, "Failed to map Tx skb data\n"); + return -EFAULT; + } + + hinic_set_sge(&sges[0], dma_addr, skb_headlen(skb)); + + for (i = 0 ; i < skb_shinfo(skb)->nr_frags; i++) { + frag = &skb_shinfo(skb)->frags[i]; + + dma_addr = skb_frag_dma_map(&pdev->dev, frag, 0, + skb_frag_size(frag), + DMA_TO_DEVICE); + if (dma_mapping_error(&pdev->dev, dma_addr)) { + dev_err(&pdev->dev, "Failed to map Tx skb frag\n"); + goto err_tx_map; + } + + hinic_set_sge(&sges[i + 1], dma_addr, skb_frag_size(frag)); + } + + return 0; + +err_tx_map: + for (j = 0; j < i; j++) + dma_unmap_page(&pdev->dev, hinic_sge_to_dma(&sges[j + 1]), + sges[j + 1].len, DMA_TO_DEVICE); + + dma_unmap_single(&pdev->dev, hinic_sge_to_dma(&sges[0]), sges[0].len, + DMA_TO_DEVICE); + return -EFAULT; +} + +/** + * tx_unmap_skb - unmap the dma address of the skb + * @nic_dev: nic device + * @skb: the skb + * @sges: the sges that are connected to the skb + **/ +static void tx_unmap_skb(struct hinic_dev *nic_dev, struct sk_buff *skb, + struct hinic_sge *sges) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + int i; + + for (i = 0; i < skb_shinfo(skb)->nr_frags ; i++) + dma_unmap_page(&pdev->dev, hinic_sge_to_dma(&sges[i + 1]), + sges[i + 1].len, DMA_TO_DEVICE); + + dma_unmap_single(&pdev->dev, hinic_sge_to_dma(&sges[0]), sges[0].len, + DMA_TO_DEVICE); +} + +netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +{ + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct netdev_queue *netdev_txq; + int nr_sges, err = NETDEV_TX_OK; + struct hinic_sq_wqe *sq_wqe; + unsigned int wqe_size; + struct hinic_txq *txq; + struct hinic_qp *qp; + u16 prod_idx; + + txq = &nic_dev->txqs[skb->queue_mapping]; + qp = container_of(txq->sq, struct hinic_qp, sq); + + if (skb->len < MIN_SKB_LEN) { + if (skb_pad(skb, MIN_SKB_LEN - skb->len)) { + netdev_err(netdev, "Failed to pad skb\n"); + goto update_error_stats; + } + + skb->len = MIN_SKB_LEN; + } + + nr_sges = skb_shinfo(skb)->nr_frags + 1; + if (nr_sges > txq->max_sges) { + netdev_err(netdev, "Too many Tx sges\n"); + goto skb_error; + } + + err = tx_map_skb(nic_dev, skb, txq->sges); + if (err) + goto skb_error; + + wqe_size = HINIC_SQ_WQE_SIZE(nr_sges); + + sq_wqe = hinic_sq_get_wqe(txq->sq, wqe_size, &prod_idx); + if (!sq_wqe) { + tx_unmap_skb(nic_dev, skb, txq->sges); + + netif_stop_subqueue(netdev, qp->q_id); + + u64_stats_update_begin(&txq->txq_stats.syncp); + txq->txq_stats.tx_busy++; + u64_stats_update_end(&txq->txq_stats.syncp); + err = NETDEV_TX_BUSY; + goto flush_skbs; + } + + hinic_sq_prepare_wqe(txq->sq, prod_idx, sq_wqe, txq->sges, nr_sges); + + hinic_sq_write_wqe(txq->sq, prod_idx, sq_wqe, skb, wqe_size); + +flush_skbs: + netdev_txq = netdev_get_tx_queue(netdev, skb->queue_mapping); + if ((!skb->xmit_more) || (netif_xmit_stopped(netdev_txq))) + hinic_sq_write_db(txq->sq, prod_idx, wqe_size, 0); + + return err; + +skb_error: + dev_kfree_skb_any(skb); + +update_error_stats: + u64_stats_update_begin(&txq->txq_stats.syncp); + txq->txq_stats.tx_dropped++; + u64_stats_update_end(&txq->txq_stats.syncp); + return err; +} + +/** + * tx_free_skb - unmap and free skb + * @nic_dev: nic device + * @skb: the skb + * @sges: the sges that are connected to the skb + **/ +static void tx_free_skb(struct hinic_dev *nic_dev, struct sk_buff *skb, + struct hinic_sge *sges) +{ + tx_unmap_skb(nic_dev, skb, sges); + + dev_kfree_skb_any(skb); +} + +/** + * free_all_rx_skbs - free all skbs in tx queue + * @txq: tx queue + **/ +static void free_all_tx_skbs(struct hinic_txq *txq) +{ + struct hinic_dev *nic_dev = netdev_priv(txq->netdev); + struct hinic_sq *sq = txq->sq; + struct hinic_sq_wqe *sq_wqe; + unsigned int wqe_size; + struct sk_buff *skb; + int nr_sges; + u16 ci; + + while ((sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &ci))) { + nr_sges = skb_shinfo(skb)->nr_frags + 1; + + hinic_sq_get_sges(sq_wqe, txq->free_sges, nr_sges); + + hinic_sq_put_wqe(sq, wqe_size); + + tx_free_skb(nic_dev, skb, txq->free_sges); + } +} + +/** + * free_tx_poll - free finished tx skbs in tx queue that connected to napi + * @napi: napi + * @budget: number of tx + * + * Return 0 - Success, negative - Failure + **/ +static int free_tx_poll(struct napi_struct *napi, int budget) +{ + struct hinic_txq *txq = container_of(napi, struct hinic_txq, napi); + struct hinic_qp *qp = container_of(txq->sq, struct hinic_qp, sq); + struct hinic_dev *nic_dev = netdev_priv(txq->netdev); + struct netdev_queue *netdev_txq; + struct hinic_sq *sq = txq->sq; + struct hinic_wq *wq = sq->wq; + struct hinic_sq_wqe *sq_wqe; + unsigned int wqe_size; + int nr_sges, pkts = 0; + struct sk_buff *skb; + u64 tx_bytes = 0; + u16 hw_ci, sw_ci; + + do { + hw_ci = HW_CONS_IDX(sq) & wq->mask; + + sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &sw_ci); + if ((!sq_wqe) || + (((hw_ci - sw_ci) & wq->mask) * wq->wqebb_size < wqe_size)) + break; + + tx_bytes += skb->len; + pkts++; + + nr_sges = skb_shinfo(skb)->nr_frags + 1; + + hinic_sq_get_sges(sq_wqe, txq->free_sges, nr_sges); + + hinic_sq_put_wqe(sq, wqe_size); + + tx_free_skb(nic_dev, skb, txq->free_sges); + } while (pkts < budget); + + if (__netif_subqueue_stopped(nic_dev->netdev, qp->q_id) && + hinic_get_sq_free_wqebbs(sq) >= HINIC_MIN_TX_NUM_WQEBBS(sq)) { + netdev_txq = netdev_get_tx_queue(txq->netdev, qp->q_id); + + __netif_tx_lock(netdev_txq, smp_processor_id()); + + netif_wake_subqueue(nic_dev->netdev, qp->q_id); + + __netif_tx_unlock(netdev_txq); + + u64_stats_update_begin(&txq->txq_stats.syncp); + txq->txq_stats.tx_wake++; + u64_stats_update_end(&txq->txq_stats.syncp); + } + + u64_stats_update_begin(&txq->txq_stats.syncp); + txq->txq_stats.bytes += tx_bytes; + txq->txq_stats.pkts += pkts; + u64_stats_update_end(&txq->txq_stats.syncp); + + if (pkts < budget) { + napi_complete(napi); + enable_irq(sq->irq); + return pkts; + } + + return budget; +} + +static void tx_napi_add(struct hinic_txq *txq, int weight) +{ + netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, weight); + napi_enable(&txq->napi); +} + +static void tx_napi_del(struct hinic_txq *txq) +{ + napi_disable(&txq->napi); + netif_napi_del(&txq->napi); +} + +static irqreturn_t tx_irq(int irq, void *data) +{ + struct hinic_txq *txq = data; + struct hinic_dev *nic_dev; + + nic_dev = netdev_priv(txq->netdev); + + /* Disable the interrupt until napi will be completed */ + disable_irq_nosync(txq->sq->irq); + + hinic_hwdev_msix_cnt_set(nic_dev->hwdev, txq->sq->msix_entry); + + napi_schedule(&txq->napi); + return IRQ_HANDLED; +} + +static int tx_request_irq(struct hinic_txq *txq) +{ + struct hinic_dev *nic_dev = netdev_priv(txq->netdev); + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_sq *sq = txq->sq; + int err; + + tx_napi_add(txq, nic_dev->tx_weight); + + hinic_hwdev_msix_set(nic_dev->hwdev, sq->msix_entry, + TX_IRQ_NO_PENDING, TX_IRQ_NO_COALESC, + TX_IRQ_NO_LLI_TIMER, TX_IRQ_NO_CREDIT, + TX_IRQ_NO_RESEND_TIMER); + + err = request_irq(sq->irq, tx_irq, 0, txq->irq_name, txq); + if (err) { + dev_err(&pdev->dev, "Failed to request Tx irq\n"); + tx_napi_del(txq); + return err; + } + + return 0; +} + +static void tx_free_irq(struct hinic_txq *txq) +{ + struct hinic_sq *sq = txq->sq; + + free_irq(sq->irq, txq); + tx_napi_del(txq); +} + +/** + * hinic_init_txq - Initialize the Tx Queue + * @txq: Logical Tx Queue + * @sq: Hardware Tx Queue to connect the Logical queue with + * @netdev: network device to connect the Logical queue with + * + * Return 0 - Success, negative - Failure + **/ +int hinic_init_txq(struct hinic_txq *txq, struct hinic_sq *sq, + struct net_device *netdev) +{ + struct hinic_qp *qp = container_of(sq, struct hinic_qp, sq); + struct hinic_dev *nic_dev = netdev_priv(netdev); + struct hinic_hwdev *hwdev = nic_dev->hwdev; + int err, irqname_len; + size_t sges_size; + + txq->netdev = netdev; + txq->sq = sq; + + txq_stats_init(txq); + + txq->max_sges = HINIC_MAX_SQ_BUFDESCS; + + sges_size = txq->max_sges * sizeof(*txq->sges); + txq->sges = devm_kzalloc(&netdev->dev, sges_size, GFP_KERNEL); + if (!txq->sges) + return -ENOMEM; + + sges_size = txq->max_sges * sizeof(*txq->free_sges); + txq->free_sges = devm_kzalloc(&netdev->dev, sges_size, GFP_KERNEL); + if (!txq->free_sges) { + err = -ENOMEM; + goto err_alloc_free_sges; + } + + irqname_len = snprintf(NULL, 0, "hinic_txq%d", qp->q_id) + 1; + txq->irq_name = devm_kzalloc(&netdev->dev, irqname_len, GFP_KERNEL); + if (!txq->irq_name) { + err = -ENOMEM; + goto err_alloc_irqname; + } + + sprintf(txq->irq_name, "hinic_txq%d", qp->q_id); + + err = hinic_hwdev_hw_ci_addr_set(hwdev, sq, CI_UPDATE_NO_PENDING, + CI_UPDATE_NO_COALESC); + if (err) + goto err_hw_ci; + + err = tx_request_irq(txq); + if (err) { + netdev_err(netdev, "Failed to request Tx irq\n"); + goto err_req_tx_irq; + } + + return 0; + +err_req_tx_irq: +err_hw_ci: + devm_kfree(&netdev->dev, txq->irq_name); + +err_alloc_irqname: + devm_kfree(&netdev->dev, txq->free_sges); + +err_alloc_free_sges: + devm_kfree(&netdev->dev, txq->sges); + return err; +} + +/** + * hinic_clean_txq - Clean the Tx Queue + * @txq: Logical Tx Queue + **/ +void hinic_clean_txq(struct hinic_txq *txq) +{ + struct net_device *netdev = txq->netdev; + + tx_free_irq(txq); + + free_all_tx_skbs(txq); + + devm_kfree(&netdev->dev, txq->irq_name); + devm_kfree(&netdev->dev, txq->free_sges); + devm_kfree(&netdev->dev, txq->sges); +} diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.h b/drivers/net/ethernet/huawei/hinic/hinic_tx.h new file mode 100644 index 000000000000..1fa55dce5aa7 --- /dev/null +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.h @@ -0,0 +1,62 @@ +/* + * Huawei HiNIC PCI Express Linux driver + * Copyright(c) 2017 Huawei Technologies Co., Ltd + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + */ + +#ifndef HINIC_TX_H +#define HINIC_TX_H + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/u64_stats_sync.h> + +#include "hinic_common.h" +#include "hinic_hw_qp.h" + +struct hinic_txq_stats { + u64 pkts; + u64 bytes; + u64 tx_busy; + u64 tx_wake; + u64 tx_dropped; + + struct u64_stats_sync syncp; +}; + +struct hinic_txq { + struct net_device *netdev; + struct hinic_sq *sq; + + struct hinic_txq_stats txq_stats; + + int max_sges; + struct hinic_sge *sges; + struct hinic_sge *free_sges; + + char *irq_name; + struct napi_struct napi; +}; + +void hinic_txq_clean_stats(struct hinic_txq *txq); + +void hinic_txq_get_stats(struct hinic_txq *txq, struct hinic_txq_stats *stats); + +netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev); + +int hinic_init_txq(struct hinic_txq *txq, struct hinic_sq *sq, + struct net_device *netdev); + +void hinic_clean_txq(struct hinic_txq *txq); + +#endif diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index b9d310f20bcc..4878b7169e0f 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3102,8 +3102,7 @@ static int ehea_setup_ports(struct ehea_adapter *adapter) dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no", NULL); if (!dn_log_port_id) { - pr_err("bad device node: eth_dn name=%s\n", - eth_dn->full_name); + pr_err("bad device node: eth_dn name=%pOF\n", eth_dn); continue; } @@ -3425,7 +3424,7 @@ static int ehea_probe_adapter(struct platform_device *dev) if (!adapter->handle) { dev_err(&dev->dev, "failed getting handle for adapter" - " '%s'\n", dev->dev.of_node->full_name); + " '%pOF'\n", dev->dev.of_node); ret = -ENODEV; goto out_free_ad; } diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 259e69a52ec5..7feff2450ed6 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -133,8 +133,7 @@ static inline void emac_report_timeout_error(struct emac_instance *dev, EMAC_FTR_440EP_PHY_CLK_FIX)) DBG(dev, "%s" NL, error); else if (net_ratelimit()) - printk(KERN_ERR "%s: %s\n", dev->ofdev->dev.of_node->full_name, - error); + printk(KERN_ERR "%pOF: %s\n", dev->ofdev->dev.of_node, error); } /* EMAC PHY clock workaround: @@ -2258,8 +2257,8 @@ static void emac_ethtool_get_drvinfo(struct net_device *ndev, strlcpy(info->driver, "ibm_emac", sizeof(info->driver)); strlcpy(info->version, DRV_VERSION, sizeof(info->version)); - snprintf(info->bus_info, sizeof(info->bus_info), "PPC 4xx EMAC-%d %s", - dev->cell_index, dev->ofdev->dev.of_node->full_name); + snprintf(info->bus_info, sizeof(info->bus_info), "PPC 4xx EMAC-%d %pOF", + dev->cell_index, dev->ofdev->dev.of_node); } static const struct ethtool_ops emac_ethtool_ops = { @@ -2431,8 +2430,8 @@ static int emac_read_uint_prop(struct device_node *np, const char *name, const u32 *prop = of_get_property(np, name, &len); if (prop == NULL || len < sizeof(u32)) { if (fatal) - printk(KERN_ERR "%s: missing %s property\n", - np->full_name, name); + printk(KERN_ERR "%pOF: missing %s property\n", + np, name); return -ENODEV; } *val = *prop; @@ -2768,7 +2767,7 @@ static int emac_init_phy(struct emac_instance *dev) #endif mutex_unlock(&emac_phy_map_lock); if (i == 0x20) { - printk(KERN_WARNING "%s: can't find PHY!\n", np->full_name); + printk(KERN_WARNING "%pOF: can't find PHY!\n", np); return -ENXIO; } @@ -2894,8 +2893,8 @@ static int emac_init_config(struct emac_instance *dev) #ifdef CONFIG_IBM_EMAC_NO_FLOW_CTRL dev->features |= EMAC_FTR_NO_FLOW_CONTROL_40x; #else - printk(KERN_ERR "%s: Flow control not disabled!\n", - np->full_name); + printk(KERN_ERR "%pOF: Flow control not disabled!\n", + np); return -ENXIO; #endif } @@ -2918,8 +2917,7 @@ static int emac_init_config(struct emac_instance *dev) #ifdef CONFIG_IBM_EMAC_TAH dev->features |= EMAC_FTR_HAS_TAH; #else - printk(KERN_ERR "%s: TAH support not enabled !\n", - np->full_name); + printk(KERN_ERR "%pOF: TAH support not enabled !\n", np); return -ENXIO; #endif } @@ -2928,8 +2926,7 @@ static int emac_init_config(struct emac_instance *dev) #ifdef CONFIG_IBM_EMAC_ZMII dev->features |= EMAC_FTR_HAS_ZMII; #else - printk(KERN_ERR "%s: ZMII support not enabled !\n", - np->full_name); + printk(KERN_ERR "%pOF: ZMII support not enabled !\n", np); return -ENXIO; #endif } @@ -2938,8 +2935,7 @@ static int emac_init_config(struct emac_instance *dev) #ifdef CONFIG_IBM_EMAC_RGMII dev->features |= EMAC_FTR_HAS_RGMII; #else - printk(KERN_ERR "%s: RGMII support not enabled !\n", - np->full_name); + printk(KERN_ERR "%pOF: RGMII support not enabled !\n", np); return -ENXIO; #endif } @@ -2947,8 +2943,8 @@ static int emac_init_config(struct emac_instance *dev) /* Read MAC-address */ p = of_get_property(np, "local-mac-address", NULL); if (p == NULL) { - printk(KERN_ERR "%s: Can't find local-mac-address property\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't find local-mac-address property\n", + np); return -ENXIO; } memcpy(dev->ndev->dev_addr, p, ETH_ALEN); @@ -3036,30 +3032,24 @@ static int emac_probe(struct platform_device *ofdev) /* Init various config data based on device-tree */ err = emac_init_config(dev); - if (err != 0) + if (err) goto err_free; /* Get interrupts. EMAC irq is mandatory, WOL irq is optional */ dev->emac_irq = irq_of_parse_and_map(np, 0); dev->wol_irq = irq_of_parse_and_map(np, 1); if (!dev->emac_irq) { - printk(KERN_ERR "%s: Can't map main interrupt\n", np->full_name); + printk(KERN_ERR "%pOF: Can't map main interrupt\n", np); + err = -ENODEV; goto err_free; } ndev->irq = dev->emac_irq; /* Map EMAC regs */ - if (of_address_to_resource(np, 0, &dev->rsrc_regs)) { - printk(KERN_ERR "%s: Can't get registers address\n", - np->full_name); - goto err_irq_unmap; - } - // TODO : request_mem_region - dev->emacp = ioremap(dev->rsrc_regs.start, - resource_size(&dev->rsrc_regs)); + // TODO : platform_get_resource() and devm_ioremap_resource() + dev->emacp = of_iomap(np, 0); if (dev->emacp == NULL) { - printk(KERN_ERR "%s: Can't map device registers!\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't map device registers!\n", np); err = -ENOMEM; goto err_irq_unmap; } @@ -3068,8 +3058,7 @@ static int emac_probe(struct platform_device *ofdev) err = emac_wait_deps(dev); if (err) { printk(KERN_ERR - "%s: Timeout waiting for dependent devices\n", - np->full_name); + "%pOF: Timeout waiting for dependent devices\n", np); /* display more info about what's missing ? */ goto err_reg_unmap; } @@ -3084,8 +3073,8 @@ static int emac_probe(struct platform_device *ofdev) dev->commac.rx_chan_mask = MAL_CHAN_MASK(dev->mal_rx_chan); err = mal_register_commac(dev->mal, &dev->commac); if (err) { - printk(KERN_ERR "%s: failed to register with mal %s!\n", - np->full_name, dev->mal_dev->dev.of_node->full_name); + printk(KERN_ERR "%pOF: failed to register with mal %pOF!\n", + np, dev->mal_dev->dev.of_node); goto err_rel_deps; } dev->rx_skb_size = emac_rx_skb_size(ndev->mtu); @@ -3161,8 +3150,8 @@ static int emac_probe(struct platform_device *ofdev) err = register_netdev(ndev); if (err) { - printk(KERN_ERR "%s: failed to register net device (%d)!\n", - np->full_name, err); + printk(KERN_ERR "%pOF: failed to register net device (%d)!\n", + np, err); goto err_detach_tah; } @@ -3176,8 +3165,8 @@ static int emac_probe(struct platform_device *ofdev) wake_up_all(&emac_probe_wait); - printk(KERN_INFO "%s: EMAC-%d %s, MAC %pM\n", - ndev->name, dev->cell_index, np->full_name, ndev->dev_addr); + printk(KERN_INFO "%s: EMAC-%d %pOF, MAC %pM\n", + ndev->name, dev->cell_index, np, ndev->dev_addr); if (dev->phy_mode == PHY_MODE_SGMII) printk(KERN_NOTICE "%s: in SGMII mode\n", ndev->name); diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index f10e156641d5..369de2cfb15b 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -167,7 +167,6 @@ struct emac_error_stats { struct emac_instance { struct net_device *ndev; - struct resource rsrc_regs; struct emac_regs __iomem *emacp; struct platform_device *ofdev; struct device_node **blist; /* bootlist entry */ diff --git a/drivers/net/ethernet/ibm/emac/debug.h b/drivers/net/ethernet/ibm/emac/debug.h index 5bdfc174a07e..9d06d3be3161 100644 --- a/drivers/net/ethernet/ibm/emac/debug.h +++ b/drivers/net/ethernet/ibm/emac/debug.h @@ -31,7 +31,7 @@ #endif #define EMAC_DBG(d, name, fmt, arg...) \ - printk(KERN_DEBUG #name "%s: " fmt, d->ofdev->dev.of_node->full_name, ## arg) + printk(KERN_DEBUG #name "%pOF: " fmt, d->ofdev->dev.of_node, ## arg) #if DBG_LEVEL > 0 # define DBG(d,f,x...) EMAC_DBG(d, emac, f, ##x) diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c index 91b1a558f37d..2c74baa2398a 100644 --- a/drivers/net/ethernet/ibm/emac/mal.c +++ b/drivers/net/ethernet/ibm/emac/mal.c @@ -579,8 +579,8 @@ static int mal_probe(struct platform_device *ofdev) mal->features |= (MAL_FTR_CLEAR_ICINTSTAT | MAL_FTR_COMMON_ERR_INT); #else - printk(KERN_ERR "%s: Support for 405EZ not enabled!\n", - ofdev->dev.of_node->full_name); + printk(KERN_ERR "%pOF: Support for 405EZ not enabled!\n", + ofdev->dev.of_node); err = -ENODEV; goto fail; #endif @@ -687,8 +687,8 @@ static int mal_probe(struct platform_device *ofdev) mal_enable_eob_irq(mal); printk(KERN_INFO - "MAL v%d %s, %d TX channels, %d RX channels\n", - mal->version, ofdev->dev.of_node->full_name, + "MAL v%d %pOF, %d TX channels, %d RX channels\n", + mal->version, ofdev->dev.of_node, mal->num_tx_chans, mal->num_rx_chans); /* Advertise this instance to the rest of the world */ diff --git a/drivers/net/ethernet/ibm/emac/rgmii.c b/drivers/net/ethernet/ibm/emac/rgmii.c index 206ccbbae7bb..c4a1ac38bba8 100644 --- a/drivers/net/ethernet/ibm/emac/rgmii.c +++ b/drivers/net/ethernet/ibm/emac/rgmii.c @@ -104,8 +104,8 @@ int rgmii_attach(struct platform_device *ofdev, int input, int mode) /* Check if we need to attach to a RGMII */ if (input < 0 || !rgmii_valid_mode(mode)) { - printk(KERN_ERR "%s: unsupported settings !\n", - ofdev->dev.of_node->full_name); + printk(KERN_ERR "%pOF: unsupported settings !\n", + ofdev->dev.of_node); return -ENODEV; } @@ -114,8 +114,8 @@ int rgmii_attach(struct platform_device *ofdev, int input, int mode) /* Enable this input */ out_be32(&p->fer, in_be32(&p->fer) | rgmii_mode_mask(mode, input)); - printk(KERN_NOTICE "%s: input %d in %s mode\n", - ofdev->dev.of_node->full_name, input, rgmii_mode_name(mode)); + printk(KERN_NOTICE "%pOF: input %d in %s mode\n", + ofdev->dev.of_node, input, rgmii_mode_name(mode)); ++dev->users; @@ -249,8 +249,7 @@ static int rgmii_probe(struct platform_device *ofdev) rc = -ENXIO; if (of_address_to_resource(np, 0, ®s)) { - printk(KERN_ERR "%s: Can't get registers address\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't get registers address\n", np); goto err_free; } @@ -258,8 +257,7 @@ static int rgmii_probe(struct platform_device *ofdev) dev->base = (struct rgmii_regs __iomem *)ioremap(regs.start, sizeof(struct rgmii_regs)); if (dev->base == NULL) { - printk(KERN_ERR "%s: Can't map device registers!\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't map device registers!\n", np); goto err_free; } @@ -278,8 +276,8 @@ static int rgmii_probe(struct platform_device *ofdev) out_be32(&dev->base->fer, 0); printk(KERN_INFO - "RGMII %s initialized with%s MDIO support\n", - ofdev->dev.of_node->full_name, + "RGMII %pOF initialized with%s MDIO support\n", + ofdev->dev.of_node, (dev->flags & EMAC_RGMII_FLAG_HAS_MDIO) ? "" : "out"); wmb(); diff --git a/drivers/net/ethernet/ibm/emac/tah.c b/drivers/net/ethernet/ibm/emac/tah.c index 32cb6c9007c5..9912456dca48 100644 --- a/drivers/net/ethernet/ibm/emac/tah.c +++ b/drivers/net/ethernet/ibm/emac/tah.c @@ -58,8 +58,7 @@ void tah_reset(struct platform_device *ofdev) --n; if (unlikely(!n)) - printk(KERN_ERR "%s: reset timeout\n", - ofdev->dev.of_node->full_name); + printk(KERN_ERR "%pOF: reset timeout\n", ofdev->dev.of_node); /* 10KB TAH TX FIFO accommodates the max MTU of 9000 */ out_be32(&p->mr, @@ -105,8 +104,7 @@ static int tah_probe(struct platform_device *ofdev) rc = -ENXIO; if (of_address_to_resource(np, 0, ®s)) { - printk(KERN_ERR "%s: Can't get registers address\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't get registers address\n", np); goto err_free; } @@ -114,8 +112,7 @@ static int tah_probe(struct platform_device *ofdev) dev->base = (struct tah_regs __iomem *)ioremap(regs.start, sizeof(struct tah_regs)); if (dev->base == NULL) { - printk(KERN_ERR "%s: Can't map device registers!\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't map device registers!\n", np); goto err_free; } @@ -124,8 +121,7 @@ static int tah_probe(struct platform_device *ofdev) /* Initialize TAH and enable IPv4 checksum verification, no TSO yet */ tah_reset(ofdev); - printk(KERN_INFO - "TAH %s initialized\n", ofdev->dev.of_node->full_name); + printk(KERN_INFO "TAH %pOF initialized\n", ofdev->dev.of_node); wmb(); return 0; diff --git a/drivers/net/ethernet/ibm/emac/zmii.c b/drivers/net/ethernet/ibm/emac/zmii.c index 8727b865ea02..89c42d362292 100644 --- a/drivers/net/ethernet/ibm/emac/zmii.c +++ b/drivers/net/ethernet/ibm/emac/zmii.c @@ -121,15 +121,15 @@ int zmii_attach(struct platform_device *ofdev, int input, int *mode) } else dev->mode = *mode; - printk(KERN_NOTICE "%s: bridge in %s mode\n", - ofdev->dev.of_node->full_name, + printk(KERN_NOTICE "%pOF: bridge in %s mode\n", + ofdev->dev.of_node, zmii_mode_name(dev->mode)); } else { /* All inputs must use the same mode */ if (*mode != PHY_MODE_NA && *mode != dev->mode) { printk(KERN_ERR - "%s: invalid mode %d specified for input %d\n", - ofdev->dev.of_node->full_name, *mode, input); + "%pOF: invalid mode %d specified for input %d\n", + ofdev->dev.of_node, *mode, input); mutex_unlock(&dev->lock); return -EINVAL; } @@ -250,8 +250,7 @@ static int zmii_probe(struct platform_device *ofdev) rc = -ENXIO; if (of_address_to_resource(np, 0, ®s)) { - printk(KERN_ERR "%s: Can't get registers address\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't get registers address\n", np); goto err_free; } @@ -259,8 +258,7 @@ static int zmii_probe(struct platform_device *ofdev) dev->base = (struct zmii_regs __iomem *)ioremap(regs.start, sizeof(struct zmii_regs)); if (dev->base == NULL) { - printk(KERN_ERR "%s: Can't map device registers!\n", - np->full_name); + printk(KERN_ERR "%pOF: Can't map device registers!\n", np); goto err_free; } @@ -270,8 +268,7 @@ static int zmii_probe(struct platform_device *ofdev) /* Disable all inputs by default */ out_be32(&dev->base->fer, 0); - printk(KERN_INFO - "ZMII %s initialized\n", ofdev->dev.of_node->full_name); + printk(KERN_INFO "ZMII %pOF initialized\n", ofdev->dev.of_node); wmb(); platform_set_drvdata(ofdev, dev); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index d17c2b03f580..f210398200ec 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1897,7 +1897,7 @@ static int ibmveth_resume(struct device *dev) return 0; } -static struct vio_device_id ibmveth_device_table[] = { +static const struct vio_device_id ibmveth_device_table[] = { { "network", "IBM,l-lan"}, { "", "" } }; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index c45e8e3b82d3..cb8182f4fdfa 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -347,6 +347,31 @@ static void replenish_pools(struct ibmvnic_adapter *adapter) } } +static void release_stats_buffers(struct ibmvnic_adapter *adapter) +{ + kfree(adapter->tx_stats_buffers); + kfree(adapter->rx_stats_buffers); +} + +static int init_stats_buffers(struct ibmvnic_adapter *adapter) +{ + adapter->tx_stats_buffers = + kcalloc(adapter->req_tx_queues, + sizeof(struct ibmvnic_tx_queue_stats), + GFP_KERNEL); + if (!adapter->tx_stats_buffers) + return -ENOMEM; + + adapter->rx_stats_buffers = + kcalloc(adapter->req_rx_queues, + sizeof(struct ibmvnic_rx_queue_stats), + GFP_KERNEL); + if (!adapter->rx_stats_buffers) + return -ENOMEM; + + return 0; +} + static void release_stats_token(struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; @@ -374,6 +399,7 @@ static int init_stats_token(struct ibmvnic_adapter *adapter) } adapter->stats_token = stok; + netdev_dbg(adapter->netdev, "Stats token initialized (%llx)\n", stok); return 0; } @@ -387,6 +413,8 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) for (i = 0; i < rx_scrqs; i++) { rx_pool = &adapter->rx_pool[i]; + netdev_dbg(adapter->netdev, "Re-setting rx_pool[%d]\n", i); + rc = reset_long_term_buff(adapter, &rx_pool->long_term_buff); if (rc) return rc; @@ -419,6 +447,8 @@ static void release_rx_pools(struct ibmvnic_adapter *adapter) for (i = 0; i < rx_scrqs; i++) { rx_pool = &adapter->rx_pool[i]; + netdev_dbg(adapter->netdev, "Releasing rx_pool[%d]\n", i); + kfree(rx_pool->free_map); free_long_term_buff(adapter, &rx_pool->long_term_buff); @@ -465,7 +495,7 @@ static int init_rx_pools(struct net_device *netdev) rx_pool = &adapter->rx_pool[i]; netdev_dbg(adapter->netdev, - "Initializing rx_pool %d, %lld buffs, %lld bytes each\n", + "Initializing rx_pool[%d], %lld buffs, %lld bytes each\n", i, adapter->req_rx_add_entries_per_subcrq, be64_to_cpu(size_array[i])); @@ -515,6 +545,8 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); for (i = 0; i < tx_scrqs; i++) { + netdev_dbg(adapter->netdev, "Re-setting tx_pool[%d]\n", i); + tx_pool = &adapter->tx_pool[i]; rc = reset_long_term_buff(adapter, &tx_pool->long_term_buff); @@ -545,6 +577,7 @@ static void release_tx_pools(struct ibmvnic_adapter *adapter) tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); for (i = 0; i < tx_scrqs; i++) { + netdev_dbg(adapter->netdev, "Releasing tx_pool[%d]\n", i); tx_pool = &adapter->tx_pool[i]; kfree(tx_pool->tx_buff); free_long_term_buff(adapter, &tx_pool->long_term_buff); @@ -571,6 +604,11 @@ static int init_tx_pools(struct net_device *netdev) for (i = 0; i < tx_subcrqs; i++) { tx_pool = &adapter->tx_pool[i]; + + netdev_dbg(adapter->netdev, + "Initializing tx_pool[%d], %lld buffs\n", + i, adapter->req_tx_entries_per_subcrq); + tx_pool->tx_buff = kcalloc(adapter->req_tx_entries_per_subcrq, sizeof(struct ibmvnic_tx_buff), GFP_KERNEL); @@ -641,8 +679,10 @@ static void ibmvnic_napi_disable(struct ibmvnic_adapter *adapter) if (!adapter->napi_enabled) return; - for (i = 0; i < adapter->req_rx_queues; i++) + for (i = 0; i < adapter->req_rx_queues; i++) { + netdev_dbg(adapter->netdev, "Disabling napi[%d]\n", i); napi_disable(&adapter->napi[i]); + } adapter->napi_enabled = false; } @@ -700,12 +740,16 @@ static void release_resources(struct ibmvnic_adapter *adapter) release_rx_pools(adapter); release_stats_token(adapter); + release_stats_buffers(adapter); release_error_buffers(adapter); if (adapter->napi) { for (i = 0; i < adapter->req_rx_queues; i++) { - if (&adapter->napi[i]) + if (&adapter->napi[i]) { + netdev_dbg(adapter->netdev, + "Releasing napi[%d]\n", i); netif_napi_del(&adapter->napi[i]); + } } } } @@ -718,7 +762,8 @@ static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state) bool resend; int rc; - netdev_err(netdev, "setting link state %d\n", link_state); + netdev_dbg(netdev, "setting link state %d\n", link_state); + memset(&crq, 0, sizeof(crq)); crq.logical_link_state.first = IBMVNIC_CRQ_CMD; crq.logical_link_state.cmd = LOGICAL_LINK_STATE; @@ -755,6 +800,9 @@ static int set_real_num_queues(struct net_device *netdev) struct ibmvnic_adapter *adapter = netdev_priv(netdev); int rc; + netdev_dbg(netdev, "Setting real tx/rx queues (%llx/%llx)\n", + adapter->req_tx_queues, adapter->req_rx_queues); + rc = netif_set_real_num_tx_queues(netdev, adapter->req_tx_queues); if (rc) { netdev_err(netdev, "failed to set the number of tx queues\n"); @@ -777,6 +825,10 @@ static int init_resources(struct ibmvnic_adapter *adapter) if (rc) return rc; + rc = init_stats_buffers(adapter); + if (rc) + return rc; + rc = init_stats_token(adapter); if (rc) return rc; @@ -788,6 +840,7 @@ static int init_resources(struct ibmvnic_adapter *adapter) return -ENOMEM; for (i = 0; i < adapter->req_rx_queues; i++) { + netdev_dbg(netdev, "Adding napi[%d]\n", i); netif_napi_add(netdev, &adapter->napi[i], ibmvnic_poll, NAPI_POLL_WEIGHT); } @@ -816,6 +869,7 @@ static int __ibmvnic_open(struct net_device *netdev) * set the logical link state to up */ for (i = 0; i < adapter->req_rx_queues; i++) { + netdev_dbg(netdev, "Enabling rx_scrq[%d] irq\n", i); if (prev_state == VNIC_CLOSED) enable_irq(adapter->rx_scrq[i]->irq); else @@ -823,6 +877,7 @@ static int __ibmvnic_open(struct net_device *netdev) } for (i = 0; i < adapter->req_tx_queues; i++) { + netdev_dbg(netdev, "Enabling tx_scrq[%d] irq\n", i); if (prev_state == VNIC_CLOSED) enable_irq(adapter->tx_scrq[i]->irq); else @@ -896,6 +951,7 @@ static void clean_tx_pools(struct ibmvnic_adapter *adapter) if (!tx_pool) continue; + netdev_dbg(adapter->netdev, "Cleaning tx_pool[%d]\n", i); for (j = 0; j < tx_entries; j++) { if (tx_pool->tx_buff[j].skb) { dev_kfree_skb_any(tx_pool->tx_buff[j].skb); @@ -923,8 +979,11 @@ static int __ibmvnic_close(struct net_device *netdev) if (adapter->tx_scrq) { for (i = 0; i < adapter->req_tx_queues; i++) - if (adapter->tx_scrq[i]->irq) + if (adapter->tx_scrq[i]->irq) { + netdev_dbg(adapter->netdev, + "Disabling tx_scrq[%d] irq\n", i); disable_irq(adapter->tx_scrq[i]->irq); + } } rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_DN); @@ -943,8 +1002,11 @@ static int __ibmvnic_close(struct net_device *netdev) break; } - if (adapter->rx_scrq[i]->irq) + if (adapter->rx_scrq[i]->irq) { + netdev_dbg(adapter->netdev, + "Disabling rx_scrq[%d] irq\n", i); disable_irq(adapter->rx_scrq[i]->irq); + } } } @@ -1259,6 +1321,9 @@ out: netdev->stats.tx_packets += tx_packets; adapter->tx_send_failed += tx_send_failed; adapter->tx_map_failed += tx_map_failed; + adapter->tx_stats_buffers[queue_num].packets += tx_packets; + adapter->tx_stats_buffers[queue_num].bytes += tx_bytes; + adapter->tx_stats_buffers[queue_num].dropped_packets += tx_dropped; return ret; } @@ -1334,6 +1399,9 @@ static int do_reset(struct ibmvnic_adapter *adapter, struct net_device *netdev = adapter->netdev; int i, rc; + netdev_dbg(adapter->netdev, "Re-setting driver (%d)\n", + rwi->reset_reason); + netif_carrier_off(netdev); adapter->reset_reason = rwi->reset_reason; @@ -1458,6 +1526,7 @@ static void __ibmvnic_reset(struct work_struct *work) } if (rc) { + netdev_dbg(adapter->netdev, "Reset failed\n"); free_all_rwi(adapter); mutex_unlock(&adapter->reset_lock); return; @@ -1491,7 +1560,7 @@ static void ibmvnic_reset(struct ibmvnic_adapter *adapter, list_for_each(entry, &adapter->rwi_list) { tmp = list_entry(entry, struct ibmvnic_rwi, list); if (tmp->reset_reason == reason) { - netdev_err(netdev, "Matching reset found, skipping\n"); + netdev_dbg(netdev, "Skipping matching reset\n"); mutex_unlock(&adapter->rwi_lock); return; } @@ -1507,6 +1576,8 @@ static void ibmvnic_reset(struct ibmvnic_adapter *adapter, rwi->reset_reason = reason; list_add_tail(&rwi->list, &adapter->rwi_list); mutex_unlock(&adapter->rwi_lock); + + netdev_dbg(adapter->netdev, "Scheduling reset (reason %d)\n", reason); schedule_work(&adapter->ibmvnic_reset); } @@ -1560,7 +1631,8 @@ restart_poll: rx_comp.correlator); /* do error checking */ if (next->rx_comp.rc) { - netdev_err(netdev, "rx error %x\n", next->rx_comp.rc); + netdev_dbg(netdev, "rx buffer returned with rc %x\n", + be16_to_cpu(next->rx_comp.rc)); /* free the entry */ next->rx_comp.first = 0; remove_buff_from_pool(adapter, rx_buff); @@ -1599,6 +1671,8 @@ restart_poll: napi_gro_receive(napi, skb); /* send it up */ netdev->stats.rx_packets++; netdev->stats.rx_bytes += length; + adapter->rx_stats_buffers[scrq_num].packets++; + adapter->rx_stats_buffers[scrq_num].bytes += length; frames_processed++; } @@ -1708,18 +1782,36 @@ static u32 ibmvnic_get_link(struct net_device *netdev) static void ibmvnic_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) { - ring->rx_max_pending = 0; - ring->tx_max_pending = 0; + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + ring->rx_max_pending = adapter->max_rx_add_entries_per_subcrq; + ring->tx_max_pending = adapter->max_tx_entries_per_subcrq; ring->rx_mini_max_pending = 0; ring->rx_jumbo_max_pending = 0; - ring->rx_pending = 0; - ring->tx_pending = 0; + ring->rx_pending = adapter->req_rx_add_entries_per_subcrq; + ring->tx_pending = adapter->req_tx_entries_per_subcrq; ring->rx_mini_pending = 0; ring->rx_jumbo_pending = 0; } +static void ibmvnic_get_channels(struct net_device *netdev, + struct ethtool_channels *channels) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + + channels->max_rx = adapter->max_rx_queues; + channels->max_tx = adapter->max_tx_queues; + channels->max_other = 0; + channels->max_combined = 0; + channels->rx_count = adapter->req_rx_queues; + channels->tx_count = adapter->req_tx_queues; + channels->other_count = 0; + channels->combined_count = 0; +} + static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) { + struct ibmvnic_adapter *adapter = netdev_priv(dev); int i; if (stringset != ETH_SS_STATS) @@ -1727,13 +1819,39 @@ static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data) for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++, data += ETH_GSTRING_LEN) memcpy(data, ibmvnic_stats[i].name, ETH_GSTRING_LEN); + + for (i = 0; i < adapter->req_tx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "tx%d_packets", i); + data += ETH_GSTRING_LEN; + + snprintf(data, ETH_GSTRING_LEN, "tx%d_bytes", i); + data += ETH_GSTRING_LEN; + + snprintf(data, ETH_GSTRING_LEN, "tx%d_dropped_packets", i); + data += ETH_GSTRING_LEN; + } + + for (i = 0; i < adapter->req_rx_queues; i++) { + snprintf(data, ETH_GSTRING_LEN, "rx%d_packets", i); + data += ETH_GSTRING_LEN; + + snprintf(data, ETH_GSTRING_LEN, "rx%d_bytes", i); + data += ETH_GSTRING_LEN; + + snprintf(data, ETH_GSTRING_LEN, "rx%d_interrupts", i); + data += ETH_GSTRING_LEN; + } } static int ibmvnic_get_sset_count(struct net_device *dev, int sset) { + struct ibmvnic_adapter *adapter = netdev_priv(dev); + switch (sset) { case ETH_SS_STATS: - return ARRAY_SIZE(ibmvnic_stats); + return ARRAY_SIZE(ibmvnic_stats) + + adapter->req_tx_queues * NUM_TX_STATS + + adapter->req_rx_queues * NUM_RX_STATS; default: return -EOPNOTSUPP; } @@ -1744,7 +1862,7 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, { struct ibmvnic_adapter *adapter = netdev_priv(dev); union ibmvnic_crq crq; - int i; + int i, j; memset(&crq, 0, sizeof(crq)); crq.request_statistics.first = IBMVNIC_CRQ_CMD; @@ -1759,7 +1877,26 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev, wait_for_completion(&adapter->stats_done); for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++) - data[i] = IBMVNIC_GET_STAT(adapter, ibmvnic_stats[i].offset); + data[i] = be64_to_cpu(IBMVNIC_GET_STAT(adapter, + ibmvnic_stats[i].offset)); + + for (j = 0; j < adapter->req_tx_queues; j++) { + data[i] = adapter->tx_stats_buffers[j].packets; + i++; + data[i] = adapter->tx_stats_buffers[j].bytes; + i++; + data[i] = adapter->tx_stats_buffers[j].dropped_packets; + i++; + } + + for (j = 0; j < adapter->req_rx_queues; j++) { + data[i] = adapter->rx_stats_buffers[j].packets; + i++; + data[i] = adapter->rx_stats_buffers[j].bytes; + i++; + data[i] = adapter->rx_stats_buffers[j].interrupts; + i++; + } } static const struct ethtool_ops ibmvnic_ethtool_ops = { @@ -1768,6 +1905,7 @@ static const struct ethtool_ops ibmvnic_ethtool_ops = { .set_msglevel = ibmvnic_set_msglevel, .get_link = ibmvnic_get_link, .get_ringparam = ibmvnic_get_ringparam, + .get_channels = ibmvnic_get_channels, .get_strings = ibmvnic_get_strings, .get_sset_count = ibmvnic_get_sset_count, .get_ethtool_stats = ibmvnic_get_ethtool_stats, @@ -1800,12 +1938,14 @@ static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter) int i, rc; for (i = 0; i < adapter->req_tx_queues; i++) { + netdev_dbg(adapter->netdev, "Re-setting tx_scrq[%d]\n", i); rc = reset_one_sub_crq_queue(adapter, adapter->tx_scrq[i]); if (rc) return rc; } for (i = 0; i < adapter->req_rx_queues; i++) { + netdev_dbg(adapter->netdev, "Re-setting rx_scrq[%d]\n", i); rc = reset_one_sub_crq_queue(adapter, adapter->rx_scrq[i]); if (rc) return rc; @@ -1909,6 +2049,8 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) if (!adapter->tx_scrq[i]) continue; + netdev_dbg(adapter->netdev, "Releasing tx_scrq[%d]\n", + i); if (adapter->tx_scrq[i]->irq) { free_irq(adapter->tx_scrq[i]->irq, adapter->tx_scrq[i]); @@ -1928,6 +2070,8 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter) if (!adapter->rx_scrq[i]) continue; + netdev_dbg(adapter->netdev, "Releasing rx_scrq[%d]\n", + i); if (adapter->rx_scrq[i]->irq) { free_irq(adapter->rx_scrq[i]->irq, adapter->rx_scrq[i]); @@ -2064,6 +2208,8 @@ static irqreturn_t ibmvnic_interrupt_rx(int irq, void *instance) struct ibmvnic_sub_crq_queue *scrq = instance; struct ibmvnic_adapter *adapter = scrq->adapter; + adapter->rx_stats_buffers[scrq->scrq_num].interrupts++; + if (napi_schedule_prep(&adapter->napi[scrq->scrq_num])) { disable_scrq_irq(adapter, scrq); __napi_schedule(&adapter->napi[scrq->scrq_num]); @@ -2080,6 +2226,8 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter) int rc = 0; for (i = 0; i < adapter->req_tx_queues; i++) { + netdev_dbg(adapter->netdev, "Initializing tx_scrq[%d] irq\n", + i); scrq = adapter->tx_scrq[i]; scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); @@ -2101,6 +2249,8 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter) } for (i = 0; i < adapter->req_rx_queues; i++) { + netdev_dbg(adapter->netdev, "Initializing rx_scrq[%d] irq\n", + i); scrq = adapter->rx_scrq[i]; scrq->irq = irq_create_mapping(NULL, scrq->hw_irq); if (!scrq->irq) { @@ -3739,31 +3889,35 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) do { rc = ibmvnic_init(adapter); - if (rc && rc != EAGAIN) { - free_netdev(netdev); - return rc; - } + if (rc && rc != EAGAIN) + goto ibmvnic_init_fail; } while (rc == EAGAIN); netdev->mtu = adapter->req_mtu - ETH_HLEN; rc = device_create_file(&dev->dev, &dev_attr_failover); - if (rc) { - free_netdev(netdev); - return rc; - } + if (rc) + goto ibmvnic_init_fail; rc = register_netdev(netdev); if (rc) { dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); - device_remove_file(&dev->dev, &dev_attr_failover); - free_netdev(netdev); - return rc; + goto ibmvnic_register_fail; } dev_info(&dev->dev, "ibmvnic registered\n"); adapter->state = VNIC_PROBED; return 0; + +ibmvnic_register_fail: + device_remove_file(&dev->dev, &dev_attr_failover); + +ibmvnic_init_fail: + release_sub_crqs(adapter); + release_crq_queue(adapter); + free_netdev(netdev); + + return rc; } static int ibmvnic_remove(struct vio_dev *dev) @@ -3859,20 +4013,16 @@ static int ibmvnic_resume(struct device *dev) { struct net_device *netdev = dev_get_drvdata(dev); struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int i; if (adapter->state != VNIC_OPEN) return 0; - /* kick the interrupt handlers just in case we lost an interrupt */ - for (i = 0; i < adapter->req_rx_queues; i++) - ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq, - adapter->rx_scrq[i]); + tasklet_schedule(&adapter->tasklet); return 0; } -static struct vio_device_id ibmvnic_device_table[] = { +static const struct vio_device_id ibmvnic_device_table[] = { {"network", "IBM,vnic"}, {"", "" } }; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 8eff6e15f4bb..d02257ccc377 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -166,6 +166,20 @@ struct ibmvnic_statistics { u8 reserved[72]; } __packed __aligned(8); +#define NUM_TX_STATS 3 +struct ibmvnic_tx_queue_stats { + u64 packets; + u64 bytes; + u64 dropped_packets; +}; + +#define NUM_RX_STATS 3 +struct ibmvnic_rx_queue_stats { + u64 packets; + u64 bytes; + u64 interrupts; +}; + struct ibmvnic_acl_buffer { __be32 len; __be32 version; @@ -956,6 +970,9 @@ struct ibmvnic_adapter { int tx_send_failed; int tx_map_failed; + struct ibmvnic_tx_queue_stats *tx_stats_buffers; + struct ibmvnic_rx_queue_stats *rx_stats_buffers; + int phys_link_state; int logical_link_state; diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 66bd5060a65b..d803b1a12349 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -100,6 +100,10 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_CNP_I219_V6 0x15BE #define E1000_DEV_ID_PCH_CNP_I219_LM7 0x15BB #define E1000_DEV_ID_PCH_CNP_I219_V7 0x15BC +#define E1000_DEV_ID_PCH_ICP_I219_LM8 0x15DF +#define E1000_DEV_ID_PCH_ICP_I219_V8 0x15E0 +#define E1000_DEV_ID_PCH_ICP_I219_LM9 0x15E1 +#define E1000_DEV_ID_PCH_ICP_I219_V9 0x15E2 #define E1000_REVISION_4 4 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 68ea8b4555ab..d6d4ed7acf03 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2437,6 +2437,8 @@ static s32 e1000_hv_phy_workarounds_ich8lan(struct e1000_hw *hw) if (hw->phy.revision < 2) { e1000e_phy_sw_reset(hw); ret_val = e1e_wphy(hw, MII_BMCR, 0x3140); + if (ret_val) + return ret_val; } } diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 2dcb5463d9b8..327dfe5bedc0 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7544,6 +7544,10 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V6), board_pch_cnp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_LM7), board_pch_cnp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CNP_I219_V7), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_LM8), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_V8), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_LM9), board_pch_cnp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ICP_I219_V9), board_pch_cnp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 5e37387c7082..e69d49d91d67 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1265,15 +1265,17 @@ err_queueing_scheme: return err; } -static int __fm10k_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc) +static int __fm10k_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; + struct tc_mqprio_qopt *mqprio = type_data; + + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - return fm10k_setup_tc(dev, tc->mqprio->num_tc); + return fm10k_setup_tc(dev, mqprio->num_tc); } static void fm10k_assign_l2_accel(struct fm10k_intfc *interface, diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index d616f698e155..d0c1bf5441d8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -75,11 +75,11 @@ #define I40E_MIN_VSI_ALLOC 83 /* LAN, ATR, FCOE, 64 VF */ /* max 16 qps */ #define i40e_default_queues_per_vmdq(pf) \ - (((pf)->flags & I40E_FLAG_RSS_AQ_CAPABLE) ? 4 : 1) + (((pf)->hw_features & I40E_HW_RSS_AQ_CAPABLE) ? 4 : 1) #define I40E_DEFAULT_QUEUES_PER_VF 4 #define I40E_DEFAULT_QUEUES_PER_TC 1 /* should be a power of 2 */ #define i40e_pf_get_max_q_per_tc(pf) \ - (((pf)->flags & I40E_FLAG_128_QP_RSS_CAPABLE) ? 128 : 64) + (((pf)->hw_features & I40E_HW_128_QP_RSS_CAPABLE) ? 128 : 64) #define I40E_FDIR_RING 0 #define I40E_FDIR_RING_COUNT 32 #define I40E_MAX_AQ_BUF_SIZE 4096 @@ -401,6 +401,27 @@ struct i40e_pf { struct timer_list service_timer; struct work_struct service_task; + u64 hw_features; +#define I40E_HW_RSS_AQ_CAPABLE BIT_ULL(0) +#define I40E_HW_128_QP_RSS_CAPABLE BIT_ULL(1) +#define I40E_HW_ATR_EVICT_CAPABLE BIT_ULL(2) +#define I40E_HW_WB_ON_ITR_CAPABLE BIT_ULL(3) +#define I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(4) +#define I40E_HW_NO_PCI_LINK_CHECK BIT_ULL(5) +#define I40E_HW_100M_SGMII_CAPABLE BIT_ULL(6) +#define I40E_HW_NO_DCB_SUPPORT BIT_ULL(7) +#define I40E_HW_USE_SET_LLDP_MIB BIT_ULL(8) +#define I40E_HW_GENEVE_OFFLOAD_CAPABLE BIT_ULL(9) +#define I40E_HW_PTP_L4_CAPABLE BIT_ULL(10) +#define I40E_HW_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(11) +#define I40E_HW_MPLS_HDR_OFFLOAD_CAPABLE BIT_ULL(12) +#define I40E_HW_HAVE_CRT_RETIMER BIT_ULL(13) +#define I40E_HW_OUTER_UDP_CSUM_CAPABLE BIT_ULL(14) +#define I40E_HW_PHY_CONTROLS_LEDS BIT_ULL(15) +#define I40E_HW_STOP_FW_LLDP BIT_ULL(16) +#define I40E_HW_PORT_ID_VALID BIT_ULL(17) +#define I40E_HW_RESTART_AUTONEG BIT_ULL(18) + u64 flags; #define I40E_FLAG_RX_CSUM_ENABLED BIT_ULL(1) #define I40E_FLAG_MSI_ENABLED BIT_ULL(2) @@ -420,33 +441,14 @@ struct i40e_pf { #define I40E_FLAG_PTP BIT_ULL(25) #define I40E_FLAG_MFP_ENABLED BIT_ULL(26) #define I40E_FLAG_UDP_FILTER_SYNC BIT_ULL(27) -#define I40E_FLAG_PORT_ID_VALID BIT_ULL(28) #define I40E_FLAG_DCB_CAPABLE BIT_ULL(29) -#define I40E_FLAG_RSS_AQ_CAPABLE BIT_ULL(31) -#define I40E_FLAG_HW_ATR_EVICT_CAPABLE BIT_ULL(32) -#define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE BIT_ULL(33) -#define I40E_FLAG_128_QP_RSS_CAPABLE BIT_ULL(34) -#define I40E_FLAG_WB_ON_ITR_CAPABLE BIT_ULL(35) #define I40E_FLAG_VEB_STATS_ENABLED BIT_ULL(37) -#define I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE BIT_ULL(38) #define I40E_FLAG_LINK_POLLING_ENABLED BIT_ULL(39) #define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40) -#define I40E_FLAG_GENEVE_OFFLOAD_CAPABLE BIT_ULL(41) -#define I40E_FLAG_NO_PCI_LINK_CHECK BIT_ULL(42) -#define I40E_FLAG_100M_SGMII_CAPABLE BIT_ULL(43) -#define I40E_FLAG_RESTART_AUTONEG BIT_ULL(44) -#define I40E_FLAG_NO_DCB_SUPPORT BIT_ULL(45) -#define I40E_FLAG_USE_SET_LLDP_MIB BIT_ULL(46) -#define I40E_FLAG_STOP_FW_LLDP BIT_ULL(47) -#define I40E_FLAG_PHY_CONTROLS_LEDS BIT_ULL(48) -#define I40E_FLAG_PF_MAC BIT_ULL(50) #define I40E_FLAG_TRUE_PROMISC_SUPPORT BIT_ULL(51) -#define I40E_FLAG_HAVE_CRT_RETIMER BIT_ULL(52) -#define I40E_FLAG_PTP_L4_CAPABLE BIT_ULL(53) #define I40E_FLAG_CLIENT_RESET BIT_ULL(54) #define I40E_FLAG_TEMP_LINK_POLLING BIT_ULL(55) #define I40E_FLAG_CLIENT_L2_CHANGE BIT_ULL(56) -#define I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE BIT_ULL(57) #define I40E_FLAG_LEGACY_RX BIT_ULL(58) struct i40e_client_instance *cinst; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 8e082a946411..111426ba5fbc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -328,9 +328,9 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, len = buf_len; /* write the full 16-byte chunks */ if (hw->debug_mask & mask) { - char prefix[20]; + char prefix[27]; - snprintf(prefix, 20, + snprintf(prefix, sizeof(prefix), "i40e %02x:%02x.%x: \t0x", hw->bus.bus_id, hw->bus.device, @@ -2529,6 +2529,10 @@ i40e_status i40e_update_link_info(struct i40e_hw *hw) if (status) return status; + hw->phy.link_info.req_fec_info = + abilities.fec_cfg_curr_mod_ext_info & + (I40E_AQ_REQUEST_FEC_KR | I40E_AQ_REQUEST_FEC_RS); + memcpy(hw->phy.link_info.module_type, &abilities.module_type, sizeof(hw->phy.link_info.module_type)); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 9692a5294fa3..05e89864f781 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -271,7 +271,7 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, *advertising |= ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) *advertising |= ADVERTISED_1000baseT_Full; - if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) { + if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) { *supported |= SUPPORTED_100baseT_Full; *advertising |= ADVERTISED_100baseT_Full; } @@ -340,12 +340,12 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, *advertising |= ADVERTISED_20000baseKR2_Full; } if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KR) { - if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) *supported |= SUPPORTED_10000baseKR_Full | SUPPORTED_Autoneg; *advertising |= ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_10GB) - if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) *advertising |= ADVERTISED_10000baseKR_Full; } if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_KX4) { @@ -356,12 +356,12 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, u32 *supported, *advertising |= ADVERTISED_10000baseKX4_Full; } if (phy_types & I40E_CAP_PHY_TYPE_1000BASE_KX) { - if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) *supported |= SUPPORTED_1000baseKX_Full | SUPPORTED_Autoneg; *advertising |= ADVERTISED_Autoneg; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) - if (!(pf->flags & I40E_FLAG_HAVE_CRT_RETIMER)) + if (!(pf->hw_features & I40E_HW_HAVE_CRT_RETIMER)) *advertising |= ADVERTISED_1000baseKX_Full; } if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR || @@ -474,7 +474,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, SUPPORTED_1000baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB) advertising |= ADVERTISED_1000baseT_Full; - if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) { + if (pf->hw_features & I40E_HW_100M_SGMII_CAPABLE) { supported |= SUPPORTED_100baseT_Full; if (hw_link_info->requested_speeds & I40E_LINK_SPEED_100MB) @@ -1091,7 +1091,7 @@ static void i40e_get_regs(struct net_device *netdev, struct ethtool_regs *regs, struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; u32 *reg_buf = p; - int i, j, ri; + unsigned int i, j, ri; u32 reg; /* Tell ethtool which driver-version-specific regs output we have. @@ -1550,9 +1550,9 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, struct i40e_ring *tx_ring, *rx_ring; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; + unsigned int j; int i = 0; char *p; - int j; struct rtnl_link_stats64 *net_stats = i40e_get_vsi_stats_struct(vsi); unsigned int start; @@ -1637,7 +1637,7 @@ static void i40e_get_strings(struct net_device *netdev, u32 stringset, struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; char *p = (char *)data; - int i; + unsigned int i; switch (stringset) { case ETH_SS_TEST: @@ -1765,7 +1765,7 @@ static int i40e_get_ts_info(struct net_device *dev, BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ); - if (pf->flags & I40E_FLAG_PTP_L4_CAPABLE) + if (pf->hw_features & I40E_HW_PTP_L4_CAPABLE) info->rx_filters |= BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | @@ -2005,7 +2005,7 @@ static int i40e_set_phys_id(struct net_device *netdev, switch (state) { case ETHTOOL_ID_ACTIVE: - if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) { + if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) { pf->led_status = i40e_led_get(hw); } else { i40e_aq_set_phy_debug(hw, I40E_PHY_DEBUG_ALL, NULL); @@ -2015,19 +2015,19 @@ static int i40e_set_phys_id(struct net_device *netdev, } return blink_freq; case ETHTOOL_ID_ON: - if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) + if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) i40e_led_set(hw, 0xf, false); else ret = i40e_led_set_phy(hw, true, pf->led_status, 0); break; case ETHTOOL_ID_OFF: - if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) + if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) i40e_led_set(hw, 0x0, false); else ret = i40e_led_set_phy(hw, false, pf->led_status, 0); break; case ETHTOOL_ID_INACTIVE: - if (!(pf->flags & I40E_FLAG_PHY_CONTROLS_LEDS)) { + if (!(pf->hw_features & I40E_HW_PHY_CONTROLS_LEDS)) { i40e_led_set(hw, pf->led_status, false); } else { ret = i40e_led_set_phy(hw, false, pf->led_status, @@ -2194,14 +2194,29 @@ static int __i40e_set_coalesce(struct net_device *netdev, int queue) { struct i40e_netdev_priv *np = netdev_priv(netdev); + u16 intrl_reg, cur_rx_itr, cur_tx_itr; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u16 intrl_reg; int i; if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) vsi->work_limit = ec->tx_max_coalesced_frames_irq; + if (queue < 0) { + cur_rx_itr = vsi->rx_rings[0]->rx_itr_setting; + cur_tx_itr = vsi->tx_rings[0]->tx_itr_setting; + } else if (queue < vsi->num_queue_pairs) { + cur_rx_itr = vsi->rx_rings[queue]->rx_itr_setting; + cur_tx_itr = vsi->tx_rings[queue]->tx_itr_setting; + } else { + netif_info(pf, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", + vsi->num_queue_pairs - 1); + return -EINVAL; + } + + cur_tx_itr &= ~I40E_ITR_DYNAMIC; + cur_rx_itr &= ~I40E_ITR_DYNAMIC; + /* tx_coalesce_usecs_high is ignored, use rx-usecs-high instead */ if (ec->tx_coalesce_usecs_high != vsi->int_rate_limit) { netif_info(pf, drv, netdev, "tx-usecs-high is not used, please program rx-usecs-high\n"); @@ -2214,15 +2229,34 @@ static int __i40e_set_coalesce(struct net_device *netdev, return -EINVAL; } - if (ec->rx_coalesce_usecs == 0) { - if (ec->use_adaptive_rx_coalesce) - netif_info(pf, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1))) { - netif_info(pf, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); - return -EINVAL; + if (ec->rx_coalesce_usecs != cur_rx_itr && + ec->use_adaptive_rx_coalesce) { + netif_info(pf, drv, netdev, "RX interrupt moderation cannot be changed if adaptive-rx is enabled.\n"); + return -EINVAL; } + if (ec->rx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + netif_info(pf, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); + return -EINVAL; + } + + if (ec->tx_coalesce_usecs != cur_tx_itr && + ec->use_adaptive_tx_coalesce) { + netif_info(pf, drv, netdev, "TX interrupt moderation cannot be changed if adaptive-tx is enabled.\n"); + return -EINVAL; + } + + if (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1)) { + netif_info(pf, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); + return -EINVAL; + } + + if (ec->use_adaptive_rx_coalesce && !cur_rx_itr) + ec->rx_coalesce_usecs = I40E_MIN_ITR << 1; + + if (ec->use_adaptive_tx_coalesce && !cur_tx_itr) + ec->tx_coalesce_usecs = I40E_MIN_ITR << 1; + intrl_reg = i40e_intrl_usec_to_reg(ec->rx_coalesce_usecs_high); vsi->int_rate_limit = INTRL_REG_TO_USEC(intrl_reg); if (vsi->int_rate_limit != ec->rx_coalesce_usecs_high) { @@ -2230,27 +2264,14 @@ static int __i40e_set_coalesce(struct net_device *netdev, vsi->int_rate_limit); } - if (ec->tx_coalesce_usecs == 0) { - if (ec->use_adaptive_tx_coalesce) - netif_info(pf, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < (I40E_MIN_ITR << 1)) || - (ec->tx_coalesce_usecs > (I40E_MAX_ITR << 1))) { - netif_info(pf, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); - return -EINVAL; - } - /* rx and tx usecs has per queue value. If user doesn't specify the queue, * apply to all queues. */ if (queue < 0) { for (i = 0; i < vsi->num_queue_pairs; i++) i40e_set_itr_per_queue(vsi, ec, i); - } else if (queue < vsi->num_queue_pairs) { - i40e_set_itr_per_queue(vsi, ec, queue); } else { - netif_info(pf, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", - vsi->num_queue_pairs - 1); - return -EINVAL; + i40e_set_itr_per_queue(vsi, ec, queue); } return 0; @@ -2727,22 +2748,22 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) switch (nfc->flow_type) { case TCP_V4_FLOW: flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; - if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK); break; case TCP_V6_FLOW: flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_TCP; - if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK); - if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK); break; case UDP_V4_FLOW: flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP; - if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP); @@ -2751,7 +2772,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) break; case UDP_V6_FLOW: flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_UDP; - if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP); @@ -4069,23 +4090,26 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - u64 changed_flags; + u64 orig_flags, new_flags, changed_flags; u32 i, j; - changed_flags = pf->flags; + orig_flags = READ_ONCE(pf->flags); + new_flags = orig_flags; for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) { const struct i40e_priv_flags *priv_flags; priv_flags = &i40e_gstrings_priv_flags[i]; - if (priv_flags->read_only) - continue; - if (flags & BIT(i)) - pf->flags |= priv_flags->flag; + new_flags |= priv_flags->flag; else - pf->flags &= ~(priv_flags->flag); + new_flags &= ~(priv_flags->flag); + + /* If this is a read-only flag, it can't be changed */ + if (priv_flags->read_only && + ((orig_flags ^ new_flags) & ~BIT(i))) + return -EOPNOTSUPP; } if (pf->hw.pf_id != 0) @@ -4096,18 +4120,40 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) priv_flags = &i40e_gl_gstrings_priv_flags[j]; - if (priv_flags->read_only) - continue; - if (flags & BIT(i + j)) - pf->flags |= priv_flags->flag; + new_flags |= priv_flags->flag; else - pf->flags &= ~(priv_flags->flag); + new_flags &= ~(priv_flags->flag); + + /* If this is a read-only flag, it can't be changed */ + if (priv_flags->read_only && + ((orig_flags ^ new_flags) & ~BIT(i))) + return -EOPNOTSUPP; } flags_complete: - /* check for flags that changed */ - changed_flags ^= pf->flags; + /* Before we finalize any flag changes, we need to perform some + * checks to ensure that the changes are supported and safe. + */ + + /* ATR eviction is not supported on all devices */ + if ((new_flags & I40E_FLAG_HW_ATR_EVICT_ENABLED) && + !(pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE)) + return -EOPNOTSUPP; + + /* Compare and exchange the new flags into place. If we failed, that + * is if cmpxchg64 returns anything but the old value, this means that + * something else has modified the flags variable since we copied it + * originally. We'll just punt with an error and log something in the + * message buffer. + */ + if (cmpxchg64(&pf->flags, orig_flags, new_flags) != orig_flags) { + dev_warn(&pf->pdev->dev, + "Unable to update pf->flags as it was modified by another thread...\n"); + return -EAGAIN; + } + + changed_flags = orig_flags ^ new_flags; /* Process any additional changes needed as a result of flag changes. * The changed_flags value reflects the list of bits that were @@ -4121,10 +4167,6 @@ flags_complete: set_bit(__I40E_FD_FLUSH_REQUESTED, pf->state); } - /* Only allow ATR evict on hardware that is capable of handling it */ - if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) - pf->flags &= ~I40E_FLAG_HW_ATR_EVICT_ENABLED; - if (changed_flags & I40E_FLAG_TRUE_PROMISC_SUPPORT) { u16 sw_flags = 0, valid_flags = 0; int ret; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2db93d3f6d23..6498da8806cb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2595,9 +2595,20 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, u16 vid) { int err; - if (!vid || vsi->info.pvid) + if (vsi->info.pvid) return -EINVAL; + /* The network stack will attempt to add VID=0, with the intention to + * receive priority tagged packets with a VLAN of 0. Our HW receives + * these packets by default when configured to receive untagged + * packets, so we don't need to add a filter for this case. + * Additionally, HW interprets adding a VID=0 filter as meaning to + * receive *only* tagged traffic and stops receiving untagged traffic. + * Thus, we do not want to actually add a filter for VID=0 + */ + if (!vid) + return 0; + /* Locked once because all functions invoked below iterates list*/ spin_lock_bh(&vsi->mac_filter_hash_lock); err = i40e_add_vlan_all_mac(vsi, vid); @@ -2674,15 +2685,7 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev, if (vid >= VLAN_N_VID) return -EINVAL; - /* If the network stack called us with vid = 0 then - * it is asking to receive priority tagged packets with - * vlan id 0. Our HW receives them by default when configured - * to receive untagged packets so there is no need to add an - * extra filter for vlan 0 tagged packets. - */ - if (vid) - ret = i40e_vsi_add_vlan(vsi, vid); - + ret = i40e_vsi_add_vlan(vsi, vid); if (!ret) set_bit(vid, vsi->active_vlans); @@ -2714,44 +2717,6 @@ static int i40e_vlan_rx_kill_vid(struct net_device *netdev, } /** - * i40e_macaddr_init - explicitly write the mac address filters - * - * @vsi: pointer to the vsi - * @macaddr: the MAC address - * - * This is needed when the macaddr has been obtained by other - * means than the default, e.g., from Open Firmware or IDPROM. - * Returns 0 on success, negative on failure - **/ -static int i40e_macaddr_init(struct i40e_vsi *vsi, u8 *macaddr) -{ - int ret; - struct i40e_aqc_add_macvlan_element_data element; - - ret = i40e_aq_mac_address_write(&vsi->back->hw, - I40E_AQC_WRITE_TYPE_LAA_WOL, - macaddr, NULL); - if (ret) { - dev_info(&vsi->back->pdev->dev, - "Addr change for VSI failed: %d\n", ret); - return -EADDRNOTAVAIL; - } - - memset(&element, 0, sizeof(element)); - ether_addr_copy(element.mac_addr, macaddr); - element.flags = cpu_to_le16(I40E_AQC_MACVLAN_ADD_PERFECT_MATCH); - ret = i40e_aq_add_macvlan(&vsi->back->hw, vsi->seid, &element, 1, NULL); - if (ret) { - dev_info(&vsi->back->pdev->dev, - "add filter failed err %s aq_err %s\n", - i40e_stat_str(&vsi->back->hw, ret), - i40e_aq_str(&vsi->back->hw, - vsi->back->hw.aq.asq_last_status)); - } - return ret; -} - -/** * i40e_restore_vlan - Reinstate vlans when vsi/netdev comes back up * @vsi: the vsi being brought back up **/ @@ -2909,22 +2874,15 @@ static void i40e_vsi_free_rx_resources(struct i40e_vsi *vsi) static void i40e_config_xps_tx_ring(struct i40e_ring *ring) { struct i40e_vsi *vsi = ring->vsi; - cpumask_var_t mask; if (!ring->q_vector || !ring->netdev) return; - /* Single TC mode enable XPS */ - if (vsi->tc_config.numtc <= 1) { - if (!test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) - netif_set_xps_queue(ring->netdev, - &ring->q_vector->affinity_mask, - ring->queue_index); - } else if (alloc_cpumask_var(&mask, GFP_KERNEL)) { - /* Disable XPS to allow selection based on TC */ - bitmap_zero(cpumask_bits(mask), nr_cpumask_bits); - netif_set_xps_queue(ring->netdev, mask, ring->queue_index); - free_cpumask_var(mask); + if ((vsi->tc_config.numtc <= 1) && + !test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) { + netif_set_xps_queue(ring->netdev, + get_cpu_mask(ring->q_vector->v_idx), + ring->queue_index); } /* schedule our worker thread which will take care of @@ -3203,19 +3161,8 @@ static void i40e_vsi_config_dcb_rings(struct i40e_vsi *vsi) **/ static void i40e_set_vsi_rx_mode(struct i40e_vsi *vsi) { - struct i40e_pf *pf = vsi->back; - int err; - if (vsi->netdev) i40e_set_rx_mode(vsi->netdev); - - if (!!(pf->flags & I40E_FLAG_PF_MAC)) { - err = i40e_macaddr_init(vsi, pf->hw.mac.addr); - if (err) { - dev_warn(&pf->pdev->dev, - "could not set up macaddr; err %d\n", err); - } - } } /** @@ -3495,7 +3442,7 @@ static void i40e_irq_affinity_notify(struct irq_affinity_notify *notify, struct i40e_q_vector *q_vector = container_of(notify, struct i40e_q_vector, affinity_notify); - q_vector->affinity_mask = *mask; + cpumask_copy(&q_vector->affinity_mask, mask); } /** @@ -3559,8 +3506,10 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) q_vector->affinity_notify.notify = i40e_irq_affinity_notify; q_vector->affinity_notify.release = i40e_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* assign the mask for this irq */ - irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); + /* get_cpu_mask returns a static constant mask with + * a permanent lifetime so it's ok to use here. + */ + irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); } vsi->irqs_ready = true; @@ -4342,7 +4291,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi) /* clear the affinity notifier in the IRQ descriptor */ irq_set_affinity_notifier(irq_num, NULL); - /* clear the affinity_mask in the IRQ descriptor */ + /* remove our suggested affinity mask for this IRQ */ irq_set_affinity_hint(irq_num, NULL); synchronize_irq(irq_num); free_irq(irq_num, vsi->q_vectors[i]); @@ -4773,7 +4722,7 @@ static void i40e_detect_recover_hung(struct i40e_pf *pf) { struct net_device *netdev; struct i40e_vsi *vsi; - int i; + unsigned int i; /* Only for LAN VSI */ vsi = pf->vsi[pf->lan_vsi]; @@ -5350,7 +5299,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) int err = 0; /* Do not enable DCB for SW1 and SW2 images even if the FW is capable */ - if (pf->flags & I40E_FLAG_NO_DCB_SUPPORT) + if (pf->hw_features & I40E_HW_NO_DCB_SUPPORT) goto out; /* Get the initial DCB configuration */ @@ -5400,6 +5349,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) char *speed = "Unknown"; char *fc = "Unknown"; char *fec = ""; + char *req_fec = ""; char *an = ""; new_speed = vsi->back->hw.phy.link_info.link_speed; @@ -5461,6 +5411,7 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) } if (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) { + req_fec = ", Requested FEC: None"; fec = ", FEC: None"; an = ", Autoneg: False"; @@ -5473,10 +5424,22 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) else if (vsi->back->hw.phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_RS_ENA) fec = ", FEC: CL108 RS-FEC"; + + /* 'CL108 RS-FEC' should be displayed when RS is requested, or + * both RS and FC are requested + */ + if (vsi->back->hw.phy.link_info.req_fec_info & + (I40E_AQ_REQUEST_FEC_KR | I40E_AQ_REQUEST_FEC_RS)) { + if (vsi->back->hw.phy.link_info.req_fec_info & + I40E_AQ_REQUEST_FEC_RS) + req_fec = ", Requested FEC: CL108 RS-FEC"; + else + req_fec = ", Requested FEC: CL74 FC-FEC/BASE-R"; + } } - netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex%s%s, Flow Control: %s\n", - speed, fec, an, fc); + netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex%s%s%s, Flow Control: %s\n", + speed, req_fec, fec, an, fc); } /** @@ -5656,16 +5619,17 @@ exit: return ret; } -static int __i40e_setup_tc(struct net_device *netdev, u32 handle, - u32 chain_index, __be16 proto, - struct tc_to_netdev *tc) +static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) { - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; + struct tc_mqprio_qopt *mqprio = type_data; - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - return i40e_setup_tc(netdev, tc->mqprio->num_tc); + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + + return i40e_setup_tc(netdev, mqprio->num_tc); } /** @@ -7331,7 +7295,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) wr32(hw, I40E_REG_MSS, val); } - if (pf->flags & I40E_FLAG_RESTART_AUTONEG) { + if (pf->hw_features & I40E_HW_RESTART_AUTONEG) { msleep(75); ret = i40e_aq_set_link_restart_an(&pf->hw, true, NULL); if (ret) @@ -7520,6 +7484,18 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) i40e_flush(hw); } +static const char *i40e_tunnel_name(struct i40e_udp_port_config *port) +{ + switch (port->type) { + case UDP_TUNNEL_TYPE_VXLAN: + return "vxlan"; + case UDP_TUNNEL_TYPE_GENEVE: + return "geneve"; + default: + return "unknown"; + } +} + /** * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters * @pf: board private structure @@ -7565,14 +7541,14 @@ static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) ret = i40e_aq_del_udp_tunnel(hw, i, NULL); if (ret) { - dev_dbg(&pf->pdev->dev, - "%s %s port %d, index %d failed, err %s aq_err %s\n", - pf->udp_ports[i].type ? "vxlan" : "geneve", - port ? "add" : "delete", - port, i, - i40e_stat_str(&pf->hw, ret), - i40e_aq_str(&pf->hw, - pf->hw.aq.asq_last_status)); + dev_info(&pf->pdev->dev, + "%s %s port %d, index %d failed, err %s aq_err %s\n", + i40e_tunnel_name(&pf->udp_ports[i]), + port ? "add" : "delete", + port, i, + i40e_stat_str(&pf->hw, ret), + i40e_aq_str(&pf->hw, + pf->hw.aq.asq_last_status)); pf->udp_ports[i].port = 0; } } @@ -7957,7 +7933,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) ring->count = vsi->num_desc; ring->size = 0; ring->dcb_tc = 0; - if (vsi->back->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) + if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; ring->tx_itr_setting = pf->tx_itr_default; vsi->tx_rings[i] = ring++; @@ -7974,7 +7950,7 @@ static int i40e_alloc_rings(struct i40e_vsi *vsi) ring->count = vsi->num_desc; ring->size = 0; ring->dcb_tc = 0; - if (vsi->back->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) + if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) ring->flags = I40E_TXR_FLAGS_WB_ON_ITR; set_ring_xdp(ring); ring->tx_itr_setting = pf->tx_itr_default; @@ -8261,7 +8237,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu) q_vector->vsi = vsi; q_vector->v_idx = v_idx; - cpumask_set_cpu(cpu, &q_vector->affinity_mask); + cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); if (vsi->netdev) netif_napi_add(vsi->netdev, &q_vector->napi, @@ -8510,7 +8486,7 @@ static int i40e_vsi_config_rss(struct i40e_vsi *vsi) u8 *lut; int ret; - if (!(pf->flags & I40E_FLAG_RSS_AQ_CAPABLE)) + if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE)) return 0; if (!vsi->rss_size) @@ -8640,7 +8616,7 @@ int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) { struct i40e_pf *pf = vsi->back; - if (pf->flags & I40E_FLAG_RSS_AQ_CAPABLE) + if (pf->hw_features & I40E_HW_RSS_AQ_CAPABLE) return i40e_config_rss_aq(vsi, seed, lut, lut_size); else return i40e_config_rss_reg(vsi, seed, lut, lut_size); @@ -8659,7 +8635,7 @@ int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) { struct i40e_pf *pf = vsi->back; - if (pf->flags & I40E_FLAG_RSS_AQ_CAPABLE) + if (pf->hw_features & I40E_HW_RSS_AQ_CAPABLE) return i40e_get_rss_aq(vsi, seed, lut, lut_size); else return i40e_get_rss_reg(vsi, seed, lut, lut_size); @@ -8987,25 +8963,56 @@ static int i40e_sw_init(struct i40e_pf *pf) pf->hw.func_caps.fd_filters_best_effort; } + if (pf->hw.mac.type == I40E_MAC_X722) { + pf->hw_features |= (I40E_HW_RSS_AQ_CAPABLE | + I40E_HW_128_QP_RSS_CAPABLE | + I40E_HW_ATR_EVICT_CAPABLE | + I40E_HW_WB_ON_ITR_CAPABLE | + I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE | + I40E_HW_NO_PCI_LINK_CHECK | + I40E_HW_USE_SET_LLDP_MIB | + I40E_HW_GENEVE_OFFLOAD_CAPABLE | + I40E_HW_PTP_L4_CAPABLE | + I40E_HW_WOL_MC_MAGIC_PKT_WAKE | + I40E_HW_OUTER_UDP_CSUM_CAPABLE); + +#define I40E_FDEVICT_PCTYPE_DEFAULT 0xc03 + if (rd32(&pf->hw, I40E_GLQF_FDEVICTENA(1)) != + I40E_FDEVICT_PCTYPE_DEFAULT) { + dev_warn(&pf->pdev->dev, + "FD EVICT PCTYPES are not right, disable FD HW EVICT\n"); + pf->hw_features &= ~I40E_HW_ATR_EVICT_CAPABLE; + } + } else if ((pf->hw.aq.api_maj_ver > 1) || + ((pf->hw.aq.api_maj_ver == 1) && + (pf->hw.aq.api_min_ver > 4))) { + /* Supported in FW API version higher than 1.4 */ + pf->hw_features |= I40E_HW_GENEVE_OFFLOAD_CAPABLE; + } + + /* Enable HW ATR eviction if possible */ + if (pf->hw_features & I40E_HW_ATR_EVICT_CAPABLE) + pf->flags |= I40E_FLAG_HW_ATR_EVICT_ENABLED; + if ((pf->hw.mac.type == I40E_MAC_XL710) && (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) || (pf->hw.aq.fw_maj_ver < 4))) { - pf->flags |= I40E_FLAG_RESTART_AUTONEG; + pf->hw_features |= I40E_HW_RESTART_AUTONEG; /* No DCB support for FW < v4.33 */ - pf->flags |= I40E_FLAG_NO_DCB_SUPPORT; + pf->hw_features |= I40E_HW_NO_DCB_SUPPORT; } /* Disable FW LLDP if FW < v4.3 */ if ((pf->hw.mac.type == I40E_MAC_XL710) && (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) || (pf->hw.aq.fw_maj_ver < 4))) - pf->flags |= I40E_FLAG_STOP_FW_LLDP; + pf->hw_features |= I40E_HW_STOP_FW_LLDP; /* Use the FW Set LLDP MIB API if FW > v4.40 */ if ((pf->hw.mac.type == I40E_MAC_XL710) && (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver >= 40)) || (pf->hw.aq.fw_maj_ver >= 5))) - pf->flags |= I40E_FLAG_USE_SET_LLDP_MIB; + pf->hw_features |= I40E_HW_USE_SET_LLDP_MIB; if (pf->hw.func_caps.vmdq) { pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI; @@ -9028,29 +9035,6 @@ static int i40e_sw_init(struct i40e_pf *pf) I40E_MAX_VF_COUNT); } #endif /* CONFIG_PCI_IOV */ - if (pf->hw.mac.type == I40E_MAC_X722) { - pf->flags |= I40E_FLAG_RSS_AQ_CAPABLE - | I40E_FLAG_128_QP_RSS_CAPABLE - | I40E_FLAG_HW_ATR_EVICT_CAPABLE - | I40E_FLAG_OUTER_UDP_CSUM_CAPABLE - | I40E_FLAG_WB_ON_ITR_CAPABLE - | I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE - | I40E_FLAG_NO_PCI_LINK_CHECK - | I40E_FLAG_USE_SET_LLDP_MIB - | I40E_FLAG_GENEVE_OFFLOAD_CAPABLE - | I40E_FLAG_PTP_L4_CAPABLE - | I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE; - } else if ((pf->hw.aq.api_maj_ver > 1) || - ((pf->hw.aq.api_maj_ver == 1) && - (pf->hw.aq.api_min_ver > 4))) { - /* Supported in FW API version higher than 1.4 */ - pf->flags |= I40E_FLAG_GENEVE_OFFLOAD_CAPABLE; - } - - /* Enable HW ATR eviction if possible */ - if (pf->flags & I40E_FLAG_HW_ATR_EVICT_CAPABLE) - pf->flags |= I40E_FLAG_HW_ATR_EVICT_ENABLED; - pf->eeprom_version = 0xDEAD; pf->lan_veb = I40E_NO_VEB; pf->lan_vsi = I40E_NO_VSI; @@ -9231,7 +9215,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN; break; case UDP_TUNNEL_TYPE_GENEVE: - if (!(pf->flags & I40E_FLAG_GENEVE_OFFLOAD_CAPABLE)) + if (!(pf->hw_features & I40E_HW_GENEVE_OFFLOAD_CAPABLE)) return; pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE; break; @@ -9298,7 +9282,7 @@ static int i40e_get_phys_port_id(struct net_device *netdev, struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; - if (!(pf->flags & I40E_FLAG_PORT_ID_VALID)) + if (!(pf->hw_features & I40E_HW_PORT_ID_VALID)) return -EOPNOTSUPP; ppid->id_len = min_t(int, sizeof(hw->mac.port_addr), sizeof(ppid->id)); @@ -9589,6 +9573,7 @@ static int i40e_xdp(struct net_device *dev, return i40e_xdp_setup(vsi, xdp->prog); case XDP_QUERY_PROG: xdp->prog_attached = i40e_enabled_xdp_vsi(vsi); + xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0; return 0; default: return -EINVAL; @@ -9675,7 +9660,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETIF_F_RXCSUM | 0; - if (!(pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE)) + if (!(pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE)) netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM; @@ -9714,8 +9699,13 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) i40e_add_mac_filter(vsi, mac_addr); spin_unlock_bh(&vsi->mac_filter_hash_lock); } else { - /* relate the VSI_VMDQ name to the VSI_MAIN name */ - snprintf(netdev->name, IFNAMSIZ, "%sv%%d", + /* Relate the VSI_VMDQ name to the VSI_MAIN name. Note that we + * are still limited by IFNAMSIZ, but we're adding 'v%d\0' to + * the end, which is 4 bytes long, so force truncation of the + * original name by IFNAMSIZ - 4 + */ + snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d", + IFNAMSIZ - 4, pf->vsi[pf->lan_vsi]->netdev->name); random_ether_addr(mac_addr); @@ -9756,8 +9746,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) /* MTU range: 68 - 9706 */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = I40E_MAX_RXBUFFER - - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); + netdev->max_mtu = I40E_MAX_RXBUFFER - I40E_PACKET_HDR_PAD; return 0; } @@ -9890,13 +9879,15 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) */ ret = i40e_vsi_config_tc(vsi, enabled_tc); if (ret) { + /* Single TC condition is not fatal, + * message and continue + */ dev_info(&pf->pdev->dev, "failed to configure TCs for main VSI tc_map 0x%08x, err %s aq_err %s\n", enabled_tc, i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - ret = -ENOENT; } } break; @@ -10387,17 +10378,6 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, switch (vsi->type) { /* setup the netdev if needed */ case I40E_VSI_MAIN: - /* Apply relevant filters if a platform-specific mac - * address was selected. - */ - if (!!(pf->flags & I40E_FLAG_PF_MAC)) { - ret = i40e_macaddr_init(vsi, pf->hw.mac.addr); - if (ret) { - dev_warn(&pf->pdev->dev, - "could not set up macaddr; err %d\n", - ret); - } - } case I40E_VSI_VMDQ2: ret = i40e_config_netdev(vsi); if (ret) @@ -10434,7 +10414,7 @@ struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, break; } - if ((pf->flags & I40E_FLAG_RSS_AQ_CAPABLE) && + if ((pf->hw_features & I40E_HW_RSS_AQ_CAPABLE) && (vsi->type == I40E_VSI_VMDQ2)) { ret = i40e_vsi_config_rss(vsi); } @@ -11443,7 +11423,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * Ignore error return codes because if it was already disabled via * hardware settings this will fail */ - if (pf->flags & I40E_FLAG_STOP_FW_LLDP) { + if (pf->hw_features & I40E_HW_STOP_FW_LLDP) { dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n"); i40e_aq_stop_lldp(hw, true, NULL); } @@ -11460,7 +11440,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ether_addr_copy(hw->mac.perm_addr, hw->mac.addr); i40e_get_port_mac_addr(hw, hw->mac.port_addr); if (is_valid_ether_addr(hw->mac.port_addr)) - pf->flags |= I40E_FLAG_PORT_ID_VALID; + pf->hw_features |= I40E_HW_PORT_ID_VALID; pci_set_drvdata(pdev, pf); pci_save_state(pdev); @@ -11576,7 +11556,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) wr32(hw, I40E_REG_MSS, val); } - if (pf->flags & I40E_FLAG_RESTART_AUTONEG) { + if (pf->hw_features & I40E_HW_RESTART_AUTONEG) { msleep(75); err = i40e_aq_set_link_restart_an(&pf->hw, true, NULL); if (err) @@ -11663,7 +11643,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * and will report PCI Gen 1 x 1 by default so don't bother * checking them. */ - if (!(pf->flags & I40E_FLAG_NO_PCI_LINK_CHECK)) { + if (!(pf->hw_features & I40E_HW_NO_PCI_LINK_CHECK)) { char speed[PCI_SPEED_SIZE] = "Unknown"; char width[PCI_WIDTH_SIZE] = "Unknown"; @@ -11734,9 +11714,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if ((pf->hw.device_id == I40E_DEV_ID_10G_BASE_T) || (pf->hw.device_id == I40E_DEV_ID_10G_BASE_T4)) - pf->flags |= I40E_FLAG_PHY_CONTROLS_LEDS; + pf->hw_features |= I40E_HW_PHY_CONTROLS_LEDS; if (pf->hw.device_id == I40E_DEV_ID_SFP_I_X722) - pf->flags |= I40E_FLAG_HAVE_CRT_RETIMER; + pf->hw_features |= I40E_HW_HAVE_CRT_RETIMER; /* print a string summarizing features */ i40e_print_features(pf); @@ -12048,7 +12028,7 @@ static void i40e_shutdown(struct pci_dev *pdev) */ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], false); - if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE)) + if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); i40e_prep_for_reset(pf, false); @@ -12080,7 +12060,7 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); - if (pf->wol_en && (pf->flags & I40E_FLAG_WOL_MC_MAGIC_PKT_WAKE)) + if (pf->wol_en && (pf->hw_features & I40E_HW_WOL_MC_MAGIC_PKT_WAKE)) i40e_enable_mc_magic_wake(pf); i40e_prep_for_reset(pf, false); @@ -12089,7 +12069,10 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); i40e_stop_misc_vector(pf); - + if (pf->msix_entries) { + synchronize_irq(pf->msix_entries[0].vector); + free_irq(pf->msix_entries[0].vector, pf); + } retval = pci_save_state(pdev); if (retval) return retval; @@ -12129,6 +12112,15 @@ static int i40e_resume(struct pci_dev *pdev) /* handling the reset will rebuild the device state */ if (test_and_clear_bit(__I40E_SUSPENDED, pf->state)) { clear_bit(__I40E_DOWN, pf->state); + if (pf->msix_entries) { + err = request_irq(pf->msix_entries[0].vector, + i40e_intr, 0, pf->int_name, pf); + if (err) { + dev_err(&pf->pdev->dev, + "request_irq for %s failed: %d\n", + pf->int_name, err); + } + } i40e_reset_and_rebuild(pf, false, false); } @@ -12168,12 +12160,14 @@ static int __init i40e_init_module(void) i40e_driver_string, i40e_driver_version_str); pr_info("%s: %s\n", i40e_driver_name, i40e_copyright); - /* we will see if single thread per module is enough for now, - * it can't be any worse than using the system workqueue which - * was already single threaded + /* There is no need to throttle the number of active tasks because + * each device limits its own task using a state bit for scheduling + * the service task, and the device tasks do not interfere with each + * other, so we don't set a max task limit. We must set WQ_MEM_RECLAIM + * since we need to be able to guarantee forward progress even under + * memory pressure. */ - i40e_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, - i40e_driver_name); + i40e_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, i40e_driver_name); if (!i40e_wq) { pr_err("%s: Failed to create workqueue\n", i40e_driver_name); return -ENOMEM; diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 800bd55d0159..57505b1df98d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -134,8 +134,25 @@ i40e_i40e_acquire_nvm_exit: **/ void i40e_release_nvm(struct i40e_hw *hw) { - if (!hw->nvm.blank_nvm_mode) - i40e_aq_release_resource(hw, I40E_NVM_RESOURCE_ID, 0, NULL); + i40e_status ret_code = I40E_SUCCESS; + u32 total_delay = 0; + + if (hw->nvm.blank_nvm_mode) + return; + + ret_code = i40e_aq_release_resource(hw, I40E_NVM_RESOURCE_ID, 0, NULL); + + /* there are some rare cases when trying to release the resource + * results in an admin Q timeout, so handle them correctly + */ + while ((ret_code == I40E_ERR_ADMIN_QUEUE_TIMEOUT) && + (total_delay < hw->aq.asq_cmd_timeout)) { + usleep_range(1000, 2000); + ret_code = i40e_aq_release_resource(hw, + I40E_NVM_RESOURCE_ID, + 0, NULL); + total_delay++; + } } /** @@ -230,6 +247,7 @@ static i40e_status i40e_read_nvm_aq(struct i40e_hw *hw, u8 module_pointer, struct i40e_asq_cmd_details cmd_details; memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; /* Here we are checking the SR limit only for the flat memory model. * We cannot do it for the module-based model, as we did not acquire @@ -266,7 +284,7 @@ static i40e_status i40e_read_nvm_aq(struct i40e_hw *hw, u8 module_pointer, * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF) * @data: word read from the Shadow RAM * - * Reads one 16 bit word from the Shadow RAM using the GLNVM_SRCTL register. + * Reads one 16 bit word from the Shadow RAM using the AdminQ **/ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, u16 *data) @@ -280,27 +298,49 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, } /** - * i40e_read_nvm_word - Reads Shadow RAM + * __i40e_read_nvm_word - Reads nvm word, assumes called does the locking * @hw: pointer to the HW structure * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF) * @data: word read from the Shadow RAM * - * Reads one 16 bit word from the Shadow RAM using the GLNVM_SRCTL register. + * Reads one 16 bit word from the Shadow RAM. + * + * Do not use this function except in cases where the nvm lock is already + * taken via i40e_acquire_nvm(). + **/ +static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, + u16 offset, u16 *data) +{ + i40e_status ret_code = 0; + + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) + ret_code = i40e_read_nvm_word_aq(hw, offset, data); + else + ret_code = i40e_read_nvm_word_srctl(hw, offset, data); + return ret_code; +} + +/** + * i40e_read_nvm_word - Reads nvm word and acquire lock if necessary + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF) + * @data: word read from the Shadow RAM + * + * Reads one 16 bit word from the Shadow RAM. **/ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) { - enum i40e_status_code ret_code = 0; + i40e_status ret_code = 0; ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); - if (!ret_code) { - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { - ret_code = i40e_read_nvm_word_aq(hw, offset, data); - } else { - ret_code = i40e_read_nvm_word_srctl(hw, offset, data); - } - i40e_release_nvm(hw); - } + if (ret_code) + return ret_code; + + ret_code = __i40e_read_nvm_word(hw, offset, data); + + i40e_release_nvm(hw); + return ret_code; } @@ -393,31 +433,25 @@ read_nvm_buffer_aq_exit: } /** - * i40e_read_nvm_buffer - Reads Shadow RAM buffer + * __i40e_read_nvm_buffer - Reads nvm buffer, caller must acquire lock * @hw: pointer to the HW structure * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF). * @words: (in) number of words to read; (out) number of words actually read * @data: words read from the Shadow RAM * * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd() - * method. The buffer read is preceded by the NVM ownership take - * and followed by the release. + * method. **/ -i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, - u16 *words, u16 *data) +static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw, + u16 offset, u16 *words, + u16 *data) { - enum i40e_status_code ret_code = 0; + i40e_status ret_code = 0; - if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { - ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); - if (!ret_code) { - ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, - data); - i40e_release_nvm(hw); - } - } else { + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) + ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, data); + else ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data); - } return ret_code; } @@ -499,15 +533,15 @@ static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw, data = (u16 *)vmem.va; /* read pointer to VPD area */ - ret_code = i40e_read_nvm_word(hw, I40E_SR_VPD_PTR, &vpd_module); + ret_code = __i40e_read_nvm_word(hw, I40E_SR_VPD_PTR, &vpd_module); if (ret_code) { ret_code = I40E_ERR_NVM_CHECKSUM; goto i40e_calc_nvm_checksum_exit; } /* read pointer to PCIe Alt Auto-load module */ - ret_code = i40e_read_nvm_word(hw, I40E_SR_PCIE_ALT_AUTO_LOAD_PTR, - &pcie_alt_module); + ret_code = __i40e_read_nvm_word(hw, I40E_SR_PCIE_ALT_AUTO_LOAD_PTR, + &pcie_alt_module); if (ret_code) { ret_code = I40E_ERR_NVM_CHECKSUM; goto i40e_calc_nvm_checksum_exit; @@ -521,7 +555,7 @@ static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw, if ((i % I40E_SR_SECTOR_SIZE_IN_WORDS) == 0) { u16 words = I40E_SR_SECTOR_SIZE_IN_WORDS; - ret_code = i40e_read_nvm_buffer(hw, i, &words, data); + ret_code = __i40e_read_nvm_buffer(hw, i, &words, data); if (ret_code) { ret_code = I40E_ERR_NVM_CHECKSUM; goto i40e_calc_nvm_checksum_exit; @@ -593,14 +627,19 @@ i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, u16 checksum_sr = 0; u16 checksum_local = 0; + /* We must acquire the NVM lock in order to correctly synchronize the + * NVM accesses across multiple PFs. Without doing so it is possible + * for one of the PFs to read invalid data potentially indicating that + * the checksum is invalid. + */ + ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (ret_code) + return ret_code; ret_code = i40e_calc_nvm_checksum(hw, &checksum_local); + __i40e_read_nvm_word(hw, I40E_SR_SW_CHECKSUM_WORD, &checksum_sr); + i40e_release_nvm(hw); if (ret_code) - goto i40e_validate_nvm_checksum_exit; - - /* Do not use i40e_read_nvm_word() because we do not want to take - * the synchronization semaphores twice here. - */ - i40e_read_nvm_word(hw, I40E_SR_SW_CHECKSUM_WORD, &checksum_sr); + return ret_code; /* Verify read checksum from EEPROM is the same as * calculated checksum @@ -612,7 +651,6 @@ i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, if (checksum) *checksum = checksum_local; -i40e_validate_nvm_checksum_exit: return ret_code; } @@ -736,6 +774,15 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; } + /* Acquire lock to prevent race condition where adminq_task + * can execute after i40e_nvmupd_nvm_read/write but before state + * variables (nvm_wait_opcode, nvm_release_on_done) are updated. + * + * During NVMUpdate, it is observed that lock could be held for + * ~5ms for most commands. However lock is held for ~60ms for + * NVMUPD_CSUM_LCB command. + */ + mutex_lock(&hw->aq.arq_mutex); switch (hw->nvmupd_state) { case I40E_NVMUPD_STATE_INIT: status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno); @@ -756,7 +803,8 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, */ if (cmd->offset == 0xffff) { i40e_nvmupd_check_wait_event(hw, hw->nvm_wait_opcode); - return 0; + status = 0; + goto exit; } status = I40E_ERR_NOT_READY; @@ -771,6 +819,8 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, *perrno = -ESRCH; break; } +exit: + mutex_unlock(&hw->aq.arq_mutex); return status; } @@ -997,6 +1047,7 @@ retry: break; case I40E_NVMUPD_CSUM_CON: + /* Assumes the caller has acquired the nvm */ status = i40e_update_nvm_checksum(hw); if (status) { *perrno = hw->aq.asq_last_status ? @@ -1011,6 +1062,7 @@ retry: break; case I40E_NVMUPD_CSUM_LCB: + /* Assumes the caller has acquired the nvm */ status = i40e_update_nvm_checksum(hw); if (status) { *perrno = hw->aq.asq_last_status ? diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index df613ea40313..a39b13197891 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -311,8 +311,6 @@ i40e_status i40e_acquire_nvm(struct i40e_hw *hw, void i40e_release_nvm(struct i40e_hw *hw); i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data); -i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, - u16 *words, u16 *data); i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw); i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, u16 *checksum); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 1a0be835fa06..d8456c381c99 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -158,13 +158,12 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); - struct timespec64 now, then; + struct timespec64 now; - then = ns_to_timespec64(delta); mutex_lock(&pf->tmreg_lock); i40e_ptp_read(pf, &now); - now = timespec64_add(now, then); + timespec64_add_ns(&now, delta); i40e_ptp_write(pf, (const struct timespec64 *)&now); mutex_unlock(&pf->tmreg_lock); @@ -570,7 +569,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - if (!(pf->flags & I40E_FLAG_PTP_L4_CAPABLE)) + if (!(pf->hw_features & I40E_HW_PTP_L4_CAPABLE)) return -ERANGE; pf->ptp_rx = true; tsyntype = I40E_PRTTSYN_CTL1_V1MESSTYPE0_MASK | @@ -584,7 +583,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - if (!(pf->flags & I40E_FLAG_PTP_L4_CAPABLE)) + if (!(pf->hw_features & I40E_HW_PTP_L4_CAPABLE)) return -ERANGE; /* fall through */ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: @@ -593,7 +592,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, pf->ptp_rx = true; tsyntype = I40E_PRTTSYN_CTL1_V2MESSTYPE0_MASK | I40E_PRTTSYN_CTL1_TSYNTYPE_V2; - if (pf->flags & I40E_FLAG_PTP_L4_CAPABLE) { + if (pf->hw_features & I40E_HW_PTP_L4_CAPABLE) { tsyntype |= I40E_PRTTSYN_CTL1_UDP_ENA_MASK; config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; } else { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 2194960d5855..1519dfb851d0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -860,7 +860,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, netdev_tx_completed_queue(txring_txq(tx_ring), total_packets, total_bytes); -#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) +#define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2)) if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && (I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { /* Make sure that anybody stopping the queue after this @@ -959,19 +959,31 @@ void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; - struct i40e_q_vector *qv = rc->ring->q_vector; u32 new_itr = rc->itr; int bytes_per_int; - int usecs; + unsigned int usecs, estimated_usecs; if (rc->total_packets == 0 || !rc->itr) return false; + usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; + bytes_per_int = rc->total_bytes / usecs; + + /* The calculations in this algorithm depend on interrupts actually + * firing at the ITR rate. This may not happen if the packet rate is + * really low, or if we've been napi polling. Check to make sure + * that's not the case before we continue. + */ + estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); + if (estimated_usecs > usecs) { + new_latency_range = I40E_LOW_LATENCY; + goto reset_latency; + } + /* simple throttlerate management * 0-10MB/s lowest (50000 ints/s) * 10-20MB/s low (20000 ints/s) * 20-1249MB/s bulk (18000 ints/s) - * > 40000 Rx packets per second (8000 ints/s) * * The math works out because the divisor is in 10^(-6) which * turns the bytes/us input value into MB/s values, but @@ -979,9 +991,6 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) * are in 2 usec increments in the ITR registers, and make sure * to use the smoothed values that the countdown timer gives us. */ - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_int = rc->total_bytes / usecs; - switch (new_latency_range) { case I40E_LOWEST_LATENCY: if (bytes_per_int > 10) @@ -994,24 +1003,13 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: - case I40E_ULTRA_LATENCY: default: if (bytes_per_int <= 20) new_latency_range = I40E_LOW_LATENCY; break; } - /* this is to adjust RX more aggressively when streaming small - * packets. The value of 40000 was picked as it is just beyond - * what the hardware can receive per second if in low latency - * mode. - */ -#define RX_ULTRA_PACKET_RATE 40000 - - if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) && - (&qv->rx == rc)) - new_latency_range = I40E_ULTRA_LATENCY; - +reset_latency: rc->latency_range = new_latency_range; switch (new_latency_range) { @@ -1024,21 +1022,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) case I40E_BULK_LATENCY: new_itr = I40E_ITR_18K; break; - case I40E_ULTRA_LATENCY: - new_itr = I40E_ITR_8K; - break; default: break; } rc->total_bytes = 0; rc->total_packets = 0; + rc->last_itr_update = jiffies; if (new_itr != rc->itr) { rc->itr = new_itr; return true; } - return false; } @@ -2065,7 +2060,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); bool failure = false, xdp_xmit = false; - while (likely(total_rx_packets < budget)) { + while (likely(total_rx_packets < (unsigned int)budget)) { struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; struct xdp_buff xdp; @@ -2198,7 +2193,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) rx_ring->q_vector->rx.total_bytes += total_rx_bytes; /* guarantee a trip back through this routine if there was a failure */ - return failure ? budget : total_rx_packets; + return failure ? budget : (int)total_rx_packets; } static u32 i40e_buildreg_itr(const int type, const u16 itr) @@ -2243,6 +2238,12 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, int idx = q_vector->v_idx; int rx_itr_setting, tx_itr_setting; + /* If we don't have MSIX, then we only need to re-enable icr0 */ + if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) { + i40e_irq_dynamic_enable_icr0(vsi->back, false); + return; + } + vector = (q_vector->v_idx + vsi->base_vector); /* avoid dynamic calculation if in countdown mode OR if @@ -2363,7 +2364,6 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) /* If work not completed, return budget and polling will return */ if (!clean_complete) { - const cpumask_t *aff_mask = &q_vector->affinity_mask; int cpu_id = smp_processor_id(); /* It is possible that the interrupt affinity has changed but, @@ -2373,15 +2373,22 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) * continue to poll, otherwise we must stop polling so the * interrupt can move to the correct cpu. */ - if (likely(cpumask_test_cpu(cpu_id, aff_mask) || - !(vsi->back->flags & I40E_FLAG_MSIX_ENABLED))) { + if (!cpumask_test_cpu(cpu_id, &q_vector->affinity_mask)) { + /* Tell napi that we are done polling */ + napi_complete_done(napi, work_done); + + /* Force an interrupt */ + i40e_force_wb(vsi, q_vector); + + /* Return budget-1 so that polling stops */ + return budget - 1; + } tx_only: - if (arm_wb) { - q_vector->tx.ring[0].tx_stats.tx_force_wb++; - i40e_enable_wb_on_itr(vsi, q_vector); - } - return budget; + if (arm_wb) { + q_vector->tx.ring[0].tx_stats.tx_force_wb++; + i40e_enable_wb_on_itr(vsi, q_vector); } + return budget; } if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) @@ -2390,16 +2397,7 @@ tx_only: /* Work is done so exit the polling mode and re-enable the interrupt */ napi_complete_done(napi, work_done); - /* If we're prematurely stopping polling to fix the interrupt - * affinity we want to make sure polling starts back up so we - * issue a call to i40e_force_wb which triggers a SW interrupt. - */ - if (!clean_complete) - i40e_force_wb(vsi, q_vector); - else if (!(vsi->back->flags & I40E_FLAG_MSIX_ENABLED)) - i40e_irq_dynamic_enable_icr0(vsi->back, false); - else - i40e_update_enable_itr(vsi, q_vector); + i40e_update_enable_itr(vsi, q_vector); return min(work_done, budget - 1); } @@ -2453,9 +2451,15 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb, hlen = (hdr.network[0] & 0x0F) << 2; l4_proto = hdr.ipv4->protocol; } else { - hlen = hdr.network - skb->data; - l4_proto = ipv6_find_hdr(skb, &hlen, IPPROTO_TCP, NULL, NULL); - hlen -= hdr.network - skb->data; + /* find the start of the innermost ipv6 header */ + unsigned int inner_hlen = hdr.network - skb->data; + unsigned int h_offset = inner_hlen; + + /* this function updates h_offset to the end of the header */ + l4_proto = + ipv6_find_hdr(skb, &h_offset, IPPROTO_TCP, NULL, NULL); + /* hlen will contain our best estimate of the tcp header */ + hlen = h_offset - inner_hlen; } if (l4_proto != IPPROTO_TCP) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index b288d58313a6..2f848bc5e391 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -112,7 +112,7 @@ enum i40e_dyn_idx_t { BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) #define i40e_pf_get_default_rss_hena(pf) \ - (((pf)->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \ + (((pf)->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \ I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA) /* Supported Rx Buffer Sizes (a multiple of 128) */ @@ -130,6 +130,7 @@ enum i40e_dyn_idx_t { * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) */ #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 +#define I40E_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) #define i40e_rx_desc i40e_32byte_rx_desc #define I40E_RX_DMA_ATTR \ @@ -453,7 +454,6 @@ enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, I40E_BULK_LATENCY = 2, - I40E_ULTRA_LATENCY = 3, }; struct i40e_ring_container { @@ -461,6 +461,7 @@ struct i40e_ring_container { struct i40e_ring *ring; unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ + unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; enum i40e_latency_range latency_range; u16 itr; diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 3a18ed13edc4..fd4bbdd88b57 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -185,6 +185,7 @@ struct i40e_link_status { enum i40e_aq_link_speed link_speed; u8 link_info; u8 an_info; + u8 req_fec_info; u8 fec_info; u8 ext_info; u8 loopback; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index ecbe40ea8ffe..4d1e670f490e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1528,54 +1528,54 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) VIRTCHNL_VF_OFFLOAD_RSS_REG | VIRTCHNL_VF_OFFLOAD_VLAN; - vfres->vf_offload_flags = VIRTCHNL_VF_OFFLOAD_L2; + vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi->info.pvid) - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; if (i40e_vf_client_capable(pf, vf->vf_id) && (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_IWARP)) { - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_IWARP; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_IWARP; set_bit(I40E_VF_STATE_IWARPENA, &vf->vf_states); } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; } else { - if ((pf->flags & I40E_FLAG_RSS_AQ_CAPABLE) && + if ((pf->hw_features & I40E_HW_RSS_AQ_CAPABLE) && (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ)) - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; else - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; } - if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) { + if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) { if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) - vfres->vf_offload_flags |= + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP) - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP; - if ((pf->flags & I40E_FLAG_OUTER_UDP_CSUM_CAPABLE) && + if ((pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE) && (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)) - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM; if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_POLLING) { if (pf->flags & I40E_FLAG_MFP_ENABLED) { dev_err(&pf->pdev->dev, "VF %d requested polling mode: this feature is supported only when the device is running in single function per port (SFP) mode\n", vf->vf_id); - ret = I40E_ERR_PARAM; + aq_ret = I40E_ERR_PARAM; goto err; } - vfres->vf_offload_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_POLLING; } - if (pf->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) { + if (pf->hw_features & I40E_HW_WB_ON_ITR_CAPABLE) { if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) - vfres->vf_offload_flags |= + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_WB_ON_ITR; } @@ -1741,16 +1741,14 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, NULL); } else if (i40e_getnum_vf_vsi_vlan_filters(vsi)) { hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { - aq_ret = 0; - if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID) { - aq_ret = - i40e_aq_set_vsi_uc_promisc_on_vlan(hw, - vsi->seid, - alluni, - f->vlan, - NULL); - aq_err = pf->hw.aq.asq_last_status; - } + if (f->vlan < 0 || f->vlan > I40E_MAX_VLANID) + continue; + aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, + vsi->seid, + alluni, + f->vlan, + NULL); + aq_err = pf->hw.aq.asq_last_status; if (aq_ret) dev_err(&pf->pdev->dev, "Could not add VLAN %d to Unicast promiscuous domain err %s aq_err %s\n", @@ -1760,7 +1758,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, } } else { aq_ret = i40e_aq_set_vsi_unicast_promiscuous(hw, vsi->seid, - allmulti, NULL, + alluni, NULL, true); aq_err = pf->hw.aq.asq_last_status; if (aq_ret) { @@ -2532,6 +2530,60 @@ err: } /** + * i40e_vc_enable_vlan_stripping + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * Enable vlan header stripping for the VF + **/ +static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg, + u16 msglen) +{ + struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + i40e_vlan_stripping_enable(vsi); + + /* send the response to the VF */ +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, + aq_ret); +} + +/** + * i40e_vc_disable_vlan_stripping + * @vf: pointer to the VF info + * @msg: pointer to the msg buffer + * @msglen: msg length + * + * Disable vlan header stripping for the VF + **/ +static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg, + u16 msglen) +{ + struct i40e_vsi *vsi = vf->pf->vsi[vf->lan_vsi_idx]; + i40e_status aq_ret = 0; + + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + aq_ret = I40E_ERR_PARAM; + goto err; + } + + i40e_vlan_stripping_disable(vsi); + + /* send the response to the VF */ +err: + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, + aq_ret); +} + +/** * i40e_vc_process_vf_msg * @pf: pointer to the PF structure * @vf_id: source VF id @@ -2650,6 +2702,12 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, case VIRTCHNL_OP_SET_RSS_HENA: ret = i40e_vc_set_rss_hena(vf, msg, msglen); break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + ret = i40e_vc_enable_vlan_stripping(vf, msg, msglen); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + ret = i40e_vc_disable_vlan_stripping(vf, msg, msglen); + break; case VIRTCHNL_OP_UNKNOWN: default: @@ -2764,7 +2822,6 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) spin_unlock_bh(&vsi->mac_filter_hash_lock); - dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id); /* program mac filter */ if (i40e_sync_vsi_filters(vsi)) { dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); @@ -2772,7 +2829,16 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto error_param; } ether_addr_copy(vf->default_lan_addr.addr, mac); - vf->pf_set_mac = true; + + if (is_zero_ether_addr(mac)) { + vf->pf_set_mac = false; + dev_info(&pf->pdev->dev, "Removing MAC on VF %d\n", vf_id); + } else { + vf->pf_set_mac = true; + dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", + mac, vf_id); + } + /* Force the VF driver stop so it has to reload with new MAC address */ i40e_vc_disable_vf(pf, vf); dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n"); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 1dd1938f594f..8d3a2bfe186a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -333,9 +333,9 @@ void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, len = buf_len; /* write the full 16-byte chunks */ if (hw->debug_mask & mask) { - char prefix[20]; + char prefix[27]; - snprintf(prefix, 20, + snprintf(prefix, sizeof(prefix), "i40evf %02x:%02x.%x: \t0x", hw->bus.bus_id, hw->bus.device, @@ -1104,7 +1104,7 @@ void i40e_vf_parse_hw_config(struct i40e_hw *hw, hw->dev_caps.num_rx_qp = msg->num_queue_pairs; hw->dev_caps.num_tx_qp = msg->num_queue_pairs; hw->dev_caps.num_msix_vectors_vf = msg->max_vectors; - hw->dev_caps.dcb = msg->vf_offload_flags & + hw->dev_caps.dcb = msg->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_L2; hw->dev_caps.fcoe = 0; for (i = 0; i < msg->num_vsis; i++) { diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h index 5e314fd3c016..a90737786c34 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h @@ -54,7 +54,7 @@ struct i40e_dma_mem { void *va; dma_addr_t pa; u32 size; -} __packed; +}; #define i40e_allocate_dma_mem(h, m, unused, s, a) \ i40evf_allocate_dma_mem_d(h, m, s, a) @@ -63,7 +63,7 @@ struct i40e_dma_mem { struct i40e_virt_mem { void *va; u32 size; -} __packed; +}; #define i40e_allocate_virt_mem(h, m, s) i40evf_allocate_virt_mem_d(h, m, s) #define i40e_free_virt_mem(h, m) i40evf_free_virt_mem_d(h, m) diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 12b02e530503..c32c62462c84 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -275,7 +275,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, netdev_tx_completed_queue(txring_txq(tx_ring), total_packets, total_bytes); -#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) +#define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2)) if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && (I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { /* Make sure that anybody stopping the queue after this @@ -357,19 +357,31 @@ void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) { enum i40e_latency_range new_latency_range = rc->latency_range; - struct i40e_q_vector *qv = rc->ring->q_vector; u32 new_itr = rc->itr; int bytes_per_int; - int usecs; + unsigned int usecs, estimated_usecs; if (rc->total_packets == 0 || !rc->itr) return false; + usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; + bytes_per_int = rc->total_bytes / usecs; + + /* The calculations in this algorithm depend on interrupts actually + * firing at the ITR rate. This may not happen if the packet rate is + * really low, or if we've been napi polling. Check to make sure + * that's not the case before we continue. + */ + estimated_usecs = jiffies_to_usecs(jiffies - rc->last_itr_update); + if (estimated_usecs > usecs) { + new_latency_range = I40E_LOW_LATENCY; + goto reset_latency; + } + /* simple throttlerate management * 0-10MB/s lowest (50000 ints/s) * 10-20MB/s low (20000 ints/s) * 20-1249MB/s bulk (18000 ints/s) - * > 40000 Rx packets per second (8000 ints/s) * * The math works out because the divisor is in 10^(-6) which * turns the bytes/us input value into MB/s values, but @@ -377,9 +389,6 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) * are in 2 usec increments in the ITR registers, and make sure * to use the smoothed values that the countdown timer gives us. */ - usecs = (rc->itr << 1) * ITR_COUNTDOWN_START; - bytes_per_int = rc->total_bytes / usecs; - switch (new_latency_range) { case I40E_LOWEST_LATENCY: if (bytes_per_int > 10) @@ -392,24 +401,13 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) new_latency_range = I40E_LOWEST_LATENCY; break; case I40E_BULK_LATENCY: - case I40E_ULTRA_LATENCY: default: if (bytes_per_int <= 20) new_latency_range = I40E_LOW_LATENCY; break; } - /* this is to adjust RX more aggressively when streaming small - * packets. The value of 40000 was picked as it is just beyond - * what the hardware can receive per second if in low latency - * mode. - */ -#define RX_ULTRA_PACKET_RATE 40000 - - if ((((rc->total_packets * 1000000) / usecs) > RX_ULTRA_PACKET_RATE) && - (&qv->rx == rc)) - new_latency_range = I40E_ULTRA_LATENCY; - +reset_latency: rc->latency_range = new_latency_range; switch (new_latency_range) { @@ -422,21 +420,18 @@ static bool i40e_set_new_dynamic_itr(struct i40e_ring_container *rc) case I40E_BULK_LATENCY: new_itr = I40E_ITR_18K; break; - case I40E_ULTRA_LATENCY: - new_itr = I40E_ITR_8K; - break; default: break; } rc->total_bytes = 0; rc->total_packets = 0; + rc->last_itr_update = jiffies; if (new_itr != rc->itr) { rc->itr = new_itr; return true; } - return false; } @@ -1299,7 +1294,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); bool failure = false; - while (likely(total_rx_packets < budget)) { + while (likely(total_rx_packets < (unsigned int)budget)) { struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; unsigned int size; @@ -1406,7 +1401,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) rx_ring->q_vector->rx.total_bytes += total_rx_bytes; /* guarantee a trip back through this routine if there was a failure */ - return failure ? budget : total_rx_packets; + return failure ? budget : (int)total_rx_packets; } static u32 i40e_buildreg_itr(const int type, const u16 itr) @@ -1575,7 +1570,6 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) /* If work not completed, return budget and polling will return */ if (!clean_complete) { - const cpumask_t *aff_mask = &q_vector->affinity_mask; int cpu_id = smp_processor_id(); /* It is possible that the interrupt affinity has changed but, @@ -1585,14 +1579,22 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) * continue to poll, otherwise we must stop polling so the * interrupt can move to the correct cpu. */ - if (likely(cpumask_test_cpu(cpu_id, aff_mask))) { + if (!cpumask_test_cpu(cpu_id, &q_vector->affinity_mask)) { + /* Tell napi that we are done polling */ + napi_complete_done(napi, work_done); + + /* Force an interrupt */ + i40evf_force_wb(vsi, q_vector); + + /* Return budget-1 so that polling stops */ + return budget - 1; + } tx_only: - if (arm_wb) { - q_vector->tx.ring[0].tx_stats.tx_force_wb++; - i40e_enable_wb_on_itr(vsi, q_vector); - } - return budget; + if (arm_wb) { + q_vector->tx.ring[0].tx_stats.tx_force_wb++; + i40e_enable_wb_on_itr(vsi, q_vector); } + return budget; } if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) @@ -1601,14 +1603,7 @@ tx_only: /* Work is done so exit the polling mode and re-enable the interrupt */ napi_complete_done(napi, work_done); - /* If we're prematurely stopping polling to fix the interrupt - * affinity we want to make sure polling starts back up so we - * issue a call to i40evf_force_wb which triggers a SW interrupt. - */ - if (!clean_complete) - i40evf_force_wb(vsi, q_vector); - else - i40e_update_enable_itr(vsi, q_vector); + i40e_update_enable_itr(vsi, q_vector); return min(work_done, budget - 1); } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 901282c87cf6..0d9f98bc07bd 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -98,10 +98,6 @@ enum i40e_dyn_idx_t { BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) -#define i40e_pf_get_default_rss_hena(pf) \ - (((pf)->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) ? \ - I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA) - /* Supported Rx Buffer Sizes (a multiple of 128) */ #define I40E_RXBUFFER_256 256 #define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ @@ -117,6 +113,7 @@ enum i40e_dyn_idx_t { * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) */ #define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 +#define I40E_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) #define i40e_rx_desc i40e_32byte_rx_desc #define I40E_RX_DMA_ATTR \ @@ -428,7 +425,6 @@ enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, I40E_BULK_LATENCY = 2, - I40E_ULTRA_LATENCY = 3, }; struct i40e_ring_container { @@ -436,6 +432,7 @@ struct i40e_ring_container { struct i40e_ring *ring; unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ + unsigned long last_itr_update; /* jiffies of last ITR update */ u16 count; enum i40e_latency_range latency_range; u16 itr; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index bde7f24af1c6..2ea919d9cdcf 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -159,6 +159,7 @@ struct i40e_link_status { enum i40e_aq_link_speed link_speed; u8 link_info; u8 an_info; + u8 req_fec_info; u8 fec_info; u8 ext_info; u8 loopback; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 6cc92089fecb..82f69031e5cd 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -39,6 +39,18 @@ #include <linux/tcp.h> #include <linux/sctp.h> #include <linux/ipv6.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/timer.h> +#include <linux/workqueue.h> +#include <linux/wait.h> +#include <linux/delay.h> +#include <linux/gfp.h> +#include <linux/skbuff.h> +#include <linux/dma-mapping.h> +#include <linux/etherdevice.h> +#include <linux/socket.h> +#include <linux/jiffies.h> #include <net/ip6_checksum.h> #include <net/udp.h> @@ -109,7 +121,7 @@ struct i40e_q_vector { #define ITR_COUNTDOWN_START 100 u8 itr_countdown; /* when 0 or 1 update ITR */ int v_idx; /* vector index in list */ - char name[IFNAMSIZ + 9]; + char name[IFNAMSIZ + 15]; bool arm_wb_state; cpumask_t affinity_mask; struct irq_affinity_notify affinity_notify; @@ -183,6 +195,7 @@ struct i40evf_adapter { struct work_struct adminq_task; struct delayed_work client_task; struct delayed_work init_task; + wait_queue_head_t down_waitqueue; struct i40e_q_vector *q_vectors; struct list_head vlan_filter_list; char misc_vector_name[IFNAMSIZ + 9]; @@ -225,8 +238,6 @@ struct i40evf_adapter { /* duplicates for common code */ #define I40E_FLAG_DCB_ENABLED 0 #define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED -#define I40E_FLAG_WB_ON_ITR_CAPABLE I40EVF_FLAG_WB_ON_ITR_CAPABLE -#define I40E_FLAG_OUTER_UDP_CSUM_CAPABLE I40EVF_FLAG_OUTER_UDP_CSUM_CAPABLE #define I40E_FLAG_LEGACY_RX I40EVF_FLAG_LEGACY_RX /* flags for admin queue service task */ u32 aq_required; @@ -250,6 +261,8 @@ struct i40evf_adapter { #define I40EVF_FLAG_AQ_RELEASE_PROMISC BIT(16) #define I40EVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17) #define I40EVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) +#define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) +#define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) /* OS defined structs */ struct net_device *netdev; @@ -266,19 +279,19 @@ struct i40evf_adapter { enum virtchnl_link_speed link_speed; enum virtchnl_ops current_op; #define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ - (_a)->vf_res->vf_offload_flags & \ + (_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_IWARP : \ 0) #define CLIENT_ENABLED(_a) ((_a)->cinst) /* RSS by the PF should be preferred over RSS via other methods. */ -#define RSS_PF(_a) ((_a)->vf_res->vf_offload_flags & \ +#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_RSS_PF) -#define RSS_AQ(_a) ((_a)->vf_res->vf_offload_flags & \ +#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_RSS_AQ) -#define RSS_REG(_a) (!((_a)->vf_res->vf_offload_flags & \ +#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \ (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \ VIRTCHNL_VF_OFFLOAD_RSS_PF))) -#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_offload_flags & \ +#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_VLAN) struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ @@ -347,6 +360,8 @@ void i40evf_get_hena(struct i40evf_adapter *adapter); void i40evf_set_hena(struct i40evf_adapter *adapter); void i40evf_set_rss_key(struct i40evf_adapter *adapter); void i40evf_set_rss_lut(struct i40evf_adapter *adapter); +void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter); +void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter); void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, enum virtchnl_ops v_opcode, i40e_status v_retval, u8 *msg, u16 msglen); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index 9bb2cc7dd4e4..65874d6b3ab9 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -165,7 +165,7 @@ static void i40evf_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { struct i40evf_adapter *adapter = netdev_priv(netdev); - int i, j; + unsigned int i, j; char *p; for (i = 0; i < I40EVF_GLOBAL_STATS_LEN; i++) { @@ -197,7 +197,7 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data) int i; if (sset == ETH_SS_STATS) { - for (i = 0; i < I40EVF_GLOBAL_STATS_LEN; i++) { + for (i = 0; i < (int)I40EVF_GLOBAL_STATS_LEN; i++) { memcpy(p, i40evf_gstrings_stats[i].stat_string, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; @@ -258,29 +258,50 @@ static u32 i40evf_get_priv_flags(struct net_device *netdev) static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags) { struct i40evf_adapter *adapter = netdev_priv(netdev); - u64 changed_flags; + u32 orig_flags, new_flags, changed_flags; u32 i; - changed_flags = adapter->flags; + orig_flags = READ_ONCE(adapter->flags); + new_flags = orig_flags; for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { const struct i40evf_priv_flags *priv_flags; priv_flags = &i40evf_gstrings_priv_flags[i]; - if (priv_flags->read_only) - continue; - if (flags & BIT(i)) - adapter->flags |= priv_flags->flag; + new_flags |= priv_flags->flag; else - adapter->flags &= ~(priv_flags->flag); + new_flags &= ~(priv_flags->flag); + + if (priv_flags->read_only && + ((orig_flags ^ new_flags) & ~BIT(i))) + return -EOPNOTSUPP; + } + + /* Before we finalize any flag changes, any checks which we need to + * perform to determine if the new flags will be supported should go + * here... + */ + + /* Compare and exchange the new flags into place. If we failed, that + * is if cmpxchg returns anything but the old value, this means + * something else must have modified the flags variable since we + * copied it. We'll just punt with an error and log something in the + * message buffer. + */ + if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { + dev_warn(&adapter->pdev->dev, + "Unable to update adapter->flags as it was modified by another thread...\n"); + return -EAGAIN; } - /* check for flags that changed */ - changed_flags ^= adapter->flags; + changed_flags = orig_flags ^ new_flags; - /* Process any additional changes needed as a result of flag changes. */ + /* Process any additional changes needed as a result of flag changes. + * The changed_flags value reflects the list of bits that were changed + * in the code above. + */ /* issue a reset to force legacy-rx change to take effect */ if (changed_flags & I40EVF_FLAG_LEGACY_RX) { diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 7c213a347909..1825d956bb00 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -520,7 +520,7 @@ static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify, struct i40e_q_vector *q_vector = container_of(notify, struct i40e_q_vector, affinity_notify); - q_vector->affinity_mask = *mask; + cpumask_copy(&q_vector->affinity_mask, mask); } /** @@ -543,9 +543,9 @@ static void i40evf_irq_affinity_release(struct kref *ref) {} static int i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) { - int vector, err, q_vectors; - int rx_int_idx = 0, tx_int_idx = 0; - int irq_num; + unsigned int vector, q_vectors; + unsigned int rx_int_idx = 0, tx_int_idx = 0; + int irq_num, err; i40evf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ @@ -556,18 +556,15 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; if (q_vector->tx.ring && q_vector->rx.ring) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "i40evf-%s-%s-%d", basename, - "TxRx", rx_int_idx++); + snprintf(q_vector->name, sizeof(q_vector->name), + "i40evf-%s-TxRx-%d", basename, rx_int_idx++); tx_int_idx++; } else if (q_vector->rx.ring) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "i40evf-%s-%s-%d", basename, - "rx", rx_int_idx++); + snprintf(q_vector->name, sizeof(q_vector->name), + "i40evf-%s-rx-%d", basename, rx_int_idx++); } else if (q_vector->tx.ring) { - snprintf(q_vector->name, sizeof(q_vector->name) - 1, - "i40evf-%s-%s-%d", basename, - "tx", tx_int_idx++); + snprintf(q_vector->name, sizeof(q_vector->name), + "i40evf-%s-tx-%d", basename, tx_int_idx++); } else { /* skip this unused q_vector */ continue; @@ -587,8 +584,10 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) q_vector->affinity_notify.release = i40evf_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* assign the mask for this irq */ - irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); + /* get_cpu_mask returns a static constant mask with + * a permanent lifetime so it's ok to use here. + */ + irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx)); } return 0; @@ -1143,6 +1142,7 @@ void i40evf_down(struct i40evf_adapter *adapter) } clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } /** @@ -1241,7 +1241,7 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; tx_ring->tx_itr_setting = (I40E_ITR_DYNAMIC | I40E_ITR_TX_DEF); - if (adapter->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) + if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; rx_ring = &adapter->rx_rings[i]; @@ -1417,7 +1417,7 @@ static int i40evf_init_rss(struct i40evf_adapter *adapter) if (!RSS_PF(adapter)) { /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */ - if (adapter->vf_res->vf_offload_flags & + if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) adapter->hena = I40E_DEFAULT_RSS_HENA_EXPANDED; else @@ -1458,6 +1458,7 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter) q_vector->adapter = adapter; q_vector->vsi = &adapter->vsi; q_vector->v_idx = q_idx; + cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); netif_napi_add(adapter->netdev, &q_vector->napi, i40evf_napi_poll, NAPI_POLL_WEIGHT); } @@ -1678,6 +1679,16 @@ static void i40evf_watchdog_task(struct work_struct *work) goto watchdog_done; } + if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) { + i40evf_enable_vlan_stripping(adapter); + goto watchdog_done; + } + + if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) { + i40evf_disable_vlan_stripping(adapter); + goto watchdog_done; + } + if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_QUEUES) { i40evf_configure_queues(adapter); goto watchdog_done; @@ -1794,6 +1805,7 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; adapter->state = __I40EVF_DOWN; + wake_up(&adapter->down_waitqueue); dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); } @@ -1877,7 +1889,7 @@ static void i40evf_reset_task(struct work_struct *work) } continue_reset: - if (netif_running(adapter->netdev)) { + if (netif_running(netdev)) { netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -1939,12 +1951,13 @@ continue_reset: i40evf_irq_enable(adapter, true); } else { adapter->state = __I40EVF_DOWN; + wake_up(&adapter->down_waitqueue); } return; reset_err: dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); - i40evf_close(adapter->netdev); + i40evf_close(netdev); } /** @@ -1957,8 +1970,8 @@ static void i40evf_adminq_task(struct work_struct *work) container_of(work, struct i40evf_adapter, adminq_task); struct i40e_hw *hw = &adapter->hw; struct i40e_arq_event_info event; - struct virtchnl_msg *v_msg; - i40e_status ret; + enum virtchnl_ops v_op; + i40e_status ret, v_ret; u32 val, oldval; u16 pending; @@ -1970,15 +1983,15 @@ static void i40evf_adminq_task(struct work_struct *work) if (!event.msg_buf) goto out; - v_msg = (struct virtchnl_msg *)&event.desc; do { ret = i40evf_clean_arq_element(hw, &event, &pending); - if (ret || !v_msg->v_opcode) + v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); + v_ret = (i40e_status)le32_to_cpu(event.desc.cookie_low); + + if (ret || !v_op) break; /* No event to process or error cleaning ARQ */ - i40evf_virtchnl_completion(adapter, v_msg->v_opcode, - (i40e_status)v_msg->v_retval, - event.msg_buf, + i40evf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf, event.msg_len); if (pending != 0) memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE); @@ -2238,6 +2251,7 @@ err_setup_tx: static int i40evf_close(struct net_device *netdev) { struct i40evf_adapter *adapter = netdev_priv(netdev); + int status; if (adapter->state <= __I40EVF_DOWN_PENDING) return 0; @@ -2255,7 +2269,18 @@ static int i40evf_close(struct net_device *netdev) * still active and can DMA into memory. Resources are cleared in * i40evf_virtchnl_completion() after we get confirmation from the PF * driver that the rings have been stopped. + * + * Also, we wait for state to transition to __I40EVF_DOWN before + * returning. State change occurs in i40evf_virtchnl_completion() after + * VF resources are released (which occurs after PF driver processes and + * responds to admin queue commands). */ + + status = wait_event_timeout(adapter->down_waitqueue, + adapter->state == __I40EVF_DOWN, + msecs_to_jiffies(200)); + if (!status) + netdev_warn(netdev, "Device resources not yet released\n"); return 0; } @@ -2282,6 +2307,28 @@ static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) } /** + * i40e_set_features - set the netdev feature flags + * @netdev: ptr to the netdev being adjusted + * @features: the feature set that the stack is suggesting + * Note: expects to be called while under rtnl_lock() + **/ +static int i40evf_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct i40evf_adapter *adapter = netdev_priv(netdev); + + if (!VLAN_ALLOWED(adapter)) + return -EINVAL; + + if (features & NETIF_F_HW_VLAN_CTAG_RX) + adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + else + adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + + return 0; +} + +/** * i40evf_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff * @netdev: This physical port's netdev @@ -2356,7 +2403,7 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev, struct i40evf_adapter *adapter = netdev_priv(netdev); features &= ~I40EVF_VLAN_FEATURES; - if (adapter->vf_res->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_VLAN) + if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) features |= I40EVF_VLAN_FEATURES; return features; } @@ -2374,6 +2421,7 @@ static const struct net_device_ops i40evf_netdev_ops = { .ndo_vlan_rx_kill_vid = i40evf_vlan_rx_kill_vid, .ndo_features_check = i40evf_features_check, .ndo_fix_features = i40evf_fix_features, + .ndo_set_features = i40evf_set_features, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = i40evf_netpoll, #endif @@ -2443,7 +2491,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter) /* advertise to stack only if offloads for encapsulated packets is * supported */ - if (vfres->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) { + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ENCAP) { hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | @@ -2453,7 +2501,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter) NETIF_F_GSO_PARTIAL | 0; - if (!(vfres->vf_offload_flags & + if (!(vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM)) netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; @@ -2481,7 +2529,7 @@ int i40evf_process_config(struct i40evf_adapter *adapter) adapter->vsi.work_limit = I40E_DEFAULT_IRQ_WORK; vsi->netdev = adapter->netdev; vsi->qs_handle = adapter->vsi_res->qset_handle; - if (vfres->vf_offload_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { adapter->rss_key_size = vfres->rss_key_size; adapter->rss_lut_size = vfres->rss_lut_size; } else { @@ -2625,7 +2673,7 @@ static void i40evf_init_task(struct work_struct *work) /* MTU range: 68 - 9710 */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = I40E_MAX_RXBUFFER - (ETH_HLEN + ETH_FCS_LEN); + netdev->max_mtu = I40E_MAX_RXBUFFER - I40E_PACKET_HDR_PAD; if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", @@ -2649,7 +2697,7 @@ static void i40evf_init_task(struct work_struct *work) if (err) goto err_sw_init; i40evf_map_rings_to_vectors(adapter); - if (adapter->vf_res->vf_offload_flags & + if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE; @@ -2683,6 +2731,7 @@ static void i40evf_init_task(struct work_struct *work) adapter->state = __I40EVF_DOWN; set_bit(__I40E_VSI_DOWN, adapter->vsi.state); i40evf_misc_irq_enable(adapter); + wake_up(&adapter->down_waitqueue); adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL); adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL); @@ -2844,6 +2893,9 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); + /* Setup the wait queue for indicating transition to down status */ + init_waitqueue_head(&adapter->down_waitqueue); + return 0; err_ioremap: diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index d2bb250a71af..85876f4fb1fb 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -821,6 +821,46 @@ void i40evf_set_rss_lut(struct i40evf_adapter *adapter) } /** + * i40evf_enable_vlan_stripping + * @adapter: adapter structure + * + * Request VLAN header stripping to be enabled + **/ +void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot enable stripping, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_ENABLE_VLAN_STRIPPING; + adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, + NULL, 0); +} + +/** + * i40evf_disable_vlan_stripping + * @adapter: adapter structure + * + * Request VLAN header stripping to be disabled + **/ +void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, "Cannot disable stripping, command %d pending\n", + adapter->current_op); + return; + } + adapter->current_op = VIRTCHNL_OP_DISABLE_VLAN_STRIPPING; + adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, + NULL, 0); +} + +/** * i40evf_print_link_message - print link up or down * @adapter: adapter structure * @@ -991,8 +1031,10 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_DISABLE_QUEUES: i40evf_free_all_tx_resources(adapter); i40evf_free_all_rx_resources(adapter); - if (adapter->state == __I40EVF_DOWN_PENDING) + if (adapter->state == __I40EVF_DOWN_PENDING) { adapter->state = __I40EVF_DOWN; + wake_up(&adapter->down_waitqueue); + } break; case VIRTCHNL_OP_VERSION: case VIRTCHNL_OP_CONFIG_IRQ_MAP: diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 4a50870e0fa7..c37cc8bccf47 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -340,6 +340,9 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw) phy->ops.set_d3_lplu_state = igb_set_d3_lplu_state_82580; phy->ops.force_speed_duplex = igb_phy_force_speed_duplex_m88; break; + case BCM54616_E_PHY_ID: + phy->type = e1000_phy_bcm54616; + break; default: ret_val = -E1000_ERR_PHY; goto out; @@ -1659,6 +1662,9 @@ static s32 igb_setup_copper_link_82575(struct e1000_hw *hw) case e1000_phy_82580: ret_val = igb_copper_link_setup_82580(hw); break; + case e1000_phy_bcm54616: + ret_val = 0; + break; default: ret_val = -E1000_ERR_PHY; break; diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index d8517779439b..1de82f247312 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -889,6 +889,7 @@ #define I210_I_PHY_ID 0x01410C00 #define M88E1543_E_PHY_ID 0x01410EA0 #define M88E1512_E_PHY_ID 0x01410DD0 +#define BCM54616_E_PHY_ID 0x03625D10 /* M88E1000 Specific Registers */ #define M88E1000_PHY_SPEC_CTRL 0x10 /* PHY Specific Control Register */ diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index 2fb2213cd562..6c9485ab4b57 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -128,6 +128,7 @@ enum e1000_phy_type { e1000_phy_ife, e1000_phy_82580, e1000_phy_i210, + e1000_phy_bcm54616, }; enum e1000_bus_type { @@ -491,13 +492,16 @@ struct e1000_fc_info { struct e1000_mbx_operations { s32 (*init_params)(struct e1000_hw *hw); - s32 (*read)(struct e1000_hw *, u32 *, u16, u16); - s32 (*write)(struct e1000_hw *, u32 *, u16, u16); - s32 (*read_posted)(struct e1000_hw *, u32 *, u16, u16); - s32 (*write_posted)(struct e1000_hw *, u32 *, u16, u16); - s32 (*check_for_msg)(struct e1000_hw *, u16); - s32 (*check_for_ack)(struct e1000_hw *, u16); - s32 (*check_for_rst)(struct e1000_hw *, u16); + s32 (*read)(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id, + bool unlock); + s32 (*write)(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id); + s32 (*read_posted)(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id); + s32 (*write_posted)(struct e1000_hw *hw, u32 *msg, u16 size, + u16 mbx_id); + s32 (*check_for_msg)(struct e1000_hw *hw, u16 mbx_id); + s32 (*check_for_ack)(struct e1000_hw *hw, u16 mbx_id); + s32 (*check_for_rst)(struct e1000_hw *hw, u16 mbx_id); + s32 (*unlock)(struct e1000_hw *hw, u16 mbx_id); }; struct e1000_mbx_stats { diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c index 00e263f0c030..bffd58f7b2a1 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.c +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c @@ -32,7 +32,8 @@ * * returns SUCCESS if it successfully read message from buffer **/ -s32 igb_read_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id) +s32 igb_read_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id, + bool unlock) { struct e1000_mbx_info *mbx = &hw->mbx; s32 ret_val = -E1000_ERR_MBX; @@ -42,7 +43,7 @@ s32 igb_read_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id) size = mbx->size; if (mbx->ops.read) - ret_val = mbx->ops.read(hw, msg, size, mbx_id); + ret_val = mbx->ops.read(hw, msg, size, mbx_id, unlock); return ret_val; } @@ -125,6 +126,24 @@ s32 igb_check_for_rst(struct e1000_hw *hw, u16 mbx_id) } /** + * igb_unlock_mbx - unlock the mailbox + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the mailbox was unlocked or else ERR_MBX + **/ +s32 igb_unlock_mbx(struct e1000_hw *hw, u16 mbx_id) +{ + struct e1000_mbx_info *mbx = &hw->mbx; + s32 ret_val = -E1000_ERR_MBX; + + if (mbx->ops.unlock) + ret_val = mbx->ops.unlock(hw, mbx_id); + + return ret_val; +} + +/** * igb_poll_for_msg - Wait for message notification * @hw: pointer to the HW structure * @mbx_id: id of mailbox to write @@ -204,7 +223,7 @@ static s32 igb_read_posted_mbx(struct e1000_hw *hw, u32 *msg, u16 size, ret_val = igb_poll_for_msg(hw, mbx_id); if (!ret_val) - ret_val = mbx->ops.read(hw, msg, size, mbx_id); + ret_val = mbx->ops.read(hw, msg, size, mbx_id, true); out: return ret_val; } @@ -341,6 +360,26 @@ static s32 igb_obtain_mbx_lock_pf(struct e1000_hw *hw, u16 vf_number) } /** + * igb_release_mbx_lock_pf - release mailbox lock + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * return SUCCESS if we released the mailbox lock + **/ +static s32 igb_release_mbx_lock_pf(struct e1000_hw *hw, u16 vf_number) +{ + u32 p2v_mailbox; + + /* drop PF lock of mailbox, if set */ + p2v_mailbox = rd32(E1000_P2VMAILBOX(vf_number)); + if (p2v_mailbox & E1000_P2VMAILBOX_PFU) + wr32(E1000_P2VMAILBOX(vf_number), + p2v_mailbox & ~E1000_P2VMAILBOX_PFU); + + return 0; +} + +/** * igb_write_mbx_pf - Places a message in the mailbox * @hw: pointer to the HW structure * @msg: The message buffer @@ -385,13 +424,14 @@ out_no_write: * @msg: The message buffer * @size: Length of buffer * @vf_number: the VF index + * @unlock: unlock the mailbox when done? * * This function copies a message from the mailbox buffer to the caller's * memory buffer. The presumption is that the caller knows that there was * a message due to a VF request so no polling for message is needed. **/ static s32 igb_read_mbx_pf(struct e1000_hw *hw, u32 *msg, u16 size, - u16 vf_number) + u16 vf_number, bool unlock) { s32 ret_val; u16 i; @@ -405,8 +445,12 @@ static s32 igb_read_mbx_pf(struct e1000_hw *hw, u32 *msg, u16 size, for (i = 0; i < size; i++) msg[i] = array_rd32(E1000_VMBMEM(vf_number), i); - /* Acknowledge the message and release buffer */ - wr32(E1000_P2VMAILBOX(vf_number), E1000_P2VMAILBOX_ACK); + /* Acknowledge the message and release mailbox lock (or not) */ + if (unlock) + wr32(E1000_P2VMAILBOX(vf_number), E1000_P2VMAILBOX_ACK); + else + wr32(E1000_P2VMAILBOX(vf_number), + E1000_P2VMAILBOX_ACK | E1000_P2VMAILBOX_PFU); /* update stats */ hw->mbx.stats.msgs_rx++; @@ -437,6 +481,7 @@ s32 igb_init_mbx_params_pf(struct e1000_hw *hw) mbx->ops.check_for_msg = igb_check_for_msg_pf; mbx->ops.check_for_ack = igb_check_for_ack_pf; mbx->ops.check_for_rst = igb_check_for_rst_pf; + mbx->ops.unlock = igb_release_mbx_lock_pf; mbx->stats.msgs_tx = 0; mbx->stats.msgs_rx = 0; diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h index 3e7fed73df15..a62b08e1572e 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.h +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h @@ -67,11 +67,13 @@ #define E1000_PF_CONTROL_MSG 0x0100 /* PF control message */ -s32 igb_read_mbx(struct e1000_hw *, u32 *, u16, u16); -s32 igb_write_mbx(struct e1000_hw *, u32 *, u16, u16); -s32 igb_check_for_msg(struct e1000_hw *, u16); -s32 igb_check_for_ack(struct e1000_hw *, u16); -s32 igb_check_for_rst(struct e1000_hw *, u16); -s32 igb_init_mbx_params_pf(struct e1000_hw *); +s32 igb_read_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id, + bool unlock); +s32 igb_write_mbx(struct e1000_hw *hw, u32 *msg, u16 size, u16 mbx_id); +s32 igb_check_for_msg(struct e1000_hw *hw, u16 mbx_id); +s32 igb_check_for_ack(struct e1000_hw *hw, u16 mbx_id); +s32 igb_check_for_rst(struct e1000_hw *hw, u16 mbx_id); +s32 igb_unlock_mbx(struct e1000_hw *hw, u16 mbx_id); +s32 igb_init_mbx_params_pf(struct e1000_hw *hw); #endif /* _E1000_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index ec62410b035a..fd4a46b03cc8 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1791,6 +1791,8 @@ void igb_down(struct igb_adapter *adapter) wr32(E1000_RCTL, rctl & ~E1000_RCTL_EN); /* flush and sleep below */ + igb_nfc_filter_exit(adapter); + netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); @@ -3317,8 +3319,6 @@ static int __igb_close(struct net_device *netdev, bool suspending) igb_down(adapter); igb_free_irq(adapter); - igb_nfc_filter_exit(adapter); - igb_free_all_tx_resources(adapter); igb_free_all_rx_resources(adapter); @@ -5380,7 +5380,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); - if (!test_and_set_bit_lock(__IGB_PTP_TX_IN_PROGRESS, + if (adapter->tstamp_config.tx_type & HWTSTAMP_TX_ON && + !test_and_set_bit_lock(__IGB_PTP_TX_IN_PROGRESS, &adapter->state)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGB_TX_FLAGS_TSTAMP; @@ -5745,8 +5746,6 @@ static void igb_tsync_interrupt(struct igb_adapter *adapter) event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) ptp_clock_event(adapter->ptp_clock, &event); - else - dev_err(&adapter->pdev->dev, "unexpected SYS WRAP"); ack |= TSINTR_SYS_WRAP; } @@ -6676,32 +6675,33 @@ static void igb_rcv_msg_from_vf(struct igb_adapter *adapter, u32 vf) struct vf_data_storage *vf_data = &adapter->vf_data[vf]; s32 retval; - retval = igb_read_mbx(hw, msgbuf, E1000_VFMAILBOX_SIZE, vf); + retval = igb_read_mbx(hw, msgbuf, E1000_VFMAILBOX_SIZE, vf, false); if (retval) { /* if receive failed revoke VF CTS stats and restart init */ dev_err(&pdev->dev, "Error receiving message from VF\n"); vf_data->flags &= ~IGB_VF_FLAG_CTS; if (!time_after(jiffies, vf_data->last_nack + (2 * HZ))) - return; + goto unlock; goto out; } /* this is a message we already processed, do nothing */ if (msgbuf[0] & (E1000_VT_MSGTYPE_ACK | E1000_VT_MSGTYPE_NACK)) - return; + goto unlock; /* until the vf completes a reset it should not be * allowed to start any configuration. */ if (msgbuf[0] == E1000_VF_RESET) { + /* unlocks mailbox */ igb_vf_reset_msg(adapter, vf); return; } if (!(vf_data->flags & IGB_VF_FLAG_CTS)) { if (!time_after(jiffies, vf_data->last_nack + (2 * HZ))) - return; + goto unlock; retval = -1; goto out; } @@ -6742,7 +6742,12 @@ out: else msgbuf[0] |= E1000_VT_MSGTYPE_ACK; + /* unlocks mailbox */ igb_write_mbx(hw, msgbuf, 1, vf); + return; + +unlock: + igb_unlock_mbx(hw, vf); } static void igb_msg_task(struct igb_adapter *adapter) diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index 34faa113a8a0..a127688e83e6 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -296,8 +296,12 @@ static int igbvf_link_test(struct igbvf_adapter *adapter, u64 *data) struct e1000_hw *hw = &adapter->hw; *data = 0; + spin_lock_bh(&hw->mbx_lock); + hw->mac.ops.check_for_link(hw); + spin_unlock_bh(&hw->mbx_lock); + if (!(er32(STATUS) & E1000_STATUS_LU)) *data = 1; diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c index 01752f44ace2..c9a441632e9f 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.c +++ b/drivers/net/ethernet/intel/igbvf/mbx.c @@ -264,6 +264,8 @@ static s32 e1000_write_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size) s32 err; u16 i; + WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock)); + /* lock the mailbox to prevent pf/vf race condition */ err = e1000_obtain_mbx_lock_vf(hw); if (err) @@ -300,6 +302,8 @@ static s32 e1000_read_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size) s32 err; u16 i; + WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock)); + /* lock the mailbox to prevent pf/vf race condition */ err = e1000_obtain_mbx_lock_vf(hw); if (err) diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 1b9cbbe88f6f..1ed556911b14 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1235,7 +1235,12 @@ static void igbvf_set_rlpml(struct igbvf_adapter *adapter) struct e1000_hw *hw = &adapter->hw; max_frame_size = adapter->max_frame_size + VLAN_TAG_SIZE; + + spin_lock_bh(&hw->mbx_lock); + e1000_rlpml_set_vf(hw, max_frame_size); + + spin_unlock_bh(&hw->mbx_lock); } static int igbvf_vlan_rx_add_vid(struct net_device *netdev, @@ -1244,10 +1249,16 @@ static int igbvf_vlan_rx_add_vid(struct net_device *netdev, struct igbvf_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + spin_lock_bh(&hw->mbx_lock); + if (hw->mac.ops.set_vfta(hw, vid, true)) { dev_err(&adapter->pdev->dev, "Failed to add vlan id %d\n", vid); + spin_unlock_bh(&hw->mbx_lock); return -EINVAL; } + + spin_unlock_bh(&hw->mbx_lock); + set_bit(vid, adapter->active_vlans); return 0; } @@ -1258,11 +1269,17 @@ static int igbvf_vlan_rx_kill_vid(struct net_device *netdev, struct igbvf_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + spin_lock_bh(&hw->mbx_lock); + if (hw->mac.ops.set_vfta(hw, vid, false)) { dev_err(&adapter->pdev->dev, "Failed to remove vlan id %d\n", vid); + spin_unlock_bh(&hw->mbx_lock); return -EINVAL; } + + spin_unlock_bh(&hw->mbx_lock); + clear_bit(vid, adapter->active_vlans); return 0; } @@ -1428,7 +1445,11 @@ static void igbvf_set_multi(struct net_device *netdev) netdev_for_each_mc_addr(ha, netdev) memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); + spin_lock_bh(&hw->mbx_lock); + hw->mac.ops.update_mc_addr_list(hw, mta_list, i, 0, 0); + + spin_unlock_bh(&hw->mbx_lock); kfree(mta_list); } @@ -1449,16 +1470,24 @@ static int igbvf_set_uni(struct net_device *netdev) return -ENOSPC; } + spin_lock_bh(&hw->mbx_lock); + /* Clear all unicast MAC filters */ hw->mac.ops.set_uc_addr(hw, E1000_VF_MAC_FILTER_CLR, NULL); + spin_unlock_bh(&hw->mbx_lock); + if (!netdev_uc_empty(netdev)) { struct netdev_hw_addr *ha; /* Add MAC filters one by one */ netdev_for_each_uc_addr(ha, netdev) { + spin_lock_bh(&hw->mbx_lock); + hw->mac.ops.set_uc_addr(hw, E1000_VF_MAC_FILTER_ADD, ha->addr); + + spin_unlock_bh(&hw->mbx_lock); udelay(200); } } @@ -1503,12 +1532,16 @@ static void igbvf_reset(struct igbvf_adapter *adapter) struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; + spin_lock_bh(&hw->mbx_lock); + /* Allow time for pending master requests to run */ if (mac->ops.reset_hw(hw)) dev_err(&adapter->pdev->dev, "PF still resetting\n"); mac->ops.init_hw(hw); + spin_unlock_bh(&hw->mbx_lock); + if (is_valid_ether_addr(adapter->hw.mac.addr)) { memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len); @@ -1643,6 +1676,7 @@ static int igbvf_sw_init(struct igbvf_adapter *adapter) igbvf_irq_disable(adapter); spin_lock_init(&adapter->stats_lock); + spin_lock_init(&adapter->hw.mbx_lock); set_bit(__IGBVF_DOWN, &adapter->state); return 0; @@ -1786,8 +1820,12 @@ static int igbvf_set_mac(struct net_device *netdev, void *p) memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); + spin_lock_bh(&hw->mbx_lock); + hw->mac.ops.rar_set(hw, hw->mac.addr, 0); + spin_unlock_bh(&hw->mbx_lock); + if (!ether_addr_equal(addr->sa_data, hw->mac.addr)) return -EADDRNOTAVAIL; @@ -1858,7 +1896,12 @@ static bool igbvf_has_link(struct igbvf_adapter *adapter) if (test_bit(__IGBVF_DOWN, &adapter->state)) return false; + spin_lock_bh(&hw->mbx_lock); + ret_val = hw->mac.ops.check_for_link(hw); + + spin_unlock_bh(&hw->mbx_lock); + link_active = !hw->mac.get_link_status; /* if check for link returns error we will need to reset */ @@ -2808,6 +2851,8 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; + spin_lock_bh(&hw->mbx_lock); + /*reset the controller to put the device in a known good state */ err = hw->mac.ops.reset_hw(hw); if (err) { @@ -2824,6 +2869,8 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->addr_len); } + spin_unlock_bh(&hw->mbx_lock); + if (!is_valid_ether_addr(netdev->dev_addr)) { dev_info(&pdev->dev, "Assigning random MAC address.\n"); eth_hw_addr_random(netdev); diff --git a/drivers/net/ethernet/intel/igbvf/vf.c b/drivers/net/ethernet/intel/igbvf/vf.c index 528be116184e..9577ccf4b26a 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.c +++ b/drivers/net/ethernet/intel/igbvf/vf.c @@ -149,7 +149,7 @@ static s32 e1000_reset_hw_vf(struct e1000_hw *hw) msgbuf[0] = E1000_VF_RESET; mbx->ops.write_posted(hw, msgbuf, 1); - msleep(10); + mdelay(10); /* set our "perm_addr" based on info provided by PF */ ret_val = mbx->ops.read_posted(hw, msgbuf, 3); @@ -230,6 +230,7 @@ static void e1000_update_mc_addr_list_vf(struct e1000_hw *hw, u16 *hash_list = (u16 *)&msgbuf[1]; u32 hash_value; u32 cnt, i; + s32 ret_val; /* Each entry in the list uses 1 16 bit word. We have 30 * 16 bit words available in our HW msg buffer (minus 1 for the @@ -250,7 +251,9 @@ static void e1000_update_mc_addr_list_vf(struct e1000_hw *hw, mc_addr_list += ETH_ALEN; } - mbx->ops.write_posted(hw, msgbuf, E1000_VFMAILBOX_SIZE); + ret_val = mbx->ops.write_posted(hw, msgbuf, E1000_VFMAILBOX_SIZE); + if (!ret_val) + mbx->ops.read_posted(hw, msgbuf, 1); } /** @@ -293,11 +296,14 @@ void e1000_rlpml_set_vf(struct e1000_hw *hw, u16 max_size) { struct e1000_mbx_info *mbx = &hw->mbx; u32 msgbuf[2]; + s32 ret_val; msgbuf[0] = E1000_VF_SET_LPE; msgbuf[1] = max_size; - mbx->ops.write_posted(hw, msgbuf, 2); + ret_val = mbx->ops.write_posted(hw, msgbuf, 2); + if (!ret_val) + mbx->ops.read_posted(hw, msgbuf, 1); } /** diff --git a/drivers/net/ethernet/intel/igbvf/vf.h b/drivers/net/ethernet/intel/igbvf/vf.h index 4cf78b0dec50..d213eefb6169 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.h +++ b/drivers/net/ethernet/intel/igbvf/vf.h @@ -245,6 +245,7 @@ struct e1000_hw { struct e1000_mac_info mac; struct e1000_mbx_info mbx; + spinlock_t mbx_lock; /* serializes mailbox ops */ union { struct e1000_dev_spec_vf vf; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 4e35e7017f3d..2c19070d2a0b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -79,16 +79,28 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) switch (hw->phy.media_type) { case ixgbe_media_type_fiber: - hw->mac.ops.check_link(hw, &speed, &link_up, false); - /* if link is down, assume supported */ - if (link_up) - supported = speed == IXGBE_LINK_SPEED_1GB_FULL ? + /* flow control autoneg black list */ + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_SFP: + case IXGBE_DEV_ID_X550EM_A_SFP_N: + supported = false; + break; + default: + hw->mac.ops.check_link(hw, &speed, &link_up, false); + /* if link is down, assume supported */ + if (link_up) + supported = speed == IXGBE_LINK_SPEED_1GB_FULL ? true : false; - else - supported = true; + else + supported = true; + } + break; case ixgbe_media_type_backplane: - supported = true; + if (hw->device_id == IXGBE_DEV_ID_X550EM_X_XFI) + supported = false; + else + supported = true; break; case ixgbe_media_type_copper: /* only some copper devices support flow control autoneg */ @@ -111,6 +123,10 @@ bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) break; } + if (!supported) + hw_dbg(hw, "Device %x does not support flow control autoneg\n", + hw->device_id); + return supported; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index b45fdc98033d..f1bfae0c41d0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1018,8 +1018,12 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) struct ixgbe_q_vector *q_vector = adapter->q_vector[v_idx]; struct ixgbe_ring *ring; - ixgbe_for_each_ring(ring, q_vector->tx) - adapter->tx_ring[ring->queue_index] = NULL; + ixgbe_for_each_ring(ring, q_vector->tx) { + if (ring_is_xdp(ring)) + adapter->xdp_ring[ring->queue_index] = NULL; + else + adapter->tx_ring[ring->queue_index] = NULL; + } ixgbe_for_each_ring(ring, q_vector->rx) adapter->rx_ring[ring->queue_index] = NULL; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index f1dbdf26d8e1..d962368d08d0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -386,7 +386,7 @@ u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg) if (ixgbe_removed(reg_addr)) return IXGBE_FAILED_READ_REG; if (unlikely(hw->phy.nw_mng_if_sel & - IXGBE_NW_MNG_IF_SEL_ENABLE_10_100M)) { + IXGBE_NW_MNG_IF_SEL_SGMII_ENABLE)) { struct ixgbe_adapter *adapter; int i; @@ -2214,7 +2214,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring, struct xdp_buff *xdp) { - int result = IXGBE_XDP_PASS; + int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; u32 act; @@ -2231,6 +2231,13 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, case XDP_TX: result = ixgbe_xmit_xdp_ring(adapter, xdp); break; + case XDP_REDIRECT: + err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); + if (!err) + result = IXGBE_XDP_TX; + else + result = IXGBE_XDP_CONSUMED; + break; default: bpf_warn_invalid_xdp_action(act); /* fallthrough */ @@ -2408,6 +2415,8 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, */ wmb(); writel(ring->next_to_use, ring->tail); + + xdp_do_flush_map(); } u64_stats_update_begin(&rx_ring->syncp); @@ -5810,6 +5819,9 @@ void ixgbe_down(struct ixgbe_adapter *adapter) usleep_range(10000, 20000); + /* synchronize_sched() needed for pending XDP buffers to drain */ + if (adapter->xdp_ring[0]) + synchronize_sched(); netif_tx_stop_all_queues(netdev); /* call carrier off first to avoid false dev_watchdog timeouts */ @@ -8839,7 +8851,6 @@ static int ixgbe_delete_clsu32(struct ixgbe_adapter *adapter, } static int ixgbe_configure_clsu32_add_hnode(struct ixgbe_adapter *adapter, - __be16 protocol, struct tc_cls_u32_offload *cls) { u32 uhtid = TC_U32_USERHTID(cls->hnode.handle); @@ -8941,7 +8952,7 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter, LIST_HEAD(actions); int err; - if (tc_no_actions(exts)) + if (!tcf_exts_has_actions(exts)) return -EINVAL; tcf_exts_to_list(exts, &actions); @@ -9025,9 +9036,9 @@ static int ixgbe_clsu32_build_input(struct ixgbe_fdir_filter *input, } static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, - __be16 protocol, struct tc_cls_u32_offload *cls) { + __be16 protocol = cls->common.protocol; u32 loc = cls->knode.handle & 0xfffff; struct ixgbe_hw *hw = &adapter->hw; struct ixgbe_mat_field *field_ptr; @@ -9214,41 +9225,49 @@ free_jump: return err; } -static int __ixgbe_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc) +static int ixgbe_setup_tc_cls_u32(struct net_device *dev, + struct tc_cls_u32_offload *cls_u32) { struct ixgbe_adapter *adapter = netdev_priv(dev); - if (chain_index) + if (!is_classid_clsact_ingress(cls_u32->common.classid) || + cls_u32->common.chain_index) return -EOPNOTSUPP; - if (TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS) && - tc->type == TC_SETUP_CLSU32) { - switch (tc->cls_u32->command) { - case TC_CLSU32_NEW_KNODE: - case TC_CLSU32_REPLACE_KNODE: - return ixgbe_configure_clsu32(adapter, - proto, tc->cls_u32); - case TC_CLSU32_DELETE_KNODE: - return ixgbe_delete_clsu32(adapter, tc->cls_u32); - case TC_CLSU32_NEW_HNODE: - case TC_CLSU32_REPLACE_HNODE: - return ixgbe_configure_clsu32_add_hnode(adapter, proto, - tc->cls_u32); - case TC_CLSU32_DELETE_HNODE: - return ixgbe_configure_clsu32_del_hnode(adapter, - tc->cls_u32); - default: - return -EINVAL; - } + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return ixgbe_configure_clsu32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return ixgbe_delete_clsu32(adapter, cls_u32); + case TC_CLSU32_NEW_HNODE: + case TC_CLSU32_REPLACE_HNODE: + return ixgbe_configure_clsu32_add_hnode(adapter, cls_u32); + case TC_CLSU32_DELETE_HNODE: + return ixgbe_configure_clsu32_del_hnode(adapter, cls_u32); + default: + return -EOPNOTSUPP; } +} - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; - - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; +static int ixgbe_setup_tc_mqprio(struct net_device *dev, + struct tc_mqprio_qopt *mqprio) +{ + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + return ixgbe_setup_tc(dev, mqprio->num_tc); +} - return ixgbe_setup_tc(dev, tc->mqprio->num_tc); +static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { + case TC_SETUP_CLSU32: + return ixgbe_setup_tc_cls_u32(dev, type_data); + case TC_SETUP_MQPRIO: + return ixgbe_setup_tc_mqprio(dev, type_data); + default: + return -EOPNOTSUPP; + } } #ifdef CONFIG_PCI_IOV @@ -9823,6 +9842,53 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_xdp *xdp) } } +static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ring *ring; + int err; + + if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) + return -ENETDOWN; + + /* During program transitions its possible adapter->xdp_prog is assigned + * but ring has not been configured yet. In this case simply abort xmit. + */ + ring = adapter->xdp_prog ? adapter->xdp_ring[smp_processor_id()] : NULL; + if (unlikely(!ring)) + return -ENXIO; + + err = ixgbe_xmit_xdp_ring(adapter, xdp); + if (err != IXGBE_XDP_TX) + return -ENOSPC; + + return 0; +} + +static void ixgbe_xdp_flush(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ring *ring; + + /* Its possible the device went down between xdp xmit and flush so + * we need to ensure device is still up. + */ + if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) + return; + + ring = adapter->xdp_prog ? adapter->xdp_ring[smp_processor_id()] : NULL; + if (unlikely(!ring)) + return; + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); + + return; +} + static const struct net_device_ops ixgbe_netdev_ops = { .ndo_open = ixgbe_open, .ndo_stop = ixgbe_close, @@ -9869,6 +9935,8 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_udp_tunnel_del = ixgbe_del_udp_tunnel_port, .ndo_features_check = ixgbe_features_check, .ndo_xdp = ixgbe_xdp, + .ndo_xdp_xmit = ixgbe_xdp_xmit, + .ndo_xdp_flush = ixgbe_xdp_flush, }; /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 0760bd7eeb01..112d24c6c9ce 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -679,8 +679,9 @@ update_vlvfb: static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, int vf, int index, unsigned char *mac_addr) { - struct list_head *pos; struct vf_macvlans *entry; + struct list_head *pos; + int retval = 0; if (index <= 1) { list_for_each(pos, &adapter->vf_mvs.l) { @@ -721,13 +722,15 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, if (!entry || !entry->free) return -ENOSPC; + retval = ixgbe_add_mac_filter(adapter, mac_addr, vf); + if (retval < 0) + return retval; + entry->free = false; entry->is_macvlan = true; entry->vf = vf; memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN); - ixgbe_add_mac_filter(adapter, mac_addr, vf); - return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 9c2460c5ef1b..ffa0ee5cd0f5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -3778,8 +3778,8 @@ struct ixgbe_info { #define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_1G BIT(19) #define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G BIT(20) #define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10G BIT(21) -#define IXGBE_NW_MNG_IF_SEL_ENABLE_10_100M BIT(23) -#define IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE BIT(24) +#define IXGBE_NW_MNG_IF_SEL_SGMII_ENABLE BIT(25) +#define IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE BIT(24) /* X552 only */ #define IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT 3 #define IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD \ (0x1F << IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 72d84a065e34..19fbb2f28ea4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1555,9 +1555,14 @@ static s32 ixgbe_restart_an_internal_phy_x550em(struct ixgbe_hw *hw) **/ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) { + struct ixgbe_mac_info *mac = &hw->mac; s32 status; u32 reg_val; + /* iXFI is only supported with X552 */ + if (mac->type != ixgbe_mac_X550EM_x) + return IXGBE_ERR_LINK_SETUP; + /* Disable AN and force speed to 10G Serial. */ status = ixgbe_read_iosf_sb_reg_x550(hw, IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), @@ -1874,8 +1879,10 @@ static s32 ixgbe_setup_mac_link_t_X550em(struct ixgbe_hw *hw, else force_speed = IXGBE_LINK_SPEED_1GB_FULL; - /* If internal link mode is XFI, then setup XFI internal link. */ - if (!(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) { + /* If X552 and internal link mode is XFI, then setup XFI internal link. + */ + if (hw->mac.type == ixgbe_mac_X550EM_x && + !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) { status = ixgbe_setup_ixfi_x550em(hw, &force_speed); if (status) @@ -2404,17 +2411,30 @@ static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); /* Enable link status change alarm */ - status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, - MDIO_MMD_AN, ®); - if (status) - return status; - reg |= IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN; + /* Enable the LASI interrupts on X552 devices to receive notifications + * of the link configurations of the external PHY and correspondingly + * support the configuration of the internal iXFI link, since iXFI does + * not support auto-negotiation. This is not required for X553 devices + * having KR support, which performs auto-negotiations and which is used + * as the internal link to the external PHY. Hence adding a check here + * to avoid enabling LASI interrupts for X553 devices. + */ + if (hw->mac.type != ixgbe_mac_x550em_a) { + status = hw->phy.ops.read_reg(hw, + IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, + MDIO_MMD_AN, ®); + if (status) + return status; - status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, - MDIO_MMD_AN, reg); - if (status) - return status; + reg |= IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN; + + status = hw->phy.ops.write_reg(hw, + IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, + MDIO_MMD_AN, reg); + if (status) + return status; + } /* Enable high temperature failure and global fault alarms */ status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK, @@ -2615,7 +2635,8 @@ static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) return IXGBE_ERR_CONFIG; - if (hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE) { + if (!(hw->mac.type == ixgbe_mac_X550EM_x && + !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE))) { speed = IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL; return ixgbe_setup_kr_speed_x550em(hw, speed); @@ -2822,7 +2843,7 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) { bool pause, asm_dir; u32 reg_val; - s32 rc; + s32 rc = 0; /* Validate the requested mode */ if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { @@ -2865,32 +2886,37 @@ static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) return IXGBE_ERR_CONFIG; } - if (hw->device_id != IXGBE_DEV_ID_X550EM_X_KR && - hw->device_id != IXGBE_DEV_ID_X550EM_A_KR && - hw->device_id != IXGBE_DEV_ID_X550EM_A_KR_L) - return 0; - - rc = hw->mac.ops.read_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, - ®_val); - if (rc) - return rc; - - reg_val &= ~(IXGBE_KRM_AN_CNTL_1_SYM_PAUSE | - IXGBE_KRM_AN_CNTL_1_ASM_PAUSE); - if (pause) - reg_val |= IXGBE_KRM_AN_CNTL_1_SYM_PAUSE; - if (asm_dir) - reg_val |= IXGBE_KRM_AN_CNTL_1_ASM_PAUSE; - rc = hw->mac.ops.write_iosf_sb_reg(hw, - IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), - IXGBE_SB_IOSF_TARGET_KR_PHY, - reg_val); - - /* This device does not fully support AN. */ - hw->fc.disable_fc_autoneg = true; + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_A_KR: + case IXGBE_DEV_ID_X550EM_A_KR_L: + rc = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, + ®_val); + if (rc) + return rc; + reg_val &= ~(IXGBE_KRM_AN_CNTL_1_SYM_PAUSE | + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE); + if (pause) + reg_val |= IXGBE_KRM_AN_CNTL_1_SYM_PAUSE; + if (asm_dir) + reg_val |= IXGBE_KRM_AN_CNTL_1_ASM_PAUSE; + rc = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, + reg_val); + + /* This device does not fully support AN. */ + hw->fc.disable_fc_autoneg = true; + break; + case IXGBE_DEV_ID_X550EM_X_XFI: + hw->fc.disable_fc_autoneg = true; + break; + default: + break; + } return rc; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 9c94ea9b2b80..81c1fac00d33 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -183,8 +183,6 @@ static char mv643xx_eth_driver_version[] = "1.4"; #define DEFAULT_TX_QUEUE_SIZE 512 #define SKB_DMA_REALIGN ((PAGE_SIZE - NET_SKB_PAD) % SMP_CACHE_BYTES) -#define TSO_HEADER_SIZE 128 - /* Max number of allowed TCP segments for software TSO */ #define MV643XX_MAX_TSO_SEGS 100 #define MV643XX_MAX_SKB_DESCS (MV643XX_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS) @@ -1123,7 +1121,7 @@ static int txq_reclaim(struct tx_queue *txq, int budget, int force) struct sk_buff *skb = __skb_dequeue(&txq->tx_skb); if (!WARN_ON(!skb)) - dev_kfree_skb(skb); + dev_consume_skb_any(skb); } if (cmd_sts & ERROR_SUMMARY) { @@ -2026,7 +2024,7 @@ static void rxq_deinit(struct rx_queue *rxq) for (i = 0; i < rxq->rx_ring_size; i++) { if (rxq->rx_skb[i]) { - dev_kfree_skb(rxq->rx_skb[i]); + dev_consume_skb_any(rxq->rx_skb[i]); rxq->rx_desc_count--; } } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 0aab74c2a209..64a04975bcf8 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -281,9 +281,6 @@ */ #define MVNETA_RSS_LU_TABLE_SIZE 1 -/* TSO header size */ -#define TSO_HEADER_SIZE 128 - /* Max number of Rx descriptors */ #define MVNETA_MAX_RXD 128 @@ -4332,7 +4329,7 @@ static int mvneta_probe(struct platform_device *pdev) } } - dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; + dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO; dev->hw_features |= dev->features; dev->vlan_features |= dev->features; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 4d598ca8503a..dd0ee2691c86 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -18,6 +18,7 @@ #include <linux/inetdevice.h> #include <linux/mbus.h> #include <linux/module.h> +#include <linux/mfd/syscon.h> #include <linux/interrupt.h> #include <linux/cpumask.h> #include <linux/of.h> @@ -27,12 +28,15 @@ #include <linux/of_address.h> #include <linux/of_device.h> #include <linux/phy.h> +#include <linux/phy/phy.h> #include <linux/clk.h> #include <linux/hrtimer.h> #include <linux/ktime.h> +#include <linux/regmap.h> #include <uapi/linux/ppp_defs.h> #include <net/ip.h> #include <net/ipv6.h> +#include <net/tso.h> /* RX Fifo Registers */ #define MVPP2_RX_DATA_FIFO_SIZE_REG(port) (0x00 + 4 * (port)) @@ -120,6 +124,9 @@ #define MVPP2_TXQ_DESC_ADDR_REG 0x2084 #define MVPP2_TXQ_DESC_SIZE_REG 0x2088 #define MVPP2_TXQ_DESC_SIZE_MASK 0x3ff0 +#define MVPP2_TXQ_THRESH_REG 0x2094 +#define MVPP2_TXQ_THRESH_OFFSET 16 +#define MVPP2_TXQ_THRESH_MASK 0x3fff #define MVPP2_AGGR_TXQ_UPDATE_REG 0x2090 #define MVPP2_TXQ_INDEX_REG 0x2098 #define MVPP2_TXQ_PREF_BUF_REG 0x209c @@ -183,22 +190,25 @@ #define MVPP22_AXI_CODE_DOMAIN_SYSTEM 3 /* Interrupt Cause and Mask registers */ +#define MVPP2_ISR_TX_THRESHOLD_REG(port) (0x5140 + 4 * (port)) +#define MVPP2_MAX_ISR_TX_THRESHOLD 0xfffff0 + #define MVPP2_ISR_RX_THRESHOLD_REG(rxq) (0x5200 + 4 * (rxq)) #define MVPP2_MAX_ISR_RX_THRESHOLD 0xfffff0 -#define MVPP21_ISR_RXQ_GROUP_REG(rxq) (0x5400 + 4 * (rxq)) +#define MVPP21_ISR_RXQ_GROUP_REG(port) (0x5400 + 4 * (port)) -#define MVPP22_ISR_RXQ_GROUP_INDEX_REG 0x5400 +#define MVPP22_ISR_RXQ_GROUP_INDEX_REG 0x5400 #define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf -#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 -#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET 7 +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET 7 #define MVPP22_ISR_RXQ_GROUP_INDEX_SUBGROUP_MASK 0xf -#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 +#define MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_MASK 0x380 -#define MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG 0x5404 -#define MVPP22_ISR_RXQ_SUB_GROUP_STARTQ_MASK 0x1f -#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_MASK 0xf00 -#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET 8 +#define MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG 0x5404 +#define MVPP22_ISR_RXQ_SUB_GROUP_STARTQ_MASK 0x1f +#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_MASK 0xf00 +#define MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET 8 #define MVPP2_ISR_ENABLE_REG(port) (0x5420 + 4 * (port)) #define MVPP2_ISR_ENABLE_INTERRUPT(mask) ((mask) & 0xffff) @@ -206,6 +216,7 @@ #define MVPP2_ISR_RX_TX_CAUSE_REG(port) (0x5480 + 4 * (port)) #define MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK 0xffff #define MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK 0xff0000 +#define MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_OFFSET 16 #define MVPP2_CAUSE_RX_FIFO_OVERRUN_MASK BIT(24) #define MVPP2_CAUSE_FCS_ERR_MASK BIT(25) #define MVPP2_CAUSE_TX_FIFO_UNDERRUN_MASK BIT(26) @@ -265,7 +276,7 @@ #define MVPP2_BM_VIRT_RLS_REG 0x64c0 #define MVPP22_BM_ADDR_HIGH_RLS_REG 0x64c4 #define MVPP22_BM_ADDR_HIGH_PHYS_RLS_MASK 0xff -#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK 0xff00 +#define MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK 0xff00 #define MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT 8 /* TX Scheduler registers */ @@ -307,57 +318,87 @@ /* Per-port registers */ #define MVPP2_GMAC_CTRL_0_REG 0x0 -#define MVPP2_GMAC_PORT_EN_MASK BIT(0) -#define MVPP2_GMAC_MAX_RX_SIZE_OFFS 2 -#define MVPP2_GMAC_MAX_RX_SIZE_MASK 0x7ffc -#define MVPP2_GMAC_MIB_CNTR_EN_MASK BIT(15) +#define MVPP2_GMAC_PORT_EN_MASK BIT(0) +#define MVPP2_GMAC_PORT_TYPE_MASK BIT(1) +#define MVPP2_GMAC_MAX_RX_SIZE_OFFS 2 +#define MVPP2_GMAC_MAX_RX_SIZE_MASK 0x7ffc +#define MVPP2_GMAC_MIB_CNTR_EN_MASK BIT(15) #define MVPP2_GMAC_CTRL_1_REG 0x4 -#define MVPP2_GMAC_PERIODIC_XON_EN_MASK BIT(1) -#define MVPP2_GMAC_GMII_LB_EN_MASK BIT(5) -#define MVPP2_GMAC_PCS_LB_EN_BIT 6 -#define MVPP2_GMAC_PCS_LB_EN_MASK BIT(6) -#define MVPP2_GMAC_SA_LOW_OFFS 7 +#define MVPP2_GMAC_PERIODIC_XON_EN_MASK BIT(1) +#define MVPP2_GMAC_GMII_LB_EN_MASK BIT(5) +#define MVPP2_GMAC_PCS_LB_EN_BIT 6 +#define MVPP2_GMAC_PCS_LB_EN_MASK BIT(6) +#define MVPP2_GMAC_SA_LOW_OFFS 7 #define MVPP2_GMAC_CTRL_2_REG 0x8 -#define MVPP2_GMAC_INBAND_AN_MASK BIT(0) -#define MVPP2_GMAC_PCS_ENABLE_MASK BIT(3) -#define MVPP2_GMAC_PORT_RGMII_MASK BIT(4) -#define MVPP2_GMAC_PORT_RESET_MASK BIT(6) +#define MVPP2_GMAC_INBAND_AN_MASK BIT(0) +#define MVPP2_GMAC_FLOW_CTRL_MASK GENMASK(2, 1) +#define MVPP2_GMAC_PCS_ENABLE_MASK BIT(3) +#define MVPP2_GMAC_PORT_RGMII_MASK BIT(4) +#define MVPP2_GMAC_DISABLE_PADDING BIT(5) +#define MVPP2_GMAC_PORT_RESET_MASK BIT(6) #define MVPP2_GMAC_AUTONEG_CONFIG 0xc -#define MVPP2_GMAC_FORCE_LINK_DOWN BIT(0) -#define MVPP2_GMAC_FORCE_LINK_PASS BIT(1) -#define MVPP2_GMAC_CONFIG_MII_SPEED BIT(5) -#define MVPP2_GMAC_CONFIG_GMII_SPEED BIT(6) -#define MVPP2_GMAC_AN_SPEED_EN BIT(7) -#define MVPP2_GMAC_FC_ADV_EN BIT(9) -#define MVPP2_GMAC_CONFIG_FULL_DUPLEX BIT(12) -#define MVPP2_GMAC_AN_DUPLEX_EN BIT(13) +#define MVPP2_GMAC_FORCE_LINK_DOWN BIT(0) +#define MVPP2_GMAC_FORCE_LINK_PASS BIT(1) +#define MVPP2_GMAC_IN_BAND_AUTONEG BIT(2) +#define MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS BIT(3) +#define MVPP2_GMAC_CONFIG_MII_SPEED BIT(5) +#define MVPP2_GMAC_CONFIG_GMII_SPEED BIT(6) +#define MVPP2_GMAC_AN_SPEED_EN BIT(7) +#define MVPP2_GMAC_FC_ADV_EN BIT(9) +#define MVPP2_GMAC_FLOW_CTRL_AUTONEG BIT(11) +#define MVPP2_GMAC_CONFIG_FULL_DUPLEX BIT(12) +#define MVPP2_GMAC_AN_DUPLEX_EN BIT(13) +#define MVPP2_GMAC_STATUS0 0x10 +#define MVPP2_GMAC_STATUS0_LINK_UP BIT(0) #define MVPP2_GMAC_PORT_FIFO_CFG_1_REG 0x1c -#define MVPP2_GMAC_TX_FIFO_MIN_TH_OFFS 6 -#define MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK 0x1fc0 -#define MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v) (((v) << 6) & \ +#define MVPP2_GMAC_TX_FIFO_MIN_TH_OFFS 6 +#define MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK 0x1fc0 +#define MVPP2_GMAC_TX_FIFO_MIN_TH_MASK(v) (((v) << 6) & \ MVPP2_GMAC_TX_FIFO_MIN_TH_ALL_MASK) +#define MVPP22_GMAC_INT_STAT 0x20 +#define MVPP22_GMAC_INT_STAT_LINK BIT(1) +#define MVPP22_GMAC_INT_MASK 0x24 +#define MVPP22_GMAC_INT_MASK_LINK_STAT BIT(1) #define MVPP22_GMAC_CTRL_4_REG 0x90 -#define MVPP22_CTRL4_EXT_PIN_GMII_SEL BIT(0) -#define MVPP22_CTRL4_DP_CLK_SEL BIT(5) -#define MVPP22_CTRL4_SYNC_BYPASS BIT(6) -#define MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE BIT(7) +#define MVPP22_CTRL4_EXT_PIN_GMII_SEL BIT(0) +#define MVPP22_CTRL4_DP_CLK_SEL BIT(5) +#define MVPP22_CTRL4_SYNC_BYPASS_DIS BIT(6) +#define MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE BIT(7) +#define MVPP22_GMAC_INT_SUM_MASK 0xa4 +#define MVPP22_GMAC_INT_SUM_MASK_LINK_STAT BIT(1) /* Per-port XGMAC registers. PPv2.2 only, only for GOP port 0, * relative to port->base. */ #define MVPP22_XLG_CTRL0_REG 0x100 -#define MVPP22_XLG_CTRL0_PORT_EN BIT(0) -#define MVPP22_XLG_CTRL0_MAC_RESET_DIS BIT(1) -#define MVPP22_XLG_CTRL0_MIB_CNT_DIS BIT(14) - +#define MVPP22_XLG_CTRL0_PORT_EN BIT(0) +#define MVPP22_XLG_CTRL0_MAC_RESET_DIS BIT(1) +#define MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN BIT(7) +#define MVPP22_XLG_CTRL0_MIB_CNT_DIS BIT(14) +#define MVPP22_XLG_CTRL1_REG 0x104 +#define MVPP22_XLG_CTRL1_FRAMESIZELIMIT_OFFS 0 +#define MVPP22_XLG_CTRL1_FRAMESIZELIMIT_MASK 0x1fff +#define MVPP22_XLG_STATUS 0x10c +#define MVPP22_XLG_STATUS_LINK_UP BIT(0) +#define MVPP22_XLG_INT_STAT 0x114 +#define MVPP22_XLG_INT_STAT_LINK BIT(1) +#define MVPP22_XLG_INT_MASK 0x118 +#define MVPP22_XLG_INT_MASK_LINK BIT(1) #define MVPP22_XLG_CTRL3_REG 0x11c -#define MVPP22_XLG_CTRL3_MACMODESELECT_MASK (7 << 13) -#define MVPP22_XLG_CTRL3_MACMODESELECT_GMAC (0 << 13) -#define MVPP22_XLG_CTRL3_MACMODESELECT_10G (1 << 13) +#define MVPP22_XLG_CTRL3_MACMODESELECT_MASK (7 << 13) +#define MVPP22_XLG_CTRL3_MACMODESELECT_GMAC (0 << 13) +#define MVPP22_XLG_CTRL3_MACMODESELECT_10G (1 << 13) +#define MVPP22_XLG_EXT_INT_MASK 0x15c +#define MVPP22_XLG_EXT_INT_MASK_XLG BIT(1) +#define MVPP22_XLG_EXT_INT_MASK_GIG BIT(2) +#define MVPP22_XLG_CTRL4_REG 0x184 +#define MVPP22_XLG_CTRL4_FWD_FC BIT(5) +#define MVPP22_XLG_CTRL4_FWD_PFC BIT(6) +#define MVPP22_XLG_CTRL4_MACMODSELECT_GMAC BIT(12) /* SMI registers. PPv2.2 only, relative to priv->iface_base. */ #define MVPP22_SMI_MISC_CFG_REG 0x1204 -#define MVPP22_SMI_POLLING_EN BIT(10) +#define MVPP22_SMI_POLLING_EN BIT(10) #define MVPP22_GMAC_BASE(port) (0x7000 + (port) * 0x1000 + 0xe00) @@ -367,11 +408,44 @@ #define MVPP2_QUEUE_NEXT_DESC(q, index) \ (((index) < (q)->last_desc) ? ((index) + 1) : 0) +/* XPCS registers. PPv2.2 only */ +#define MVPP22_MPCS_BASE(port) (0x7000 + (port) * 0x1000) +#define MVPP22_MPCS_CTRL 0x14 +#define MVPP22_MPCS_CTRL_FWD_ERR_CONN BIT(10) +#define MVPP22_MPCS_CLK_RESET 0x14c +#define MAC_CLK_RESET_SD_TX BIT(0) +#define MAC_CLK_RESET_SD_RX BIT(1) +#define MAC_CLK_RESET_MAC BIT(2) +#define MVPP22_MPCS_CLK_RESET_DIV_RATIO(n) ((n) << 4) +#define MVPP22_MPCS_CLK_RESET_DIV_SET BIT(11) + +/* XPCS registers. PPv2.2 only */ +#define MVPP22_XPCS_BASE(port) (0x7400 + (port) * 0x1000) +#define MVPP22_XPCS_CFG0 0x0 +#define MVPP22_XPCS_CFG0_PCS_MODE(n) ((n) << 3) +#define MVPP22_XPCS_CFG0_ACTIVE_LANE(n) ((n) << 5) + +/* System controller registers. Accessed through a regmap. */ +#define GENCONF_SOFT_RESET1 0x1108 +#define GENCONF_SOFT_RESET1_GOP BIT(6) +#define GENCONF_PORT_CTRL0 0x1110 +#define GENCONF_PORT_CTRL0_BUS_WIDTH_SELECT BIT(1) +#define GENCONF_PORT_CTRL0_RX_DATA_SAMPLE BIT(29) +#define GENCONF_PORT_CTRL0_CLK_DIV_PHASE_CLR BIT(31) +#define GENCONF_PORT_CTRL1 0x1114 +#define GENCONF_PORT_CTRL1_EN(p) BIT(p) +#define GENCONF_PORT_CTRL1_RESET(p) (BIT(p) << 28) +#define GENCONF_CTRL0 0x1120 +#define GENCONF_CTRL0_PORT0_RGMII BIT(0) +#define GENCONF_CTRL0_PORT1_RGMII_MII BIT(1) +#define GENCONF_CTRL0_PORT1_RGMII BIT(2) + /* Various constants */ /* Coalescing */ #define MVPP2_TXDONE_COAL_PKTS_THRESH 15 #define MVPP2_TXDONE_HRTIMER_PERIOD_NS 1000000UL +#define MVPP2_TXDONE_COAL_USEC 1000 #define MVPP2_RX_COAL_PKTS 32 #define MVPP2_RX_COAL_USEC 100 @@ -685,7 +759,8 @@ enum mvpp2_prs_l3_cast { #define MVPP21_ADDR_SPACE_SZ 0 #define MVPP22_ADDR_SPACE_SZ SZ_64K -#define MVPP2_MAX_CPUS 4 +#define MVPP2_MAX_THREADS 8 +#define MVPP2_MAX_QVECS MVPP2_MAX_THREADS enum mvpp2_bm_type { MVPP2_BM_FREE, @@ -701,11 +776,17 @@ struct mvpp2 { void __iomem *lms_base; void __iomem *iface_base; - /* On PPv2.2, each CPU can access the base register through a - * separate address space, each 64 KB apart from each - * other. + /* On PPv2.2, each "software thread" can access the base + * register through a separate address space, each 64 KB apart + * from each other. Typically, such address spaces will be + * used per CPU. + */ + void __iomem *swth_base[MVPP2_MAX_THREADS]; + + /* On PPv2.2, some port control registers are located into the system + * controller space. These registers are accessible through a regmap. */ - void __iomem *cpu_base[MVPP2_MAX_CPUS]; + struct regmap *sysctrl_base; /* Common clocks */ struct clk *pp_clk; @@ -752,6 +833,18 @@ struct mvpp2_port_pcpu { struct tasklet_struct tx_done_tasklet; }; +struct mvpp2_queue_vector { + int irq; + struct napi_struct napi; + enum { MVPP2_QUEUE_VECTOR_SHARED, MVPP2_QUEUE_VECTOR_PRIVATE } type; + int sw_thread_id; + u16 sw_thread_mask; + int first_rxq; + int nrxqs; + u32 pending_cause_rx; + struct mvpp2_port *port; +}; + struct mvpp2_port { u8 id; @@ -760,7 +853,7 @@ struct mvpp2_port { */ int gop_id; - int irq; + int link_irq; struct mvpp2 *priv; @@ -768,14 +861,13 @@ struct mvpp2_port { void __iomem *base; struct mvpp2_rx_queue **rxqs; + unsigned int nrxqs; struct mvpp2_tx_queue **txqs; + unsigned int ntxqs; struct net_device *dev; int pkt_size; - u32 pending_cause_rx; - struct napi_struct napi; - /* Per-CPU port control */ struct mvpp2_port_pcpu __percpu *pcpu; @@ -788,6 +880,7 @@ struct mvpp2_port { phy_interface_t phy_interface; struct device_node *phy_node; + struct phy *comphy; unsigned int link; unsigned int duplex; unsigned int speed; @@ -797,6 +890,12 @@ struct mvpp2_port { /* Index of first port's physical RXQ */ u8 first_rxq; + + struct mvpp2_queue_vector qvecs[MVPP2_MAX_QVECS]; + unsigned int nqvecs; + bool has_tx_irqs; + + u32 tx_time_coal; }; /* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the @@ -932,6 +1031,10 @@ struct mvpp2_txq_pcpu { /* Index of the TX DMA descriptor to be cleaned up */ int txq_get_index; + + /* DMA buffer for TSO headers */ + char *tso_headers; + dma_addr_t tso_headers_dma; }; struct mvpp2_tx_queue { @@ -1062,12 +1165,14 @@ struct mvpp2_bm_pool { u32 port_map; }; -/* Static declaractions */ +/* Queue modes */ +#define MVPP2_QDIST_SINGLE_MODE 0 +#define MVPP2_QDIST_MULTI_MODE 1 -/* Number of RXQs used by single port */ -static int rxq_number = MVPP2_DEFAULT_RXQ; -/* Number of TXQs used by single port */ -static int txq_number = MVPP2_MAX_TXQ; +static int queue_mode = MVPP2_QDIST_SINGLE_MODE; + +module_param(queue_mode, int, 0444); +MODULE_PARM_DESC(queue_mode, "Set queue_mode (single=0, multi=1)"); #define MVPP2_DRIVER_NAME "mvpp2" #define MVPP2_DRIVER_VERSION "1.0" @@ -1076,12 +1181,12 @@ static int txq_number = MVPP2_MAX_TXQ; static void mvpp2_write(struct mvpp2 *priv, u32 offset, u32 data) { - writel(data, priv->cpu_base[0] + offset); + writel(data, priv->swth_base[0] + offset); } static u32 mvpp2_read(struct mvpp2 *priv, u32 offset) { - return readl(priv->cpu_base[0] + offset); + return readl(priv->swth_base[0] + offset); } /* These accessors should be used to access: @@ -1123,13 +1228,13 @@ static u32 mvpp2_read(struct mvpp2 *priv, u32 offset) static void mvpp2_percpu_write(struct mvpp2 *priv, int cpu, u32 offset, u32 data) { - writel(data, priv->cpu_base[cpu] + offset); + writel(data, priv->swth_base[cpu] + offset); } static u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu, u32 offset) { - return readl(priv->cpu_base[cpu] + offset); + return readl(priv->swth_base[cpu] + offset); } static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port, @@ -4070,7 +4175,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) port->pool_long->port_map |= (1 << port->id); - for (rxq = 0; rxq < rxq_number; rxq++) + for (rxq = 0; rxq < port->nrxqs; rxq++) mvpp2_rxq_long_pool_set(port, rxq, port->pool_long->id); } @@ -4084,7 +4189,7 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) port->pool_short->port_map |= (1 << port->id); - for (rxq = 0; rxq < rxq_number; rxq++) + for (rxq = 0; rxq < port->nrxqs; rxq++) mvpp2_rxq_short_pool_set(port, rxq, port->pool_short->id); } @@ -4125,22 +4230,40 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) static inline void mvpp2_interrupts_enable(struct mvpp2_port *port) { - int cpu, cpu_mask = 0; + int i, sw_thread_mask = 0; + + for (i = 0; i < port->nqvecs; i++) + sw_thread_mask |= port->qvecs[i].sw_thread_mask; - for_each_present_cpu(cpu) - cpu_mask |= 1 << cpu; mvpp2_write(port->priv, MVPP2_ISR_ENABLE_REG(port->id), - MVPP2_ISR_ENABLE_INTERRUPT(cpu_mask)); + MVPP2_ISR_ENABLE_INTERRUPT(sw_thread_mask)); } static inline void mvpp2_interrupts_disable(struct mvpp2_port *port) { - int cpu, cpu_mask = 0; + int i, sw_thread_mask = 0; + + for (i = 0; i < port->nqvecs; i++) + sw_thread_mask |= port->qvecs[i].sw_thread_mask; - for_each_present_cpu(cpu) - cpu_mask |= 1 << cpu; mvpp2_write(port->priv, MVPP2_ISR_ENABLE_REG(port->id), - MVPP2_ISR_DISABLE_INTERRUPT(cpu_mask)); + MVPP2_ISR_DISABLE_INTERRUPT(sw_thread_mask)); +} + +static inline void mvpp2_qvec_interrupt_enable(struct mvpp2_queue_vector *qvec) +{ + struct mvpp2_port *port = qvec->port; + + mvpp2_write(port->priv, MVPP2_ISR_ENABLE_REG(port->id), + MVPP2_ISR_ENABLE_INTERRUPT(qvec->sw_thread_mask)); +} + +static inline void mvpp2_qvec_interrupt_disable(struct mvpp2_queue_vector *qvec) +{ + struct mvpp2_port *port = qvec->port; + + mvpp2_write(port->priv, MVPP2_ISR_ENABLE_REG(port->id), + MVPP2_ISR_DISABLE_INTERRUPT(qvec->sw_thread_mask)); } /* Mask the current CPU's Rx/Tx interrupts @@ -4162,15 +4285,346 @@ static void mvpp2_interrupts_mask(void *arg) static void mvpp2_interrupts_unmask(void *arg) { struct mvpp2_port *port = arg; + u32 val; + + val = MVPP2_CAUSE_MISC_SUM_MASK | + MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; + if (port->has_tx_irqs) + val |= MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; mvpp2_percpu_write(port->priv, smp_processor_id(), - MVPP2_ISR_RX_TX_MASK_REG(port->id), - (MVPP2_CAUSE_MISC_SUM_MASK | - MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK)); + MVPP2_ISR_RX_TX_MASK_REG(port->id), val); +} + +static void +mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask) +{ + u32 val; + int i; + + if (port->priv->hw_version != MVPP22) + return; + + if (mask) + val = 0; + else + val = MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; + + for (i = 0; i < port->nqvecs; i++) { + struct mvpp2_queue_vector *v = port->qvecs + i; + + if (v->type != MVPP2_QUEUE_VECTOR_SHARED) + continue; + + mvpp2_percpu_write(port->priv, v->sw_thread_id, + MVPP2_ISR_RX_TX_MASK_REG(port->id), val); + } } /* Port configuration routines */ +static void mvpp22_gop_init_rgmii(struct mvpp2_port *port) +{ + struct mvpp2 *priv = port->priv; + u32 val; + + regmap_read(priv->sysctrl_base, GENCONF_PORT_CTRL0, &val); + val |= GENCONF_PORT_CTRL0_BUS_WIDTH_SELECT; + regmap_write(priv->sysctrl_base, GENCONF_PORT_CTRL0, val); + + regmap_read(priv->sysctrl_base, GENCONF_CTRL0, &val); + if (port->gop_id == 2) + val |= GENCONF_CTRL0_PORT0_RGMII | GENCONF_CTRL0_PORT1_RGMII; + else if (port->gop_id == 3) + val |= GENCONF_CTRL0_PORT1_RGMII_MII; + regmap_write(priv->sysctrl_base, GENCONF_CTRL0, val); +} + +static void mvpp22_gop_init_sgmii(struct mvpp2_port *port) +{ + struct mvpp2 *priv = port->priv; + u32 val; + + regmap_read(priv->sysctrl_base, GENCONF_PORT_CTRL0, &val); + val |= GENCONF_PORT_CTRL0_BUS_WIDTH_SELECT | + GENCONF_PORT_CTRL0_RX_DATA_SAMPLE; + regmap_write(priv->sysctrl_base, GENCONF_PORT_CTRL0, val); + + if (port->gop_id > 1) { + regmap_read(priv->sysctrl_base, GENCONF_CTRL0, &val); + if (port->gop_id == 2) + val &= ~GENCONF_CTRL0_PORT0_RGMII; + else if (port->gop_id == 3) + val &= ~GENCONF_CTRL0_PORT1_RGMII_MII; + regmap_write(priv->sysctrl_base, GENCONF_CTRL0, val); + } +} + +static void mvpp22_gop_init_10gkr(struct mvpp2_port *port) +{ + struct mvpp2 *priv = port->priv; + void __iomem *mpcs = priv->iface_base + MVPP22_MPCS_BASE(port->gop_id); + void __iomem *xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id); + u32 val; + + /* XPCS */ + val = readl(xpcs + MVPP22_XPCS_CFG0); + val &= ~(MVPP22_XPCS_CFG0_PCS_MODE(0x3) | + MVPP22_XPCS_CFG0_ACTIVE_LANE(0x3)); + val |= MVPP22_XPCS_CFG0_ACTIVE_LANE(2); + writel(val, xpcs + MVPP22_XPCS_CFG0); + + /* MPCS */ + val = readl(mpcs + MVPP22_MPCS_CTRL); + val &= ~MVPP22_MPCS_CTRL_FWD_ERR_CONN; + writel(val, mpcs + MVPP22_MPCS_CTRL); + + val = readl(mpcs + MVPP22_MPCS_CLK_RESET); + val &= ~(MVPP22_MPCS_CLK_RESET_DIV_RATIO(0x7) | MAC_CLK_RESET_MAC | + MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX); + val |= MVPP22_MPCS_CLK_RESET_DIV_RATIO(1); + writel(val, mpcs + MVPP22_MPCS_CLK_RESET); + + val &= ~MVPP22_MPCS_CLK_RESET_DIV_SET; + val |= MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX; + writel(val, mpcs + MVPP22_MPCS_CLK_RESET); +} + +static int mvpp22_gop_init(struct mvpp2_port *port) +{ + struct mvpp2 *priv = port->priv; + u32 val; + + if (!priv->sysctrl_base) + return 0; + + switch (port->phy_interface) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + if (port->gop_id == 0) + goto invalid_conf; + mvpp22_gop_init_rgmii(port); + break; + case PHY_INTERFACE_MODE_SGMII: + mvpp22_gop_init_sgmii(port); + break; + case PHY_INTERFACE_MODE_10GKR: + if (port->gop_id != 0) + goto invalid_conf; + mvpp22_gop_init_10gkr(port); + break; + default: + goto unsupported_conf; + } + + regmap_read(priv->sysctrl_base, GENCONF_PORT_CTRL1, &val); + val |= GENCONF_PORT_CTRL1_RESET(port->gop_id) | + GENCONF_PORT_CTRL1_EN(port->gop_id); + regmap_write(priv->sysctrl_base, GENCONF_PORT_CTRL1, val); + + regmap_read(priv->sysctrl_base, GENCONF_PORT_CTRL0, &val); + val |= GENCONF_PORT_CTRL0_CLK_DIV_PHASE_CLR; + regmap_write(priv->sysctrl_base, GENCONF_PORT_CTRL0, val); + + regmap_read(priv->sysctrl_base, GENCONF_SOFT_RESET1, &val); + val |= GENCONF_SOFT_RESET1_GOP; + regmap_write(priv->sysctrl_base, GENCONF_SOFT_RESET1, val); + +unsupported_conf: + return 0; + +invalid_conf: + netdev_err(port->dev, "Invalid port configuration\n"); + return -EINVAL; +} + +static void mvpp22_gop_unmask_irq(struct mvpp2_port *port) +{ + u32 val; + + if (phy_interface_mode_is_rgmii(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + /* Enable the GMAC link status irq for this port */ + val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK); + val |= MVPP22_GMAC_INT_SUM_MASK_LINK_STAT; + writel(val, port->base + MVPP22_GMAC_INT_SUM_MASK); + } + + if (port->gop_id == 0) { + /* Enable the XLG/GIG irqs for this port */ + val = readl(port->base + MVPP22_XLG_EXT_INT_MASK); + if (port->phy_interface == PHY_INTERFACE_MODE_10GKR) + val |= MVPP22_XLG_EXT_INT_MASK_XLG; + else + val |= MVPP22_XLG_EXT_INT_MASK_GIG; + writel(val, port->base + MVPP22_XLG_EXT_INT_MASK); + } +} + +static void mvpp22_gop_mask_irq(struct mvpp2_port *port) +{ + u32 val; + + if (port->gop_id == 0) { + val = readl(port->base + MVPP22_XLG_EXT_INT_MASK); + val &= ~(MVPP22_XLG_EXT_INT_MASK_XLG | + MVPP22_XLG_EXT_INT_MASK_GIG); + writel(val, port->base + MVPP22_XLG_EXT_INT_MASK); + } + + if (phy_interface_mode_is_rgmii(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK); + val &= ~MVPP22_GMAC_INT_SUM_MASK_LINK_STAT; + writel(val, port->base + MVPP22_GMAC_INT_SUM_MASK); + } +} + +static void mvpp22_gop_setup_irq(struct mvpp2_port *port) +{ + u32 val; + + if (phy_interface_mode_is_rgmii(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + val = readl(port->base + MVPP22_GMAC_INT_MASK); + val |= MVPP22_GMAC_INT_MASK_LINK_STAT; + writel(val, port->base + MVPP22_GMAC_INT_MASK); + } + + if (port->gop_id == 0) { + val = readl(port->base + MVPP22_XLG_INT_MASK); + val |= MVPP22_XLG_INT_MASK_LINK; + writel(val, port->base + MVPP22_XLG_INT_MASK); + } + + mvpp22_gop_unmask_irq(port); +} + +static int mvpp22_comphy_init(struct mvpp2_port *port) +{ + enum phy_mode mode; + int ret; + + if (!port->comphy) + return 0; + + switch (port->phy_interface) { + case PHY_INTERFACE_MODE_SGMII: + mode = PHY_MODE_SGMII; + break; + case PHY_INTERFACE_MODE_10GKR: + mode = PHY_MODE_10GKR; + break; + default: + return -EINVAL; + } + + ret = phy_set_mode(port->comphy, mode); + if (ret) + return ret; + + return phy_power_on(port->comphy); +} + +static void mvpp2_port_mii_gmac_configure_mode(struct mvpp2_port *port) +{ + u32 val; + + if (port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + val = readl(port->base + MVPP22_GMAC_CTRL_4_REG); + val |= MVPP22_CTRL4_SYNC_BYPASS_DIS | MVPP22_CTRL4_DP_CLK_SEL | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; + writel(val, port->base + MVPP22_GMAC_CTRL_4_REG); + + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); + val |= MVPP2_GMAC_DISABLE_PADDING; + val &= ~MVPP2_GMAC_FLOW_CTRL_MASK; + writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); + } else if (phy_interface_mode_is_rgmii(port->phy_interface)) { + val = readl(port->base + MVPP22_GMAC_CTRL_4_REG); + val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL | + MVPP22_CTRL4_SYNC_BYPASS_DIS | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + val &= ~MVPP22_CTRL4_DP_CLK_SEL; + writel(val, port->base + MVPP22_GMAC_CTRL_4_REG); + + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); + val &= ~MVPP2_GMAC_DISABLE_PADDING; + writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); + } + + /* The port is connected to a copper PHY */ + val = readl(port->base + MVPP2_GMAC_CTRL_0_REG); + val &= ~MVPP2_GMAC_PORT_TYPE_MASK; + writel(val, port->base + MVPP2_GMAC_CTRL_0_REG); + + val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + val |= MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS | + MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG | + MVPP2_GMAC_AN_DUPLEX_EN; + if (port->phy_interface == PHY_INTERFACE_MODE_SGMII) + val |= MVPP2_GMAC_IN_BAND_AUTONEG; + writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); +} + +static void mvpp2_port_mii_gmac_configure(struct mvpp2_port *port) +{ + u32 val; + + /* Force link down */ + val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + val &= ~MVPP2_GMAC_FORCE_LINK_PASS; + val |= MVPP2_GMAC_FORCE_LINK_DOWN; + writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + + /* Set the GMAC in a reset state */ + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); + val |= MVPP2_GMAC_PORT_RESET_MASK; + writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); + + /* Configure the PCS and in-band AN */ + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); + if (port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + val |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK; + } else if (phy_interface_mode_is_rgmii(port->phy_interface)) { + val &= ~MVPP2_GMAC_PCS_ENABLE_MASK; + val |= MVPP2_GMAC_PORT_RGMII_MASK; + } + writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); + + mvpp2_port_mii_gmac_configure_mode(port); + + /* Unset the GMAC reset state */ + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); + val &= ~MVPP2_GMAC_PORT_RESET_MASK; + writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); + + /* Stop forcing link down */ + val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + val &= ~MVPP2_GMAC_FORCE_LINK_DOWN; + writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); +} + +static void mvpp2_port_mii_xlg_configure(struct mvpp2_port *port) +{ + u32 val; + + if (port->gop_id != 0) + return; + + val = readl(port->base + MVPP22_XLG_CTRL0_REG); + val |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN; + writel(val, port->base + MVPP22_XLG_CTRL0_REG); + + val = readl(port->base + MVPP22_XLG_CTRL4_REG); + val &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC; + val |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC; + writel(val, port->base + MVPP22_XLG_CTRL4_REG); +} + static void mvpp22_port_mii_set(struct mvpp2_port *port) { u32 val; @@ -4188,38 +4642,18 @@ static void mvpp22_port_mii_set(struct mvpp2_port *port) writel(val, port->base + MVPP22_XLG_CTRL3_REG); } - - val = readl(port->base + MVPP22_GMAC_CTRL_4_REG); - if (port->phy_interface == PHY_INTERFACE_MODE_RGMII) - val |= MVPP22_CTRL4_EXT_PIN_GMII_SEL; - else - val &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; - val &= ~MVPP22_CTRL4_DP_CLK_SEL; - val |= MVPP22_CTRL4_SYNC_BYPASS; - val |= MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; - writel(val, port->base + MVPP22_GMAC_CTRL_4_REG); } static void mvpp2_port_mii_set(struct mvpp2_port *port) { - u32 val; - if (port->priv->hw_version == MVPP22) mvpp22_port_mii_set(port); - val = readl(port->base + MVPP2_GMAC_CTRL_2_REG); - - switch (port->phy_interface) { - case PHY_INTERFACE_MODE_SGMII: - val |= MVPP2_GMAC_INBAND_AN_MASK; - break; - case PHY_INTERFACE_MODE_RGMII: - val |= MVPP2_GMAC_PORT_RGMII_MASK; - default: - val &= ~MVPP2_GMAC_PCS_ENABLE_MASK; - } - - writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); + if (phy_interface_mode_is_rgmii(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) + mvpp2_port_mii_gmac_configure(port); + else if (port->phy_interface == PHY_INTERFACE_MODE_10GKR) + mvpp2_port_mii_xlg_configure(port); } static void mvpp2_port_fc_adv_enable(struct mvpp2_port *port) @@ -4326,6 +4760,18 @@ static inline void mvpp2_gmac_max_rx_size_set(struct mvpp2_port *port) writel(val, port->base + MVPP2_GMAC_CTRL_0_REG); } +/* Change maximum receive size of the port */ +static inline void mvpp2_xlg_max_rx_size_set(struct mvpp2_port *port) +{ + u32 val; + + val = readl(port->base + MVPP22_XLG_CTRL1_REG); + val &= ~MVPP22_XLG_CTRL1_FRAMESIZELIMIT_MASK; + val |= ((port->pkt_size - MVPP2_MH_SIZE) / 2) << + MVPP22_XLG_CTRL1_FRAMESIZELIMIT_OFFS; + writel(val, port->base + MVPP22_XLG_CTRL1_REG); +} + /* Set defaults to the MVPP2 port */ static void mvpp2_defaults_set(struct mvpp2_port *port) { @@ -4376,7 +4822,7 @@ static void mvpp2_defaults_set(struct mvpp2_port *port) MVPP2_RX_LOW_LATENCY_PKT_SIZE(256)); /* Enable Rx cache snoop */ - for (lrxq = 0; lrxq < rxq_number; lrxq++) { + for (lrxq = 0; lrxq < port->nrxqs; lrxq++) { queue = port->rxqs[lrxq]->id; val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(queue)); val |= MVPP2_SNOOP_PKT_SIZE_MASK | @@ -4394,7 +4840,7 @@ static void mvpp2_ingress_enable(struct mvpp2_port *port) u32 val; int lrxq, queue; - for (lrxq = 0; lrxq < rxq_number; lrxq++) { + for (lrxq = 0; lrxq < port->nrxqs; lrxq++) { queue = port->rxqs[lrxq]->id; val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(queue)); val &= ~MVPP2_RXQ_DISABLE_MASK; @@ -4407,7 +4853,7 @@ static void mvpp2_ingress_disable(struct mvpp2_port *port) u32 val; int lrxq, queue; - for (lrxq = 0; lrxq < rxq_number; lrxq++) { + for (lrxq = 0; lrxq < port->nrxqs; lrxq++) { queue = port->rxqs[lrxq]->id; val = mvpp2_read(port->priv, MVPP2_RXQ_CONFIG_REG(queue)); val |= MVPP2_RXQ_DISABLE_MASK; @@ -4426,7 +4872,7 @@ static void mvpp2_egress_enable(struct mvpp2_port *port) /* Enable all initialized TXs. */ qmap = 0; - for (queue = 0; queue < txq_number; queue++) { + for (queue = 0; queue < port->ntxqs; queue++) { struct mvpp2_tx_queue *txq = port->txqs[queue]; if (txq->descs) @@ -4712,7 +5158,7 @@ static void mvpp2_txq_sent_counter_clear(void *arg) struct mvpp2_port *port = arg; int queue; - for (queue = 0; queue < txq_number; queue++) { + for (queue = 0; queue < port->ntxqs; queue++) { int id = port->txqs[queue]->id; mvpp2_percpu_read(port->priv, smp_processor_id(), @@ -4753,7 +5199,7 @@ static void mvpp2_txp_max_tx_size_set(struct mvpp2_port *port) mvpp2_write(port->priv, MVPP2_TXP_SCHED_TOKEN_SIZE_REG, val); } - for (txq = 0; txq < txq_number; txq++) { + for (txq = 0; txq < port->ntxqs; txq++) { val = mvpp2_read(port->priv, MVPP2_TXQ_SCHED_TOKEN_SIZE_REG(txq)); size = val & MVPP2_TXQ_TOKEN_SIZE_MAX; @@ -4787,6 +5233,23 @@ static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, put_cpu(); } +/* For some reason in the LSP this is done on each CPU. Why ? */ +static void mvpp2_tx_pkts_coal_set(struct mvpp2_port *port, + struct mvpp2_tx_queue *txq) +{ + int cpu = get_cpu(); + u32 val; + + if (txq->done_pkts_coal > MVPP2_TXQ_THRESH_MASK) + txq->done_pkts_coal = MVPP2_TXQ_THRESH_MASK; + + val = (txq->done_pkts_coal << MVPP2_TXQ_THRESH_OFFSET); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_percpu_write(port->priv, cpu, MVPP2_TXQ_THRESH_REG, val); + + put_cpu(); +} + static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz) { u64 tmp = (u64)clk_hz * usec; @@ -4823,6 +5286,22 @@ static void mvpp2_rx_time_coal_set(struct mvpp2_port *port, mvpp2_write(port->priv, MVPP2_ISR_RX_THRESHOLD_REG(rxq->id), val); } +static void mvpp2_tx_time_coal_set(struct mvpp2_port *port) +{ + unsigned long freq = port->priv->tclk; + u32 val = mvpp2_usec_to_cycles(port->tx_time_coal, freq); + + if (val > MVPP2_MAX_ISR_TX_THRESHOLD) { + port->tx_time_coal = + mvpp2_cycles_to_usec(MVPP2_MAX_ISR_TX_THRESHOLD, freq); + + /* re-evaluate to get actual register value */ + val = mvpp2_usec_to_cycles(port->tx_time_coal, freq); + } + + mvpp2_write(port->priv, MVPP2_ISR_TX_THRESHOLD_REG(port->id), val); +} + /* Free Tx queue skbuffs */ static void mvpp2_txq_bufs_free(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, @@ -4881,7 +5360,8 @@ static void mvpp2_txq_done(struct mvpp2_port *port, struct mvpp2_tx_queue *txq, netif_tx_wake_queue(nq); } -static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause) +static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause, + int cpu) { struct mvpp2_tx_queue *txq; struct mvpp2_txq_pcpu *txq_pcpu; @@ -4892,7 +5372,7 @@ static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause) if (!txq) break; - txq_pcpu = this_cpu_ptr(txq->pcpu); + txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); if (txq_pcpu->count) { mvpp2_txq_done(port, txq, txq_pcpu); @@ -4908,15 +5388,14 @@ static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause) /* Allocate and initialize descriptors for aggr TXQ */ static int mvpp2_aggr_txq_init(struct platform_device *pdev, - struct mvpp2_tx_queue *aggr_txq, - int desc_num, int cpu, + struct mvpp2_tx_queue *aggr_txq, int cpu, struct mvpp2 *priv) { u32 txq_dma; /* Allocate memory for TX descriptors */ aggr_txq->descs = dma_alloc_coherent(&pdev->dev, - desc_num * MVPP2_DESC_ALIGNED_SIZE, + MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, &aggr_txq->descs_dma, GFP_KERNEL); if (!aggr_txq->descs) return -ENOMEM; @@ -4937,7 +5416,8 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev, MVPP22_AGGR_TXQ_DESC_ADDR_OFFS; mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_ADDR_REG(cpu), txq_dma); - mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), desc_num); + mvpp2_write(priv, MVPP2_AGGR_TXQ_DESC_SIZE_REG(cpu), + MVPP2_AGGR_TXQ_SIZE); return 0; } @@ -5118,6 +5598,14 @@ static int mvpp2_txq_init(struct mvpp2_port *port, txq_pcpu->reserved_num = 0; txq_pcpu->txq_put_index = 0; txq_pcpu->txq_get_index = 0; + + txq_pcpu->tso_headers = + dma_alloc_coherent(port->dev->dev.parent, + MVPP2_AGGR_TXQ_SIZE * TSO_HEADER_SIZE, + &txq_pcpu->tso_headers_dma, + GFP_KERNEL); + if (!txq_pcpu->tso_headers) + goto cleanup; } return 0; @@ -5125,6 +5613,11 @@ cleanup: for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); kfree(txq_pcpu->buffs); + + dma_free_coherent(port->dev->dev.parent, + MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, + txq_pcpu->tso_headers, + txq_pcpu->tso_headers_dma); } dma_free_coherent(port->dev->dev.parent, @@ -5144,6 +5637,11 @@ static void mvpp2_txq_deinit(struct mvpp2_port *port, for_each_present_cpu(cpu) { txq_pcpu = per_cpu_ptr(txq->pcpu, cpu); kfree(txq_pcpu->buffs); + + dma_free_coherent(port->dev->dev.parent, + MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE, + txq_pcpu->tso_headers, + txq_pcpu->tso_headers_dma); } if (txq->descs) @@ -5229,7 +5727,7 @@ static void mvpp2_cleanup_txqs(struct mvpp2_port *port) val |= MVPP2_TX_PORT_FLUSH_MASK(port->id); mvpp2_write(port->priv, MVPP2_TX_PORT_FLUSH_REG, val); - for (queue = 0; queue < txq_number; queue++) { + for (queue = 0; queue < port->ntxqs; queue++) { txq = port->txqs[queue]; mvpp2_txq_clean(port, txq); mvpp2_txq_deinit(port, txq); @@ -5246,7 +5744,7 @@ static void mvpp2_cleanup_rxqs(struct mvpp2_port *port) { int queue; - for (queue = 0; queue < rxq_number; queue++) + for (queue = 0; queue < port->nrxqs; queue++) mvpp2_rxq_deinit(port, port->rxqs[queue]); } @@ -5255,7 +5753,7 @@ static int mvpp2_setup_rxqs(struct mvpp2_port *port) { int queue, err; - for (queue = 0; queue < rxq_number; queue++) { + for (queue = 0; queue < port->nrxqs; queue++) { err = mvpp2_rxq_init(port, port->rxqs[queue]); if (err) goto err_cleanup; @@ -5273,13 +5771,21 @@ static int mvpp2_setup_txqs(struct mvpp2_port *port) struct mvpp2_tx_queue *txq; int queue, err; - for (queue = 0; queue < txq_number; queue++) { + for (queue = 0; queue < port->ntxqs; queue++) { txq = port->txqs[queue]; err = mvpp2_txq_init(port, txq); if (err) goto err_cleanup; } + if (port->has_tx_irqs) { + mvpp2_tx_time_coal_set(port); + for (queue = 0; queue < port->ntxqs; queue++) { + txq = port->txqs[queue]; + mvpp2_tx_pkts_coal_set(port, txq); + } + } + on_each_cpu(mvpp2_txq_sent_counter_clear, port, 1); return 0; @@ -5291,72 +5797,170 @@ err_cleanup: /* The callback for per-port interrupt */ static irqreturn_t mvpp2_isr(int irq, void *dev_id) { + struct mvpp2_queue_vector *qv = dev_id; + + mvpp2_qvec_interrupt_disable(qv); + + napi_schedule(&qv->napi); + + return IRQ_HANDLED; +} + +/* Per-port interrupt for link status changes */ +static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id) +{ struct mvpp2_port *port = (struct mvpp2_port *)dev_id; + struct net_device *dev = port->dev; + bool event = false, link = false; + u32 val; - mvpp2_interrupts_disable(port); + mvpp22_gop_mask_irq(port); - napi_schedule(&port->napi); + if (port->gop_id == 0 && + port->phy_interface == PHY_INTERFACE_MODE_10GKR) { + val = readl(port->base + MVPP22_XLG_INT_STAT); + if (val & MVPP22_XLG_INT_STAT_LINK) { + event = true; + val = readl(port->base + MVPP22_XLG_STATUS); + if (val & MVPP22_XLG_STATUS_LINK_UP) + link = true; + } + } else if (phy_interface_mode_is_rgmii(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + val = readl(port->base + MVPP22_GMAC_INT_STAT); + if (val & MVPP22_GMAC_INT_STAT_LINK) { + event = true; + val = readl(port->base + MVPP2_GMAC_STATUS0); + if (val & MVPP2_GMAC_STATUS0_LINK_UP) + link = true; + } + } + + if (!netif_running(dev) || !event) + goto handled; + + if (link) { + mvpp2_interrupts_enable(port); + mvpp2_egress_enable(port); + mvpp2_ingress_enable(port); + netif_carrier_on(dev); + netif_tx_wake_all_queues(dev); + } else { + netif_tx_stop_all_queues(dev); + netif_carrier_off(dev); + mvpp2_ingress_disable(port); + mvpp2_egress_disable(port); + + mvpp2_interrupts_disable(port); + } + +handled: + mvpp22_gop_unmask_irq(port); return IRQ_HANDLED; } +static void mvpp2_gmac_set_autoneg(struct mvpp2_port *port, + struct phy_device *phydev) +{ + u32 val; + + if (port->phy_interface != PHY_INTERFACE_MODE_RGMII && + port->phy_interface != PHY_INTERFACE_MODE_RGMII_ID && + port->phy_interface != PHY_INTERFACE_MODE_RGMII_RXID && + port->phy_interface != PHY_INTERFACE_MODE_RGMII_TXID && + port->phy_interface != PHY_INTERFACE_MODE_SGMII) + return; + + val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + val &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX | + MVPP2_GMAC_AN_SPEED_EN | + MVPP2_GMAC_AN_DUPLEX_EN); + + if (phydev->duplex) + val |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; + + if (phydev->speed == SPEED_1000) + val |= MVPP2_GMAC_CONFIG_GMII_SPEED; + else if (phydev->speed == SPEED_100) + val |= MVPP2_GMAC_CONFIG_MII_SPEED; + + writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); +} + /* Adjust link */ static void mvpp2_link_event(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); struct phy_device *phydev = dev->phydev; - int status_change = 0; + bool link_reconfigured = false; u32 val; if (phydev->link) { + if (port->phy_interface != phydev->interface && port->comphy) { + /* disable current port for reconfiguration */ + mvpp2_interrupts_disable(port); + netif_carrier_off(port->dev); + mvpp2_port_disable(port); + phy_power_off(port->comphy); + + /* comphy reconfiguration */ + port->phy_interface = phydev->interface; + mvpp22_comphy_init(port); + + /* gop/mac reconfiguration */ + mvpp22_gop_init(port); + mvpp2_port_mii_set(port); + + link_reconfigured = true; + } + if ((port->speed != phydev->speed) || (port->duplex != phydev->duplex)) { - u32 val; - - val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - val &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | - MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_CONFIG_FULL_DUPLEX | - MVPP2_GMAC_AN_SPEED_EN | - MVPP2_GMAC_AN_DUPLEX_EN); - - if (phydev->duplex) - val |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; - - if (phydev->speed == SPEED_1000) - val |= MVPP2_GMAC_CONFIG_GMII_SPEED; - else if (phydev->speed == SPEED_100) - val |= MVPP2_GMAC_CONFIG_MII_SPEED; - - writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + mvpp2_gmac_set_autoneg(port, phydev); port->duplex = phydev->duplex; port->speed = phydev->speed; } } - if (phydev->link != port->link) { - if (!phydev->link) { - port->duplex = -1; - port->speed = 0; - } - + if (phydev->link != port->link || link_reconfigured) { port->link = phydev->link; - status_change = 1; - } - if (status_change) { if (phydev->link) { - val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - val |= (MVPP2_GMAC_FORCE_LINK_PASS | - MVPP2_GMAC_FORCE_LINK_DOWN); - writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + if (port->phy_interface == PHY_INTERFACE_MODE_RGMII || + port->phy_interface == PHY_INTERFACE_MODE_RGMII_ID || + port->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID || + port->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { + val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + val |= (MVPP2_GMAC_FORCE_LINK_PASS | + MVPP2_GMAC_FORCE_LINK_DOWN); + writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + } + + mvpp2_interrupts_enable(port); + mvpp2_port_enable(port); + mvpp2_egress_enable(port); mvpp2_ingress_enable(port); + netif_carrier_on(dev); + netif_tx_wake_all_queues(dev); } else { + port->duplex = -1; + port->speed = 0; + + netif_tx_stop_all_queues(dev); + netif_carrier_off(dev); mvpp2_ingress_disable(port); mvpp2_egress_disable(port); + + mvpp2_port_disable(port); + mvpp2_interrupts_disable(port); } + phy_print_status(phydev); } } @@ -5385,8 +5989,8 @@ static void mvpp2_tx_proc_cb(unsigned long data) port_pcpu->timer_scheduled = false; /* Process all the Tx queues */ - cause = (1 << txq_number) - 1; - tx_todo = mvpp2_tx_done(port, cause); + cause = (1 << port->ntxqs) - 1; + tx_todo = mvpp2_tx_done(port, cause, smp_processor_id()); /* Set the timer in case not all the packets were processed */ if (tx_todo) @@ -5498,8 +6102,8 @@ static u32 mvpp2_skb_tx_csum(struct mvpp2_port *port, struct sk_buff *skb) } /* Main rx processing */ -static int mvpp2_rx(struct mvpp2_port *port, int rx_todo, - struct mvpp2_rx_queue *rxq) +static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, + int rx_todo, struct mvpp2_rx_queue *rxq) { struct net_device *dev = port->dev; int rx_received; @@ -5577,7 +6181,7 @@ err_drop_frame: skb->protocol = eth_type_trans(skb, dev); mvpp2_rx_csum(port, rx_status, skb); - napi_gro_receive(&port->napi, skb); + napi_gro_receive(napi, skb); } if (rcvd_pkts) { @@ -5665,6 +6269,123 @@ cleanup: return -ENOMEM; } +static inline void mvpp2_tso_put_hdr(struct sk_buff *skb, + struct net_device *dev, + struct mvpp2_tx_queue *txq, + struct mvpp2_tx_queue *aggr_txq, + struct mvpp2_txq_pcpu *txq_pcpu, + int hdr_sz) +{ + struct mvpp2_port *port = netdev_priv(dev); + struct mvpp2_tx_desc *tx_desc = mvpp2_txq_next_desc_get(aggr_txq); + dma_addr_t addr; + + mvpp2_txdesc_txq_set(port, tx_desc, txq->id); + mvpp2_txdesc_size_set(port, tx_desc, hdr_sz); + + addr = txq_pcpu->tso_headers_dma + + txq_pcpu->txq_put_index * TSO_HEADER_SIZE; + mvpp2_txdesc_offset_set(port, tx_desc, addr & MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_dma_addr_set(port, tx_desc, addr & ~MVPP2_TX_DESC_ALIGN); + + mvpp2_txdesc_cmd_set(port, tx_desc, mvpp2_skb_tx_csum(port, skb) | + MVPP2_TXD_F_DESC | + MVPP2_TXD_PADDING_DISABLE); + mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc); +} + +static inline int mvpp2_tso_put_data(struct sk_buff *skb, + struct net_device *dev, struct tso_t *tso, + struct mvpp2_tx_queue *txq, + struct mvpp2_tx_queue *aggr_txq, + struct mvpp2_txq_pcpu *txq_pcpu, + int sz, bool left, bool last) +{ + struct mvpp2_port *port = netdev_priv(dev); + struct mvpp2_tx_desc *tx_desc = mvpp2_txq_next_desc_get(aggr_txq); + dma_addr_t buf_dma_addr; + + mvpp2_txdesc_txq_set(port, tx_desc, txq->id); + mvpp2_txdesc_size_set(port, tx_desc, sz); + + buf_dma_addr = dma_map_single(dev->dev.parent, tso->data, sz, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev->dev.parent, buf_dma_addr))) { + mvpp2_txq_desc_put(txq); + return -ENOMEM; + } + + mvpp2_txdesc_offset_set(port, tx_desc, + buf_dma_addr & MVPP2_TX_DESC_ALIGN); + mvpp2_txdesc_dma_addr_set(port, tx_desc, + buf_dma_addr & ~MVPP2_TX_DESC_ALIGN); + + if (!left) { + mvpp2_txdesc_cmd_set(port, tx_desc, MVPP2_TXD_L_DESC); + if (last) { + mvpp2_txq_inc_put(port, txq_pcpu, skb, tx_desc); + return 0; + } + } else { + mvpp2_txdesc_cmd_set(port, tx_desc, 0); + } + + mvpp2_txq_inc_put(port, txq_pcpu, NULL, tx_desc); + return 0; +} + +static int mvpp2_tx_tso(struct sk_buff *skb, struct net_device *dev, + struct mvpp2_tx_queue *txq, + struct mvpp2_tx_queue *aggr_txq, + struct mvpp2_txq_pcpu *txq_pcpu) +{ + struct mvpp2_port *port = netdev_priv(dev); + struct tso_t tso; + int hdr_sz = skb_transport_offset(skb) + tcp_hdrlen(skb); + int i, len, descs = 0; + + /* Check number of available descriptors */ + if (mvpp2_aggr_desc_num_check(port->priv, aggr_txq, + tso_count_descs(skb)) || + mvpp2_txq_reserved_desc_num_proc(port->priv, txq, txq_pcpu, + tso_count_descs(skb))) + return 0; + + tso_start(skb, &tso); + len = skb->len - hdr_sz; + while (len > 0) { + int left = min_t(int, skb_shinfo(skb)->gso_size, len); + char *hdr = txq_pcpu->tso_headers + + txq_pcpu->txq_put_index * TSO_HEADER_SIZE; + + len -= left; + descs++; + + tso_build_hdr(skb, hdr, &tso, left, len == 0); + mvpp2_tso_put_hdr(skb, dev, txq, aggr_txq, txq_pcpu, hdr_sz); + + while (left > 0) { + int sz = min_t(int, tso.size, left); + left -= sz; + descs++; + + if (mvpp2_tso_put_data(skb, dev, &tso, txq, aggr_txq, + txq_pcpu, sz, left, len == 0)) + goto release; + tso_build_data(skb, &tso, sz); + } + } + + return descs; + +release: + for (i = descs - 1; i >= 0; i--) { + struct mvpp2_tx_desc *tx_desc = txq->descs + i; + tx_desc_unmap_put(port, txq, tx_desc); + } + return 0; +} + /* Main tx processing */ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) { @@ -5682,6 +6403,10 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) txq_pcpu = this_cpu_ptr(txq->pcpu); aggr_txq = &port->priv->aggr_txqs[smp_processor_id()]; + if (skb_is_gso(skb)) { + frags = mvpp2_tx_tso(skb, dev, txq, aggr_txq, txq_pcpu); + goto out; + } frags = skb_shinfo(skb)->nr_frags + 1; /* Check number of available descriptors */ @@ -5731,22 +6456,21 @@ static int mvpp2_tx(struct sk_buff *skb, struct net_device *dev) } } - txq_pcpu->reserved_num -= frags; - txq_pcpu->count += frags; - aggr_txq->count += frags; - - /* Enable transmit */ - wmb(); - mvpp2_aggr_txq_pend_desc_add(port, frags); - - if (txq_pcpu->size - txq_pcpu->count < MAX_SKB_FRAGS + 1) { - struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id); - - netif_tx_stop_queue(nq); - } out: if (frags > 0) { struct mvpp2_pcpu_stats *stats = this_cpu_ptr(port->stats); + struct netdev_queue *nq = netdev_get_tx_queue(dev, txq_id); + + txq_pcpu->reserved_num -= frags; + txq_pcpu->count += frags; + aggr_txq->count += frags; + + /* Enable transmit */ + wmb(); + mvpp2_aggr_txq_pend_desc_add(port, frags); + + if (txq_pcpu->size - txq_pcpu->count < MAX_SKB_FRAGS + 1) + netif_tx_stop_queue(nq); u64_stats_update_begin(&stats->syncp); stats->tx_packets++; @@ -5762,7 +6486,8 @@ out: mvpp2_txq_done(port, txq, txq_pcpu); /* Set the timer in case not all frags were processed */ - if (txq_pcpu->count <= frags && txq_pcpu->count > 0) { + if (!port->has_tx_irqs && txq_pcpu->count <= frags && + txq_pcpu->count > 0) { struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu); mvpp2_timer_set(port_pcpu); @@ -5783,11 +6508,14 @@ static inline void mvpp2_cause_error(struct net_device *dev, int cause) static int mvpp2_poll(struct napi_struct *napi, int budget) { - u32 cause_rx_tx, cause_rx, cause_misc; + u32 cause_rx_tx, cause_rx, cause_tx, cause_misc; int rx_done = 0; struct mvpp2_port *port = netdev_priv(napi->dev); + struct mvpp2_queue_vector *qv; int cpu = smp_processor_id(); + qv = container_of(napi, struct mvpp2_queue_vector, napi); + /* Rx/Tx cause register * * Bits 0-15: each bit indicates received packets on the Rx queue @@ -5798,11 +6526,10 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) * * Each CPU has its own Rx/Tx cause register */ - cause_rx_tx = mvpp2_percpu_read(port->priv, cpu, + cause_rx_tx = mvpp2_percpu_read(port->priv, qv->sw_thread_id, MVPP2_ISR_RX_TX_CAUSE_REG(port->id)); - cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; - cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK; + cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK; if (cause_misc) { mvpp2_cause_error(port->dev, cause_misc); @@ -5813,10 +6540,16 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK); } - cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; + cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK; + if (cause_tx) { + cause_tx >>= MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_OFFSET; + mvpp2_tx_done(port, cause_tx, qv->sw_thread_id); + } /* Process RX packets */ - cause_rx |= port->pending_cause_rx; + cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK; + cause_rx <<= qv->first_rxq; + cause_rx |= qv->pending_cause_rx; while (cause_rx && budget > 0) { int count; struct mvpp2_rx_queue *rxq; @@ -5825,7 +6558,7 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) if (!rxq) break; - count = mvpp2_rx(port, budget, rxq); + count = mvpp2_rx(port, napi, budget, rxq); rx_done += count; budget -= count; if (budget > 0) { @@ -5841,9 +6574,9 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) cause_rx = 0; napi_complete_done(napi, rx_done); - mvpp2_interrupts_enable(port); + mvpp2_qvec_interrupt_enable(qv); } - port->pending_cause_rx = cause_rx; + qv->pending_cause_rx = cause_rx; return rx_done; } @@ -5851,17 +6584,32 @@ static int mvpp2_poll(struct napi_struct *napi, int budget) static void mvpp2_start_dev(struct mvpp2_port *port) { struct net_device *ndev = port->dev; + int i; + + if (port->gop_id == 0 && + (port->phy_interface == PHY_INTERFACE_MODE_XAUI || + port->phy_interface == PHY_INTERFACE_MODE_10GKR)) + mvpp2_xlg_max_rx_size_set(port); + else + mvpp2_gmac_max_rx_size_set(port); - mvpp2_gmac_max_rx_size_set(port); mvpp2_txp_max_tx_size_set(port); - napi_enable(&port->napi); + for (i = 0; i < port->nqvecs; i++) + napi_enable(&port->qvecs[i].napi); /* Enable interrupts on all CPUs */ mvpp2_interrupts_enable(port); + if (port->priv->hw_version == MVPP22) { + mvpp22_comphy_init(port); + mvpp22_gop_init(port); + } + + mvpp2_port_mii_set(port); mvpp2_port_enable(port); - phy_start(ndev->phydev); + if (ndev->phydev) + phy_start(ndev->phydev); netif_tx_start_all_queues(port->dev); } @@ -5869,6 +6617,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port) static void mvpp2_stop_dev(struct mvpp2_port *port) { struct net_device *ndev = port->dev; + int i; /* Stop new packets from arriving to RXQs */ mvpp2_ingress_disable(port); @@ -5878,14 +6627,17 @@ static void mvpp2_stop_dev(struct mvpp2_port *port) /* Disable interrupts on all CPUs */ mvpp2_interrupts_disable(port); - napi_disable(&port->napi); + for (i = 0; i < port->nqvecs; i++) + napi_disable(&port->qvecs[i].napi); netif_carrier_off(port->dev); netif_tx_stop_all_queues(port->dev); mvpp2_egress_disable(port); mvpp2_port_disable(port); - phy_stop(ndev->phydev); + if (ndev->phydev) + phy_stop(ndev->phydev); + phy_power_off(port->comphy); } static int mvpp2_check_ringparam_valid(struct net_device *dev, @@ -5941,6 +6693,10 @@ static int mvpp2_phy_connect(struct mvpp2_port *port) { struct phy_device *phy_dev; + /* No PHY is attached */ + if (!port->phy_node) + return 0; + phy_dev = of_phy_connect(port->dev, port->phy_node, mvpp2_link_event, 0, port->phy_interface); if (!phy_dev) { @@ -5961,12 +6717,56 @@ static void mvpp2_phy_disconnect(struct mvpp2_port *port) { struct net_device *ndev = port->dev; + if (!ndev->phydev) + return; + phy_disconnect(ndev->phydev); } +static int mvpp2_irqs_init(struct mvpp2_port *port) +{ + int err, i; + + for (i = 0; i < port->nqvecs; i++) { + struct mvpp2_queue_vector *qv = port->qvecs + i; + + err = request_irq(qv->irq, mvpp2_isr, 0, port->dev->name, qv); + if (err) + goto err; + + if (qv->type == MVPP2_QUEUE_VECTOR_PRIVATE) + irq_set_affinity_hint(qv->irq, + cpumask_of(qv->sw_thread_id)); + } + + return 0; +err: + for (i = 0; i < port->nqvecs; i++) { + struct mvpp2_queue_vector *qv = port->qvecs + i; + + irq_set_affinity_hint(qv->irq, NULL); + free_irq(qv->irq, qv); + } + + return err; +} + +static void mvpp2_irqs_deinit(struct mvpp2_port *port) +{ + int i; + + for (i = 0; i < port->nqvecs; i++) { + struct mvpp2_queue_vector *qv = port->qvecs + i; + + irq_set_affinity_hint(qv->irq, NULL); + free_irq(qv->irq, qv); + } +} + static int mvpp2_open(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); + struct mvpp2 *priv = port->priv; unsigned char mac_bcast[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; int err; @@ -6006,28 +6806,44 @@ static int mvpp2_open(struct net_device *dev) goto err_cleanup_rxqs; } - err = request_irq(port->irq, mvpp2_isr, 0, dev->name, port); + err = mvpp2_irqs_init(port); if (err) { - netdev_err(port->dev, "cannot request IRQ %d\n", port->irq); + netdev_err(port->dev, "cannot init IRQs\n"); goto err_cleanup_txqs; } + if (priv->hw_version == MVPP22 && !port->phy_node && port->link_irq) { + err = request_irq(port->link_irq, mvpp2_link_status_isr, 0, + dev->name, port); + if (err) { + netdev_err(port->dev, "cannot request link IRQ %d\n", + port->link_irq); + goto err_free_irq; + } + + mvpp22_gop_setup_irq(port); + } + /* In default link is down */ netif_carrier_off(port->dev); err = mvpp2_phy_connect(port); if (err < 0) - goto err_free_irq; + goto err_free_link_irq; /* Unmask interrupts on all CPUs */ on_each_cpu(mvpp2_interrupts_unmask, port, 1); + mvpp2_shared_interrupt_mask_unmask(port, false); mvpp2_start_dev(port); return 0; +err_free_link_irq: + if (priv->hw_version == MVPP22 && !port->phy_node && port->link_irq) + free_irq(port->link_irq, port); err_free_irq: - free_irq(port->irq, port); + mvpp2_irqs_deinit(port); err_cleanup_txqs: mvpp2_cleanup_txqs(port); err_cleanup_rxqs: @@ -6039,6 +6855,7 @@ static int mvpp2_stop(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); struct mvpp2_port_pcpu *port_pcpu; + struct mvpp2 *priv = port->priv; int cpu; mvpp2_stop_dev(port); @@ -6046,14 +6863,20 @@ static int mvpp2_stop(struct net_device *dev) /* Mask interrupts on all CPUs */ on_each_cpu(mvpp2_interrupts_mask, port, 1); + mvpp2_shared_interrupt_mask_unmask(port, true); - free_irq(port->irq, port); - for_each_present_cpu(cpu) { - port_pcpu = per_cpu_ptr(port->pcpu, cpu); + if (priv->hw_version == MVPP22 && !port->phy_node && port->link_irq) + free_irq(port->link_irq, port); + + mvpp2_irqs_deinit(port); + if (!port->has_tx_irqs) { + for_each_present_cpu(cpu) { + port_pcpu = per_cpu_ptr(port->pcpu, cpu); - hrtimer_cancel(&port_pcpu->tx_done_timer); - port_pcpu->timer_scheduled = false; - tasklet_kill(&port_pcpu->tx_done_tasklet); + hrtimer_cancel(&port_pcpu->tx_done_timer); + port_pcpu->timer_scheduled = false; + tasklet_kill(&port_pcpu->tx_done_tasklet); + } } mvpp2_cleanup_rxqs(port); mvpp2_cleanup_txqs(port); @@ -6228,7 +7051,7 @@ static int mvpp2_ethtool_set_coalesce(struct net_device *dev, struct mvpp2_port *port = netdev_priv(dev); int queue; - for (queue = 0; queue < rxq_number; queue++) { + for (queue = 0; queue < port->nrxqs; queue++) { struct mvpp2_rx_queue *rxq = port->rxqs[queue]; rxq->time_coal = c->rx_coalesce_usecs; @@ -6237,10 +7060,18 @@ static int mvpp2_ethtool_set_coalesce(struct net_device *dev, mvpp2_rx_time_coal_set(port, rxq); } - for (queue = 0; queue < txq_number; queue++) { + if (port->has_tx_irqs) { + port->tx_time_coal = c->tx_coalesce_usecs; + mvpp2_tx_time_coal_set(port); + } + + for (queue = 0; queue < port->ntxqs; queue++) { struct mvpp2_tx_queue *txq = port->txqs[queue]; txq->done_pkts_coal = c->tx_max_coalesced_frames; + + if (port->has_tx_irqs) + mvpp2_tx_pkts_coal_set(port, txq); } return 0; @@ -6365,6 +7196,129 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, }; +/* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that + * had a single IRQ defined per-port. + */ +static int mvpp2_simple_queue_vectors_init(struct mvpp2_port *port, + struct device_node *port_node) +{ + struct mvpp2_queue_vector *v = &port->qvecs[0]; + + v->first_rxq = 0; + v->nrxqs = port->nrxqs; + v->type = MVPP2_QUEUE_VECTOR_SHARED; + v->sw_thread_id = 0; + v->sw_thread_mask = *cpumask_bits(cpu_online_mask); + v->port = port; + v->irq = irq_of_parse_and_map(port_node, 0); + if (v->irq <= 0) + return -EINVAL; + netif_napi_add(port->dev, &v->napi, mvpp2_poll, + NAPI_POLL_WEIGHT); + + port->nqvecs = 1; + + return 0; +} + +static int mvpp2_multi_queue_vectors_init(struct mvpp2_port *port, + struct device_node *port_node) +{ + struct mvpp2_queue_vector *v; + int i, ret; + + port->nqvecs = num_possible_cpus(); + if (queue_mode == MVPP2_QDIST_SINGLE_MODE) + port->nqvecs += 1; + + for (i = 0; i < port->nqvecs; i++) { + char irqname[16]; + + v = port->qvecs + i; + + v->port = port; + v->type = MVPP2_QUEUE_VECTOR_PRIVATE; + v->sw_thread_id = i; + v->sw_thread_mask = BIT(i); + + snprintf(irqname, sizeof(irqname), "tx-cpu%d", i); + + if (queue_mode == MVPP2_QDIST_MULTI_MODE) { + v->first_rxq = i * MVPP2_DEFAULT_RXQ; + v->nrxqs = MVPP2_DEFAULT_RXQ; + } else if (queue_mode == MVPP2_QDIST_SINGLE_MODE && + i == (port->nqvecs - 1)) { + v->first_rxq = 0; + v->nrxqs = port->nrxqs; + v->type = MVPP2_QUEUE_VECTOR_SHARED; + strncpy(irqname, "rx-shared", sizeof(irqname)); + } + + v->irq = of_irq_get_byname(port_node, irqname); + if (v->irq <= 0) { + ret = -EINVAL; + goto err; + } + + netif_napi_add(port->dev, &v->napi, mvpp2_poll, + NAPI_POLL_WEIGHT); + } + + return 0; + +err: + for (i = 0; i < port->nqvecs; i++) + irq_dispose_mapping(port->qvecs[i].irq); + return ret; +} + +static int mvpp2_queue_vectors_init(struct mvpp2_port *port, + struct device_node *port_node) +{ + if (port->has_tx_irqs) + return mvpp2_multi_queue_vectors_init(port, port_node); + else + return mvpp2_simple_queue_vectors_init(port, port_node); +} + +static void mvpp2_queue_vectors_deinit(struct mvpp2_port *port) +{ + int i; + + for (i = 0; i < port->nqvecs; i++) + irq_dispose_mapping(port->qvecs[i].irq); +} + +/* Configure Rx queue group interrupt for this port */ +static void mvpp2_rx_irqs_setup(struct mvpp2_port *port) +{ + struct mvpp2 *priv = port->priv; + u32 val; + int i; + + if (priv->hw_version == MVPP21) { + mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(port->id), + port->nrxqs); + return; + } + + /* Handle the more complicated PPv2.2 case */ + for (i = 0; i < port->nqvecs; i++) { + struct mvpp2_queue_vector *qv = port->qvecs + i; + + if (!qv->nrxqs) + continue; + + val = qv->sw_thread_id; + val |= port->id << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET; + mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val); + + val = qv->first_rxq; + val |= qv->nrxqs << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET; + mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val); + } +} + /* Initialize port HW */ static int mvpp2_port_init(struct mvpp2_port *port) { @@ -6373,15 +7327,22 @@ static int mvpp2_port_init(struct mvpp2_port *port) struct mvpp2_txq_pcpu *txq_pcpu; int queue, cpu, err; - if (port->first_rxq + rxq_number > + /* Checks for hardware constraints */ + if (port->first_rxq + port->nrxqs > MVPP2_MAX_PORTS * priv->max_port_rxqs) return -EINVAL; + if (port->nrxqs % 4 || (port->nrxqs > priv->max_port_rxqs) || + (port->ntxqs > MVPP2_MAX_TXQ)) + return -EINVAL; + /* Disable port */ mvpp2_egress_disable(port); mvpp2_port_disable(port); - port->txqs = devm_kcalloc(dev, txq_number, sizeof(*port->txqs), + port->tx_time_coal = MVPP2_TXDONE_COAL_USEC; + + port->txqs = devm_kcalloc(dev, port->ntxqs, sizeof(*port->txqs), GFP_KERNEL); if (!port->txqs) return -ENOMEM; @@ -6389,7 +7350,7 @@ static int mvpp2_port_init(struct mvpp2_port *port) /* Associate physical Tx queues to this port and initialize. * The mapping is predefined. */ - for (queue = 0; queue < txq_number; queue++) { + for (queue = 0; queue < port->ntxqs; queue++) { int queue_phy_id = mvpp2_txq_phys(port->id, queue); struct mvpp2_tx_queue *txq; @@ -6416,7 +7377,7 @@ static int mvpp2_port_init(struct mvpp2_port *port) port->txqs[queue] = txq; } - port->rxqs = devm_kcalloc(dev, rxq_number, sizeof(*port->rxqs), + port->rxqs = devm_kcalloc(dev, port->nrxqs, sizeof(*port->rxqs), GFP_KERNEL); if (!port->rxqs) { err = -ENOMEM; @@ -6424,7 +7385,7 @@ static int mvpp2_port_init(struct mvpp2_port *port) } /* Allocate and initialize Rx queue for this port */ - for (queue = 0; queue < rxq_number; queue++) { + for (queue = 0; queue < port->nrxqs; queue++) { struct mvpp2_rx_queue *rxq; /* Map physical Rx queue to port's logical Rx queue */ @@ -6441,22 +7402,10 @@ static int mvpp2_port_init(struct mvpp2_port *port) port->rxqs[queue] = rxq; } - /* Configure Rx queue group interrupt for this port */ - if (priv->hw_version == MVPP21) { - mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(port->id), - rxq_number); - } else { - u32 val; - - val = (port->id << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET); - mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val); - - val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET); - mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val); - } + mvpp2_rx_irqs_setup(port); /* Create Rx descriptor rings */ - for (queue = 0; queue < rxq_number; queue++) { + for (queue = 0; queue < port->nrxqs; queue++) { struct mvpp2_rx_queue *rxq = port->rxqs[queue]; rxq->size = port->rx_ring_size; @@ -6484,7 +7433,7 @@ static int mvpp2_port_init(struct mvpp2_port *port) return 0; err_free_percpu: - for (queue = 0; queue < txq_number; queue++) { + for (queue = 0; queue < port->ntxqs; queue++) { if (!port->txqs[queue]) continue; free_percpu(port->txqs[queue]->pcpu); @@ -6492,35 +7441,93 @@ err_free_percpu: return err; } +/* Checks if the port DT description has the TX interrupts + * described. On PPv2.1, there are no such interrupts. On PPv2.2, + * there are available, but we need to keep support for old DTs. + */ +static bool mvpp2_port_has_tx_irqs(struct mvpp2 *priv, + struct device_node *port_node) +{ + char *irqs[5] = { "rx-shared", "tx-cpu0", "tx-cpu1", + "tx-cpu2", "tx-cpu3" }; + int ret, i; + + if (priv->hw_version == MVPP21) + return false; + + for (i = 0; i < 5; i++) { + ret = of_property_match_string(port_node, "interrupt-names", + irqs[i]); + if (ret < 0) + return false; + } + + return true; +} + +static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, + struct device_node *port_node, + char **mac_from) +{ + struct mvpp2_port *port = netdev_priv(dev); + char hw_mac_addr[ETH_ALEN] = {0}; + const char *dt_mac_addr; + + dt_mac_addr = of_get_mac_address(port_node); + if (dt_mac_addr && is_valid_ether_addr(dt_mac_addr)) { + *mac_from = "device tree"; + ether_addr_copy(dev->dev_addr, dt_mac_addr); + return; + } + + if (priv->hw_version == MVPP21) { + mvpp21_get_mac_address(port, hw_mac_addr); + if (is_valid_ether_addr(hw_mac_addr)) { + *mac_from = "hardware"; + ether_addr_copy(dev->dev_addr, hw_mac_addr); + return; + } + } + + *mac_from = "random"; + eth_hw_addr_random(dev); +} + /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, struct device_node *port_node, struct mvpp2 *priv) { struct device_node *phy_node; + struct phy *comphy; struct mvpp2_port *port; struct mvpp2_port_pcpu *port_pcpu; struct net_device *dev; struct resource *res; - const char *dt_mac_addr; - const char *mac_from; - char hw_mac_addr[ETH_ALEN] = {0}; + char *mac_from = ""; + unsigned int ntxqs, nrxqs; + bool has_tx_irqs; u32 id; int features; int phy_mode; int err, i, cpu; - dev = alloc_etherdev_mqs(sizeof(*port), txq_number, rxq_number); + has_tx_irqs = mvpp2_port_has_tx_irqs(priv, port_node); + + if (!has_tx_irqs) + queue_mode = MVPP2_QDIST_SINGLE_MODE; + + ntxqs = MVPP2_MAX_TXQ; + if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_MULTI_MODE) + nrxqs = MVPP2_DEFAULT_RXQ * num_possible_cpus(); + else + nrxqs = MVPP2_DEFAULT_RXQ; + + dev = alloc_etherdev_mqs(sizeof(*port), ntxqs, nrxqs); if (!dev) return -ENOMEM; phy_node = of_parse_phandle(port_node, "phy", 0); - if (!phy_node) { - dev_err(&pdev->dev, "missing phy\n"); - err = -ENODEV; - goto err_free_netdev; - } - phy_mode = of_get_phy_mode(port_node); if (phy_mode < 0) { dev_err(&pdev->dev, "incorrect phy mode\n"); @@ -6528,6 +7535,15 @@ static int mvpp2_port_probe(struct platform_device *pdev, goto err_free_netdev; } + comphy = devm_of_phy_get(&pdev->dev, port_node, NULL); + if (IS_ERR(comphy)) { + if (PTR_ERR(comphy) == -EPROBE_DEFER) { + err = -EPROBE_DEFER; + goto err_free_netdev; + } + comphy = NULL; + } + if (of_property_read_u32(port_node, "port-id", &id)) { err = -EINVAL; dev_err(&pdev->dev, "missing port-id value\n"); @@ -6540,25 +7556,37 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->ethtool_ops = &mvpp2_eth_tool_ops; port = netdev_priv(dev); + port->dev = dev; + port->ntxqs = ntxqs; + port->nrxqs = nrxqs; + port->priv = priv; + port->has_tx_irqs = has_tx_irqs; - port->irq = irq_of_parse_and_map(port_node, 0); - if (port->irq <= 0) { - err = -EINVAL; + err = mvpp2_queue_vectors_init(port, port_node); + if (err) goto err_free_netdev; + + port->link_irq = of_irq_get_byname(port_node, "link"); + if (port->link_irq == -EPROBE_DEFER) { + err = -EPROBE_DEFER; + goto err_deinit_qvecs; } + if (port->link_irq <= 0) + /* the link irq is optional */ + port->link_irq = 0; if (of_property_read_bool(port_node, "marvell,loopback")) port->flags |= MVPP2_F_LOOPBACK; - port->priv = priv; port->id = id; if (priv->hw_version == MVPP21) - port->first_rxq = port->id * rxq_number; + port->first_rxq = port->id * port->nrxqs; else port->first_rxq = port->id * priv->max_port_rxqs; port->phy_node = phy_node; port->phy_interface = phy_mode; + port->comphy = comphy; if (priv->hw_version == MVPP21) { res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id); @@ -6572,7 +7600,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, &port->gop_id)) { err = -EINVAL; dev_err(&pdev->dev, "missing gop-port-id value\n"); - goto err_free_irq; + goto err_deinit_qvecs; } port->base = priv->iface_base + MVPP22_GMAC_BASE(port->gop_id); @@ -6585,25 +7613,10 @@ static int mvpp2_port_probe(struct platform_device *pdev, goto err_free_irq; } - dt_mac_addr = of_get_mac_address(port_node); - if (dt_mac_addr && is_valid_ether_addr(dt_mac_addr)) { - mac_from = "device tree"; - ether_addr_copy(dev->dev_addr, dt_mac_addr); - } else { - if (priv->hw_version == MVPP21) - mvpp21_get_mac_address(port, hw_mac_addr); - if (is_valid_ether_addr(hw_mac_addr)) { - mac_from = "hardware"; - ether_addr_copy(dev->dev_addr, hw_mac_addr); - } else { - mac_from = "random"; - eth_hw_addr_random(dev); - } - } + mvpp2_port_copy_mac_addr(dev, priv, port_node, &mac_from); port->tx_ring_size = MVPP2_MAX_TXD; port->rx_ring_size = MVPP2_MAX_RXD; - port->dev = dev; SET_NETDEV_DEV(dev, &pdev->dev); err = mvpp2_port_init(port); @@ -6612,7 +7625,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, goto err_free_stats; } - mvpp2_port_mii_set(port); mvpp2_port_periodic_xon_disable(port); if (priv->hw_version == MVPP21) @@ -6626,20 +7638,22 @@ static int mvpp2_port_probe(struct platform_device *pdev, goto err_free_txq_pcpu; } - for_each_present_cpu(cpu) { - port_pcpu = per_cpu_ptr(port->pcpu, cpu); + if (!port->has_tx_irqs) { + for_each_present_cpu(cpu) { + port_pcpu = per_cpu_ptr(port->pcpu, cpu); - hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED); - port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb; - port_pcpu->timer_scheduled = false; + hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb; + port_pcpu->timer_scheduled = false; - tasklet_init(&port_pcpu->tx_done_tasklet, mvpp2_tx_proc_cb, - (unsigned long)dev); + tasklet_init(&port_pcpu->tx_done_tasklet, + mvpp2_tx_proc_cb, + (unsigned long)dev); + } } - netif_napi_add(dev, &port->napi, mvpp2_poll, NAPI_POLL_WEIGHT); - features = NETIF_F_SG | NETIF_F_IP_CSUM; + features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; dev->features = features | NETIF_F_RXCSUM; dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO; dev->vlan_features |= features; @@ -6662,12 +7676,15 @@ static int mvpp2_port_probe(struct platform_device *pdev, err_free_port_pcpu: free_percpu(port->pcpu); err_free_txq_pcpu: - for (i = 0; i < txq_number; i++) + for (i = 0; i < port->ntxqs; i++) free_percpu(port->txqs[i]->pcpu); err_free_stats: free_percpu(port->stats); err_free_irq: - irq_dispose_mapping(port->irq); + if (port->link_irq) + irq_dispose_mapping(port->link_irq); +err_deinit_qvecs: + mvpp2_queue_vectors_deinit(port); err_free_netdev: of_node_put(phy_node); free_netdev(dev); @@ -6683,9 +7700,11 @@ static void mvpp2_port_remove(struct mvpp2_port *port) of_node_put(port->phy_node); free_percpu(port->pcpu); free_percpu(port->stats); - for (i = 0; i < txq_number; i++) + for (i = 0; i < port->ntxqs; i++) free_percpu(port->txqs[i]->pcpu); - irq_dispose_mapping(port->irq); + mvpp2_queue_vectors_deinit(port); + if (port->link_irq) + irq_dispose_mapping(port->link_irq); free_netdev(port->dev); } @@ -6800,13 +7819,6 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) int err, i; u32 val; - /* Checks for hardware constraints */ - if (rxq_number % 4 || (rxq_number > priv->max_port_rxqs) || - (txq_number > MVPP2_MAX_TXQ)) { - dev_err(&pdev->dev, "invalid queue size parameter\n"); - return -EINVAL; - } - /* MBUS windows configuration */ dram_target_info = mv_mbus_dram_info(); if (dram_target_info) @@ -6836,8 +7848,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) for_each_present_cpu(i) { priv->aggr_txqs[i].id = i; priv->aggr_txqs[i].size = MVPP2_AGGR_TXQ_SIZE; - err = mvpp2_aggr_txq_init(pdev, &priv->aggr_txqs[i], - MVPP2_AGGR_TXQ_SIZE, i, priv); + err = mvpp2_aggr_txq_init(pdev, &priv->aggr_txqs[i], i, priv); if (err < 0) return err; } @@ -6845,23 +7856,6 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) /* Rx Fifo Init */ mvpp2_rx_fifo_init(priv); - /* Reset Rx queue group interrupt configuration */ - for (i = 0; i < MVPP2_MAX_PORTS; i++) { - if (priv->hw_version == MVPP21) { - mvpp2_write(priv, MVPP21_ISR_RXQ_GROUP_REG(i), - rxq_number); - continue; - } else { - u32 val; - - val = (i << MVPP22_ISR_RXQ_GROUP_INDEX_GROUP_OFFSET); - mvpp2_write(priv, MVPP22_ISR_RXQ_GROUP_INDEX_REG, val); - - val = (rxq_number << MVPP22_ISR_RXQ_SUB_GROUP_SIZE_OFFSET); - mvpp2_write(priv, MVPP22_ISR_RXQ_SUB_GROUP_CONFIG_REG, val); - } - } - if (priv->hw_version == MVPP21) writel(MVPP2_EXT_GLOBAL_CTRL_DEFAULT, priv->lms_base + MVPP2_MNG_EXTENDED_GLOBAL_CTRL_REG); @@ -6892,7 +7886,7 @@ static int mvpp2_probe(struct platform_device *pdev) struct mvpp2 *priv; struct resource *res; void __iomem *base; - int port_count, cpu; + int port_count, i; int err; priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); @@ -6917,14 +7911,25 @@ static int mvpp2_probe(struct platform_device *pdev) priv->iface_base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(priv->iface_base)) return PTR_ERR(priv->iface_base); + + priv->sysctrl_base = + syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "marvell,system-controller"); + if (IS_ERR(priv->sysctrl_base)) + /* The system controller regmap is optional for dt + * compatibility reasons. When not provided, the + * configuration of the GoP relies on the + * firmware/bootloader. + */ + priv->sysctrl_base = NULL; } - for_each_present_cpu(cpu) { + for (i = 0; i < MVPP2_MAX_THREADS; i++) { u32 addr_space_sz; addr_space_sz = (priv->hw_version == MVPP21 ? MVPP21_ADDR_SPACE_SZ : MVPP22_ADDR_SPACE_SZ); - priv->cpu_base[cpu] = base + cpu * addr_space_sz; + priv->swth_base[i] = base + i * addr_space_sz; } if (priv->hw_version == MVPP21) diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 5d7d94de4e00..8a835e82256a 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3516,7 +3516,7 @@ static const char *skge_board_name(const struct skge_hw *hw) if (skge_chips[i].id == hw->chip_id) return skge_chips[i].name; - snprintf(buf, sizeof buf, "chipid 0x%x", hw->chip_id); + snprintf(buf, sizeof(buf), "chipid 0x%x", hw->chip_id); return buf; } diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index 698bb89aa901..f9149d2a4694 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -7,11 +7,11 @@ config NET_VENDOR_MEDIATEK if NET_VENDOR_MEDIATEK config NET_MEDIATEK_SOC - tristate "MediaTek MT7623 Gigabit ethernet support" - depends on NET_VENDOR_MEDIATEK && (MACH_MT7623 || MACH_MT2701) + tristate "MediaTek SoC Gigabit Ethernet support" + depends on NET_VENDOR_MEDIATEK select PHYLIB ---help--- This driver supports the gigabit ethernet MACs in the - MediaTek MT2701/MT7623 chipset family. + MediaTek SoC family. endif #NET_VENDOR_MEDIATEK diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index e588a0cdb074..5e81a7263654 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -53,7 +53,8 @@ static const struct mtk_ethtool_stats { }; static const char * const mtk_clks_source_name[] = { - "ethif", "esw", "gp1", "gp2", "trgpll" + "ethif", "esw", "gp0", "gp1", "gp2", "trgpll", "sgmii_tx250m", + "sgmii_rx250m", "sgmii_cdr_ref", "sgmii_cdr_fb", "sgmii_ck", "eth2pll" }; void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg) @@ -163,6 +164,47 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed) mtk_w32(eth, val, TRGMII_TCK_CTRL); } +static void mtk_gmac_sgmii_hw_setup(struct mtk_eth *eth, int mac_id) +{ + u32 val; + + /* Setup the link timer and QPHY power up inside SGMIISYS */ + regmap_write(eth->sgmiisys, SGMSYS_PCS_LINK_TIMER, + SGMII_LINK_TIMER_DEFAULT); + + regmap_read(eth->sgmiisys, SGMSYS_SGMII_MODE, &val); + val |= SGMII_REMOTE_FAULT_DIS; + regmap_write(eth->sgmiisys, SGMSYS_SGMII_MODE, val); + + regmap_read(eth->sgmiisys, SGMSYS_PCS_CONTROL_1, &val); + val |= SGMII_AN_RESTART; + regmap_write(eth->sgmiisys, SGMSYS_PCS_CONTROL_1, val); + + regmap_read(eth->sgmiisys, SGMSYS_QPHY_PWR_STATE_CTRL, &val); + val &= ~SGMII_PHYA_PWD; + regmap_write(eth->sgmiisys, SGMSYS_QPHY_PWR_STATE_CTRL, val); + + /* Determine MUX for which GMAC uses the SGMII interface */ + if (MTK_HAS_CAPS(eth->soc->caps, MTK_DUAL_GMAC_SHARED_SGMII)) { + regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); + val &= ~SYSCFG0_SGMII_MASK; + val |= !mac_id ? SYSCFG0_SGMII_GMAC1 : SYSCFG0_SGMII_GMAC2; + regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val); + + dev_info(eth->dev, "setup shared sgmii for gmac=%d\n", + mac_id); + } + + /* Setup the GMAC1 going through SGMII path when SoC also support + * ESW on GMAC1 + */ + if (MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC1_ESW | MTK_GMAC1_SGMII) && + !mac_id) { + mtk_w32(eth, 0, MTK_MAC_MISC); + dev_info(eth->dev, "setup gmac1 going through sgmii"); + } +} + static void mtk_phy_link_adjust(struct net_device *dev) { struct mtk_mac *mac = netdev_priv(dev); @@ -185,7 +227,8 @@ static void mtk_phy_link_adjust(struct net_device *dev) break; }; - if (mac->id == 0 && !mac->trgmii) + if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GMAC1_TRGMII) && + !mac->id && !mac->trgmii) mtk_gmac0_rgmii_adjust(mac->hw, dev->phydev->speed); if (dev->phydev->link) @@ -269,6 +312,7 @@ static int mtk_phy_connect(struct net_device *dev) if (!np) return -ENODEV; + mac->ge_mode = 0; switch (of_get_phy_mode(np)) { case PHY_INTERFACE_MODE_TRGMII: mac->trgmii = true; @@ -276,7 +320,10 @@ static int mtk_phy_connect(struct net_device *dev) case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII: - mac->ge_mode = 0; + break; + case PHY_INTERFACE_MODE_SGMII: + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII)) + mtk_gmac_sgmii_hw_setup(eth, mac->id); break; case PHY_INTERFACE_MODE_MII: mac->ge_mode = 1; @@ -1032,7 +1079,6 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) unsigned int done[MTK_MAX_DEVS]; unsigned int bytes[MTK_MAX_DEVS]; u32 cpu, dma; - static int condition; int total = 0, i; memset(done, 0, sizeof(done)); @@ -1056,10 +1102,8 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) mac = 1; skb = tx_buf->skb; - if (!skb) { - condition = 1; + if (!skb) break; - } if (skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC) { bytes[mac] += skb->len; @@ -1241,9 +1285,19 @@ static void mtk_tx_clean(struct mtk_eth *eth) static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) { - struct mtk_rx_ring *ring = ð->rx_ring[ring_no]; + struct mtk_rx_ring *ring; int rx_data_len, rx_dma_size; int i; + u32 offset = 0; + + if (rx_flag == MTK_RX_FLAGS_QDMA) { + if (ring_no) + return -EINVAL; + ring = ð->rx_ring_qdma; + offset = 0x1000; + } else { + ring = ð->rx_ring[ring_no]; + } if (rx_flag == MTK_RX_FLAGS_HWLRO) { rx_data_len = MTK_MAX_LRO_RX_LENGTH; @@ -1293,17 +1347,16 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) */ wmb(); - mtk_w32(eth, ring->phys, MTK_PRX_BASE_PTR_CFG(ring_no)); - mtk_w32(eth, rx_dma_size, MTK_PRX_MAX_CNT_CFG(ring_no)); - mtk_w32(eth, ring->calc_idx, ring->crx_idx_reg); - mtk_w32(eth, MTK_PST_DRX_IDX_CFG(ring_no), MTK_PDMA_RST_IDX); + mtk_w32(eth, ring->phys, MTK_PRX_BASE_PTR_CFG(ring_no) + offset); + mtk_w32(eth, rx_dma_size, MTK_PRX_MAX_CNT_CFG(ring_no) + offset); + mtk_w32(eth, ring->calc_idx, ring->crx_idx_reg + offset); + mtk_w32(eth, MTK_PST_DRX_IDX_CFG(ring_no), MTK_PDMA_RST_IDX + offset); return 0; } -static void mtk_rx_clean(struct mtk_eth *eth, int ring_no) +static void mtk_rx_clean(struct mtk_eth *eth, struct mtk_rx_ring *ring) { - struct mtk_rx_ring *ring = ð->rx_ring[ring_no]; int i; if (ring->data && ring->dma) { @@ -1629,6 +1682,10 @@ static int mtk_dma_init(struct mtk_eth *eth) if (err) return err; + err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_QDMA); + if (err) + return err; + err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_NORMAL); if (err) return err; @@ -1668,12 +1725,13 @@ static void mtk_dma_free(struct mtk_eth *eth) eth->phy_scratch_ring = 0; } mtk_tx_clean(eth); - mtk_rx_clean(eth, 0); + mtk_rx_clean(eth, ð->rx_ring[0]); + mtk_rx_clean(eth, ð->rx_ring_qdma); if (eth->hwlro) { mtk_hwlro_rx_uninit(eth); for (i = 1; i < MTK_MAX_RX_RING_NUM; i++) - mtk_rx_clean(eth, i); + mtk_rx_clean(eth, ð->rx_ring[i]); } kfree(eth->scratch_head); @@ -1740,7 +1798,9 @@ static int mtk_start_dma(struct mtk_eth *eth) mtk_w32(eth, MTK_TX_WB_DDONE | MTK_TX_DMA_EN | - MTK_DMA_SIZE_16DWORDS | MTK_NDP_CO_PRO, + MTK_DMA_SIZE_16DWORDS | MTK_NDP_CO_PRO | + MTK_RX_DMA_EN | MTK_RX_2B_OFFSET | + MTK_RX_BT_32DWORDS, MTK_QDMA_GLO_CFG); mtk_w32(eth, @@ -1837,9 +1897,36 @@ static void ethsys_reset(struct mtk_eth *eth, u32 reset_bits) mdelay(10); } +static void mtk_clk_disable(struct mtk_eth *eth) +{ + int clk; + + for (clk = MTK_CLK_MAX - 1; clk >= 0; clk--) + clk_disable_unprepare(eth->clks[clk]); +} + +static int mtk_clk_enable(struct mtk_eth *eth) +{ + int clk, ret; + + for (clk = 0; clk < MTK_CLK_MAX ; clk++) { + ret = clk_prepare_enable(eth->clks[clk]); + if (ret) + goto err_disable_clks; + } + + return 0; + +err_disable_clks: + while (--clk >= 0) + clk_disable_unprepare(eth->clks[clk]); + + return ret; +} + static int mtk_hw_init(struct mtk_eth *eth) { - int i, val; + int i, val, ret; if (test_and_set_bit(MTK_HW_INIT, ð->state)) return 0; @@ -1847,10 +1934,10 @@ static int mtk_hw_init(struct mtk_eth *eth) pm_runtime_enable(eth->dev); pm_runtime_get_sync(eth->dev); - clk_prepare_enable(eth->clks[MTK_CLK_ETHIF]); - clk_prepare_enable(eth->clks[MTK_CLK_ESW]); - clk_prepare_enable(eth->clks[MTK_CLK_GP1]); - clk_prepare_enable(eth->clks[MTK_CLK_GP2]); + ret = mtk_clk_enable(eth); + if (ret) + goto err_disable_pm; + ethsys_reset(eth, RSTCTRL_FE); ethsys_reset(eth, RSTCTRL_PPE); @@ -1918,6 +2005,12 @@ static int mtk_hw_init(struct mtk_eth *eth) } return 0; + +err_disable_pm: + pm_runtime_put_sync(eth->dev); + pm_runtime_disable(eth->dev); + + return ret; } static int mtk_hw_deinit(struct mtk_eth *eth) @@ -1925,10 +2018,7 @@ static int mtk_hw_deinit(struct mtk_eth *eth) if (!test_and_clear_bit(MTK_HW_INIT, ð->state)) return 0; - clk_disable_unprepare(eth->clks[MTK_CLK_GP2]); - clk_disable_unprepare(eth->clks[MTK_CLK_GP1]); - clk_disable_unprepare(eth->clks[MTK_CLK_ESW]); - clk_disable_unprepare(eth->clks[MTK_CLK_ETHIF]); + mtk_clk_disable(eth); pm_runtime_put_sync(eth->dev); pm_runtime_disable(eth->dev); @@ -2395,6 +2485,7 @@ static int mtk_get_chip_id(struct mtk_eth *eth, u32 *chip_id) static bool mtk_is_hwlro_supported(struct mtk_eth *eth) { switch (eth->chip_id) { + case MT7622_ETH: case MT7623_ETH: return true; } @@ -2406,6 +2497,7 @@ static int mtk_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct device_node *mac_np; + const struct of_device_id *match; struct mtk_eth *eth; int err; int i; @@ -2414,6 +2506,9 @@ static int mtk_probe(struct platform_device *pdev) if (!eth) return -ENOMEM; + match = of_match_device(of_mtk_match, &pdev->dev); + eth->soc = (struct mtk_soc_data *)match->data; + eth->dev = &pdev->dev; eth->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(eth->base)) @@ -2430,6 +2525,16 @@ static int mtk_probe(struct platform_device *pdev) return PTR_ERR(eth->ethsys); } + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII)) { + eth->sgmiisys = + syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "mediatek,sgmiisys"); + if (IS_ERR(eth->sgmiisys)) { + dev_err(&pdev->dev, "no sgmiisys regmap found\n"); + return PTR_ERR(eth->sgmiisys); + } + } + eth->pctl = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "mediatek,pctl"); if (IS_ERR(eth->pctl)) { @@ -2450,7 +2555,12 @@ static int mtk_probe(struct platform_device *pdev) if (IS_ERR(eth->clks[i])) { if (PTR_ERR(eth->clks[i]) == -EPROBE_DEFER) return -EPROBE_DEFER; - return -ENODEV; + if (eth->soc->required_clks & BIT(i)) { + dev_err(&pdev->dev, "clock %s not found\n", + mtk_clks_source_name[i]); + return -EINVAL; + } + eth->clks[i] = NULL; } } @@ -2553,8 +2663,25 @@ static int mtk_remove(struct platform_device *pdev) return 0; } +static const struct mtk_soc_data mt2701_data = { + .caps = MTK_GMAC1_TRGMII, + .required_clks = MT7623_CLKS_BITMAP +}; + +static const struct mtk_soc_data mt7622_data = { + .caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW, + .required_clks = MT7622_CLKS_BITMAP +}; + +static const struct mtk_soc_data mt7623_data = { + .caps = MTK_GMAC1_TRGMII, + .required_clks = MT7623_CLKS_BITMAP +}; + const struct of_device_id of_mtk_match[] = { - { .compatible = "mediatek,mt2701-eth" }, + { .compatible = "mediatek,mt2701-eth", .data = &mt2701_data}, + { .compatible = "mediatek,mt7622-eth", .data = &mt7622_data}, + { .compatible = "mediatek,mt7623-eth", .data = &mt7623_data}, {}, }; MODULE_DEVICE_TABLE(of, of_mtk_match); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 5868a09f623a..3d3c24a28112 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -302,6 +302,9 @@ #define PHY_IAC_REG_SHIFT 25 #define PHY_IAC_TIMEOUT HZ +#define MTK_MAC_MISC 0x1000c +#define MTK_MUX_TO_ESW BIT(0) + /* Mac control registers */ #define MTK_MAC_MCR(x) (0x10100 + (x * 0x100)) #define MAC_MCR_MAX_RX_1536 BIT(24) @@ -357,11 +360,15 @@ #define ETHSYS_CHIPID0_3 0x0 #define ETHSYS_CHIPID4_7 0x4 #define MT7623_ETH 7623 +#define MT7622_ETH 7622 /* ethernet subsystem config register */ #define ETHSYS_SYSCFG0 0x14 #define SYSCFG0_GE_MASK 0x3 #define SYSCFG0_GE_MODE(x, y) (x << (12 + (y * 2))) +#define SYSCFG0_SGMII_MASK (3 << 8) +#define SYSCFG0_SGMII_GMAC1 ((2 << 8) & GENMASK(9, 8)) +#define SYSCFG0_SGMII_GMAC2 ((3 << 8) & GENMASK(9, 8)) /* ethernet subsystem clock register */ #define ETHSYS_CLKCFG0 0x2c @@ -372,6 +379,23 @@ #define RSTCTRL_FE BIT(6) #define RSTCTRL_PPE BIT(31) +/* SGMII subsystem config registers */ +/* Register to auto-negotiation restart */ +#define SGMSYS_PCS_CONTROL_1 0x0 +#define SGMII_AN_RESTART BIT(9) + +/* Register to programmable link timer, the unit in 2 * 8ns */ +#define SGMSYS_PCS_LINK_TIMER 0x18 +#define SGMII_LINK_TIMER_DEFAULT (0x186a0 & GENMASK(19, 0)) + +/* Register to control remote fault */ +#define SGMSYS_SGMII_MODE 0x20 +#define SGMII_REMOTE_FAULT_DIS BIT(8) + +/* Register to power up QPHY */ +#define SGMSYS_QPHY_PWR_STATE_CTRL 0xe8 +#define SGMII_PHYA_PWD BIT(4) + struct mtk_rx_dma { unsigned int rxd1; unsigned int rxd2; @@ -437,12 +461,31 @@ enum mtk_tx_flags { enum mtk_clks_map { MTK_CLK_ETHIF, MTK_CLK_ESW, + MTK_CLK_GP0, MTK_CLK_GP1, MTK_CLK_GP2, MTK_CLK_TRGPLL, + MTK_CLK_SGMII_TX_250M, + MTK_CLK_SGMII_RX_250M, + MTK_CLK_SGMII_CDR_REF, + MTK_CLK_SGMII_CDR_FB, + MTK_CLK_SGMII_CK, + MTK_CLK_ETH2PLL, MTK_CLK_MAX }; +#define MT7623_CLKS_BITMAP (BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) | \ + BIT(MTK_CLK_GP1) | BIT(MTK_CLK_GP2) | \ + BIT(MTK_CLK_TRGPLL)) +#define MT7622_CLKS_BITMAP (BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) | \ + BIT(MTK_CLK_GP0) | BIT(MTK_CLK_GP1) | \ + BIT(MTK_CLK_GP2) | \ + BIT(MTK_CLK_SGMII_TX_250M) | \ + BIT(MTK_CLK_SGMII_RX_250M) | \ + BIT(MTK_CLK_SGMII_CDR_REF) | \ + BIT(MTK_CLK_SGMII_CDR_FB) | \ + BIT(MTK_CLK_SGMII_CK) | \ + BIT(MTK_CLK_ETH2PLL)) enum mtk_dev_state { MTK_HW_INIT, MTK_RESETTING @@ -489,6 +532,7 @@ struct mtk_tx_ring { enum mtk_rx_flags { MTK_RX_FLAGS_NORMAL = 0, MTK_RX_FLAGS_HWLRO, + MTK_RX_FLAGS_QDMA, }; /* struct mtk_rx_ring - This struct holds info describing a RX ring @@ -511,6 +555,28 @@ struct mtk_rx_ring { u32 crx_idx_reg; }; +#define MTK_TRGMII BIT(0) +#define MTK_GMAC1_TRGMII (BIT(1) | MTK_TRGMII) +#define MTK_ESW BIT(4) +#define MTK_GMAC1_ESW (BIT(5) | MTK_ESW) +#define MTK_SGMII BIT(8) +#define MTK_GMAC1_SGMII (BIT(9) | MTK_SGMII) +#define MTK_GMAC2_SGMII (BIT(10) | MTK_SGMII) +#define MTK_DUAL_GMAC_SHARED_SGMII (BIT(11) | MTK_GMAC1_SGMII | \ + MTK_GMAC2_SGMII) +#define MTK_HAS_CAPS(caps, _x) (((caps) & (_x)) == (_x)) + +/* struct mtk_eth_data - This is the structure holding all differences + * among various plaforms + * @caps Flags shown the extra capability for the SoC + * @required_clks Flags shown the bitmap for required clocks on + * the target SoC + */ +struct mtk_soc_data { + u32 caps; + u32 required_clks; +}; + /* currently no SoC has more than 2 macs */ #define MTK_MAX_DEVS 2 @@ -529,11 +595,14 @@ struct mtk_rx_ring { * @msg_enable: Ethtool msg level * @ethsys: The register map pointing at the range used to setup * MII modes + * @sgmiisys: The register map pointing at the range used to setup + * SGMII modes * @pctl: The register map pointing at the range used to setup * GMAC port drive/slew values * @dma_refcnt: track how many netdevs are using the DMA engine - * @tx_ring: Pointer to the memore holding info about the TX ring - * @rx_ring: Pointer to the memore holding info about the RX ring + * @tx_ring: Pointer to the memory holding info about the TX ring + * @rx_ring: Pointer to the memory holding info about the RX ring + * @rx_ring_qdma: Pointer to the memory holding info about the QDMA RX ring * @tx_napi: The TX NAPI struct * @rx_napi: The RX NAPI struct * @scratch_ring: Newer SoCs need memory for a second HW managed TX ring @@ -542,7 +611,8 @@ struct mtk_rx_ring { * @clks: clock array for all clocks required * @mii_bus: If there is a bus we need to create an instance for it * @pending_work: The workqueue used to reset the dma ring - * @state Initialization and runtime state of the device. + * @state: Initialization and runtime state of the device + * @soc: Holding specific data among vaious SoCs */ struct mtk_eth { @@ -558,12 +628,14 @@ struct mtk_eth { u32 msg_enable; unsigned long sysclk; struct regmap *ethsys; + struct regmap *sgmiisys; struct regmap *pctl; u32 chip_id; bool hwlro; atomic_t dma_refcnt; struct mtk_tx_ring tx_ring; struct mtk_rx_ring rx_ring[MTK_MAX_RX_RING_NUM]; + struct mtk_rx_ring rx_ring_qdma; struct napi_struct tx_napi; struct napi_struct rx_napi; struct mtk_tx_dma *scratch_ring; @@ -574,6 +646,8 @@ struct mtk_eth { struct mii_bus *mii_bus; struct work_struct pending_work; unsigned long state; + + const struct mtk_soc_data *soc; }; /* struct mtk_mac - the structure that holds the info about the MACs of the diff --git a/drivers/net/ethernet/mellanox/Kconfig b/drivers/net/ethernet/mellanox/Kconfig index 84a200764111..872548cd9431 100644 --- a/drivers/net/ethernet/mellanox/Kconfig +++ b/drivers/net/ethernet/mellanox/Kconfig @@ -5,9 +5,10 @@ config NET_VENDOR_MELLANOX bool "Mellanox devices" default y - depends on PCI + depends on PCI || I2C ---help--- - If you have a network (Ethernet) card belonging to this class, say Y. + If you have a network (Ethernet or RDMA) device belonging to this + class, say Y. Note that the answer to this question doesn't directly affect the kernel: saying N will just cause the configurator to skip all diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index b651c1210555..6dabd983e7e0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -186,7 +186,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, bitmap->effective_len = bitmap->avail; spin_lock_init(&bitmap->lock); bitmap->table = kzalloc(BITS_TO_LONGS(bitmap->max) * - sizeof (long), GFP_KERNEL); + sizeof(long), GFP_KERNEL); if (!bitmap->table) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 78b89ceb4f46..6a9086dc1e92 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -1958,19 +1958,19 @@ static void mlx4_allocate_port_vpps(struct mlx4_dev *dev, int port) int i; int err; int num_vfs; - u16 availible_vpp; + u16 available_vpp; u8 vpp_param[MLX4_NUM_UP]; struct mlx4_qos_manager *port_qos; struct mlx4_priv *priv = mlx4_priv(dev); - err = mlx4_ALLOCATE_VPP_get(dev, port, &availible_vpp, vpp_param); + err = mlx4_ALLOCATE_VPP_get(dev, port, &available_vpp, vpp_param); if (err) { - mlx4_info(dev, "Failed query availible VPPs\n"); + mlx4_info(dev, "Failed query available VPPs\n"); return; } port_qos = &priv->mfunc.master.qos_ctl[port]; - num_vfs = (availible_vpp / + num_vfs = (available_vpp / bitmap_weight(port_qos->priority_bm, MLX4_NUM_UP)); for (i = 0; i < MLX4_NUM_UP; i++) { @@ -1985,14 +1985,14 @@ static void mlx4_allocate_port_vpps(struct mlx4_dev *dev, int port) } /* Query actual allocated VPP, just to make sure */ - err = mlx4_ALLOCATE_VPP_get(dev, port, &availible_vpp, vpp_param); + err = mlx4_ALLOCATE_VPP_get(dev, port, &available_vpp, vpp_param); if (err) { - mlx4_info(dev, "Failed query availible VPPs\n"); + mlx4_info(dev, "Failed query available VPPs\n"); return; } port_qos->num_of_qos_vfs = num_vfs; - mlx4_dbg(dev, "Port %d Availible VPPs %d\n", port, availible_vpp); + mlx4_dbg(dev, "Port %d Available VPPs %d\n", port, available_vpp); for (i = 0; i < MLX4_NUM_UP; i++) mlx4_dbg(dev, "Port %d UP %d Allocated %d VPPs\n", port, i, @@ -2637,7 +2637,7 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev) int err = 0; priv->cmd.context = kmalloc(priv->cmd.max_cmds * - sizeof (struct mlx4_cmd_context), + sizeof(struct mlx4_cmd_context), GFP_KERNEL); if (!priv->cmd.context) return -ENOMEM; @@ -2695,7 +2695,7 @@ struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev) { struct mlx4_cmd_mailbox *mailbox; - mailbox = kmalloc(sizeof *mailbox, GFP_KERNEL); + mailbox = kmalloc(sizeof(*mailbox), GFP_KERNEL); if (!mailbox) return ERR_PTR(-ENOMEM); @@ -2891,7 +2891,7 @@ static int mlx4_set_vport_qos(struct mlx4_priv *priv, int slave, int port, memset(vpp_qos, 0, sizeof(struct mlx4_vport_qos_param) * MLX4_NUM_UP); if (slave > port_qos->num_of_qos_vfs) { - mlx4_info(dev, "No availible VPP resources for this VF\n"); + mlx4_info(dev, "No available VPP resources for this VF\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index f849eec21824..1e487acb4667 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -209,12 +209,10 @@ int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) cq->moder_cnt, cq->moder_time); } -int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) +void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) { mlx4_cq_arm(&cq->mcq, MLX4_CQ_DB_REQ_NOT, priv->mdev->uar_map, &priv->mdev->uar_lock); - - return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index 2b0cbca4beb5..686e18de9a97 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -147,7 +147,7 @@ void mlx4_en_update_loopback_state(struct net_device *dev, mutex_unlock(&priv->mdev->state_lock); } -static int mlx4_en_get_profile(struct mlx4_en_dev *mdev) +static void mlx4_en_get_profile(struct mlx4_en_dev *mdev) { struct mlx4_en_profile *params = &mdev->profile; int i; @@ -176,8 +176,6 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev) params->prof[i].rss_rings = 0; params->prof[i].inline_thold = inline_thold; } - - return 0; } static void *mlx4_en_get_netdev(struct mlx4_dev *dev, void *ctx, u8 port) @@ -309,10 +307,7 @@ static void *mlx4_en_add(struct mlx4_dev *dev) } /* Build device profile according to supplied module parameters */ - if (mlx4_en_get_profile(mdev)) { - mlx4_err(mdev, "Bad module parameters, aborting\n"); - goto err_mr; - } + mlx4_en_get_profile(mdev); /* Configure which ports to start according to module parameters */ mdev->port_cnt = 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index e3e6d9fa69fd..9c218f1cfc6c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -130,19 +130,20 @@ out: return err; } -static int __mlx4_en_setup_tc(struct net_device *dev, u32 handle, - u32 chain_index, __be16 proto, - struct tc_to_netdev *tc) +static int __mlx4_en_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; + struct tc_mqprio_qopt *mqprio = type_data; + + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - if (tc->mqprio->num_tc && tc->mqprio->num_tc != MLX4_EN_NUM_UP_HIGH) + if (mqprio->num_tc && mqprio->num_tc != MLX4_EN_NUM_UP_HIGH) return -EINVAL; - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - return mlx4_en_alloc_tx_queue_per_tc(dev, tc->mqprio->num_tc); + return mlx4_en_alloc_tx_queue_per_tc(dev, mqprio->num_tc); } #ifdef CONFIG_RFS_ACCEL @@ -732,6 +733,21 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64); } +static void mlx4_en_update_user_mac(struct mlx4_en_priv *priv, + unsigned char new_mac[ETH_ALEN + 2]) +{ + struct mlx4_en_dev *mdev = priv->mdev; + int err; + + if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_USER_MAC_EN)) + return; + + err = mlx4_SET_PORT_user_mac(mdev->dev, priv->port, new_mac); + if (err) + en_err(priv, "Failed to pass user MAC(%pM) to Firmware for port %d, with error %d\n", + new_mac, priv->port, err); +} + static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv, unsigned char new_mac[ETH_ALEN + 2]) { @@ -766,8 +782,12 @@ static int mlx4_en_set_mac(struct net_device *dev, void *addr) mutex_lock(&mdev->state_lock); memcpy(new_mac, saddr->sa_data, ETH_ALEN); err = mlx4_en_do_set_mac(priv, new_mac); - if (!err) - memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN); + if (err) + goto out; + + memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN); + mlx4_en_update_user_mac(priv, new_mac); +out: mutex_unlock(&mdev->state_lock); return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 86d2d42d658d..5a47f9669621 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -44,7 +44,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, struct mlx4_en_dev *mdev = priv->mdev; struct net_device *dev = priv->dev; - memset(context, 0, sizeof *context); + memset(context, 0, sizeof(*context)); context->flags = cpu_to_be32(7 << 16 | rss << MLX4_RSS_QPC_FLAG_OFFSET); context->pd = cpu_to_be32(mdev->priv_pdn); context->mtu_msgmax = 0xff; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index ec24c4057be6..b97a55c827eb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -1056,7 +1056,7 @@ static int mlx4_en_config_rss_qp(struct mlx4_en_priv *priv, int qpn, } qp->event = mlx4_en_sqp_event; - memset(context, 0, sizeof *context); + memset(context, 0, sizeof(*context)); mlx4_en_fill_qp_context(priv, ring->actual_size, ring->stride, 0, 0, qpn, ring->cqn, -1, context); context->db_rec_addr = cpu_to_be64(ring->wqres.db.dma); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index a81db2582555..8a32a8f7f9c0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -644,7 +644,7 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, void *fragptr) { struct mlx4_wqe_inline_seg *inl = &tx_desc->inl; - int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl; + int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof(*inl); unsigned int hlen = skb_headlen(skb); if (skb->len <= spc) { diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 07406cf2eacd..6f57c052053e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -259,7 +259,7 @@ int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port) if (!s_slave->active) return 0; - memset(&eqe, 0, sizeof eqe); + memset(&eqe, 0, sizeof(eqe)); eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; eqe.subtype = MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE; @@ -276,7 +276,7 @@ int mlx4_gen_guid_change_eqe(struct mlx4_dev *dev, int slave, u8 port) /*don't send if we don't have the that slave */ if (dev->persist->num_vfs < slave) return 0; - memset(&eqe, 0, sizeof eqe); + memset(&eqe, 0, sizeof(eqe)); eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; eqe.subtype = MLX4_DEV_PMC_SUBTYPE_GUID_INFO; @@ -295,7 +295,7 @@ int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port, /*don't send if we don't have the that slave */ if (dev->persist->num_vfs < slave) return 0; - memset(&eqe, 0, sizeof eqe); + memset(&eqe, 0, sizeof(eqe)); eqe.type = MLX4_EVENT_TYPE_PORT_CHANGE; eqe.subtype = port_subtype_change; @@ -432,7 +432,7 @@ int mlx4_gen_slaves_port_mgt_ev(struct mlx4_dev *dev, u8 port, int attr) { struct mlx4_eqe eqe; - memset(&eqe, 0, sizeof eqe); + memset(&eqe, 0, sizeof(eqe)); eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; eqe.subtype = MLX4_DEV_PMC_SUBTYPE_PORT_INFO; @@ -726,7 +726,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) } memcpy(&priv->mfunc.master.comm_arm_bit_vector, eqe->event.comm_channel_arm.bit_vec, - sizeof eqe->event.comm_channel_arm.bit_vec); + sizeof(eqe->event.comm_channel_arm.bit_vec)); queue_work(priv->mfunc.master.comm_wq, &priv->mfunc.master.comm_work); break; @@ -984,15 +984,15 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent, */ npages = PAGE_ALIGN(eq->nent * dev->caps.eqe_size) / PAGE_SIZE; - eq->page_list = kmalloc(npages * sizeof *eq->page_list, - GFP_KERNEL); + eq->page_list = kmalloc_array(npages, sizeof(*eq->page_list), + GFP_KERNEL); if (!eq->page_list) goto err_out; for (i = 0; i < npages; ++i) eq->page_list[i].buf = NULL; - dma_list = kmalloc(npages * sizeof *dma_list, GFP_KERNEL); + dma_list = kmalloc_array(npages, sizeof(*dma_list), GFP_KERNEL); if (!dma_list) goto err_out_free; @@ -1161,7 +1161,7 @@ int mlx4_alloc_eq_table(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); priv->eq_table.eq = kcalloc(dev->caps.num_eqs - dev->caps.reserved_eqs, - sizeof *priv->eq_table.eq, GFP_KERNEL); + sizeof(*priv->eq_table.eq), GFP_KERNEL); if (!priv->eq_table.eq) return -ENOMEM; @@ -1180,7 +1180,7 @@ int mlx4_init_eq_table(struct mlx4_dev *dev) int i; priv->eq_table.uar_map = kcalloc(mlx4_num_eq_uar(dev), - sizeof *priv->eq_table.uar_map, + sizeof(*priv->eq_table.uar_map), GFP_KERNEL); if (!priv->eq_table.uar_map) { err = -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 041c0ed65929..16c09949afd5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -36,6 +36,7 @@ #include <linux/mlx4/cmd.h> #include <linux/module.h> #include <linux/cache.h> +#include <linux/kernel.h> #include "fw.h" #include "icm.h" @@ -57,7 +58,7 @@ MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)"); do { \ void *__p = (char *) (source) + (offset); \ u64 val; \ - switch (sizeof (dest)) { \ + switch (sizeof(dest)) { \ case 1: (dest) = *(u8 *) __p; break; \ case 2: (dest) = be16_to_cpup(__p); break; \ case 4: (dest) = be32_to_cpup(__p); break; \ @@ -162,6 +163,7 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [35] = "Diag counters per port", [36] = "QinQ VST mode support", [37] = "sl to vl mapping table change event support", + [38] = "user MAC support", }; int i; @@ -679,22 +681,22 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port, if (func_cap->flags1 & QUERY_FUNC_CAP_VF_ENABLE_QP0) { MLX4_GET(qkey, outbox, QUERY_FUNC_CAP_PRIV_VF_QKEY_OFFSET); - func_cap->qp0_qkey = qkey; + func_cap->spec_qps.qp0_qkey = qkey; } else { - func_cap->qp0_qkey = 0; + func_cap->spec_qps.qp0_qkey = 0; } MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP0_TUNNEL); - func_cap->qp0_tunnel_qpn = size & 0xFFFFFF; + func_cap->spec_qps.qp0_tunnel = size & 0xFFFFFF; MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP0_PROXY); - func_cap->qp0_proxy_qpn = size & 0xFFFFFF; + func_cap->spec_qps.qp0_proxy = size & 0xFFFFFF; MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP1_TUNNEL); - func_cap->qp1_tunnel_qpn = size & 0xFFFFFF; + func_cap->spec_qps.qp1_tunnel = size & 0xFFFFFF; MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP1_PROXY); - func_cap->qp1_proxy_qpn = size & 0xFFFFFF; + func_cap->spec_qps.qp1_proxy = size & 0xFFFFFF; if (func_cap->flags1 & QUERY_FUNC_CAP_FLAGS1_NIC_INFO) MLX4_GET(func_cap->phys_port_id, outbox, @@ -778,6 +780,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) #define QUERY_DEV_CAP_MAX_DESC_SZ_SQ_OFFSET 0x52 #define QUERY_DEV_CAP_MAX_SG_RQ_OFFSET 0x55 #define QUERY_DEV_CAP_MAX_DESC_SZ_RQ_OFFSET 0x56 +#define QUERY_DEV_CAP_USER_MAC_EN_OFFSET 0x5C #define QUERY_DEV_CAP_SVLAN_BY_QP_OFFSET 0x5D #define QUERY_DEV_CAP_MAX_QP_MCG_OFFSET 0x61 #define QUERY_DEV_CAP_RSVD_MCG_OFFSET 0x62 @@ -949,6 +952,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) MLX4_GET(size, outbox, QUERY_DEV_CAP_MAX_DESC_SZ_SQ_OFFSET); dev_cap->max_sq_desc_sz = size; + MLX4_GET(field, outbox, QUERY_DEV_CAP_USER_MAC_EN_OFFSET); + if (field & (1 << 2)) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_USER_MAC_EN; MLX4_GET(field, outbox, QUERY_DEV_CAP_SVLAN_BY_QP_OFFSET); if (field & 0x1) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP; @@ -1534,7 +1540,7 @@ int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt) for (i = 0; i < mlx4_icm_size(&iter) >> lg; ++i) { if (virt != -1) { pages[nent * 2] = cpu_to_be64(virt); - virt += 1 << lg; + virt += 1ULL << lg; } pages[nent * 2 + 1] = @@ -2450,14 +2456,14 @@ int mlx4_config_dev_retrieval(struct mlx4_dev *dev, csum_mask = (config_dev.rx_checksum_val >> CONFIG_DEV_RX_CSUM_MODE_PORT1_BIT_OFFSET) & CONFIG_DEV_RX_CSUM_MODE_MASK; - if (csum_mask >= sizeof(config_dev_csum_flags)/sizeof(config_dev_csum_flags[0])) + if (csum_mask >= ARRAY_SIZE(config_dev_csum_flags)) return -EINVAL; params->rx_csum_flags_port_1 = config_dev_csum_flags[csum_mask]; csum_mask = (config_dev.rx_checksum_val >> CONFIG_DEV_RX_CSUM_MODE_PORT2_BIT_OFFSET) & CONFIG_DEV_RX_CSUM_MODE_MASK; - if (csum_mask >= sizeof(config_dev_csum_flags)/sizeof(config_dev_csum_flags[0])) + if (csum_mask >= ARRAY_SIZE(config_dev_csum_flags)) return -EINVAL; params->rx_csum_flags_port_2 = config_dev_csum_flags[csum_mask]; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index b52ba01aa486..cd6399c76bfd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -144,11 +144,7 @@ struct mlx4_func_cap { int max_eq; int reserved_eq; int mcg_quota; - u32 qp0_qkey; - u32 qp0_tunnel_qpn; - u32 qp0_proxy_qpn; - u32 qp1_tunnel_qpn; - u32 qp1_proxy_qpn; + struct mlx4_spec_qps spec_qps; u32 reserved_lkey; u8 physical_port; u8 flags0; diff --git a/drivers/net/ethernet/mellanox/mlx4/fw_qos.c b/drivers/net/ethernet/mellanox/mlx4/fw_qos.c index 8f2fde0487c4..3a09d7122d3b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw_qos.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw_qos.c @@ -65,7 +65,7 @@ struct mlx4_set_port_scheduler_context { /* Granular Qos (per VF) section */ struct mlx4_alloc_vpp_param { - __be32 availible_vpp; + __be32 available_vpp; __be32 vpp_p_up[MLX4_NUM_UP]; }; @@ -157,7 +157,7 @@ int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw, EXPORT_SYMBOL(mlx4_SET_PORT_SCHEDULER); int mlx4_ALLOCATE_VPP_get(struct mlx4_dev *dev, u8 port, - u16 *availible_vpp, u8 *vpp_p_up) + u16 *available_vpp, u8 *vpp_p_up) { int i; int err; @@ -179,7 +179,7 @@ int mlx4_ALLOCATE_VPP_get(struct mlx4_dev *dev, u8 port, goto out; /* Total number of supported VPPs */ - *availible_vpp = (u16)be32_to_cpu(out_param->availible_vpp); + *available_vpp = (u16)be32_to_cpu(out_param->available_vpp); for (i = 0; i < MLX4_NUM_UP; i++) vpp_p_up[i] = (u8)be32_to_cpu(out_param->vpp_p_up[i]); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw_qos.h b/drivers/net/ethernet/mellanox/mlx4/fw_qos.h index ac1f331878e6..582997577a04 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw_qos.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw_qos.h @@ -84,23 +84,23 @@ int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc); int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw, u8 *pg, u16 *ratelimit); /** - * mlx4_ALLOCATE_VPP_get - Query port VPP availible resources and allocation. - * Before distribution of VPPs to priorities, only availible_vpp is returned. + * mlx4_ALLOCATE_VPP_get - Query port VPP available resources and allocation. + * Before distribution of VPPs to priorities, only available_vpp is returned. * After initialization it returns the distribution of VPPs among priorities. * * @dev: mlx4_dev. * @port: Physical port number. - * @availible_vpp: Pointer to variable where number of availible VPPs is stored + * @available_vpp: Pointer to variable where number of available VPPs is stored * @vpp_p_up: Distribution of VPPs to priorities is stored in this array * * Returns 0 on success or a negative mlx4_core errno code. **/ int mlx4_ALLOCATE_VPP_get(struct mlx4_dev *dev, u8 port, - u16 *availible_vpp, u8 *vpp_p_up); + u16 *available_vpp, u8 *vpp_p_up); /** * mlx4_ALLOCATE_VPP_set - Distribution of VPPs among differnt priorities. * The total number of VPPs assigned to all for a port must not exceed - * the value reported by availible_vpp in mlx4_ALLOCATE_VPP_get. + * the value reported by available_vpp in mlx4_ALLOCATE_VPP_get. * VPP allocation is allowed only after the port type has been set, * and while no QPs are open for this port. * diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index 5a7816e7c7b4..a822f7a56bc5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -400,7 +400,7 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table, obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size; num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk; - table->icm = kcalloc(num_icm, sizeof *table->icm, GFP_KERNEL); + table->icm = kcalloc(num_icm, sizeof(*table->icm), GFP_KERNEL); if (!table->icm) return -ENOMEM; table->virt = virt; diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h index dee67fa39107..c9169a490557 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.h +++ b/drivers/net/ethernet/mellanox/mlx4/icm.h @@ -39,8 +39,8 @@ #include <linux/mutex.h> #define MLX4_ICM_CHUNK_LEN \ - ((256 - sizeof (struct list_head) - 2 * sizeof (int)) / \ - (sizeof (struct scatterlist))) + ((256 - sizeof(struct list_head) - 2 * sizeof(int)) / \ + (sizeof(struct scatterlist))) enum { MLX4_ICM_PAGE_SHIFT = 12, diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c index e00f627331cb..2edcce98ab2d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/intf.c +++ b/drivers/net/ethernet/mellanox/mlx4/intf.c @@ -53,7 +53,7 @@ static void mlx4_add_device(struct mlx4_interface *intf, struct mlx4_priv *priv) { struct mlx4_device_context *dev_ctx; - dev_ctx = kmalloc(sizeof *dev_ctx, GFP_KERNEL); + dev_ctx = kmalloc(sizeof(*dev_ctx), GFP_KERNEL); if (!dev_ctx) return; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index a594bfd9e095..e61c99ef741d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -34,6 +34,7 @@ */ #include <linux/module.h> +#include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/pci.h> @@ -121,7 +122,7 @@ static char mlx4_version[] = DRV_NAME ": Mellanox ConnectX core driver v" DRV_VERSION "\n"; -static struct mlx4_profile default_profile = { +static const struct mlx4_profile default_profile = { .num_qp = 1 << 18, .num_srq = 1 << 16, .rdmarc_per_qp = 1 << 4, @@ -131,7 +132,7 @@ static struct mlx4_profile default_profile = { .num_mtt = 1 << 20, /* It is really num mtt segements */ }; -static struct mlx4_profile low_mem_profile = { +static const struct mlx4_profile low_mem_profile = { .num_qp = 1 << 17, .num_srq = 1 << 6, .rdmarc_per_qp = 1 << 4, @@ -819,38 +820,93 @@ static void slave_adjust_steering_mode(struct mlx4_dev *dev, mlx4_steering_mode_str(dev->caps.steering_mode)); } +static void mlx4_slave_destroy_special_qp_cap(struct mlx4_dev *dev) +{ + kfree(dev->caps.spec_qps); + dev->caps.spec_qps = NULL; +} + +static int mlx4_slave_special_qp_cap(struct mlx4_dev *dev) +{ + struct mlx4_func_cap *func_cap = NULL; + struct mlx4_caps *caps = &dev->caps; + int i, err = 0; + + func_cap = kzalloc(sizeof(*func_cap), GFP_KERNEL); + caps->spec_qps = kcalloc(caps->num_ports, sizeof(*caps->spec_qps), GFP_KERNEL); + + if (!func_cap || !caps->spec_qps) { + mlx4_err(dev, "Failed to allocate memory for special qps cap\n"); + err = -ENOMEM; + goto err_mem; + } + + for (i = 1; i <= caps->num_ports; ++i) { + err = mlx4_QUERY_FUNC_CAP(dev, i, func_cap); + if (err) { + mlx4_err(dev, "QUERY_FUNC_CAP port command failed for port %d, aborting (%d)\n", + i, err); + goto err_mem; + } + caps->spec_qps[i - 1] = func_cap->spec_qps; + caps->port_mask[i] = caps->port_type[i]; + caps->phys_port_id[i] = func_cap->phys_port_id; + err = mlx4_get_slave_pkey_gid_tbl_len(dev, i, + &caps->gid_table_len[i], + &caps->pkey_table_len[i]); + if (err) { + mlx4_err(dev, "QUERY_PORT command failed for port %d, aborting (%d)\n", + i, err); + goto err_mem; + } + } + +err_mem: + if (err) + mlx4_slave_destroy_special_qp_cap(dev); + kfree(func_cap); + return err; +} + static int mlx4_slave_cap(struct mlx4_dev *dev) { int err; u32 page_size; - struct mlx4_dev_cap dev_cap; - struct mlx4_func_cap func_cap; - struct mlx4_init_hca_param hca_param; - u8 i; + struct mlx4_dev_cap *dev_cap = NULL; + struct mlx4_func_cap *func_cap = NULL; + struct mlx4_init_hca_param *hca_param = NULL; + + hca_param = kzalloc(sizeof(*hca_param), GFP_KERNEL); + func_cap = kzalloc(sizeof(*func_cap), GFP_KERNEL); + dev_cap = kzalloc(sizeof(*dev_cap), GFP_KERNEL); + if (!hca_param || !func_cap || !dev_cap) { + mlx4_err(dev, "Failed to allocate memory for slave_cap\n"); + err = -ENOMEM; + goto free_mem; + } - memset(&hca_param, 0, sizeof(hca_param)); - err = mlx4_QUERY_HCA(dev, &hca_param); + err = mlx4_QUERY_HCA(dev, hca_param); if (err) { mlx4_err(dev, "QUERY_HCA command failed, aborting\n"); - return err; + goto free_mem; } /* fail if the hca has an unknown global capability * at this time global_caps should be always zeroed */ - if (hca_param.global_caps) { + if (hca_param->global_caps) { mlx4_err(dev, "Unknown hca global capabilities\n"); - return -EINVAL; + err = -EINVAL; + goto free_mem; } - dev->caps.hca_core_clock = hca_param.hca_core_clock; + dev->caps.hca_core_clock = hca_param->hca_core_clock; - memset(&dev_cap, 0, sizeof(dev_cap)); - dev->caps.max_qp_dest_rdma = 1 << hca_param.log_rd_per_qp; - err = mlx4_dev_cap(dev, &dev_cap); + dev->caps.max_qp_dest_rdma = 1 << hca_param->log_rd_per_qp; + err = mlx4_dev_cap(dev, dev_cap); if (err) { mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n"); - return err; + goto free_mem; } err = mlx4_QUERY_FW(dev); @@ -862,21 +918,23 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) if (page_size > PAGE_SIZE) { mlx4_err(dev, "HCA minimum page size of %d bigger than kernel PAGE_SIZE of %ld, aborting\n", page_size, PAGE_SIZE); - return -ENODEV; + err = -ENODEV; + goto free_mem; } /* Set uar_page_shift for VF */ - dev->uar_page_shift = hca_param.uar_page_sz + 12; + dev->uar_page_shift = hca_param->uar_page_sz + 12; /* Make sure the master uar page size is valid */ if (dev->uar_page_shift > PAGE_SHIFT) { mlx4_err(dev, "Invalid configuration: uar page size is larger than system page size\n"); - return -ENODEV; + err = -ENODEV; + goto free_mem; } /* Set reserved_uars based on the uar_page_shift */ - mlx4_set_num_reserved_uars(dev, &dev_cap); + mlx4_set_num_reserved_uars(dev, dev_cap); /* Although uar page size in FW differs from system page size, * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core) @@ -884,34 +942,35 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) */ dev->caps.uar_page_size = PAGE_SIZE; - memset(&func_cap, 0, sizeof(func_cap)); - err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap); + err = mlx4_QUERY_FUNC_CAP(dev, 0, func_cap); if (err) { mlx4_err(dev, "QUERY_FUNC_CAP general command failed, aborting (%d)\n", err); - return err; + goto free_mem; } - if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) != + if ((func_cap->pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) != PF_CONTEXT_BEHAVIOUR_MASK) { mlx4_err(dev, "Unknown pf context behaviour %x known flags %x\n", - func_cap.pf_context_behaviour, PF_CONTEXT_BEHAVIOUR_MASK); - return -EINVAL; - } - - dev->caps.num_ports = func_cap.num_ports; - dev->quotas.qp = func_cap.qp_quota; - dev->quotas.srq = func_cap.srq_quota; - dev->quotas.cq = func_cap.cq_quota; - dev->quotas.mpt = func_cap.mpt_quota; - dev->quotas.mtt = func_cap.mtt_quota; - dev->caps.num_qps = 1 << hca_param.log_num_qps; - dev->caps.num_srqs = 1 << hca_param.log_num_srqs; - dev->caps.num_cqs = 1 << hca_param.log_num_cqs; - dev->caps.num_mpts = 1 << hca_param.log_mpt_sz; - dev->caps.num_eqs = func_cap.max_eq; - dev->caps.reserved_eqs = func_cap.reserved_eq; - dev->caps.reserved_lkey = func_cap.reserved_lkey; + func_cap->pf_context_behaviour, + PF_CONTEXT_BEHAVIOUR_MASK); + err = -EINVAL; + goto free_mem; + } + + dev->caps.num_ports = func_cap->num_ports; + dev->quotas.qp = func_cap->qp_quota; + dev->quotas.srq = func_cap->srq_quota; + dev->quotas.cq = func_cap->cq_quota; + dev->quotas.mpt = func_cap->mpt_quota; + dev->quotas.mtt = func_cap->mtt_quota; + dev->caps.num_qps = 1 << hca_param->log_num_qps; + dev->caps.num_srqs = 1 << hca_param->log_num_srqs; + dev->caps.num_cqs = 1 << hca_param->log_num_cqs; + dev->caps.num_mpts = 1 << hca_param->log_mpt_sz; + dev->caps.num_eqs = func_cap->max_eq; + dev->caps.reserved_eqs = func_cap->reserved_eq; + dev->caps.reserved_lkey = func_cap->reserved_lkey; dev->caps.num_pds = MLX4_NUM_PDS; dev->caps.num_mgms = 0; dev->caps.num_amgms = 0; @@ -919,43 +978,16 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) if (dev->caps.num_ports > MLX4_MAX_PORTS) { mlx4_err(dev, "HCA has %d ports, but we only support %d, aborting\n", dev->caps.num_ports, MLX4_MAX_PORTS); - return -ENODEV; + err = -ENODEV; + goto free_mem; } mlx4_replace_zero_macs(dev); - dev->caps.qp0_qkey = kcalloc(dev->caps.num_ports, sizeof(u32), GFP_KERNEL); - dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - dev->caps.qp1_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - dev->caps.qp1_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - - if (!dev->caps.qp0_tunnel || !dev->caps.qp0_proxy || - !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy || - !dev->caps.qp0_qkey) { - err = -ENOMEM; - goto err_mem; - } - - for (i = 1; i <= dev->caps.num_ports; ++i) { - err = mlx4_QUERY_FUNC_CAP(dev, i, &func_cap); - if (err) { - mlx4_err(dev, "QUERY_FUNC_CAP port command failed for port %d, aborting (%d)\n", - i, err); - goto err_mem; - } - dev->caps.qp0_qkey[i - 1] = func_cap.qp0_qkey; - dev->caps.qp0_tunnel[i - 1] = func_cap.qp0_tunnel_qpn; - dev->caps.qp0_proxy[i - 1] = func_cap.qp0_proxy_qpn; - dev->caps.qp1_tunnel[i - 1] = func_cap.qp1_tunnel_qpn; - dev->caps.qp1_proxy[i - 1] = func_cap.qp1_proxy_qpn; - dev->caps.port_mask[i] = dev->caps.port_type[i]; - dev->caps.phys_port_id[i] = func_cap.phys_port_id; - err = mlx4_get_slave_pkey_gid_tbl_len(dev, i, - &dev->caps.gid_table_len[i], - &dev->caps.pkey_table_len[i]); - if (err) - goto err_mem; + err = mlx4_slave_special_qp_cap(dev); + if (err) { + mlx4_err(dev, "Set special QP caps failed. aborting\n"); + goto free_mem; } if (dev->caps.uar_page_size * (dev->caps.num_uars - @@ -970,7 +1002,7 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) goto err_mem; } - if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_64B_EQE_ENABLED) { + if (hca_param->dev_cap_enabled & MLX4_DEV_CAP_64B_EQE_ENABLED) { dev->caps.eqe_size = 64; dev->caps.eqe_factor = 1; } else { @@ -978,20 +1010,20 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.eqe_factor = 0; } - if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_64B_CQE_ENABLED) { + if (hca_param->dev_cap_enabled & MLX4_DEV_CAP_64B_CQE_ENABLED) { dev->caps.cqe_size = 64; dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE; } else { dev->caps.cqe_size = 32; } - if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_EQE_STRIDE_ENABLED) { - dev->caps.eqe_size = hca_param.eqe_size; + if (hca_param->dev_cap_enabled & MLX4_DEV_CAP_EQE_STRIDE_ENABLED) { + dev->caps.eqe_size = hca_param->eqe_size; dev->caps.eqe_factor = 0; } - if (hca_param.dev_cap_enabled & MLX4_DEV_CAP_CQE_STRIDE_ENABLED) { - dev->caps.cqe_size = hca_param.cqe_size; + if (hca_param->dev_cap_enabled & MLX4_DEV_CAP_CQE_STRIDE_ENABLED) { + dev->caps.cqe_size = hca_param->cqe_size; /* User still need to know when CQE > 32B */ dev->caps.userspace_caps |= MLX4_USER_DEV_CAP_LARGE_CQE; } @@ -999,31 +1031,27 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; mlx4_warn(dev, "Timestamping is not supported in slave mode\n"); - slave_adjust_steering_mode(dev, &dev_cap, &hca_param); + dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_USER_MAC_EN; + mlx4_dbg(dev, "User MAC FW update is not supported in slave mode\n"); + + slave_adjust_steering_mode(dev, dev_cap, hca_param); mlx4_dbg(dev, "RSS support for IP fragments is %s\n", - hca_param.rss_ip_frags ? "on" : "off"); + hca_param->rss_ip_frags ? "on" : "off"); - if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_BF_RES_QP && + if (func_cap->extra_flags & MLX4_QUERY_FUNC_FLAGS_BF_RES_QP && dev->caps.bf_reg_size) dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_ETH_BF_QP; - if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_A0_RES_QP) + if (func_cap->extra_flags & MLX4_QUERY_FUNC_FLAGS_A0_RES_QP) dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_A0_QP; - return 0; - err_mem: - kfree(dev->caps.qp0_qkey); - kfree(dev->caps.qp0_tunnel); - kfree(dev->caps.qp0_proxy); - kfree(dev->caps.qp1_tunnel); - kfree(dev->caps.qp1_proxy); - dev->caps.qp0_qkey = NULL; - dev->caps.qp0_tunnel = NULL; - dev->caps.qp0_proxy = NULL; - dev->caps.qp1_tunnel = NULL; - dev->caps.qp1_proxy = NULL; - + if (err) + mlx4_slave_destroy_special_qp_cap(dev); +free_mem: + kfree(hca_param); + kfree(func_cap); + kfree(dev_cap); return err; } @@ -2399,7 +2427,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev) dev->caps.rx_checksum_flags_port[2] = params.rx_csum_flags_port_2; } priv->eq_table.inta_pin = adapter.inta_pin; - memcpy(dev->board_id, adapter.board_id, sizeof dev->board_id); + memcpy(dev->board_id, adapter.board_id, sizeof(dev->board_id)); return 0; @@ -2407,13 +2435,8 @@ unmap_bf: unmap_internal_clock(dev); unmap_bf_area(dev); - if (mlx4_is_slave(dev)) { - kfree(dev->caps.qp0_qkey); - kfree(dev->caps.qp0_tunnel); - kfree(dev->caps.qp0_proxy); - kfree(dev->caps.qp1_tunnel); - kfree(dev->caps.qp1_proxy); - } + if (mlx4_is_slave(dev)) + mlx4_slave_destroy_special_qp_cap(dev); err_close: if (mlx4_is_slave(dev)) @@ -2870,7 +2893,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) dev->caps.num_eqs - dev->caps.reserved_eqs, MAX_MSIX); - entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL); + entries = kcalloc(nreq, sizeof(*entries), GFP_KERNEL); if (!entries) goto no_msi; @@ -3597,13 +3620,8 @@ err_master_mfunc: mlx4_multi_func_cleanup(dev); } - if (mlx4_is_slave(dev)) { - kfree(dev->caps.qp0_qkey); - kfree(dev->caps.qp0_tunnel); - kfree(dev->caps.qp0_proxy); - kfree(dev->caps.qp1_tunnel); - kfree(dev->caps.qp1_proxy); - } + if (mlx4_is_slave(dev)) + mlx4_slave_destroy_special_qp_cap(dev); err_close: mlx4_close_hca(dev); @@ -3659,7 +3677,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, * per port, we must limit the number of VFs to 63 (since their are * 128 MACs) */ - for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && i < num_vfs_argc; + for (i = 0; i < ARRAY_SIZE(nvfs) && i < num_vfs_argc; total_vfs += nvfs[param_map[num_vfs_argc - 1][i]], i++) { nvfs[param_map[num_vfs_argc - 1][i]] = num_vfs[i]; if (nvfs[i] < 0) { @@ -3668,7 +3686,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, goto err_disable_pdev; } } - for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]) && i < probe_vfs_argc; + for (i = 0; i < ARRAY_SIZE(prb_vf) && i < probe_vfs_argc; i++) { prb_vf[param_map[probe_vfs_argc - 1][i]] = probe_vf[i]; if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) { @@ -3747,11 +3765,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, if (total_vfs) { unsigned vfs_offset = 0; - for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && + for (i = 0; i < ARRAY_SIZE(nvfs) && vfs_offset + nvfs[i] < extended_func_num(pdev); vfs_offset += nvfs[i], i++) ; - if (i == sizeof(nvfs)/sizeof(nvfs[0])) { + if (i == ARRAY_SIZE(nvfs)) { err = -ENODEV; goto err_release_regions; } @@ -3783,7 +3801,6 @@ err_release_regions: err_disable_pdev: mlx4_pci_disable_device(&priv->dev); - pci_set_drvdata(pdev, NULL); return err; } @@ -3944,11 +3961,7 @@ static void mlx4_unload_one(struct pci_dev *pdev) if (!mlx4_is_slave(dev)) mlx4_free_ownership(dev); - kfree(dev->caps.qp0_qkey); - kfree(dev->caps.qp0_tunnel); - kfree(dev->caps.qp0_proxy); - kfree(dev->caps.qp1_tunnel); - kfree(dev->caps.qp1_proxy); + mlx4_slave_destroy_special_qp_cap(dev); kfree(dev->dev_vfs); mlx4_clean_dev(dev); @@ -3998,7 +4011,6 @@ static void mlx4_remove_one(struct pci_dev *pdev) devlink_unregister(devlink); kfree(dev->persist); devlink_free(devlink); - pci_set_drvdata(pdev, NULL); } static int restore_current_port_types(struct mlx4_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 0710b3677464..4c5306dbcf11 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -162,7 +162,7 @@ static int new_steering_entry(struct mlx4_dev *dev, u8 port, return -EINVAL; s_steer = &mlx4_priv(dev)->steer[port - 1]; - new_entry = kzalloc(sizeof *new_entry, GFP_KERNEL); + new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL); if (!new_entry) return -ENOMEM; @@ -175,7 +175,7 @@ static int new_steering_entry(struct mlx4_dev *dev, u8 port, */ pqp = get_promisc_qp(dev, port, steer, qpn); if (pqp) { - dqp = kmalloc(sizeof *dqp, GFP_KERNEL); + dqp = kmalloc(sizeof(*dqp), GFP_KERNEL); if (!dqp) { err = -ENOMEM; goto out_alloc; @@ -274,7 +274,7 @@ static int existing_steering_entry(struct mlx4_dev *dev, u8 port, } /* add the qp as a duplicate on this index */ - dqp = kmalloc(sizeof *dqp, GFP_KERNEL); + dqp = kmalloc(sizeof(*dqp), GFP_KERNEL); if (!dqp) return -ENOMEM; dqp->qpn = qpn; @@ -443,7 +443,7 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 port, goto out_mutex; } - pqp = kmalloc(sizeof *pqp, GFP_KERNEL); + pqp = kmalloc(sizeof(*pqp), GFP_KERNEL); if (!pqp) { err = -ENOMEM; goto out_mutex; @@ -514,7 +514,7 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 port, /* add the new qpn to list of promisc qps */ list_add_tail(&pqp->list, &s_steer->promisc_qps[steer]); /* now need to add all the promisc qps to default entry */ - memset(mgm, 0, sizeof *mgm); + memset(mgm, 0, sizeof(*mgm)); members_count = 0; list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list) { if (members_count == dev->caps.num_qp_per_mgm) { @@ -1144,7 +1144,7 @@ int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16], index += dev->caps.num_mgms; new_entry = 1; - memset(mgm, 0, sizeof *mgm); + memset(mgm, 0, sizeof(*mgm)); memcpy(mgm->gid, gid, 16); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 852d00a5b016..c68da1986e51 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -807,6 +807,8 @@ struct mlx4_set_port_general_context { u8 phv_en; u8 reserved6[5]; __be16 user_mtu; + u16 reserved7; + u8 user_mac[6]; }; struct mlx4_set_port_rqp_calc_context { diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index d350b2158104..fdb3ad0cbe54 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -685,7 +685,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, int cq_idx); void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); -int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); +void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c index 24282cd017d3..c7c0764991c9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mr.c +++ b/drivers/net/ethernet/mellanox/mlx4/mr.c @@ -106,9 +106,9 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order) buddy->max_order = max_order; spin_lock_init(&buddy->lock); - buddy->bits = kcalloc(buddy->max_order + 1, sizeof (long *), + buddy->bits = kcalloc(buddy->max_order + 1, sizeof(long *), GFP_KERNEL); - buddy->num_free = kcalloc((buddy->max_order + 1), sizeof *buddy->num_free, + buddy->num_free = kcalloc(buddy->max_order + 1, sizeof(*buddy->num_free), GFP_KERNEL); if (!buddy->bits || !buddy->num_free) goto err_out; @@ -703,13 +703,13 @@ static int mlx4_write_mtt_chunk(struct mlx4_dev *dev, struct mlx4_mtt *mtt, return -ENOMEM; dma_sync_single_for_cpu(&dev->persist->pdev->dev, dma_handle, - npages * sizeof (u64), DMA_TO_DEVICE); + npages * sizeof(u64), DMA_TO_DEVICE); for (i = 0; i < npages; ++i) mtts[i] = cpu_to_be64(page_list[i] | MLX4_MTT_FLAG_PRESENT); dma_sync_single_for_device(&dev->persist->pdev->dev, dma_handle, - npages * sizeof (u64), DMA_TO_DEVICE); + npages * sizeof(u64), DMA_TO_DEVICE); return 0; } @@ -1052,7 +1052,7 @@ int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages, return -EINVAL; /* All MTTs must fit in the same page */ - if (max_pages * sizeof *fmr->mtts > PAGE_SIZE) + if (max_pages * sizeof(*fmr->mtts) > PAGE_SIZE) return -EINVAL; fmr->page_shift = page_shift; diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index 4e36e287d605..3ef3406ff4cb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -52,6 +52,7 @@ #define MLX4_FLAG2_V_IGNORE_FCS_MASK BIT(1) #define MLX4_FLAG2_V_USER_MTU_MASK BIT(5) +#define MLX4_FLAG2_V_USER_MAC_MASK BIT(6) #define MLX4_FLAG_V_MTU_MASK BIT(0) #define MLX4_FLAG_V_PPRX_MASK BIT(1) #define MLX4_FLAG_V_PPTX_MASK BIT(2) @@ -1700,6 +1701,30 @@ int mlx4_SET_PORT_user_mtu(struct mlx4_dev *dev, u8 port, u16 user_mtu) } EXPORT_SYMBOL(mlx4_SET_PORT_user_mtu); +int mlx4_SET_PORT_user_mac(struct mlx4_dev *dev, u8 port, u8 *user_mac) +{ + struct mlx4_cmd_mailbox *mailbox; + struct mlx4_set_port_general_context *context; + u32 in_mod; + int err; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + context = mailbox->buf; + context->flags2 |= MLX4_FLAG2_V_USER_MAC_MASK; + memcpy(context->user_mac, user_mac, sizeof(context->user_mac)); + + in_mod = MLX4_SET_PORT_GENERAL << 8 | port; + err = mlx4_cmd(dev, mailbox->dma, in_mod, MLX4_SET_PORT_ETH_OPCODE, + MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B, + MLX4_CMD_NATIVE); + + mlx4_free_cmd_mailbox(dev, mailbox); + return err; +} +EXPORT_SYMBOL(mlx4_SET_PORT_user_mac); + int mlx4_SET_PORT_fcs_check(struct mlx4_dev *dev, u8 port, u8 ignore_fcs_value) { struct mlx4_cmd_mailbox *mailbox; diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 5e5b4475b85e..728a2fb1f5c0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -174,7 +174,7 @@ static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt, cpu_to_be16(mlx4_qp_roce_entropy(dev, qp->qpn)); *(__be32 *) mailbox->buf = cpu_to_be32(optpar); - memcpy(mailbox->buf + 8, context, sizeof *context); + memcpy(mailbox->buf + 8, context, sizeof(*context)); ((struct mlx4_qp_context *) (mailbox->buf + 8))->local_qpn = cpu_to_be32(qp->qpn); @@ -845,24 +845,21 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) /* In mfunc, calculate proxy and tunnel qp offsets for the PF here, * since the PF does not call mlx4_slave_caps */ - dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - dev->caps.qp1_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - dev->caps.qp1_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL); - - if (!dev->caps.qp0_tunnel || !dev->caps.qp0_proxy || - !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy) { + dev->caps.spec_qps = kcalloc(dev->caps.num_ports, + sizeof(*dev->caps.spec_qps), + GFP_KERNEL); + if (!dev->caps.spec_qps) { err = -ENOMEM; goto err_mem; } for (k = 0; k < dev->caps.num_ports; k++) { - dev->caps.qp0_proxy[k] = dev->phys_caps.base_proxy_sqpn + + dev->caps.spec_qps[k].qp0_proxy = dev->phys_caps.base_proxy_sqpn + 8 * mlx4_master_func_num(dev) + k; - dev->caps.qp0_tunnel[k] = dev->caps.qp0_proxy[k] + 8 * MLX4_MFUNC_MAX; - dev->caps.qp1_proxy[k] = dev->phys_caps.base_proxy_sqpn + + dev->caps.spec_qps[k].qp0_tunnel = dev->caps.spec_qps[k].qp0_proxy + 8 * MLX4_MFUNC_MAX; + dev->caps.spec_qps[k].qp1_proxy = dev->phys_caps.base_proxy_sqpn + 8 * mlx4_master_func_num(dev) + MLX4_MAX_PORTS + k; - dev->caps.qp1_tunnel[k] = dev->caps.qp1_proxy[k] + 8 * MLX4_MFUNC_MAX; + dev->caps.spec_qps[k].qp1_tunnel = dev->caps.spec_qps[k].qp1_proxy + 8 * MLX4_MFUNC_MAX; } } @@ -874,12 +871,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) return err; err_mem: - kfree(dev->caps.qp0_tunnel); - kfree(dev->caps.qp0_proxy); - kfree(dev->caps.qp1_tunnel); - kfree(dev->caps.qp1_proxy); - dev->caps.qp0_tunnel = dev->caps.qp0_proxy = - dev->caps.qp1_tunnel = dev->caps.qp1_proxy = NULL; + kfree(dev->caps.spec_qps); + dev->caps.spec_qps = NULL; mlx4_cleanup_qp_zones(dev); return err; } @@ -908,7 +901,7 @@ int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp, MLX4_CMD_QUERY_QP, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (!err) - memcpy(context, mailbox->buf + 8, sizeof *context); + memcpy(context, mailbox->buf + 8, sizeof(*context)); mlx4_free_cmd_mailbox(dev, mailbox); return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 215e21c3dc8a..fabb53379727 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -1040,7 +1040,7 @@ static struct res_common *alloc_qp_tr(int id) { struct res_qp *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1058,7 +1058,7 @@ static struct res_common *alloc_mtt_tr(int id, int order) { struct res_mtt *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1074,7 +1074,7 @@ static struct res_common *alloc_mpt_tr(int id, int key) { struct res_mpt *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1089,7 +1089,7 @@ static struct res_common *alloc_eq_tr(int id) { struct res_eq *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1103,7 +1103,7 @@ static struct res_common *alloc_cq_tr(int id) { struct res_cq *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1118,7 +1118,7 @@ static struct res_common *alloc_srq_tr(int id) { struct res_srq *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1133,7 +1133,7 @@ static struct res_common *alloc_counter_tr(int id, int port) { struct res_counter *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1148,7 +1148,7 @@ static struct res_common *alloc_xrcdn_tr(int id) { struct res_xrcdn *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1162,7 +1162,7 @@ static struct res_common *alloc_fs_rule_tr(u64 id, int qpn) { struct res_fs_rule *ret; - ret = kzalloc(sizeof *ret, GFP_KERNEL); + ret = kzalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return NULL; @@ -1274,7 +1274,7 @@ static int add_res_range(struct mlx4_dev *dev, int slave, u64 base, int count, struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker; struct rb_root *root = &tracker->res_tree[type]; - res_arr = kzalloc(count * sizeof *res_arr, GFP_KERNEL); + res_arr = kcalloc(count, sizeof(*res_arr), GFP_KERNEL); if (!res_arr) return -ENOMEM; @@ -2027,7 +2027,7 @@ static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port, if (mlx4_grant_resource(dev, slave, RES_MAC, 1, port)) return -EINVAL; - res = kzalloc(sizeof *res, GFP_KERNEL); + res = kzalloc(sizeof(*res), GFP_KERNEL); if (!res) { mlx4_release_resource(dev, slave, RES_MAC, 1, port); return -ENOMEM; @@ -4020,7 +4020,7 @@ static int add_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp, struct res_gid *res; int err; - res = kzalloc(sizeof *res, GFP_KERNEL); + res = kzalloc(sizeof(*res), GFP_KERNEL); if (!res) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 5aee05992f27..fdaef00465d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -34,6 +34,27 @@ config MLX5_CORE_EN ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. +config MLX5_MPFS + bool "Mellanox Technologies MLX5 MPFS support" + depends on MLX5_CORE_EN + default y + ---help--- + Mellanox Technologies Ethernet Multi-Physical Function Switch (MPFS) + support in ConnectX NIC. MPFs is required for when multi-PF configuration + is enabled to allow passing user configured unicast MAC addresses to the + requesting PF. + +config MLX5_ESWITCH + bool "Mellanox Technologies MLX5 SRIOV E-Switch support" + depends on MLX5_CORE_EN + default y + ---help--- + Mellanox Technologies Ethernet SRIOV E-Switch support in ConnectX NIC. + E-Switch provides internal SRIOV packet steering and switching for the + enabled VFs and PF in two available modes: + Legacy SRIOV mode (L2 mac vlan steering based). + Switchdev mode (eswitch offloads). + config MLX5_CORE_EN_DCB bool "Data Center Bridging (DCB) Support" default y diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 9d17e4e76d3a..87a3099808f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -4,17 +4,21 @@ subdir-ccflags-y += -I$(src) mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \ mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ - fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o + fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \ + diag/fs_tracepoint.o mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ fpga/ipsec.o -mlx5_core-$(CONFIG_MLX5_CORE_EN) += eswitch.o eswitch_offloads.o \ - en_main.o en_common.o en_fs.o en_ethtool.o en_tx.o \ - en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \ - en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o en_selftest.o +mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ + en_tx.o en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \ + en_arfs.o en_fs_ethtool.o en_selftest.o + +mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o + +mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o @@ -22,3 +26,5 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ en_accel/ipsec_stats.o + +CFLAGS_tracepoint.o := -I$(src) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 3c95f7f53802..47239bf7bf43 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -258,6 +258,7 @@ EXPORT_SYMBOL_GPL(mlx5_db_alloc); void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db) { u32 db_per_page = PAGE_SIZE / cache_line_size(); + mutex_lock(&dev->priv.pgdir_mutex); __set_bit(db->index, db->u.pgdir->bitmap); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1acbb721f38d..1fffdebbc9e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -802,7 +802,6 @@ static void cmd_work_handler(struct work_struct *work) bool poll_cmd = ent->polling; int alloc_ret; - sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index a62f4b6a21a5..ff60cf7342ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -45,11 +45,70 @@ struct mlx5_device_context { unsigned long state; }; +struct mlx5_delayed_event { + struct list_head list; + struct mlx5_core_dev *dev; + enum mlx5_dev_event event; + unsigned long param; +}; + enum { MLX5_INTERFACE_ADDED, MLX5_INTERFACE_ATTACHED, }; +static void add_delayed_event(struct mlx5_priv *priv, + struct mlx5_core_dev *dev, + enum mlx5_dev_event event, + unsigned long param) +{ + struct mlx5_delayed_event *delayed_event; + + delayed_event = kzalloc(sizeof(*delayed_event), GFP_ATOMIC); + if (!delayed_event) { + mlx5_core_err(dev, "event %d is missed\n", event); + return; + } + + mlx5_core_dbg(dev, "Accumulating event %d\n", event); + delayed_event->dev = dev; + delayed_event->event = event; + delayed_event->param = param; + list_add_tail(&delayed_event->list, &priv->waiting_events_list); +} + +static void fire_delayed_event_locked(struct mlx5_device_context *dev_ctx, + struct mlx5_core_dev *dev, + struct mlx5_priv *priv) +{ + struct mlx5_delayed_event *de; + struct mlx5_delayed_event *n; + + /* stop delaying events */ + priv->is_accum_events = false; + + /* fire all accumulated events before new event comes */ + list_for_each_entry_safe(de, n, &priv->waiting_events_list, list) { + dev_ctx->intf->event(dev, dev_ctx->context, de->event, de->param); + list_del(&de->list); + kfree(de); + } +} + +static void cleanup_delayed_evets(struct mlx5_priv *priv) +{ + struct mlx5_delayed_event *de; + struct mlx5_delayed_event *n; + + spin_lock_irq(&priv->ctx_lock); + priv->is_accum_events = false; + list_for_each_entry_safe(de, n, &priv->waiting_events_list, list) { + list_del(&de->list); + kfree(de); + } + spin_unlock_irq(&priv->ctx_lock); +} + void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) { struct mlx5_device_context *dev_ctx; @@ -63,6 +122,12 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) return; dev_ctx->intf = intf; + /* accumulating events that can come after mlx5_ib calls to + * ib_register_device, till adding that interface to the events list. + */ + + priv->is_accum_events = true; + dev_ctx->context = intf->add(dev); set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); if (intf->attach) @@ -71,6 +136,9 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) if (dev_ctx->context) { spin_lock_irq(&priv->ctx_lock); list_add_tail(&dev_ctx->list, &priv->ctx_list); + + fire_delayed_event_locked(dev_ctx, dev, priv); + #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING if (dev_ctx->intf->pfault) { if (priv->pfault) { @@ -84,6 +152,8 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) spin_unlock_irq(&priv->ctx_lock); } else { kfree(dev_ctx); + /* delete all accumulated events */ + cleanup_delayed_evets(priv); } } @@ -341,6 +411,9 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, spin_lock_irqsave(&priv->ctx_lock, flags); + if (priv->is_accum_events) + add_delayed_event(priv, dev, event, param); + list_for_each_entry(dev_ctx, &priv->ctx_list, list) if (dev_ctx->intf->event) dev_ctx->intf->event(dev, dev_ctx->context, event, param); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/diag/Makefile new file mode 100644 index 000000000000..d8e17110f25d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/Makefile @@ -0,0 +1 @@ +subdir-ccflags-y += -I$(src)/.. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c new file mode 100644 index 000000000000..0be4575b58a2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -0,0 +1,261 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#define CREATE_TRACE_POINTS + +#include "fs_tracepoint.h" +#include <linux/stringify.h> + +#define DECLARE_MASK_VAL(type, name) struct {type m; type v; } name +#define MASK_VAL(type, spec, name, mask, val, fld) \ + DECLARE_MASK_VAL(type, name) = \ + {.m = MLX5_GET(spec, mask, fld),\ + .v = MLX5_GET(spec, val, fld)} +#define MASK_VAL_BE(type, spec, name, mask, val, fld) \ + DECLARE_MASK_VAL(type, name) = \ + {.m = MLX5_GET_BE(type, spec, mask, fld),\ + .v = MLX5_GET_BE(type, spec, val, fld)} +#define GET_MASKED_VAL(name) (name.m & name.v) + +#define GET_MASK_VAL(name, type, mask, val, fld) \ + (name.m = MLX5_GET(type, mask, fld), \ + name.v = MLX5_GET(type, val, fld), \ + name.m & name.v) +#define PRINT_MASKED_VAL(name, p, format) { \ + if (name.m) \ + trace_seq_printf(p, __stringify(name) "=" format " ", name.v); \ + } +#define PRINT_MASKED_VALP(name, cast, p, format) { \ + if (name.m) \ + trace_seq_printf(p, __stringify(name) "=" format " ", \ + (cast)&name.v);\ + } + +static void print_lyr_2_4_hdrs(struct trace_seq *p, + const u32 *mask, const u32 *value) +{ +#define MASK_VAL_L2(type, name, fld) \ + MASK_VAL(type, fte_match_set_lyr_2_4, name, mask, value, fld) + DECLARE_MASK_VAL(u64, smac) = { + .m = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_47_16) << 16 | + MLX5_GET(fte_match_set_lyr_2_4, mask, smac_15_0), + .v = MLX5_GET(fte_match_set_lyr_2_4, value, smac_47_16) << 16 | + MLX5_GET(fte_match_set_lyr_2_4, value, smac_15_0)}; + DECLARE_MASK_VAL(u64, dmac) = { + .m = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_47_16) << 16 | + MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_15_0), + .v = MLX5_GET(fte_match_set_lyr_2_4, value, dmac_47_16) << 16 | + MLX5_GET(fte_match_set_lyr_2_4, value, dmac_15_0)}; + MASK_VAL_L2(u16, ethertype, ethertype); + + PRINT_MASKED_VALP(smac, u8 *, p, "%pM"); + PRINT_MASKED_VALP(dmac, u8 *, p, "%pM"); + PRINT_MASKED_VAL(ethertype, p, "%04x"); + + if (ethertype.m == 0xffff) { + if (ethertype.v == ETH_P_IP) { +#define MASK_VAL_L2_BE(type, name, fld) \ + MASK_VAL_BE(type, fte_match_set_lyr_2_4, name, mask, value, fld) + MASK_VAL_L2_BE(u32, src_ipv4, + src_ipv4_src_ipv6.ipv4_layout.ipv4); + MASK_VAL_L2_BE(u32, dst_ipv4, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4); + + PRINT_MASKED_VALP(src_ipv4, typeof(&src_ipv4.v), p, + "%pI4"); + PRINT_MASKED_VALP(dst_ipv4, typeof(&dst_ipv4.v), p, + "%pI4"); + } else if (ethertype.v == ETH_P_IPV6) { + static const struct in6_addr full_ones = { + .in6_u.u6_addr32 = {htonl(0xffffffff), + htonl(0xffffffff), + htonl(0xffffffff), + htonl(0xffffffff)}, + }; + DECLARE_MASK_VAL(struct in6_addr, src_ipv6); + DECLARE_MASK_VAL(struct in6_addr, dst_ipv6); + + memcpy(src_ipv6.m.in6_u.u6_addr8, + MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + sizeof(src_ipv6.m)); + memcpy(dst_ipv6.m.in6_u.u6_addr8, + MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + sizeof(dst_ipv6.m)); + memcpy(src_ipv6.v.in6_u.u6_addr8, + MLX5_ADDR_OF(fte_match_set_lyr_2_4, value, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + sizeof(src_ipv6.v)); + memcpy(dst_ipv6.v.in6_u.u6_addr8, + MLX5_ADDR_OF(fte_match_set_lyr_2_4, value, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + sizeof(dst_ipv6.v)); + + if (!memcmp(&src_ipv6.m, &full_ones, sizeof(full_ones))) + trace_seq_printf(p, "src_ipv6=%pI6 ", + &src_ipv6.v); + if (!memcmp(&dst_ipv6.m, &full_ones, sizeof(full_ones))) + trace_seq_printf(p, "dst_ipv6=%pI6 ", + &dst_ipv6.v); + } + } + +#define PRINT_MASKED_VAL_L2(type, name, fld, p, format) {\ + MASK_VAL_L2(type, name, fld); \ + PRINT_MASKED_VAL(name, p, format); \ +} + + PRINT_MASKED_VAL_L2(u8, ip_protocol, ip_protocol, p, "%02x"); + PRINT_MASKED_VAL_L2(u16, tcp_flags, tcp_flags, p, "%x"); + PRINT_MASKED_VAL_L2(u16, tcp_sport, tcp_sport, p, "%u"); + PRINT_MASKED_VAL_L2(u16, tcp_dport, tcp_dport, p, "%u"); + PRINT_MASKED_VAL_L2(u16, udp_sport, udp_sport, p, "%u"); + PRINT_MASKED_VAL_L2(u16, udp_dport, udp_dport, p, "%u"); + PRINT_MASKED_VAL_L2(u16, first_vid, first_vid, p, "%04x"); + PRINT_MASKED_VAL_L2(u8, first_prio, first_prio, p, "%x"); + PRINT_MASKED_VAL_L2(u8, first_cfi, first_cfi, p, "%d"); + PRINT_MASKED_VAL_L2(u8, ip_dscp, ip_dscp, p, "%02x"); + PRINT_MASKED_VAL_L2(u8, ip_ecn, ip_ecn, p, "%x"); + PRINT_MASKED_VAL_L2(u8, cvlan_tag, cvlan_tag, p, "%d"); + PRINT_MASKED_VAL_L2(u8, svlan_tag, svlan_tag, p, "%d"); + PRINT_MASKED_VAL_L2(u8, frag, frag, p, "%d"); +} + +static void print_misc_parameters_hdrs(struct trace_seq *p, + const u32 *mask, const u32 *value) +{ +#define MASK_VAL_MISC(type, name, fld) \ + MASK_VAL(type, fte_match_set_misc, name, mask, value, fld) +#define PRINT_MASKED_VAL_MISC(type, name, fld, p, format) {\ + MASK_VAL_MISC(type, name, fld); \ + PRINT_MASKED_VAL(name, p, format); \ +} + DECLARE_MASK_VAL(u64, gre_key) = { + .m = MLX5_GET(fte_match_set_misc, mask, gre_key_h) << 8 | + MLX5_GET(fte_match_set_misc, mask, gre_key_l), + .v = MLX5_GET(fte_match_set_misc, value, gre_key_h) << 8 | + MLX5_GET(fte_match_set_misc, value, gre_key_l)}; + + PRINT_MASKED_VAL(gre_key, p, "%llu"); + PRINT_MASKED_VAL_MISC(u32, source_sqn, source_sqn, p, "%u"); + PRINT_MASKED_VAL_MISC(u16, source_port, source_port, p, "%u"); + PRINT_MASKED_VAL_MISC(u8, outer_second_prio, outer_second_prio, + p, "%u"); + PRINT_MASKED_VAL_MISC(u8, outer_second_cfi, outer_second_cfi, p, "%u"); + PRINT_MASKED_VAL_MISC(u16, outer_second_vid, outer_second_vid, p, "%u"); + PRINT_MASKED_VAL_MISC(u8, inner_second_prio, inner_second_prio, + p, "%u"); + PRINT_MASKED_VAL_MISC(u8, inner_second_cfi, inner_second_cfi, p, "%u"); + PRINT_MASKED_VAL_MISC(u16, inner_second_vid, inner_second_vid, p, "%u"); + + PRINT_MASKED_VAL_MISC(u8, outer_second_cvlan_tag, + outer_second_cvlan_tag, p, "%u"); + PRINT_MASKED_VAL_MISC(u8, inner_second_cvlan_tag, + inner_second_cvlan_tag, p, "%u"); + PRINT_MASKED_VAL_MISC(u8, outer_second_svlan_tag, + outer_second_svlan_tag, p, "%u"); + PRINT_MASKED_VAL_MISC(u8, inner_second_svlan_tag, + inner_second_svlan_tag, p, "%u"); + + PRINT_MASKED_VAL_MISC(u8, gre_protocol, gre_protocol, p, "%u"); + + PRINT_MASKED_VAL_MISC(u32, vxlan_vni, vxlan_vni, p, "%u"); + PRINT_MASKED_VAL_MISC(u32, outer_ipv6_flow_label, outer_ipv6_flow_label, + p, "%x"); + PRINT_MASKED_VAL_MISC(u32, inner_ipv6_flow_label, inner_ipv6_flow_label, + p, "%x"); +} + +const char *parse_fs_hdrs(struct trace_seq *p, + u8 match_criteria_enable, + const u32 *mask_outer, + const u32 *mask_misc, + const u32 *mask_inner, + const u32 *value_outer, + const u32 *value_misc, + const u32 *value_inner) +{ + const char *ret = trace_seq_buffer_ptr(p); + + if (match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS) { + trace_seq_printf(p, "[outer] "); + print_lyr_2_4_hdrs(p, mask_outer, value_outer); + } + + if (match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS) { + trace_seq_printf(p, "[misc] "); + print_misc_parameters_hdrs(p, mask_misc, value_misc); + } + if (match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS) { + trace_seq_printf(p, "[inner] "); + print_lyr_2_4_hdrs(p, mask_inner, value_inner); + } + trace_seq_putc(p, 0); + return ret; +} + +const char *parse_fs_dst(struct trace_seq *p, + const struct mlx5_flow_destination *dst, + u32 counter_id) +{ + const char *ret = trace_seq_buffer_ptr(p); + + switch (dst->type) { + case MLX5_FLOW_DESTINATION_TYPE_VPORT: + trace_seq_printf(p, "vport=%u\n", dst->vport_num); + break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: + trace_seq_printf(p, "ft=%p\n", dst->ft); + break; + case MLX5_FLOW_DESTINATION_TYPE_TIR: + trace_seq_printf(p, "tir=%u\n", dst->tir_num); + break; + case MLX5_FLOW_DESTINATION_TYPE_COUNTER: + trace_seq_printf(p, "counter_id=%u\n", counter_id); + break; + } + + trace_seq_putc(p, 0); + return ret; +} + +EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_add_fg); +EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_del_fg); +EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_set_fte); +EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_del_fte); +EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_add_rule); +EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_del_rule); + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h new file mode 100644 index 000000000000..1e3a6c3e4132 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h @@ -0,0 +1,282 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#if !defined(_MLX5_FS_TP_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_FS_TP_ + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> +#include "../fs_core.h" + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#define __parse_fs_hdrs(match_criteria_enable, mouter, mmisc, minner, vouter, \ + vinner, vmisc) \ + parse_fs_hdrs(p, match_criteria_enable, mouter, mmisc, minner, vouter,\ + vinner, vmisc) + +const char *parse_fs_hdrs(struct trace_seq *p, + u8 match_criteria_enable, + const u32 *mask_outer, + const u32 *mask_misc, + const u32 *mask_inner, + const u32 *value_outer, + const u32 *value_misc, + const u32 *value_inner); + +#define __parse_fs_dst(dst, counter_id) \ + parse_fs_dst(p, (const struct mlx5_flow_destination *)dst, counter_id) + +const char *parse_fs_dst(struct trace_seq *p, + const struct mlx5_flow_destination *dst, + u32 counter_id); + +TRACE_EVENT(mlx5_fs_add_fg, + TP_PROTO(const struct mlx5_flow_group *fg), + TP_ARGS(fg), + TP_STRUCT__entry( + __field(const struct mlx5_flow_group *, fg) + __field(const struct mlx5_flow_table *, ft) + __field(u32, start_index) + __field(u32, end_index) + __field(u32, id) + __field(u8, mask_enable) + __array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) + __array(u32, mask_inner, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) + __array(u32, mask_misc, MLX5_ST_SZ_DW(fte_match_set_misc)) + ), + TP_fast_assign( + __entry->fg = fg; + fs_get_obj(__entry->ft, fg->node.parent); + __entry->start_index = fg->start_index; + __entry->end_index = fg->start_index + fg->max_ftes; + __entry->id = fg->id; + __entry->mask_enable = fg->mask.match_criteria_enable; + memcpy(__entry->mask_outer, + MLX5_ADDR_OF(fte_match_param, + &fg->mask.match_criteria, + outer_headers), + sizeof(__entry->mask_outer)); + memcpy(__entry->mask_inner, + MLX5_ADDR_OF(fte_match_param, + &fg->mask.match_criteria, + inner_headers), + sizeof(__entry->mask_inner)); + memcpy(__entry->mask_misc, + MLX5_ADDR_OF(fte_match_param, + &fg->mask.match_criteria, + misc_parameters), + sizeof(__entry->mask_misc)); + + ), + TP_printk("fg=%p ft=%p id=%u start=%u end=%u bit_mask=%02x %s\n", + __entry->fg, __entry->ft, __entry->id, + __entry->start_index, __entry->end_index, + __entry->mask_enable, + __parse_fs_hdrs(__entry->mask_enable, + __entry->mask_outer, + __entry->mask_misc, + __entry->mask_inner, + __entry->mask_outer, + __entry->mask_misc, + __entry->mask_inner)) + ); + +TRACE_EVENT(mlx5_fs_del_fg, + TP_PROTO(const struct mlx5_flow_group *fg), + TP_ARGS(fg), + TP_STRUCT__entry( + __field(const struct mlx5_flow_group *, fg) + __field(u32, id) + ), + TP_fast_assign( + __entry->fg = fg; + __entry->id = fg->id; + + ), + TP_printk("fg=%p id=%u\n", + __entry->fg, __entry->id) + ); + +#define ACTION_FLAGS \ + {MLX5_FLOW_CONTEXT_ACTION_ALLOW, "ALLOW"},\ + {MLX5_FLOW_CONTEXT_ACTION_DROP, "DROP"},\ + {MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, "FWD"},\ + {MLX5_FLOW_CONTEXT_ACTION_COUNT, "CNT"},\ + {MLX5_FLOW_CONTEXT_ACTION_ENCAP, "ENCAP"},\ + {MLX5_FLOW_CONTEXT_ACTION_DECAP, "DECAP"},\ + {MLX5_FLOW_CONTEXT_ACTION_MOD_HDR, "MOD_HDR"},\ + {MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO, "NEXT_PRIO"} + +TRACE_EVENT(mlx5_fs_set_fte, + TP_PROTO(const struct fs_fte *fte, bool new_fte), + TP_ARGS(fte, new_fte), + TP_STRUCT__entry( + __field(const struct fs_fte *, fte) + __field(const struct mlx5_flow_group *, fg) + __field(u32, group_index) + __field(u32, index) + __field(u32, action) + __field(u32, flow_tag) + __field(u8, mask_enable) + __field(bool, new_fte) + __array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) + __array(u32, mask_inner, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) + __array(u32, mask_misc, MLX5_ST_SZ_DW(fte_match_set_misc)) + __array(u32, value_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) + __array(u32, value_inner, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4)) + __array(u32, value_misc, MLX5_ST_SZ_DW(fte_match_set_misc)) + ), + TP_fast_assign( + __entry->fte = fte; + __entry->new_fte = new_fte; + fs_get_obj(__entry->fg, fte->node.parent); + __entry->group_index = __entry->fg->id; + __entry->index = fte->index; + __entry->action = fte->action; + __entry->mask_enable = __entry->fg->mask.match_criteria_enable; + __entry->flow_tag = fte->flow_tag; + memcpy(__entry->mask_outer, + MLX5_ADDR_OF(fte_match_param, + &__entry->fg->mask.match_criteria, + outer_headers), + sizeof(__entry->mask_outer)); + memcpy(__entry->mask_inner, + MLX5_ADDR_OF(fte_match_param, + &__entry->fg->mask.match_criteria, + inner_headers), + sizeof(__entry->mask_inner)); + memcpy(__entry->mask_misc, + MLX5_ADDR_OF(fte_match_param, + &__entry->fg->mask.match_criteria, + misc_parameters), + sizeof(__entry->mask_misc)); + memcpy(__entry->value_outer, + MLX5_ADDR_OF(fte_match_param, + &fte->val, + outer_headers), + sizeof(__entry->value_outer)); + memcpy(__entry->value_inner, + MLX5_ADDR_OF(fte_match_param, + &fte->val, + inner_headers), + sizeof(__entry->value_inner)); + memcpy(__entry->value_misc, + MLX5_ADDR_OF(fte_match_param, + &fte->val, + misc_parameters), + sizeof(__entry->value_misc)); + + ), + TP_printk("op=%s fte=%p fg=%p index=%u group_index=%u action=<%s> flow_tag=%x %s\n", + __entry->new_fte ? "add" : "set", + __entry->fte, __entry->fg, __entry->index, + __entry->group_index, __print_flags(__entry->action, "|", + ACTION_FLAGS), + __entry->flow_tag, + __parse_fs_hdrs(__entry->mask_enable, + __entry->mask_outer, + __entry->mask_misc, + __entry->mask_inner, + __entry->value_outer, + __entry->value_misc, + __entry->value_inner)) + ); + +TRACE_EVENT(mlx5_fs_del_fte, + TP_PROTO(const struct fs_fte *fte), + TP_ARGS(fte), + TP_STRUCT__entry( + __field(const struct fs_fte *, fte) + __field(u32, index) + ), + TP_fast_assign( + __entry->fte = fte; + __entry->index = fte->index; + + ), + TP_printk("fte=%p index=%u\n", + __entry->fte, __entry->index) + ); + +TRACE_EVENT(mlx5_fs_add_rule, + TP_PROTO(const struct mlx5_flow_rule *rule), + TP_ARGS(rule), + TP_STRUCT__entry( + __field(const struct mlx5_flow_rule *, rule) + __field(const struct fs_fte *, fte) + __field(u32, sw_action) + __field(u32, index) + __field(u32, counter_id) + __array(u8, destination, sizeof(struct mlx5_flow_destination)) + ), + TP_fast_assign( + __entry->rule = rule; + fs_get_obj(__entry->fte, rule->node.parent); + __entry->index = __entry->fte->dests_size - 1; + __entry->sw_action = rule->sw_action; + memcpy(__entry->destination, + &rule->dest_attr, + sizeof(__entry->destination)); + if (rule->dest_attr.type & MLX5_FLOW_DESTINATION_TYPE_COUNTER && + rule->dest_attr.counter) + __entry->counter_id = + rule->dest_attr.counter->id; + ), + TP_printk("rule=%p fte=%p index=%u sw_action=<%s> [dst] %s\n", + __entry->rule, __entry->fte, __entry->index, + __print_flags(__entry->sw_action, "|", ACTION_FLAGS), + __parse_fs_dst(__entry->destination, __entry->counter_id)) + ); + +TRACE_EVENT(mlx5_fs_del_rule, + TP_PROTO(const struct mlx5_flow_rule *rule), + TP_ARGS(rule), + TP_STRUCT__entry( + __field(const struct mlx5_flow_rule *, rule) + __field(const struct fs_fte *, fte) + ), + TP_fast_assign( + __entry->rule = rule; + fs_get_obj(__entry->fte, rule->node.parent); + ), + TP_printk("rule=%p fte=%p\n", + __entry->rule, __entry->fte) + ); +#endif + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ./diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE fs_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 040d1af310b4..cc13d3dbd366 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -291,10 +291,11 @@ struct mlx5e_tstamp { enum { MLX5E_RQ_STATE_ENABLED, - MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, MLX5E_RQ_STATE_AM, }; +#define MLX5E_TEST_BIT(state, nr) (state & BIT(nr)) + struct mlx5e_cq { /* data path - accessed per cqe */ struct mlx5_cqwq wq; @@ -342,7 +343,6 @@ enum { struct mlx5e_sq_wqe_info { u8 opcode; - u8 num_wqebbs; }; struct mlx5e_txqsq { @@ -418,13 +418,8 @@ struct mlx5e_xdpsq { struct mlx5e_icosq { /* data path */ - /* dirtied @completion */ - u16 cc; - /* dirtied @xmit */ u16 pc ____cacheline_aligned_in_smp; - u32 dma_fifo_pc; - u16 prev_cc; struct mlx5e_cq cq; @@ -438,7 +433,6 @@ struct mlx5e_icosq { void __iomem *uar_map; u32 sqn; u16 edge; - struct device *pdev; __be32 mkey_be; unsigned long state; @@ -507,7 +501,7 @@ struct mlx5e_rx_am { /* Adaptive Moderation */ */ #define MLX5E_CACHE_UNIT (MLX5_MPWRQ_PAGES_PER_WQE > NAPI_POLL_WEIGHT ? \ MLX5_MPWRQ_PAGES_PER_WQE : NAPI_POLL_WEIGHT) -#define MLX5E_CACHE_SIZE (2 * roundup_pow_of_two(MLX5E_CACHE_UNIT)) +#define MLX5E_CACHE_SIZE (4 * roundup_pow_of_two(MLX5E_CACHE_UNIT)) struct mlx5e_page_cache { u32 head; u32 tail; @@ -516,7 +510,7 @@ struct mlx5e_page_cache { struct mlx5e_rq; typedef void (*mlx5e_fp_handle_rx_cqe)(struct mlx5e_rq*, struct mlx5_cqe64*); -typedef int (*mlx5e_fp_alloc_wqe)(struct mlx5e_rq*, struct mlx5e_rx_wqe*, u16); +typedef bool (*mlx5e_fp_post_rx_wqes)(struct mlx5e_rq *rq); typedef void (*mlx5e_fp_dealloc_wqe)(struct mlx5e_rq*, u16); struct mlx5e_rq { @@ -527,21 +521,26 @@ struct mlx5e_rq { struct { struct mlx5e_wqe_frag_info *frag_info; u32 frag_sz; /* max possible skb frag_sz */ - bool page_reuse; - bool xdp_xmit; + union { + bool page_reuse; + bool xdp_xmit; + }; } wqe; struct { struct mlx5e_mpw_info *info; void *mtt_no_align; + u16 num_strides; + u8 log_stride_sz; + bool umr_in_progress; } mpwqe; }; struct { + u16 headroom; u8 page_order; - u32 wqe_sz; /* wqe data buffer size */ u8 map_dir; /* dma map direction */ } buff; - __be32 mkey_be; + struct mlx5e_channel *channel; struct device *pdev; struct net_device *netdev; struct mlx5e_tstamp *tstamp; @@ -550,12 +549,11 @@ struct mlx5e_rq { struct mlx5e_page_cache page_cache; mlx5e_fp_handle_rx_cqe handle_rx_cqe; - mlx5e_fp_alloc_wqe alloc_wqe; + mlx5e_fp_post_rx_wqes post_wqes; mlx5e_fp_dealloc_wqe dealloc_wqe; unsigned long state; int ix; - u16 rx_headroom; struct mlx5e_rx_am am; /* Adaptive Moderation */ @@ -565,19 +563,13 @@ struct mlx5e_rq { /* control */ struct mlx5_wq_ctrl wq_ctrl; + __be32 mkey_be; u8 wq_type; - u32 mpwqe_stride_sz; - u32 mpwqe_num_strides; u32 rqn; - struct mlx5e_channel *channel; struct mlx5_core_dev *mdev; struct mlx5_core_mkey umr_mkey; } ____cacheline_aligned_in_smp; -enum channel_flags { - MLX5E_CHANNEL_NAPI_SCHED = 1, -}; - struct mlx5e_channel { /* data path */ struct mlx5e_rq rq; @@ -589,7 +581,9 @@ struct mlx5e_channel { struct net_device *netdev; __be32 mkey_be; u8 num_tc; - unsigned long flags; + + /* data path - accessed per napi poll */ + struct irq_desc *irq_desc; /* control */ struct mlx5e_priv *priv; @@ -620,6 +614,12 @@ enum mlx5e_traffic_types { MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY, }; +enum mlx5e_tunnel_types { + MLX5E_TT_IPV4_GRE, + MLX5E_TT_IPV6_GRE, + MLX5E_NUM_TUNNEL_TT, +}; + enum { MLX5E_STATE_ASYNC_EVENTS_ENABLED, MLX5E_STATE_OPENED, @@ -679,6 +679,7 @@ struct mlx5e_l2_table { struct mlx5e_ttc_table { struct mlx5e_flow_table ft; struct mlx5_flow_handle *rules[MLX5E_NUM_TT]; + struct mlx5_flow_handle *tunnel_rules[MLX5E_NUM_TUNNEL_TT]; }; #define ARFS_HASH_SHIFT BITS_PER_BYTE @@ -711,6 +712,7 @@ enum { MLX5E_VLAN_FT_LEVEL = 0, MLX5E_L2_FT_LEVEL, MLX5E_TTC_FT_LEVEL, + MLX5E_INNER_TTC_FT_LEVEL, MLX5E_ARFS_FT_LEVEL }; @@ -736,6 +738,7 @@ struct mlx5e_flow_steering { struct mlx5e_vlan_table vlan; struct mlx5e_l2_table l2; struct mlx5e_ttc_table ttc; + struct mlx5e_ttc_table inner_ttc; struct mlx5e_arfs_tables arfs; }; @@ -769,6 +772,7 @@ struct mlx5e_priv { u32 tisn[MLX5E_MAX_NUM_TC]; struct mlx5e_rqt indir_rqt; struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; + struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir direct_tir[MLX5E_MAX_NUM_CHANNELS]; u32 tx_rates[MLX5E_MAX_NUM_SQS]; int hard_mtu; @@ -839,11 +843,9 @@ void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); -int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix); -int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix); +bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq); void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix); void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix); -void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq); void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi); void mlx5e_rx_am(struct mlx5e_rq *rq); @@ -903,7 +905,7 @@ int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, struct mlx5e_redirect_rqt_param rrp); void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params, enum mlx5e_traffic_types tt, - void *tirc); + void *tirc, bool inner); int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); @@ -922,8 +924,7 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, void mlx5e_activate_priv_channels(struct mlx5e_priv *priv); void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv); -void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev, - u32 *indirection_rqt, int len, +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, int num_channels); int mlx5e_get_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); @@ -932,6 +933,12 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params, u8 rq_type); +static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) +{ + return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); +} + static inline struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index f5594014715b..d12e9fc0d76b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -176,7 +176,6 @@ static bool mlx5e_query_global_pause_combined(struct mlx5e_priv *priv) int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset) { - switch (sset) { case ETH_SS_STATS: return NUM_SW_COUNTERS + @@ -207,7 +206,7 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset) return mlx5e_ethtool_get_sset_count(priv, sset); } -static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) +static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, u8 *data) { int i, j, tc, prio, idx = 0; unsigned long pfc_combined; @@ -242,10 +241,22 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_phy_statistical_stats_desc[i].format); + for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS(priv); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + pport_eth_ext_stats_desc[i].format); + for (i = 0; i < NUM_PCIE_PERF_COUNTERS(priv); i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, pcie_perf_stats_desc[i].format); + for (i = 0; i < NUM_PCIE_PERF_COUNTERS64(priv); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + pcie_perf_stats_desc64[i].format); + + for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS(priv); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + pcie_perf_stall_stats_desc[i].format); + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++) sprintf(data + (idx++) * ETH_GSTRING_LEN, @@ -297,8 +308,7 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) priv->channel_tc2txq[i][tc]); } -void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, - uint32_t stringset, uint8_t *data) +void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data) { int i; @@ -320,8 +330,7 @@ void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, } } -static void mlx5e_get_strings(struct net_device *dev, - uint32_t stringset, uint8_t *data) +static void mlx5e_get_strings(struct net_device *dev, u32 stringset, u8 *data) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -373,10 +382,22 @@ void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv, data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.phy_statistical_counters, pport_phy_statistical_stats_desc, i); + for (i = 0; i < NUM_PPORT_ETH_EXT_COUNTERS(priv); i++) + data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.eth_ext_counters, + pport_eth_ext_stats_desc, i); + for (i = 0; i < NUM_PCIE_PERF_COUNTERS(priv); i++) data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters, pcie_perf_stats_desc, i); + for (i = 0; i < NUM_PCIE_PERF_COUNTERS64(priv); i++) + data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pcie.pcie_perf_counters, + pcie_perf_stats_desc64, i); + + for (i = 0; i < NUM_PCIE_PERF_STALL_COUNTERS(priv); i++) + data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters, + pcie_perf_stall_stats_desc, i); + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++) data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio], @@ -642,8 +663,7 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, new_channels.params = priv->channels.params; new_channels.params.num_channels = count; if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->mdev, - new_channels.params.indirection_rqt, + mlx5e_build_default_indir_rqt(new_channels.params.indirection_rqt, MLX5E_INDIR_RQT_SIZE, count); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { @@ -966,24 +986,27 @@ static u8 get_connector_port(u32 eth_proto, u8 connector_type) if (connector_type && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) return ptys2connector_type[connector_type]; - if (eth_proto & (MLX5E_PROT_MASK(MLX5E_10GBASE_SR) - | MLX5E_PROT_MASK(MLX5E_40GBASE_SR4) - | MLX5E_PROT_MASK(MLX5E_100GBASE_SR4) - | MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII))) { - return PORT_FIBRE; + if (eth_proto & + (MLX5E_PROT_MASK(MLX5E_10GBASE_SR) | + MLX5E_PROT_MASK(MLX5E_40GBASE_SR4) | + MLX5E_PROT_MASK(MLX5E_100GBASE_SR4) | + MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII))) { + return PORT_FIBRE; } - if (eth_proto & (MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) - | MLX5E_PROT_MASK(MLX5E_10GBASE_CR) - | MLX5E_PROT_MASK(MLX5E_100GBASE_CR4))) { - return PORT_DA; + if (eth_proto & + (MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) | + MLX5E_PROT_MASK(MLX5E_10GBASE_CR) | + MLX5E_PROT_MASK(MLX5E_100GBASE_CR4))) { + return PORT_DA; } - if (eth_proto & (MLX5E_PROT_MASK(MLX5E_10GBASE_KX4) - | MLX5E_PROT_MASK(MLX5E_10GBASE_KR) - | MLX5E_PROT_MASK(MLX5E_40GBASE_KR4) - | MLX5E_PROT_MASK(MLX5E_100GBASE_KR4))) { - return PORT_NONE; + if (eth_proto & + (MLX5E_PROT_MASK(MLX5E_10GBASE_KX4) | + MLX5E_PROT_MASK(MLX5E_10GBASE_KR) | + MLX5E_PROT_MASK(MLX5E_40GBASE_KR4) | + MLX5E_PROT_MASK(MLX5E_100GBASE_KR4))) { + return PORT_NONE; } return PORT_OTHER; @@ -1190,9 +1213,18 @@ static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen) for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { memset(tirc, 0, ctxlen); - mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc); + mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false); mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen); } + + if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + return; + + for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { + memset(tirc, 0, ctxlen); + mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true); + mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in, inlen); + } } static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index dfccb5305e9c..f11fd07ac4dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -36,6 +36,7 @@ #include <linux/tcp.h> #include <linux/mlx5/fs.h> #include "en.h" +#include "lib/mpfs.h" static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv, struct mlx5e_l2_rule *ai, int type); @@ -65,6 +66,7 @@ struct mlx5e_l2_hash_node { struct hlist_node hlist; u8 action; struct mlx5e_l2_rule ai; + bool mpfs; }; static inline int mlx5e_hash_l2(u8 *addr) @@ -362,17 +364,30 @@ static void mlx5e_del_vlan_rules(struct mlx5e_priv *priv) static void mlx5e_execute_l2_action(struct mlx5e_priv *priv, struct mlx5e_l2_hash_node *hn) { - switch (hn->action) { + u8 action = hn->action; + int l2_err = 0; + + switch (action) { case MLX5E_ACTION_ADD: mlx5e_add_l2_flow_rule(priv, &hn->ai, MLX5E_FULLMATCH); + if (!is_multicast_ether_addr(hn->ai.addr)) { + l2_err = mlx5_mpfs_add_mac(priv->mdev, hn->ai.addr); + hn->mpfs = !l2_err; + } hn->action = MLX5E_ACTION_NONE; break; case MLX5E_ACTION_DEL: + if (!is_multicast_ether_addr(hn->ai.addr) && hn->mpfs) + l2_err = mlx5_mpfs_del_mac(priv->mdev, hn->ai.addr); mlx5e_del_l2_flow_rule(priv, &hn->ai); mlx5e_del_l2_from_hash(hn); break; } + + if (l2_err) + netdev_warn(priv->netdev, "MPFS, failed to %s mac %pM, err(%d)\n", + action == MLX5E_ACTION_ADD ? "add" : "del", hn->ai.addr, l2_err); } static void mlx5e_sync_netdev_addr(struct mlx5e_priv *priv) @@ -593,12 +608,21 @@ static void mlx5e_cleanup_ttc_rules(struct mlx5e_ttc_table *ttc) ttc->rules[i] = NULL; } } + + for (i = 0; i < MLX5E_NUM_TUNNEL_TT; i++) { + if (!IS_ERR_OR_NULL(ttc->tunnel_rules[i])) { + mlx5_del_flow_rules(ttc->tunnel_rules[i]); + ttc->tunnel_rules[i] = NULL; + } + } } -static struct { +struct mlx5e_etype_proto { u16 etype; u8 proto; -} ttc_rules[] = { +}; + +static struct mlx5e_etype_proto ttc_rules[] = { [MLX5E_TT_IPV4_TCP] = { .etype = ETH_P_IP, .proto = IPPROTO_TCP, @@ -645,6 +669,28 @@ static struct { }, }; +static struct mlx5e_etype_proto ttc_tunnel_rules[] = { + [MLX5E_TT_IPV4_GRE] = { + .etype = ETH_P_IP, + .proto = IPPROTO_GRE, + }, + [MLX5E_TT_IPV6_GRE] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_GRE, + }, +}; + +static u8 mlx5e_etype_to_ipv(u16 ethertype) +{ + if (ethertype == ETH_P_IP) + return 4; + + if (ethertype == ETH_P_IPV6) + return 6; + + return 0; +} + static struct mlx5_flow_handle * mlx5e_generate_ttc_rule(struct mlx5e_priv *priv, struct mlx5_flow_table *ft, @@ -652,10 +698,12 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv, u16 etype, u8 proto) { + int match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version); MLX5_DECLARE_FLOW_ACT(flow_act); struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; int err = 0; + u8 ipv; spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) @@ -666,7 +714,13 @@ mlx5e_generate_ttc_rule(struct mlx5e_priv *priv, MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_protocol); MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, proto); } - if (etype) { + + ipv = mlx5e_etype_to_ipv(etype); + if (match_ipv_outer && ipv) { + spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ip_version); + MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_version, ipv); + } else if (etype) { spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.ethertype); MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype); @@ -708,6 +762,20 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv) goto del_rules; } + if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + return 0; + + rules = ttc->tunnel_rules; + dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest.ft = priv->fs.inner_ttc.ft.t; + for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { + rules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest, + ttc_tunnel_rules[tt].etype, + ttc_tunnel_rules[tt].proto); + if (IS_ERR(rules[tt])) + goto del_rules; + } + return 0; del_rules: @@ -718,13 +786,23 @@ del_rules: } #define MLX5E_TTC_NUM_GROUPS 3 -#define MLX5E_TTC_GROUP1_SIZE BIT(3) -#define MLX5E_TTC_GROUP2_SIZE BIT(1) -#define MLX5E_TTC_GROUP3_SIZE BIT(0) +#define MLX5E_TTC_GROUP1_SIZE (BIT(3) + MLX5E_NUM_TUNNEL_TT) +#define MLX5E_TTC_GROUP2_SIZE BIT(1) +#define MLX5E_TTC_GROUP3_SIZE BIT(0) #define MLX5E_TTC_TABLE_SIZE (MLX5E_TTC_GROUP1_SIZE +\ MLX5E_TTC_GROUP2_SIZE +\ MLX5E_TTC_GROUP3_SIZE) -static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc) + +#define MLX5E_INNER_TTC_NUM_GROUPS 3 +#define MLX5E_INNER_TTC_GROUP1_SIZE BIT(3) +#define MLX5E_INNER_TTC_GROUP2_SIZE BIT(1) +#define MLX5E_INNER_TTC_GROUP3_SIZE BIT(0) +#define MLX5E_INNER_TTC_TABLE_SIZE (MLX5E_INNER_TTC_GROUP1_SIZE +\ + MLX5E_INNER_TTC_GROUP2_SIZE +\ + MLX5E_INNER_TTC_GROUP3_SIZE) + +static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc, + bool use_ipv) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5e_flow_table *ft = &ttc->ft; @@ -746,7 +824,10 @@ static int mlx5e_create_ttc_table_groups(struct mlx5e_ttc_table *ttc) /* L4 Group */ mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_protocol); - MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); + if (use_ipv) + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ip_version); + else + MLX5_SET_TO_ONES(fte_match_param, mc, outer_headers.ethertype); MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); MLX5_SET_CFG(in, start_flow_index, ix); ix += MLX5E_TTC_GROUP1_SIZE; @@ -787,6 +868,190 @@ err: return err; } +static struct mlx5_flow_handle * +mlx5e_generate_inner_ttc_rule(struct mlx5e_priv *priv, + struct mlx5_flow_table *ft, + struct mlx5_flow_destination *dest, + u16 etype, u8 proto) +{ + MLX5_DECLARE_FLOW_ACT(flow_act); + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err = 0; + u8 ipv; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return ERR_PTR(-ENOMEM); + + ipv = mlx5e_etype_to_ipv(etype); + if (etype && ipv) { + spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_version); + MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_version, ipv); + } + + if (proto) { + spec->match_criteria_enable = MLX5_MATCH_INNER_HEADERS; + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, inner_headers.ip_protocol); + MLX5_SET(fte_match_param, spec->match_value, inner_headers.ip_protocol, proto); + } + + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + netdev_err(priv->netdev, "%s: add rule failed\n", __func__); + } + + kvfree(spec); + return err ? ERR_PTR(err) : rule; +} + +static int mlx5e_generate_inner_ttc_table_rules(struct mlx5e_priv *priv) +{ + struct mlx5_flow_destination dest; + struct mlx5_flow_handle **rules; + struct mlx5e_ttc_table *ttc; + struct mlx5_flow_table *ft; + int err; + int tt; + + ttc = &priv->fs.inner_ttc; + ft = ttc->ft.t; + rules = ttc->rules; + + dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; + for (tt = 0; tt < MLX5E_NUM_TT; tt++) { + if (tt == MLX5E_TT_ANY) + dest.tir_num = priv->direct_tir[0].tirn; + else + dest.tir_num = priv->inner_indir_tir[tt].tirn; + + rules[tt] = mlx5e_generate_inner_ttc_rule(priv, ft, &dest, + ttc_rules[tt].etype, + ttc_rules[tt].proto); + if (IS_ERR(rules[tt])) + goto del_rules; + } + + return 0; + +del_rules: + err = PTR_ERR(rules[tt]); + rules[tt] = NULL; + mlx5e_cleanup_ttc_rules(ttc); + return err; +} + +static int mlx5e_create_inner_ttc_table_groups(struct mlx5e_ttc_table *ttc) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5e_flow_table *ft = &ttc->ft; + int ix = 0; + u32 *in; + int err; + u8 *mc; + + ft->g = kcalloc(MLX5E_INNER_TTC_NUM_GROUPS, sizeof(*ft->g), GFP_KERNEL); + if (!ft->g) + return -ENOMEM; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + kfree(ft->g); + return -ENOMEM; + } + + /* L4 Group */ + mc = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_protocol); + MLX5_SET_TO_ONES(fte_match_param, mc, inner_headers.ip_version); + MLX5_SET_CFG(in, match_criteria_enable, MLX5_MATCH_INNER_HEADERS); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_INNER_TTC_GROUP1_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err; + ft->num_groups++; + + /* L3 Group */ + MLX5_SET(fte_match_param, mc, inner_headers.ip_protocol, 0); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_INNER_TTC_GROUP2_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err; + ft->num_groups++; + + /* Any Group */ + memset(in, 0, inlen); + MLX5_SET_CFG(in, start_flow_index, ix); + ix += MLX5E_INNER_TTC_GROUP3_SIZE; + MLX5_SET_CFG(in, end_flow_index, ix - 1); + ft->g[ft->num_groups] = mlx5_create_flow_group(ft->t, in); + if (IS_ERR(ft->g[ft->num_groups])) + goto err; + ft->num_groups++; + + kvfree(in); + return 0; + +err: + err = PTR_ERR(ft->g[ft->num_groups]); + ft->g[ft->num_groups] = NULL; + kvfree(in); + + return err; +} + +static int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv) +{ + struct mlx5e_ttc_table *ttc = &priv->fs.inner_ttc; + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5e_flow_table *ft = &ttc->ft; + int err; + + if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + return 0; + + ft_attr.max_fte = MLX5E_INNER_TTC_TABLE_SIZE; + ft_attr.level = MLX5E_INNER_TTC_FT_LEVEL; + ft_attr.prio = MLX5E_NIC_PRIO; + + ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr); + if (IS_ERR(ft->t)) { + err = PTR_ERR(ft->t); + ft->t = NULL; + return err; + } + + err = mlx5e_create_inner_ttc_table_groups(ttc); + if (err) + goto err; + + err = mlx5e_generate_inner_ttc_table_rules(priv); + if (err) + goto err; + + return 0; + +err: + mlx5e_destroy_flow_table(ft); + return err; +} + +static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv) +{ + struct mlx5e_ttc_table *ttc = &priv->fs.inner_ttc; + + if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + return; + + mlx5e_cleanup_ttc_rules(ttc); + mlx5e_destroy_flow_table(&ttc->ft); +} + void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) { struct mlx5e_ttc_table *ttc = &priv->fs.ttc; @@ -797,6 +1062,7 @@ void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv) int mlx5e_create_ttc_table(struct mlx5e_priv *priv) { + bool match_ipv_outer = MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ft_field_support.outer_ip_version); struct mlx5e_ttc_table *ttc = &priv->fs.ttc; struct mlx5_flow_table_attr ft_attr = {}; struct mlx5e_flow_table *ft = &ttc->ft; @@ -813,7 +1079,7 @@ int mlx5e_create_ttc_table(struct mlx5e_priv *priv) return err; } - err = mlx5e_create_ttc_table_groups(ttc); + err = mlx5e_create_ttc_table_groups(ttc, match_ipv_outer); if (err) goto err; @@ -1139,11 +1405,18 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv) priv->netdev->hw_features &= ~NETIF_F_NTUPLE; } + err = mlx5e_create_inner_ttc_table(priv); + if (err) { + netdev_err(priv->netdev, "Failed to create inner ttc table, err=%d\n", + err); + goto err_destroy_arfs_tables; + } + err = mlx5e_create_ttc_table(priv); if (err) { netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n", err); - goto err_destroy_arfs_tables; + goto err_destroy_inner_ttc_table; } err = mlx5e_create_l2_table(priv); @@ -1168,6 +1441,8 @@ err_destroy_l2_table: mlx5e_destroy_l2_table(priv); err_destroy_ttc_table: mlx5e_destroy_ttc_table(priv); +err_destroy_inner_ttc_table: + mlx5e_destroy_inner_ttc_table(priv); err_destroy_arfs_tables: mlx5e_arfs_destroy_tables(priv); @@ -1179,6 +1454,7 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv) mlx5e_destroy_vlan_table(priv); mlx5e_destroy_l2_table(priv); mlx5e_destroy_ttc_table(priv); + mlx5e_destroy_inner_ttc_table(priv); mlx5e_arfs_destroy_tables(priv); mlx5e_ethtool_cleanup_steering(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d75f3099d164..dfc29720ab77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -213,6 +213,7 @@ static void mlx5e_update_sw_counters(struct mlx5e_priv *priv) s->rx_cache_full += rq_stats->cache_full; s->rx_cache_empty += rq_stats->cache_empty; s->rx_cache_busy += rq_stats->cache_busy; + s->rx_cache_waive += rq_stats->cache_waive; for (j = 0; j < priv->channels.params.num_tc; j++) { sq_stats = &c->sq[j].stats; @@ -293,6 +294,12 @@ static void mlx5e_update_pport_counters(struct mlx5e_priv *priv, bool full) mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0); } + if (MLX5_CAP_PCAM_FEATURE(mdev, rx_buffer_fullness_counters)) { + out = pstats->eth_ext_counters; + MLX5_SET(ppcnt_reg, in, grp, MLX5_ETHERNET_EXTENDED_COUNTERS_GROUP); + mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0); + } + MLX5_SET(ppcnt_reg, in, grp, MLX5_PER_PRIORITY_COUNTERS_GROUP); for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { out = pstats->per_prio_counters[prio]; @@ -593,12 +600,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, } rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - rq->rx_headroom = params->rq_headroom; + rq->buff.headroom = params->rq_headroom; switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - rq->alloc_wqe = mlx5e_alloc_rx_mpwqe; + rq->post_wqes = mlx5e_post_rx_mpwqes; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; rq->handle_rx_cqe = c->priv->profile->rx_handlers.handle_rx_cqe_mpwqe; @@ -615,11 +622,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, goto err_rq_wq_destroy; } - rq->mpwqe_stride_sz = BIT(params->mpwqe_log_stride_sz); - rq->mpwqe_num_strides = BIT(params->mpwqe_log_num_strides); + rq->mpwqe.log_stride_sz = params->mpwqe_log_stride_sz; + rq->mpwqe.num_strides = BIT(params->mpwqe_log_num_strides); - rq->buff.wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides; - byte_count = rq->buff.wqe_sz; + byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz; err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) @@ -639,7 +645,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = -ENOMEM; goto err_rq_wq_destroy; } - rq->alloc_wqe = mlx5e_alloc_rx_wqe; + rq->post_wqes = mlx5e_post_rx_wqes; rq->dealloc_wqe = mlx5e_dealloc_rx_wqe; #ifdef CONFIG_MLX5_EN_IPSEC @@ -655,18 +661,17 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, goto err_rq_wq_destroy; } - rq->buff.wqe_sz = params->lro_en ? + byte_count = params->lro_en ? params->lro_wqe_sz : MLX5E_SW2HW_MTU(c->priv, c->netdev->mtu); #ifdef CONFIG_MLX5_EN_IPSEC if (MLX5_IPSEC_DEV(mdev)) - rq->buff.wqe_sz += MLX5E_METADATA_ETHER_LEN; + byte_count += MLX5E_METADATA_ETHER_LEN; #endif rq->wqe.page_reuse = !params->xdp_prog && !params->lro_en; - byte_count = rq->buff.wqe_sz; /* calc the required page order */ - rq->wqe.frag_sz = MLX5_SKB_FRAG_SZ(rq->rx_headroom + byte_count); + rq->wqe.frag_sz = MLX5_SKB_FRAG_SZ(rq->buff.headroom + byte_count); npages = DIV_ROUND_UP(rq->wqe.frag_sz, PAGE_SIZE); rq->buff.page_order = order_base_2(npages); @@ -677,6 +682,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, for (i = 0; i < wq_sz; i++) { struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i); + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, i) << PAGE_SHIFT; + + wqe->data.addr = cpu_to_be64(dma_offset); + } + wqe->data.byte_count = cpu_to_be32(byte_count); wqe->data.lkey = rq->mkey_be; } @@ -883,7 +894,8 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) u16 wqe_ix; /* UMR WQE (if in progress) is always at wq->head */ - if (test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && + rq->mpwqe.umr_in_progress) mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); while (!mlx5_wq_ll_is_empty(wq)) { @@ -926,7 +938,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, goto err_destroy_rq; if (params->rx_am_enabled) - set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); + c->rq.state |= BIT(MLX5E_RQ_STATE_AM); return 0; @@ -946,7 +958,6 @@ static void mlx5e_activate_rq(struct mlx5e_rq *rq) set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP; - sq->db.ico_wqe[pi].num_wqebbs = 1; nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &nopwqe->ctrl); } @@ -1048,7 +1059,6 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = c->mdev; int err; - sq->pdev = c->pdev; sq->mkey_be = c->mkey_be; sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; @@ -1752,7 +1762,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_cq_moder icocq_moder = {0, 0}; struct net_device *netdev = priv->netdev; struct mlx5e_channel *c; + unsigned int irq; int err; + int eqn; c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix)); if (!c) @@ -1768,6 +1780,9 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->num_tc = params->num_tc; c->xdp = !!params->xdp_prog; + mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq); + c->irq_desc = irq_to_desc(irq); + netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64); err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq); @@ -2345,9 +2360,10 @@ static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc) void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params, enum mlx5e_traffic_types tt, - void *tirc) + void *tirc, bool inner) { - void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); + void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) : + MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer); #define MLX5_HASH_IP (MLX5_HASH_FIELD_SEL_SRC_IP |\ MLX5_HASH_FIELD_SEL_DST_IP) @@ -2496,6 +2512,21 @@ free_in: return err; } +static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv, + enum mlx5e_traffic_types tt, + u32 *tirc) +{ + MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn); + + mlx5e_build_tir_ctx_lro(&priv->channels.params, tirc); + + MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); + MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn); + MLX5_SET(tirc, tirc, tunneled_offload_en, 0x1); + + mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true); +} + static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu) { struct mlx5_core_dev *mdev = priv->mdev; @@ -2583,12 +2614,6 @@ static void mlx5e_build_channels_tx_maps(struct mlx5e_priv *priv) } } -static bool mlx5e_is_eswitch_vport_mngr(struct mlx5_core_dev *mdev) -{ - return (MLX5_CAP_GEN(mdev, vport_group_manager) && - MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH); -} - void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { int num_txqs = priv->channels.num * priv->channels.params.num_tc; @@ -2602,7 +2627,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_activate_channels(&priv->channels); netif_tx_start_all_queues(priv->netdev); - if (mlx5e_is_eswitch_vport_mngr(priv->mdev)) + if (MLX5_VPORT_MANAGER(priv->mdev)) mlx5e_add_sqs_fwd_rules(priv); mlx5e_wait_channels_min_rx_wqes(&priv->channels); @@ -2613,7 +2638,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { mlx5e_redirect_rqts_to_drop(priv); - if (mlx5e_is_eswitch_vport_mngr(priv->mdev)) + if (MLX5_VPORT_MANAGER(priv->mdev)) mlx5e_remove_sqs_fwd_rules(priv); /* FIXME: This is a W/A only for tx timeout watch dog false alarm when @@ -2690,6 +2715,8 @@ int mlx5e_open(struct net_device *netdev) mutex_lock(&priv->state_lock); err = mlx5e_open_locked(netdev); + if (!err) + mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP); mutex_unlock(&priv->state_lock); return err; @@ -2724,6 +2751,7 @@ int mlx5e_close(struct net_device *netdev) return -ENODEV; mutex_lock(&priv->state_lock); + mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_DOWN); err = mlx5e_close_locked(netdev); mutex_unlock(&priv->state_lock); @@ -2864,7 +2892,7 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT); MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn); - mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc); + mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false); } static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc) @@ -2883,6 +2911,7 @@ int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv) struct mlx5e_tir *tir; void *tirc; int inlen; + int i = 0; int err; u32 *in; int tt; @@ -2898,16 +2927,36 @@ int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv) tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); mlx5e_build_indir_tir_ctx(priv, tt, tirc); err = mlx5e_create_tir(priv->mdev, tir, in, inlen); - if (err) - goto err_destroy_tirs; + if (err) { + mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err); + goto err_destroy_inner_tirs; + } } + if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + goto out; + + for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) { + memset(in, 0, inlen); + tir = &priv->inner_indir_tir[i]; + tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); + mlx5e_build_inner_indir_tir_ctx(priv, i, tirc); + err = mlx5e_create_tir(priv->mdev, tir, in, inlen); + if (err) { + mlx5_core_warn(priv->mdev, "create inner indirect tirs failed, %d\n", err); + goto err_destroy_inner_tirs; + } + } + +out: kvfree(in); return 0; -err_destroy_tirs: - mlx5_core_warn(priv->mdev, "create indirect tirs failed, %d\n", err); +err_destroy_inner_tirs: + for (i--; i >= 0; i--) + mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]); + for (tt--; tt >= 0; tt--) mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[tt]); @@ -2961,6 +3010,12 @@ void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv) for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) mlx5e_destroy_tir(priv->mdev, &priv->indir_tir[i]); + + if (!mlx5e_tunnel_inner_ft_supported(priv->mdev)) + return; + + for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++) + mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]); } void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv) @@ -3000,12 +3055,16 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) return 0; } -static int mlx5e_setup_tc(struct net_device *netdev, u8 tc) +static int mlx5e_setup_tc_mqprio(struct net_device *netdev, + struct tc_mqprio_qopt *mqprio) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels new_channels = {}; + u8 tc = mqprio->num_tc; int err = 0; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + if (tc && tc != MLX5E_MAX_NUM_TC) return -EINVAL; @@ -3029,39 +3088,42 @@ out: return err; } -static int mlx5e_ndo_setup_tc(struct net_device *dev, u32 handle, - u32 chain_index, __be16 proto, - struct tc_to_netdev *tc) +#ifdef CONFIG_MLX5_ESWITCH +static int mlx5e_setup_tc_cls_flower(struct net_device *dev, + struct tc_cls_flower_offload *cls_flower) { struct mlx5e_priv *priv = netdev_priv(dev); - if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS)) - goto mqprio; + if (!is_classid_clsact_ingress(cls_flower->common.classid) || + cls_flower->common.chain_index) + return -EOPNOTSUPP; - if (chain_index) + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return mlx5e_configure_flower(priv, cls_flower); + case TC_CLSFLOWER_DESTROY: + return mlx5e_delete_flower(priv, cls_flower); + case TC_CLSFLOWER_STATS: + return mlx5e_stats_flower(priv, cls_flower); + default: return -EOPNOTSUPP; + } +} +#endif - switch (tc->type) { +static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { +#ifdef CONFIG_MLX5_ESWITCH case TC_SETUP_CLSFLOWER: - switch (tc->cls_flower->command) { - case TC_CLSFLOWER_REPLACE: - return mlx5e_configure_flower(priv, proto, tc->cls_flower); - case TC_CLSFLOWER_DESTROY: - return mlx5e_delete_flower(priv, tc->cls_flower); - case TC_CLSFLOWER_STATS: - return mlx5e_stats_flower(priv, tc->cls_flower); - } + return mlx5e_setup_tc_cls_flower(dev, type_data); +#endif + case TC_SETUP_MQPRIO: + return mlx5e_setup_tc_mqprio(dev, type_data); default: return -EOPNOTSUPP; } - -mqprio: - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; - - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - - return mlx5e_setup_tc(dev, tc->mqprio->num_tc); } static void @@ -3358,6 +3420,7 @@ static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } +#ifdef CONFIG_MLX5_ESWITCH static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -3460,6 +3523,7 @@ static int mlx5e_get_vf_stats(struct net_device *dev, return mlx5_eswitch_get_vport_stats(mdev->priv.eswitch, vf + 1, vf_stats); } +#endif static void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti) @@ -3489,13 +3553,13 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev, mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0); } -static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv, - struct sk_buff *skb, - netdev_features_t features) +static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, + struct sk_buff *skb, + netdev_features_t features) { struct udphdr *udph; - u16 proto; - u16 port = 0; + u8 proto; + u16 port; switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): @@ -3508,14 +3572,17 @@ static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv, goto out; } - if (proto == IPPROTO_UDP) { + switch (proto) { + case IPPROTO_GRE: + return features; + case IPPROTO_UDP: udph = udp_hdr(skb); port = be16_to_cpu(udph->dest); - } - /* Verify if UDP port is being offloaded by HW */ - if (port && mlx5e_vxlan_lookup_port(priv, port)) - return features; + /* Verify if UDP port is being offloaded by HW */ + if (mlx5e_vxlan_lookup_port(priv, port)) + return features; + } out: /* Disable CSUM and GSO if the udp dport is not offloaded by HW */ @@ -3539,7 +3606,7 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb, /* Validate if the tunneled packet is being offloaded by HW */ if (skb->encapsulation && (features & NETIF_F_CSUM_MASK || features & NETIF_F_GSO_MASK)) - return mlx5e_vxlan_features_check(priv, skb, features); + return mlx5e_tunnel_features_check(priv, skb, features); return features; } @@ -3636,7 +3703,6 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); /* napi_schedule in case we have missed anything */ - set_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags); napi_schedule(&c->napi); if (old_prog) @@ -3693,11 +3759,11 @@ static void mlx5e_netpoll(struct net_device *dev) } #endif -static const struct net_device_ops mlx5e_netdev_ops_basic = { +static const struct net_device_ops mlx5e_netdev_ops = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, .ndo_start_xmit = mlx5e_xmit, - .ndo_setup_tc = mlx5e_ndo_setup_tc, + .ndo_setup_tc = mlx5e_setup_tc, .ndo_select_queue = mlx5e_select_queue, .ndo_get_stats64 = mlx5e_get_stats, .ndo_set_rx_mode = mlx5e_set_rx_mode, @@ -3708,6 +3774,9 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = { .ndo_change_mtu = mlx5e_change_mtu, .ndo_do_ioctl = mlx5e_ioctl, .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate, + .ndo_udp_tunnel_add = mlx5e_add_vxlan_port, + .ndo_udp_tunnel_del = mlx5e_del_vxlan_port, + .ndo_features_check = mlx5e_features_check, #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif @@ -3716,29 +3785,8 @@ static const struct net_device_ops mlx5e_netdev_ops_basic = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = mlx5e_netpoll, #endif -}; - -static const struct net_device_ops mlx5e_netdev_ops_sriov = { - .ndo_open = mlx5e_open, - .ndo_stop = mlx5e_close, - .ndo_start_xmit = mlx5e_xmit, - .ndo_setup_tc = mlx5e_ndo_setup_tc, - .ndo_select_queue = mlx5e_select_queue, - .ndo_get_stats64 = mlx5e_get_stats, - .ndo_set_rx_mode = mlx5e_set_rx_mode, - .ndo_set_mac_address = mlx5e_set_mac, - .ndo_vlan_rx_add_vid = mlx5e_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid, - .ndo_set_features = mlx5e_set_features, - .ndo_change_mtu = mlx5e_change_mtu, - .ndo_do_ioctl = mlx5e_ioctl, - .ndo_udp_tunnel_add = mlx5e_add_vxlan_port, - .ndo_udp_tunnel_del = mlx5e_del_vxlan_port, - .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate, - .ndo_features_check = mlx5e_features_check, -#ifdef CONFIG_RFS_ACCEL - .ndo_rx_flow_steer = mlx5e_rx_flow_steer, -#endif +#ifdef CONFIG_MLX5_ESWITCH + /* SRIOV E-Switch NDOs */ .ndo_set_vf_mac = mlx5e_set_vf_mac, .ndo_set_vf_vlan = mlx5e_set_vf_vlan, .ndo_set_vf_spoofchk = mlx5e_set_vf_spoofchk, @@ -3747,13 +3795,9 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { .ndo_get_vf_config = mlx5e_get_vf_config, .ndo_set_vf_link_state = mlx5e_set_vf_link_state, .ndo_get_vf_stats = mlx5e_get_vf_stats, - .ndo_tx_timeout = mlx5e_tx_timeout, - .ndo_xdp = mlx5e_xdp, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = mlx5e_netpoll, -#endif .ndo_has_offload_stats = mlx5e_has_offload_stats, .ndo_get_offload_stats = mlx5e_get_offload_stats, +#endif }; static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) @@ -3790,8 +3834,7 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev) 2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/; } -void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev, - u32 *indirection_rqt, int len, +void mlx5e_build_default_indir_rqt(u32 *indirection_rqt, int len, int num_channels) { int i; @@ -3934,7 +3977,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, /* RSS */ params->rss_hfunc = ETH_RSS_HASH_XOR; netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key)); - mlx5e_build_default_indir_rqt(mdev, params->indirection_rqt, + mlx5e_build_default_indir_rqt(params->indirection_rqt, MLX5E_INDIR_RQT_SIZE, max_channels); } @@ -3973,9 +4016,11 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) } } +#if IS_ENABLED(CONFIG_NET_SWITCHDEV) && IS_ENABLED(CONFIG_MLX5_ESWITCH) static const struct switchdev_ops mlx5e_switchdev_ops = { .switchdev_port_attr_get = mlx5e_attr_get, }; +#endif static void mlx5e_build_nic_netdev(struct net_device *netdev) { @@ -3986,15 +4031,12 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) SET_NETDEV_DEV(netdev, &mdev->pdev->dev); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) { - netdev->netdev_ops = &mlx5e_netdev_ops_sriov; + netdev->netdev_ops = &mlx5e_netdev_ops; + #ifdef CONFIG_MLX5_CORE_EN_DCB - if (MLX5_CAP_GEN(mdev, qos)) - netdev->dcbnl_ops = &mlx5e_dcbnl_ops; + if (MLX5_CAP_GEN(mdev, vport_group_manager) && MLX5_CAP_GEN(mdev, qos)) + netdev->dcbnl_ops = &mlx5e_dcbnl_ops; #endif - } else { - netdev->netdev_ops = &mlx5e_netdev_ops_basic; - } netdev->watchdog_timeo = 15 * HZ; @@ -4017,20 +4059,32 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; - if (mlx5e_vxlan_allowed(mdev)) { - netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; + if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + netdev->hw_features |= NETIF_F_GSO_PARTIAL; netdev->hw_enc_features |= NETIF_F_IP_CSUM; netdev->hw_enc_features |= NETIF_F_IPV6_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; netdev->hw_enc_features |= NETIF_F_TSO6; - netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; - netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; + netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL; + } + + if (mlx5e_vxlan_allowed(mdev)) { + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; } + if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + netdev->hw_features |= NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM; + netdev->hw_enc_features |= NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM; + netdev->gso_partial_features |= NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM; + } + mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled); if (fcs_supported) @@ -4066,8 +4120,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_set_netdev_dev_addr(netdev); -#ifdef CONFIG_NET_SWITCHDEV - if (MLX5_CAP_GEN(mdev, vport_group_manager)) +#if IS_ENABLED(CONFIG_NET_SWITCHDEV) && IS_ENABLED(CONFIG_MLX5_ESWITCH) + if (MLX5_VPORT_MANAGER(mdev)) netdev->switchdev_ops = &mlx5e_switchdev_ops; #endif @@ -4199,6 +4253,10 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_init_l2_addr(priv); + /* Marking the link as currently not needed by the Driver */ + if (!netif_running(netdev)) + mlx5_set_port_admin_status(mdev, MLX5_PORT_DOWN); + /* MTU range: 68 - hw-specific max */ netdev->min_mtu = ETH_MIN_MTU; mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1); @@ -4209,7 +4267,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_enable_async_events(priv); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) + if (MLX5_VPORT_MANAGER(priv->mdev)) mlx5e_register_vport_reps(priv); if (netdev->reg_state != NETREG_REGISTERED) @@ -4243,7 +4301,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) + if (MLX5_VPORT_MANAGER(priv->mdev)) mlx5e_unregister_vport_reps(priv); mlx5e_disable_async_events(priv); @@ -4416,32 +4474,29 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv) static void *mlx5e_add(struct mlx5_core_dev *mdev) { - struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); - struct mlx5e_rep_priv *rpriv = NULL; + struct net_device *netdev; + void *rpriv = NULL; void *priv; - int vport; int err; - struct net_device *netdev; err = mlx5e_check_required_hca_cap(mdev); if (err) return NULL; - if (MLX5_CAP_GEN(mdev, vport_group_manager)) { - rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL); +#ifdef CONFIG_MLX5_ESWITCH + if (MLX5_VPORT_MANAGER(mdev)) { + rpriv = mlx5e_alloc_nic_rep_priv(mdev); if (!rpriv) { - mlx5_core_warn(mdev, - "Not creating net device, Failed to alloc rep priv data\n"); + mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n"); return NULL; } - rpriv->rep = &esw->offloads.vport_reps[0]; } +#endif netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, rpriv); if (!netdev) { mlx5_core_err(mdev, "mlx5e_create_netdev failed\n"); - goto err_unregister_reps; + goto err_free_rpriv; } priv = netdev_priv(netdev); @@ -4462,14 +4517,9 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev) err_detach: mlx5e_detach(mdev, priv); - err_destroy_netdev: mlx5e_destroy_netdev(priv); - -err_unregister_reps: - for (vport = 1; vport < total_vfs; vport++) - mlx5_eswitch_unregister_vport_rep(esw, vport); - +err_free_rpriv: kfree(rpriv); return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 45e60be9c277..45e03c427faf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -613,15 +613,18 @@ static int mlx5e_rep_open(struct net_device *dev) struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int err; - err = mlx5e_open(dev); + mutex_lock(&priv->state_lock); + err = mlx5e_open_locked(dev); if (err) - return err; + goto unlock; - err = mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP); - if (!err) + if (!mlx5_eswitch_set_vport_state(esw, rep->vport, + MLX5_ESW_VPORT_ADMIN_STATE_UP)) netif_carrier_on(dev); - return 0; +unlock: + mutex_unlock(&priv->state_lock); + return err; } static int mlx5e_rep_close(struct net_device *dev) @@ -630,10 +633,13 @@ static int mlx5e_rep_close(struct net_device *dev) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + int ret; + mutex_lock(&priv->state_lock); (void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN); - - return mlx5e_close(dev); + ret = mlx5e_close_locked(dev); + mutex_unlock(&priv->state_lock); + return ret; } static int mlx5e_rep_get_phys_port_name(struct net_device *dev, @@ -651,37 +657,42 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev, return 0; } -static int mlx5e_rep_ndo_setup_tc(struct net_device *dev, u32 handle, - u32 chain_index, __be16 proto, - struct tc_to_netdev *tc) +static int +mlx5e_rep_setup_tc_cls_flower(struct net_device *dev, + struct tc_cls_flower_offload *cls_flower) { struct mlx5e_priv *priv = netdev_priv(dev); - if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS)) + if (!is_classid_clsact_ingress(cls_flower->common.classid) || + cls_flower->common.chain_index) return -EOPNOTSUPP; - if (tc->egress_dev) { + if (cls_flower->egress_dev) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *uplink_dev = mlx5_eswitch_get_uplink_netdev(esw); - return uplink_dev->netdev_ops->ndo_setup_tc(uplink_dev, handle, - chain_index, - proto, tc); + dev = mlx5_eswitch_get_uplink_netdev(esw); + return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER, + cls_flower); } - if (chain_index) + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return mlx5e_configure_flower(priv, cls_flower); + case TC_CLSFLOWER_DESTROY: + return mlx5e_delete_flower(priv, cls_flower); + case TC_CLSFLOWER_STATS: + return mlx5e_stats_flower(priv, cls_flower); + default: return -EOPNOTSUPP; + } +} - switch (tc->type) { +static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + switch (type) { case TC_SETUP_CLSFLOWER: - switch (tc->cls_flower->command) { - case TC_CLSFLOWER_REPLACE: - return mlx5e_configure_flower(priv, proto, tc->cls_flower); - case TC_CLSFLOWER_DESTROY: - return mlx5e_delete_flower(priv, tc->cls_flower); - case TC_CLSFLOWER_STATS: - return mlx5e_stats_flower(priv, tc->cls_flower); - } + return mlx5e_rep_setup_tc_cls_flower(dev, type_data); default: return -EOPNOTSUPP; } @@ -773,7 +784,7 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_stop = mlx5e_rep_close, .ndo_start_xmit = mlx5e_xmit, .ndo_get_phys_port_name = mlx5e_rep_get_phys_port_name, - .ndo_setup_tc = mlx5e_rep_ndo_setup_tc, + .ndo_setup_tc = mlx5e_rep_setup_tc, .ndo_get_stats64 = mlx5e_rep_get_stats, .ndo_has_offload_stats = mlx5e_has_offload_stats, .ndo_get_offload_stats = mlx5e_get_offload_stats, @@ -913,7 +924,7 @@ static int mlx5e_get_rep_max_num_channels(struct mlx5_core_dev *mdev) return MLX5E_PORT_REPRESENTOR_NCH; } -static struct mlx5e_profile mlx5e_rep_profile = { +static const struct mlx5e_profile mlx5e_rep_profile = { .init = mlx5e_init_rep, .init_rx = mlx5e_init_rep_rx, .cleanup_rx = mlx5e_cleanup_rep_rx, @@ -1099,3 +1110,16 @@ void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv) mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */ mlx5_eswitch_unregister_vport_rep(esw, 0); /* UPLINK PF*/ } + +void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev) +{ + struct mlx5_eswitch *esw = mdev->priv.eswitch; + struct mlx5e_rep_priv *rpriv; + + rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL); + if (!rpriv) + return NULL; + + rpriv->rep = &esw->offloads.vport_reps[0]; + return rpriv; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index a0a1a7a1d6c0..5659ed9f51e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -38,6 +38,7 @@ #include "eswitch.h" #include "en.h" +#ifdef CONFIG_MLX5_ESWITCH struct mlx5e_neigh_update_table { struct rhashtable neigh_ht; /* Save the neigh hash entries in a list in addition to the hash table @@ -123,6 +124,7 @@ struct mlx5e_encap_entry { int encap_size; }; +void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev); void mlx5e_register_vport_reps(struct mlx5e_priv *priv); void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv); bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv); @@ -141,5 +143,12 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv); +#else /* CONFIG_MLX5_ESWITCH */ +static inline void mlx5e_register_vport_reps(struct mlx5e_priv *priv) {} +static inline void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv) {} +static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; } +static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; } +static inline void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) {} +#endif #endif /* __MLX5E_REP_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 7344433259fc..f1dd638384d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -163,7 +163,7 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, static inline bool mlx5e_page_is_reserved(struct page *page) { - return page_is_pfmemalloc(page) || page_to_nid(page) != numa_node_id(); + return page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id(); } static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, @@ -177,8 +177,10 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq, return false; } - if (unlikely(page_is_pfmemalloc(dma_info->page))) + if (unlikely(mlx5e_page_is_reserved(dma_info->page))) { + rq->stats.cache_waive++; return false; + } cache->page_cache[cache->tail] = *dma_info; cache->tail = tail_next; @@ -252,7 +254,7 @@ static inline bool mlx5e_page_reuse(struct mlx5e_rq *rq, !mlx5e_page_is_reserved(wi->di.page); } -int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix) +static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix) { struct mlx5e_wqe_frag_info *wi = &rq->wqe.frag_info[ix]; @@ -263,8 +265,7 @@ int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix) wi->offset = 0; } - wqe->data.addr = cpu_to_be64(wi->di.addr + wi->offset + - rq->rx_headroom); + wqe->data.addr = cpu_to_be64(wi->di.addr + wi->offset + rq->buff.headroom); return 0; } @@ -296,7 +297,7 @@ void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix) static inline int mlx5e_mpwqe_strides_per_page(struct mlx5e_rq *rq) { - return rq->mpwqe_num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER; + return rq->mpwqe.num_strides >> MLX5_MPWRQ_WQE_PAGE_ORDER; } static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq, @@ -305,7 +306,7 @@ static inline void mlx5e_add_skb_frag_mpwqe(struct mlx5e_rq *rq, u32 page_idx, u32 frag_offset, u32 len) { - unsigned int truesize = ALIGN(len, rq->mpwqe_stride_sz); + unsigned int truesize = ALIGN(len, BIT(rq->mpwqe.log_stride_sz)); dma_sync_single_for_cpu(rq->pdev, wi->umr.dma_info[page_idx].addr + frag_offset, @@ -358,7 +359,6 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix) /* fill sq edge with nops to avoid wqe wrap around */ while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) { sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP; - sq->db.ico_wqe[pi].num_wqebbs = 1; mlx5e_post_nop(wq, sq->sqn, &sq->pc); } @@ -369,41 +369,35 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix) MLX5_OPCODE_UMR); sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR; - sq->db.ico_wqe[pi].num_wqebbs = num_wqebbs; sq->pc += num_wqebbs; mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &wqe->ctrl); } static int mlx5e_alloc_rx_umr_mpwqe(struct mlx5e_rq *rq, - struct mlx5e_rx_wqe *wqe, u16 ix) { struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix]; - u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT; int pg_strides = mlx5e_mpwqe_strides_per_page(rq); + struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0]; int err; int i; - for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) { - struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i]; - + for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) { err = mlx5e_page_alloc_mapped(rq, dma_info); if (unlikely(err)) goto err_unmap; wi->umr.mtt[i] = cpu_to_be64(dma_info->addr | MLX5_EN_WR); page_ref_add(dma_info->page, pg_strides); - wi->skbs_frags[i] = 0; } + memset(wi->skbs_frags, 0, sizeof(*wi->skbs_frags) * MLX5_MPWRQ_PAGES_PER_WQE); wi->consumed_strides = 0; - wqe->data.addr = cpu_to_be64(dma_offset); return 0; err_unmap: while (--i >= 0) { - struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i]; - + dma_info--; page_ref_sub(dma_info->page, pg_strides); mlx5e_page_release(rq, dma_info, true); } @@ -414,27 +408,21 @@ err_unmap: void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi) { int pg_strides = mlx5e_mpwqe_strides_per_page(rq); + struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[0]; int i; - for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) { - struct mlx5e_dma_info *dma_info = &wi->umr.dma_info[i]; - + for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) { page_ref_sub(dma_info->page, pg_strides - wi->skbs_frags[i]); mlx5e_page_release(rq, dma_info, true); } } -void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) +static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) { struct mlx5_wq_ll *wq = &rq->wq; struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); - clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state); - - if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) { - mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); - return; - } + rq->mpwqe.umr_in_progress = false; mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index)); @@ -444,16 +432,18 @@ void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) mlx5_wq_ll_update_db_record(wq); } -int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe *wqe, u16 ix) +static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) { int err; - err = mlx5e_alloc_rx_umr_mpwqe(rq, wqe, ix); - if (unlikely(err)) + err = mlx5e_alloc_rx_umr_mpwqe(rq, ix); + if (unlikely(err)) { + rq->stats.buff_alloc_err++; return err; - set_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state); + } + rq->mpwqe.umr_in_progress = true; mlx5e_post_umr_wqe(rq, ix); - return -EBUSY; + return 0; } void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) @@ -463,94 +453,150 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) mlx5e_free_rx_mpwqe(rq, wi); } -#define RQ_CANNOT_POST(rq) \ - (!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state) || \ - test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) - bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) { struct mlx5_wq_ll *wq = &rq->wq; + int err; - if (unlikely(RQ_CANNOT_POST(rq))) + if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED))) return false; - while (!mlx5_wq_ll_is_full(wq)) { + if (mlx5_wq_ll_is_full(wq)) + return false; + + do { struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head); - int err; - err = rq->alloc_wqe(rq, wqe, wq->head); - if (err == -EBUSY) - return true; + err = mlx5e_alloc_rx_wqe(rq, wqe, wq->head); if (unlikely(err)) { rq->stats.buff_alloc_err++; break; } mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index)); - } + } while (!mlx5_wq_ll_is_full(wq)); /* ensure wqes are visible to device before updating doorbell record */ dma_wmb(); mlx5_wq_ll_update_db_record(wq); - return !mlx5_wq_ll_is_full(wq); + return !!err; +} + +static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq, + struct mlx5e_icosq *sq, + struct mlx5e_rq *rq, + struct mlx5_cqe64 *cqe) +{ + struct mlx5_wq_cyc *wq = &sq->wq; + u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1; + struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci]; + + mlx5_cqwq_pop(&cq->wq); + + if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) { + WARN_ONCE(true, "mlx5e: Bad OP in ICOSQ CQE: 0x%x\n", + cqe->op_own); + return; + } + + if (likely(icowi->opcode == MLX5_OPCODE_UMR)) { + mlx5e_post_rx_mpwqe(rq); + return; + } + + if (unlikely(icowi->opcode != MLX5_OPCODE_NOP)) + WARN_ONCE(true, + "mlx5e: Bad OPCODE in ICOSQ WQE info: 0x%x\n", + icowi->opcode); +} + +static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) +{ + struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq); + struct mlx5_cqe64 *cqe; + + if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED))) + return; + + cqe = mlx5_cqwq_get_cqe(&cq->wq); + if (likely(!cqe)) + return; + + /* by design, there's only a single cqe */ + mlx5e_poll_ico_single_cqe(cq, sq, rq, cqe); + + mlx5_cqwq_update_db_record(&cq->wq); +} + +bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) +{ + struct mlx5_wq_ll *wq = &rq->wq; + + if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED))) + return false; + + mlx5e_poll_ico_cq(&rq->channel->icosq.cq, rq); + + if (mlx5_wq_ll_is_full(wq)) + return false; + + if (!rq->mpwqe.umr_in_progress) + mlx5e_alloc_rx_mpwqe(rq, wq->head); + + return true; } static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, u32 cqe_bcnt) { struct ethhdr *eth = (struct ethhdr *)(skb->data); - struct iphdr *ipv4; - struct ipv6hdr *ipv6; struct tcphdr *tcp; int network_depth = 0; __be16 proto; u16 tot_len; + void *ip_p; u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe); - int tcp_ack = ((CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA == l4_hdr_type) || - (CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA == l4_hdr_type)); + u8 tcp_ack = (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA) || + (l4_hdr_type == CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA); skb->mac_len = ETH_HLEN; proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth); - ipv4 = (struct iphdr *)(skb->data + network_depth); - ipv6 = (struct ipv6hdr *)(skb->data + network_depth); tot_len = cqe_bcnt - network_depth; + ip_p = skb->data + network_depth; if (proto == htons(ETH_P_IP)) { - tcp = (struct tcphdr *)(skb->data + network_depth + - sizeof(struct iphdr)); - ipv6 = NULL; - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; - } else { - tcp = (struct tcphdr *)(skb->data + network_depth + - sizeof(struct ipv6hdr)); - ipv4 = NULL; - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - } - - if (get_cqe_lro_tcppsh(cqe)) - tcp->psh = 1; + struct iphdr *ipv4 = ip_p; - if (tcp_ack) { - tcp->ack = 1; - tcp->ack_seq = cqe->lro_ack_seq_num; - tcp->window = cqe->lro_tcp_win; - } + tcp = ip_p + sizeof(struct iphdr); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; - if (ipv4) { ipv4->ttl = cqe->lro_min_ttl; ipv4->tot_len = cpu_to_be16(tot_len); ipv4->check = 0; ipv4->check = ip_fast_csum((unsigned char *)ipv4, ipv4->ihl); } else { + struct ipv6hdr *ipv6 = ip_p; + + tcp = ip_p + sizeof(struct ipv6hdr); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + ipv6->hop_limit = cqe->lro_min_ttl; ipv6->payload_len = cpu_to_be16(tot_len - sizeof(struct ipv6hdr)); } + + tcp->psh = get_cqe_lro_tcppsh(cqe); + + if (tcp_ack) { + tcp->ack = 1; + tcp->ack_seq = cqe->lro_ack_seq_num; + tcp->window = cqe->lro_tcp_win; + } } static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe, @@ -776,9 +822,9 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt) { struct mlx5e_dma_info *di = &wi->di; + u16 rx_headroom = rq->buff.headroom; struct sk_buff *skb; void *va, *data; - u16 rx_headroom = rq->rx_headroom; bool consumed; u32 frag_size; @@ -857,6 +903,7 @@ wq_ll_pop: &wqe->next.next_wqe_index); } +#ifdef CONFIG_MLX5_ESWITCH void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { struct net_device *netdev = rq->netdev; @@ -901,6 +948,7 @@ wq_ll_pop: mlx5_wq_ll_pop(&rq->wq, wqe_counter_be, &wqe->next.next_wqe_index); } +#endif static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, @@ -909,7 +957,7 @@ static inline void mlx5e_mpwqe_fill_rx_skb(struct mlx5e_rq *rq, struct sk_buff *skb) { u16 stride_ix = mpwrq_get_cqe_stride_index(cqe); - u32 wqe_offset = stride_ix * rq->mpwqe_stride_sz; + u32 wqe_offset = stride_ix << rq->mpwqe.log_stride_sz; u32 head_offset = wqe_offset & (PAGE_SIZE - 1); u32 page_idx = wqe_offset >> PAGE_SHIFT; u32 head_page_idx = page_idx; @@ -977,7 +1025,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) napi_gro_receive(rq->cq.napi, skb); mpwrq_cqe_out: - if (likely(wi->consumed_strides < rq->mpwqe_num_strides)) + if (likely(wi->consumed_strides < rq->mpwqe.num_strides)) return; mlx5e_free_rx_mpwqe(rq, wi); @@ -987,21 +1035,23 @@ mpwrq_cqe_out: int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) { struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq); - struct mlx5e_xdpsq *xdpsq = &rq->xdpsq; + struct mlx5e_xdpsq *xdpsq; + struct mlx5_cqe64 *cqe; int work_done = 0; - if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) + if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_ENABLED))) return 0; if (cq->decmprs_left) work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget); - for (; work_done < budget; work_done++) { - struct mlx5_cqe64 *cqe = mlx5_cqwq_get_cqe(&cq->wq); + cqe = mlx5_cqwq_get_cqe(&cq->wq); + if (!cqe) + return 0; - if (!cqe) - break; + xdpsq = &rq->xdpsq; + do { if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) { work_done += mlx5e_decompress_cqes_start(rq, cq, @@ -1012,7 +1062,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) mlx5_cqwq_pop(&cq->wq); rq->handle_rx_cqe(rq, cqe); - } + } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); if (xdpsq->db.doorbell) { mlx5e_xmit_xdp_doorbell(xdpsq); @@ -1030,13 +1080,18 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) { struct mlx5e_xdpsq *sq; + struct mlx5_cqe64 *cqe; struct mlx5e_rq *rq; u16 sqcc; int i; sq = container_of(cq, struct mlx5e_xdpsq, cq); - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) + if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED))) + return false; + + cqe = mlx5_cqwq_get_cqe(&cq->wq); + if (!cqe) return false; rq = container_of(sq, struct mlx5e_rq, xdpsq); @@ -1046,15 +1101,11 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) */ sqcc = sq->cc; - for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) { - struct mlx5_cqe64 *cqe; + i = 0; + do { u16 wqe_counter; bool last_wqe; - cqe = mlx5_cqwq_get_cqe(&cq->wq); - if (!cqe) - break; - mlx5_cqwq_pop(&cq->wq); wqe_counter = be16_to_cpu(cqe->wqe_counter); @@ -1072,7 +1123,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) /* Recycle RX page */ mlx5e_page_release(rq, di, true); } while (!last_wqe); - } + } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); mlx5_cqwq_update_db_record(&cq->wq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index e65517eafc58..6d199ffb1c0b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -47,7 +47,7 @@ struct counter_desc { char format[ETH_GSTRING_LEN]; - int offset; /* Byte offset */ + size_t offset; /* Byte offset */ }; struct mlx5e_sw_stats { @@ -84,6 +84,7 @@ struct mlx5e_sw_stats { u64 rx_cache_full; u64 rx_cache_empty; u64 rx_cache_busy; + u64 rx_cache_waive; /* Special handling counters */ u64 link_down_events_phy; @@ -123,6 +124,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, link_down_events_phy) }, }; @@ -216,6 +218,12 @@ static const struct counter_desc vport_stats_desc[] = { MLX5_GET64(ppcnt_reg, pstats->per_prio_counters[prio], \ counter_set.eth_per_prio_grp_data_layout.c##_high) #define NUM_PPORT_PRIO 8 +#define PPORT_ETH_EXT_OFF(c) \ + MLX5_BYTE_OFF(ppcnt_reg, \ + counter_set.eth_extended_cntrs_grp_data_layout.c##_high) +#define PPORT_ETH_EXT_GET(pstats, c) \ + MLX5_GET64(ppcnt_reg, (pstats)->eth_ext_counters, \ + counter_set.eth_extended_cntrs_grp_data_layout.c##_high) struct mlx5e_pport_stats { __be64 IEEE_802_3_counters[MLX5_ST_SZ_QW(ppcnt_reg)]; @@ -224,6 +232,7 @@ struct mlx5e_pport_stats { __be64 per_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)]; __be64 phy_counters[MLX5_ST_SZ_QW(ppcnt_reg)]; __be64 phy_statistical_counters[MLX5_ST_SZ_QW(ppcnt_reg)]; + __be64 eth_ext_counters[MLX5_ST_SZ_QW(ppcnt_reg)]; }; static const struct counter_desc pport_802_3_stats_desc[] = { @@ -290,12 +299,22 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = { { "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) }, }; +static const struct counter_desc pport_eth_ext_stats_desc[] = { + { "rx_buffer_passed_thres_phy", PPORT_ETH_EXT_OFF(rx_buffer_almost_full) }, +}; + #define PCIE_PERF_OFF(c) \ MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c) #define PCIE_PERF_GET(pcie_stats, c) \ MLX5_GET(mpcnt_reg, (pcie_stats)->pcie_perf_counters, \ counter_set.pcie_perf_cntrs_grp_data_layout.c) +#define PCIE_PERF_OFF64(c) \ + MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c##_high) +#define PCIE_PERF_GET64(pcie_stats, c) \ + MLX5_GET64(mpcnt_reg, (pcie_stats)->pcie_perf_counters, \ + counter_set.pcie_perf_cntrs_grp_data_layout.c##_high) + struct mlx5e_pcie_stats { __be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)]; }; @@ -305,6 +324,17 @@ static const struct counter_desc pcie_perf_stats_desc[] = { { "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) }, }; +static const struct counter_desc pcie_perf_stats_desc64[] = { + { "outbound_pci_buffer_overflow", PCIE_PERF_OFF64(tx_overflow_buffer_pkt) }, +}; + +static const struct counter_desc pcie_perf_stall_stats_desc[] = { + { "outbound_pci_stalled_rd", PCIE_PERF_OFF(outbound_stalled_reads) }, + { "outbound_pci_stalled_wr", PCIE_PERF_OFF(outbound_stalled_writes) }, + { "outbound_pci_stalled_rd_events", PCIE_PERF_OFF(outbound_stalled_reads_events) }, + { "outbound_pci_stalled_wr_events", PCIE_PERF_OFF(outbound_stalled_writes_events) }, +}; + struct mlx5e_rq_stats { u64 packets; u64 bytes; @@ -326,6 +356,7 @@ struct mlx5e_rq_stats { u64 cache_full; u64 cache_empty; u64 cache_busy; + u64 cache_waive; }; static const struct counter_desc rq_stats_desc[] = { @@ -349,6 +380,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_full) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) }, }; struct mlx5e_sq_stats { @@ -397,17 +429,29 @@ static const struct counter_desc sq_stats_desc[] = { #define NUM_PCIE_PERF_COUNTERS(priv) \ (ARRAY_SIZE(pcie_perf_stats_desc) * \ MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_performance_group)) +#define NUM_PCIE_PERF_COUNTERS64(priv) \ + (ARRAY_SIZE(pcie_perf_stats_desc64) * \ + MLX5_CAP_MCAM_FEATURE((priv)->mdev, tx_overflow_buffer_pkt)) +#define NUM_PCIE_PERF_STALL_COUNTERS(priv) \ + (ARRAY_SIZE(pcie_perf_stall_stats_desc) * \ + MLX5_CAP_MCAM_FEATURE((priv)->mdev, pcie_outbound_stalled)) #define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \ ARRAY_SIZE(pport_per_prio_traffic_stats_desc) #define NUM_PPORT_PER_PRIO_PFC_COUNTERS \ ARRAY_SIZE(pport_per_prio_pfc_stats_desc) +#define NUM_PPORT_ETH_EXT_COUNTERS(priv) \ + (ARRAY_SIZE(pport_eth_ext_stats_desc) * \ + MLX5_CAP_PCAM_FEATURE((priv)->mdev, rx_buffer_fullness_counters)) #define NUM_PPORT_COUNTERS(priv) (NUM_PPORT_802_3_COUNTERS + \ NUM_PPORT_2863_COUNTERS + \ NUM_PPORT_2819_COUNTERS + \ NUM_PPORT_PHY_STATISTICAL_COUNTERS(priv) + \ NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \ - NUM_PPORT_PRIO) -#define NUM_PCIE_COUNTERS(priv) NUM_PCIE_PERF_COUNTERS(priv) + NUM_PPORT_PRIO + \ + NUM_PPORT_ETH_EXT_COUNTERS(priv)) +#define NUM_PCIE_COUNTERS(priv) (NUM_PCIE_PERF_COUNTERS(priv) + \ + NUM_PCIE_PERF_COUNTERS64(priv) +\ + NUM_PCIE_PERF_STALL_COUNTERS(priv)) #define NUM_RQ_STATS ARRAY_SIZE(rq_stats_desc) #define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 7f282e8f4e7f..da503e6411da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1326,7 +1326,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, LIST_HEAD(actions); int err; - if (tc_no_actions(exts)) + if (!tcf_exts_has_actions(exts)) return -EINVAL; attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; @@ -1837,7 +1837,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, bool encap = false; int err = 0; - if (tc_no_actions(exts)) + if (!tcf_exts_has_actions(exts)) return -EINVAL; memset(attr, 0, sizeof(*attr)); @@ -1937,7 +1937,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, return err; } -int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, +int mlx5e_configure_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index ecbe30d808ae..c14c263a739b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -33,12 +33,15 @@ #ifndef __MLX5_EN_TC_H__ #define __MLX5_EN_TC_H__ +#include <net/pkt_cls.h> + #define MLX5E_TC_FLOW_ID_MASK 0x0000ffff +#ifdef CONFIG_MLX5_ESWITCH int mlx5e_tc_init(struct mlx5e_priv *priv); void mlx5e_tc_cleanup(struct mlx5e_priv *priv); -int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, +int mlx5e_configure_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f); int mlx5e_delete_flower(struct mlx5e_priv *priv, struct tc_cls_flower_offload *f); @@ -60,4 +63,10 @@ static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) return atomic_read(&priv->fs.tc.ht.nelems); } +#else /* CONFIG_MLX5_ESWITCH */ +static inline int mlx5e_tc_init(struct mlx5e_priv *priv) { return 0; } +static inline void mlx5e_tc_cleanup(struct mlx5e_priv *priv) {} +static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv) { return 0; } +#endif + #endif /* __MLX5_EN_TC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 31353e5c3c78..fee43e40fa16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -394,6 +394,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_txqsq *sq; + struct mlx5_cqe64 *cqe; u32 dma_fifo_cc; u32 nbytes; u16 npkts; @@ -402,7 +403,11 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_txqsq, cq); - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) + if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_ENABLED))) + return false; + + cqe = mlx5_cqwq_get_cqe(&cq->wq); + if (!cqe) return false; npkts = 0; @@ -416,15 +421,11 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) /* avoid dirtying sq cache line every cqe */ dma_fifo_cc = sq->dma_fifo_cc; - for (i = 0; i < MLX5E_TX_CQ_POLL_BUDGET; i++) { - struct mlx5_cqe64 *cqe; + i = 0; + do { u16 wqe_counter; bool last_wqe; - cqe = mlx5_cqwq_get_cqe(&cq->wq); - if (!cqe) - break; - mlx5_cqwq_pop(&cq->wq); wqe_counter = be16_to_cpu(cqe->wqe_counter); @@ -467,7 +468,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sqcc += wi->num_wqebbs; napi_consume_skb(skb, napi_budget); } while (!last_wqe); - } + + } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); mlx5_cqwq_update_db_record(&cq->wq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 92db28a9ed43..e906b754415c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -30,66 +30,18 @@ * SOFTWARE. */ +#include <linux/irq.h> #include "en.h" -static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq, - struct mlx5e_icosq *sq, - struct mlx5_cqe64 *cqe, - u16 *sqcc) +static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) { - struct mlx5_wq_cyc *wq = &sq->wq; - u16 ci = be16_to_cpu(cqe->wqe_counter) & wq->sz_m1; - struct mlx5e_sq_wqe_info *icowi = &sq->db.ico_wqe[ci]; - struct mlx5e_rq *rq = &sq->channel->rq; - - prefetch(rq); - mlx5_cqwq_pop(&cq->wq); - *sqcc += icowi->num_wqebbs; - - if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) { - WARN_ONCE(true, "mlx5e: Bad OP in ICOSQ CQE: 0x%x\n", - cqe->op_own); - return; - } - - if (likely(icowi->opcode == MLX5_OPCODE_UMR)) { - mlx5e_post_rx_mpwqe(rq); - return; - } - - if (unlikely(icowi->opcode != MLX5_OPCODE_NOP)) - WARN_ONCE(true, - "mlx5e: Bad OPCODE in ICOSQ WQE info: 0x%x\n", - icowi->opcode); -} - -static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) -{ - struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq); - struct mlx5_cqe64 *cqe; - u16 sqcc; - - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return; - - cqe = mlx5_cqwq_get_cqe(&cq->wq); - if (likely(!cqe)) - return; + int current_cpu = smp_processor_id(); + const struct cpumask *aff; + struct irq_data *idata; - /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), - * otherwise a cq overrun may occur - */ - sqcc = sq->cc; - - /* by design, there's only a single cqe */ - mlx5e_poll_ico_single_cqe(cq, sq, cqe, &sqcc); - - mlx5_cqwq_update_db_record(&cq->wq); - - /* ensure cq space is freed before enabling more cqes */ - wmb(); - - sq->cc = sqcc; + idata = irq_desc_get_irq_data(c->irq_desc); + aff = irq_data_get_affinity_mask(idata); + return cpumask_test_cpu(current_cpu, aff); } int mlx5e_napi_poll(struct napi_struct *napi, int budget) @@ -100,8 +52,6 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) int work_done; int i; - clear_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags); - for (i = 0; i < c->num_tc; i++) busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget); @@ -111,25 +61,22 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget); busy |= work_done == budget; - mlx5e_poll_ico_cq(&c->icosq.cq); + busy |= c->rq.post_wqes(&c->rq); - busy |= mlx5e_post_rx_wqes(&c->rq); - - if (busy) - return budget; - - napi_complete_done(napi, work_done); + if (busy) { + if (likely(mlx5e_channel_no_affinity_change(c))) + return budget; + if (work_done == budget) + work_done--; + } - /* avoid losing completion event during/after polling cqs */ - if (test_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags)) { - napi_schedule(napi); + if (unlikely(!napi_complete_done(napi, work_done))) return work_done; - } for (i = 0; i < c->num_tc; i++) mlx5e_cq_arm(&c->sq[i].cq); - if (test_bit(MLX5E_RQ_STATE_AM, &c->rq.state)) + if (MLX5E_TEST_BIT(c->rq.state, MLX5E_RQ_STATE_AM)) mlx5e_rx_am(&c->rq); mlx5e_cq_arm(&c->rq.cq); @@ -143,7 +90,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq) struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq); cq->event_ctr++; - set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags); napi_schedule(cq->napi); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index edd11ebd392e..fc606bfd1d6e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -36,9 +36,7 @@ #include <linux/mlx5/cmd.h> #include "mlx5_core.h" #include "fpga/core.h" -#ifdef CONFIG_MLX5_CORE_EN #include "eswitch.h" -#endif enum { MLX5_EQE_SIZE = sizeof(struct mlx5_eqe), @@ -193,6 +191,7 @@ static void eq_update_ci(struct mlx5_eq *eq, int arm) { __be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2); u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24); + __raw_writel((__force u32)cpu_to_be32(val), addr); /* We still want ordering, just not swabbing, so add a barrier */ mb(); @@ -483,11 +482,9 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) } break; -#ifdef CONFIG_MLX5_CORE_EN case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE: mlx5_eswitch_vport_event(dev->priv.eswitch, eqe); break; -#endif case MLX5_EVENT_TYPE_PORT_MODULE_EVENT: mlx5_port_module_event(dev, eqe); @@ -702,9 +699,7 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev) u64 async_event_mask = MLX5_ASYNC_EVENT_MASK; int err; - if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH && - MLX5_CAP_GEN(dev, vport_group_manager) && - mlx5_core_is_pf(dev)) + if (MLX5_VPORT_MANAGER(dev)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE); if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5b41f692acad..c77f4c0c7769 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -46,19 +46,13 @@ enum { MLX5_ACTION_DEL = 2, }; -/* E-Switch UC L2 table hash node */ -struct esw_uc_addr { - struct l2addr_node node; - u32 table_index; - u32 vport; -}; - /* Vport UC/MC hash node */ struct vport_addr { struct l2addr_node node; u8 action; u32 vport; - struct mlx5_flow_handle *flow_rule; /* SRIOV only */ + struct mlx5_flow_handle *flow_rule; + bool mpfs; /* UC MAC was added to MPFs */ /* A flag indicating that mac was added due to mc promiscuous vport */ bool mc_promisc; }; @@ -154,81 +148,6 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, return modify_esw_vport_context_cmd(dev, vport, in, sizeof(in)); } -/* HW L2 Table (MPFS) management */ -static int set_l2_table_entry_cmd(struct mlx5_core_dev *dev, u32 index, - u8 *mac, u8 vlan_valid, u16 vlan) -{ - u32 in[MLX5_ST_SZ_DW(set_l2_table_entry_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(set_l2_table_entry_out)] = {0}; - u8 *in_mac_addr; - - MLX5_SET(set_l2_table_entry_in, in, opcode, - MLX5_CMD_OP_SET_L2_TABLE_ENTRY); - MLX5_SET(set_l2_table_entry_in, in, table_index, index); - MLX5_SET(set_l2_table_entry_in, in, vlan_valid, vlan_valid); - MLX5_SET(set_l2_table_entry_in, in, vlan, vlan); - - in_mac_addr = MLX5_ADDR_OF(set_l2_table_entry_in, in, mac_address); - ether_addr_copy(&in_mac_addr[2], mac); - - return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); -} - -static int del_l2_table_entry_cmd(struct mlx5_core_dev *dev, u32 index) -{ - u32 in[MLX5_ST_SZ_DW(delete_l2_table_entry_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(delete_l2_table_entry_out)] = {0}; - - MLX5_SET(delete_l2_table_entry_in, in, opcode, - MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY); - MLX5_SET(delete_l2_table_entry_in, in, table_index, index); - return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); -} - -static int alloc_l2_table_index(struct mlx5_l2_table *l2_table, u32 *ix) -{ - int err = 0; - - *ix = find_first_zero_bit(l2_table->bitmap, l2_table->size); - if (*ix >= l2_table->size) - err = -ENOSPC; - else - __set_bit(*ix, l2_table->bitmap); - - return err; -} - -static void free_l2_table_index(struct mlx5_l2_table *l2_table, u32 ix) -{ - __clear_bit(ix, l2_table->bitmap); -} - -static int set_l2_table_entry(struct mlx5_core_dev *dev, u8 *mac, - u8 vlan_valid, u16 vlan, - u32 *index) -{ - struct mlx5_l2_table *l2_table = &dev->priv.eswitch->l2_table; - int err; - - err = alloc_l2_table_index(l2_table, index); - if (err) - return err; - - err = set_l2_table_entry_cmd(dev, *index, mac, vlan_valid, vlan); - if (err) - free_l2_table_index(l2_table, *index); - - return err; -} - -static void del_l2_table_entry(struct mlx5_core_dev *dev, u32 index) -{ - struct mlx5_l2_table *l2_table = &dev->priv.eswitch->l2_table; - - del_l2_table_entry_cmd(dev, index); - free_l2_table_index(l2_table, index); -} - /* E-Switch FDB */ static struct mlx5_flow_handle * __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, @@ -455,65 +374,60 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { - struct hlist_head *hash = esw->l2_table.l2_hash; - struct esw_uc_addr *esw_uc; u8 *mac = vaddr->node.addr; u32 vport = vaddr->vport; int err; - esw_uc = l2addr_hash_find(hash, mac, struct esw_uc_addr); - if (esw_uc) { + /* Skip mlx5_mpfs_add_mac for PFs, + * it is already done by the PF netdev in mlx5e_execute_l2_action + */ + if (!vport) + goto fdb_add; + + err = mlx5_mpfs_add_mac(esw->dev, mac); + if (err) { esw_warn(esw->dev, - "Failed to set L2 mac(%pM) for vport(%d), mac is already in use by vport(%d)\n", - mac, vport, esw_uc->vport); - return -EEXIST; + "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n", + mac, vport, err); + return err; } + vaddr->mpfs = true; - esw_uc = l2addr_hash_add(hash, mac, struct esw_uc_addr, GFP_KERNEL); - if (!esw_uc) - return -ENOMEM; - esw_uc->vport = vport; - - err = set_l2_table_entry(esw->dev, mac, 0, 0, &esw_uc->table_index); - if (err) - goto abort; - +fdb_add: /* SRIOV is enabled: Forward UC MAC to vport */ if (esw->fdb_table.fdb && esw->mode == SRIOV_LEGACY) vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport); - esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM index:%d fr(%p)\n", - vport, mac, esw_uc->table_index, vaddr->flow_rule); - return err; -abort: - l2addr_hash_del(esw_uc); - return err; + esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n", + vport, mac, vaddr->flow_rule); + + return 0; } static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { - struct hlist_head *hash = esw->l2_table.l2_hash; - struct esw_uc_addr *esw_uc; u8 *mac = vaddr->node.addr; u32 vport = vaddr->vport; + int err = 0; - esw_uc = l2addr_hash_find(hash, mac, struct esw_uc_addr); - if (!esw_uc || esw_uc->vport != vport) { - esw_debug(esw->dev, - "MAC(%pM) doesn't belong to vport (%d)\n", - mac, vport); - return -EINVAL; - } - esw_debug(esw->dev, "\tDELETE UC MAC: vport[%d] %pM index:%d fr(%p)\n", - vport, mac, esw_uc->table_index, vaddr->flow_rule); + /* Skip mlx5_mpfs_del_mac for PFs, + * it is already done by the PF netdev in mlx5e_execute_l2_action + */ + if (!vport || !vaddr->mpfs) + goto fdb_del; - del_l2_table_entry(esw->dev, esw_uc->table_index); + err = mlx5_mpfs_del_mac(esw->dev, mac); + if (err) + esw_warn(esw->dev, + "Failed to del L2 table mac(%pM) for vport(%d), err(%d)\n", + mac, vport, err); + vaddr->mpfs = false; +fdb_del: if (vaddr->flow_rule) mlx5_del_flow_rules(vaddr->flow_rule); vaddr->flow_rule = NULL; - l2addr_hash_del(esw_uc); return 0; } @@ -1611,13 +1525,14 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) } /* Public E-Switch API */ +#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev)) + int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { int err; int i, enabled_events; - if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) || - MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + if (!ESW_ALLOWED(esw)) return 0; if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) || @@ -1634,7 +1549,6 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode); esw->mode = mode; - esw_disable_vport(esw, 0); if (mode == SRIOV_LEGACY) err = esw_create_legacy_fdb_table(esw, nvfs + 1); @@ -1647,7 +1561,11 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) if (err) esw_warn(esw->dev, "Failed to create eswitch TSAR"); - enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : UC_ADDR_CHANGE; + /* Don't enable vport events when in SRIOV_OFFLOADS mode, since: + * 1. L2 table (MPFS) is programmed by PF/VF representors netdevs set_rx_mode + * 2. FDB/Eswitch is programmed by user space tools + */ + enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0; for (i = 0; i <= nvfs; i++) esw_enable_vport(esw, i, enabled_events); @@ -1656,7 +1574,6 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) return 0; abort: - esw_enable_vport(esw, 0, UC_ADDR_CHANGE); esw->mode = SRIOV_NONE; return err; } @@ -1667,9 +1584,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) int nvports; int i; - if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) || - MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH || - esw->mode == SRIOV_NONE) + if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE) return; esw_info(esw->dev, "disable SRIOV: active vports(%d) mode(%d)\n", @@ -1692,44 +1607,21 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) esw_offloads_cleanup(esw, nvports); esw->mode = SRIOV_NONE; - /* VPORT 0 (PF) must be enabled back with non-sriov configuration */ - esw_enable_vport(esw, 0, UC_ADDR_CHANGE); -} - -void mlx5_eswitch_attach(struct mlx5_eswitch *esw) -{ - if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) || - MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) - return; - - esw_enable_vport(esw, 0, UC_ADDR_CHANGE); - /* VF Vports will be enabled when SRIOV is enabled */ -} - -void mlx5_eswitch_detach(struct mlx5_eswitch *esw) -{ - if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) || - MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) - return; - - esw_disable_vport(esw, 0); } int mlx5_eswitch_init(struct mlx5_core_dev *dev) { - int l2_table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); int total_vports = MLX5_TOTAL_VPORTS(dev); struct mlx5_eswitch *esw; int vport_num; int err; - if (!MLX5_CAP_GEN(dev, vport_group_manager) || - MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + if (!MLX5_VPORT_MANAGER(dev)) return 0; esw_info(dev, - "Total vports %d, l2 table size(%d), per vport: max uc(%d) max mc(%d)\n", - total_vports, l2_table_size, + "Total vports %d, per vport: max uc(%d) max mc(%d)\n", + total_vports, MLX5_MAX_UC_PER_VPORT(dev), MLX5_MAX_MC_PER_VPORT(dev)); @@ -1739,14 +1631,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->dev = dev; - esw->l2_table.bitmap = kcalloc(BITS_TO_LONGS(l2_table_size), - sizeof(uintptr_t), GFP_KERNEL); - if (!esw->l2_table.bitmap) { - err = -ENOMEM; - goto abort; - } - esw->l2_table.size = l2_table_size; - esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq"); if (!esw->work_queue) { err = -ENOMEM; @@ -1797,7 +1681,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) abort: if (esw->work_queue) destroy_workqueue(esw->work_queue); - kfree(esw->l2_table.bitmap); kfree(esw->vports); kfree(esw->offloads.vport_reps); kfree(esw); @@ -1806,15 +1689,13 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager) || - MLX5_CAP_GEN(esw->dev, port_type) != MLX5_CAP_PORT_TYPE_ETH) + if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); - kfree(esw->l2_table.bitmap); kfree(esw->offloads.vport_reps); kfree(esw->vports); kfree(esw); @@ -1838,8 +1719,6 @@ void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe) } /* Vport Administration */ -#define ESW_ALLOWED(esw) \ - (esw && MLX5_CAP_GEN(esw->dev, vport_group_manager) && mlx5_core_is_pf(esw->dev)) #define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports) int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 834a33050969..565c8b7a399a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -37,6 +37,15 @@ #include <linux/if_link.h> #include <net/devlink.h> #include <linux/mlx5/device.h> +#include "lib/mpfs.h" + +enum { + SRIOV_NONE, + SRIOV_LEGACY, + SRIOV_OFFLOADS +}; + +#ifdef CONFIG_MLX5_ESWITCH #define MLX5_MAX_UC_PER_VPORT(dev) \ (1 << MLX5_CAP_GEN(dev, log_max_current_uc_list)) @@ -44,9 +53,6 @@ #define MLX5_MAX_MC_PER_VPORT(dev) \ (1 << MLX5_CAP_GEN(dev, log_max_current_mc_list)) -#define MLX5_L2_ADDR_HASH_SIZE (BIT(BITS_PER_BYTE)) -#define MLX5_L2_ADDR_HASH(addr) (addr[5]) - #define FDB_UPLINK_VPORT 0xffff #define MLX5_MIN_BW_SHARE 1 @@ -54,48 +60,6 @@ #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ min_t(u32, max_t(u32, (rate) / (divider), MLX5_MIN_BW_SHARE), limit) -/* L2 -mac address based- hash helpers */ -struct l2addr_node { - struct hlist_node hlist; - u8 addr[ETH_ALEN]; -}; - -#define for_each_l2hash_node(hn, tmp, hash, i) \ - for (i = 0; i < MLX5_L2_ADDR_HASH_SIZE; i++) \ - hlist_for_each_entry_safe(hn, tmp, &hash[i], hlist) - -#define l2addr_hash_find(hash, mac, type) ({ \ - int ix = MLX5_L2_ADDR_HASH(mac); \ - bool found = false; \ - type *ptr = NULL; \ - \ - hlist_for_each_entry(ptr, &hash[ix], node.hlist) \ - if (ether_addr_equal(ptr->node.addr, mac)) {\ - found = true; \ - break; \ - } \ - if (!found) \ - ptr = NULL; \ - ptr; \ -}) - -#define l2addr_hash_add(hash, mac, type, gfp) ({ \ - int ix = MLX5_L2_ADDR_HASH(mac); \ - type *ptr = NULL; \ - \ - ptr = kzalloc(sizeof(type), gfp); \ - if (ptr) { \ - ether_addr_copy(ptr->node.addr, mac); \ - hlist_add_head(&ptr->node.hlist, &hash[ix]);\ - } \ - ptr; \ -}) - -#define l2addr_hash_del(ptr) ({ \ - hlist_del(&ptr->node.hlist); \ - kfree(ptr); \ -}) - struct vport_ingress { struct mlx5_flow_table *acl; struct mlx5_flow_group *allow_untagged_spoofchk_grp; @@ -150,12 +114,6 @@ struct mlx5_vport { u16 enabled_events; }; -struct mlx5_l2_table { - struct hlist_head l2_hash[MLX5_L2_ADDR_HASH_SIZE]; - u32 size; - unsigned long *bitmap; -}; - struct mlx5_eswitch_fdb { void *fdb; union { @@ -175,12 +133,6 @@ struct mlx5_eswitch_fdb { }; }; -enum { - SRIOV_NONE, - SRIOV_LEGACY, - SRIOV_OFFLOADS -}; - struct mlx5_esw_sq { struct mlx5_flow_handle *send_to_vport_rule; struct list_head list; @@ -222,7 +174,6 @@ struct esw_mc_addr { /* SRIOV only */ struct mlx5_eswitch { struct mlx5_core_dev *dev; - struct mlx5_l2_table l2_table; struct mlx5_eswitch_fdb fdb_table; struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE]; struct workqueue_struct *work_queue; @@ -250,8 +201,6 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports); /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw); -void mlx5_eswitch_attach(struct mlx5_eswitch *esw); -void mlx5_eswitch_detach(struct mlx5_eswitch *esw); void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe); int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode); void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw); @@ -345,4 +294,13 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, #define esw_debug(dev, format, ...) \ mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__) +#else /* CONFIG_MLX5_ESWITCH */ +/* eswitch API stubs */ +static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {} +static inline void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe) {} +static inline int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; } +static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {} +#endif /* CONFIG_MLX5_ESWITCH */ + #endif /* __MLX5_ESWITCH_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 5bc0593bd76e..d9fd8570b07c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -433,6 +433,8 @@ static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw) struct mlx5_flow_table *fdb = NULL; int esw_size, err = 0; u32 flags = 0; + u32 max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) | + MLX5_CAP_GEN(dev, max_flow_counter_15_0); root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); if (!root_ns) { @@ -443,9 +445,9 @@ static int esw_create_offloads_fast_fdb_table(struct mlx5_eswitch *esw) esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d)*groups(%d))\n", MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size), - MLX5_CAP_GEN(dev, max_flow_counter), ESW_OFFLOADS_NUM_GROUPS); + max_flow_counter, ESW_OFFLOADS_NUM_GROUPS); - esw_size = min_t(int, MLX5_CAP_GEN(dev, max_flow_counter) * ESW_OFFLOADS_NUM_GROUPS, + esw_size = min_t(int, max_flow_counter * ESW_OFFLOADS_NUM_GROUPS, 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index e750f07793b8..e0d0efd903bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -263,7 +263,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(flow_context, in_flow_context, modify_header_id, fte->modify_id); in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context, match_value); - memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param)); + memcpy(in_match_value, &fte->val, sizeof(fte->val)); in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); if (fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { @@ -359,7 +359,7 @@ int mlx5_cmd_delete_fte(struct mlx5_core_dev *dev, return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u16 *id) +int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) { u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)] = {0}; u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0}; @@ -374,7 +374,7 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u16 *id) return err; } -int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u16 id) +int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id) { u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)] = {0}; u32 out[MLX5_ST_SZ_DW(dealloc_flow_counter_out)] = {0}; @@ -385,7 +385,7 @@ int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u16 id) return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u16 id, +int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes) { u32 out[MLX5_ST_SZ_BYTES(query_flow_counter_out) + @@ -409,14 +409,14 @@ int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u16 id, } struct mlx5_cmd_fc_bulk { - u16 id; + u32 id; int num; int outlen; u32 out[0]; }; struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u16 id, int num) +mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num) { struct mlx5_cmd_fc_bulk *b; int outlen = @@ -453,7 +453,7 @@ mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b) } void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u16 id, + struct mlx5_cmd_fc_bulk *b, u32 id, u64 *packets, u64 *bytes) { int index = id - b->id; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 0f98a7cf4877..c6d7bdf255b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -74,20 +74,20 @@ int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft, u32 underlay_qpn); -int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u16 *id); -int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u16 id); -int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u16 id, +int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); +int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); +int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes); struct mlx5_cmd_fc_bulk; struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u16 id, int num); +mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num); void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b); int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b); void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u16 id, + struct mlx5_cmd_fc_bulk *b, u32 id, u64 *packets, u64 *bytes); #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index e8690fe46bf2..5a7bea688ec8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -36,6 +36,7 @@ #include "mlx5_core.h" #include "fs_core.h" #include "fs_cmd.h" +#include "diag/fs_tracepoint.h" #define INIT_TREE_NODE_ARRAY_SIZE(...) (sizeof((struct init_tree_node[]){__VA_ARGS__}) /\ sizeof(struct init_tree_node)) @@ -82,8 +83,8 @@ #define ETHTOOL_PRIO_NUM_LEVELS 1 #define ETHTOOL_NUM_PRIOS 11 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS) -/* Vlan, mac, ttc, aRFS */ -#define KERNEL_NIC_PRIO_NUM_LEVELS 4 +/* Vlan, mac, ttc, inner ttc, aRFS */ +#define KERNEL_NIC_PRIO_NUM_LEVELS 5 #define KERNEL_NIC_NUM_PRIOS 1 /* One more level for tc */ #define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1) @@ -150,6 +151,23 @@ enum fs_i_mutex_lock_class { FS_MUTEX_CHILD }; +static const struct rhashtable_params rhash_fte = { + .key_len = FIELD_SIZEOF(struct fs_fte, val), + .key_offset = offsetof(struct fs_fte, val), + .head_offset = offsetof(struct fs_fte, hash), + .automatic_shrinking = true, + .min_size = 1, +}; + +static const struct rhashtable_params rhash_fg = { + .key_len = FIELD_SIZEOF(struct mlx5_flow_group, mask), + .key_offset = offsetof(struct mlx5_flow_group, mask), + .head_offset = offsetof(struct mlx5_flow_group, hash), + .automatic_shrinking = true, + .min_size = 1, + +}; + static void del_rule(struct fs_node *node); static void del_flow_table(struct fs_node *node); static void del_flow_group(struct fs_node *node); @@ -255,71 +273,77 @@ static struct fs_prio *find_prio(struct mlx5_flow_namespace *ns, return NULL; } -static bool masked_memcmp(void *mask, void *val1, void *val2, size_t size) +static bool check_last_reserved(const u32 *match_criteria) { - unsigned int i; + char *match_criteria_reserved = + MLX5_ADDR_OF(fte_match_param, match_criteria, MLX5_FTE_MATCH_PARAM_RESERVED); - for (i = 0; i < size; i++, mask++, val1++, val2++) - if ((*((u8 *)val1) & (*(u8 *)mask)) != - ((*(u8 *)val2) & (*(u8 *)mask))) - return false; - - return true; + return !match_criteria_reserved[0] && + !memcmp(match_criteria_reserved, match_criteria_reserved + 1, + MLX5_FLD_SZ_BYTES(fte_match_param, + MLX5_FTE_MATCH_PARAM_RESERVED) - 1); } -static bool compare_match_value(struct mlx5_flow_group_mask *mask, - void *fte_param1, void *fte_param2) +static bool check_valid_mask(u8 match_criteria_enable, const u32 *match_criteria) { - if (mask->match_criteria_enable & - 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS) { - void *fte_match1 = MLX5_ADDR_OF(fte_match_param, - fte_param1, outer_headers); - void *fte_match2 = MLX5_ADDR_OF(fte_match_param, - fte_param2, outer_headers); - void *fte_mask = MLX5_ADDR_OF(fte_match_param, - mask->match_criteria, outer_headers); + if (match_criteria_enable & ~( + (1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS) | + (1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS) | + (1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS))) + return false; - if (!masked_memcmp(fte_mask, fte_match1, fte_match2, - MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4))) + if (!(match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS)) { + char *fg_type_mask = MLX5_ADDR_OF(fte_match_param, + match_criteria, outer_headers); + + if (fg_type_mask[0] || + memcmp(fg_type_mask, fg_type_mask + 1, + MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4) - 1)) return false; } - if (mask->match_criteria_enable & - 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS) { - void *fte_match1 = MLX5_ADDR_OF(fte_match_param, - fte_param1, misc_parameters); - void *fte_match2 = MLX5_ADDR_OF(fte_match_param, - fte_param2, misc_parameters); - void *fte_mask = MLX5_ADDR_OF(fte_match_param, - mask->match_criteria, misc_parameters); + if (!(match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS)) { + char *fg_type_mask = MLX5_ADDR_OF(fte_match_param, + match_criteria, misc_parameters); - if (!masked_memcmp(fte_mask, fte_match1, fte_match2, - MLX5_ST_SZ_BYTES(fte_match_set_misc))) + if (fg_type_mask[0] || + memcmp(fg_type_mask, fg_type_mask + 1, + MLX5_ST_SZ_BYTES(fte_match_set_misc) - 1)) return false; } - if (mask->match_criteria_enable & - 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS) { - void *fte_match1 = MLX5_ADDR_OF(fte_match_param, - fte_param1, inner_headers); - void *fte_match2 = MLX5_ADDR_OF(fte_match_param, - fte_param2, inner_headers); - void *fte_mask = MLX5_ADDR_OF(fte_match_param, - mask->match_criteria, inner_headers); + if (!(match_criteria_enable & + 1 << MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_INNER_HEADERS)) { + char *fg_type_mask = MLX5_ADDR_OF(fte_match_param, + match_criteria, inner_headers); - if (!masked_memcmp(fte_mask, fte_match1, fte_match2, - MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4))) + if (fg_type_mask[0] || + memcmp(fg_type_mask, fg_type_mask + 1, + MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4) - 1)) return false; } - return true; + + return check_last_reserved(match_criteria); } -static bool compare_match_criteria(u8 match_criteria_enable1, - u8 match_criteria_enable2, - void *mask1, void *mask2) +static bool check_valid_spec(const struct mlx5_flow_spec *spec) { - return match_criteria_enable1 == match_criteria_enable2 && - !memcmp(mask1, mask2, MLX5_ST_SZ_BYTES(fte_match_param)); + int i; + + if (!check_valid_mask(spec->match_criteria_enable, spec->match_criteria)) { + pr_warn("mlx5_core: Match criteria given mismatches match_criteria_enable\n"); + return false; + } + + for (i = 0; i < MLX5_ST_SZ_DW_MATCH_PARAM; i++) + if (spec->match_value[i] & ~spec->match_criteria[i]) { + pr_warn("mlx5_core: match_value differs from match_criteria\n"); + return false; + } + + return check_last_reserved(spec->match_value); } static struct mlx5_flow_root_namespace *find_root(struct fs_node *node) @@ -360,6 +384,8 @@ static void del_flow_table(struct fs_node *node) err = mlx5_cmd_destroy_flow_table(dev, ft); if (err) mlx5_core_warn(dev, "flow steering can't destroy ft\n"); + ida_destroy(&ft->fte_allocator); + rhltable_destroy(&ft->fgs_hash); fs_get_obj(prio, ft->node.parent); prio->num_ft--; } @@ -370,22 +396,16 @@ static void del_rule(struct fs_node *node) struct mlx5_flow_table *ft; struct mlx5_flow_group *fg; struct fs_fte *fte; - u32 *match_value; int modify_mask; struct mlx5_core_dev *dev = get_dev(node); - int match_len = MLX5_ST_SZ_BYTES(fte_match_param); int err; bool update_fte = false; - match_value = kvzalloc(match_len, GFP_KERNEL); - if (!match_value) - return; - fs_get_obj(rule, node); fs_get_obj(fte, rule->node.parent); fs_get_obj(fg, fte->node.parent); - memcpy(match_value, fte->val, sizeof(fte->val)); fs_get_obj(ft, fg->node.parent); + trace_mlx5_fs_del_rule(rule); list_del(&rule->node.list); if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { mutex_lock(&rule->dest_attr.ft->lock); @@ -414,7 +434,18 @@ out: "%s can't del rule fg id=%d fte_index=%d\n", __func__, fg->id, fte->index); } - kvfree(match_value); +} + +static void destroy_fte(struct fs_fte *fte, struct mlx5_flow_group *fg) +{ + struct mlx5_flow_table *ft; + int ret; + + ret = rhashtable_remove_fast(&fg->ftes_hash, &fte->hash, rhash_fte); + WARN_ON(ret); + fte->status = 0; + fs_get_obj(ft, fg->node.parent); + ida_simple_remove(&ft->fte_allocator, fte->index); } static void del_fte(struct fs_node *node) @@ -428,6 +459,7 @@ static void del_fte(struct fs_node *node) fs_get_obj(fte, node); fs_get_obj(fg, fte->node.parent); fs_get_obj(ft, fg->node.parent); + trace_mlx5_fs_del_fte(fte); dev = get_dev(&ft->node); err = mlx5_cmd_delete_fte(dev, ft, @@ -437,8 +469,7 @@ static void del_fte(struct fs_node *node) "flow steering can't delete fte in index %d of flow group id %d\n", fte->index, fg->id); - fte->status = 0; - fg->num_ftes--; + destroy_fte(fte, fg); } static void del_flow_group(struct fs_node *node) @@ -446,14 +477,21 @@ static void del_flow_group(struct fs_node *node) struct mlx5_flow_group *fg; struct mlx5_flow_table *ft; struct mlx5_core_dev *dev; + int err; fs_get_obj(fg, node); fs_get_obj(ft, fg->node.parent); dev = get_dev(&ft->node); + trace_mlx5_fs_del_fg(fg); if (ft->autogroup.active) ft->autogroup.num_groups--; + rhashtable_destroy(&fg->ftes_hash); + err = rhltable_remove(&ft->fgs_hash, + &fg->hash, + rhash_fg); + WARN_ON(err); if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", fg->id, ft->id); @@ -488,10 +526,17 @@ static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) u8 match_criteria_enable = MLX5_GET(create_flow_group_in, create_fg_in, match_criteria_enable); + int ret; + fg = kzalloc(sizeof(*fg), GFP_KERNEL); if (!fg) return ERR_PTR(-ENOMEM); + ret = rhashtable_init(&fg->ftes_hash, &rhash_fte); + if (ret) { + kfree(fg); + return ERR_PTR(ret); + } fg->mask.match_criteria_enable = match_criteria_enable; memcpy(&fg->mask.match_criteria, match_criteria, sizeof(fg->mask.match_criteria)); @@ -509,10 +554,17 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft u32 flags) { struct mlx5_flow_table *ft; + int ret; ft = kzalloc(sizeof(*ft), GFP_KERNEL); if (!ft) - return NULL; + return ERR_PTR(-ENOMEM); + + ret = rhltable_init(&ft->fgs_hash, &rhash_fg); + if (ret) { + kfree(ft); + return ERR_PTR(ret); + } ft->level = level; ft->node.type = FS_TYPE_FLOW_TABLE; @@ -523,6 +575,7 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft ft->flags = flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); + ida_init(&ft->fte_allocator); return ft; } @@ -812,8 +865,8 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa ft_attr->max_fte ? roundup_pow_of_two(ft_attr->max_fte) : 0, root->table_type, op_mod, ft_attr->flags); - if (!ft) { - err = -ENOMEM; + if (IS_ERR(ft)) { + err = PTR_ERR(ft); goto unlock_root; } @@ -839,6 +892,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa destroy_ft: mlx5_cmd_destroy_flow_table(root->dev, ft); free_ft: + ida_destroy(&ft->fte_allocator); kfree(ft); unlock_root: mutex_unlock(&root->chain_lock); @@ -924,11 +978,13 @@ static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table * if (IS_ERR(fg)) return fg; + err = rhltable_insert(&ft->fgs_hash, &fg->hash, rhash_fg); + if (err) + goto err_free_fg; + err = mlx5_cmd_create_flow_group(dev, ft, fg_in, &fg->id); - if (err) { - kfree(fg); - return ERR_PTR(err); - } + if (err) + goto err_remove_fg; if (ft->autogroup.active) ft->autogroup.num_groups++; @@ -938,14 +994,33 @@ static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table * /* Add node to group list */ list_add(&fg->node.list, prev_fg); + trace_mlx5_fs_add_fg(fg); return fg; + +err_remove_fg: + WARN_ON(rhltable_remove(&ft->fgs_hash, + &fg->hash, + rhash_fg)); +err_free_fg: + rhashtable_destroy(&fg->ftes_hash); + kfree(fg); + + return ERR_PTR(err); } struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *fg_in) { + void *match_criteria = MLX5_ADDR_OF(create_flow_group_in, + fg_in, match_criteria); + u8 match_criteria_enable = MLX5_GET(create_flow_group_in, + fg_in, + match_criteria_enable); struct mlx5_flow_group *fg; + if (!check_valid_mask(match_criteria_enable, match_criteria)) + return ERR_PTR(-EINVAL); + if (ft->autogroup.active) return ERR_PTR(-EPERM); @@ -1102,43 +1177,38 @@ free_handle: return ERR_PTR(err); } -/* Assumed fg is locked */ -static unsigned int get_free_fte_index(struct mlx5_flow_group *fg, - struct list_head **prev) -{ - struct fs_fte *fte; - unsigned int start = fg->start_index; - - if (prev) - *prev = &fg->node.children; - - /* assumed list is sorted by index */ - fs_for_each_fte(fte, fg) { - if (fte->index != start) - return start; - start++; - if (prev) - *prev = &fte->node.list; - } - - return start; -} - -/* prev is output, prev->next = new_fte */ static struct fs_fte *create_fte(struct mlx5_flow_group *fg, u32 *match_value, - struct mlx5_flow_act *flow_act, - struct list_head **prev) + struct mlx5_flow_act *flow_act) { + struct mlx5_flow_table *ft; struct fs_fte *fte; int index; + int ret; + + fs_get_obj(ft, fg->node.parent); + index = ida_simple_get(&ft->fte_allocator, fg->start_index, + fg->start_index + fg->max_ftes, + GFP_KERNEL); + if (index < 0) + return ERR_PTR(index); - index = get_free_fte_index(fg, prev); fte = alloc_fte(flow_act, match_value, index); - if (IS_ERR(fte)) - return fte; + if (IS_ERR(fte)) { + ret = PTR_ERR(fte); + goto err_alloc; + } + ret = rhashtable_insert_fast(&fg->ftes_hash, &fte->hash, rhash_fte); + if (ret) + goto err_hash; return fte; + +err_hash: + kfree(fte); +err_alloc: + ida_simple_remove(&ft->fte_allocator, index); + return ERR_PTR(ret); } static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, @@ -1226,79 +1296,104 @@ static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte, return NULL; } +static bool check_conflicting_actions(u32 action1, u32 action2) +{ + u32 xored_actions = action1 ^ action2; + + /* if one rule only wants to count, it's ok */ + if (action1 == MLX5_FLOW_CONTEXT_ACTION_COUNT || + action2 == MLX5_FLOW_CONTEXT_ACTION_COUNT) + return false; + + if (xored_actions & (MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_ENCAP | + MLX5_FLOW_CONTEXT_ACTION_DECAP)) + return true; + + return false; +} + +static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act *flow_act) +{ + if (check_conflicting_actions(flow_act->action, fte->action)) { + mlx5_core_warn(get_dev(&fte->node), + "Found two FTEs with conflicting actions\n"); + return -EEXIST; + } + + if (fte->flow_tag != flow_act->flow_tag) { + mlx5_core_warn(get_dev(&fte->node), + "FTE flow tag %u already exists with different flow tag %u\n", + fte->flow_tag, + flow_act->flow_tag); + return -EEXIST; + } + + return 0; +} + static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, u32 *match_value, struct mlx5_flow_act *flow_act, struct mlx5_flow_destination *dest, - int dest_num) + int dest_num, + struct fs_fte *fte) { struct mlx5_flow_handle *handle; struct mlx5_flow_table *ft; - struct list_head *prev; - struct fs_fte *fte; int i; - nested_lock_ref_node(&fg->node, FS_MUTEX_PARENT); - fs_for_each_fte(fte, fg) { + if (fte) { + int old_action; + int ret; + nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); - if (compare_match_value(&fg->mask, match_value, &fte->val) && - (flow_act->action & fte->action)) { - int old_action = fte->action; - - if (fte->flow_tag != flow_act->flow_tag) { - mlx5_core_warn(get_dev(&fte->node), - "FTE flow tag %u already exists with different flow tag %u\n", - fte->flow_tag, - flow_act->flow_tag); - handle = ERR_PTR(-EEXIST); - goto unlock_fte; - } + ret = check_conflicting_ftes(fte, flow_act); + if (ret) { + handle = ERR_PTR(ret); + goto unlock_fte; + } - fte->action |= flow_act->action; - handle = add_rule_fte(fte, fg, dest, dest_num, - old_action != flow_act->action); - if (IS_ERR(handle)) { - fte->action = old_action; - goto unlock_fte; - } else { - goto add_rules; - } + old_action = fte->action; + fte->action |= flow_act->action; + handle = add_rule_fte(fte, fg, dest, dest_num, + old_action != flow_act->action); + if (IS_ERR(handle)) { + fte->action = old_action; + goto unlock_fte; + } else { + trace_mlx5_fs_set_fte(fte, false); + goto add_rules; } - unlock_ref_node(&fte->node); } fs_get_obj(ft, fg->node.parent); - if (fg->num_ftes >= fg->max_ftes) { - handle = ERR_PTR(-ENOSPC); - goto unlock_fg; - } - fte = create_fte(fg, match_value, flow_act, &prev); - if (IS_ERR(fte)) { - handle = (void *)fte; - goto unlock_fg; - } + fte = create_fte(fg, match_value, flow_act); + if (IS_ERR(fte)) + return (void *)fte; tree_init_node(&fte->node, 0, del_fte); nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); handle = add_rule_fte(fte, fg, dest, dest_num, false); if (IS_ERR(handle)) { unlock_ref_node(&fte->node); + destroy_fte(fte, fg); kfree(fte); - goto unlock_fg; + return handle; } - fg->num_ftes++; - tree_add_node(&fte->node, &fg->node); - list_add(&fte->node.list, prev); + /* fte list isn't sorted */ + list_add_tail(&fte->node.list, &fg->node.children); + trace_mlx5_fs_set_fte(fte, true); add_rules: for (i = 0; i < handle->num_rules; i++) { - if (atomic_read(&handle->rule[i]->node.refcount) == 1) + if (atomic_read(&handle->rule[i]->node.refcount) == 1) { tree_add_node(&handle->rule[i]->node, &fte->node); + trace_mlx5_fs_add_rule(handle->rule[i]); + } } unlock_fte: unlock_ref_node(&fte->node); -unlock_fg: - unlock_ref_node(&fg->node); return handle; } @@ -1347,6 +1442,96 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest, } static struct mlx5_flow_handle * +try_add_to_existing_fg(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec, + struct mlx5_flow_act *flow_act, + struct mlx5_flow_destination *dest, + int dest_num) +{ + struct mlx5_flow_group *g; + struct mlx5_flow_handle *rule = ERR_PTR(-ENOENT); + struct rhlist_head *tmp, *list; + struct match_list { + struct list_head list; + struct mlx5_flow_group *g; + } match_list, *iter; + LIST_HEAD(match_head); + + rcu_read_lock(); + /* Collect all fgs which has a matching match_criteria */ + list = rhltable_lookup(&ft->fgs_hash, spec, rhash_fg); + rhl_for_each_entry_rcu(g, tmp, list, hash) { + struct match_list *curr_match; + + if (likely(list_empty(&match_head))) { + match_list.g = g; + list_add_tail(&match_list.list, &match_head); + continue; + } + curr_match = kmalloc(sizeof(*curr_match), GFP_ATOMIC); + + if (!curr_match) { + rcu_read_unlock(); + rule = ERR_PTR(-ENOMEM); + goto free_list; + } + curr_match->g = g; + list_add_tail(&curr_match->list, &match_head); + } + rcu_read_unlock(); + + /* Try to find a fg that already contains a matching fte */ + list_for_each_entry(iter, &match_head, list) { + struct fs_fte *fte; + + g = iter->g; + nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); + fte = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, + rhash_fte); + if (fte) { + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, fte); + unlock_ref_node(&g->node); + goto free_list; + } + unlock_ref_node(&g->node); + } + + /* No group with matching fte found. Try to add a new fte to any + * matching fg. + */ + list_for_each_entry(iter, &match_head, list) { + g = iter->g; + + nested_lock_ref_node(&g->node, FS_MUTEX_PARENT); + rule = add_rule_fg(g, spec->match_value, + flow_act, dest, dest_num, NULL); + if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) { + unlock_ref_node(&g->node); + goto free_list; + } + unlock_ref_node(&g->node); + } + +free_list: + if (!list_empty(&match_head)) { + struct match_list *match_tmp; + + /* The most common case is having one FG. Since we want to + * optimize this case, we save the first on the stack. + * Therefore, no need to free it. + */ + list_del(&list_first_entry(&match_head, typeof(*iter), list)->list); + list_for_each_entry_safe(iter, match_tmp, &match_head, list) { + list_del(&iter->list); + kfree(iter); + } + } + + return rule; +} + +static struct mlx5_flow_handle * _mlx5_add_flow_rules(struct mlx5_flow_table *ft, struct mlx5_flow_spec *spec, struct mlx5_flow_act *flow_act, @@ -1358,22 +1543,18 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, struct mlx5_flow_handle *rule; int i; + if (!check_valid_spec(spec)) + return ERR_PTR(-EINVAL); + for (i = 0; i < dest_num; i++) { if (!dest_is_valid(&dest[i], flow_act->action, ft)) return ERR_PTR(-EINVAL); } nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); - fs_for_each_fg(g, ft) - if (compare_match_criteria(g->mask.match_criteria_enable, - spec->match_criteria_enable, - g->mask.match_criteria, - spec->match_criteria)) { - rule = add_rule_fg(g, spec->match_value, - flow_act, dest, dest_num); - if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) - goto unlock; - } + rule = try_add_to_existing_fg(ft, spec, flow_act, dest, dest_num); + if (!IS_ERR(rule)) + goto unlock; g = create_autogroup(ft, spec->match_criteria_enable, spec->match_criteria); @@ -1382,7 +1563,8 @@ _mlx5_add_flow_rules(struct mlx5_flow_table *ft, goto unlock; } - rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num); + rule = add_rule_fg(g, spec->match_value, flow_act, dest, + dest_num, NULL); if (IS_ERR(rule)) { /* Remove assumes refcount > 0 and autogroup creates a group * with a refcount = 0. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 990acee6fb09..5509a752f98e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -34,6 +34,7 @@ #define _MLX5_FS_CORE_ #include <linux/mlx5/fs.h> +#include <linux/rhashtable.h> enum fs_node_type { FS_TYPE_NAMESPACE, @@ -118,6 +119,8 @@ struct mlx5_flow_table { /* FWD rules that point on this flow table */ struct list_head fwd_rules; u32 flags; + struct ida fte_allocator; + struct rhltable fgs_hash; }; struct mlx5_fc_cache { @@ -136,17 +139,29 @@ struct mlx5_fc { u64 lastpackets; u64 lastbytes; - u16 id; + u32 id; bool deleted; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_600 +/* Calculate the fte_match_param length and without the reserved length. + * Make sure the reserved field is the last. + */ +#define MLX5_ST_SZ_DW_MATCH_PARAM \ + ((MLX5_BYTE_OFF(fte_match_param, MLX5_FTE_MATCH_PARAM_RESERVED) / sizeof(u32)) + \ + BUILD_BUG_ON_ZERO(MLX5_ST_SZ_BYTES(fte_match_param) != \ + MLX5_FLD_SZ_BYTES(fte_match_param, \ + MLX5_FTE_MATCH_PARAM_RESERVED) +\ + MLX5_BYTE_OFF(fte_match_param, \ + MLX5_FTE_MATCH_PARAM_RESERVED))) + /* Type of children is mlx5_flow_rule */ struct fs_fte { struct fs_node node; - u32 val[MLX5_ST_SZ_DW(fte_match_param)]; + u32 val[MLX5_ST_SZ_DW_MATCH_PARAM]; u32 dests_size; u32 flow_tag; u32 index; @@ -155,6 +170,7 @@ struct fs_fte { u32 modify_id; enum fs_fte_status status; struct mlx5_fc *counter; + struct rhash_head hash; }; /* Type of children is mlx5_flow_table/namespace */ @@ -174,7 +190,7 @@ struct mlx5_flow_namespace { struct mlx5_flow_group_mask { u8 match_criteria_enable; - u32 match_criteria[MLX5_ST_SZ_DW(fte_match_param)]; + u32 match_criteria[MLX5_ST_SZ_DW_MATCH_PARAM]; }; /* Type of children is fs_fte */ @@ -183,8 +199,9 @@ struct mlx5_flow_group { struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; - u32 num_ftes; u32 id; + struct rhashtable ftes_hash; + struct rhlist_head hash; }; struct mlx5_flow_root_namespace { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 6507d8acc54d..89d1f8650033 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -38,6 +38,8 @@ #include "fs_cmd.h" #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) +/* Max number of counters to query in bulk read is 32K */ +#define MLX5_SW_MAX_COUNTERS_BULK BIT(15) /* locking scheme: * @@ -90,16 +92,21 @@ static void mlx5_fc_stats_insert(struct rb_root *root, struct mlx5_fc *counter) rb_insert_color(&counter->node, root); } +/* The function returns the last node that was queried so the caller + * function can continue calling it till all counters are queried. + */ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, struct mlx5_fc *first, - u16 last_id) + u32 last_id) { struct mlx5_cmd_fc_bulk *b; struct rb_node *node = NULL; - u16 afirst_id; + u32 afirst_id; int num; int err; - int max_bulk = 1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk); + + int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); /* first id must be aligned to 4 when using bulk query */ afirst_id = first->id & ~0x3; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index eb04e97d8765..43c126c63955 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -39,10 +39,11 @@ static void mlx5i_get_drvinfo(struct net_device *dev, struct mlx5e_priv *priv = mlx5i_epriv(dev); mlx5e_ethtool_get_drvinfo(priv, drvinfo); + strlcpy(drvinfo->driver, DRIVER_NAME "[ib_ipoib]", + sizeof(drvinfo->driver)); } -static void mlx5i_get_strings(struct net_device *dev, - uint32_t stringset, uint8_t *data) +static void mlx5i_get_strings(struct net_device *dev, u32 stringset, u8 *data) { struct mlx5e_priv *priv = mlx5i_epriv(dev); @@ -129,17 +130,123 @@ static int mlx5i_flash_device(struct net_device *netdev, return mlx5e_ethtool_flash_device(priv, flash); } +enum mlx5_ptys_width { + MLX5_PTYS_WIDTH_1X = 1 << 0, + MLX5_PTYS_WIDTH_2X = 1 << 1, + MLX5_PTYS_WIDTH_4X = 1 << 2, + MLX5_PTYS_WIDTH_8X = 1 << 3, + MLX5_PTYS_WIDTH_12X = 1 << 4, +}; + +static inline int mlx5_ptys_width_enum_to_int(enum mlx5_ptys_width width) +{ + switch (width) { + case MLX5_PTYS_WIDTH_1X: return 1; + case MLX5_PTYS_WIDTH_2X: return 2; + case MLX5_PTYS_WIDTH_4X: return 4; + case MLX5_PTYS_WIDTH_8X: return 8; + case MLX5_PTYS_WIDTH_12X: return 12; + default: return -1; + } +} + +enum mlx5_ptys_rate { + MLX5_PTYS_RATE_SDR = 1 << 0, + MLX5_PTYS_RATE_DDR = 1 << 1, + MLX5_PTYS_RATE_QDR = 1 << 2, + MLX5_PTYS_RATE_FDR10 = 1 << 3, + MLX5_PTYS_RATE_FDR = 1 << 4, + MLX5_PTYS_RATE_EDR = 1 << 5, + MLX5_PTYS_RATE_HDR = 1 << 6, +}; + +static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) +{ + switch (rate) { + case MLX5_PTYS_RATE_SDR: return 2500; + case MLX5_PTYS_RATE_DDR: return 5000; + case MLX5_PTYS_RATE_QDR: + case MLX5_PTYS_RATE_FDR10: return 10000; + case MLX5_PTYS_RATE_FDR: return 14000; + case MLX5_PTYS_RATE_EDR: return 25000; + case MLX5_PTYS_RATE_HDR: return 50000; + default: return -1; + } +} + +static int mlx5i_get_port_settings(struct net_device *netdev, + u16 *ib_link_width_oper, u16 *ib_proto_oper) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0}; + int ret; + + ret = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_IB, 1); + if (ret) + return ret; + + *ib_link_width_oper = MLX5_GET(ptys_reg, out, ib_link_width_oper); + *ib_proto_oper = MLX5_GET(ptys_reg, out, ib_proto_oper); + + return 0; +} + +static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) +{ + int rate, width; + + rate = mlx5_ptys_rate_enum_to_int(ib_proto_oper); + if (rate < 0) + return -EINVAL; + width = mlx5_ptys_width_enum_to_int(ib_link_width_oper); + if (width < 0) + return -EINVAL; + + return rate * width; +} + +static int mlx5i_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *link_ksettings) +{ + u16 ib_link_width_oper; + u16 ib_proto_oper; + int speed, ret; + + ret = mlx5i_get_port_settings(netdev, &ib_link_width_oper, &ib_proto_oper); + if (ret) + return ret; + + ethtool_link_ksettings_zero_link_mode(link_ksettings, supported); + ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); + + speed = mlx5i_get_speed_settings(ib_link_width_oper, ib_proto_oper); + if (speed < 0) + return -EINVAL; + + link_ksettings->base.duplex = DUPLEX_FULL; + link_ksettings->base.port = PORT_OTHER; + + link_ksettings->base.autoneg = AUTONEG_DISABLE; + + link_ksettings->base.speed = speed; + + return 0; +} + const struct ethtool_ops mlx5i_ethtool_ops = { - .get_drvinfo = mlx5i_get_drvinfo, - .get_strings = mlx5i_get_strings, - .get_sset_count = mlx5i_get_sset_count, - .get_ethtool_stats = mlx5i_get_ethtool_stats, - .get_ringparam = mlx5i_get_ringparam, - .set_ringparam = mlx5i_set_ringparam, - .flash_device = mlx5i_flash_device, - .get_channels = mlx5i_get_channels, - .set_channels = mlx5i_set_channels, - .get_coalesce = mlx5i_get_coalesce, - .set_coalesce = mlx5i_set_coalesce, - .get_ts_info = mlx5i_get_ts_info, + .get_drvinfo = mlx5i_get_drvinfo, + .get_strings = mlx5i_get_strings, + .get_sset_count = mlx5i_get_sset_count, + .get_ethtool_stats = mlx5i_get_ethtool_stats, + .get_ringparam = mlx5i_get_ringparam, + .set_ringparam = mlx5i_set_ringparam, + .flash_device = mlx5i_flash_device, + .get_channels = mlx5i_get_channels, + .set_channels = mlx5i_set_channels, + .get_coalesce = mlx5i_get_coalesce, + .set_coalesce = mlx5i_set_coalesce, + .get_ts_info = mlx5i_get_ts_info, + .get_link_ksettings = mlx5i_get_link_ksettings, + .get_link = ethtool_op_get_link, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c new file mode 100644 index 000000000000..7cb67122e8b5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -0,0 +1,201 @@ +/* + * Copyright (c) 2017, Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/etherdevice.h> +#include <linux/mlx5/driver.h> +#include <linux/mlx5/mlx5_ifc.h> +#include "mlx5_core.h" +#include "lib/mpfs.h" + +/* HW L2 Table (MPFS) management */ +static int set_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index, u8 *mac) +{ + u32 in[MLX5_ST_SZ_DW(set_l2_table_entry_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(set_l2_table_entry_out)] = {0}; + u8 *in_mac_addr; + + MLX5_SET(set_l2_table_entry_in, in, opcode, MLX5_CMD_OP_SET_L2_TABLE_ENTRY); + MLX5_SET(set_l2_table_entry_in, in, table_index, index); + + in_mac_addr = MLX5_ADDR_OF(set_l2_table_entry_in, in, mac_address); + ether_addr_copy(&in_mac_addr[2], mac); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +static int del_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index) +{ + u32 in[MLX5_ST_SZ_DW(delete_l2_table_entry_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(delete_l2_table_entry_out)] = {0}; + + MLX5_SET(delete_l2_table_entry_in, in, opcode, MLX5_CMD_OP_DELETE_L2_TABLE_ENTRY); + MLX5_SET(delete_l2_table_entry_in, in, table_index, index); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +/* UC L2 table hash node */ +struct l2table_node { + struct l2addr_node node; + u32 index; /* index in HW l2 table */ +}; + +struct mlx5_mpfs { + struct hlist_head hash[MLX5_L2_ADDR_HASH_SIZE]; + struct mutex lock; /* Synchronize l2 table access */ + u32 size; + unsigned long *bitmap; +}; + +static int alloc_l2table_index(struct mlx5_mpfs *l2table, u32 *ix) +{ + int err = 0; + + *ix = find_first_zero_bit(l2table->bitmap, l2table->size); + if (*ix >= l2table->size) + err = -ENOSPC; + else + __set_bit(*ix, l2table->bitmap); + + return err; +} + +static void free_l2table_index(struct mlx5_mpfs *l2table, u32 ix) +{ + __clear_bit(ix, l2table->bitmap); +} + +int mlx5_mpfs_init(struct mlx5_core_dev *dev) +{ + int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table); + struct mlx5_mpfs *mpfs; + + if (!MLX5_VPORT_MANAGER(dev)) + return 0; + + mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL); + if (!mpfs) + return -ENOMEM; + + mutex_init(&mpfs->lock); + mpfs->size = l2table_size; + mpfs->bitmap = kcalloc(BITS_TO_LONGS(l2table_size), + sizeof(uintptr_t), GFP_KERNEL); + if (!mpfs->bitmap) { + kfree(mpfs); + return -ENOMEM; + } + + dev->priv.mpfs = mpfs; + return 0; +} + +void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_mpfs *mpfs = dev->priv.mpfs; + + if (!MLX5_VPORT_MANAGER(dev)) + return; + + WARN_ON(!hlist_empty(mpfs->hash)); + kfree(mpfs->bitmap); + kfree(mpfs); +} + +int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) +{ + struct mlx5_mpfs *mpfs = dev->priv.mpfs; + struct l2table_node *l2addr; + u32 index; + int err; + + if (!MLX5_VPORT_MANAGER(dev)) + return 0; + + mutex_lock(&mpfs->lock); + + l2addr = l2addr_hash_find(mpfs->hash, mac, struct l2table_node); + if (l2addr) { + err = -EEXIST; + goto abort; + } + + err = alloc_l2table_index(mpfs, &index); + if (err) + goto abort; + + l2addr = l2addr_hash_add(mpfs->hash, mac, struct l2table_node, GFP_KERNEL); + if (!l2addr) { + free_l2table_index(mpfs, index); + err = -ENOMEM; + goto abort; + } + + l2addr->index = index; + err = set_l2table_entry_cmd(dev, index, mac); + if (err) { + l2addr_hash_del(l2addr); + free_l2table_index(mpfs, index); + } + + mlx5_core_dbg(dev, "MPFS mac added %pM, index (%d)\n", mac, index); +abort: + mutex_unlock(&mpfs->lock); + return err; +} + +int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) +{ + struct mlx5_mpfs *mpfs = dev->priv.mpfs; + struct l2table_node *l2addr; + int err = 0; + u32 index; + + if (!MLX5_VPORT_MANAGER(dev)) + return 0; + + mutex_lock(&mpfs->lock); + + l2addr = l2addr_hash_find(mpfs->hash, mac, struct l2table_node); + if (!l2addr) { + err = -ENOENT; + goto unlock; + } + + index = l2addr->index; + del_l2table_entry_cmd(dev, index); + l2addr_hash_del(l2addr); + free_l2table_index(mpfs, index); + mlx5_core_dbg(dev, "MPFS mac deleted %pM, index (%d)\n", mac, index); +unlock: + mutex_unlock(&mpfs->lock); + return err; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h new file mode 100644 index 000000000000..4a7b2c3203a7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h @@ -0,0 +1,95 @@ +/* + * Copyright (c) 2017, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef __MLX5_MPFS_H__ +#define __MLX5_MPFS_H__ + +#include <linux/if_ether.h> +#include <linux/mlx5/device.h> + +/* L2 -mac address based- hash helpers */ +#define MLX5_L2_ADDR_HASH_SIZE (BIT(BITS_PER_BYTE)) +#define MLX5_L2_ADDR_HASH(addr) (addr[5]) + +struct l2addr_node { + struct hlist_node hlist; + u8 addr[ETH_ALEN]; +}; + +#define for_each_l2hash_node(hn, tmp, hash, i) \ + for (i = 0; i < MLX5_L2_ADDR_HASH_SIZE; i++) \ + hlist_for_each_entry_safe(hn, tmp, &(hash)[i], hlist) + +#define l2addr_hash_find(hash, mac, type) ({ \ + int ix = MLX5_L2_ADDR_HASH(mac); \ + bool found = false; \ + type *ptr = NULL; \ + \ + hlist_for_each_entry(ptr, &(hash)[ix], node.hlist) \ + if (ether_addr_equal(ptr->node.addr, mac)) {\ + found = true; \ + break; \ + } \ + if (!found) \ + ptr = NULL; \ + ptr; \ +}) + +#define l2addr_hash_add(hash, mac, type, gfp) ({ \ + int ix = MLX5_L2_ADDR_HASH(mac); \ + type *ptr = NULL; \ + \ + ptr = kzalloc(sizeof(type), gfp); \ + if (ptr) { \ + ether_addr_copy(ptr->node.addr, mac); \ + hlist_add_head(&ptr->node.hlist, &(hash)[ix]);\ + } \ + ptr; \ +}) + +#define l2addr_hash_del(ptr) ({ \ + hlist_del(&(ptr)->node.hlist); \ + kfree(ptr); \ +}) + +#ifdef CONFIG_MLX5_MPFS +int mlx5_mpfs_init(struct mlx5_core_dev *dev); +void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev); +int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac); +int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac); +#else /* #ifndef CONFIG_MLX5_MPFS */ +static inline int mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {} +static inline int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +static inline int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) { return 0; } +#endif +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8c4b45ef539c..0d2c8dcd6eae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -54,9 +54,8 @@ #include <net/devlink.h> #include "mlx5_core.h" #include "fs_core.h" -#ifdef CONFIG_MLX5_CORE_EN +#include "lib/mpfs.h" #include "eswitch.h" -#endif #include "lib/mlx5.h" #include "fpga/core.h" #include "accel/ipsec.h" @@ -788,7 +787,6 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) return -EOPNOTSUPP; } - static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) { struct pci_dev *pdev = dev->pdev; @@ -897,13 +895,17 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto err_tables_cleanup; } -#ifdef CONFIG_MLX5_CORE_EN + err = mlx5_mpfs_init(dev); + if (err) { + dev_err(&pdev->dev, "Failed to init l2 table %d\n", err); + goto err_rl_cleanup; + } + err = mlx5_eswitch_init(dev); if (err) { dev_err(&pdev->dev, "Failed to init eswitch %d\n", err); - goto err_rl_cleanup; + goto err_mpfs_cleanup; } -#endif err = mlx5_sriov_init(dev); if (err) { @@ -922,13 +924,11 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) err_sriov_cleanup: mlx5_sriov_cleanup(dev); err_eswitch_cleanup: -#ifdef CONFIG_MLX5_CORE_EN mlx5_eswitch_cleanup(dev->priv.eswitch); - +err_mpfs_cleanup: + mlx5_mpfs_cleanup(dev); err_rl_cleanup: -#endif mlx5_cleanup_rl_table(dev); - err_tables_cleanup: mlx5_cleanup_mkey_table(dev); mlx5_cleanup_srq_table(dev); @@ -946,9 +946,8 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { mlx5_fpga_cleanup(dev); mlx5_sriov_cleanup(dev); -#ifdef CONFIG_MLX5_CORE_EN mlx5_eswitch_cleanup(dev->priv.eswitch); -#endif + mlx5_mpfs_cleanup(dev); mlx5_cleanup_rl_table(dev); mlx5_cleanup_reserved_gids(dev); mlx5_cleanup_mkey_table(dev); @@ -1106,10 +1105,6 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_fs; } -#ifdef CONFIG_MLX5_CORE_EN - mlx5_eswitch_attach(dev->priv.eswitch); -#endif - err = mlx5_sriov_attach(dev); if (err) { dev_err(&pdev->dev, "sriov init failed %d\n", err); @@ -1152,9 +1147,6 @@ err_fpga_start: mlx5_sriov_detach(dev); err_sriov: -#ifdef CONFIG_MLX5_CORE_EN - mlx5_eswitch_detach(dev->priv.eswitch); -#endif mlx5_cleanup_fs(dev); err_fs: @@ -1225,9 +1217,6 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_fpga_device_stop(dev); mlx5_sriov_detach(dev); -#ifdef CONFIG_MLX5_CORE_EN - mlx5_eswitch_detach(dev->priv.eswitch); -#endif mlx5_cleanup_fs(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); @@ -1258,7 +1247,7 @@ struct mlx5_core_event_handler { }; static const struct devlink_ops mlx5_devlink_ops = { -#ifdef CONFIG_MLX5_CORE_EN +#ifdef CONFIG_MLX5_ESWITCH .eswitch_mode_set = mlx5_devlink_eswitch_mode_set, .eswitch_mode_get = mlx5_devlink_eswitch_mode_get, .eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set, @@ -1298,6 +1287,9 @@ static int init_one(struct pci_dev *pdev, mutex_init(&dev->pci_status_mutex); mutex_init(&dev->intf_state_mutex); + INIT_LIST_HEAD(&priv->waiting_events_list); + priv->is_accum_events = false; + #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING err = init_srcu_struct(&priv->pfault_srcu); if (err) { @@ -1352,7 +1344,6 @@ clean_srcu: cleanup_srcu_struct(&priv->pfault_srcu); clean_dev: #endif - pci_set_drvdata(pdev, NULL); devlink_free(devlink); return err; @@ -1379,7 +1370,6 @@ static void remove_one(struct pci_dev *pdev) #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING cleanup_srcu_struct(&priv->pfault_srcu); #endif - pci_set_drvdata(pdev, NULL); devlink_free(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 01d637dac533..b7c2900b75f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -43,6 +43,10 @@ #define DRIVER_VERSION "5.0-0" #define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs(mdev->pdev)) +#define MLX5_VPORT_MANAGER(mdev) \ + (MLX5_CAP_GEN(mdev, vport_group_manager) && \ + (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ + mlx5_core_is_pf(mdev)) extern uint mlx5_core_debug_mask; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 28d8472b36f1..6c48e9959b65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -34,9 +34,7 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/vport.h> #include "mlx5_core.h" -#ifdef CONFIG_MLX5_CORE_EN #include "eswitch.h" -#endif bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev) { @@ -90,14 +88,12 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) return -EBUSY; } -#ifdef CONFIG_MLX5_CORE_EN err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY); if (err) { mlx5_core_warn(dev, "failed to enable eswitch SRIOV (%d)\n", err); return err; } -#endif for (vf = 0; vf < num_vfs; vf++) { err = mlx5_core_enable_hca(dev, vf + 1); @@ -117,7 +113,6 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs) } } mlx5_core_dbg(dev, "successfully enabled VF* %d\n", vf); - } return 0; @@ -130,11 +125,7 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) int vf; if (!sriov->enabled_vfs) -#ifdef CONFIG_MLX5_CORE_EN - goto disable_sriov_resources; -#else - return; -#endif + goto out; for (vf = 0; vf < sriov->num_vfs; vf++) { if (!sriov->vfs_ctx[vf].enabled) @@ -148,10 +139,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev) sriov->enabled_vfs--; } -#ifdef CONFIG_MLX5_CORE_EN -disable_sriov_resources: +out: mlx5_eswitch_disable_sriov(dev->priv.eswitch); -#endif if (mlx5_wait_for_vf_pages(dev)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 695adff89d71..d56eea310509 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -75,6 +75,7 @@ config MLXSW_SPECTRUM depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV && VLAN_8021Q depends on PSAMPLE || PSAMPLE=n depends on BRIDGE || BRIDGE=n + depends on IPV6 || IPV6=n select PARMAN select MLXFW default m diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 62fc42f396bb..891ff418bb5e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -16,8 +16,9 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_switchdev.o spectrum_router.o \ spectrum_kvdl.o spectrum_acl_tcam.o \ spectrum_acl.o spectrum_flower.o \ - spectrum_cnt.o spectrum_dpipe.o \ - spectrum_fid.o + spectrum_cnt.o spectrum_fid.o \ + spectrum_ipip.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o +mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o mlxsw_minimal-objs := minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index affe84eb4bff..9d5e7cf288be 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -667,7 +667,7 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, int err; dev_dbg(mlxsw_core->bus_info->dev, "EMAD reg access (tid=%llx,reg_id=%x(%s),type=%s)\n", - trans->tid, reg->id, mlxsw_reg_id_str(reg->id), + tid, reg->id, mlxsw_reg_id_str(reg->id), mlxsw_core_reg_access_type_str(type)); skb = mlxsw_emad_alloc(mlxsw_core, reg->len); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h index 9807ef814e42..f6963b0b4a55 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h @@ -57,6 +57,9 @@ enum mlxsw_afk_element { MLXSW_AFK_ELEMENT_VID, MLXSW_AFK_ELEMENT_PCP, MLXSW_AFK_ELEMENT_TCP_FLAGS, + MLXSW_AFK_ELEMENT_IP_TTL_, + MLXSW_AFK_ELEMENT_IP_ECN, + MLXSW_AFK_ELEMENT_IP_DSCP, MLXSW_AFK_ELEMENT_MAX, }; @@ -104,6 +107,9 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = { MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12), MLXSW_AFK_ELEMENT_INFO_U32(PCP, 0x10, 20, 3), MLXSW_AFK_ELEMENT_INFO_U32(TCP_FLAGS, 0x10, 23, 9), + MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x14, 0, 8), + MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x14, 9, 2), + MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x14, 11, 6), MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x18, 0, 32), MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x1C, 0, 32), MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x18, 8), diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 1bd34d9a7b9e..cc27c5de5a1d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5,6 +5,7 @@ * Copyright (c) 2015 Elad Raz <eladr@mellanox.com> * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> + * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -3679,15 +3680,17 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_LACP, MLXSW_REG_HTGT_TRAP_GROUP_SP_LLDP, MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP, - MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP_IPV4, + MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP, MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF, MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP, - MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP_MISS, + MLXSW_REG_HTGT_TRAP_GROUP_SP_HOST_MISS, MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP, MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE, MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME, MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP, MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT, + MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD, + MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND, }; /* reg_htgt_trap_group @@ -3952,10 +3955,12 @@ MLXSW_ITEM32(reg, rgcr, pcp_rw, 0x18, 16, 2); */ MLXSW_ITEM32(reg, rgcr, activity_dis, 0x20, 0, 8); -static inline void mlxsw_reg_rgcr_pack(char *payload, bool ipv4_en) +static inline void mlxsw_reg_rgcr_pack(char *payload, bool ipv4_en, + bool ipv6_en) { MLXSW_REG_ZERO(rgcr, payload); mlxsw_reg_rgcr_ipv4_en_set(payload, ipv4_en); + mlxsw_reg_rgcr_ipv6_en_set(payload, ipv6_en); } /* RITR - Router Interface Table Register @@ -3988,16 +3993,18 @@ MLXSW_ITEM32(reg, ritr, ipv4, 0x00, 29, 1); MLXSW_ITEM32(reg, ritr, ipv6, 0x00, 28, 1); enum mlxsw_reg_ritr_if_type { + /* VLAN interface. */ MLXSW_REG_RITR_VLAN_IF, + /* FID interface. */ MLXSW_REG_RITR_FID_IF, + /* Sub-port interface. */ MLXSW_REG_RITR_SP_IF, + /* Loopback Interface. */ + MLXSW_REG_RITR_LOOPBACK_IF, }; /* reg_ritr_type - * Router interface type. - * 0 - VLAN interface. - * 1 - FID interface. - * 2 - Sub-port interface. + * Router interface type as per enum mlxsw_reg_ritr_if_type. * Access: RW */ MLXSW_ITEM32(reg, ritr, type, 0x00, 23, 3); @@ -4125,6 +4132,67 @@ MLXSW_ITEM32(reg, ritr, sp_if_system_port, 0x08, 0, 16); */ MLXSW_ITEM32(reg, ritr, sp_if_vid, 0x18, 0, 12); +/* Loopback Interface */ + +enum mlxsw_reg_ritr_loopback_protocol { + /* IPinIP IPv4 underlay Unicast */ + MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4, + /* IPinIP IPv6 underlay Unicast */ + MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV6, +}; + +/* reg_ritr_loopback_protocol + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, loopback_protocol, 0x08, 28, 4); + +enum mlxsw_reg_ritr_loopback_ipip_type { + /* Tunnel is IPinIP. */ + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_IP, + /* Tunnel is GRE, no key. */ + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP, + /* Tunnel is GRE, with a key. */ + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP, +}; + +/* reg_ritr_loopback_ipip_type + * Encapsulation type. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, loopback_ipip_type, 0x10, 24, 4); + +enum mlxsw_reg_ritr_loopback_ipip_options { + /* The key is defined by gre_key. */ + MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET, +}; + +/* reg_ritr_loopback_ipip_options + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, loopback_ipip_options, 0x10, 20, 4); + +/* reg_ritr_loopback_ipip_uvr + * Underlay Virtual Router ID. + * Range is 0..cap_max_virtual_routers-1. + * Reserved for Spectrum-2. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, loopback_ipip_uvr, 0x10, 0, 16); + +/* reg_ritr_loopback_ipip_usip* + * Encapsulation Underlay source IP. + * Access: RW + */ +MLXSW_ITEM_BUF(reg, ritr, loopback_ipip_usip6, 0x18, 16); +MLXSW_ITEM32(reg, ritr, loopback_ipip_usip4, 0x24, 0, 32); + +/* reg_ritr_loopback_ipip_gre_key + * GRE Key. + * Reserved when ipip_type is not IP_IN_GRE_KEY_IN_IP. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, loopback_ipip_gre_key, 0x28, 0, 32); + /* Shared between ingress/egress */ enum mlxsw_reg_ritr_counter_set_type { /* No Count. */ @@ -4195,24 +4263,54 @@ static inline void mlxsw_reg_ritr_sp_if_pack(char *payload, bool lag, static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, enum mlxsw_reg_ritr_if_type type, - u16 rif, u16 vr_id, u16 mtu, - const char *mac) + u16 rif, u16 vr_id, u16 mtu) { bool op = enable ? MLXSW_REG_RITR_RIF_CREATE : MLXSW_REG_RITR_RIF_DEL; MLXSW_REG_ZERO(ritr, payload); mlxsw_reg_ritr_enable_set(payload, enable); mlxsw_reg_ritr_ipv4_set(payload, 1); + mlxsw_reg_ritr_ipv6_set(payload, 1); mlxsw_reg_ritr_type_set(payload, type); mlxsw_reg_ritr_op_set(payload, op); mlxsw_reg_ritr_rif_set(payload, rif); mlxsw_reg_ritr_ipv4_fe_set(payload, 1); + mlxsw_reg_ritr_ipv6_fe_set(payload, 1); mlxsw_reg_ritr_lb_en_set(payload, 1); mlxsw_reg_ritr_virtual_router_set(payload, vr_id); mlxsw_reg_ritr_mtu_set(payload, mtu); +} + +static inline void mlxsw_reg_ritr_mac_pack(char *payload, const char *mac) +{ mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac); } +static inline void +mlxsw_reg_ritr_loopback_ipip_common_pack(char *payload, + enum mlxsw_reg_ritr_loopback_ipip_type ipip_type, + enum mlxsw_reg_ritr_loopback_ipip_options options, + u16 uvr_id, u32 gre_key) +{ + mlxsw_reg_ritr_loopback_ipip_type_set(payload, ipip_type); + mlxsw_reg_ritr_loopback_ipip_options_set(payload, options); + mlxsw_reg_ritr_loopback_ipip_uvr_set(payload, uvr_id); + mlxsw_reg_ritr_loopback_ipip_gre_key_set(payload, gre_key); +} + +static inline void +mlxsw_reg_ritr_loopback_ipip4_pack(char *payload, + enum mlxsw_reg_ritr_loopback_ipip_type ipip_type, + enum mlxsw_reg_ritr_loopback_ipip_options options, + u16 uvr_id, u32 usip, u32 gre_key) +{ + mlxsw_reg_ritr_loopback_protocol_set(payload, + MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4); + mlxsw_reg_ritr_loopback_ipip_common_pack(payload, ipip_type, options, + uvr_id, gre_key); + mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip); +} + /* RATR - Router Adjacency Table Register * -------------------------------------- * The RATR register is used to configure the Router Adjacency (next-hop) @@ -4268,6 +4366,38 @@ MLXSW_ITEM32(reg, ratr, v, 0x00, 24, 1); */ MLXSW_ITEM32(reg, ratr, a, 0x00, 16, 1); +enum mlxsw_reg_ratr_type { + /* Ethernet */ + MLXSW_REG_RATR_TYPE_ETHERNET, + /* IPoIB Unicast without GRH. + * Reserved for Spectrum. + */ + MLXSW_REG_RATR_TYPE_IPOIB_UC, + /* IPoIB Unicast with GRH. Supported only in table 0 (Ethernet unicast + * adjacency). + * Reserved for Spectrum. + */ + MLXSW_REG_RATR_TYPE_IPOIB_UC_W_GRH, + /* IPoIB Multicast. + * Reserved for Spectrum. + */ + MLXSW_REG_RATR_TYPE_IPOIB_MC, + /* MPLS. + * Reserved for SwitchX/-2. + */ + MLXSW_REG_RATR_TYPE_MPLS, + /* IPinIP Encap. + * Reserved for SwitchX/-2. + */ + MLXSW_REG_RATR_TYPE_IPIP, +}; + +/* reg_ratr_type + * Adjacency entry type. + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, type, 0x04, 28, 4); + /* reg_ratr_adjacency_index_low * Bits 15:0 of index into the adjacency table. * For SwitchX and SwitchX-2, the adjacency table is linear and @@ -4297,17 +4427,17 @@ enum mlxsw_reg_ratr_trap_action { */ MLXSW_ITEM32(reg, ratr, trap_action, 0x0C, 28, 4); -enum mlxsw_reg_ratr_trap_id { - MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS0 = 0, - MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS1 = 1, -}; - /* reg_ratr_adjacency_index_high * Bits 23:16 of the adjacency_index. * Access: Index */ MLXSW_ITEM32(reg, ratr, adjacency_index_high, 0x0C, 16, 8); +enum mlxsw_reg_ratr_trap_id { + MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS0, + MLXSW_REG_RATR_TRAP_ID_RTR_EGRESS1, +}; + /* reg_ratr_trap_id * Trap ID to be reported to CPU. * Trap-ID is RTR_EGRESS0 or RTR_EGRESS1. @@ -4322,14 +4452,44 @@ MLXSW_ITEM32(reg, ratr, trap_id, 0x0C, 0, 8); */ MLXSW_ITEM_BUF(reg, ratr, eth_destination_mac, 0x12, 6); +enum mlxsw_reg_ratr_ipip_type { + /* IPv4, address set by mlxsw_reg_ratr_ipip_ipv4_udip. */ + MLXSW_REG_RATR_IPIP_TYPE_IPV4, + /* IPv6, address set by mlxsw_reg_ratr_ipip_ipv6_ptr. */ + MLXSW_REG_RATR_IPIP_TYPE_IPV6, +}; + +/* reg_ratr_ipip_type + * Underlay destination ip type. + * Note: the type field must match the protocol of the router interface. + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, ipip_type, 0x10, 16, 4); + +/* reg_ratr_ipip_ipv4_udip + * Underlay ipv4 dip. + * Reserved when ipip_type is IPv6. + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, ipip_ipv4_udip, 0x18, 0, 32); + +/* reg_ratr_ipip_ipv6_ptr + * Pointer to IPv6 underlay destination ip address. + * For Spectrum: Pointer to KVD linear space. + * Access: RW + */ +MLXSW_ITEM32(reg, ratr, ipip_ipv6_ptr, 0x1C, 0, 24); + static inline void mlxsw_reg_ratr_pack(char *payload, enum mlxsw_reg_ratr_op op, bool valid, + enum mlxsw_reg_ratr_type type, u32 adjacency_index, u16 egress_rif) { MLXSW_REG_ZERO(ratr, payload); mlxsw_reg_ratr_op_set(payload, op); mlxsw_reg_ratr_v_set(payload, valid); + mlxsw_reg_ratr_type_set(payload, type); mlxsw_reg_ratr_adjacency_index_low_set(payload, adjacency_index); mlxsw_reg_ratr_adjacency_index_high_set(payload, adjacency_index >> 16); mlxsw_reg_ratr_egress_router_interface_set(payload, egress_rif); @@ -4341,6 +4501,12 @@ static inline void mlxsw_reg_ratr_eth_entry_pack(char *payload, mlxsw_reg_ratr_eth_destination_mac_memcpy_to(payload, dest_mac); } +static inline void mlxsw_reg_ratr_ipip4_entry_pack(char *payload, u32 ipv4_udip) +{ + mlxsw_reg_ratr_ipip_type_set(payload, MLXSW_REG_RATR_IPIP_TYPE_IPV4); + mlxsw_reg_ratr_ipip_ipv4_udip_set(payload, ipv4_udip); +} + /* RICNT - Router Interface Counter Register * ----------------------------------------- * The RICNT register retrieves per port performance counters @@ -4712,12 +4878,13 @@ MLXSW_ITEM32(reg, ralue, prefix_len, 0x08, 0, 8); /* reg_ralue_dip* * The prefix of the route or of the marker that the object of the LPM * is compared with. The most significant bits of the dip are the prefix. - * The list significant bits must be '0' if the prefix_len is smaller + * The least significant bits must be '0' if the prefix_len is smaller * than 128 for IPv6 or smaller than 32 for IPv4. * IPv4 address uses bits dip[31:0] and bits dip[127:32] are reserved. * Access: Index */ MLXSW_ITEM32(reg, ralue, dip4, 0x18, 0, 32); +MLXSW_ITEM_BUF(reg, ralue, dip6, 0x0C, 16); enum mlxsw_reg_ralue_entry_type { MLXSW_REG_RALUE_ENTRY_TYPE_MARKER_ENTRY = 1, @@ -4806,7 +4973,7 @@ MLXSW_ITEM32(reg, ralue, ecmp_size, 0x28, 0, 13); */ MLXSW_ITEM32(reg, ralue, local_erif, 0x24, 0, 16); -/* reg_ralue_v +/* reg_ralue_ip2me_v * Valid bit for the tunnel_ptr field. * If valid = 0 then trap to CPU as IP2ME trap ID. * If valid = 1 and the packet format allows NVE or IPinIP tunnel @@ -4816,15 +4983,15 @@ MLXSW_ITEM32(reg, ralue, local_erif, 0x24, 0, 16); * Only relevant in case of IP2ME action. * Access: RW */ -MLXSW_ITEM32(reg, ralue, v, 0x24, 31, 1); +MLXSW_ITEM32(reg, ralue, ip2me_v, 0x24, 31, 1); -/* reg_ralue_tunnel_ptr +/* reg_ralue_ip2me_tunnel_ptr * Tunnel Pointer for NVE or IPinIP tunnel decapsulation. * For Spectrum, pointer to KVD Linear. * Only relevant in case of IP2ME action. * Access: RW */ -MLXSW_ITEM32(reg, ralue, tunnel_ptr, 0x24, 0, 24); +MLXSW_ITEM32(reg, ralue, ip2me_tunnel_ptr, 0x24, 0, 24); static inline void mlxsw_reg_ralue_pack(char *payload, enum mlxsw_reg_ralxx_protocol protocol, @@ -4851,6 +5018,16 @@ static inline void mlxsw_reg_ralue_pack4(char *payload, mlxsw_reg_ralue_dip4_set(payload, dip); } +static inline void mlxsw_reg_ralue_pack6(char *payload, + enum mlxsw_reg_ralxx_protocol protocol, + enum mlxsw_reg_ralue_op op, + u16 virtual_router, u8 prefix_len, + const void *dip) +{ + mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len); + mlxsw_reg_ralue_dip6_memcpy_to(payload, dip); +} + static inline void mlxsw_reg_ralue_act_remote_pack(char *payload, enum mlxsw_reg_ralue_trap_action trap_action, @@ -4883,6 +5060,15 @@ mlxsw_reg_ralue_act_ip2me_pack(char *payload) MLXSW_REG_RALUE_ACTION_TYPE_IP2ME); } +static inline void +mlxsw_reg_ralue_act_ip2me_tun_pack(char *payload, u32 tunnel_ptr) +{ + mlxsw_reg_ralue_action_type_set(payload, + MLXSW_REG_RALUE_ACTION_TYPE_IP2ME); + mlxsw_reg_ralue_ip2me_v_set(payload, 1); + mlxsw_reg_ralue_ip2me_tunnel_ptr_set(payload, tunnel_ptr); +} + /* RAUHT - Router Algorithmic LPM Unicast Host Table Register * ---------------------------------------------------------- * The RAUHT register is used to configure and query the Unicast Host table in @@ -4954,6 +5140,7 @@ MLXSW_ITEM32(reg, rauht, rif, 0x00, 0, 16); * Access: Index */ MLXSW_ITEM32(reg, rauht, dip4, 0x1C, 0x0, 32); +MLXSW_ITEM_BUF(reg, rauht, dip6, 0x10, 16); enum mlxsw_reg_rauht_trap_action { MLXSW_REG_RAUHT_TRAP_ACTION_NOP, @@ -4982,6 +5169,15 @@ enum mlxsw_reg_rauht_trap_id { */ MLXSW_ITEM32(reg, rauht, trap_id, 0x60, 0, 9); +enum mlxsw_reg_flow_counter_set_type { + /* No count */ + MLXSW_REG_FLOW_COUNTER_SET_TYPE_NO_COUNT = 0x00, + /* Count packets and bytes */ + MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, + /* Count only packets */ + MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS = 0x05, +}; + /* reg_rauht_counter_set_type * Counter set type for flow counters * Access: RW @@ -5018,6 +5214,23 @@ static inline void mlxsw_reg_rauht_pack4(char *payload, mlxsw_reg_rauht_dip4_set(payload, dip); } +static inline void mlxsw_reg_rauht_pack6(char *payload, + enum mlxsw_reg_rauht_op op, u16 rif, + const char *mac, const char *dip) +{ + mlxsw_reg_rauht_pack(payload, op, rif, mac); + mlxsw_reg_rauht_type_set(payload, MLXSW_REG_RAUHT_TYPE_IPV6); + mlxsw_reg_rauht_dip6_memcpy_to(payload, dip); +} + +static inline void mlxsw_reg_rauht_pack_counter(char *payload, + u64 counter_index) +{ + mlxsw_reg_rauht_counter_index_set(payload, counter_index); + mlxsw_reg_rauht_counter_set_type_set(payload, + MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES); +} + /* RALEU - Router Algorithmic LPM ECMP Update Register * --------------------------------------------------- * The register enables updating the ECMP section in the action for multiple @@ -5216,6 +5429,30 @@ MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_rif, MLXSW_REG_RAUHTD_BASE_LEN, 0, MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv4_ent_dip, MLXSW_REG_RAUHTD_BASE_LEN, 0, 32, MLXSW_REG_RAUHTD_IPV4_ENT_LEN, 0x04, false); +#define MLXSW_REG_RAUHTD_IPV6_ENT_LEN 0x20 + +/* reg_rauhtd_ipv6_ent_a + * Activity. Set for new entries. Set if a packet lookup has hit on the + * specific entry. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv6_ent_a, MLXSW_REG_RAUHTD_BASE_LEN, 16, 1, + MLXSW_REG_RAUHTD_IPV6_ENT_LEN, 0x00, false); + +/* reg_rauhtd_ipv6_ent_rif + * Router interface. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, rauhtd, ipv6_ent_rif, MLXSW_REG_RAUHTD_BASE_LEN, 0, + 16, MLXSW_REG_RAUHTD_IPV6_ENT_LEN, 0x00, false); + +/* reg_rauhtd_ipv6_ent_dip + * Destination IPv6 address. + * Access: RO + */ +MLXSW_ITEM_BUF_INDEXED(reg, rauhtd, ipv6_ent_dip, MLXSW_REG_RAUHTD_BASE_LEN, + 16, MLXSW_REG_RAUHTD_IPV6_ENT_LEN, 0x10); + static inline void mlxsw_reg_rauhtd_ent_ipv4_unpack(char *payload, int ent_index, u16 *p_rif, u32 *p_dip) @@ -5224,6 +5461,141 @@ static inline void mlxsw_reg_rauhtd_ent_ipv4_unpack(char *payload, *p_dip = mlxsw_reg_rauhtd_ipv4_ent_dip_get(payload, ent_index); } +static inline void mlxsw_reg_rauhtd_ent_ipv6_unpack(char *payload, + int rec_index, u16 *p_rif, + char *p_dip) +{ + *p_rif = mlxsw_reg_rauhtd_ipv6_ent_rif_get(payload, rec_index); + mlxsw_reg_rauhtd_ipv6_ent_dip_memcpy_from(payload, rec_index, p_dip); +} + +/* RTDP - Routing Tunnel Decap Properties Register + * ----------------------------------------------- + * The RTDP register is used for configuring the tunnel decap properties of NVE + * and IPinIP. + */ +#define MLXSW_REG_RTDP_ID 0x8020 +#define MLXSW_REG_RTDP_LEN 0x44 + +MLXSW_REG_DEFINE(rtdp, MLXSW_REG_RTDP_ID, MLXSW_REG_RTDP_LEN); + +enum mlxsw_reg_rtdp_type { + MLXSW_REG_RTDP_TYPE_NVE, + MLXSW_REG_RTDP_TYPE_IPIP, +}; + +/* reg_rtdp_type + * Type of the RTDP entry as per enum mlxsw_reg_rtdp_type. + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, type, 0x00, 28, 4); + +/* reg_rtdp_tunnel_index + * Index to the Decap entry. + * For Spectrum, Index to KVD Linear. + * Access: Index + */ +MLXSW_ITEM32(reg, rtdp, tunnel_index, 0x00, 0, 24); + +/* IPinIP */ + +/* reg_rtdp_ipip_irif + * Ingress Router Interface for the overlay router + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, ipip_irif, 0x04, 16, 16); + +enum mlxsw_reg_rtdp_ipip_sip_check { + /* No sip checks. */ + MLXSW_REG_RTDP_IPIP_SIP_CHECK_NO, + /* Filter packet if underlay is not IPv4 or if underlay SIP does not + * equal ipv4_usip. + */ + MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV4, + /* Filter packet if underlay is not IPv6 or if underlay SIP does not + * equal ipv6_usip. + */ + MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV6 = 3, +}; + +/* reg_rtdp_ipip_sip_check + * SIP check to perform. If decapsulation failed due to these configurations + * then trap_id is IPIP_DECAP_ERROR. + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, ipip_sip_check, 0x04, 0, 3); + +/* If set, allow decapsulation of IPinIP (without GRE). */ +#define MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_IPIP BIT(0) +/* If set, allow decapsulation of IPinGREinIP without a key. */ +#define MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE BIT(1) +/* If set, allow decapsulation of IPinGREinIP with a key. */ +#define MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY BIT(2) + +/* reg_rtdp_ipip_type_check + * Flags as per MLXSW_REG_RTDP_IPIP_TYPE_CHECK_*. If decapsulation failed due to + * these configurations then trap_id is IPIP_DECAP_ERROR. + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, ipip_type_check, 0x08, 24, 3); + +/* reg_rtdp_ipip_gre_key_check + * Whether GRE key should be checked. When check is enabled: + * - A packet received as IPinIP (without GRE) will always pass. + * - A packet received as IPinGREinIP without a key will not pass the check. + * - A packet received as IPinGREinIP with a key will pass the check only if the + * key in the packet is equal to expected_gre_key. + * If decapsulation failed due to GRE key then trap_id is IPIP_DECAP_ERROR. + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, ipip_gre_key_check, 0x08, 23, 1); + +/* reg_rtdp_ipip_ipv4_usip + * Underlay IPv4 address for ipv4 source address check. + * Reserved when sip_check is not '1'. + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, ipip_ipv4_usip, 0x0C, 0, 32); + +/* reg_rtdp_ipip_ipv6_usip_ptr + * This field is valid when sip_check is "sipv6 check explicitly". This is a + * pointer to the IPv6 DIP which is configured by RIPS. For Spectrum, the index + * is to the KVD linear. + * Reserved when sip_check is not MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV6. + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, ipip_ipv6_usip_ptr, 0x10, 0, 24); + +/* reg_rtdp_ipip_expected_gre_key + * GRE key for checking. + * Reserved when gre_key_check is '0'. + * Access: RW + */ +MLXSW_ITEM32(reg, rtdp, ipip_expected_gre_key, 0x14, 0, 32); + +static inline void mlxsw_reg_rtdp_pack(char *payload, + enum mlxsw_reg_rtdp_type type, + u32 tunnel_index) +{ + MLXSW_REG_ZERO(rtdp, payload); + mlxsw_reg_rtdp_type_set(payload, type); + mlxsw_reg_rtdp_tunnel_index_set(payload, tunnel_index); +} + +static inline void +mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif, + enum mlxsw_reg_rtdp_ipip_sip_check sip_check, + unsigned int type_check, bool gre_key_check, + u32 ipv4_usip, u32 expected_gre_key) +{ + mlxsw_reg_rtdp_ipip_irif_set(payload, irif); + mlxsw_reg_rtdp_ipip_sip_check_set(payload, sip_check); + mlxsw_reg_rtdp_ipip_type_check_set(payload, type_check); + mlxsw_reg_rtdp_ipip_gre_key_check_set(payload, gre_key_check); + mlxsw_reg_rtdp_ipip_ipv4_usip_set(payload, ipv4_usip); + mlxsw_reg_rtdp_ipip_expected_gre_key_set(payload, expected_gre_key); +} + /* MFCR - Management Fan Control Register * -------------------------------------- * This register controls the settings of the Fan Speed PWM mechanism. @@ -5982,15 +6354,6 @@ static inline void mlxsw_reg_mpsc_pack(char *payload, u8 local_port, bool e, MLXSW_REG_DEFINE(mgpc, MLXSW_REG_MGPC_ID, MLXSW_REG_MGPC_LEN); -enum mlxsw_reg_mgpc_counter_set_type { - /* No count */ - MLXSW_REG_MGPC_COUNTER_SET_TYPE_NO_COUT = 0x00, - /* Count packets and bytes */ - MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES = 0x03, - /* Count only packets */ - MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS = 0x05, -}; - /* reg_mgpc_counter_set_type * Counter set type. * Access: OP @@ -6030,7 +6393,7 @@ MLXSW_ITEM64(reg, mgpc, packet_counter, 0x10, 0, 64); static inline void mlxsw_reg_mgpc_pack(char *payload, u32 counter_index, enum mlxsw_reg_mgpc_opcode opcode, - enum mlxsw_reg_mgpc_counter_set_type set_type) + enum mlxsw_reg_flow_counter_set_type set_type) { MLXSW_REG_ZERO(mgpc, payload); mlxsw_reg_mgpc_counter_index_set(payload, counter_index); @@ -6494,6 +6857,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(rgcr), MLXSW_REG(ritr), MLXSW_REG(ratr), + MLXSW_REG(rtdp), MLXSW_REG(ricnt), MLXSW_REG(ralta), MLXSW_REG(ralst), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c6a3e61b53bd..ed7cd6c48019 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -58,6 +58,7 @@ #include <net/tc_act/tc_mirred.h> #include <net/netevent.h> #include <net/tc_act/tc_sample.h> +#include <net/addrconf.h> #include "spectrum.h" #include "pci.h" @@ -381,12 +382,14 @@ int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, int err; mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_NOP, - MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES); + MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl); if (err) return err; - *packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl); - *bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl); + if (packets) + *packets = mlxsw_reg_mgpc_packet_counter_get(mgpc_pl); + if (bytes) + *bytes = mlxsw_reg_mgpc_byte_counter_get(mgpc_pl); return 0; } @@ -396,7 +399,7 @@ static int mlxsw_sp_flow_counter_clear(struct mlxsw_sp *mlxsw_sp, char mgpc_pl[MLXSW_REG_MGPC_LEN]; mlxsw_reg_mgpc_pack(mgpc_pl, counter_index, MLXSW_REG_MGPC_OPCODE_CLEAR, - MLXSW_REG_MGPC_COUNTER_SET_TYPE_PACKETS_BYTES); + MLXSW_REG_FLOW_COUNTER_SET_TYPE_PACKETS_BYTES); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mgpc), mgpc_pl); } @@ -1616,16 +1619,16 @@ mlxsw_sp_port_del_cls_matchall_sample(struct mlxsw_sp_port *mlxsw_sp_port) } static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, - __be16 protocol, - struct tc_cls_matchall_offload *cls, + struct tc_cls_matchall_offload *f, bool ingress) { struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; + __be16 protocol = f->common.protocol; const struct tc_action *a; LIST_HEAD(actions); int err; - if (!tc_single_action(cls->exts)) { + if (!tcf_exts_has_one_action(f->exts)) { netdev_err(mlxsw_sp_port->dev, "only singular actions are supported\n"); return -EOPNOTSUPP; } @@ -1633,9 +1636,9 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); if (!mall_tc_entry) return -ENOMEM; - mall_tc_entry->cookie = cls->cookie; + mall_tc_entry->cookie = f->cookie; - tcf_exts_to_list(cls->exts, &actions); + tcf_exts_to_list(f->exts, &actions); a = list_first_entry(&actions, struct tc_action, list); if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) { @@ -1647,7 +1650,7 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, mirror, a, ingress); } else if (is_tcf_sample(a) && protocol == htons(ETH_P_ALL)) { mall_tc_entry->type = MLXSW_SP_PORT_MALL_SAMPLE; - err = mlxsw_sp_port_add_cls_matchall_sample(mlxsw_sp_port, cls, + err = mlxsw_sp_port_add_cls_matchall_sample(mlxsw_sp_port, f, a, ingress); } else { err = -EOPNOTSUPP; @@ -1665,12 +1668,12 @@ err_add_action: } static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, - struct tc_cls_matchall_offload *cls) + struct tc_cls_matchall_offload *f) { struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry; mall_tc_entry = mlxsw_sp_port_mall_tc_entry_find(mlxsw_sp_port, - cls->cookie); + f->cookie); if (!mall_tc_entry) { netdev_dbg(mlxsw_sp_port->dev, "tc entry not found on port\n"); return; @@ -1692,49 +1695,72 @@ static void mlxsw_sp_port_del_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, kfree(mall_tc_entry); } -static int mlxsw_sp_setup_tc(struct net_device *dev, u32 handle, - u32 chain_index, __be16 proto, - struct tc_to_netdev *tc) +static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, + struct tc_cls_matchall_offload *f) { - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - bool ingress = TC_H_MAJ(handle) == TC_H_MAJ(TC_H_INGRESS); + bool ingress; - if (chain_index) + if (is_classid_clsact_ingress(f->common.classid)) + ingress = true; + else if (is_classid_clsact_egress(f->common.classid)) + ingress = false; + else return -EOPNOTSUPP; - switch (tc->type) { - case TC_SETUP_MATCHALL: - switch (tc->cls_mall->command) { - case TC_CLSMATCHALL_REPLACE: - return mlxsw_sp_port_add_cls_matchall(mlxsw_sp_port, - proto, - tc->cls_mall, - ingress); - case TC_CLSMATCHALL_DESTROY: - mlxsw_sp_port_del_cls_matchall(mlxsw_sp_port, - tc->cls_mall); - return 0; - default: - return -EOPNOTSUPP; - } - case TC_SETUP_CLSFLOWER: - switch (tc->cls_flower->command) { - case TC_CLSFLOWER_REPLACE: - return mlxsw_sp_flower_replace(mlxsw_sp_port, ingress, - proto, tc->cls_flower); - case TC_CLSFLOWER_DESTROY: - mlxsw_sp_flower_destroy(mlxsw_sp_port, ingress, - tc->cls_flower); - return 0; - case TC_CLSFLOWER_STATS: - return mlxsw_sp_flower_stats(mlxsw_sp_port, ingress, - tc->cls_flower); - default: - return -EOPNOTSUPP; - } + if (f->common.chain_index) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_CLSMATCHALL_REPLACE: + return mlxsw_sp_port_add_cls_matchall(mlxsw_sp_port, f, + ingress); + case TC_CLSMATCHALL_DESTROY: + mlxsw_sp_port_del_cls_matchall(mlxsw_sp_port, f); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int +mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_port *mlxsw_sp_port, + struct tc_cls_flower_offload *f) +{ + bool ingress; + + if (is_classid_clsact_ingress(f->common.classid)) + ingress = true; + else if (is_classid_clsact_egress(f->common.classid)) + ingress = false; + else + return -EOPNOTSUPP; + + switch (f->command) { + case TC_CLSFLOWER_REPLACE: + return mlxsw_sp_flower_replace(mlxsw_sp_port, ingress, f); + case TC_CLSFLOWER_DESTROY: + mlxsw_sp_flower_destroy(mlxsw_sp_port, ingress, f); + return 0; + case TC_CLSFLOWER_STATS: + return mlxsw_sp_flower_stats(mlxsw_sp_port, ingress, f); + default: + return -EOPNOTSUPP; } +} - return -EOPNOTSUPP; +static int mlxsw_sp_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + + switch (type) { + case TC_SETUP_CLSMATCHALL: + return mlxsw_sp_setup_tc_cls_matchall(mlxsw_sp_port, type_data); + case TC_SETUP_CLSFLOWER: + return mlxsw_sp_setup_tc_cls_flower(mlxsw_sp_port, type_data); + default: + return -EOPNOTSUPP; + } } static const struct net_device_ops mlxsw_sp_port_netdev_ops = { @@ -3333,15 +3359,48 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MARK(ARPBC, MIRROR_TO_CPU, ARP, false), MLXSW_SP_RXL_MARK(ARPUC, MIRROR_TO_CPU, ARP, false), MLXSW_SP_RXL_NO_MARK(FID_MISS, TRAP_TO_CPU, IP2ME, false), + MLXSW_SP_RXL_MARK(IPV6_MLDV12_LISTENER_QUERY, MIRROR_TO_CPU, IPV6_MLD, + false), + MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_REPORT, TRAP_TO_CPU, IPV6_MLD, + false), + MLXSW_SP_RXL_NO_MARK(IPV6_MLDV1_LISTENER_DONE, TRAP_TO_CPU, IPV6_MLD, + false), + MLXSW_SP_RXL_NO_MARK(IPV6_MLDV2_LISTENER_REPORT, TRAP_TO_CPU, IPV6_MLD, + false), /* L3 traps */ - MLXSW_SP_RXL_NO_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_NO_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_NO_MARK(LBERROR, TRAP_TO_CPU, ROUTER_EXP, false), - MLXSW_SP_RXL_MARK(OSPF, TRAP_TO_CPU, OSPF, false), - MLXSW_SP_RXL_NO_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false), - MLXSW_SP_RXL_NO_MARK(RTR_INGRESS0, TRAP_TO_CPU, REMOTE_ROUTE, false), - MLXSW_SP_RXL_NO_MARK(HOST_MISS_IPV4, TRAP_TO_CPU, ARP_MISS, false), - MLXSW_SP_RXL_NO_MARK(BGP_IPV4, TRAP_TO_CPU, BGP_IPV4, false), + MLXSW_SP_RXL_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(LBERROR, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false), + MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP, + false), + MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IPV6_LINK_LOCAL_SRC, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IPV6_ALL_NODES_LINK, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IPV6_ALL_ROUTERS_LINK, TRAP_TO_CPU, ROUTER_EXP, + false), + MLXSW_SP_RXL_MARK(IPV4_OSPF, TRAP_TO_CPU, OSPF, false), + MLXSW_SP_RXL_MARK(IPV6_OSPF, TRAP_TO_CPU, OSPF, false), + MLXSW_SP_RXL_MARK(IPV6_DHCP, TRAP_TO_CPU, DHCP, false), + MLXSW_SP_RXL_MARK(RTR_INGRESS0, TRAP_TO_CPU, REMOTE_ROUTE, false), + MLXSW_SP_RXL_MARK(IPV4_BGP, TRAP_TO_CPU, BGP, false), + MLXSW_SP_RXL_MARK(IPV6_BGP, TRAP_TO_CPU, BGP, false), + MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_SOLICITATION, TRAP_TO_CPU, IPV6_ND, + false), + MLXSW_SP_RXL_MARK(L3_IPV6_ROUTER_ADVERTISMENT, TRAP_TO_CPU, IPV6_ND, + false), + MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_SOLICITATION, TRAP_TO_CPU, IPV6_ND, + false), + MLXSW_SP_RXL_MARK(L3_IPV6_NEIGHBOR_ADVERTISMENT, TRAP_TO_CPU, IPV6_ND, + false), + MLXSW_SP_RXL_MARK(L3_IPV6_REDIRECTION, TRAP_TO_CPU, IPV6_ND, false), + MLXSW_SP_RXL_MARK(IPV6_MC_LINK_LOCAL_DEST, TRAP_TO_CPU, ROUTER_EXP, + false), + MLXSW_SP_RXL_MARK(HOST_MISS_IPV4, TRAP_TO_CPU, HOST_MISS, false), + MLXSW_SP_RXL_MARK(HOST_MISS_IPV6, TRAP_TO_CPU, HOST_MISS, false), + MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false), + MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false), /* PKT Sample trap */ MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU, false, SP_IP2ME, DISCARD), @@ -3376,15 +3435,17 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) burst_size = 7; break; case MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD: rate = 16 * 1024; burst_size = 10; break; - case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP_IPV4: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP: case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP: case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP: - case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP_MISS: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_HOST_MISS: case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP: case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND: rate = 1024; burst_size = 7; break; @@ -3433,21 +3494,23 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core) priority = 5; tc = 5; break; - case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP_IPV4: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_BGP: case MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP: priority = 4; tc = 4; break; case MLXSW_REG_HTGT_TRAP_GROUP_SP_IGMP: case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD: priority = 3; tc = 3; break; case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND: priority = 2; tc = 2; break; - case MLXSW_REG_HTGT_TRAP_GROUP_SP_ARP_MISS: + case MLXSW_REG_HTGT_TRAP_GROUP_SP_HOST_MISS: case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP: case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE: priority = 1; @@ -3694,7 +3757,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_fids_fini(mlxsw_sp); } -static struct mlxsw_config_profile mlxsw_sp_config_profile = { +static const struct mlxsw_config_profile mlxsw_sp_config_profile = { .used_max_vepa_channels = 1, .max_vepa_channels = 0, .used_max_mid = 1, @@ -4363,6 +4426,10 @@ static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = { .priority = 10, /* Must be called before FIB notifier block */ }; +static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = { + .notifier_call = mlxsw_sp_inet6addr_event, +}; + static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = { .notifier_call = mlxsw_sp_router_netevent_event, }; @@ -4383,6 +4450,7 @@ static int __init mlxsw_sp_module_init(void) register_netdevice_notifier(&mlxsw_sp_netdevice_nb); register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); + register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); register_netevent_notifier(&mlxsw_sp_router_netevent_nb); err = mlxsw_core_driver_register(&mlxsw_sp_driver); @@ -4399,6 +4467,7 @@ err_pci_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp_driver); err_core_driver_register: unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb); + unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); return err; @@ -4409,6 +4478,7 @@ static void __exit mlxsw_sp_module_exit(void) mlxsw_pci_driver_unregister(&mlxsw_sp_pci_driver); mlxsw_core_driver_unregister(&mlxsw_sp_driver); unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb); + unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb); unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb); unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 5ef98d4d0ab6..84ce83acdc19 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -77,6 +77,7 @@ enum mlxsw_sp_rif_type { MLXSW_SP_RIF_TYPE_SUBPORT, MLXSW_SP_RIF_TYPE_VLAN, MLXSW_SP_RIF_TYPE_FID, + MLXSW_SP_RIF_TYPE_IPIP_LB, /* IP-in-IP loopback. */ MLXSW_SP_RIF_TYPE_MAX, }; @@ -384,6 +385,8 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused, int mlxsw_sp_netdevice_router_port_event(struct net_device *dev); int mlxsw_sp_inetaddr_event(struct notifier_block *unused, unsigned long event, void *ptr); +int mlxsw_sp_inet6addr_event(struct notifier_block *unused, + unsigned long event, void *ptr); int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, struct netdev_notifier_changeupper_info *info); void @@ -415,6 +418,7 @@ struct mlxsw_sp_acl_profile_ops { int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, struct net_device *dev, bool ingress); void (*ruleset_unbind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv); + u16 (*ruleset_group_id)(void *ruleset_priv); size_t rule_priv_size; int (*rule_add)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, @@ -438,11 +442,16 @@ struct mlxsw_sp_acl_ruleset; /* spectrum_acl.c */ struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl); struct mlxsw_sp_acl_ruleset * -mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp, - struct net_device *dev, bool ingress, +mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp, struct net_device *dev, + bool ingress, u32 chain_index, + enum mlxsw_sp_acl_profile profile); +struct mlxsw_sp_acl_ruleset * +mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp, struct net_device *dev, + bool ingress, u32 chain_index, enum mlxsw_sp_acl_profile profile); void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset); +u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset); struct mlxsw_sp_acl_rule_info * mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl); @@ -506,7 +515,7 @@ extern const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops; /* spectrum_flower.c */ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, - __be16 protocol, struct tc_cls_flower_offload *f); + struct tc_cls_flower_offload *f); void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, struct tc_cls_flower_offload *f); int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 01a1501b56ca..4b2455e3e079 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -74,6 +74,7 @@ struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl) struct mlxsw_sp_acl_ruleset_ht_key { struct net_device *dev; /* dev this ruleset is bound to */ bool ingress; + u32 chain_index; const struct mlxsw_sp_acl_profile_ops *ops; }; @@ -163,7 +164,8 @@ static void mlxsw_sp_acl_ruleset_destroy(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_ruleset *ruleset, - struct net_device *dev, bool ingress) + struct net_device *dev, bool ingress, + u32 chain_index) { const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; struct mlxsw_sp_acl *acl = mlxsw_sp->acl; @@ -171,13 +173,20 @@ static int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp, ruleset->ht_key.dev = dev; ruleset->ht_key.ingress = ingress; + ruleset->ht_key.chain_index = chain_index; err = rhashtable_insert_fast(&acl->ruleset_ht, &ruleset->ht_node, mlxsw_sp_acl_ruleset_ht_params); if (err) return err; - err = ops->ruleset_bind(mlxsw_sp, ruleset->priv, dev, ingress); - if (err) - goto err_ops_ruleset_bind; + if (!ruleset->ht_key.chain_index) { + /* We only need ruleset with chain index 0, the implicit one, + * to be directly bound to device. The rest of the rulesets + * are bound by "Goto action set". + */ + err = ops->ruleset_bind(mlxsw_sp, ruleset->priv, dev, ingress); + if (err) + goto err_ops_ruleset_bind; + } return 0; err_ops_ruleset_bind: @@ -192,7 +201,8 @@ static void mlxsw_sp_acl_ruleset_unbind(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; struct mlxsw_sp_acl *acl = mlxsw_sp->acl; - ops->ruleset_unbind(mlxsw_sp, ruleset->priv); + if (!ruleset->ht_key.chain_index) + ops->ruleset_unbind(mlxsw_sp, ruleset->priv); rhashtable_remove_fast(&acl->ruleset_ht, &ruleset->ht_node, mlxsw_sp_acl_ruleset_ht_params); } @@ -211,14 +221,48 @@ static void mlxsw_sp_acl_ruleset_ref_dec(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_ruleset_destroy(mlxsw_sp, ruleset); } +static struct mlxsw_sp_acl_ruleset * +__mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp_acl *acl, struct net_device *dev, + bool ingress, u32 chain_index, + const struct mlxsw_sp_acl_profile_ops *ops) +{ + struct mlxsw_sp_acl_ruleset_ht_key ht_key; + + memset(&ht_key, 0, sizeof(ht_key)); + ht_key.dev = dev; + ht_key.ingress = ingress; + ht_key.chain_index = chain_index; + ht_key.ops = ops; + return rhashtable_lookup_fast(&acl->ruleset_ht, &ht_key, + mlxsw_sp_acl_ruleset_ht_params); +} + struct mlxsw_sp_acl_ruleset * -mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp, - struct net_device *dev, bool ingress, +mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp, struct net_device *dev, + bool ingress, u32 chain_index, + enum mlxsw_sp_acl_profile profile) +{ + const struct mlxsw_sp_acl_profile_ops *ops; + struct mlxsw_sp_acl *acl = mlxsw_sp->acl; + struct mlxsw_sp_acl_ruleset *ruleset; + + ops = acl->ops->profile_ops(mlxsw_sp, profile); + if (!ops) + return ERR_PTR(-EINVAL); + ruleset = __mlxsw_sp_acl_ruleset_lookup(acl, dev, ingress, + chain_index, ops); + if (!ruleset) + return ERR_PTR(-ENOENT); + return ruleset; +} + +struct mlxsw_sp_acl_ruleset * +mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp, struct net_device *dev, + bool ingress, u32 chain_index, enum mlxsw_sp_acl_profile profile) { const struct mlxsw_sp_acl_profile_ops *ops; struct mlxsw_sp_acl *acl = mlxsw_sp->acl; - struct mlxsw_sp_acl_ruleset_ht_key ht_key; struct mlxsw_sp_acl_ruleset *ruleset; int err; @@ -226,12 +270,8 @@ mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp, if (!ops) return ERR_PTR(-EINVAL); - memset(&ht_key, 0, sizeof(ht_key)); - ht_key.dev = dev; - ht_key.ingress = ingress; - ht_key.ops = ops; - ruleset = rhashtable_lookup_fast(&acl->ruleset_ht, &ht_key, - mlxsw_sp_acl_ruleset_ht_params); + ruleset = __mlxsw_sp_acl_ruleset_lookup(acl, dev, ingress, + chain_index, ops); if (ruleset) { mlxsw_sp_acl_ruleset_ref_inc(ruleset); return ruleset; @@ -239,7 +279,8 @@ mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp, ruleset = mlxsw_sp_acl_ruleset_create(mlxsw_sp, ops); if (IS_ERR(ruleset)) return ruleset; - err = mlxsw_sp_acl_ruleset_bind(mlxsw_sp, ruleset, dev, ingress); + err = mlxsw_sp_acl_ruleset_bind(mlxsw_sp, ruleset, dev, + ingress, chain_index); if (err) goto err_ruleset_bind; return ruleset; @@ -255,6 +296,13 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_ruleset_ref_dec(mlxsw_sp, ruleset); } +u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset) +{ + const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + + return ops->ruleset_group_id(ruleset->priv); +} + static int mlxsw_sp_acl_rulei_counter_alloc(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei) @@ -369,7 +417,7 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp, local_port = mlxsw_sp_port->local_port; in_port = false; } else { - /* If out_dev is NULL, the called wants to + /* If out_dev is NULL, the caller wants to * set forward to ingress port. */ local_port = 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h index 85d5001a5818..fb8031828454 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h @@ -70,6 +70,9 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = { static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = { MLXSW_AFK_ELEMENT_INST_U32(SRC_IP4, 0x00, 0, 32), + MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 4, 2), + MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 24, 8), + MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x08, 0, 6), MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x08, 8, 9), /* TCP_CONTROL+TCP_ECN */ }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 61a10f166f97..50b40de1fb91 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -295,6 +295,12 @@ mlxsw_sp_acl_tcam_group_unbind(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ppbt), ppbt_pl); } +static u16 +mlxsw_sp_acl_tcam_group_id(struct mlxsw_sp_acl_tcam_group *group) +{ + return group->id; +} + static unsigned int mlxsw_sp_acl_tcam_region_prio(struct mlxsw_sp_acl_tcam_region *region) { @@ -984,6 +990,9 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_VID, MLXSW_AFK_ELEMENT_PCP, MLXSW_AFK_ELEMENT_TCP_FLAGS, + MLXSW_AFK_ELEMENT_IP_TTL_, + MLXSW_AFK_ELEMENT_IP_ECN, + MLXSW_AFK_ELEMENT_IP_DSCP, }; static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = { @@ -1060,6 +1069,14 @@ mlxsw_sp_acl_tcam_flower_ruleset_unbind(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_tcam_group_unbind(mlxsw_sp, &ruleset->group); } +static u16 +mlxsw_sp_acl_tcam_flower_ruleset_group_id(void *ruleset_priv) +{ + struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv; + + return mlxsw_sp_acl_tcam_group_id(&ruleset->group); +} + static int mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, @@ -1096,6 +1113,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { .ruleset_del = mlxsw_sp_acl_tcam_flower_ruleset_del, .ruleset_bind = mlxsw_sp_acl_tcam_flower_ruleset_bind, .ruleset_unbind = mlxsw_sp_acl_tcam_flower_ruleset_unbind, + .ruleset_group_id = mlxsw_sp_acl_tcam_flower_ruleset_group_id, .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_rule), .rule_add = mlxsw_sp_acl_tcam_flower_rule_add, .rule_del = mlxsw_sp_acl_tcam_flower_rule_del, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c index af2c65a3fd9f..51e6846da72b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c @@ -74,6 +74,9 @@ static struct devlink_dpipe_header mlxsw_sp_dpipe_header_metadata = { static struct devlink_dpipe_header *mlxsw_dpipe_headers[] = { &mlxsw_sp_dpipe_header_metadata, + &devlink_dpipe_header_ethernet, + &devlink_dpipe_header_ipv4, + &devlink_dpipe_header_ipv6, }; static struct devlink_dpipe_headers mlxsw_sp_dpipe_headers = { @@ -114,26 +117,6 @@ static int mlxsw_sp_dpipe_table_erif_matches_dump(void *priv, return devlink_dpipe_match_put(skb, &match); } -static void mlxsw_sp_erif_entry_clear(struct devlink_dpipe_entry *entry) -{ - unsigned int value_count, value_index; - struct devlink_dpipe_value *value; - - value = entry->action_values; - value_count = entry->action_values_count; - for (value_index = 0; value_index < value_count; value_index++) { - kfree(value[value_index].value); - kfree(value[value_index].mask); - } - - value = entry->match_values; - value_count = entry->match_values_count; - for (value_index = 0; value_index < value_count; value_index++) { - kfree(value[value_index].value); - kfree(value[value_index].mask); - } -} - static void mlxsw_sp_erif_match_action_prepare(struct devlink_dpipe_match *match, struct devlink_dpipe_action *action) @@ -215,8 +198,8 @@ static int mlxsw_sp_erif_entry_get(struct mlxsw_sp *mlxsw_sp, } static int -mlxsw_sp_table_erif_entries_dump(void *priv, bool counters_enabled, - struct devlink_dpipe_dump_ctx *dump_ctx) +mlxsw_sp_dpipe_table_erif_entries_dump(void *priv, bool counters_enabled, + struct devlink_dpipe_dump_ctx *dump_ctx) { struct devlink_dpipe_value match_value, action_value; struct devlink_dpipe_action action = {0}; @@ -270,16 +253,16 @@ start_again: goto start_again; rtnl_unlock(); - mlxsw_sp_erif_entry_clear(&entry); + devlink_dpipe_entry_clear(&entry); return 0; err_entry_append: err_entry_get: rtnl_unlock(); - mlxsw_sp_erif_entry_clear(&entry); + devlink_dpipe_entry_clear(&entry); return err; } -static int mlxsw_sp_table_erif_counters_update(void *priv, bool enable) +static int mlxsw_sp_dpipe_table_erif_counters_update(void *priv, bool enable) { struct mlxsw_sp *mlxsw_sp = priv; int i; @@ -301,24 +284,29 @@ static int mlxsw_sp_table_erif_counters_update(void *priv, bool enable) return 0; } +static u64 mlxsw_sp_dpipe_table_erif_size_get(void *priv) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + return MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); +} + static struct devlink_dpipe_table_ops mlxsw_sp_erif_ops = { .matches_dump = mlxsw_sp_dpipe_table_erif_matches_dump, .actions_dump = mlxsw_sp_dpipe_table_erif_actions_dump, - .entries_dump = mlxsw_sp_table_erif_entries_dump, - .counters_set_update = mlxsw_sp_table_erif_counters_update, + .entries_dump = mlxsw_sp_dpipe_table_erif_entries_dump, + .counters_set_update = mlxsw_sp_dpipe_table_erif_counters_update, + .size_get = mlxsw_sp_dpipe_table_erif_size_get, }; static int mlxsw_sp_dpipe_erif_table_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); - u64 table_size; - table_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); return devlink_dpipe_table_register(devlink, MLXSW_SP_DPIPE_TABLE_NAME_ERIF, &mlxsw_sp_erif_ops, - mlxsw_sp, table_size, - false); + mlxsw_sp, false); } static void mlxsw_sp_dpipe_erif_table_fini(struct mlxsw_sp *mlxsw_sp) @@ -328,6 +316,516 @@ static void mlxsw_sp_dpipe_erif_table_fini(struct mlxsw_sp *mlxsw_sp) devlink_dpipe_table_unregister(devlink, MLXSW_SP_DPIPE_TABLE_NAME_ERIF); } +static int mlxsw_sp_dpipe_table_host_matches_dump(struct sk_buff *skb, int type) +{ + struct devlink_dpipe_match match = {0}; + int err; + + match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match.header = &mlxsw_sp_dpipe_header_metadata; + match.field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT; + + err = devlink_dpipe_match_put(skb, &match); + if (err) + return err; + + switch (type) { + case AF_INET: + match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match.header = &devlink_dpipe_header_ipv4; + match.field_id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP; + break; + case AF_INET6: + match.type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match.header = &devlink_dpipe_header_ipv6; + match.field_id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP; + break; + default: + WARN_ON(1); + return -EINVAL; + } + + return devlink_dpipe_match_put(skb, &match); +} + +static int +mlxsw_sp_dpipe_table_host4_matches_dump(void *priv, struct sk_buff *skb) +{ + return mlxsw_sp_dpipe_table_host_matches_dump(skb, AF_INET); +} + +static int +mlxsw_sp_dpipe_table_host_actions_dump(void *priv, struct sk_buff *skb) +{ + struct devlink_dpipe_action action = {0}; + + action.type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY; + action.header = &devlink_dpipe_header_ethernet; + action.field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC; + + return devlink_dpipe_action_put(skb, &action); +} + +enum mlxsw_sp_dpipe_table_host_match { + MLXSW_SP_DPIPE_TABLE_HOST_MATCH_RIF, + MLXSW_SP_DPIPE_TABLE_HOST_MATCH_DIP, + MLXSW_SP_DPIPE_TABLE_HOST_MATCH_COUNT, +}; + +static void +mlxsw_sp_dpipe_table_host_match_action_prepare(struct devlink_dpipe_match *matches, + struct devlink_dpipe_action *action, + int type) +{ + struct devlink_dpipe_match *match; + + match = &matches[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_RIF]; + match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + match->header = &mlxsw_sp_dpipe_header_metadata; + match->field_id = MLXSW_SP_DPIPE_FIELD_METADATA_ERIF_PORT; + + match = &matches[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_DIP]; + match->type = DEVLINK_DPIPE_MATCH_TYPE_FIELD_EXACT; + switch (type) { + case AF_INET: + match->header = &devlink_dpipe_header_ipv4; + match->field_id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP; + break; + case AF_INET6: + match->header = &devlink_dpipe_header_ipv6; + match->field_id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP; + break; + default: + WARN_ON(1); + return; + } + + action->type = DEVLINK_DPIPE_ACTION_TYPE_FIELD_MODIFY; + action->header = &devlink_dpipe_header_ethernet; + action->field_id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC; +} + +static int +mlxsw_sp_dpipe_table_host_entry_prepare(struct devlink_dpipe_entry *entry, + struct devlink_dpipe_value *match_values, + struct devlink_dpipe_match *matches, + struct devlink_dpipe_value *action_value, + struct devlink_dpipe_action *action, + int type) +{ + struct devlink_dpipe_value *match_value; + struct devlink_dpipe_match *match; + + entry->match_values = match_values; + entry->match_values_count = MLXSW_SP_DPIPE_TABLE_HOST_MATCH_COUNT; + + entry->action_values = action_value; + entry->action_values_count = 1; + + match = &matches[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_RIF]; + match_value = &match_values[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_RIF]; + + match_value->match = match; + match_value->value_size = sizeof(u32); + match_value->value = kmalloc(match_value->value_size, GFP_KERNEL); + if (!match_value->value) + return -ENOMEM; + + match = &matches[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_DIP]; + match_value = &match_values[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_DIP]; + + match_value->match = match; + switch (type) { + case AF_INET: + match_value->value_size = sizeof(u32); + break; + case AF_INET6: + match_value->value_size = sizeof(struct in6_addr); + break; + default: + WARN_ON(1); + return -EINVAL; + } + + match_value->value = kmalloc(match_value->value_size, GFP_KERNEL); + if (!match_value->value) + return -ENOMEM; + + action_value->action = action; + action_value->value_size = sizeof(u64); + action_value->value = kmalloc(action_value->value_size, GFP_KERNEL); + if (!action_value->value) + return -ENOMEM; + + return 0; +} + +static void +__mlxsw_sp_dpipe_table_host_entry_fill(struct devlink_dpipe_entry *entry, + struct mlxsw_sp_rif *rif, + unsigned char *ha, void *dip) +{ + struct devlink_dpipe_value *value; + u32 *rif_value; + u8 *ha_value; + + /* Set Match RIF index */ + value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_RIF]; + + rif_value = value->value; + *rif_value = mlxsw_sp_rif_index(rif); + value->mapping_value = mlxsw_sp_rif_dev_ifindex(rif); + value->mapping_valid = true; + + /* Set Match DIP */ + value = &entry->match_values[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_DIP]; + memcpy(value->value, dip, value->value_size); + + /* Set Action DMAC */ + value = entry->action_values; + ha_value = value->value; + ether_addr_copy(ha_value, ha); +} + +static void +mlxsw_sp_dpipe_table_host4_entry_fill(struct devlink_dpipe_entry *entry, + struct mlxsw_sp_neigh_entry *neigh_entry, + struct mlxsw_sp_rif *rif) +{ + unsigned char *ha; + u32 dip; + + ha = mlxsw_sp_neigh_entry_ha(neigh_entry); + dip = mlxsw_sp_neigh4_entry_dip(neigh_entry); + __mlxsw_sp_dpipe_table_host_entry_fill(entry, rif, ha, &dip); +} + +static void +mlxsw_sp_dpipe_table_host6_entry_fill(struct devlink_dpipe_entry *entry, + struct mlxsw_sp_neigh_entry *neigh_entry, + struct mlxsw_sp_rif *rif) +{ + struct in6_addr *dip; + unsigned char *ha; + + ha = mlxsw_sp_neigh_entry_ha(neigh_entry); + dip = mlxsw_sp_neigh6_entry_dip(neigh_entry); + + __mlxsw_sp_dpipe_table_host_entry_fill(entry, rif, ha, dip); +} + +static void +mlxsw_sp_dpipe_table_host_entry_fill(struct mlxsw_sp *mlxsw_sp, + struct devlink_dpipe_entry *entry, + struct mlxsw_sp_neigh_entry *neigh_entry, + struct mlxsw_sp_rif *rif, + int type) +{ + int err; + + switch (type) { + case AF_INET: + mlxsw_sp_dpipe_table_host4_entry_fill(entry, neigh_entry, rif); + break; + case AF_INET6: + mlxsw_sp_dpipe_table_host6_entry_fill(entry, neigh_entry, rif); + break; + default: + WARN_ON(1); + return; + } + + err = mlxsw_sp_neigh_counter_get(mlxsw_sp, neigh_entry, + &entry->counter); + if (!err) + entry->counter_valid = true; +} + +static int +mlxsw_sp_dpipe_table_host_entries_get(struct mlxsw_sp *mlxsw_sp, + struct devlink_dpipe_entry *entry, + bool counters_enabled, + struct devlink_dpipe_dump_ctx *dump_ctx, + int type) +{ + int rif_neigh_count = 0; + int rif_neigh_skip = 0; + int neigh_count = 0; + int rif_count; + int i, j; + int err; + + rtnl_lock(); + i = 0; + rif_count = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); +start_again: + err = devlink_dpipe_entry_ctx_prepare(dump_ctx); + if (err) + goto err_ctx_prepare; + j = 0; + rif_neigh_skip = rif_neigh_count; + for (; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { + struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); + struct mlxsw_sp_neigh_entry *neigh_entry; + + if (!rif) + continue; + + rif_neigh_count = 0; + mlxsw_sp_rif_neigh_for_each(neigh_entry, rif) { + int neigh_type = mlxsw_sp_neigh_entry_type(neigh_entry); + + if (neigh_type != type) + continue; + + if (neigh_type == AF_INET6 && + mlxsw_sp_neigh_ipv6_ignore(neigh_entry)) + continue; + + if (rif_neigh_count < rif_neigh_skip) + goto skip; + + mlxsw_sp_dpipe_table_host_entry_fill(mlxsw_sp, entry, + neigh_entry, rif, + type); + entry->index = neigh_count; + err = devlink_dpipe_entry_ctx_append(dump_ctx, entry); + if (err) { + if (err == -EMSGSIZE) { + if (!j) + goto err_entry_append; + else + goto out; + } + goto err_entry_append; + } + neigh_count++; + j++; +skip: + rif_neigh_count++; + } + rif_neigh_skip = 0; + } +out: + devlink_dpipe_entry_ctx_close(dump_ctx); + if (i != rif_count) + goto start_again; + + rtnl_unlock(); + return 0; + +err_ctx_prepare: +err_entry_append: + rtnl_unlock(); + return err; +} + +static int +mlxsw_sp_dpipe_table_host_entries_dump(struct mlxsw_sp *mlxsw_sp, + bool counters_enabled, + struct devlink_dpipe_dump_ctx *dump_ctx, + int type) +{ + struct devlink_dpipe_value match_values[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_COUNT]; + struct devlink_dpipe_match matches[MLXSW_SP_DPIPE_TABLE_HOST_MATCH_COUNT]; + struct devlink_dpipe_value action_value; + struct devlink_dpipe_action action = {0}; + struct devlink_dpipe_entry entry = {0}; + int err; + + memset(matches, 0, MLXSW_SP_DPIPE_TABLE_HOST_MATCH_COUNT * + sizeof(matches[0])); + memset(match_values, 0, MLXSW_SP_DPIPE_TABLE_HOST_MATCH_COUNT * + sizeof(match_values[0])); + memset(&action_value, 0, sizeof(action_value)); + + mlxsw_sp_dpipe_table_host_match_action_prepare(matches, &action, type); + err = mlxsw_sp_dpipe_table_host_entry_prepare(&entry, match_values, + matches, &action_value, + &action, type); + if (err) + goto out; + + err = mlxsw_sp_dpipe_table_host_entries_get(mlxsw_sp, &entry, + counters_enabled, dump_ctx, + type); +out: + devlink_dpipe_entry_clear(&entry); + return err; +} + +static int +mlxsw_sp_dpipe_table_host4_entries_dump(void *priv, bool counters_enabled, + struct devlink_dpipe_dump_ctx *dump_ctx) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + return mlxsw_sp_dpipe_table_host_entries_dump(mlxsw_sp, + counters_enabled, + dump_ctx, AF_INET); +} + +static void +mlxsw_sp_dpipe_table_host_counters_update(struct mlxsw_sp *mlxsw_sp, + bool enable, int type) +{ + int i; + + rtnl_lock(); + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { + struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); + struct mlxsw_sp_neigh_entry *neigh_entry; + + if (!rif) + continue; + mlxsw_sp_rif_neigh_for_each(neigh_entry, rif) { + int neigh_type = mlxsw_sp_neigh_entry_type(neigh_entry); + + if (neigh_type != type) + continue; + + if (neigh_type == AF_INET6 && + mlxsw_sp_neigh_ipv6_ignore(neigh_entry)) + continue; + + mlxsw_sp_neigh_entry_counter_update(mlxsw_sp, + neigh_entry, + enable); + } + } + rtnl_unlock(); +} + +static int mlxsw_sp_dpipe_table_host4_counters_update(void *priv, bool enable) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + mlxsw_sp_dpipe_table_host_counters_update(mlxsw_sp, enable, AF_INET); + return 0; +} + +static u64 +mlxsw_sp_dpipe_table_host_size_get(struct mlxsw_sp *mlxsw_sp, int type) +{ + u64 size = 0; + int i; + + rtnl_lock(); + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) { + struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i); + struct mlxsw_sp_neigh_entry *neigh_entry; + + if (!rif) + continue; + mlxsw_sp_rif_neigh_for_each(neigh_entry, rif) { + int neigh_type = mlxsw_sp_neigh_entry_type(neigh_entry); + + if (neigh_type != type) + continue; + + if (neigh_type == AF_INET6 && + mlxsw_sp_neigh_ipv6_ignore(neigh_entry)) + continue; + + size++; + } + } + rtnl_unlock(); + + return size; +} + +static u64 mlxsw_sp_dpipe_table_host4_size_get(void *priv) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + return mlxsw_sp_dpipe_table_host_size_get(mlxsw_sp, AF_INET); +} + +static struct devlink_dpipe_table_ops mlxsw_sp_host4_ops = { + .matches_dump = mlxsw_sp_dpipe_table_host4_matches_dump, + .actions_dump = mlxsw_sp_dpipe_table_host_actions_dump, + .entries_dump = mlxsw_sp_dpipe_table_host4_entries_dump, + .counters_set_update = mlxsw_sp_dpipe_table_host4_counters_update, + .size_get = mlxsw_sp_dpipe_table_host4_size_get, +}; + +static int mlxsw_sp_dpipe_host4_table_init(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + return devlink_dpipe_table_register(devlink, + MLXSW_SP_DPIPE_TABLE_NAME_HOST4, + &mlxsw_sp_host4_ops, + mlxsw_sp, false); +} + +static void mlxsw_sp_dpipe_host4_table_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + devlink_dpipe_table_unregister(devlink, + MLXSW_SP_DPIPE_TABLE_NAME_HOST4); +} + +static int +mlxsw_sp_dpipe_table_host6_matches_dump(void *priv, struct sk_buff *skb) +{ + return mlxsw_sp_dpipe_table_host_matches_dump(skb, AF_INET6); +} + +static int +mlxsw_sp_dpipe_table_host6_entries_dump(void *priv, bool counters_enabled, + struct devlink_dpipe_dump_ctx *dump_ctx) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + return mlxsw_sp_dpipe_table_host_entries_dump(mlxsw_sp, + counters_enabled, + dump_ctx, AF_INET6); +} + +static int mlxsw_sp_dpipe_table_host6_counters_update(void *priv, bool enable) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + mlxsw_sp_dpipe_table_host_counters_update(mlxsw_sp, enable, AF_INET6); + return 0; +} + +static u64 mlxsw_sp_dpipe_table_host6_size_get(void *priv) +{ + struct mlxsw_sp *mlxsw_sp = priv; + + return mlxsw_sp_dpipe_table_host_size_get(mlxsw_sp, AF_INET6); +} + +static struct devlink_dpipe_table_ops mlxsw_sp_host6_ops = { + .matches_dump = mlxsw_sp_dpipe_table_host6_matches_dump, + .actions_dump = mlxsw_sp_dpipe_table_host_actions_dump, + .entries_dump = mlxsw_sp_dpipe_table_host6_entries_dump, + .counters_set_update = mlxsw_sp_dpipe_table_host6_counters_update, + .size_get = mlxsw_sp_dpipe_table_host6_size_get, +}; + +static int mlxsw_sp_dpipe_host6_table_init(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + return devlink_dpipe_table_register(devlink, + MLXSW_SP_DPIPE_TABLE_NAME_HOST6, + &mlxsw_sp_host6_ops, + mlxsw_sp, false); +} + +static void mlxsw_sp_dpipe_host6_table_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + devlink_dpipe_table_unregister(devlink, + MLXSW_SP_DPIPE_TABLE_NAME_HOST6); +} + int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); @@ -339,10 +837,22 @@ int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp) return err; err = mlxsw_sp_dpipe_erif_table_init(mlxsw_sp); if (err) - goto err_erif_register; + goto err_erif_table_init; + + err = mlxsw_sp_dpipe_host4_table_init(mlxsw_sp); + if (err) + goto err_host4_table_init; + + err = mlxsw_sp_dpipe_host6_table_init(mlxsw_sp); + if (err) + goto err_host6_table_init; return 0; -err_erif_register: +err_host6_table_init: + mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp); +err_host4_table_init: + mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp); +err_erif_table_init: devlink_dpipe_headers_unregister(priv_to_devlink(mlxsw_sp->core)); return err; } @@ -351,6 +861,8 @@ void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp) { struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + mlxsw_sp_dpipe_host6_table_fini(mlxsw_sp); + mlxsw_sp_dpipe_host4_table_fini(mlxsw_sp); mlxsw_sp_dpipe_erif_table_fini(mlxsw_sp); devlink_dpipe_headers_unregister(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h index d2089298cba3..283fde4e6783 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h @@ -35,9 +35,26 @@ #ifndef _MLXSW_PIPELINE_H_ #define _MLXSW_PIPELINE_H_ +#if IS_ENABLED(CONFIG_NET_DEVLINK) + int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp); +#else + +static inline int mlxsw_sp_dpipe_init(struct mlxsw_sp *mlxsw_sp) +{ + return 0; +} + +static inline void mlxsw_sp_dpipe_fini(struct mlxsw_sp *mlxsw_sp) +{ +} + +#endif + #define MLXSW_SP_DPIPE_TABLE_NAME_ERIF "mlxsw_erif" +#define MLXSW_SP_DPIPE_TABLE_NAME_HOST4 "mlxsw_host4" +#define MLXSW_SP_DPIPE_TABLE_NAME_HOST6 "mlxsw_host6" #endif /* _MLXSW_PIPELINE_H_*/ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c index 6afbe9ec64e2..bbd238e50f05 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c @@ -109,7 +109,6 @@ static const int mlxsw_sp_sfgc_uc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { static const int mlxsw_sp_sfgc_bc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { [MLXSW_REG_SFGC_TYPE_BROADCAST] = 1, - [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6] = 1, [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP] = 1, [MLXSW_REG_SFGC_TYPE_IPV4_LINK_LOCAL] = 1, [MLXSW_REG_SFGC_TYPE_IPV6_ALL_HOST] = 1, @@ -117,6 +116,7 @@ static const int mlxsw_sp_sfgc_bc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { static const int mlxsw_sp_sfgc_mc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = { [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4] = 1, + [MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6] = 1, }; static const int *mlxsw_sp_packet_type_sfgc_types[] = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 21bb2bf62d3e..8aace9a06a5d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -45,7 +45,7 @@ #include "core_acl_flex_keys.h" static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, - struct net_device *dev, + struct net_device *dev, bool ingress, struct mlxsw_sp_acl_rule_info *rulei, struct tcf_exts *exts) { @@ -53,7 +53,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, LIST_HEAD(actions); int err; - if (tc_no_actions(exts)) + if (!tcf_exts_has_actions(exts)) return 0; /* Count action is inserted first */ @@ -71,6 +71,20 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_acl_rulei_act_trap(rulei); if (err) return err; + } else if (is_tcf_gact_goto_chain(a)) { + u32 chain_index = tcf_gact_goto_chain_index(a); + struct mlxsw_sp_acl_ruleset *ruleset; + u16 group_id; + + ruleset = mlxsw_sp_acl_ruleset_lookup(mlxsw_sp, dev, + ingress, + chain_index, + MLXSW_SP_ACL_PROFILE_FLOWER); + if (IS_ERR(ruleset)) + return PTR_ERR(ruleset); + + group_id = mlxsw_sp_acl_ruleset_group_id(ruleset); + mlxsw_sp_acl_rulei_act_jump(rulei, group_id); } else if (is_tcf_mirred_egress_redirect(a)) { int ifindex = tcf_mirred_ifindex(a); struct net_device *out_dev; @@ -212,11 +226,46 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp, return 0; } +static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_rule_info *rulei, + struct tc_cls_flower_offload *f, + u16 n_proto) +{ + struct flow_dissector_key_ip *key, *mask; + + if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) + return 0; + + if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) { + dev_err(mlxsw_sp->bus_info->dev, "IP keys supported only for IPv4/6\n"); + return -EINVAL; + } + + key = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IP, + f->key); + mask = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_IP, + f->mask); + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_TTL_, + key->ttl, mask->ttl); + + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_ECN, + key->tos & 0x3, mask->tos & 0x3); + + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_DSCP, + key->tos >> 6, mask->tos >> 6); + + return 0; +} + static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, - struct net_device *dev, + struct net_device *dev, bool ingress, struct mlxsw_sp_acl_rule_info *rulei, struct tc_cls_flower_offload *f) { + u16 n_proto_mask = 0; + u16 n_proto_key = 0; u16 addr_type = 0; u8 ip_proto = 0; int err; @@ -229,12 +278,13 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | BIT(FLOW_DISSECTOR_KEY_PORTS) | BIT(FLOW_DISSECTOR_KEY_TCP) | + BIT(FLOW_DISSECTOR_KEY_IP) | BIT(FLOW_DISSECTOR_KEY_VLAN))) { dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n"); return -EOPNOTSUPP; } - mlxsw_sp_acl_rulei_priority(rulei, f->prio); + mlxsw_sp_acl_rulei_priority(rulei, f->common.prio); if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_dissector_key_control *key = @@ -253,8 +303,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_BASIC, f->mask); - u16 n_proto_key = ntohs(key->n_proto); - u16 n_proto_mask = ntohs(mask->n_proto); + n_proto_key = ntohs(key->n_proto); + n_proto_mask = ntohs(mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; @@ -324,11 +374,16 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, if (err) return err; - return mlxsw_sp_flower_parse_actions(mlxsw_sp, dev, rulei, f->exts); + err = mlxsw_sp_flower_parse_ip(mlxsw_sp, rulei, f, n_proto_key & n_proto_mask); + if (err) + return err; + + return mlxsw_sp_flower_parse_actions(mlxsw_sp, dev, ingress, + rulei, f->exts); } int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, - __be16 protocol, struct tc_cls_flower_offload *f) + struct tc_cls_flower_offload *f) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct net_device *dev = mlxsw_sp_port->dev; @@ -338,6 +393,7 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, int err; ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, dev, ingress, + f->common.chain_index, MLXSW_SP_ACL_PROFILE_FLOWER); if (IS_ERR(ruleset)) return PTR_ERR(ruleset); @@ -349,7 +405,7 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, } rulei = mlxsw_sp_acl_rule_rulei(rule); - err = mlxsw_sp_flower_parse(mlxsw_sp, dev, rulei, f); + err = mlxsw_sp_flower_parse(mlxsw_sp, dev, ingress, rulei, f); if (err) goto err_flower_parse; @@ -381,7 +437,7 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, struct mlxsw_sp_acl_rule *rule; ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev, - ingress, + ingress, f->common.chain_index, MLXSW_SP_ACL_PROFILE_FLOWER); if (IS_ERR(ruleset)) return; @@ -407,7 +463,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress, int err; ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, mlxsw_sp_port->dev, - ingress, + ingress, f->common.chain_index, MLXSW_SP_ACL_PROFILE_FLOWER); if (WARN_ON(IS_ERR(ruleset))) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c new file mode 100644 index 000000000000..702fe945227c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -0,0 +1,214 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <net/ip_tunnels.h> + +#include "spectrum_ipip.h" + +static bool +mlxsw_sp_ipip_netdev_has_ikey(const struct net_device *ol_dev) +{ + struct ip_tunnel *tun = netdev_priv(ol_dev); + + return !!(tun->parms.i_flags & TUNNEL_KEY); +} + +static bool +mlxsw_sp_ipip_netdev_has_okey(const struct net_device *ol_dev) +{ + struct ip_tunnel *tun = netdev_priv(ol_dev); + + return !!(tun->parms.o_flags & TUNNEL_KEY); +} + +static u32 mlxsw_sp_ipip_netdev_ikey(const struct net_device *ol_dev) +{ + struct ip_tunnel *tun = netdev_priv(ol_dev); + + return mlxsw_sp_ipip_netdev_has_ikey(ol_dev) ? + be32_to_cpu(tun->parms.i_key) : 0; +} + +static u32 mlxsw_sp_ipip_netdev_okey(const struct net_device *ol_dev) +{ + struct ip_tunnel *tun = netdev_priv(ol_dev); + + return mlxsw_sp_ipip_netdev_has_okey(ol_dev) ? + be32_to_cpu(tun->parms.o_key) : 0; +} + +static int +mlxsw_sp_ipip_nexthop_update_gre4(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); + __be32 daddr4 = mlxsw_sp_ipip_netdev_daddr4(ipip_entry->ol_dev); + char ratr_pl[MLXSW_REG_RATR_LEN]; + + mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, + true, MLXSW_REG_RATR_TYPE_IPIP, + adj_index, rif_index); + mlxsw_reg_ratr_ipip4_entry_pack(ratr_pl, be32_to_cpu(daddr4)); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); +} + +static int +mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp, + u32 tunnel_index, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + bool has_ikey = mlxsw_sp_ipip_netdev_has_ikey(ipip_entry->ol_dev); + u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); + u32 ikey = mlxsw_sp_ipip_netdev_ikey(ipip_entry->ol_dev); + char rtdp_pl[MLXSW_REG_RTDP_LEN]; + unsigned int type_check; + u32 daddr4; + + mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index); + + type_check = has_ikey ? + MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY : + MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE; + + /* Linux demuxes tunnels based on packet SIP (which must match tunnel + * remote IP). Thus configure decap so that it filters out packets that + * are not IPv4 or have the wrong SIP. IPIP_DECAP_ERROR trap is + * generated for packets that fail this criterion. Linux then handles + * such packets in slow path and generates ICMP destination unreachable. + */ + daddr4 = be32_to_cpu(mlxsw_sp_ipip_netdev_daddr4(ipip_entry->ol_dev)); + mlxsw_reg_rtdp_ipip4_pack(rtdp_pl, rif_index, + MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV4, + type_check, has_ikey, daddr4, ikey); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl); +} + +static int +mlxsw_sp_ipip_fib_entry_op_gre4_ralue(struct mlxsw_sp *mlxsw_sp, + u32 dip, u8 prefix_len, u16 ul_vr_id, + enum mlxsw_reg_ralue_op op, + u32 tunnel_index) +{ + char ralue_pl[MLXSW_REG_RALUE_LEN]; + + mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_REG_RALXX_PROTOCOL_IPV4, op, + ul_vr_id, prefix_len, dip); + mlxsw_reg_ralue_act_ip2me_tun_pack(ralue_pl, tunnel_index); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); +} + +static int mlxsw_sp_ipip_fib_entry_op_gre4(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + enum mlxsw_reg_ralue_op op, + u32 tunnel_index) +{ + u16 ul_vr_id = mlxsw_sp_ipip_lb_ul_vr_id(ipip_entry->ol_lb); + __be32 dip; + int err; + + err = mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(mlxsw_sp, tunnel_index, + ipip_entry); + if (err) + return err; + + dip = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4, + ipip_entry->ol_dev).addr4; + return mlxsw_sp_ipip_fib_entry_op_gre4_ralue(mlxsw_sp, be32_to_cpu(dip), + 32, ul_vr_id, op, + tunnel_index); +} + +static bool mlxsw_sp_ipip_tunnel_complete(enum mlxsw_sp_l3proto proto, + const struct net_device *ol_dev) +{ + union mlxsw_sp_l3addr saddr = mlxsw_sp_ipip_netdev_saddr(proto, ol_dev); + union mlxsw_sp_l3addr daddr = mlxsw_sp_ipip_netdev_daddr(proto, ol_dev); + union mlxsw_sp_l3addr naddr = {0}; + + /* Tunnels with unset local or remote address are valid in Linux and + * used for lightweight tunnels (LWT) and Non-Broadcast Multi-Access + * (NBMA) tunnels. In principle these can be offloaded, but the driver + * currently doesn't support this. So punt. + */ + return memcmp(&saddr, &naddr, sizeof(naddr)) && + memcmp(&daddr, &naddr, sizeof(naddr)); +} + +static bool mlxsw_sp_ipip_can_offload_gre4(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev, + enum mlxsw_sp_l3proto ol_proto) +{ + struct ip_tunnel *tunnel = netdev_priv(ol_dev); + __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ + bool inherit_ttl = tunnel->parms.iph.ttl == 0; + bool inherit_tos = tunnel->parms.iph.tos & 0x1; + + return (tunnel->parms.i_flags & ~okflags) == 0 && + (tunnel->parms.o_flags & ~okflags) == 0 && + inherit_ttl && inherit_tos && + mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV4, ol_dev); +} + +static struct mlxsw_sp_rif_ipip_lb_config +mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; + + lb_ipipt = mlxsw_sp_ipip_netdev_has_okey(ol_dev) ? + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP : + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP; + return (struct mlxsw_sp_rif_ipip_lb_config){ + .lb_ipipt = lb_ipipt, + .okey = mlxsw_sp_ipip_netdev_okey(ol_dev), + .ul_protocol = MLXSW_SP_L3_PROTO_IPV4, + .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4, + ol_dev), + }; +} + +static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = { + .dev_type = ARPHRD_IPGRE, + .ul_proto = MLXSW_SP_L3_PROTO_IPV4, + .nexthop_update = mlxsw_sp_ipip_nexthop_update_gre4, + .fib_entry_op = mlxsw_sp_ipip_fib_entry_op_gre4, + .can_offload = mlxsw_sp_ipip_can_offload_gre4, + .ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre4, +}; + +const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[] = { + [MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops, +}; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h new file mode 100644 index 000000000000..1c2db831d83b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -0,0 +1,79 @@ +/* + * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h + * Copyright (c) 2017 Mellanox Technologies. All rights reserved. + * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _MLXSW_IPIP_H_ +#define _MLXSW_IPIP_H_ + +#include "spectrum_router.h" +#include <net/ip_fib.h> + +enum mlxsw_sp_ipip_type { + MLXSW_SP_IPIP_TYPE_GRE4, + MLXSW_SP_IPIP_TYPE_MAX, +}; + +struct mlxsw_sp_ipip_entry { + enum mlxsw_sp_ipip_type ipipt; + struct net_device *ol_dev; /* Overlay. */ + struct mlxsw_sp_rif_ipip_lb *ol_lb; + unsigned int ref_count; /* Number of next hops using the tunnel. */ + struct mlxsw_sp_fib_entry *decap_fib_entry; + struct list_head ipip_list_node; +}; + +struct mlxsw_sp_ipip_ops { + int dev_type; + enum mlxsw_sp_l3proto ul_proto; /* Underlay. */ + + int (*nexthop_update)(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_ipip_entry *ipip_entry); + + bool (*can_offload)(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev, + enum mlxsw_sp_l3proto ol_proto); + + /* Return a configuration for creating an overlay loopback RIF. */ + struct mlxsw_sp_rif_ipip_lb_config + (*ol_loopback_config)(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev); + + int (*fib_entry_op)(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + enum mlxsw_reg_ralue_op op, + u32 tunnel_index); +}; + +extern const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[]; + +#endif /* _MLXSW_IPIP_H_*/ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4b2e0fd7d51e..f0fb898533fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1,9 +1,10 @@ /* * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016-2017 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com> * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com> + * Copyright (c) 2017 Petr Machata <petrm@mellanox.com> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: @@ -43,18 +44,27 @@ #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_bridge.h> +#include <linux/socket.h> +#include <linux/route.h> #include <net/netevent.h> #include <net/neighbour.h> #include <net/arp.h> #include <net/ip_fib.h> +#include <net/ip6_fib.h> #include <net/fib_rules.h> +#include <net/ip_tunnels.h> #include <net/l3mdev.h> +#include <net/addrconf.h> +#include <net/ndisc.h> +#include <net/ipv6.h> +#include <net/fib_notifier.h> #include "spectrum.h" #include "core.h" #include "reg.h" #include "spectrum_cnt.h" #include "spectrum_dpipe.h" +#include "spectrum_ipip.h" #include "spectrum_router.h" struct mlxsw_sp_vr; @@ -79,9 +89,11 @@ struct mlxsw_sp_router { struct delayed_work nexthop_probe_dw; #define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */ struct list_head nexthop_neighs_list; + struct list_head ipip_list; bool aborted; struct notifier_block fib_nb; const struct mlxsw_sp_rif_ops **rif_ops_arr; + const struct mlxsw_sp_ipip_ops **ipip_ops_arr; }; struct mlxsw_sp_rif { @@ -122,6 +134,17 @@ struct mlxsw_sp_rif_subport { bool lag; }; +struct mlxsw_sp_rif_ipip_lb { + struct mlxsw_sp_rif common; + struct mlxsw_sp_rif_ipip_lb_config lb_config; + u16 ul_vr_id; /* Reserved for Spectrum-2. */ +}; + +struct mlxsw_sp_rif_params_ipip_lb { + struct mlxsw_sp_rif_params common; + struct mlxsw_sp_rif_ipip_lb_config lb_config; +}; + struct mlxsw_sp_rif_ops { enum mlxsw_sp_rif_type type; size_t rif_size; @@ -304,7 +327,7 @@ static struct mlxsw_sp_rif * mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp, const struct net_device *dev); -#define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE) +#define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE + 1) struct mlxsw_sp_prefix_usage { DECLARE_BITMAP(b, MLXSW_SP_PREFIX_COUNT); @@ -314,19 +337,6 @@ struct mlxsw_sp_prefix_usage { for_each_set_bit(prefix, (prefix_usage)->b, MLXSW_SP_PREFIX_COUNT) static bool -mlxsw_sp_prefix_usage_subset(struct mlxsw_sp_prefix_usage *prefix_usage1, - struct mlxsw_sp_prefix_usage *prefix_usage2) -{ - unsigned char prefix; - - mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage1) { - if (!test_bit(prefix, prefix_usage2->b)) - return false; - } - return true; -} - -static bool mlxsw_sp_prefix_usage_eq(struct mlxsw_sp_prefix_usage *prefix_usage1, struct mlxsw_sp_prefix_usage *prefix_usage2) { @@ -371,6 +381,14 @@ enum mlxsw_sp_fib_entry_type { MLXSW_SP_FIB_ENTRY_TYPE_REMOTE, MLXSW_SP_FIB_ENTRY_TYPE_LOCAL, MLXSW_SP_FIB_ENTRY_TYPE_TRAP, + + /* This is a special case of local delivery, where a packet should be + * decapsulated on reception. Note that there is no corresponding ENCAP, + * because that's a type of next hop, not of FIB entry. (There can be + * several next hops in a REMOTE entry, and some of them may be + * encapsulating entries.) + */ + MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP, }; struct mlxsw_sp_nexthop_group; @@ -384,11 +402,9 @@ struct mlxsw_sp_fib_node { struct mlxsw_sp_fib_key key; }; -struct mlxsw_sp_fib_entry_params { - u32 tb_id; - u32 prio; - u8 tos; - u8 type; +struct mlxsw_sp_fib_entry_decap { + struct mlxsw_sp_ipip_entry *ipip_entry; + u32 tunnel_index; }; struct mlxsw_sp_fib_entry { @@ -397,13 +413,26 @@ struct mlxsw_sp_fib_entry { enum mlxsw_sp_fib_entry_type type; struct list_head nexthop_group_node; struct mlxsw_sp_nexthop_group *nh_group; - struct mlxsw_sp_fib_entry_params params; - bool offloaded; + struct mlxsw_sp_fib_entry_decap decap; /* Valid for decap entries. */ +}; + +struct mlxsw_sp_fib4_entry { + struct mlxsw_sp_fib_entry common; + u32 tb_id; + u32 prio; + u8 tos; + u8 type; +}; + +struct mlxsw_sp_fib6_entry { + struct mlxsw_sp_fib_entry common; + struct list_head rt6_list; + unsigned int nrt6; }; -enum mlxsw_sp_l3proto { - MLXSW_SP_L3_PROTO_IPV4, - MLXSW_SP_L3_PROTO_IPV6, +struct mlxsw_sp_rt6 { + struct list_head list; + struct rt6_info *rt; }; struct mlxsw_sp_lpm_tree { @@ -428,6 +457,7 @@ struct mlxsw_sp_vr { u32 tb_id; /* kernel fib table id */ unsigned int rif_count; struct mlxsw_sp_fib *fib4; + struct mlxsw_sp_fib *fib6; }; static const struct rhashtable_params mlxsw_sp_fib_ht_params; @@ -487,15 +517,15 @@ static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); } -static int mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_lpm_tree *lpm_tree) +static void mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree) { char ralta_pl[MLXSW_REG_RALTA_LEN]; mlxsw_reg_ralta_pack(ralta_pl, false, (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, lpm_tree->id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); } static int @@ -551,10 +581,10 @@ err_left_struct_set: return ERR_PTR(err); } -static int mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_lpm_tree *lpm_tree) +static void mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree) { - return mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); + mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); } static struct mlxsw_sp_lpm_tree * @@ -571,24 +601,21 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, lpm_tree->proto == proto && mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage, prefix_usage)) - goto inc_ref_count; + return lpm_tree; } - lpm_tree = mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, - proto); - if (IS_ERR(lpm_tree)) - return lpm_tree; + return mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, proto); +} -inc_ref_count: +static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) +{ lpm_tree->ref_count++; - return lpm_tree; } -static int mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_lpm_tree *lpm_tree) +static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_lpm_tree *lpm_tree) { if (--lpm_tree->ref_count == 0) - return mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); - return 0; + mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); } #define MLXSW_SP_LPM_TREE_MIN 1 /* tree 0 is reserved */ @@ -625,7 +652,7 @@ static void mlxsw_sp_lpm_fini(struct mlxsw_sp *mlxsw_sp) static bool mlxsw_sp_vr_is_used(const struct mlxsw_sp_vr *vr) { - return !!vr->fib4; + return !!vr->fib4 || !!vr->fib6; } static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) @@ -642,13 +669,13 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) } static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_fib *fib) + const struct mlxsw_sp_fib *fib, u8 tree_id) { char raltb_pl[MLXSW_REG_RALTB_LEN]; mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, (enum mlxsw_reg_ralxx_protocol) fib->proto, - fib->lpm_tree->id); + tree_id); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } @@ -694,7 +721,7 @@ static struct mlxsw_sp_fib *mlxsw_sp_vr_fib(const struct mlxsw_sp_vr *vr, case MLXSW_SP_L3_PROTO_IPV4: return vr->fib4; case MLXSW_SP_L3_PROTO_IPV6: - BUG_ON(1); + return vr->fib6; } return NULL; } @@ -703,6 +730,7 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, u32 tb_id) { struct mlxsw_sp_vr *vr; + int err; vr = mlxsw_sp_vr_find_unused(mlxsw_sp); if (!vr) @@ -710,54 +738,26 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_create(struct mlxsw_sp *mlxsw_sp, vr->fib4 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV4); if (IS_ERR(vr->fib4)) return ERR_CAST(vr->fib4); + vr->fib6 = mlxsw_sp_fib_create(vr, MLXSW_SP_L3_PROTO_IPV6); + if (IS_ERR(vr->fib6)) { + err = PTR_ERR(vr->fib6); + goto err_fib6_create; + } vr->tb_id = tb_id; return vr; -} -static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) -{ +err_fib6_create: mlxsw_sp_fib_destroy(vr->fib4); vr->fib4 = NULL; + return ERR_PTR(err); } -static int -mlxsw_sp_vr_lpm_tree_check(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib *fib, - struct mlxsw_sp_prefix_usage *req_prefix_usage) +static void mlxsw_sp_vr_destroy(struct mlxsw_sp_vr *vr) { - struct mlxsw_sp_lpm_tree *lpm_tree = fib->lpm_tree; - struct mlxsw_sp_lpm_tree *new_tree; - int err; - - if (mlxsw_sp_prefix_usage_eq(req_prefix_usage, &lpm_tree->prefix_usage)) - return 0; - - new_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, req_prefix_usage, - fib->proto); - if (IS_ERR(new_tree)) { - /* We failed to get a tree according to the required - * prefix usage. However, the current tree might be still good - * for us if our requirement is subset of the prefixes used - * in the tree. - */ - if (mlxsw_sp_prefix_usage_subset(req_prefix_usage, - &lpm_tree->prefix_usage)) - return 0; - return PTR_ERR(new_tree); - } - - /* Prevent packet loss by overwriting existing binding */ - fib->lpm_tree = new_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); - if (err) - goto err_tree_bind; - mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); - - return 0; - -err_tree_bind: - fib->lpm_tree = lpm_tree; - mlxsw_sp_lpm_tree_put(mlxsw_sp, new_tree); - return err; + mlxsw_sp_fib_destroy(vr->fib6); + vr->fib6 = NULL; + mlxsw_sp_fib_destroy(vr->fib4); + vr->fib4 = NULL; } static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) @@ -773,10 +773,105 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id) static void mlxsw_sp_vr_put(struct mlxsw_sp_vr *vr) { - if (!vr->rif_count && list_empty(&vr->fib4->node_list)) + if (!vr->rif_count && list_empty(&vr->fib4->node_list) && + list_empty(&vr->fib6->node_list)) mlxsw_sp_vr_destroy(vr); } +static bool +mlxsw_sp_vr_lpm_tree_should_replace(struct mlxsw_sp_vr *vr, + enum mlxsw_sp_l3proto proto, u8 tree_id) +{ + struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto); + + if (!mlxsw_sp_vr_is_used(vr)) + return false; + if (fib->lpm_tree && fib->lpm_tree->id == tree_id) + return true; + return false; +} + +static int mlxsw_sp_vr_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib *fib, + struct mlxsw_sp_lpm_tree *new_tree) +{ + struct mlxsw_sp_lpm_tree *old_tree = fib->lpm_tree; + int err; + + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, new_tree->id); + if (err) + return err; + fib->lpm_tree = new_tree; + mlxsw_sp_lpm_tree_hold(new_tree); + mlxsw_sp_lpm_tree_put(mlxsw_sp, old_tree); + return 0; +} + +static int mlxsw_sp_vrs_lpm_tree_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib *fib, + struct mlxsw_sp_lpm_tree *new_tree) +{ + struct mlxsw_sp_lpm_tree *old_tree = fib->lpm_tree; + enum mlxsw_sp_l3proto proto = fib->proto; + u8 old_id, new_id = new_tree->id; + struct mlxsw_sp_vr *vr; + int i, err; + + if (!old_tree) + goto no_replace; + old_id = old_tree->id; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + vr = &mlxsw_sp->router->vrs[i]; + if (!mlxsw_sp_vr_lpm_tree_should_replace(vr, proto, old_id)) + continue; + err = mlxsw_sp_vr_lpm_tree_replace(mlxsw_sp, + mlxsw_sp_vr_fib(vr, proto), + new_tree); + if (err) + goto err_tree_replace; + } + + return 0; + +err_tree_replace: + for (i--; i >= 0; i--) { + if (!mlxsw_sp_vr_lpm_tree_should_replace(vr, proto, new_id)) + continue; + mlxsw_sp_vr_lpm_tree_replace(mlxsw_sp, + mlxsw_sp_vr_fib(vr, proto), + old_tree); + } + return err; + +no_replace: + err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, new_tree->id); + if (err) + return err; + fib->lpm_tree = new_tree; + mlxsw_sp_lpm_tree_hold(new_tree); + return 0; +} + +static void +mlxsw_sp_vrs_prefixes(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_l3proto proto, + struct mlxsw_sp_prefix_usage *req_prefix_usage) +{ + int i; + + for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { + struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i]; + struct mlxsw_sp_fib *fib = mlxsw_sp_vr_fib(vr, proto); + unsigned char prefix; + + if (!mlxsw_sp_vr_is_used(vr)) + continue; + mlxsw_sp_prefix_usage_for_each(prefix, &fib->prefix_usage) + mlxsw_sp_prefix_usage_set(req_prefix_usage, prefix); + } +} + static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_vr *vr; @@ -816,6 +911,374 @@ static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->router->vrs); } +static struct net_device * +__mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev) +{ + struct ip_tunnel *tun = netdev_priv(ol_dev); + struct net *net = dev_net(ol_dev); + + return __dev_get_by_index(net, tun->parms.link); +} + +static u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) +{ + struct net_device *d = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + + if (d) + return l3mdev_fib_table(d) ? : RT_TABLE_MAIN; + else + return l3mdev_fib_table(ol_dev) ? : RT_TABLE_MAIN; +} + +static struct mlxsw_sp_rif * +mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_rif_params *params); + +static struct mlxsw_sp_rif_ipip_lb * +mlxsw_sp_ipip_ol_ipip_lb_create(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt, + struct net_device *ol_dev) +{ + struct mlxsw_sp_rif_params_ipip_lb lb_params; + const struct mlxsw_sp_ipip_ops *ipip_ops; + struct mlxsw_sp_rif *rif; + + ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; + lb_params = (struct mlxsw_sp_rif_params_ipip_lb) { + .common.dev = ol_dev, + .common.lag = false, + .lb_config = ipip_ops->ol_loopback_config(mlxsw_sp, ol_dev), + }; + + rif = mlxsw_sp_rif_create(mlxsw_sp, &lb_params.common); + if (IS_ERR(rif)) + return ERR_CAST(rif); + return container_of(rif, struct mlxsw_sp_rif_ipip_lb, common); +} + +static struct mlxsw_sp_ipip_entry * +mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt, + struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + struct mlxsw_sp_ipip_entry *ret = NULL; + + ipip_entry = kzalloc(sizeof(*ipip_entry), GFP_KERNEL); + if (!ipip_entry) + return ERR_PTR(-ENOMEM); + + ipip_entry->ol_lb = mlxsw_sp_ipip_ol_ipip_lb_create(mlxsw_sp, ipipt, + ol_dev); + if (IS_ERR(ipip_entry->ol_lb)) { + ret = ERR_CAST(ipip_entry->ol_lb); + goto err_ol_ipip_lb_create; + } + + ipip_entry->ipipt = ipipt; + ipip_entry->ol_dev = ol_dev; + + return ipip_entry; + +err_ol_ipip_lb_create: + kfree(ipip_entry); + return ret; +} + +static void +mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp_ipip_entry *ipip_entry) +{ + WARN_ON(ipip_entry->ref_count > 0); + mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); + kfree(ipip_entry); +} + +static __be32 +mlxsw_sp_ipip_netdev_saddr4(const struct net_device *ol_dev) +{ + struct ip_tunnel *tun = netdev_priv(ol_dev); + + return tun->parms.iph.saddr; +} + +union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, + const struct net_device *ol_dev) +{ + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return (union mlxsw_sp_l3addr) { + .addr4 = mlxsw_sp_ipip_netdev_saddr4(ol_dev), + }; + case MLXSW_SP_L3_PROTO_IPV6: + break; + }; + + WARN_ON(1); + return (union mlxsw_sp_l3addr) { + .addr4 = 0, + }; +} + +__be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) +{ + struct ip_tunnel *tun = netdev_priv(ol_dev); + + return tun->parms.iph.daddr; +} + +union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, + const struct net_device *ol_dev) +{ + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return (union mlxsw_sp_l3addr) { + .addr4 = mlxsw_sp_ipip_netdev_daddr4(ol_dev), + }; + case MLXSW_SP_L3_PROTO_IPV6: + break; + }; + + WARN_ON(1); + return (union mlxsw_sp_l3addr) { + .addr4 = 0, + }; +} + +static bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1, + const union mlxsw_sp_l3addr *addr2) +{ + return !memcmp(addr1, addr2, sizeof(*addr1)); +} + +static bool +mlxsw_sp_ipip_entry_saddr_matches(struct mlxsw_sp *mlxsw_sp, + const enum mlxsw_sp_l3proto ul_proto, + union mlxsw_sp_l3addr saddr, + u32 ul_tb_id, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + u32 tun_ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ipip_entry->ol_dev); + enum mlxsw_sp_ipip_type ipipt = ipip_entry->ipipt; + union mlxsw_sp_l3addr tun_saddr; + + if (mlxsw_sp->router->ipip_ops_arr[ipipt]->ul_proto != ul_proto) + return false; + + tun_saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ipip_entry->ol_dev); + return tun_ul_tb_id == ul_tb_id && + mlxsw_sp_l3addr_eq(&tun_saddr, &saddr); +} + +static int +mlxsw_sp_fib_entry_decap_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + u32 tunnel_index; + int err; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &tunnel_index); + if (err) + return err; + + ipip_entry->decap_fib_entry = fib_entry; + fib_entry->decap.ipip_entry = ipip_entry; + fib_entry->decap.tunnel_index = tunnel_index; + return 0; +} + +static void mlxsw_sp_fib_entry_decap_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ + /* Unlink this node from the IPIP entry that it's the decap entry of. */ + fib_entry->decap.ipip_entry->decap_fib_entry = NULL; + fib_entry->decap.ipip_entry = NULL; + mlxsw_sp_kvdl_free(mlxsw_sp, fib_entry->decap.tunnel_index); +} + +static struct mlxsw_sp_fib_node * +mlxsw_sp_fib_node_lookup(struct mlxsw_sp_fib *fib, const void *addr, + size_t addr_len, unsigned char prefix_len); +static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry); + +static void +mlxsw_sp_ipip_entry_demote_decap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + struct mlxsw_sp_fib_entry *fib_entry = ipip_entry->decap_fib_entry; + + mlxsw_sp_fib_entry_decap_fini(mlxsw_sp, fib_entry); + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + + mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); +} + +static void +mlxsw_sp_ipip_entry_promote_decap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct mlxsw_sp_fib_entry *decap_fib_entry) +{ + if (mlxsw_sp_fib_entry_decap_init(mlxsw_sp, decap_fib_entry, + ipip_entry)) + return; + decap_fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP; + + if (mlxsw_sp_fib_entry_update(mlxsw_sp, decap_fib_entry)) + mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); +} + +/* Given an IPIP entry, find the corresponding decap route. */ +static struct mlxsw_sp_fib_entry * +mlxsw_sp_ipip_entry_find_decap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + static struct mlxsw_sp_fib_node *fib_node; + const struct mlxsw_sp_ipip_ops *ipip_ops; + struct mlxsw_sp_fib_entry *fib_entry; + unsigned char saddr_prefix_len; + union mlxsw_sp_l3addr saddr; + struct mlxsw_sp_fib *ul_fib; + struct mlxsw_sp_vr *ul_vr; + const void *saddrp; + size_t saddr_len; + u32 ul_tb_id; + u32 saddr4; + + ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]; + + ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ipip_entry->ol_dev); + ul_vr = mlxsw_sp_vr_find(mlxsw_sp, ul_tb_id); + if (!ul_vr) + return NULL; + + ul_fib = mlxsw_sp_vr_fib(ul_vr, ipip_ops->ul_proto); + saddr = mlxsw_sp_ipip_netdev_saddr(ipip_ops->ul_proto, + ipip_entry->ol_dev); + + switch (ipip_ops->ul_proto) { + case MLXSW_SP_L3_PROTO_IPV4: + saddr4 = be32_to_cpu(saddr.addr4); + saddrp = &saddr4; + saddr_len = 4; + saddr_prefix_len = 32; + break; + case MLXSW_SP_L3_PROTO_IPV6: + WARN_ON(1); + return NULL; + } + + fib_node = mlxsw_sp_fib_node_lookup(ul_fib, saddrp, saddr_len, + saddr_prefix_len); + if (!fib_node || list_empty(&fib_node->entry_list)) + return NULL; + + fib_entry = list_first_entry(&fib_node->entry_list, + struct mlxsw_sp_fib_entry, list); + if (fib_entry->type != MLXSW_SP_FIB_ENTRY_TYPE_TRAP) + return NULL; + + return fib_entry; +} + +static struct mlxsw_sp_ipip_entry * +mlxsw_sp_ipip_entry_get(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt, + struct net_device *ol_dev) +{ + u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ol_dev); + struct mlxsw_sp_router *router = mlxsw_sp->router; + struct mlxsw_sp_fib_entry *decap_fib_entry; + struct mlxsw_sp_ipip_entry *ipip_entry; + enum mlxsw_sp_l3proto ul_proto; + union mlxsw_sp_l3addr saddr; + + list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list, + ipip_list_node) { + if (ipip_entry->ol_dev == ol_dev) + goto inc_ref_count; + + /* The configuration where several tunnels have the same local + * address in the same underlay table needs special treatment in + * the HW. That is currently not implemented in the driver. + */ + ul_proto = router->ipip_ops_arr[ipip_entry->ipipt]->ul_proto; + saddr = mlxsw_sp_ipip_netdev_saddr(ul_proto, ol_dev); + if (mlxsw_sp_ipip_entry_saddr_matches(mlxsw_sp, ul_proto, saddr, + ul_tb_id, ipip_entry)) + return ERR_PTR(-EEXIST); + } + + ipip_entry = mlxsw_sp_ipip_entry_alloc(mlxsw_sp, ipipt, ol_dev); + if (IS_ERR(ipip_entry)) + return ipip_entry; + + decap_fib_entry = mlxsw_sp_ipip_entry_find_decap(mlxsw_sp, ipip_entry); + if (decap_fib_entry) + mlxsw_sp_ipip_entry_promote_decap(mlxsw_sp, ipip_entry, + decap_fib_entry); + + list_add_tail(&ipip_entry->ipip_list_node, + &mlxsw_sp->router->ipip_list); + +inc_ref_count: + ++ipip_entry->ref_count; + return ipip_entry; +} + +static void +mlxsw_sp_ipip_entry_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + if (--ipip_entry->ref_count == 0) { + list_del(&ipip_entry->ipip_list_node); + if (ipip_entry->decap_fib_entry) + mlxsw_sp_ipip_entry_demote_decap(mlxsw_sp, ipip_entry); + mlxsw_sp_ipip_entry_destroy(ipip_entry); + } +} + +static bool +mlxsw_sp_ipip_entry_matches_decap(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ul_dev, + enum mlxsw_sp_l3proto ul_proto, + union mlxsw_sp_l3addr ul_dip, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + u32 ul_tb_id = l3mdev_fib_table(ul_dev) ? : RT_TABLE_MAIN; + enum mlxsw_sp_ipip_type ipipt = ipip_entry->ipipt; + struct net_device *ipip_ul_dev; + + if (mlxsw_sp->router->ipip_ops_arr[ipipt]->ul_proto != ul_proto) + return false; + + ipip_ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ipip_entry->ol_dev); + return mlxsw_sp_ipip_entry_saddr_matches(mlxsw_sp, ul_proto, ul_dip, + ul_tb_id, ipip_entry) && + (!ipip_ul_dev || ipip_ul_dev == ul_dev); +} + +/* Given decap parameters, find the corresponding IPIP entry. */ +static struct mlxsw_sp_ipip_entry * +mlxsw_sp_ipip_entry_find_by_decap(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ul_dev, + enum mlxsw_sp_l3proto ul_proto, + union mlxsw_sp_l3addr ul_dip) +{ + struct mlxsw_sp_ipip_entry *ipip_entry; + + list_for_each_entry(ipip_entry, &mlxsw_sp->router->ipip_list, + ipip_list_node) + if (mlxsw_sp_ipip_entry_matches_decap(mlxsw_sp, ul_dev, + ul_proto, ul_dip, + ipip_entry)) + return ipip_entry; + + return NULL; +} + struct mlxsw_sp_neigh_key { struct neighbour *n; }; @@ -831,6 +1294,8 @@ struct mlxsw_sp_neigh_entry { * this neigh entry */ struct list_head nexthop_neighs_list_node; + unsigned int counter_index; + bool counter_valid; }; static const struct rhashtable_params mlxsw_sp_neigh_ht_params = { @@ -839,6 +1304,62 @@ static const struct rhashtable_params mlxsw_sp_neigh_ht_params = { .key_len = sizeof(struct mlxsw_sp_neigh_key), }; +struct mlxsw_sp_neigh_entry * +mlxsw_sp_rif_neigh_next(struct mlxsw_sp_rif *rif, + struct mlxsw_sp_neigh_entry *neigh_entry) +{ + if (!neigh_entry) { + if (list_empty(&rif->neigh_list)) + return NULL; + else + return list_first_entry(&rif->neigh_list, + typeof(*neigh_entry), + rif_list_node); + } + if (neigh_entry->rif_list_node.next == &rif->neigh_list) + return NULL; + return list_next_entry(neigh_entry, rif_list_node); +} + +int mlxsw_sp_neigh_entry_type(struct mlxsw_sp_neigh_entry *neigh_entry) +{ + return neigh_entry->key.n->tbl->family; +} + +unsigned char * +mlxsw_sp_neigh_entry_ha(struct mlxsw_sp_neigh_entry *neigh_entry) +{ + return neigh_entry->ha; +} + +u32 mlxsw_sp_neigh4_entry_dip(struct mlxsw_sp_neigh_entry *neigh_entry) +{ + struct neighbour *n; + + n = neigh_entry->key.n; + return ntohl(*((__be32 *) n->primary_key)); +} + +struct in6_addr * +mlxsw_sp_neigh6_entry_dip(struct mlxsw_sp_neigh_entry *neigh_entry) +{ + struct neighbour *n; + + n = neigh_entry->key.n; + return (struct in6_addr *) &n->primary_key; +} + +int mlxsw_sp_neigh_counter_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry, + u64 *p_counter) +{ + if (!neigh_entry->counter_valid) + return -EINVAL; + + return mlxsw_sp_flow_counter_get(mlxsw_sp, neigh_entry->counter_index, + p_counter, NULL); +} + static struct mlxsw_sp_neigh_entry * mlxsw_sp_neigh_entry_alloc(struct mlxsw_sp *mlxsw_sp, struct neighbour *n, u16 rif) @@ -879,6 +1400,53 @@ mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_neigh_ht_params); } +static bool +mlxsw_sp_neigh_counter_should_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry) +{ + struct devlink *devlink; + const char *table_name; + + switch (mlxsw_sp_neigh_entry_type(neigh_entry)) { + case AF_INET: + table_name = MLXSW_SP_DPIPE_TABLE_NAME_HOST4; + break; + case AF_INET6: + table_name = MLXSW_SP_DPIPE_TABLE_NAME_HOST6; + break; + default: + WARN_ON(1); + return false; + } + + devlink = priv_to_devlink(mlxsw_sp->core); + return devlink_dpipe_table_counter_enabled(devlink, table_name); +} + +static void +mlxsw_sp_neigh_counter_alloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry) +{ + if (!mlxsw_sp_neigh_counter_should_alloc(mlxsw_sp, neigh_entry)) + return; + + if (mlxsw_sp_flow_counter_alloc(mlxsw_sp, &neigh_entry->counter_index)) + return; + + neigh_entry->counter_valid = true; +} + +static void +mlxsw_sp_neigh_counter_free(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry) +{ + if (!neigh_entry->counter_valid) + return; + mlxsw_sp_flow_counter_free(mlxsw_sp, + neigh_entry->counter_index); + neigh_entry->counter_valid = false; +} + static struct mlxsw_sp_neigh_entry * mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) { @@ -898,6 +1466,7 @@ mlxsw_sp_neigh_entry_create(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) if (err) goto err_neigh_entry_insert; + mlxsw_sp_neigh_counter_alloc(mlxsw_sp, neigh_entry); list_add(&neigh_entry->rif_list_node, &rif->neigh_list); return neigh_entry; @@ -912,6 +1481,7 @@ mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_neigh_entry *neigh_entry) { list_del(&neigh_entry->rif_list_node); + mlxsw_sp_neigh_counter_free(mlxsw_sp, neigh_entry); mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry); mlxsw_sp_neigh_entry_free(neigh_entry); } @@ -929,8 +1499,15 @@ mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) static void mlxsw_sp_router_neighs_update_interval_init(struct mlxsw_sp *mlxsw_sp) { - unsigned long interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME); + unsigned long interval; +#if IS_ENABLED(CONFIG_IPV6) + interval = min_t(unsigned long, + NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME), + NEIGH_VAR(&nd_tbl.parms, DELAY_PROBE_TIME)); +#else + interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME); +#endif mlxsw_sp->router->neighs_update.interval = jiffies_to_msecs(interval); } @@ -965,6 +1542,44 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, neigh_release(n); } +#if IS_ENABLED(CONFIG_IPV6) +static void mlxsw_sp_router_neigh_ent_ipv6_process(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, + int rec_index) +{ + struct net_device *dev; + struct neighbour *n; + struct in6_addr dip; + u16 rif; + + mlxsw_reg_rauhtd_ent_ipv6_unpack(rauhtd_pl, rec_index, &rif, + (char *) &dip); + + if (!mlxsw_sp->router->rifs[rif]) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n"); + return; + } + + dev = mlxsw_sp->router->rifs[rif]->dev; + n = neigh_lookup(&nd_tbl, &dip, dev); + if (!n) { + netdev_err(dev, "Failed to find matching neighbour for IP=%pI6c\n", + &dip); + return; + } + + netdev_dbg(dev, "Updating neighbour with IP=%pI6c\n", &dip); + neigh_event_send(n, NULL); + neigh_release(n); +} +#else +static void mlxsw_sp_router_neigh_ent_ipv6_process(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, + int rec_index) +{ +} +#endif + static void mlxsw_sp_router_neigh_rec_ipv4_process(struct mlxsw_sp *mlxsw_sp, char *rauhtd_pl, int rec_index) @@ -988,6 +1603,15 @@ static void mlxsw_sp_router_neigh_rec_ipv4_process(struct mlxsw_sp *mlxsw_sp, } +static void mlxsw_sp_router_neigh_rec_ipv6_process(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, + int rec_index) +{ + /* One record contains one entry. */ + mlxsw_sp_router_neigh_ent_ipv6_process(mlxsw_sp, rauhtd_pl, + rec_index); +} + static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp, char *rauhtd_pl, int rec_index) { @@ -997,7 +1621,8 @@ static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp, rec_index); break; case MLXSW_REG_RAUHTD_TYPE_IPV6: - WARN_ON_ONCE(1); + mlxsw_sp_router_neigh_rec_ipv6_process(mlxsw_sp, rauhtd_pl, + rec_index); break; } } @@ -1022,22 +1647,20 @@ static bool mlxsw_sp_router_rauhtd_is_full(char *rauhtd_pl) return false; } -static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) +static int +__mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp, + char *rauhtd_pl, + enum mlxsw_reg_rauhtd_type type) { - char *rauhtd_pl; - u8 num_rec; - int i, err; - - rauhtd_pl = kmalloc(MLXSW_REG_RAUHTD_LEN, GFP_KERNEL); - if (!rauhtd_pl) - return -ENOMEM; + int i, num_rec; + int err; /* Make sure the neighbour's netdev isn't removed in the * process. */ rtnl_lock(); do { - mlxsw_reg_rauhtd_pack(rauhtd_pl, MLXSW_REG_RAUHTD_TYPE_IPV4); + mlxsw_reg_rauhtd_pack(rauhtd_pl, type); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(rauhtd), rauhtd_pl); if (err) { @@ -1051,6 +1674,27 @@ static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) } while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl)); rtnl_unlock(); + return err; +} + +static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) +{ + enum mlxsw_reg_rauhtd_type type; + char *rauhtd_pl; + int err; + + rauhtd_pl = kmalloc(MLXSW_REG_RAUHTD_LEN, GFP_KERNEL); + if (!rauhtd_pl) + return -ENOMEM; + + type = MLXSW_REG_RAUHTD_TYPE_IPV4; + err = __mlxsw_sp_router_neighs_update_rauhtd(mlxsw_sp, rauhtd_pl, type); + if (err) + goto out; + + type = MLXSW_REG_RAUHTD_TYPE_IPV6; + err = __mlxsw_sp_router_neighs_update_rauhtd(mlxsw_sp, rauhtd_pl, type); +out: kfree(rauhtd_pl); return err; } @@ -1143,9 +1787,43 @@ mlxsw_sp_router_neigh_entry_op4(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_rauht_pack4(rauht_pl, op, neigh_entry->rif, neigh_entry->ha, dip); + if (neigh_entry->counter_valid) + mlxsw_reg_rauht_pack_counter(rauht_pl, + neigh_entry->counter_index); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); +} + +static void +mlxsw_sp_router_neigh_entry_op6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry, + enum mlxsw_reg_rauht_op op) +{ + struct neighbour *n = neigh_entry->key.n; + char rauht_pl[MLXSW_REG_RAUHT_LEN]; + const char *dip = n->primary_key; + + mlxsw_reg_rauht_pack6(rauht_pl, op, neigh_entry->rif, neigh_entry->ha, + dip); + if (neigh_entry->counter_valid) + mlxsw_reg_rauht_pack_counter(rauht_pl, + neigh_entry->counter_index); mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); } +bool mlxsw_sp_neigh_ipv6_ignore(struct mlxsw_sp_neigh_entry *neigh_entry) +{ + struct neighbour *n = neigh_entry->key.n; + + /* Packets with a link-local destination address are trapped + * after LPM lookup and never reach the neighbour table, so + * there is no need to program such neighbours to the device. + */ + if (ipv6_addr_type((struct in6_addr *) &n->primary_key) & + IPV6_ADDR_LINKLOCAL) + return true; + return false; +} + static void mlxsw_sp_neigh_entry_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_neigh_entry *neigh_entry, @@ -1154,11 +1832,29 @@ mlxsw_sp_neigh_entry_update(struct mlxsw_sp *mlxsw_sp, if (!adding && !neigh_entry->connected) return; neigh_entry->connected = adding; - if (neigh_entry->key.n->tbl == &arp_tbl) + if (neigh_entry->key.n->tbl->family == AF_INET) { mlxsw_sp_router_neigh_entry_op4(mlxsw_sp, neigh_entry, mlxsw_sp_rauht_op(adding)); - else + } else if (neigh_entry->key.n->tbl->family == AF_INET6) { + if (mlxsw_sp_neigh_ipv6_ignore(neigh_entry)) + return; + mlxsw_sp_router_neigh_entry_op6(mlxsw_sp, neigh_entry, + mlxsw_sp_rauht_op(adding)); + } else { WARN_ON_ONCE(1); + } +} + +void +mlxsw_sp_neigh_entry_counter_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry, + bool adding) +{ + if (adding) + mlxsw_sp_neigh_counter_alloc(mlxsw_sp, neigh_entry); + else + mlxsw_sp_neigh_counter_free(mlxsw_sp, neigh_entry); + mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, true); } struct mlxsw_sp_neigh_event_work { @@ -1227,7 +1923,8 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused, p = ptr; /* We don't care about changes in the default table. */ - if (!p->dev || p->tbl != &arp_tbl) + if (!p->dev || (p->tbl->family != AF_INET && + p->tbl->family != AF_INET6)) return NOTIFY_DONE; /* We are in atomic context and can't take RTNL mutex, @@ -1246,7 +1943,7 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused, case NETEVENT_NEIGH_UPDATE: n = ptr; - if (n->tbl != &arp_tbl) + if (n->tbl->family != AF_INET && n->tbl->family != AF_INET6) return NOTIFY_DONE; mlxsw_sp_port = mlxsw_sp_port_lower_dev_hold(n->dev); @@ -1307,27 +2004,23 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp) rhashtable_destroy(&mlxsw_sp->router->neigh_ht); } -static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif *rif) -{ - char rauht_pl[MLXSW_REG_RAUHT_LEN]; - - mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL, - rif->rif_index, rif->addr); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); -} - static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif) { struct mlxsw_sp_neigh_entry *neigh_entry, *tmp; - mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif); list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list, - rif_list_node) + rif_list_node) { + mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, false); mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); + } } +enum mlxsw_sp_nexthop_type { + MLXSW_SP_NEXTHOP_TYPE_ETH, + MLXSW_SP_NEXTHOP_TYPE_IPIP, +}; + struct mlxsw_sp_nexthop_key { struct fib_nh *fib_nh; }; @@ -1340,6 +2033,8 @@ struct mlxsw_sp_nexthop { */ struct rhash_head ht_node; struct mlxsw_sp_nexthop_key key; + unsigned char gw_addr[sizeof(struct in6_addr)]; + int ifindex; struct mlxsw_sp_rif *rif; u8 should_offload:1, /* set indicates this neigh is connected and * should be put to KVD linear area of this group. @@ -1350,17 +2045,18 @@ struct mlxsw_sp_nexthop { update:1; /* set indicates that MAC of this neigh should be * updated in HW */ - struct mlxsw_sp_neigh_entry *neigh_entry; -}; - -struct mlxsw_sp_nexthop_group_key { - struct fib_info *fi; + enum mlxsw_sp_nexthop_type type; + union { + struct mlxsw_sp_neigh_entry *neigh_entry; + struct mlxsw_sp_ipip_entry *ipip_entry; + }; }; struct mlxsw_sp_nexthop_group { + void *priv; struct rhash_head ht_node; struct list_head fib_list; /* list of fib entries that use this group */ - struct mlxsw_sp_nexthop_group_key key; + struct neigh_table *neigh_tbl; u8 adj_index_valid:1, gateway:1; /* routes using the group use a gateway */ u32 adj_index; @@ -1370,15 +2066,154 @@ struct mlxsw_sp_nexthop_group { #define nh_rif nexthops[0].rif }; +static struct fib_info * +mlxsw_sp_nexthop4_group_fi(const struct mlxsw_sp_nexthop_group *nh_grp) +{ + return nh_grp->priv; +} + +struct mlxsw_sp_nexthop_group_cmp_arg { + enum mlxsw_sp_l3proto proto; + union { + struct fib_info *fi; + struct mlxsw_sp_fib6_entry *fib6_entry; + }; +}; + +static bool +mlxsw_sp_nexthop6_group_has_nexthop(const struct mlxsw_sp_nexthop_group *nh_grp, + const struct in6_addr *gw, int ifindex) +{ + int i; + + for (i = 0; i < nh_grp->count; i++) { + const struct mlxsw_sp_nexthop *nh; + + nh = &nh_grp->nexthops[i]; + if (nh->ifindex == ifindex && + ipv6_addr_equal(gw, (struct in6_addr *) nh->gw_addr)) + return true; + } + + return false; +} + +static bool +mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp, + const struct mlxsw_sp_fib6_entry *fib6_entry) +{ + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + + if (nh_grp->count != fib6_entry->nrt6) + return false; + + list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { + struct in6_addr *gw; + int ifindex; + + ifindex = mlxsw_sp_rt6->rt->dst.dev->ifindex; + gw = &mlxsw_sp_rt6->rt->rt6i_gateway; + if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex)) + return false; + } + + return true; +} + +static int +mlxsw_sp_nexthop_group_cmp(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct mlxsw_sp_nexthop_group_cmp_arg *cmp_arg = arg->key; + const struct mlxsw_sp_nexthop_group *nh_grp = ptr; + + switch (cmp_arg->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return cmp_arg->fi != mlxsw_sp_nexthop4_group_fi(nh_grp); + case MLXSW_SP_L3_PROTO_IPV6: + return !mlxsw_sp_nexthop6_group_cmp(nh_grp, + cmp_arg->fib6_entry); + default: + WARN_ON(1); + return 1; + } +} + +static int +mlxsw_sp_nexthop_group_type(const struct mlxsw_sp_nexthop_group *nh_grp) +{ + return nh_grp->neigh_tbl->family; +} + +static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct mlxsw_sp_nexthop_group *nh_grp = data; + const struct mlxsw_sp_nexthop *nh; + struct fib_info *fi; + unsigned int val; + int i; + + switch (mlxsw_sp_nexthop_group_type(nh_grp)) { + case AF_INET: + fi = mlxsw_sp_nexthop4_group_fi(nh_grp); + return jhash(&fi, sizeof(fi), seed); + case AF_INET6: + val = nh_grp->count; + for (i = 0; i < nh_grp->count; i++) { + nh = &nh_grp->nexthops[i]; + val ^= nh->ifindex; + } + return jhash(&val, sizeof(val), seed); + default: + WARN_ON(1); + return 0; + } +} + +static u32 +mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed) +{ + unsigned int val = fib6_entry->nrt6; + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + struct net_device *dev; + + list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { + dev = mlxsw_sp_rt6->rt->dst.dev; + val ^= dev->ifindex; + } + + return jhash(&val, sizeof(val), seed); +} + +static u32 +mlxsw_sp_nexthop_group_hash(const void *data, u32 len, u32 seed) +{ + const struct mlxsw_sp_nexthop_group_cmp_arg *cmp_arg = data; + + switch (cmp_arg->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return jhash(&cmp_arg->fi, sizeof(cmp_arg->fi), seed); + case MLXSW_SP_L3_PROTO_IPV6: + return mlxsw_sp_nexthop6_group_hash(cmp_arg->fib6_entry, seed); + default: + WARN_ON(1); + return 0; + } +} + static const struct rhashtable_params mlxsw_sp_nexthop_group_ht_params = { - .key_offset = offsetof(struct mlxsw_sp_nexthop_group, key), .head_offset = offsetof(struct mlxsw_sp_nexthop_group, ht_node), - .key_len = sizeof(struct mlxsw_sp_nexthop_group_key), + .hashfn = mlxsw_sp_nexthop_group_hash, + .obj_hashfn = mlxsw_sp_nexthop_group_hash_obj, + .obj_cmpfn = mlxsw_sp_nexthop_group_cmp, }; static int mlxsw_sp_nexthop_group_insert(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { + if (mlxsw_sp_nexthop_group_type(nh_grp) == AF_INET6 && + !nh_grp->gateway) + return 0; + return rhashtable_insert_fast(&mlxsw_sp->router->nexthop_group_ht, &nh_grp->ht_node, mlxsw_sp_nexthop_group_ht_params); @@ -1387,16 +2222,38 @@ static int mlxsw_sp_nexthop_group_insert(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_nexthop_group_remove(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { + if (mlxsw_sp_nexthop_group_type(nh_grp) == AF_INET6 && + !nh_grp->gateway) + return; + rhashtable_remove_fast(&mlxsw_sp->router->nexthop_group_ht, &nh_grp->ht_node, mlxsw_sp_nexthop_group_ht_params); } static struct mlxsw_sp_nexthop_group * -mlxsw_sp_nexthop_group_lookup(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group_key key) +mlxsw_sp_nexthop4_group_lookup(struct mlxsw_sp *mlxsw_sp, + struct fib_info *fi) +{ + struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg; + + cmp_arg.proto = MLXSW_SP_L3_PROTO_IPV4; + cmp_arg.fi = fi; + return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht, + &cmp_arg, + mlxsw_sp_nexthop_group_ht_params); +} + +static struct mlxsw_sp_nexthop_group * +mlxsw_sp_nexthop6_group_lookup(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) { - return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht, &key, + struct mlxsw_sp_nexthop_group_cmp_arg cmp_arg; + + cmp_arg.proto = MLXSW_SP_L3_PROTO_IPV6; + cmp_arg.fib6_entry = fib6_entry; + return rhashtable_lookup_fast(&mlxsw_sp->router->nexthop_group_ht, + &cmp_arg, mlxsw_sp_nexthop_group_ht_params); } @@ -1473,15 +2330,26 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index, char ratr_pl[MLXSW_REG_RATR_LEN]; mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, - true, adj_index, neigh_entry->rif); + true, MLXSW_REG_RATR_TYPE_ETHERNET, + adj_index, neigh_entry->rif); mlxsw_reg_ratr_eth_entry_pack(ratr_pl, neigh_entry->ha); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); } +static int mlxsw_sp_nexthop_ipip_update(struct mlxsw_sp *mlxsw_sp, + u32 adj_index, + struct mlxsw_sp_nexthop *nh) +{ + const struct mlxsw_sp_ipip_ops *ipip_ops; + + ipip_ops = mlxsw_sp->router->ipip_ops_arr[nh->ipip_entry->ipipt]; + return ipip_ops->nexthop_update(mlxsw_sp, adj_index, nh->ipip_entry); +} + static int -mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp, - bool reallocate) +mlxsw_sp_nexthop_group_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + bool reallocate) { u32 adj_index = nh_grp->adj_index; /* base */ struct mlxsw_sp_nexthop *nh; @@ -1497,8 +2365,16 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, } if (nh->update || reallocate) { - err = mlxsw_sp_nexthop_mac_update(mlxsw_sp, - adj_index, nh); + switch (nh->type) { + case MLXSW_SP_NEXTHOP_TYPE_ETH: + err = mlxsw_sp_nexthop_mac_update + (mlxsw_sp, adj_index, nh); + break; + case MLXSW_SP_NEXTHOP_TYPE_IPIP: + err = mlxsw_sp_nexthop_ipip_update + (mlxsw_sp, adj_index, nh); + break; + } if (err) return err; nh->update = 0; @@ -1509,9 +2385,6 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp, return 0; } -static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry); - static bool mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node, const struct mlxsw_sp_fib_entry *fib_entry); @@ -1535,6 +2408,24 @@ mlxsw_sp_nexthop_fib_entries_update(struct mlxsw_sp *mlxsw_sp, } static void +mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op, int err); + +static void +mlxsw_sp_nexthop_fib_entries_refresh(struct mlxsw_sp_nexthop_group *nh_grp) +{ + enum mlxsw_reg_ralue_op op = MLXSW_REG_RALUE_OP_WRITE_WRITE; + struct mlxsw_sp_fib_entry *fib_entry; + + list_for_each_entry(fib_entry, &nh_grp->fib_list, nexthop_group_node) { + if (!mlxsw_sp_fib_node_entry_is_first(fib_entry->fib_node, + fib_entry)) + continue; + mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, 0); + } +} + +static void mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp) { @@ -1556,7 +2447,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; - if (nh->should_offload ^ nh->offloaded) { + if (nh->should_offload != nh->offloaded) { offload_change = true; if (nh->should_offload) nh->update = 1; @@ -1568,8 +2459,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, /* Nothing was added or removed, so no need to reallocate. Just * update MAC on existing adjacency indexes. */ - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, - false); + err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, false); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; @@ -1596,7 +2486,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, nh_grp->adj_index_valid = 1; nh_grp->adj_index = adj_index; nh_grp->ecmp_size = ecmp_size; - err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true); + err = mlxsw_sp_nexthop_group_update(mlxsw_sp, nh_grp, true); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n"); goto set_trap; @@ -1621,6 +2511,10 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n"); goto set_trap; } + + /* Offload state within the group changed, so update the flags. */ + mlxsw_sp_nexthop_fib_entries_refresh(nh_grp); + return; set_trap: @@ -1640,9 +2534,9 @@ set_trap: static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh, bool removing) { - if (!removing && !nh->should_offload) + if (!removing) nh->should_offload = 1; - else if (removing && nh->offloaded) + else if (nh->offloaded) nh->should_offload = 0; nh->update = 1; } @@ -1684,7 +2578,6 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh) { struct mlxsw_sp_neigh_entry *neigh_entry; - struct fib_nh *fib_nh = nh->key.fib_nh; struct neighbour *n; u8 nud_state, dead; int err; @@ -1693,13 +2586,14 @@ static int mlxsw_sp_nexthop_neigh_init(struct mlxsw_sp *mlxsw_sp, return 0; /* Take a reference of neigh here ensuring that neigh would - * not be detructed before the nexthop entry is finished. + * not be destructed before the nexthop entry is finished. * The reference is taken either in neigh_lookup() or * in neigh_create() in case n is not found. */ - n = neigh_lookup(&arp_tbl, &fib_nh->nh_gw, fib_nh->nh_dev); + n = neigh_lookup(nh->nh_grp->neigh_tbl, &nh->gw_addr, nh->rif->dev); if (!n) { - n = neigh_create(&arp_tbl, &fib_nh->nh_gw, fib_nh->nh_dev); + n = neigh_create(nh->nh_grp->neigh_tbl, &nh->gw_addr, + nh->rif->dev); if (IS_ERR(n)) return PTR_ERR(n); neigh_event_send(n, NULL); @@ -1761,18 +2655,131 @@ static void mlxsw_sp_nexthop_neigh_fini(struct mlxsw_sp *mlxsw_sp, neigh_release(n); } -static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp, - struct mlxsw_sp_nexthop *nh, - struct fib_nh *fib_nh) +static bool mlxsw_sp_netdev_ipip_type(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *dev, + enum mlxsw_sp_ipip_type *p_type) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + const struct mlxsw_sp_ipip_ops *ipip_ops; + enum mlxsw_sp_ipip_type ipipt; + + for (ipipt = 0; ipipt < MLXSW_SP_IPIP_TYPE_MAX; ++ipipt) { + ipip_ops = router->ipip_ops_arr[ipipt]; + if (dev->type == ipip_ops->dev_type) { + if (p_type) + *p_type = ipipt; + return true; + } + } + return false; +} + +static int mlxsw_sp_nexthop_ipip_init(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt, + struct mlxsw_sp_nexthop *nh, + struct net_device *ol_dev) +{ + if (!nh->nh_grp->gateway || nh->ipip_entry) + return 0; + + nh->ipip_entry = mlxsw_sp_ipip_entry_get(mlxsw_sp, ipipt, ol_dev); + if (IS_ERR(nh->ipip_entry)) + return PTR_ERR(nh->ipip_entry); + + __mlxsw_sp_nexthop_neigh_update(nh, false); + return 0; +} + +static void mlxsw_sp_nexthop_ipip_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + struct mlxsw_sp_ipip_entry *ipip_entry = nh->ipip_entry; + + if (!ipip_entry) + return; + + __mlxsw_sp_nexthop_neigh_update(nh, true); + mlxsw_sp_ipip_entry_put(mlxsw_sp, ipip_entry); + nh->ipip_entry = NULL; +} + +static bool mlxsw_sp_nexthop4_ipip_type(const struct mlxsw_sp *mlxsw_sp, + const struct fib_nh *fib_nh, + enum mlxsw_sp_ipip_type *p_ipipt) { struct net_device *dev = fib_nh->nh_dev; - struct in_device *in_dev; + + return dev && + fib_nh->nh_parent->fib_type == RTN_UNICAST && + mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, p_ipipt); +} + +static void mlxsw_sp_nexthop_type_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + switch (nh->type) { + case MLXSW_SP_NEXTHOP_TYPE_ETH: + mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh); + mlxsw_sp_nexthop_rif_fini(nh); + break; + case MLXSW_SP_NEXTHOP_TYPE_IPIP: + mlxsw_sp_nexthop_ipip_fini(mlxsw_sp, nh); + break; + } +} + +static int mlxsw_sp_nexthop4_type_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh, + struct fib_nh *fib_nh) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + struct net_device *dev = fib_nh->nh_dev; + enum mlxsw_sp_ipip_type ipipt; struct mlxsw_sp_rif *rif; int err; + if (mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, fib_nh, &ipipt) && + router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, + MLXSW_SP_L3_PROTO_IPV4)) { + nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; + return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + } + + nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) + return 0; + + mlxsw_sp_nexthop_rif_init(nh, rif); + err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); + if (err) + goto err_neigh_init; + + return 0; + +err_neigh_init: + mlxsw_sp_nexthop_rif_fini(nh); + return err; +} + +static void mlxsw_sp_nexthop4_type_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); +} + +static int mlxsw_sp_nexthop4_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop *nh, + struct fib_nh *fib_nh) +{ + struct net_device *dev = fib_nh->nh_dev; + struct in_device *in_dev; + int err; + nh->nh_grp = nh_grp; nh->key.fib_nh = fib_nh; + memcpy(&nh->gw_addr, &fib_nh->nh_gw, sizeof(fib_nh->nh_gw)); err = mlxsw_sp_nexthop_insert(mlxsw_sp, nh); if (err) return err; @@ -1785,37 +2792,29 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, fib_nh->nh_flags & RTNH_F_LINKDOWN) return 0; - rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!rif) - return 0; - mlxsw_sp_nexthop_rif_init(nh, rif); - - err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); + err = mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh); if (err) goto err_nexthop_neigh_init; return 0; err_nexthop_neigh_init: - mlxsw_sp_nexthop_rif_fini(nh); mlxsw_sp_nexthop_remove(mlxsw_sp, nh); return err; } -static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop *nh) +static void mlxsw_sp_nexthop4_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) { - mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh); - mlxsw_sp_nexthop_rif_fini(nh); + mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh); mlxsw_sp_nexthop_remove(mlxsw_sp, nh); } -static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, - unsigned long event, struct fib_nh *fib_nh) +static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp, + unsigned long event, struct fib_nh *fib_nh) { struct mlxsw_sp_nexthop_key key; struct mlxsw_sp_nexthop *nh; - struct mlxsw_sp_rif *rif; if (mlxsw_sp->router->aborted) return; @@ -1825,18 +2824,12 @@ static void mlxsw_sp_nexthop_event(struct mlxsw_sp *mlxsw_sp, if (WARN_ON_ONCE(!nh)) return; - rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, fib_nh->nh_dev); - if (!rif) - return; - switch (event) { case FIB_EVENT_NH_ADD: - mlxsw_sp_nexthop_rif_init(nh, rif); - mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); + mlxsw_sp_nexthop4_type_init(mlxsw_sp, nh, fib_nh); break; case FIB_EVENT_NH_DEL: - mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh); - mlxsw_sp_nexthop_rif_fini(nh); + mlxsw_sp_nexthop4_type_fini(mlxsw_sp, nh); break; } @@ -1849,14 +2842,20 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop *nh, *tmp; list_for_each_entry_safe(nh, tmp, &rif->nexthop_list, rif_list_node) { - mlxsw_sp_nexthop_neigh_fini(mlxsw_sp, nh); - mlxsw_sp_nexthop_rif_fini(nh); + mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh->nh_grp); } } +static bool mlxsw_sp_fi_is_gateway(const struct mlxsw_sp *mlxsw_sp, + const struct fib_info *fi) +{ + return fi->fib_nh->nh_scope == RT_SCOPE_LINK || + mlxsw_sp_nexthop4_ipip_type(mlxsw_sp, fi->fib_nh, NULL); +} + static struct mlxsw_sp_nexthop_group * -mlxsw_sp_nexthop_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) +mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) { struct mlxsw_sp_nexthop_group *nh_grp; struct mlxsw_sp_nexthop *nh; @@ -1870,17 +2869,19 @@ mlxsw_sp_nexthop_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) nh_grp = kzalloc(alloc_size, GFP_KERNEL); if (!nh_grp) return ERR_PTR(-ENOMEM); + nh_grp->priv = fi; INIT_LIST_HEAD(&nh_grp->fib_list); - nh_grp->gateway = fi->fib_nh->nh_scope == RT_SCOPE_LINK; + nh_grp->neigh_tbl = &arp_tbl; + + nh_grp->gateway = mlxsw_sp_fi_is_gateway(mlxsw_sp, fi); nh_grp->count = fi->fib_nhs; - nh_grp->key.fi = fi; fib_info_hold(fi); for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; fib_nh = &fi->fib_nh[i]; - err = mlxsw_sp_nexthop_init(mlxsw_sp, nh_grp, nh, fib_nh); + err = mlxsw_sp_nexthop4_init(mlxsw_sp, nh_grp, nh, fib_nh); if (err) - goto err_nexthop_init; + goto err_nexthop4_init; } err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp); if (err) @@ -1889,19 +2890,19 @@ mlxsw_sp_nexthop_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) return nh_grp; err_nexthop_group_insert: -err_nexthop_init: +err_nexthop4_init: for (i--; i >= 0; i--) { nh = &nh_grp->nexthops[i]; - mlxsw_sp_nexthop_fini(mlxsw_sp, nh); + mlxsw_sp_nexthop4_fini(mlxsw_sp, nh); } - fib_info_put(nh_grp->key.fi); + fib_info_put(fi); kfree(nh_grp); return ERR_PTR(err); } static void -mlxsw_sp_nexthop_group_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_nexthop_group *nh_grp) +mlxsw_sp_nexthop4_group_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) { struct mlxsw_sp_nexthop *nh; int i; @@ -1909,25 +2910,23 @@ mlxsw_sp_nexthop_group_destroy(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp); for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; - mlxsw_sp_nexthop_fini(mlxsw_sp, nh); + mlxsw_sp_nexthop4_fini(mlxsw_sp, nh); } mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); WARN_ON_ONCE(nh_grp->adj_index_valid); - fib_info_put(nh_grp->key.fi); + fib_info_put(mlxsw_sp_nexthop4_group_fi(nh_grp)); kfree(nh_grp); } -static int mlxsw_sp_nexthop_group_get(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, - struct fib_info *fi) +static int mlxsw_sp_nexthop4_group_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + struct fib_info *fi) { - struct mlxsw_sp_nexthop_group_key key; struct mlxsw_sp_nexthop_group *nh_grp; - key.fi = fi; - nh_grp = mlxsw_sp_nexthop_group_lookup(mlxsw_sp, key); + nh_grp = mlxsw_sp_nexthop4_group_lookup(mlxsw_sp, fi); if (!nh_grp) { - nh_grp = mlxsw_sp_nexthop_group_create(mlxsw_sp, fi); + nh_grp = mlxsw_sp_nexthop4_group_create(mlxsw_sp, fi); if (IS_ERR(nh_grp)) return PTR_ERR(nh_grp); } @@ -1936,15 +2935,25 @@ static int mlxsw_sp_nexthop_group_get(struct mlxsw_sp *mlxsw_sp, return 0; } -static void mlxsw_sp_nexthop_group_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry) +static void mlxsw_sp_nexthop4_group_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) { struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; list_del(&fib_entry->nexthop_group_node); if (!list_empty(&nh_grp->fib_list)) return; - mlxsw_sp_nexthop_group_destroy(mlxsw_sp, nh_grp); + mlxsw_sp_nexthop4_group_destroy(mlxsw_sp, nh_grp); +} + +static bool +mlxsw_sp_fib4_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry) +{ + struct mlxsw_sp_fib4_entry *fib4_entry; + + fib4_entry = container_of(fib_entry, struct mlxsw_sp_fib4_entry, + common); + return !fib4_entry->tos; } static bool @@ -1952,29 +2961,133 @@ mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry) { struct mlxsw_sp_nexthop_group *nh_group = fib_entry->nh_group; - if (fib_entry->params.tos) - return false; + switch (fib_entry->fib_node->fib->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + if (!mlxsw_sp_fib4_entry_should_offload(fib_entry)) + return false; + break; + case MLXSW_SP_L3_PROTO_IPV6: + break; + } switch (fib_entry->type) { case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE: return !!nh_group->adj_index_valid; case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: return !!nh_group->nh_rif; + case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: + return true; default: return false; } } -static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) +static struct mlxsw_sp_nexthop * +mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp, + const struct mlxsw_sp_rt6 *mlxsw_sp_rt6) +{ + int i; + + for (i = 0; i < nh_grp->count; i++) { + struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; + struct rt6_info *rt = mlxsw_sp_rt6->rt; + + if (nh->rif && nh->rif->dev == rt->dst.dev && + ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr, + &rt->rt6i_gateway)) + return nh; + continue; + } + + return NULL; +} + +static void +mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) +{ + struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; + int i; + + if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL || + fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP) { + nh_grp->nexthops->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD; + return; + } + + for (i = 0; i < nh_grp->count; i++) { + struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; + + if (nh->offloaded) + nh->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD; + else + nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD; + } +} + +static void +mlxsw_sp_fib4_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) { - fib_entry->offloaded = true; + struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; + int i; + + for (i = 0; i < nh_grp->count; i++) { + struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; + + nh->key.fib_nh->nh_flags &= ~RTNH_F_OFFLOAD; + } +} + +static void +mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) +{ + struct mlxsw_sp_fib6_entry *fib6_entry; + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + + fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry, + common); + + if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) { + list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, + list)->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; + return; + } + list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { + struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; + struct mlxsw_sp_nexthop *nh; + + nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6); + if (nh && nh->offloaded) + mlxsw_sp_rt6->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; + else + mlxsw_sp_rt6->rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; + } +} + +static void +mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) +{ + struct mlxsw_sp_fib6_entry *fib6_entry; + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + + fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry, + common); + list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { + struct rt6_info *rt = mlxsw_sp_rt6->rt; + + rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; + } +} + +static void mlxsw_sp_fib_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) +{ switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: - fib_info_offload_inc(fib_entry->nh_group->key.fi); + mlxsw_sp_fib4_entry_offload_set(fib_entry); break; case MLXSW_SP_L3_PROTO_IPV6: - WARN_ON_ONCE(1); + mlxsw_sp_fib6_entry_offload_set(fib_entry); + break; } } @@ -1983,13 +3096,12 @@ mlxsw_sp_fib_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) { switch (fib_entry->fib_node->fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: - fib_info_offload_dec(fib_entry->nh_group->key.fi); + mlxsw_sp_fib4_entry_offload_unset(fib_entry); break; case MLXSW_SP_L3_PROTO_IPV6: - WARN_ON_ONCE(1); + mlxsw_sp_fib6_entry_offload_unset(fib_entry); + break; } - - fib_entry->offloaded = false; } static void @@ -1998,17 +3110,13 @@ mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry, { switch (op) { case MLXSW_REG_RALUE_OP_WRITE_DELETE: - if (!fib_entry->offloaded) - return; return mlxsw_sp_fib_entry_offload_unset(fib_entry); case MLXSW_REG_RALUE_OP_WRITE_WRITE: if (err) return; - if (mlxsw_sp_fib_entry_should_offload(fib_entry) && - !fib_entry->offloaded) + if (mlxsw_sp_fib_entry_should_offload(fib_entry)) mlxsw_sp_fib_entry_offload_set(fib_entry); - else if (!mlxsw_sp_fib_entry_should_offload(fib_entry) && - fib_entry->offloaded) + else if (!mlxsw_sp_fib_entry_should_offload(fib_entry)) mlxsw_sp_fib_entry_offload_unset(fib_entry); return; default: @@ -2016,13 +3124,37 @@ mlxsw_sp_fib_entry_offload_refresh(struct mlxsw_sp_fib_entry *fib_entry, } } -static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) +static void +mlxsw_sp_fib_entry_ralue_pack(char *ralue_pl, + const struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) { - char ralue_pl[MLXSW_REG_RALUE_LEN]; struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; - u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; + enum mlxsw_reg_ralxx_protocol proto; + u32 *p_dip; + + proto = (enum mlxsw_reg_ralxx_protocol) fib->proto; + + switch (fib->proto) { + case MLXSW_SP_L3_PROTO_IPV4: + p_dip = (u32 *) fib_entry->fib_node->key.addr; + mlxsw_reg_ralue_pack4(ralue_pl, proto, op, fib->vr->id, + fib_entry->fib_node->key.prefix_len, + *p_dip); + break; + case MLXSW_SP_L3_PROTO_IPV6: + mlxsw_reg_ralue_pack6(ralue_pl, proto, op, fib->vr->id, + fib_entry->fib_node->key.prefix_len, + fib_entry->fib_node->key.addr); + break; + } +} + +static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + char ralue_pl[MLXSW_REG_RALUE_LEN]; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; @@ -2041,24 +3173,19 @@ static int mlxsw_sp_fib_entry_op4_remote(struct mlxsw_sp *mlxsw_sp, trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; } - mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) fib->proto, op, - fib->vr->id, fib_entry->fib_node->key.prefix_len, - *p_dip); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id, adjacency_index, ecmp_size); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } -static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) +static int mlxsw_sp_fib_entry_op_local(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) { struct mlxsw_sp_rif *rif = fib_entry->nh_group->nh_rif; - struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; enum mlxsw_reg_ralue_trap_action trap_action; char ralue_pl[MLXSW_REG_RALUE_LEN]; - u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; u16 trap_id = 0; u16 rif_index = 0; @@ -2070,42 +3197,53 @@ static int mlxsw_sp_fib_entry_op4_local(struct mlxsw_sp *mlxsw_sp, trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; } - mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) fib->proto, op, - fib->vr->id, fib_entry->fib_node->key.prefix_len, - *p_dip); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, rif_index); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } -static int mlxsw_sp_fib_entry_op4_trap(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) +static int mlxsw_sp_fib_entry_op_trap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) { - struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; char ralue_pl[MLXSW_REG_RALUE_LEN]; - u32 *p_dip = (u32 *) fib_entry->fib_node->key.addr; - mlxsw_reg_ralue_pack4(ralue_pl, - (enum mlxsw_reg_ralxx_protocol) fib->proto, op, - fib->vr->id, fib_entry->fib_node->key.prefix_len, - *p_dip); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } -static int mlxsw_sp_fib_entry_op4(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_reg_ralue_op op) +static int +mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + struct mlxsw_sp_ipip_entry *ipip_entry = fib_entry->decap.ipip_entry; + const struct mlxsw_sp_ipip_ops *ipip_ops; + + if (WARN_ON(!ipip_entry)) + return -EINVAL; + + ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]; + return ipip_ops->fib_entry_op(mlxsw_sp, ipip_entry, op, + fib_entry->decap.tunnel_index); +} + +static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) { switch (fib_entry->type) { case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE: - return mlxsw_sp_fib_entry_op4_remote(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_remote(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: - return mlxsw_sp_fib_entry_op4_local(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_local(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_TRAP: - return mlxsw_sp_fib_entry_op4_trap(mlxsw_sp, fib_entry, op); + return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op); + case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: + return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, + fib_entry, op); } return -EINVAL; } @@ -2114,16 +3252,10 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, enum mlxsw_reg_ralue_op op) { - int err = -EINVAL; + int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op); - switch (fib_entry->fib_node->fib->proto) { - case MLXSW_SP_L3_PROTO_IPV4: - err = mlxsw_sp_fib_entry_op4(mlxsw_sp, fib_entry, op); - break; - case MLXSW_SP_L3_PROTO_IPV6: - return err; - } mlxsw_sp_fib_entry_offload_refresh(fib_entry, op, err); + return err; } @@ -2146,11 +3278,23 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info, struct mlxsw_sp_fib_entry *fib_entry) { + union mlxsw_sp_l3addr dip = { .addr4 = htonl(fen_info->dst) }; + struct net_device *dev = fen_info->fi->fib_dev; + struct mlxsw_sp_ipip_entry *ipip_entry; struct fib_info *fi = fen_info->fi; switch (fen_info->type) { - case RTN_BROADCAST: /* fall through */ case RTN_LOCAL: + ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, dev, + MLXSW_SP_L3_PROTO_IPV4, dip); + if (ipip_entry) { + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP; + return mlxsw_sp_fib_entry_decap_init(mlxsw_sp, + fib_entry, + ipip_entry); + } + /* fall through */ + case RTN_BROADCAST: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; return 0; case RTN_UNREACHABLE: /* fall through */ @@ -2163,82 +3307,87 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; return 0; case RTN_UNICAST: - if (fi->fib_nh->nh_scope != RT_SCOPE_LINK) - fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; - else + if (mlxsw_sp_fi_is_gateway(mlxsw_sp, fi)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; + else + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; return 0; default: return -EINVAL; } } -static struct mlxsw_sp_fib_entry * +static struct mlxsw_sp_fib4_entry * mlxsw_sp_fib4_entry_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node, const struct fib_entry_notifier_info *fen_info) { + struct mlxsw_sp_fib4_entry *fib4_entry; struct mlxsw_sp_fib_entry *fib_entry; int err; - fib_entry = kzalloc(sizeof(*fib_entry), GFP_KERNEL); - if (!fib_entry) { - err = -ENOMEM; - goto err_fib_entry_alloc; - } + fib4_entry = kzalloc(sizeof(*fib4_entry), GFP_KERNEL); + if (!fib4_entry) + return ERR_PTR(-ENOMEM); + fib_entry = &fib4_entry->common; err = mlxsw_sp_fib4_entry_type_set(mlxsw_sp, fen_info, fib_entry); if (err) goto err_fib4_entry_type_set; - err = mlxsw_sp_nexthop_group_get(mlxsw_sp, fib_entry, fen_info->fi); + err = mlxsw_sp_nexthop4_group_get(mlxsw_sp, fib_entry, fen_info->fi); if (err) - goto err_nexthop_group_get; + goto err_nexthop4_group_get; - fib_entry->params.prio = fen_info->fi->fib_priority; - fib_entry->params.tb_id = fen_info->tb_id; - fib_entry->params.type = fen_info->type; - fib_entry->params.tos = fen_info->tos; + fib4_entry->prio = fen_info->fi->fib_priority; + fib4_entry->tb_id = fen_info->tb_id; + fib4_entry->type = fen_info->type; + fib4_entry->tos = fen_info->tos; fib_entry->fib_node = fib_node; - return fib_entry; + return fib4_entry; -err_nexthop_group_get: +err_nexthop4_group_get: err_fib4_entry_type_set: - kfree(fib_entry); -err_fib_entry_alloc: + kfree(fib4_entry); return ERR_PTR(err); } static void mlxsw_sp_fib4_entry_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry) + struct mlxsw_sp_fib4_entry *fib4_entry) { - mlxsw_sp_nexthop_group_put(mlxsw_sp, fib_entry); - kfree(fib_entry); + mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); + kfree(fib4_entry); } -static struct mlxsw_sp_fib_node * -mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, - const struct fib_entry_notifier_info *fen_info); - -static struct mlxsw_sp_fib_entry * +static struct mlxsw_sp_fib4_entry * mlxsw_sp_fib4_entry_lookup(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info) { - struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_fib4_entry *fib4_entry; struct mlxsw_sp_fib_node *fib_node; + struct mlxsw_sp_fib *fib; + struct mlxsw_sp_vr *vr; - fib_node = mlxsw_sp_fib4_node_get(mlxsw_sp, fen_info); - if (IS_ERR(fib_node)) + vr = mlxsw_sp_vr_find(mlxsw_sp, fen_info->tb_id); + if (!vr) return NULL; + fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4); - list_for_each_entry(fib_entry, &fib_node->entry_list, list) { - if (fib_entry->params.tb_id == fen_info->tb_id && - fib_entry->params.tos == fen_info->tos && - fib_entry->params.type == fen_info->type && - fib_entry->nh_group->key.fi == fen_info->fi) { - return fib_entry; + fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst, + sizeof(fen_info->dst), + fen_info->dst_len); + if (!fib_node) + return NULL; + + list_for_each_entry(fib4_entry, &fib_node->entry_list, common.list) { + if (fib4_entry->tb_id == fen_info->tb_id && + fib4_entry->tos == fen_info->tos && + fib4_entry->type == fen_info->type && + mlxsw_sp_nexthop4_group_fi(fib4_entry->common.nh_group) == + fen_info->fi) { + return fib4_entry; } } @@ -2311,6 +3460,67 @@ mlxsw_sp_fib_node_entry_is_first(const struct mlxsw_sp_fib_node *fib_node, struct mlxsw_sp_fib_entry, list) == fib_entry; } +static int mlxsw_sp_fib_lpm_tree_link(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib *fib, + struct mlxsw_sp_fib_node *fib_node) +{ + struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } }; + struct mlxsw_sp_lpm_tree *lpm_tree; + int err; + + /* Since the tree is shared between all virtual routers we must + * make sure it contains all the required prefix lengths. This + * can be computed by either adding the new prefix length to the + * existing prefix usage of a bound tree, or by aggregating the + * prefix lengths across all virtual routers and adding the new + * one as well. + */ + if (fib->lpm_tree) + mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, + &fib->lpm_tree->prefix_usage); + else + mlxsw_sp_vrs_prefixes(mlxsw_sp, fib->proto, &req_prefix_usage); + mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len); + + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + fib->proto); + if (IS_ERR(lpm_tree)) + return PTR_ERR(lpm_tree); + + if (fib->lpm_tree && fib->lpm_tree->id == lpm_tree->id) + return 0; + + err = mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree); + if (err) + return err; + + return 0; +} + +static void mlxsw_sp_fib_lpm_tree_unlink(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib *fib) +{ + struct mlxsw_sp_prefix_usage req_prefix_usage = {{ 0 } }; + struct mlxsw_sp_lpm_tree *lpm_tree; + + /* Aggregate prefix lengths across all virtual routers to make + * sure we only have used prefix lengths in the LPM tree. + */ + mlxsw_sp_vrs_prefixes(mlxsw_sp, fib->proto, &req_prefix_usage); + lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, + fib->proto); + if (IS_ERR(lpm_tree)) + goto err_tree_get; + mlxsw_sp_vrs_lpm_tree_replace(mlxsw_sp, fib, lpm_tree); + +err_tree_get: + if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) + return; + mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); + mlxsw_sp_lpm_tree_put(mlxsw_sp, fib->lpm_tree); + fib->lpm_tree = NULL; +} + static void mlxsw_sp_fib_node_prefix_inc(struct mlxsw_sp_fib_node *fib_node) { unsigned char prefix_len = fib_node->key.prefix_len; @@ -2333,8 +3543,6 @@ static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node, struct mlxsw_sp_fib *fib) { - struct mlxsw_sp_prefix_usage req_prefix_usage; - struct mlxsw_sp_lpm_tree *lpm_tree; int err; err = mlxsw_sp_fib_node_insert(fib, fib_node); @@ -2342,33 +3550,15 @@ static int mlxsw_sp_fib_node_init(struct mlxsw_sp *mlxsw_sp, return err; fib_node->fib = fib; - mlxsw_sp_prefix_usage_cpy(&req_prefix_usage, &fib->prefix_usage); - mlxsw_sp_prefix_usage_set(&req_prefix_usage, fib_node->key.prefix_len); - - if (!mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { - err = mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, - &req_prefix_usage); - if (err) - goto err_tree_check; - } else { - lpm_tree = mlxsw_sp_lpm_tree_get(mlxsw_sp, &req_prefix_usage, - fib->proto); - if (IS_ERR(lpm_tree)) - return PTR_ERR(lpm_tree); - fib->lpm_tree = lpm_tree; - err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib); - if (err) - goto err_tree_bind; - } + err = mlxsw_sp_fib_lpm_tree_link(mlxsw_sp, fib, fib_node); + if (err) + goto err_fib_lpm_tree_link; mlxsw_sp_fib_node_prefix_inc(fib_node); return 0; -err_tree_bind: - fib->lpm_tree = NULL; - mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); -err_tree_check: +err_fib_lpm_tree_link: fib_node->fib = NULL; mlxsw_sp_fib_node_remove(fib, fib_node); return err; @@ -2377,46 +3567,34 @@ err_tree_check: static void mlxsw_sp_fib_node_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - struct mlxsw_sp_lpm_tree *lpm_tree = fib_node->fib->lpm_tree; struct mlxsw_sp_fib *fib = fib_node->fib; mlxsw_sp_fib_node_prefix_dec(fib_node); - - if (mlxsw_sp_prefix_usage_none(&fib->prefix_usage)) { - mlxsw_sp_vr_lpm_tree_unbind(mlxsw_sp, fib); - fib->lpm_tree = NULL; - mlxsw_sp_lpm_tree_put(mlxsw_sp, lpm_tree); - } else { - mlxsw_sp_vr_lpm_tree_check(mlxsw_sp, fib, &fib->prefix_usage); - } - + mlxsw_sp_fib_lpm_tree_unlink(mlxsw_sp, fib); fib_node->fib = NULL; mlxsw_sp_fib_node_remove(fib, fib_node); } static struct mlxsw_sp_fib_node * -mlxsw_sp_fib4_node_get(struct mlxsw_sp *mlxsw_sp, - const struct fib_entry_notifier_info *fen_info) +mlxsw_sp_fib_node_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id, const void *addr, + size_t addr_len, unsigned char prefix_len, + enum mlxsw_sp_l3proto proto) { struct mlxsw_sp_fib_node *fib_node; struct mlxsw_sp_fib *fib; struct mlxsw_sp_vr *vr; int err; - vr = mlxsw_sp_vr_get(mlxsw_sp, fen_info->tb_id); + vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id); if (IS_ERR(vr)) return ERR_CAST(vr); - fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV4); + fib = mlxsw_sp_vr_fib(vr, proto); - fib_node = mlxsw_sp_fib_node_lookup(fib, &fen_info->dst, - sizeof(fen_info->dst), - fen_info->dst_len); + fib_node = mlxsw_sp_fib_node_lookup(fib, addr, addr_len, prefix_len); if (fib_node) return fib_node; - fib_node = mlxsw_sp_fib_node_create(fib, &fen_info->dst, - sizeof(fen_info->dst), - fen_info->dst_len); + fib_node = mlxsw_sp_fib_node_create(fib, addr, addr_len, prefix_len); if (!fib_node) { err = -ENOMEM; goto err_fib_node_create; @@ -2435,8 +3613,8 @@ err_fib_node_create: return ERR_PTR(err); } -static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_node *fib_node) +static void mlxsw_sp_fib_node_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node) { struct mlxsw_sp_vr *vr = fib_node->fib->vr; @@ -2447,95 +3625,100 @@ static void mlxsw_sp_fib4_node_put(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_vr_put(vr); } -static struct mlxsw_sp_fib_entry * +static struct mlxsw_sp_fib4_entry * mlxsw_sp_fib4_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, - const struct mlxsw_sp_fib_entry_params *params) + const struct mlxsw_sp_fib4_entry *new4_entry) { - struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_fib4_entry *fib4_entry; - list_for_each_entry(fib_entry, &fib_node->entry_list, list) { - if (fib_entry->params.tb_id > params->tb_id) + list_for_each_entry(fib4_entry, &fib_node->entry_list, common.list) { + if (fib4_entry->tb_id > new4_entry->tb_id) continue; - if (fib_entry->params.tb_id != params->tb_id) + if (fib4_entry->tb_id != new4_entry->tb_id) break; - if (fib_entry->params.tos > params->tos) + if (fib4_entry->tos > new4_entry->tos) continue; - if (fib_entry->params.prio >= params->prio || - fib_entry->params.tos < params->tos) - return fib_entry; + if (fib4_entry->prio >= new4_entry->prio || + fib4_entry->tos < new4_entry->tos) + return fib4_entry; } return NULL; } -static int mlxsw_sp_fib4_node_list_append(struct mlxsw_sp_fib_entry *fib_entry, - struct mlxsw_sp_fib_entry *new_entry) +static int +mlxsw_sp_fib4_node_list_append(struct mlxsw_sp_fib4_entry *fib4_entry, + struct mlxsw_sp_fib4_entry *new4_entry) { struct mlxsw_sp_fib_node *fib_node; - if (WARN_ON(!fib_entry)) + if (WARN_ON(!fib4_entry)) return -EINVAL; - fib_node = fib_entry->fib_node; - list_for_each_entry_from(fib_entry, &fib_node->entry_list, list) { - if (fib_entry->params.tb_id != new_entry->params.tb_id || - fib_entry->params.tos != new_entry->params.tos || - fib_entry->params.prio != new_entry->params.prio) + fib_node = fib4_entry->common.fib_node; + list_for_each_entry_from(fib4_entry, &fib_node->entry_list, + common.list) { + if (fib4_entry->tb_id != new4_entry->tb_id || + fib4_entry->tos != new4_entry->tos || + fib4_entry->prio != new4_entry->prio) break; } - list_add_tail(&new_entry->list, &fib_entry->list); + list_add_tail(&new4_entry->common.list, &fib4_entry->common.list); return 0; } static int -mlxsw_sp_fib4_node_list_insert(struct mlxsw_sp_fib_node *fib_node, - struct mlxsw_sp_fib_entry *new_entry, +mlxsw_sp_fib4_node_list_insert(struct mlxsw_sp_fib4_entry *new4_entry, bool replace, bool append) { - struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_fib_node *fib_node = new4_entry->common.fib_node; + struct mlxsw_sp_fib4_entry *fib4_entry; - fib_entry = mlxsw_sp_fib4_node_entry_find(fib_node, &new_entry->params); + fib4_entry = mlxsw_sp_fib4_node_entry_find(fib_node, new4_entry); if (append) - return mlxsw_sp_fib4_node_list_append(fib_entry, new_entry); - if (replace && WARN_ON(!fib_entry)) + return mlxsw_sp_fib4_node_list_append(fib4_entry, new4_entry); + if (replace && WARN_ON(!fib4_entry)) return -EINVAL; /* Insert new entry before replaced one, so that we can later * remove the second. */ - if (fib_entry) { - list_add_tail(&new_entry->list, &fib_entry->list); + if (fib4_entry) { + list_add_tail(&new4_entry->common.list, + &fib4_entry->common.list); } else { - struct mlxsw_sp_fib_entry *last; + struct mlxsw_sp_fib4_entry *last; - list_for_each_entry(last, &fib_node->entry_list, list) { - if (new_entry->params.tb_id > last->params.tb_id) + list_for_each_entry(last, &fib_node->entry_list, common.list) { + if (new4_entry->tb_id > last->tb_id) break; - fib_entry = last; + fib4_entry = last; } - if (fib_entry) - list_add(&new_entry->list, &fib_entry->list); + if (fib4_entry) + list_add(&new4_entry->common.list, + &fib4_entry->common.list); else - list_add(&new_entry->list, &fib_node->entry_list); + list_add(&new4_entry->common.list, + &fib_node->entry_list); } return 0; } static void -mlxsw_sp_fib4_node_list_remove(struct mlxsw_sp_fib_entry *fib_entry) +mlxsw_sp_fib4_node_list_remove(struct mlxsw_sp_fib4_entry *fib4_entry) { - list_del(&fib_entry->list); + list_del(&fib4_entry->common.list); } -static int -mlxsw_sp_fib4_node_entry_add(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_fib_node *fib_node, - struct mlxsw_sp_fib_entry *fib_entry) +static int mlxsw_sp_fib_node_entry_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) { + struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; + if (!mlxsw_sp_fib_node_entry_is_first(fib_node, fib_entry)) return 0; @@ -2552,11 +3735,11 @@ mlxsw_sp_fib4_node_entry_add(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); } -static void -mlxsw_sp_fib4_node_entry_del(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_fib_node *fib_node, - struct mlxsw_sp_fib_entry *fib_entry) +static void mlxsw_sp_fib_node_entry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) { + struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; + if (!mlxsw_sp_fib_node_entry_is_first(fib_node, fib_entry)) return; @@ -2574,54 +3757,53 @@ mlxsw_sp_fib4_node_entry_del(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_fib4_node_entry_link(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, + struct mlxsw_sp_fib4_entry *fib4_entry, bool replace, bool append) { - struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; int err; - err = mlxsw_sp_fib4_node_list_insert(fib_node, fib_entry, replace, - append); + err = mlxsw_sp_fib4_node_list_insert(fib4_entry, replace, append); if (err) return err; - err = mlxsw_sp_fib4_node_entry_add(mlxsw_sp, fib_node, fib_entry); + err = mlxsw_sp_fib_node_entry_add(mlxsw_sp, &fib4_entry->common); if (err) - goto err_fib4_node_entry_add; + goto err_fib_node_entry_add; return 0; -err_fib4_node_entry_add: - mlxsw_sp_fib4_node_list_remove(fib_entry); +err_fib_node_entry_add: + mlxsw_sp_fib4_node_list_remove(fib4_entry); return err; } static void mlxsw_sp_fib4_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry) + struct mlxsw_sp_fib4_entry *fib4_entry) { - struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; + mlxsw_sp_fib_node_entry_del(mlxsw_sp, &fib4_entry->common); + mlxsw_sp_fib4_node_list_remove(fib4_entry); - mlxsw_sp_fib4_node_entry_del(mlxsw_sp, fib_node, fib_entry); - mlxsw_sp_fib4_node_list_remove(fib_entry); + if (fib4_entry->common.type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP) + mlxsw_sp_fib_entry_decap_fini(mlxsw_sp, &fib4_entry->common); } static void mlxsw_sp_fib4_entry_replace(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, + struct mlxsw_sp_fib4_entry *fib4_entry, bool replace) { - struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; - struct mlxsw_sp_fib_entry *replaced; + struct mlxsw_sp_fib_node *fib_node = fib4_entry->common.fib_node; + struct mlxsw_sp_fib4_entry *replaced; if (!replace) return; /* We inserted the new entry before replaced one */ - replaced = list_next_entry(fib_entry, list); + replaced = list_next_entry(fib4_entry, common.list); mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, replaced); mlxsw_sp_fib4_entry_destroy(mlxsw_sp, replaced); - mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); } static int @@ -2629,76 +3811,774 @@ mlxsw_sp_router_fib4_add(struct mlxsw_sp *mlxsw_sp, const struct fib_entry_notifier_info *fen_info, bool replace, bool append) { - struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_fib4_entry *fib4_entry; struct mlxsw_sp_fib_node *fib_node; int err; if (mlxsw_sp->router->aborted) return 0; - fib_node = mlxsw_sp_fib4_node_get(mlxsw_sp, fen_info); + fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, fen_info->tb_id, + &fen_info->dst, sizeof(fen_info->dst), + fen_info->dst_len, + MLXSW_SP_L3_PROTO_IPV4); if (IS_ERR(fib_node)) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to get FIB node\n"); return PTR_ERR(fib_node); } - fib_entry = mlxsw_sp_fib4_entry_create(mlxsw_sp, fib_node, fen_info); - if (IS_ERR(fib_entry)) { + fib4_entry = mlxsw_sp_fib4_entry_create(mlxsw_sp, fib_node, fen_info); + if (IS_ERR(fib4_entry)) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to create FIB entry\n"); - err = PTR_ERR(fib_entry); + err = PTR_ERR(fib4_entry); goto err_fib4_entry_create; } - err = mlxsw_sp_fib4_node_entry_link(mlxsw_sp, fib_entry, replace, + err = mlxsw_sp_fib4_node_entry_link(mlxsw_sp, fib4_entry, replace, append); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to link FIB entry to node\n"); goto err_fib4_node_entry_link; } - mlxsw_sp_fib4_entry_replace(mlxsw_sp, fib_entry, replace); + mlxsw_sp_fib4_entry_replace(mlxsw_sp, fib4_entry, replace); return 0; err_fib4_node_entry_link: - mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib_entry); + mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_entry); err_fib4_entry_create: - mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); return err; } static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, struct fib_entry_notifier_info *fen_info) { + struct mlxsw_sp_fib4_entry *fib4_entry; + struct mlxsw_sp_fib_node *fib_node; + + if (mlxsw_sp->router->aborted) + return; + + fib4_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info); + if (WARN_ON(!fib4_entry)) + return; + fib_node = fib4_entry->common.fib_node; + + mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, fib4_entry); + mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_entry); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); +} + +static bool mlxsw_sp_fib6_rt_should_ignore(const struct rt6_info *rt) +{ + /* Packets with link-local destination IP arriving to the router + * are trapped to the CPU, so no need to program specific routes + * for them. + */ + if (ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LINKLOCAL) + return true; + + /* Multicast routes aren't supported, so ignore them. Neighbour + * Discovery packets are specifically trapped. + */ + if (ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_MULTICAST) + return true; + + /* Cloned routes are irrelevant in the forwarding path. */ + if (rt->rt6i_flags & RTF_CACHE) + return true; + + return false; +} + +static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt) +{ + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + + mlxsw_sp_rt6 = kzalloc(sizeof(*mlxsw_sp_rt6), GFP_KERNEL); + if (!mlxsw_sp_rt6) + return ERR_PTR(-ENOMEM); + + /* In case of route replace, replaced route is deleted with + * no notification. Take reference to prevent accessing freed + * memory. + */ + mlxsw_sp_rt6->rt = rt; + rt6_hold(rt); + + return mlxsw_sp_rt6; +} + +#if IS_ENABLED(CONFIG_IPV6) +static void mlxsw_sp_rt6_release(struct rt6_info *rt) +{ + rt6_release(rt); +} +#else +static void mlxsw_sp_rt6_release(struct rt6_info *rt) +{ +} +#endif + +static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) +{ + mlxsw_sp_rt6_release(mlxsw_sp_rt6->rt); + kfree(mlxsw_sp_rt6); +} + +static bool mlxsw_sp_fib6_rt_can_mp(const struct rt6_info *rt) +{ + /* RTF_CACHE routes are ignored */ + return (rt->rt6i_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; +} + +static struct rt6_info * +mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) +{ + return list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, + list)->rt; +} + +static struct mlxsw_sp_fib6_entry * +mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, + const struct rt6_info *nrt, bool replace) +{ + struct mlxsw_sp_fib6_entry *fib6_entry; + + if (!mlxsw_sp_fib6_rt_can_mp(nrt) || replace) + return NULL; + + list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { + struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + + /* RT6_TABLE_LOCAL and RT6_TABLE_MAIN share the same + * virtual router. + */ + if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id) + continue; + if (rt->rt6i_table->tb6_id != nrt->rt6i_table->tb6_id) + break; + if (rt->rt6i_metric < nrt->rt6i_metric) + continue; + if (rt->rt6i_metric == nrt->rt6i_metric && + mlxsw_sp_fib6_rt_can_mp(rt)) + return fib6_entry; + if (rt->rt6i_metric > nrt->rt6i_metric) + break; + } + + return NULL; +} + +static struct mlxsw_sp_rt6 * +mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry, + const struct rt6_info *rt) +{ + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + + list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { + if (mlxsw_sp_rt6->rt == rt) + return mlxsw_sp_rt6; + } + + return NULL; +} + +static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp, + const struct rt6_info *rt, + enum mlxsw_sp_ipip_type *ret) +{ + return rt->dst.dev && + mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->dst.dev, ret); +} + +static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop *nh, + const struct rt6_info *rt) +{ + struct mlxsw_sp_router *router = mlxsw_sp->router; + struct net_device *dev = rt->dst.dev; + enum mlxsw_sp_ipip_type ipipt; + struct mlxsw_sp_rif *rif; + int err; + + if (mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, &ipipt) && + router->ipip_ops_arr[ipipt]->can_offload(mlxsw_sp, dev, + MLXSW_SP_L3_PROTO_IPV6)) { + nh->type = MLXSW_SP_NEXTHOP_TYPE_IPIP; + return mlxsw_sp_nexthop_ipip_init(mlxsw_sp, ipipt, nh, dev); + } + + nh->type = MLXSW_SP_NEXTHOP_TYPE_ETH; + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) + return 0; + mlxsw_sp_nexthop_rif_init(nh, rif); + + err = mlxsw_sp_nexthop_neigh_init(mlxsw_sp, nh); + if (err) + goto err_nexthop_neigh_init; + + return 0; + +err_nexthop_neigh_init: + mlxsw_sp_nexthop_rif_fini(nh); + return err; +} + +static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + mlxsw_sp_nexthop_type_fini(mlxsw_sp, nh); +} + +static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp, + struct mlxsw_sp_nexthop *nh, + const struct rt6_info *rt) +{ + struct net_device *dev = rt->dst.dev; + + nh->nh_grp = nh_grp; + memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr)); + + if (!dev) + return 0; + nh->ifindex = dev->ifindex; + + return mlxsw_sp_nexthop6_type_init(mlxsw_sp, nh_grp, nh, rt); +} + +static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop *nh) +{ + mlxsw_sp_nexthop6_type_fini(mlxsw_sp, nh); +} + +static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, + const struct rt6_info *rt) +{ + return rt->rt6i_flags & RTF_GATEWAY || + mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL); +} + +static struct mlxsw_sp_nexthop_group * +mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + struct mlxsw_sp_nexthop *nh; + size_t alloc_size; + int i = 0; + int err; + + alloc_size = sizeof(*nh_grp) + + fib6_entry->nrt6 * sizeof(struct mlxsw_sp_nexthop); + nh_grp = kzalloc(alloc_size, GFP_KERNEL); + if (!nh_grp) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&nh_grp->fib_list); +#if IS_ENABLED(CONFIG_IPV6) + nh_grp->neigh_tbl = &nd_tbl; +#endif + mlxsw_sp_rt6 = list_first_entry(&fib6_entry->rt6_list, + struct mlxsw_sp_rt6, list); + nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt); + nh_grp->count = fib6_entry->nrt6; + for (i = 0; i < nh_grp->count; i++) { + struct rt6_info *rt = mlxsw_sp_rt6->rt; + + nh = &nh_grp->nexthops[i]; + err = mlxsw_sp_nexthop6_init(mlxsw_sp, nh_grp, nh, rt); + if (err) + goto err_nexthop6_init; + mlxsw_sp_rt6 = list_next_entry(mlxsw_sp_rt6, list); + } + + err = mlxsw_sp_nexthop_group_insert(mlxsw_sp, nh_grp); + if (err) + goto err_nexthop_group_insert; + + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + return nh_grp; + +err_nexthop_group_insert: +err_nexthop6_init: + for (i--; i >= 0; i--) { + nh = &nh_grp->nexthops[i]; + mlxsw_sp_nexthop6_fini(mlxsw_sp, nh); + } + kfree(nh_grp); + return ERR_PTR(err); +} + +static void +mlxsw_sp_nexthop6_group_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nexthop_group *nh_grp) +{ + struct mlxsw_sp_nexthop *nh; + int i = nh_grp->count; + + mlxsw_sp_nexthop_group_remove(mlxsw_sp, nh_grp); + for (i--; i >= 0; i--) { + nh = &nh_grp->nexthops[i]; + mlxsw_sp_nexthop6_fini(mlxsw_sp, nh); + } + mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); + WARN_ON(nh_grp->adj_index_valid); + kfree(nh_grp); +} + +static int mlxsw_sp_nexthop6_group_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + struct mlxsw_sp_nexthop_group *nh_grp; + + nh_grp = mlxsw_sp_nexthop6_group_lookup(mlxsw_sp, fib6_entry); + if (!nh_grp) { + nh_grp = mlxsw_sp_nexthop6_group_create(mlxsw_sp, fib6_entry); + if (IS_ERR(nh_grp)) + return PTR_ERR(nh_grp); + } + + list_add_tail(&fib6_entry->common.nexthop_group_node, + &nh_grp->fib_list); + fib6_entry->common.nh_group = nh_grp; + + return 0; +} + +static void mlxsw_sp_nexthop6_group_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) +{ + struct mlxsw_sp_nexthop_group *nh_grp = fib_entry->nh_group; + + list_del(&fib_entry->nexthop_group_node); + if (!list_empty(&nh_grp->fib_list)) + return; + mlxsw_sp_nexthop6_group_destroy(mlxsw_sp, nh_grp); +} + +static int +mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + struct mlxsw_sp_nexthop_group *old_nh_grp = fib6_entry->common.nh_group; + int err; + + fib6_entry->common.nh_group = NULL; + list_del(&fib6_entry->common.nexthop_group_node); + + err = mlxsw_sp_nexthop6_group_get(mlxsw_sp, fib6_entry); + if (err) + goto err_nexthop6_group_get; + + /* In case this entry is offloaded, then the adjacency index + * currently associated with it in the device's table is that + * of the old group. Start using the new one instead. + */ + err = mlxsw_sp_fib_node_entry_add(mlxsw_sp, &fib6_entry->common); + if (err) + goto err_fib_node_entry_add; + + if (list_empty(&old_nh_grp->fib_list)) + mlxsw_sp_nexthop6_group_destroy(mlxsw_sp, old_nh_grp); + + return 0; + +err_fib_node_entry_add: + mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common); +err_nexthop6_group_get: + list_add_tail(&fib6_entry->common.nexthop_group_node, + &old_nh_grp->fib_list); + fib6_entry->common.nh_group = old_nh_grp; + return err; +} + +static int +mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry, + struct rt6_info *rt) +{ + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + int err; + + mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt); + if (IS_ERR(mlxsw_sp_rt6)) + return PTR_ERR(mlxsw_sp_rt6); + + list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list); + fib6_entry->nrt6++; + + err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); + if (err) + goto err_nexthop6_group_update; + + return 0; + +err_nexthop6_group_update: + fib6_entry->nrt6--; + list_del(&mlxsw_sp_rt6->list); + mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); + return err; +} + +static void +mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry, + struct rt6_info *rt) +{ + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + + mlxsw_sp_rt6 = mlxsw_sp_fib6_entry_rt_find(fib6_entry, rt); + if (WARN_ON(!mlxsw_sp_rt6)) + return; + + fib6_entry->nrt6--; + list_del(&mlxsw_sp_rt6->list); + mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); + mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); +} + +static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + const struct rt6_info *rt) +{ + /* Packets hitting RTF_REJECT routes need to be discarded by the + * stack. We can rely on their destination device not having a + * RIF (it's the loopback device) and can thus use action type + * local, which will cause them to be trapped with a lower + * priority than packets that need to be locally received. + */ + if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + else if (rt->rt6i_flags & RTF_REJECT) + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt)) + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; + else + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; +} + +static void +mlxsw_sp_fib6_entry_rt_destroy_all(struct mlxsw_sp_fib6_entry *fib6_entry) +{ + struct mlxsw_sp_rt6 *mlxsw_sp_rt6, *tmp; + + list_for_each_entry_safe(mlxsw_sp_rt6, tmp, &fib6_entry->rt6_list, + list) { + fib6_entry->nrt6--; + list_del(&mlxsw_sp_rt6->list); + mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); + } +} + +static struct mlxsw_sp_fib6_entry * +mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node, + struct rt6_info *rt) +{ + struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_entry *fib_entry; + struct mlxsw_sp_rt6 *mlxsw_sp_rt6; + int err; + + fib6_entry = kzalloc(sizeof(*fib6_entry), GFP_KERNEL); + if (!fib6_entry) + return ERR_PTR(-ENOMEM); + fib_entry = &fib6_entry->common; + + mlxsw_sp_rt6 = mlxsw_sp_rt6_create(rt); + if (IS_ERR(mlxsw_sp_rt6)) { + err = PTR_ERR(mlxsw_sp_rt6); + goto err_rt6_create; + } + + mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, mlxsw_sp_rt6->rt); + + INIT_LIST_HEAD(&fib6_entry->rt6_list); + list_add_tail(&mlxsw_sp_rt6->list, &fib6_entry->rt6_list); + fib6_entry->nrt6 = 1; + err = mlxsw_sp_nexthop6_group_get(mlxsw_sp, fib6_entry); + if (err) + goto err_nexthop6_group_get; + + fib_entry->fib_node = fib_node; + + return fib6_entry; + +err_nexthop6_group_get: + list_del(&mlxsw_sp_rt6->list); + mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); +err_rt6_create: + kfree(fib6_entry); + return ERR_PTR(err); +} + +static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common); + mlxsw_sp_fib6_entry_rt_destroy_all(fib6_entry); + WARN_ON(fib6_entry->nrt6); + kfree(fib6_entry); +} + +static struct mlxsw_sp_fib6_entry * +mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, + const struct rt6_info *nrt, bool replace) +{ + struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL; + + list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { + struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + + if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id) + continue; + if (rt->rt6i_table->tb6_id != nrt->rt6i_table->tb6_id) + break; + if (replace && rt->rt6i_metric == nrt->rt6i_metric) { + if (mlxsw_sp_fib6_rt_can_mp(rt) == + mlxsw_sp_fib6_rt_can_mp(nrt)) + return fib6_entry; + if (mlxsw_sp_fib6_rt_can_mp(nrt)) + fallback = fallback ?: fib6_entry; + } + if (rt->rt6i_metric > nrt->rt6i_metric) + return fallback ?: fib6_entry; + } + + return fallback; +} + +static int +mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry, + bool replace) +{ + struct mlxsw_sp_fib_node *fib_node = new6_entry->common.fib_node; + struct rt6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry); + struct mlxsw_sp_fib6_entry *fib6_entry; + + fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, replace); + + if (replace && WARN_ON(!fib6_entry)) + return -EINVAL; + + if (fib6_entry) { + list_add_tail(&new6_entry->common.list, + &fib6_entry->common.list); + } else { + struct mlxsw_sp_fib6_entry *last; + + list_for_each_entry(last, &fib_node->entry_list, common.list) { + struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(last); + + if (nrt->rt6i_table->tb6_id > rt->rt6i_table->tb6_id) + break; + fib6_entry = last; + } + + if (fib6_entry) + list_add(&new6_entry->common.list, + &fib6_entry->common.list); + else + list_add(&new6_entry->common.list, + &fib_node->entry_list); + } + + return 0; +} + +static void +mlxsw_sp_fib6_node_list_remove(struct mlxsw_sp_fib6_entry *fib6_entry) +{ + list_del(&fib6_entry->common.list); +} + +static int mlxsw_sp_fib6_node_entry_link(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry, + bool replace) +{ + int err; + + err = mlxsw_sp_fib6_node_list_insert(fib6_entry, replace); + if (err) + return err; + + err = mlxsw_sp_fib_node_entry_add(mlxsw_sp, &fib6_entry->common); + if (err) + goto err_fib_node_entry_add; + + return 0; + +err_fib_node_entry_add: + mlxsw_sp_fib6_node_list_remove(fib6_entry); + return err; +} + +static void +mlxsw_sp_fib6_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + mlxsw_sp_fib_node_entry_del(mlxsw_sp, &fib6_entry->common); + mlxsw_sp_fib6_node_list_remove(fib6_entry); +} + +static struct mlxsw_sp_fib6_entry * +mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp, + const struct rt6_info *rt) +{ + struct mlxsw_sp_fib6_entry *fib6_entry; + struct mlxsw_sp_fib_node *fib_node; + struct mlxsw_sp_fib *fib; + struct mlxsw_sp_vr *vr; + + vr = mlxsw_sp_vr_find(mlxsw_sp, rt->rt6i_table->tb6_id); + if (!vr) + return NULL; + fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV6); + + fib_node = mlxsw_sp_fib_node_lookup(fib, &rt->rt6i_dst.addr, + sizeof(rt->rt6i_dst.addr), + rt->rt6i_dst.plen); + if (!fib_node) + return NULL; + + list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { + struct rt6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + + if (rt->rt6i_table->tb6_id == iter_rt->rt6i_table->tb6_id && + rt->rt6i_metric == iter_rt->rt6i_metric && + mlxsw_sp_fib6_entry_rt_find(fib6_entry, rt)) + return fib6_entry; + } + + return NULL; +} + +static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry, + bool replace) +{ + struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node; + struct mlxsw_sp_fib6_entry *replaced; + + if (!replace) + return; + + replaced = list_next_entry(fib6_entry, common.list); + + mlxsw_sp_fib6_node_entry_unlink(mlxsw_sp, replaced); + mlxsw_sp_fib6_entry_destroy(mlxsw_sp, replaced); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); +} + +static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, + struct rt6_info *rt, bool replace) +{ + struct mlxsw_sp_fib6_entry *fib6_entry; + struct mlxsw_sp_fib_node *fib_node; + int err; + + if (mlxsw_sp->router->aborted) + return 0; + + if (rt->rt6i_src.plen) + return -EINVAL; + + if (mlxsw_sp_fib6_rt_should_ignore(rt)) + return 0; + + fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, rt->rt6i_table->tb6_id, + &rt->rt6i_dst.addr, + sizeof(rt->rt6i_dst.addr), + rt->rt6i_dst.plen, + MLXSW_SP_L3_PROTO_IPV6); + if (IS_ERR(fib_node)) + return PTR_ERR(fib_node); + + /* Before creating a new entry, try to append route to an existing + * multipath entry. + */ + fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace); + if (fib6_entry) { + err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt); + if (err) + goto err_fib6_entry_nexthop_add; + return 0; + } + + fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt); + if (IS_ERR(fib6_entry)) { + err = PTR_ERR(fib6_entry); + goto err_fib6_entry_create; + } + + err = mlxsw_sp_fib6_node_entry_link(mlxsw_sp, fib6_entry, replace); + if (err) + goto err_fib6_node_entry_link; + + mlxsw_sp_fib6_entry_replace(mlxsw_sp, fib6_entry, replace); + + return 0; + +err_fib6_node_entry_link: + mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); +err_fib6_entry_create: +err_fib6_entry_nexthop_add: + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); + return err; +} + +static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, + struct rt6_info *rt) +{ + struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; if (mlxsw_sp->router->aborted) return; - fib_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info); - if (WARN_ON(!fib_entry)) + if (mlxsw_sp_fib6_rt_should_ignore(rt)) return; - fib_node = fib_entry->fib_node; - mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, fib_entry); - mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib_entry); - mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node); + fib6_entry = mlxsw_sp_fib6_entry_lookup(mlxsw_sp, rt); + if (WARN_ON(!fib6_entry)) + return; + + /* If route is part of a multipath entry, but not the last one + * removed, then only reduce its nexthop group. + */ + if (!list_is_singular(&fib6_entry->rt6_list)) { + mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt); + return; + } + + fib_node = fib6_entry->common.fib_node; + + mlxsw_sp_fib6_node_entry_unlink(mlxsw_sp, fib6_entry); + mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); } -static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) +static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_reg_ralxx_protocol proto, + u8 tree_id) { char ralta_pl[MLXSW_REG_RALTA_LEN]; char ralst_pl[MLXSW_REG_RALST_LEN]; int i, err; - mlxsw_reg_ralta_pack(ralta_pl, true, MLXSW_REG_RALXX_PROTOCOL_IPV4, - MLXSW_SP_LPM_TREE_MIN); + mlxsw_reg_ralta_pack(ralta_pl, true, proto, tree_id); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); if (err) return err; - mlxsw_reg_ralst_pack(ralst_pl, 0xff, MLXSW_SP_LPM_TREE_MIN); + mlxsw_reg_ralst_pack(ralst_pl, 0xff, tree_id); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl); if (err) return err; @@ -2708,20 +4588,14 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) char raltb_pl[MLXSW_REG_RALTB_LEN]; char ralue_pl[MLXSW_REG_RALUE_LEN]; - if (!mlxsw_sp_vr_is_used(vr)) - continue; - - mlxsw_reg_raltb_pack(raltb_pl, vr->id, - MLXSW_REG_RALXX_PROTOCOL_IPV4, - MLXSW_SP_LPM_TREE_MIN); + mlxsw_reg_raltb_pack(raltb_pl, vr->id, proto, tree_id); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); if (err) return err; - mlxsw_reg_ralue_pack4(ralue_pl, MLXSW_SP_L3_PROTO_IPV4, - MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0, - 0); + mlxsw_reg_ralue_pack(ralue_pl, proto, + MLXSW_REG_RALUE_OP_WRITE_WRITE, vr->id, 0); mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); @@ -2732,17 +4606,33 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) return 0; } +static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) +{ + enum mlxsw_reg_ralxx_protocol proto = MLXSW_REG_RALXX_PROTOCOL_IPV4; + int err; + + err = __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto, + MLXSW_SP_LPM_TREE_MIN); + if (err) + return err; + + proto = MLXSW_REG_RALXX_PROTOCOL_IPV6; + return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto, + MLXSW_SP_LPM_TREE_MIN + 1); +} + static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { - struct mlxsw_sp_fib_entry *fib_entry, *tmp; + struct mlxsw_sp_fib4_entry *fib4_entry, *tmp; - list_for_each_entry_safe(fib_entry, tmp, &fib_node->entry_list, list) { - bool do_break = &tmp->list == &fib_node->entry_list; + list_for_each_entry_safe(fib4_entry, tmp, &fib_node->entry_list, + common.list) { + bool do_break = &tmp->common.list == &fib_node->entry_list; - mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, fib_entry); - mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib_entry); - mlxsw_sp_fib4_node_put(mlxsw_sp, fib_node); + mlxsw_sp_fib4_node_entry_unlink(mlxsw_sp, fib4_entry); + mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_entry); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); /* Break when entry list is empty and node was freed. * Otherwise, we'll access freed memory in the next * iteration. @@ -2752,6 +4642,23 @@ static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, } } +static void mlxsw_sp_fib6_node_flush(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_node *fib_node) +{ + struct mlxsw_sp_fib6_entry *fib6_entry, *tmp; + + list_for_each_entry_safe(fib6_entry, tmp, &fib_node->entry_list, + common.list) { + bool do_break = &tmp->common.list == &fib_node->entry_list; + + mlxsw_sp_fib6_node_entry_unlink(mlxsw_sp, fib6_entry); + mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); + mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); + if (do_break) + break; + } +} + static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { @@ -2760,7 +4667,7 @@ static void mlxsw_sp_fib_node_flush(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_fib4_node_flush(mlxsw_sp, fib_node); break; case MLXSW_SP_L3_PROTO_IPV6: - WARN_ON_ONCE(1); + mlxsw_sp_fib6_node_flush(mlxsw_sp, fib_node); break; } } @@ -2791,10 +4698,17 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) if (!mlxsw_sp_vr_is_used(vr)) continue; mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV4); + + /* If virtual router was only used for IPv4, then it's no + * longer used. + */ + if (!mlxsw_sp_vr_is_used(vr)) + continue; + mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); } } -static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp) { int err; @@ -2811,6 +4725,7 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) struct mlxsw_sp_fib_event_work { struct work_struct work; union { + struct fib6_entry_notifier_info fen6_info; struct fib_entry_notifier_info fen_info; struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; @@ -2819,7 +4734,7 @@ struct mlxsw_sp_fib_event_work { unsigned long event; }; -static void mlxsw_sp_router_fib_event_work(struct work_struct *work) +static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) { struct mlxsw_sp_fib_event_work *fib_work = container_of(work, struct mlxsw_sp_fib_event_work, work); @@ -2839,7 +4754,7 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) err = mlxsw_sp_router_fib4_add(mlxsw_sp, &fib_work->fen_info, replace, append); if (err) - mlxsw_sp_router_fib4_abort(mlxsw_sp); + mlxsw_sp_router_fib_abort(mlxsw_sp); fib_info_put(fib_work->fen_info.fi); break; case FIB_EVENT_ENTRY_DEL: @@ -2850,13 +4765,13 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) case FIB_EVENT_RULE_DEL: rule = fib_work->fr_info.rule; if (!fib4_rule_default(rule) && !rule->l3mdev) - mlxsw_sp_router_fib4_abort(mlxsw_sp); + mlxsw_sp_router_fib_abort(mlxsw_sp); fib_rule_put(rule); break; case FIB_EVENT_NH_ADD: /* fall through */ case FIB_EVENT_NH_DEL: - mlxsw_sp_nexthop_event(mlxsw_sp, fib_work->event, - fib_work->fnh_info.fib_nh); + mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event, + fib_work->fnh_info.fib_nh); fib_info_put(fib_work->fnh_info.fib_nh->nh_parent); break; } @@ -2864,6 +4779,87 @@ static void mlxsw_sp_router_fib_event_work(struct work_struct *work) kfree(fib_work); } +static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) +{ + struct mlxsw_sp_fib_event_work *fib_work = + container_of(work, struct mlxsw_sp_fib_event_work, work); + struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; + struct fib_rule *rule; + bool replace; + int err; + + rtnl_lock(); + switch (fib_work->event) { + case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_ADD: + replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; + err = mlxsw_sp_router_fib6_add(mlxsw_sp, + fib_work->fen6_info.rt, replace); + if (err) + mlxsw_sp_router_fib_abort(mlxsw_sp); + mlxsw_sp_rt6_release(fib_work->fen6_info.rt); + break; + case FIB_EVENT_ENTRY_DEL: + mlxsw_sp_router_fib6_del(mlxsw_sp, fib_work->fen6_info.rt); + mlxsw_sp_rt6_release(fib_work->fen6_info.rt); + break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + rule = fib_work->fr_info.rule; + if (!fib6_rule_default(rule) && !rule->l3mdev) + mlxsw_sp_router_fib_abort(mlxsw_sp); + fib_rule_put(rule); + break; + } + rtnl_unlock(); + kfree(fib_work); +} + +static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, + struct fib_notifier_info *info) +{ + switch (fib_work->event) { + case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_APPEND: /* fall through */ + case FIB_EVENT_ENTRY_ADD: /* fall through */ + case FIB_EVENT_ENTRY_DEL: + memcpy(&fib_work->fen_info, info, sizeof(fib_work->fen_info)); + /* Take referece on fib_info to prevent it from being + * freed while work is queued. Release it afterwards. + */ + fib_info_hold(fib_work->fen_info.fi); + break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; + case FIB_EVENT_NH_ADD: /* fall through */ + case FIB_EVENT_NH_DEL: + memcpy(&fib_work->fnh_info, info, sizeof(fib_work->fnh_info)); + fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent); + break; + } +} + +static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, + struct fib_notifier_info *info) +{ + switch (fib_work->event) { + case FIB_EVENT_ENTRY_REPLACE: /* fall through */ + case FIB_EVENT_ENTRY_ADD: /* fall through */ + case FIB_EVENT_ENTRY_DEL: + memcpy(&fib_work->fen6_info, info, sizeof(fib_work->fen6_info)); + rt6_hold(fib_work->fen6_info.rt); + break; + case FIB_EVENT_RULE_ADD: /* fall through */ + case FIB_EVENT_RULE_DEL: + memcpy(&fib_work->fr_info, info, sizeof(fib_work->fr_info)); + fib_rule_get(fib_work->fr_info.rule); + break; + } +} + /* Called with rcu_read_lock() */ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, unsigned long event, void *ptr) @@ -2879,31 +4875,18 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, if (WARN_ON(!fib_work)) return NOTIFY_BAD; - INIT_WORK(&fib_work->work, mlxsw_sp_router_fib_event_work); router = container_of(nb, struct mlxsw_sp_router, fib_nb); fib_work->mlxsw_sp = router->mlxsw_sp; fib_work->event = event; - switch (event) { - case FIB_EVENT_ENTRY_REPLACE: /* fall through */ - case FIB_EVENT_ENTRY_APPEND: /* fall through */ - case FIB_EVENT_ENTRY_ADD: /* fall through */ - case FIB_EVENT_ENTRY_DEL: - memcpy(&fib_work->fen_info, ptr, sizeof(fib_work->fen_info)); - /* Take referece on fib_info to prevent it from being - * freed while work is queued. Release it afterwards. - */ - fib_info_hold(fib_work->fen_info.fi); + switch (info->family) { + case AF_INET: + INIT_WORK(&fib_work->work, mlxsw_sp_router_fib4_event_work); + mlxsw_sp_router_fib4_event(fib_work, info); break; - case FIB_EVENT_RULE_ADD: /* fall through */ - case FIB_EVENT_RULE_DEL: - memcpy(&fib_work->fr_info, ptr, sizeof(fib_work->fr_info)); - fib_rule_get(fib_work->fr_info.rule); - break; - case FIB_EVENT_NH_ADD: /* fall through */ - case FIB_EVENT_NH_DEL: - memcpy(&fib_work->fnh_info, ptr, sizeof(fib_work->fnh_info)); - fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent); + case AF_INET6: + INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work); + mlxsw_sp_router_fib6_event(fib_work, info); break; } @@ -2948,17 +4931,28 @@ static void mlxsw_sp_router_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_neigh_rif_gone_sync(mlxsw_sp, rif); } -static bool mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, - const struct in_device *in_dev, - unsigned long event) +static bool +mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, struct net_device *dev, + unsigned long event) { + struct inet6_dev *inet6_dev; + bool addr_list_empty = true; + struct in_device *idev; + switch (event) { case NETDEV_UP: - if (!rif) - return true; - return false; + return rif == NULL; case NETDEV_DOWN: - if (rif && !in_dev->ifa_list && + idev = __in_dev_get_rtnl(dev); + if (idev && idev->ifa_list) + addr_list_empty = false; + + inet6_dev = __in6_dev_get(dev); + if (addr_list_empty && inet6_dev && + !list_empty(&inet6_dev->addr_list)) + addr_list_empty = false; + + if (rif && addr_list_empty && !netif_is_l3_slave(rif->dev)) return true; /* It is possible we already removed the RIF ourselves @@ -2977,7 +4971,10 @@ mlxsw_sp_dev_rif_type(const struct mlxsw_sp *mlxsw_sp, { enum mlxsw_sp_fid_type type; - /* RIF type is derived from the type of the underlying FID */ + if (mlxsw_sp_netdev_ipip_type(mlxsw_sp, dev, NULL)) + return MLXSW_SP_RIF_TYPE_IPIP_LB; + + /* Otherwise RIF type is derived from the type of the underlying FID. */ if (is_vlan_dev(dev) && netif_is_bridge_master(vlan_dev_real_dev(dev))) type = MLXSW_SP_FID_TYPE_8021Q; else if (netif_is_bridge_master(dev) && br_vlan_enabled(dev)) @@ -3036,6 +5033,16 @@ u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif) return rif->rif_index; } +u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif) +{ + return lb_rif->common.rif_index; +} + +u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif) +{ + return lb_rif->ul_vr_id; +} + int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif) { return rif->dev->ifindex; @@ -3047,9 +5054,9 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, { u32 tb_id = l3mdev_fib_table(params->dev); const struct mlxsw_sp_rif_ops *ops; + struct mlxsw_sp_fid *fid = NULL; enum mlxsw_sp_rif_type type; struct mlxsw_sp_rif *rif; - struct mlxsw_sp_fid *fid; struct mlxsw_sp_vr *vr; u16 rif_index; int err; @@ -3073,12 +5080,14 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, rif->mlxsw_sp = mlxsw_sp; rif->ops = ops; - fid = ops->fid_get(rif); - if (IS_ERR(fid)) { - err = PTR_ERR(fid); - goto err_fid_get; + if (ops->fid_get) { + fid = ops->fid_get(rif); + if (IS_ERR(fid)) { + err = PTR_ERR(fid); + goto err_fid_get; + } + rif->fid = fid; } - rif->fid = fid; if (ops->setup) ops->setup(rif, params); @@ -3087,22 +5096,15 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_configure; - err = mlxsw_sp_rif_fdb_op(mlxsw_sp, params->dev->dev_addr, - mlxsw_sp_fid_index(fid), true); - if (err) - goto err_rif_fdb_op; - mlxsw_sp_rif_counters_alloc(rif); - mlxsw_sp_fid_rif_set(fid, rif); mlxsw_sp->router->rifs[rif_index] = rif; vr->rif_count++; return rif; -err_rif_fdb_op: - ops->deconfigure(rif); err_configure: - mlxsw_sp_fid_put(fid); + if (fid) + mlxsw_sp_fid_put(fid); err_fid_get: kfree(rif); err_rif_alloc: @@ -3123,12 +5125,11 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) vr->rif_count--; mlxsw_sp->router->rifs[rif->rif_index] = NULL; - mlxsw_sp_fid_rif_set(fid, NULL); mlxsw_sp_rif_counters_free(rif); - mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->dev->dev_addr, - mlxsw_sp_fid_index(fid), false); ops->deconfigure(rif); - mlxsw_sp_fid_put(fid); + if (fid) + /* Loopback RIFs are not associated with a FID. */ + mlxsw_sp_fid_put(fid); kfree(rif); mlxsw_sp_vr_put(vr); } @@ -3356,7 +5357,7 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused, goto out; rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); - if (!mlxsw_sp_rif_should_config(rif, ifa->ifa_dev, event)) + if (!mlxsw_sp_rif_should_config(rif, dev, event)) goto out; err = __mlxsw_sp_inetaddr_event(dev, event); @@ -3364,6 +5365,61 @@ out: return notifier_from_errno(err); } +struct mlxsw_sp_inet6addr_event_work { + struct work_struct work; + struct net_device *dev; + unsigned long event; +}; + +static void mlxsw_sp_inet6addr_event_work(struct work_struct *work) +{ + struct mlxsw_sp_inet6addr_event_work *inet6addr_work = + container_of(work, struct mlxsw_sp_inet6addr_event_work, work); + struct net_device *dev = inet6addr_work->dev; + unsigned long event = inet6addr_work->event; + struct mlxsw_sp *mlxsw_sp; + struct mlxsw_sp_rif *rif; + + rtnl_lock(); + mlxsw_sp = mlxsw_sp_lower_get(dev); + if (!mlxsw_sp) + goto out; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!mlxsw_sp_rif_should_config(rif, dev, event)) + goto out; + + __mlxsw_sp_inetaddr_event(dev, event); +out: + rtnl_unlock(); + dev_put(dev); + kfree(inet6addr_work); +} + +/* Called with rcu_read_lock() */ +int mlxsw_sp_inet6addr_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *if6 = (struct inet6_ifaddr *) ptr; + struct mlxsw_sp_inet6addr_event_work *inet6addr_work; + struct net_device *dev = if6->idev->dev; + + if (!mlxsw_sp_port_dev_lower_find_rcu(dev)) + return NOTIFY_DONE; + + inet6addr_work = kzalloc(sizeof(*inet6addr_work), GFP_ATOMIC); + if (!inet6addr_work) + return NOTIFY_BAD; + + INIT_WORK(&inet6addr_work->work, mlxsw_sp_inet6addr_event_work); + inet6addr_work->dev = dev; + inet6addr_work->event = event; + dev_hold(dev); + mlxsw_core_schedule_work(&inet6addr_work->work); + + return NOTIFY_DONE; +} + static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index, const char *mac, int mtu) { @@ -3501,8 +5557,8 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable) rif_subport = mlxsw_sp_rif_subport_rif(rif); mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_SP_IF, - rif->rif_index, rif->vr_id, rif->dev->mtu, - rif->dev->dev_addr); + rif->rif_index, rif->vr_id, rif->dev->mtu); + mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr); mlxsw_reg_ritr_sp_if_pack(ritr_pl, rif_subport->lag, rif_subport->lag ? rif_subport->lag_id : rif_subport->system_port, @@ -3513,11 +5569,32 @@ static int mlxsw_sp_rif_subport_op(struct mlxsw_sp_rif *rif, bool enable) static int mlxsw_sp_rif_subport_configure(struct mlxsw_sp_rif *rif) { - return mlxsw_sp_rif_subport_op(rif, true); + int err; + + err = mlxsw_sp_rif_subport_op(rif, true); + if (err) + return err; + + err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_fid_index(rif->fid), true); + if (err) + goto err_rif_fdb_op; + + mlxsw_sp_fid_rif_set(rif->fid, rif); + return 0; + +err_rif_fdb_op: + mlxsw_sp_rif_subport_op(rif, false); + return err; } static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif) { + struct mlxsw_sp_fid *fid = rif->fid; + + mlxsw_sp_fid_rif_set(fid, NULL); + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_fid_index(fid), false); mlxsw_sp_rif_subport_op(rif, false); } @@ -3544,7 +5621,8 @@ static int mlxsw_sp_rif_vlan_fid_op(struct mlxsw_sp_rif *rif, char ritr_pl[MLXSW_REG_RITR_LEN]; mlxsw_reg_ritr_pack(ritr_pl, enable, type, rif->rif_index, rif->vr_id, - rif->dev->mtu, rif->dev->dev_addr); + rif->dev->mtu); + mlxsw_reg_ritr_mac_pack(ritr_pl, rif->dev->dev_addr); mlxsw_reg_ritr_fid_set(ritr_pl, type, vid_fid); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); @@ -3565,25 +5643,48 @@ static int mlxsw_sp_rif_vlan_configure(struct mlxsw_sp_rif *rif) if (err) return err; + err = mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, + mlxsw_sp_router_port(mlxsw_sp), true); + if (err) + goto err_fid_mc_flood_set; + err = mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, mlxsw_sp_router_port(mlxsw_sp), true); if (err) goto err_fid_bc_flood_set; + err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_fid_index(rif->fid), true); + if (err) + goto err_rif_fdb_op; + + mlxsw_sp_fid_rif_set(rif->fid, rif); return 0; +err_rif_fdb_op: + mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, + mlxsw_sp_router_port(mlxsw_sp), false); err_fid_bc_flood_set: + mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, + mlxsw_sp_router_port(mlxsw_sp), false); +err_fid_mc_flood_set: mlxsw_sp_rif_vlan_fid_op(rif, MLXSW_REG_RITR_VLAN_IF, vid, false); return err; } static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif) { - struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid); + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_fid *fid = rif->fid; + mlxsw_sp_fid_rif_set(fid, NULL); + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_fid_index(fid), false); mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, mlxsw_sp_router_port(mlxsw_sp), false); + mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, + mlxsw_sp_router_port(mlxsw_sp), false); mlxsw_sp_rif_vlan_fid_op(rif, MLXSW_REG_RITR_VLAN_IF, vid, false); } @@ -3614,25 +5715,48 @@ static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif) if (err) return err; + err = mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, + mlxsw_sp_router_port(mlxsw_sp), true); + if (err) + goto err_fid_mc_flood_set; + err = mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, mlxsw_sp_router_port(mlxsw_sp), true); if (err) goto err_fid_bc_flood_set; + err = mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_fid_index(rif->fid), true); + if (err) + goto err_rif_fdb_op; + + mlxsw_sp_fid_rif_set(rif->fid, rif); return 0; +err_rif_fdb_op: + mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, + mlxsw_sp_router_port(mlxsw_sp), false); err_fid_bc_flood_set: + mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, + mlxsw_sp_router_port(mlxsw_sp), false); +err_fid_mc_flood_set: mlxsw_sp_rif_vlan_fid_op(rif, MLXSW_REG_RITR_FID_IF, fid_index, false); return err; } static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif) { - struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; u16 fid_index = mlxsw_sp_fid_index(rif->fid); + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_fid *fid = rif->fid; + mlxsw_sp_fid_rif_set(fid, NULL); + mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr, + mlxsw_sp_fid_index(fid), false); mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC, mlxsw_sp_router_port(mlxsw_sp), false); + mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC, + mlxsw_sp_router_port(mlxsw_sp), false); mlxsw_sp_rif_vlan_fid_op(rif, MLXSW_REG_RITR_FID_IF, fid_index, false); } @@ -3650,10 +5774,104 @@ static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = { .fid_get = mlxsw_sp_rif_fid_fid_get, }; +static struct mlxsw_sp_rif_ipip_lb * +mlxsw_sp_rif_ipip_lb_rif(struct mlxsw_sp_rif *rif) +{ + return container_of(rif, struct mlxsw_sp_rif_ipip_lb, common); +} + +static void +mlxsw_sp_rif_ipip_lb_setup(struct mlxsw_sp_rif *rif, + const struct mlxsw_sp_rif_params *params) +{ + struct mlxsw_sp_rif_params_ipip_lb *params_lb; + struct mlxsw_sp_rif_ipip_lb *rif_lb; + + params_lb = container_of(params, struct mlxsw_sp_rif_params_ipip_lb, + common); + rif_lb = mlxsw_sp_rif_ipip_lb_rif(rif); + rif_lb->lb_config = params_lb->lb_config; +} + +static int +mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, + struct mlxsw_sp_vr *ul_vr, bool enable) +{ + struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config; + struct mlxsw_sp_rif *rif = &lb_rif->common; + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + char ritr_pl[MLXSW_REG_RITR_LEN]; + u32 saddr4; + + switch (lb_cf.ul_protocol) { + case MLXSW_SP_L3_PROTO_IPV4: + saddr4 = be32_to_cpu(lb_cf.saddr.addr4); + mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF, + rif->rif_index, rif->vr_id, rif->dev->mtu); + mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt, + MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET, + ul_vr->id, saddr4, lb_cf.okey); + break; + + case MLXSW_SP_L3_PROTO_IPV6: + return -EAFNOSUPPORT; + } + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); +} + +static int +mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif) +{ + struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif); + u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev); + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_vr *ul_vr; + int err; + + ul_vr = mlxsw_sp_vr_get(mlxsw_sp, ul_tb_id); + if (IS_ERR(ul_vr)) + return PTR_ERR(ul_vr); + + err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, true); + if (err) + goto err_loopback_op; + + lb_rif->ul_vr_id = ul_vr->id; + ++ul_vr->rif_count; + return 0; + +err_loopback_op: + mlxsw_sp_vr_put(ul_vr); + return err; +} + +static void mlxsw_sp_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif) +{ + struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif); + struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; + struct mlxsw_sp_vr *ul_vr; + + ul_vr = &mlxsw_sp->router->vrs[lb_rif->ul_vr_id]; + mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, false); + + --ul_vr->rif_count; + mlxsw_sp_vr_put(ul_vr); +} + +static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_ipip_lb_ops = { + .type = MLXSW_SP_RIF_TYPE_IPIP_LB, + .rif_size = sizeof(struct mlxsw_sp_rif_ipip_lb), + .setup = mlxsw_sp_rif_ipip_lb_setup, + .configure = mlxsw_sp_rif_ipip_lb_configure, + .deconfigure = mlxsw_sp_rif_ipip_lb_deconfigure, +}; + static const struct mlxsw_sp_rif_ops *mlxsw_sp_rif_ops_arr[] = { [MLXSW_SP_RIF_TYPE_SUBPORT] = &mlxsw_sp_rif_subport_ops, [MLXSW_SP_RIF_TYPE_VLAN] = &mlxsw_sp_rif_vlan_ops, [MLXSW_SP_RIF_TYPE_FID] = &mlxsw_sp_rif_fid_ops, + [MLXSW_SP_RIF_TYPE_IPIP_LB] = &mlxsw_sp_rif_ipip_lb_ops, }; static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp) @@ -3681,6 +5899,18 @@ static void mlxsw_sp_rifs_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->router->rifs); } +static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->router->ipip_ops_arr = mlxsw_sp_ipip_ops_arr; + INIT_LIST_HEAD(&mlxsw_sp->router->ipip_list); + return 0; +} + +static void mlxsw_sp_ipips_fini(struct mlxsw_sp *mlxsw_sp) +{ + WARN_ON(!list_empty(&mlxsw_sp->router->ipip_list)); +} + static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) { struct mlxsw_sp_router *router; @@ -3704,7 +5934,7 @@ static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) return -EIO; max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); - mlxsw_reg_rgcr_pack(rgcr_pl, true); + mlxsw_reg_rgcr_pack(rgcr_pl, true, true); mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); if (err) @@ -3716,7 +5946,7 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) { char rgcr_pl[MLXSW_REG_RGCR_LEN]; - mlxsw_reg_rgcr_pack(rgcr_pl, false); + mlxsw_reg_rgcr_pack(rgcr_pl, false, false); mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); } @@ -3740,6 +5970,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp) if (err) goto err_rifs_init; + err = mlxsw_sp_ipips_init(mlxsw_sp); + if (err) + goto err_ipips_init; + err = rhashtable_init(&mlxsw_sp->router->nexthop_ht, &mlxsw_sp_nexthop_ht_params); if (err) @@ -3781,6 +6015,8 @@ err_lpm_init: err_nexthop_group_ht_init: rhashtable_destroy(&mlxsw_sp->router->nexthop_ht); err_nexthop_ht_init: + mlxsw_sp_ipips_fini(mlxsw_sp); +err_ipips_init: mlxsw_sp_rifs_fini(mlxsw_sp); err_rifs_init: __mlxsw_sp_router_fini(mlxsw_sp); @@ -3797,6 +6033,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_lpm_fini(mlxsw_sp); rhashtable_destroy(&mlxsw_sp->router->nexthop_group_ht); rhashtable_destroy(&mlxsw_sp->router->nexthop_ht); + mlxsw_sp_ipips_fini(mlxsw_sp); mlxsw_sp_rifs_fini(mlxsw_sp); __mlxsw_sp_router_fini(mlxsw_sp); kfree(mlxsw_sp->router); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index a3e8d2b25148..345fcc4f38e9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -36,15 +36,38 @@ #define _MLXSW_ROUTER_H_ #include "spectrum.h" +#include "reg.h" + +enum mlxsw_sp_l3proto { + MLXSW_SP_L3_PROTO_IPV4, + MLXSW_SP_L3_PROTO_IPV6, +}; + +union mlxsw_sp_l3addr { + __be32 addr4; + struct in6_addr addr6; +}; + +struct mlxsw_sp_rif_ipip_lb; +struct mlxsw_sp_rif_ipip_lb_config { + enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; + u32 okey; + enum mlxsw_sp_l3proto ul_protocol; /* Underlay. */ + union mlxsw_sp_l3addr saddr; +}; enum mlxsw_sp_rif_counter_dir { MLXSW_SP_RIF_COUNTER_INGRESS, MLXSW_SP_RIF_COUNTER_EGRESS, }; +struct mlxsw_sp_neigh_entry; + struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp, u16 rif_index); u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif); +u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif); +u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif); int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif); int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif, @@ -56,5 +79,33 @@ void mlxsw_sp_rif_counter_free(struct mlxsw_sp *mlxsw_sp, int mlxsw_sp_rif_counter_alloc(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif, enum mlxsw_sp_rif_counter_dir dir); +struct mlxsw_sp_neigh_entry * +mlxsw_sp_rif_neigh_next(struct mlxsw_sp_rif *rif, + struct mlxsw_sp_neigh_entry *neigh_entry); +int mlxsw_sp_neigh_entry_type(struct mlxsw_sp_neigh_entry *neigh_entry); +unsigned char * +mlxsw_sp_neigh_entry_ha(struct mlxsw_sp_neigh_entry *neigh_entry); +u32 mlxsw_sp_neigh4_entry_dip(struct mlxsw_sp_neigh_entry *neigh_entry); +struct in6_addr * +mlxsw_sp_neigh6_entry_dip(struct mlxsw_sp_neigh_entry *neigh_entry); + +#define mlxsw_sp_rif_neigh_for_each(neigh_entry, rif) \ + for (neigh_entry = mlxsw_sp_rif_neigh_next(rif, NULL); neigh_entry; \ + neigh_entry = mlxsw_sp_rif_neigh_next(rif, neigh_entry)) +int mlxsw_sp_neigh_counter_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry, + u64 *p_counter); +void +mlxsw_sp_neigh_entry_counter_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_neigh_entry *neigh_entry, + bool adding); +bool mlxsw_sp_neigh_ipv6_ignore(struct mlxsw_sp_neigh_entry *neigh_entry); +union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, + const struct net_device *ol_dev); +union mlxsw_sp_l3addr +mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, + const struct net_device *ol_dev); +__be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev); #endif /* _MLXSW_ROUTER_H_*/ diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c index 74341fe0eb25..ab7a29846bfa 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchib.c @@ -497,7 +497,7 @@ static void mlxsw_sib_fini(struct mlxsw_core *mlxsw_core) mlxsw_sib_ports_remove(mlxsw_sib); } -static struct mlxsw_config_profile mlxsw_sib_config_profile = { +static const struct mlxsw_config_profile mlxsw_sib_config_profile = { .used_max_system_port = 1, .max_system_port = 48000, .used_max_ib_mc = 1, diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 3b0f72455681..f3c29bbf07e2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -1674,7 +1674,7 @@ static void mlxsw_sx_fini(struct mlxsw_core *mlxsw_core) mlxsw_sx_ports_remove(mlxsw_sx); } -static struct mlxsw_config_profile mlxsw_sx_config_profile = { +static const struct mlxsw_config_profile mlxsw_sx_config_profile = { .used_max_vepa_channels = 1, .max_vepa_channels = 0, .used_max_mid = 1, diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 12b5ed58f3eb..f396a1fef633 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -61,11 +61,33 @@ enum { MLXSW_TRAP_ID_MTUERROR = 0x52, MLXSW_TRAP_ID_TTLERROR = 0x53, MLXSW_TRAP_ID_LBERROR = 0x54, - MLXSW_TRAP_ID_OSPF = 0x55, + MLXSW_TRAP_ID_IPV4_OSPF = 0x55, MLXSW_TRAP_ID_IP2ME = 0x5F, + MLXSW_TRAP_ID_IPV6_UNSPECIFIED_ADDRESS = 0x60, + MLXSW_TRAP_ID_IPV6_LINK_LOCAL_DEST = 0x61, + MLXSW_TRAP_ID_IPV6_LINK_LOCAL_SRC = 0x62, + MLXSW_TRAP_ID_IPV6_ALL_NODES_LINK = 0x63, + MLXSW_TRAP_ID_IPV6_OSPF = 0x64, + MLXSW_TRAP_ID_IPV6_MLDV12_LISTENER_QUERY = 0x65, + MLXSW_TRAP_ID_IPV6_MLDV1_LISTENER_REPORT = 0x66, + MLXSW_TRAP_ID_IPV6_MLDV1_LISTENER_DONE = 0x67, + MLXSW_TRAP_ID_IPV6_MLDV2_LISTENER_REPORT = 0x68, + MLXSW_TRAP_ID_IPV6_DHCP = 0x69, + MLXSW_TRAP_ID_IPV6_ALL_ROUTERS_LINK = 0x6F, MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70, - MLXSW_TRAP_ID_BGP_IPV4 = 0x88, + MLXSW_TRAP_ID_IPV4_BGP = 0x88, + MLXSW_TRAP_ID_IPV6_BGP = 0x89, + MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A, + MLXSW_TRAP_ID_L3_IPV6_ROUTER_ADVERTISMENT = 0x8B, + MLXSW_TRAP_ID_L3_IPV6_NEIGHBOR_SOLICITATION = 0x8C, + MLXSW_TRAP_ID_L3_IPV6_NEIGHBOR_ADVERTISMENT = 0x8D, + MLXSW_TRAP_ID_L3_IPV6_REDIRECTION = 0x8E, MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90, + MLXSW_TRAP_ID_IPV6_MC_LINK_LOCAL_DEST = 0x91, + MLXSW_TRAP_ID_HOST_MISS_IPV6 = 0x92, + MLXSW_TRAP_ID_IPIP_DECAP_ERROR = 0xB1, + MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6, + MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7, MLXSW_TRAP_ID_ACL0 = 0x1C0, MLXSW_TRAP_ID_MAX = 0x1FF diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index c0d7d5eec7e7..2e4effa9fe45 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -161,7 +161,7 @@ static void moxart_mac_setup_desc_ring(struct net_device *ndev) priv->rx_head = 0; - /* reset the MAC controller TX/RX desciptor base address */ + /* reset the MAC controller TX/RX descriptor base address */ writel(priv->tx_base, priv->base + REG_TXR_BASE_ADDRESS); writel(priv->rx_base, priv->base + REG_RXR_BASE_ADDRESS); } @@ -269,9 +269,8 @@ rx_next: priv->rx_head = rx_head; } - if (rx < budget) { + if (rx < budget) napi_complete_done(napi, rx); - } priv->reg_imr |= RPKT_FINISH_M; writel(priv->reg_imr, priv->base + REG_INTERRUPT_MASK); @@ -289,8 +288,8 @@ static int moxart_tx_queue_space(struct net_device *ndev) static void moxart_tx_finished(struct net_device *ndev) { struct moxart_mac_priv_t *priv = netdev_priv(ndev); - unsigned tx_head = priv->tx_head; - unsigned tx_tail = priv->tx_tail; + unsigned int tx_head = priv->tx_head; + unsigned int tx_tail = priv->tx_tail; while (tx_tail != tx_head) { dma_unmap_single(&ndev->dev, priv->tx_mapping[tx_tail], @@ -312,7 +311,7 @@ static void moxart_tx_finished(struct net_device *ndev) static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id) { - struct net_device *ndev = (struct net_device *) dev_id; + struct net_device *ndev = (struct net_device *)dev_id; struct moxart_mac_priv_t *priv = netdev_priv(ndev); unsigned int ists = readl(priv->base + REG_INTERRUPT_STATUS); @@ -495,7 +494,7 @@ static int moxart_mac_probe(struct platform_device *pdev) priv->tx_desc_base = dma_alloc_coherent(NULL, TX_REG_DESC_SIZE * TX_DESC_NUM, &priv->tx_base, GFP_DMA | GFP_KERNEL); - if (priv->tx_desc_base == NULL) { + if (!priv->tx_desc_base) { ret = -ENOMEM; goto init_fail; } @@ -503,7 +502,7 @@ static int moxart_mac_probe(struct platform_device *pdev) priv->rx_desc_base = dma_alloc_coherent(NULL, RX_REG_DESC_SIZE * RX_DESC_NUM, &priv->rx_base, GFP_DMA | GFP_KERNEL); - if (priv->rx_desc_base == NULL) { + if (!priv->rx_desc_base) { ret = -ENOMEM; goto init_fail; } diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h index 686b8957d5cf..bee608b547d1 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.h +++ b/drivers/net/ethernet/moxa/moxart_ether.h @@ -55,17 +55,17 @@ #define RX_DESC2_ADDRESS_VIRT 4 #define TX_DESC_NUM 64 -#define TX_DESC_NUM_MASK (TX_DESC_NUM-1) +#define TX_DESC_NUM_MASK (TX_DESC_NUM - 1) #define TX_NEXT(N) (((N) + 1) & (TX_DESC_NUM_MASK)) #define TX_BUF_SIZE 1600 -#define TX_BUF_SIZE_MAX (TX_DESC1_BUF_SIZE_MASK+1) +#define TX_BUF_SIZE_MAX (TX_DESC1_BUF_SIZE_MASK + 1) #define TX_WAKE_THRESHOLD 16 #define RX_DESC_NUM 64 -#define RX_DESC_NUM_MASK (RX_DESC_NUM-1) +#define RX_DESC_NUM_MASK (RX_DESC_NUM - 1) #define RX_NEXT(N) (((N) + 1) & (RX_DESC_NUM_MASK)) #define RX_BUF_SIZE 1600 -#define RX_BUF_SIZE_MAX (RX_DESC1_BUF_SIZE_MASK+1) +#define RX_BUF_SIZE_MAX (RX_DESC1_BUF_SIZE_MASK + 1) #define REG_INTERRUPT_STATUS 0 #define REG_INTERRUPT_MASK 4 diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index fd2ec36c6fa1..462eda926b1c 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -42,8 +42,6 @@ * aggregated as a single large packet * napi: This parameter used to enable/disable NAPI (polling Rx) * Possible values '1' for enable and '0' for disable. Default is '1' - * ufo: This parameter used to enable/disable UDP Fragmentation Offload(UFO) - * Possible values '1' for enable and '0' for disable. Default is '0' * vlan_tag_strip: This can be used to enable or disable vlan stripping. * Possible values '1' for enable , '0' for disable. * Default is '2' - which means disable in promisc mode @@ -453,7 +451,6 @@ S2IO_PARM_INT(lro_max_pkts, 0xFFFF); S2IO_PARM_INT(indicate_max_pkts, 0); S2IO_PARM_INT(napi, 1); -S2IO_PARM_INT(ufo, 0); S2IO_PARM_INT(vlan_tag_strip, NO_STRIP_IN_PROMISC); static unsigned int tx_fifo_len[MAX_TX_FIFOS] = @@ -4128,32 +4125,6 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev) } frg_len = skb_headlen(skb); - if (offload_type == SKB_GSO_UDP) { - int ufo_size; - - ufo_size = s2io_udp_mss(skb); - ufo_size &= ~7; - txdp->Control_1 |= TXD_UFO_EN; - txdp->Control_1 |= TXD_UFO_MSS(ufo_size); - txdp->Control_1 |= TXD_BUFFER0_SIZE(8); -#ifdef __BIG_ENDIAN - /* both variants do cpu_to_be64(be32_to_cpu(...)) */ - fifo->ufo_in_band_v[put_off] = - (__force u64)skb_shinfo(skb)->ip6_frag_id; -#else - fifo->ufo_in_band_v[put_off] = - (__force u64)skb_shinfo(skb)->ip6_frag_id << 32; -#endif - txdp->Host_Control = (unsigned long)fifo->ufo_in_band_v; - txdp->Buffer_Pointer = pci_map_single(sp->pdev, - fifo->ufo_in_band_v, - sizeof(u64), - PCI_DMA_TODEVICE); - if (pci_dma_mapping_error(sp->pdev, txdp->Buffer_Pointer)) - goto pci_map_failed; - txdp++; - } - txdp->Buffer_Pointer = pci_map_single(sp->pdev, skb->data, frg_len, PCI_DMA_TODEVICE); if (pci_dma_mapping_error(sp->pdev, txdp->Buffer_Pointer)) @@ -4161,8 +4132,6 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev) txdp->Host_Control = (unsigned long)skb; txdp->Control_1 |= TXD_BUFFER0_SIZE(frg_len); - if (offload_type == SKB_GSO_UDP) - txdp->Control_1 |= TXD_UFO_EN; frg_cnt = skb_shinfo(skb)->nr_frags; /* For fragmented SKB. */ @@ -4177,14 +4146,9 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev) skb_frag_size(frag), DMA_TO_DEVICE); txdp->Control_1 = TXD_BUFFER0_SIZE(skb_frag_size(frag)); - if (offload_type == SKB_GSO_UDP) - txdp->Control_1 |= TXD_UFO_EN; } txdp->Control_1 |= TXD_GATHER_CODE_LAST; - if (offload_type == SKB_GSO_UDP) - frg_cnt++; /* as Txd0 was used for inband header */ - tx_fifo = mac_control->tx_FIFO_start[queue]; val64 = fifo->list_info[put_off].list_phy_addr; writeq(val64, &tx_fifo->TxDL_Pointer); @@ -7910,11 +7874,6 @@ s2io_init_nic(struct pci_dev *pdev, const struct pci_device_id *pre) NETIF_F_RXCSUM | NETIF_F_LRO; dev->features |= dev->hw_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; - if (sp->device_type & XFRAME_II_DEVICE) { - dev->hw_features |= NETIF_F_UFO; - if (ufo) - dev->features |= NETIF_F_UFO; - } if (sp->high_dma_flag == true) dev->features |= NETIF_F_HIGHDMA; dev->watchdog_timeo = WATCH_DOG_TIMEOUT; @@ -8147,10 +8106,6 @@ s2io_init_nic(struct pci_dev *pdev, const struct pci_device_id *pre) DBG_PRINT(ERR_DBG, "%s: Large receive offload enabled\n", dev->name); - if (ufo) - DBG_PRINT(ERR_DBG, - "%s: UDP Fragmentation Offload(UFO) enabled\n", - dev->name); /* Initialize device name */ snprintf(sp->name, sizeof(sp->name), "%s Neterion %s", dev->name, sp->product_name); diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig index 0e331e2f685a..ae0c46ba7546 100644 --- a/drivers/net/ethernet/netronome/Kconfig +++ b/drivers/net/ethernet/netronome/Kconfig @@ -29,6 +29,7 @@ config NFP_APP_FLOWER bool "NFP4000/NFP6000 TC Flower offload support" depends on NFP depends on NET_SWITCHDEV + default y ---help--- Enable driver support for TC Flower offload on NFP4000 and NFP6000. Say Y, if you are planning to make use of TC Flower offload diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index b8e1358868bd..96e579a15cbe 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -23,6 +23,7 @@ nfp-objs := \ nfp_net_ethtool.o \ nfp_net_main.o \ nfp_net_repr.o \ + nfp_net_sriov.o \ nfp_netvf_main.o \ nfp_port.o \ bpf/main.o \ diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 8e57fda6b8b5..239dfbe8a0a1 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1238,6 +1238,16 @@ static int jge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true); } +static int jlt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false); +} + +static int jle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true); +} + static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; @@ -1325,6 +1335,16 @@ static int jge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true); } +static int jlt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false); +} + +static int jle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true); +} + static int jset_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return wrp_test_reg(nfp_prog, meta, ALU_OP_AND, BR_BNE); @@ -1383,11 +1403,15 @@ static const instr_cb_t instr_cb[256] = { [BPF_JMP | BPF_JEQ | BPF_K] = jeq_imm, [BPF_JMP | BPF_JGT | BPF_K] = jgt_imm, [BPF_JMP | BPF_JGE | BPF_K] = jge_imm, + [BPF_JMP | BPF_JLT | BPF_K] = jlt_imm, + [BPF_JMP | BPF_JLE | BPF_K] = jle_imm, [BPF_JMP | BPF_JSET | BPF_K] = jset_imm, [BPF_JMP | BPF_JNE | BPF_K] = jne_imm, [BPF_JMP | BPF_JEQ | BPF_X] = jeq_reg, [BPF_JMP | BPF_JGT | BPF_X] = jgt_reg, [BPF_JMP | BPF_JGE | BPF_X] = jge_reg, + [BPF_JMP | BPF_JLT | BPF_X] = jlt_reg, + [BPF_JMP | BPF_JLE | BPF_X] = jle_reg, [BPF_JMP | BPF_JSET | BPF_X] = jset_reg, [BPF_JMP | BPF_JNE | BPF_X] = jne_reg, [BPF_JMP | BPF_EXIT] = goto_out, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index afbdf5fd4e4f..be2cf10a2cd7 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -84,7 +84,7 @@ static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn) } static int -nfp_bpf_vnic_init(struct nfp_app *app, struct nfp_net *nn, unsigned int id) +nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) { struct nfp_net_bpf_priv *priv; int ret; @@ -106,14 +106,14 @@ nfp_bpf_vnic_init(struct nfp_app *app, struct nfp_net *nn, unsigned int id) setup_timer(&priv->rx_filter_stats_timer, nfp_net_filter_stats_timer, (unsigned long)nn); - ret = nfp_app_nic_vnic_init(app, nn, id); + ret = nfp_app_nic_vnic_alloc(app, nn, id); if (ret) kfree(priv); return ret; } -static void nfp_bpf_vnic_clean(struct nfp_app *app, struct nfp_net *nn) +static void nfp_bpf_vnic_free(struct nfp_app *app, struct nfp_net *nn) { if (nn->dp.bpf_offload_xdp) nfp_bpf_xdp_offload(app, nn, NULL); @@ -121,23 +121,21 @@ static void nfp_bpf_vnic_clean(struct nfp_app *app, struct nfp_net *nn) } static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev, - u32 handle, __be16 proto, struct tc_to_netdev *tc) + enum tc_setup_type type, void *type_data) { + struct tc_cls_bpf_offload *cls_bpf = type_data; struct nfp_net *nn = netdev_priv(netdev); - if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS)) - return -EOPNOTSUPP; - if (proto != htons(ETH_P_ALL)) + if (type != TC_SETUP_CLSBPF || !nfp_net_ebpf_capable(nn) || + !is_classid_clsact_ingress(cls_bpf->common.classid) || + cls_bpf->common.protocol != htons(ETH_P_ALL) || + cls_bpf->common.chain_index) return -EOPNOTSUPP; - if (tc->type == TC_SETUP_CLSBPF && nfp_net_ebpf_capable(nn)) { - if (!nn->dp.bpf_offload_xdp) - return nfp_net_bpf_offload(nn, tc->cls_bpf); - else - return -EBUSY; - } + if (nn->dp.bpf_offload_xdp) + return -EBUSY; - return -EINVAL; + return nfp_net_bpf_offload(nn, cls_bpf); } static bool nfp_bpf_tc_busy(struct nfp_app *app, struct nfp_net *nn) @@ -151,8 +149,8 @@ const struct nfp_app_type app_bpf = { .extra_cap = nfp_bpf_extra_cap, - .vnic_init = nfp_bpf_vnic_init, - .vnic_clean = nfp_bpf_vnic_clean, + .vnic_alloc = nfp_bpf_vnic_alloc, + .vnic_free = nfp_bpf_vnic_free, .setup_tc = nfp_bpf_setup_tc, .tc_busy = nfp_bpf_tc_busy, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 78d80a364edb..a88bb5bc0082 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -115,14 +115,14 @@ nfp_net_bpf_get_act(struct nfp_net *nn, struct tc_cls_bpf_offload *cls_bpf) /* TC direct action */ if (cls_bpf->exts_integrated) { - if (tc_no_actions(cls_bpf->exts)) + if (!tcf_exts_has_actions(cls_bpf->exts)) return NN_ACT_DIRECT; return -EOPNOTSUPP; } /* TC legacy mode */ - if (!tc_single_action(cls_bpf->exts)) + if (!tcf_exts_has_one_action(cls_bpf->exts)) return -EOPNOTSUPP; tcf_exts_to_list(cls_bpf->exts, &actions); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index d696ba46f70a..5b783a91b115 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -79,28 +79,32 @@ nfp_bpf_check_exit(struct nfp_prog *nfp_prog, const struct bpf_verifier_env *env) { const struct bpf_reg_state *reg0 = &env->cur_state.regs[0]; + u64 imm; if (nfp_prog->act == NN_ACT_XDP) return 0; - if (reg0->type != CONST_IMM) { - pr_info("unsupported exit state: %d, imm: %llx\n", - reg0->type, reg0->imm); + if (!(reg0->type == SCALAR_VALUE && tnum_is_const(reg0->var_off))) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg0->var_off); + pr_info("unsupported exit state: %d, var_off: %s\n", + reg0->type, tn_buf); return -EINVAL; } - if (nfp_prog->act != NN_ACT_DIRECT && - reg0->imm != 0 && (reg0->imm & ~0U) != ~0U) { + imm = reg0->var_off.value; + if (nfp_prog->act != NN_ACT_DIRECT && imm != 0 && (imm & ~0U) != ~0U) { pr_info("unsupported exit state: %d, imm: %llx\n", - reg0->type, reg0->imm); + reg0->type, imm); return -EINVAL; } - if (nfp_prog->act == NN_ACT_DIRECT && reg0->imm <= TC_ACT_REDIRECT && - reg0->imm != TC_ACT_SHOT && reg0->imm != TC_ACT_STOLEN && - reg0->imm != TC_ACT_QUEUED) { + if (nfp_prog->act == NN_ACT_DIRECT && imm <= TC_ACT_REDIRECT && + imm != TC_ACT_SHOT && imm != TC_ACT_STOLEN && + imm != TC_ACT_QUEUED) { pr_info("unsupported exit state: %d, imm: %llx\n", - reg0->type, reg0->imm); + reg0->type, imm); return -EINVAL; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index b0837b58c3a1..c3ca05d10fe1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -34,10 +34,12 @@ #include <linux/bitfield.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <linux/workqueue.h> #include <net/dst_metadata.h> #include "main.h" #include "../nfpcore/nfp_cpp.h" +#include "../nfp_net.h" #include "../nfp_net_repr.h" #include "./cmsg.h" @@ -75,6 +77,39 @@ nfp_flower_cmsg_alloc(struct nfp_app *app, unsigned int size, return skb; } +struct sk_buff * +nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports) +{ + struct nfp_flower_cmsg_mac_repr *msg; + struct sk_buff *skb; + unsigned int size; + + size = sizeof(*msg) + num_ports * sizeof(msg->ports[0]); + skb = nfp_flower_cmsg_alloc(app, size, NFP_FLOWER_CMSG_TYPE_MAC_REPR); + if (!skb) + return NULL; + + msg = nfp_flower_cmsg_get_data(skb); + memset(msg->reserved, 0, sizeof(msg->reserved)); + msg->num_ports = num_ports; + + return skb; +} + +void +nfp_flower_cmsg_mac_repr_add(struct sk_buff *skb, unsigned int idx, + unsigned int nbi, unsigned int nbi_port, + unsigned int phys_port) +{ + struct nfp_flower_cmsg_mac_repr *msg; + + msg = nfp_flower_cmsg_get_data(skb); + msg->ports[idx].idx = idx; + msg->ports[idx].info = nbi & NFP_FLOWER_CMSG_MAC_REPR_NBI; + msg->ports[idx].nbi_port = nbi_port; + msg->ports[idx].phys_port = phys_port; +} + int nfp_flower_cmsg_portmod(struct nfp_repr *repr, bool carrier_ok) { struct nfp_flower_cmsg_portmod *msg; @@ -106,23 +141,33 @@ nfp_flower_cmsg_portmod_rx(struct nfp_app *app, struct sk_buff *skb) msg = nfp_flower_cmsg_get_data(skb); link = msg->info & NFP_FLOWER_CMSG_PORTMOD_INFO_LINK; + rtnl_lock(); rcu_read_lock(); netdev = nfp_app_repr_get(app, be32_to_cpu(msg->portnum)); + rcu_read_unlock(); if (!netdev) { nfp_flower_cmsg_warn(app, "ctrl msg for unknown port 0x%08x\n", be32_to_cpu(msg->portnum)); - rcu_read_unlock(); + rtnl_unlock(); return; } - if (link) + if (link) { + u16 mtu = be16_to_cpu(msg->mtu); + netif_carrier_on(netdev); - else + + /* An MTU of 0 from the firmware should be ignored */ + if (mtu) + dev_set_mtu(netdev, mtu); + } else { netif_carrier_off(netdev); - rcu_read_unlock(); + } + rtnl_unlock(); } -void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb) +static void +nfp_flower_cmsg_process_one_rx(struct nfp_app *app, struct sk_buff *skb) { struct nfp_flower_cmsg_hdr *cmsg_hdr; enum nfp_flower_cmsg_type_port type; @@ -146,8 +191,30 @@ void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb) default: nfp_flower_cmsg_warn(app, "Cannot handle invalid repr control type %u\n", type); + goto out; } + dev_consume_skb_any(skb); + return; out: dev_kfree_skb_any(skb); } + +void nfp_flower_cmsg_process_rx(struct work_struct *work) +{ + struct nfp_flower_priv *priv; + struct sk_buff *skb; + + priv = container_of(work, struct nfp_flower_priv, cmsg_work); + + while ((skb = skb_dequeue(&priv->cmsg_skbs))) + nfp_flower_cmsg_process_one_rx(priv->app, skb); +} + +void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb) +{ + struct nfp_flower_priv *priv = app->priv; + + skb_queue_tail(&priv->cmsg_skbs, skb); + schedule_work(&priv->cmsg_work); +} diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index cf738de170ab..a2ec60344236 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -247,12 +247,27 @@ struct nfp_flower_cmsg_hdr { enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_FLOW_ADD = 0, NFP_FLOWER_CMSG_TYPE_FLOW_DEL = 2, + NFP_FLOWER_CMSG_TYPE_MAC_REPR = 7, NFP_FLOWER_CMSG_TYPE_PORT_MOD = 8, NFP_FLOWER_CMSG_TYPE_FLOW_STATS = 15, NFP_FLOWER_CMSG_TYPE_PORT_ECHO = 16, NFP_FLOWER_CMSG_TYPE_MAX = 32, }; +/* NFP_FLOWER_CMSG_TYPE_MAC_REPR */ +struct nfp_flower_cmsg_mac_repr { + u8 reserved[3]; + u8 num_ports; + struct { + u8 idx; + u8 info; + u8 nbi_port; + u8 phys_port; + } ports[0]; +}; + +#define NFP_FLOWER_CMSG_MAC_REPR_NBI GENMASK(1, 0) + /* NFP_FLOWER_CMSG_TYPE_PORT_MOD */ struct nfp_flower_cmsg_portmod { __be32 portnum; @@ -308,7 +323,14 @@ static inline void *nfp_flower_cmsg_get_data(struct sk_buff *skb) return (unsigned char *)skb->data + NFP_FLOWER_CMSG_HLEN; } +struct sk_buff * +nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports); +void +nfp_flower_cmsg_mac_repr_add(struct sk_buff *skb, unsigned int idx, + unsigned int nbi, unsigned int nbi_port, + unsigned int phys_port); int nfp_flower_cmsg_portmod(struct nfp_repr *repr, bool carrier_ok); +void nfp_flower_cmsg_process_rx(struct work_struct *work); void nfp_flower_cmsg_rx(struct nfp_app *app, struct sk_buff *skb); struct sk_buff * nfp_flower_cmsg_alloc(struct nfp_app *app, unsigned int size, diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 6a65c8b33807..91fe03617106 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -127,6 +127,11 @@ nfp_flower_repr_netdev_stop(struct nfp_app *app, struct nfp_repr *repr) static void nfp_flower_sriov_disable(struct nfp_app *app) { + struct nfp_flower_priv *priv = app->priv; + + if (!priv->nn) + return; + nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_VF); } @@ -159,12 +164,18 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app, goto err_reprs_clean; } + /* For now we only support 1 PF */ + WARN_ON(repr_type == NFP_REPR_TYPE_PF && i); + port = nfp_port_alloc(app, port_type, reprs->reprs[i]); if (repr_type == NFP_REPR_TYPE_PF) { port->pf_id = i; + port->vnic = priv->nn->dp.ctrl_bar; } else { - port->pf_id = 0; /* For now we only support 1 PF */ + port->pf_id = 0; port->vf_id = i; + port->vnic = + app->pf->vf_cfg_mem + i * NFP_NET_CFG_BAR_SZ; } eth_hw_addr_random(reprs->reprs[i]); @@ -197,32 +208,37 @@ err_reprs_clean: static int nfp_flower_sriov_enable(struct nfp_app *app, int num_vfs) { + struct nfp_flower_priv *priv = app->priv; + + if (!priv->nn) + return 0; + return nfp_flower_spawn_vnic_reprs(app, NFP_FLOWER_CMSG_PORT_VNIC_TYPE_VF, NFP_REPR_TYPE_VF, num_vfs); } -static void nfp_flower_stop(struct nfp_app *app) -{ - nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PF); - nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT); - -} - static int nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv) { struct nfp_eth_table *eth_tbl = app->pf->eth_tbl; struct nfp_reprs *reprs, *old_reprs; + struct sk_buff *ctrl_skb; unsigned int i; int err; - reprs = nfp_reprs_alloc(eth_tbl->max_index + 1); - if (!reprs) + ctrl_skb = nfp_flower_cmsg_mac_repr_start(app, eth_tbl->count); + if (!ctrl_skb) return -ENOMEM; + reprs = nfp_reprs_alloc(eth_tbl->max_index + 1); + if (!reprs) { + err = -ENOMEM; + goto err_free_ctrl_skb; + } + for (i = 0; i < eth_tbl->count; i++) { - int phys_port = eth_tbl->ports[i].index; + unsigned int phys_port = eth_tbl->ports[i].index; struct nfp_port *port; u32 cmsg_port_id; @@ -255,6 +271,11 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv) goto err_reprs_clean; } + nfp_flower_cmsg_mac_repr_add(ctrl_skb, i, + eth_tbl->ports[i].nbi, + eth_tbl->ports[i].base, + phys_port); + nfp_info(app->cpp, "Phys Port %d Representor(%s) created\n", phys_port, reprs->reprs[phys_port]->name); } @@ -265,37 +286,31 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv) goto err_reprs_clean; } + /* The MAC_REPR control message should be sent after the MAC + * representors are registered using nfp_app_reprs_set(). This is + * because the firmware may respond with control messages for the + * MAC representors, f.e. to provide the driver with information + * about their state, and without registration the driver will drop + * any such messages. + */ + nfp_ctrl_tx(app->ctrl, ctrl_skb); + return 0; err_reprs_clean: nfp_reprs_clean_and_free(reprs); +err_free_ctrl_skb: + kfree_skb(ctrl_skb); return err; } -static int nfp_flower_start(struct nfp_app *app) -{ - int err; - - err = nfp_flower_spawn_phy_reprs(app, app->priv); - if (err) - return err; - - return nfp_flower_spawn_vnic_reprs(app, - NFP_FLOWER_CMSG_PORT_VNIC_TYPE_PF, - NFP_REPR_TYPE_PF, 1); -} - -static int nfp_flower_vnic_init(struct nfp_app *app, struct nfp_net *nn, - unsigned int id) +static int nfp_flower_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, + unsigned int id) { - struct nfp_flower_priv *priv = app->priv; - if (id > 0) { nfp_warn(app->cpp, "FlowerNIC doesn't support more than one data vNIC\n"); goto err_invalid_port; } - priv->nn = nn; - eth_hw_addr_random(nn->dp.netdev); netif_keep_dst(nn->dp.netdev); @@ -306,9 +321,59 @@ err_invalid_port: return PTR_ERR_OR_ZERO(nn->port); } +static void nfp_flower_vnic_clean(struct nfp_app *app, struct nfp_net *nn) +{ + struct nfp_flower_priv *priv = app->priv; + + if (app->pf->num_vfs) + nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_VF); + nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PF); + nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT); + + priv->nn = NULL; +} + +static int nfp_flower_vnic_init(struct nfp_app *app, struct nfp_net *nn) +{ + struct nfp_flower_priv *priv = app->priv; + int err; + + priv->nn = nn; + + err = nfp_flower_spawn_phy_reprs(app, app->priv); + if (err) + goto err_clear_nn; + + err = nfp_flower_spawn_vnic_reprs(app, + NFP_FLOWER_CMSG_PORT_VNIC_TYPE_PF, + NFP_REPR_TYPE_PF, 1); + if (err) + goto err_destroy_reprs_phy; + + if (app->pf->num_vfs) { + err = nfp_flower_spawn_vnic_reprs(app, + NFP_FLOWER_CMSG_PORT_VNIC_TYPE_VF, + NFP_REPR_TYPE_VF, + app->pf->num_vfs); + if (err) + goto err_destroy_reprs_pf; + } + + return 0; + +err_destroy_reprs_pf: + nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PF); +err_destroy_reprs_phy: + nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT); +err_clear_nn: + priv->nn = NULL; + return err; +} + static int nfp_flower_init(struct nfp_app *app) { const struct nfp_pf *pf = app->pf; + struct nfp_flower_priv *app_priv; u64 version; int err; @@ -339,10 +404,15 @@ static int nfp_flower_init(struct nfp_app *app) return -EINVAL; } - app->priv = vzalloc(sizeof(struct nfp_flower_priv)); - if (!app->priv) + app_priv = vzalloc(sizeof(struct nfp_flower_priv)); + if (!app_priv) return -ENOMEM; + app->priv = app_priv; + app_priv->app = app; + skb_queue_head_init(&app_priv->cmsg_skbs); + INIT_WORK(&app_priv->cmsg_work, nfp_flower_cmsg_process_rx); + err = nfp_flower_metadata_init(app); if (err) goto err_free_app_priv; @@ -356,6 +426,11 @@ err_free_app_priv: static void nfp_flower_clean(struct nfp_app *app) { + struct nfp_flower_priv *app_priv = app->priv; + + skb_queue_purge(&app_priv->cmsg_skbs); + flush_work(&app_priv->cmsg_work); + nfp_flower_metadata_cleanup(app); vfree(app->priv); app->priv = NULL; @@ -371,14 +446,13 @@ const struct nfp_app_type app_flower = { .init = nfp_flower_init, .clean = nfp_flower_clean, + .vnic_alloc = nfp_flower_vnic_alloc, .vnic_init = nfp_flower_vnic_init, + .vnic_clean = nfp_flower_vnic_clean, .repr_open = nfp_flower_repr_netdev_open, .repr_stop = nfp_flower_repr_netdev_stop, - .start = nfp_flower_start, - .stop = nfp_flower_stop, - .ctrl_msg_rx = nfp_flower_cmsg_rx, .sriov_enable = nfp_flower_sriov_enable, diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 9e64c048e83f..c20dd00a1cae 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -38,8 +38,9 @@ #include <linux/hashtable.h> #include <linux/time64.h> #include <linux/types.h> +#include <net/pkt_cls.h> +#include <linux/workqueue.h> -struct tc_to_netdev; struct net_device; struct nfp_app; @@ -71,6 +72,7 @@ struct nfp_fl_stats_id { /** * struct nfp_flower_priv - Flower APP per-vNIC priv data + * @app: Back pointer to app * @nn: Pointer to vNIC * @mask_id_seed: Seed used for mask hash table * @flower_version: HW version of flower @@ -78,8 +80,11 @@ struct nfp_fl_stats_id { * @mask_ids: List of free mask ids * @mask_table: Hash table used to store masks * @flow_table: Hash table used to store flower rules + * @cmsg_work: Workqueue for control messages processing + * @cmsg_skbs: List of skbs for control message processing */ struct nfp_flower_priv { + struct nfp_app *app; struct nfp_net *nn; u32 mask_id_seed; u64 flower_version; @@ -87,6 +92,8 @@ struct nfp_flower_priv { struct nfp_fl_mask_id mask_ids; DECLARE_HASHTABLE(mask_table, NFP_FLOWER_MASK_HASH_BITS); DECLARE_HASHTABLE(flow_table, NFP_FLOWER_HASH_BITS); + struct work_struct cmsg_work; + struct sk_buff_head cmsg_skbs; }; struct nfp_fl_key_ls { @@ -135,7 +142,7 @@ int nfp_flower_metadata_init(struct nfp_app *app); void nfp_flower_metadata_cleanup(struct nfp_app *app); int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev, - u32 handle, __be16 proto, struct tc_to_netdev *tc); + enum tc_setup_type type, void *type_data); int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, struct nfp_fl_key_ls *key_ls, struct net_device *netdev, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 74a96d6bb05c..d396183108f7 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -409,16 +409,15 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev, } int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev, - u32 handle, __be16 proto, struct tc_to_netdev *tc) + enum tc_setup_type type, void *type_data) { - if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS)) - return -EOPNOTSUPP; + struct tc_cls_flower_offload *cls_flower = type_data; - if (!eth_proto_is_802_3(proto)) + if (type != TC_SETUP_CLSFLOWER || + !is_classid_clsact_ingress(cls_flower->common.classid) || + !eth_proto_is_802_3(cls_flower->common.protocol) || + cls_flower->common.chain_index) return -EOPNOTSUPP; - if (tc->type != TC_SETUP_CLSFLOWER) - return -EINVAL; - - return nfp_flower_repr_offload(app, netdev, tc->cls_flower); + return nfp_flower_repr_offload(app, netdev, cls_flower); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c index c704c022574f..82c290763529 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c @@ -38,6 +38,7 @@ #include "nfpcore/nfp_nffw.h" #include "nfp_app.h" #include "nfp_main.h" +#include "nfp_net.h" #include "nfp_net_repr.h" static const struct nfp_app_type *apps[] = { @@ -48,6 +49,25 @@ static const struct nfp_app_type *apps[] = { #endif }; +struct nfp_app *nfp_app_from_netdev(struct net_device *netdev) +{ + if (nfp_netdev_is_nfp_net(netdev)) { + struct nfp_net *nn = netdev_priv(netdev); + + return nn->app; + } + + if (nfp_netdev_is_nfp_repr(netdev)) { + struct nfp_repr *repr = netdev_priv(netdev); + + return repr->app; + } + + WARN(1, "Unknown netdev type for nfp_app\n"); + + return NULL; +} + const char *nfp_app_mip_name(struct nfp_app *app) { if (!app || !app->pf->mip) @@ -105,7 +125,7 @@ struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id) return ERR_PTR(-EINVAL); } - if (WARN_ON(!apps[i]->name || !apps[i]->vnic_init)) + if (WARN_ON(!apps[i]->name || !apps[i]->vnic_alloc)) return ERR_PTR(-EINVAL); app = kzalloc(sizeof(*app), GFP_KERNEL); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index 5d714e10d9a9..af640b5c2108 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -42,7 +42,6 @@ struct bpf_prog; struct net_device; struct pci_dev; struct sk_buff; -struct tc_to_netdev; struct sk_buff; struct nfp_app; struct nfp_cpp; @@ -70,8 +69,10 @@ extern const struct nfp_app_type app_flower; * @init: perform basic app checks and init * @clean: clean app state * @extra_cap: extra capabilities string - * @vnic_init: init vNICs (assign port types, etc.) - * @vnic_clean: clean up app's vNIC state + * @vnic_alloc: allocate vNICs (assign port types, etc.) + * @vnic_free: free up app's vNIC state + * @vnic_init: vNIC netdev was registered + * @vnic_clean: vNIC netdev about to be unregistered * @repr_open: representor netdev open callback * @repr_stop: representor netdev stop callback * @start: start application logic @@ -96,8 +97,10 @@ struct nfp_app_type { const char *(*extra_cap)(struct nfp_app *app, struct nfp_net *nn); - int (*vnic_init)(struct nfp_app *app, struct nfp_net *nn, - unsigned int id); + int (*vnic_alloc)(struct nfp_app *app, struct nfp_net *nn, + unsigned int id); + void (*vnic_free)(struct nfp_app *app, struct nfp_net *nn); + int (*vnic_init)(struct nfp_app *app, struct nfp_net *nn); void (*vnic_clean)(struct nfp_app *app, struct nfp_net *nn); int (*repr_open)(struct nfp_app *app, struct nfp_repr *repr); @@ -109,7 +112,7 @@ struct nfp_app_type { void (*ctrl_msg_rx)(struct nfp_app *app, struct sk_buff *skb); int (*setup_tc)(struct nfp_app *app, struct net_device *netdev, - u32 handle, __be16 proto, struct tc_to_netdev *tc); + enum tc_setup_type type, void *type_data); bool (*tc_busy)(struct nfp_app *app, struct nfp_net *nn); int (*xdp_offload)(struct nfp_app *app, struct nfp_net *nn, struct bpf_prog *prog); @@ -158,10 +161,23 @@ static inline void nfp_app_clean(struct nfp_app *app) app->type->clean(app); } -static inline int nfp_app_vnic_init(struct nfp_app *app, struct nfp_net *nn, - unsigned int id) +static inline int nfp_app_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, + unsigned int id) +{ + return app->type->vnic_alloc(app, nn, id); +} + +static inline void nfp_app_vnic_free(struct nfp_app *app, struct nfp_net *nn) +{ + if (app->type->vnic_free) + app->type->vnic_free(app, nn); +} + +static inline int nfp_app_vnic_init(struct nfp_app *app, struct nfp_net *nn) { - return app->type->vnic_init(app, nn, id); + if (!app->type->vnic_init) + return 0; + return app->type->vnic_init(app, nn); } static inline void nfp_app_vnic_clean(struct nfp_app *app, struct nfp_net *nn) @@ -238,12 +254,11 @@ static inline bool nfp_app_tc_busy(struct nfp_app *app, struct nfp_net *nn) static inline int nfp_app_setup_tc(struct nfp_app *app, struct net_device *netdev, - u32 handle, __be16 proto, - struct tc_to_netdev *tc) + enum tc_setup_type type, void *type_data) { if (!app || !app->type->setup_tc) return -EOPNOTSUPP; - return app->type->setup_tc(app, netdev, handle, proto, tc); + return app->type->setup_tc(app, netdev, type, type_data); } static inline int nfp_app_xdp_offload(struct nfp_app *app, struct nfp_net *nn, @@ -295,6 +310,8 @@ static inline struct net_device *nfp_app_repr_get(struct nfp_app *app, u32 id) return app->type->repr_get(app, id); } +struct nfp_app *nfp_app_from_netdev(struct net_device *netdev); + struct nfp_reprs * nfp_app_reprs_set(struct nfp_app *app, enum nfp_repr_type type, struct nfp_reprs *reprs); @@ -308,7 +325,7 @@ void nfp_app_free(struct nfp_app *app); /* Callbacks shared between apps */ -int nfp_app_nic_vnic_init(struct nfp_app *app, struct nfp_net *nn, - unsigned int id); +int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, + unsigned int id); #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c b/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c index 4e37c81f9eaf..2a2f2fbc8850 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_app_nic.c @@ -60,8 +60,8 @@ nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app, return nn->port->type == NFP_PORT_INVALID; } -int nfp_app_nic_vnic_init(struct nfp_app *app, struct nfp_net *nn, - unsigned int id) +int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, + unsigned int id) { int err; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 3f199db2002e..f055b1774d65 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -172,6 +172,21 @@ static int nfp_pcie_sriov_configure(struct pci_dev *pdev, int num_vfs) return nfp_pcie_sriov_enable(pdev, num_vfs); } +static const struct firmware * +nfp_net_fw_request(struct pci_dev *pdev, struct nfp_pf *pf, const char *name) +{ + const struct firmware *fw = NULL; + int err; + + err = request_firmware_direct(&fw, name, &pdev->dev); + nfp_info(pf->cpp, " %s: %s\n", + name, err ? "not found" : "found, loading..."); + if (err) + return NULL; + + return fw; +} + /** * nfp_net_fw_find() - Find the correct firmware image for netdev mode * @pdev: PCI Device structure @@ -182,13 +197,32 @@ static int nfp_pcie_sriov_configure(struct pci_dev *pdev, int num_vfs) static const struct firmware * nfp_net_fw_find(struct pci_dev *pdev, struct nfp_pf *pf) { - const struct firmware *fw = NULL; struct nfp_eth_table_port *port; + const struct firmware *fw; const char *fw_model; char fw_name[256]; - int spc, err = 0; - int i, j; + const u8 *serial; + u16 interface; + int spc, i, j; + nfp_info(pf->cpp, "Looking for firmware file in order of priority:\n"); + + /* First try to find a firmware image specific for this device */ + interface = nfp_cpp_interface(pf->cpp); + nfp_cpp_serial(pf->cpp, &serial); + sprintf(fw_name, "netronome/serial-%pMF-%02hhx-%02hhx.nffw", + serial, interface >> 8, interface & 0xff); + fw = nfp_net_fw_request(pdev, pf, fw_name); + if (fw) + return fw; + + /* Then try the PCI name */ + sprintf(fw_name, "netronome/pci-%s.nffw", pci_name(pdev)); + fw = nfp_net_fw_request(pdev, pf, fw_name); + if (fw) + return fw; + + /* Finally try the card type and media */ if (!pf->eth_tbl) { dev_err(&pdev->dev, "Error: can't identify media config\n"); return NULL; @@ -221,13 +255,7 @@ nfp_net_fw_find(struct pci_dev *pdev, struct nfp_pf *pf) if (spc <= 0) return NULL; - err = request_firmware(&fw, fw_name, &pdev->dev); - if (err) - return NULL; - - dev_info(&pdev->dev, "Loading FW image: %s\n", fw_name); - - return fw; + return nfp_net_fw_request(pdev, pf, fw_name); } /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index 6922410806db..be0ee59f2eb9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -73,6 +73,8 @@ struct nfp_rtsym_table; * @mac_stats_mem: Pointer to mapped MAC stats area * @vf_cfg_bar: Pointer to the CPP area for the VF configuration BAR * @vf_cfg_mem: Pointer to mapped VF configuration area + * @vfcfg_tbl2_area: Pointer to the CPP area for the VF config table + * @vfcfg_tbl2: Pointer to mapped VF config table * @irq_entries: Array of MSI-X entries for all vNICs * @limit_vfs: Number of VFs supported by firmware (~0 for PCI limit) * @num_vfs: Number of SR-IOV VFs enabled @@ -107,6 +109,8 @@ struct nfp_pf { u8 __iomem *mac_stats_mem; struct nfp_cpp_area *vf_cfg_bar; u8 __iomem *vf_cfg_mem; + struct nfp_cpp_area *vfcfg_tbl2_area; + u8 __iomem *vfcfg_tbl2; struct msix_entry *irq_entries; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index b1fa77bd708b..d51d8237b984 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -573,7 +573,6 @@ struct nfp_net_dp { * @tx_bar: Pointer to mapped TX queues * @rx_bar: Pointer to mapped FL/RX queues * @debugfs_dir: Device directory in debugfs - * @ethtool_dump_flag: Ethtool dump flag * @vnic_list: Entry on device vNIC list * @pdev: Backpointer to PCI device * @app: APP handle if available @@ -640,7 +639,6 @@ struct nfp_net { u8 __iomem *rx_bar; struct dentry *debugfs_dir; - u32 ethtool_dump_flag; struct list_head vnic_list; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 66a09e490cf5..1c0187f0af51 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -71,6 +71,7 @@ #include "nfp_app.h" #include "nfp_net_ctrl.h" #include "nfp_net.h" +#include "nfp_net_sriov.h" #include "nfp_port.h" /** @@ -990,7 +991,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring) /* check for last gather fragment */ if (fidx == nr_frags - 1) - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); tx_ring->txbufs[idx].dma_addr = 0; tx_ring->txbufs[idx].skb = NULL; @@ -2659,6 +2660,7 @@ static int nfp_net_netdev_close(struct net_device *netdev) /* Step 2: Tell NFP */ nfp_net_clear_config_and_disable(nn); + nfp_port_configure(netdev, false); /* Step 3: Free resources */ @@ -2776,16 +2778,21 @@ static int nfp_net_netdev_open(struct net_device *netdev) goto err_free_all; /* Step 2: Configure the NFP + * - Ifup the physical interface if it exists * - Enable rings from 0 to tx_rings/rx_rings - 1. * - Write MAC address (in case it changed) * - Set the MTU * - Set the Freelist buffer size * - Enable the FW */ - err = nfp_net_set_config_and_enable(nn); + err = nfp_port_configure(netdev, true); if (err) goto err_free_all; + err = nfp_net_set_config_and_enable(nn); + if (err) + goto err_port_disable; + /* Step 3: Enable for kernel * - put some freelist descriptors on each RX ring * - enable NAPI on each ring @@ -2796,6 +2803,8 @@ static int nfp_net_netdev_open(struct net_device *netdev) return 0; +err_port_disable: + nfp_port_configure(netdev, false); err_free_all: nfp_net_close_free_all(nn); return err; @@ -3413,6 +3422,11 @@ const struct net_device_ops nfp_net_netdev_ops = { .ndo_get_stats64 = nfp_net_stat64, .ndo_vlan_rx_add_vid = nfp_net_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = nfp_net_vlan_rx_kill_vid, + .ndo_set_vf_mac = nfp_app_set_vf_mac, + .ndo_set_vf_vlan = nfp_app_set_vf_vlan, + .ndo_set_vf_spoofchk = nfp_app_set_vf_spoofchk, + .ndo_get_vf_config = nfp_app_get_vf_config, + .ndo_set_vf_link_state = nfp_app_set_vf_link_state, .ndo_setup_tc = nfp_port_setup_tc, .ndo_tx_timeout = nfp_net_tx_timeout, .ndo_set_rx_mode = nfp_net_set_rx_mode, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h index e5e94e0746ec..b0a452ba9039 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h @@ -164,6 +164,7 @@ #define NFP_NET_CFG_UPDATE_BPF (0x1 << 10) /* BPF program load */ #define NFP_NET_CFG_UPDATE_MACADDR (0x1 << 11) /* MAC address change */ #define NFP_NET_CFG_UPDATE_MBOX (0x1 << 12) /* Mailbox update */ +#define NFP_NET_CFG_UPDATE_VF (0x1 << 13) /* VF settings change */ #define NFP_NET_CFG_UPDATE_ERR (0x1 << 31) /* A error occurred */ #define NFP_NET_CFG_TXRS_ENABLE 0x0008 #define NFP_NET_CFG_RXRS_ENABLE 0x0010 diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c index 40217ece5fcb..cf81cf95d1d8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c @@ -125,7 +125,6 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data) struct nfp_net_tx_ring *tx_ring; struct nfp_net_tx_desc *txd; int d_rd_p, d_wr_p, txd_cnt; - struct sk_buff *skb; struct nfp_net *nn; int i; @@ -158,13 +157,15 @@ static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data) txd->vals[0], txd->vals[1], txd->vals[2], txd->vals[3]); - skb = READ_ONCE(tx_ring->txbufs[i].skb); - if (skb) { - if (tx_ring == r_vec->tx_ring) + if (tx_ring == r_vec->tx_ring) { + struct sk_buff *skb = READ_ONCE(tx_ring->txbufs[i].skb); + + if (skb) seq_printf(file, " skb->head=%p skb->data=%p", skb->head, skb->data); - else - seq_printf(file, " frag=%p", skb); + } else { + seq_printf(file, " frag=%p", + READ_ONCE(tx_ring->txbufs[i].frag)); } if (tx_ring->txbufs[i].dma_addr) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 6e31355c3567..07969f06df10 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -59,82 +59,129 @@ enum nfp_dump_diag { NFP_DUMP_NSP_DIAG = 0, }; -/* Support for stats. Returns netdev, driver, and device stats */ -enum { NETDEV_ET_STATS, NFP_NET_DRV_ET_STATS, NFP_NET_DEV_ET_STATS }; -struct _nfp_net_et_stats { +struct nfp_et_stat { char name[ETH_GSTRING_LEN]; - int type; - int sz; int off; }; -#define NN_ET_NETDEV_STAT(m) NETDEV_ET_STATS, \ - FIELD_SIZEOF(struct net_device_stats, m), \ - offsetof(struct net_device_stats, m) -/* For stats in the control BAR (other than Q stats) */ -#define NN_ET_DEV_STAT(m) NFP_NET_DEV_ET_STATS, \ - sizeof(u64), \ - (m) -static const struct _nfp_net_et_stats nfp_net_et_stats[] = { - /* netdev stats */ - {"rx_packets", NN_ET_NETDEV_STAT(rx_packets)}, - {"tx_packets", NN_ET_NETDEV_STAT(tx_packets)}, - {"rx_bytes", NN_ET_NETDEV_STAT(rx_bytes)}, - {"tx_bytes", NN_ET_NETDEV_STAT(tx_bytes)}, - {"rx_errors", NN_ET_NETDEV_STAT(rx_errors)}, - {"tx_errors", NN_ET_NETDEV_STAT(tx_errors)}, - {"rx_dropped", NN_ET_NETDEV_STAT(rx_dropped)}, - {"tx_dropped", NN_ET_NETDEV_STAT(tx_dropped)}, - {"multicast", NN_ET_NETDEV_STAT(multicast)}, - {"collisions", NN_ET_NETDEV_STAT(collisions)}, - {"rx_over_errors", NN_ET_NETDEV_STAT(rx_over_errors)}, - {"rx_crc_errors", NN_ET_NETDEV_STAT(rx_crc_errors)}, - {"rx_frame_errors", NN_ET_NETDEV_STAT(rx_frame_errors)}, - {"rx_fifo_errors", NN_ET_NETDEV_STAT(rx_fifo_errors)}, - {"rx_missed_errors", NN_ET_NETDEV_STAT(rx_missed_errors)}, - {"tx_aborted_errors", NN_ET_NETDEV_STAT(tx_aborted_errors)}, - {"tx_carrier_errors", NN_ET_NETDEV_STAT(tx_carrier_errors)}, - {"tx_fifo_errors", NN_ET_NETDEV_STAT(tx_fifo_errors)}, +static const struct nfp_et_stat nfp_net_et_stats[] = { /* Stats from the device */ - {"dev_rx_discards", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_DISCARDS)}, - {"dev_rx_errors", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_ERRORS)}, - {"dev_rx_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_OCTETS)}, - {"dev_rx_uc_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_UC_OCTETS)}, - {"dev_rx_mc_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_MC_OCTETS)}, - {"dev_rx_bc_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_BC_OCTETS)}, - {"dev_rx_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_FRAMES)}, - {"dev_rx_mc_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_MC_FRAMES)}, - {"dev_rx_bc_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_RX_BC_FRAMES)}, - - {"dev_tx_discards", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_DISCARDS)}, - {"dev_tx_errors", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_ERRORS)}, - {"dev_tx_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_OCTETS)}, - {"dev_tx_uc_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_UC_OCTETS)}, - {"dev_tx_mc_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_MC_OCTETS)}, - {"dev_tx_bc_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_BC_OCTETS)}, - {"dev_tx_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_FRAMES)}, - {"dev_tx_mc_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_MC_FRAMES)}, - {"dev_tx_bc_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_TX_BC_FRAMES)}, - - {"bpf_pass_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP0_FRAMES)}, - {"bpf_pass_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP0_BYTES)}, + { "dev_rx_discards", NFP_NET_CFG_STATS_RX_DISCARDS }, + { "dev_rx_errors", NFP_NET_CFG_STATS_RX_ERRORS }, + { "dev_rx_bytes", NFP_NET_CFG_STATS_RX_OCTETS }, + { "dev_rx_uc_bytes", NFP_NET_CFG_STATS_RX_UC_OCTETS }, + { "dev_rx_mc_bytes", NFP_NET_CFG_STATS_RX_MC_OCTETS }, + { "dev_rx_bc_bytes", NFP_NET_CFG_STATS_RX_BC_OCTETS }, + { "dev_rx_pkts", NFP_NET_CFG_STATS_RX_FRAMES }, + { "dev_rx_mc_pkts", NFP_NET_CFG_STATS_RX_MC_FRAMES }, + { "dev_rx_bc_pkts", NFP_NET_CFG_STATS_RX_BC_FRAMES }, + + { "dev_tx_discards", NFP_NET_CFG_STATS_TX_DISCARDS }, + { "dev_tx_errors", NFP_NET_CFG_STATS_TX_ERRORS }, + { "dev_tx_bytes", NFP_NET_CFG_STATS_TX_OCTETS }, + { "dev_tx_uc_bytes", NFP_NET_CFG_STATS_TX_UC_OCTETS }, + { "dev_tx_mc_bytes", NFP_NET_CFG_STATS_TX_MC_OCTETS }, + { "dev_tx_bc_bytes", NFP_NET_CFG_STATS_TX_BC_OCTETS }, + { "dev_tx_pkts", NFP_NET_CFG_STATS_TX_FRAMES }, + { "dev_tx_mc_pkts", NFP_NET_CFG_STATS_TX_MC_FRAMES }, + { "dev_tx_bc_pkts", NFP_NET_CFG_STATS_TX_BC_FRAMES }, + + { "bpf_pass_pkts", NFP_NET_CFG_STATS_APP0_FRAMES }, + { "bpf_pass_bytes", NFP_NET_CFG_STATS_APP0_BYTES }, /* see comments in outro functions in nfp_bpf_jit.c to find out * how different BPF modes use app-specific counters */ - {"bpf_app1_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP1_FRAMES)}, - {"bpf_app1_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP1_BYTES)}, - {"bpf_app2_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP2_FRAMES)}, - {"bpf_app2_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP2_BYTES)}, - {"bpf_app3_pkts", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP3_FRAMES)}, - {"bpf_app3_bytes", NN_ET_DEV_STAT(NFP_NET_CFG_STATS_APP3_BYTES)}, + { "bpf_app1_pkts", NFP_NET_CFG_STATS_APP1_FRAMES }, + { "bpf_app1_bytes", NFP_NET_CFG_STATS_APP1_BYTES }, + { "bpf_app2_pkts", NFP_NET_CFG_STATS_APP2_FRAMES }, + { "bpf_app2_bytes", NFP_NET_CFG_STATS_APP2_BYTES }, + { "bpf_app3_pkts", NFP_NET_CFG_STATS_APP3_FRAMES }, + { "bpf_app3_bytes", NFP_NET_CFG_STATS_APP3_BYTES }, +}; + +static const struct nfp_et_stat nfp_mac_et_stats[] = { + { "rx_octets", NFP_MAC_STATS_RX_IN_OCTETS, }, + { "rx_frame_too_long_errors", + NFP_MAC_STATS_RX_FRAME_TOO_LONG_ERRORS, }, + { "rx_range_length_errors", NFP_MAC_STATS_RX_RANGE_LENGTH_ERRORS, }, + { "rx_vlan_reveive_ok", NFP_MAC_STATS_RX_VLAN_REVEIVE_OK, }, + { "rx_errors", NFP_MAC_STATS_RX_IN_ERRORS, }, + { "rx_broadcast_pkts", NFP_MAC_STATS_RX_IN_BROADCAST_PKTS, }, + { "rx_drop_events", NFP_MAC_STATS_RX_DROP_EVENTS, }, + { "rx_alignment_errors", NFP_MAC_STATS_RX_ALIGNMENT_ERRORS, }, + { "rx_pause_mac_ctrl_frames", + NFP_MAC_STATS_RX_PAUSE_MAC_CTRL_FRAMES, }, + { "rx_frames_received_ok", NFP_MAC_STATS_RX_FRAMES_RECEIVED_OK, }, + { "rx_frame_check_sequence_errors", + NFP_MAC_STATS_RX_FRAME_CHECK_SEQUENCE_ERRORS, }, + { "rx_unicast_pkts", NFP_MAC_STATS_RX_UNICAST_PKTS, }, + { "rx_multicast_pkts", NFP_MAC_STATS_RX_MULTICAST_PKTS, }, + { "rx_pkts", NFP_MAC_STATS_RX_PKTS, }, + { "rx_undersize_pkts", NFP_MAC_STATS_RX_UNDERSIZE_PKTS, }, + { "rx_pkts_64_octets", NFP_MAC_STATS_RX_PKTS_64_OCTETS, }, + { "rx_pkts_65_to_127_octets", + NFP_MAC_STATS_RX_PKTS_65_TO_127_OCTETS, }, + { "rx_pkts_128_to_255_octets", + NFP_MAC_STATS_RX_PKTS_128_TO_255_OCTETS, }, + { "rx_pkts_256_to_511_octets", + NFP_MAC_STATS_RX_PKTS_256_TO_511_OCTETS, }, + { "rx_pkts_512_to_1023_octets", + NFP_MAC_STATS_RX_PKTS_512_TO_1023_OCTETS, }, + { "rx_pkts_1024_to_1518_octets", + NFP_MAC_STATS_RX_PKTS_1024_TO_1518_OCTETS, }, + { "rx_pkts_1519_to_max_octets", + NFP_MAC_STATS_RX_PKTS_1519_TO_MAX_OCTETS, }, + { "rx_jabbers", NFP_MAC_STATS_RX_JABBERS, }, + { "rx_fragments", NFP_MAC_STATS_RX_FRAGMENTS, }, + { "rx_oversize_pkts", NFP_MAC_STATS_RX_OVERSIZE_PKTS, }, + { "rx_pause_frames_class0", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS0, }, + { "rx_pause_frames_class1", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS1, }, + { "rx_pause_frames_class2", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS2, }, + { "rx_pause_frames_class3", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS3, }, + { "rx_pause_frames_class4", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS4, }, + { "rx_pause_frames_class5", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS5, }, + { "rx_pause_frames_class6", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS6, }, + { "rx_pause_frames_class7", NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS7, }, + { "rx_mac_ctrl_frames_received", + NFP_MAC_STATS_RX_MAC_CTRL_FRAMES_RECEIVED, }, + { "rx_mac_head_drop", NFP_MAC_STATS_RX_MAC_HEAD_DROP, }, + { "tx_queue_drop", NFP_MAC_STATS_TX_QUEUE_DROP, }, + { "tx_octets", NFP_MAC_STATS_TX_OUT_OCTETS, }, + { "tx_vlan_transmitted_ok", NFP_MAC_STATS_TX_VLAN_TRANSMITTED_OK, }, + { "tx_errors", NFP_MAC_STATS_TX_OUT_ERRORS, }, + { "tx_broadcast_pkts", NFP_MAC_STATS_TX_BROADCAST_PKTS, }, + { "tx_pause_mac_ctrl_frames", + NFP_MAC_STATS_TX_PAUSE_MAC_CTRL_FRAMES, }, + { "tx_frames_transmitted_ok", + NFP_MAC_STATS_TX_FRAMES_TRANSMITTED_OK, }, + { "tx_unicast_pkts", NFP_MAC_STATS_TX_UNICAST_PKTS, }, + { "tx_multicast_pkts", NFP_MAC_STATS_TX_MULTICAST_PKTS, }, + { "tx_pkts_64_octets", NFP_MAC_STATS_TX_PKTS_64_OCTETS, }, + { "tx_pkts_65_to_127_octets", + NFP_MAC_STATS_TX_PKTS_65_TO_127_OCTETS, }, + { "tx_pkts_128_to_255_octets", + NFP_MAC_STATS_TX_PKTS_128_TO_255_OCTETS, }, + { "tx_pkts_256_to_511_octets", + NFP_MAC_STATS_TX_PKTS_256_TO_511_OCTETS, }, + { "tx_pkts_512_to_1023_octets", + NFP_MAC_STATS_TX_PKTS_512_TO_1023_OCTETS, }, + { "tx_pkts_1024_to_1518_octets", + NFP_MAC_STATS_TX_PKTS_1024_TO_1518_OCTETS, }, + { "tx_pkts_1519_to_max_octets", + NFP_MAC_STATS_TX_PKTS_1519_TO_MAX_OCTETS, }, + { "tx_pause_frames_class0", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS0, }, + { "tx_pause_frames_class1", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS1, }, + { "tx_pause_frames_class2", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS2, }, + { "tx_pause_frames_class3", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS3, }, + { "tx_pause_frames_class4", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS4, }, + { "tx_pause_frames_class5", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS5, }, + { "tx_pause_frames_class6", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS6, }, + { "tx_pause_frames_class7", NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS7, }, }; #define NN_ET_GLOBAL_STATS_LEN ARRAY_SIZE(nfp_net_et_stats) -#define NN_ET_RVEC_STATS_LEN (nn->dp.num_r_vecs * 3) +#define NN_ET_SWITCH_STATS_LEN 9 #define NN_ET_RVEC_GATHER_STATS 7 -#define NN_ET_QUEUE_STATS_LEN ((nn->dp.num_tx_rings + nn->dp.num_rx_rings) * 2) -#define NN_ET_STATS_LEN (NN_ET_GLOBAL_STATS_LEN + NN_ET_RVEC_GATHER_STATS + \ - NN_ET_RVEC_STATS_LEN + NN_ET_QUEUE_STATS_LEN) static void nfp_net_get_nspinfo(struct nfp_app *app, char *version) { @@ -147,34 +194,53 @@ static void nfp_net_get_nspinfo(struct nfp_app *app, char *version) if (IS_ERR(nsp)) return; - snprintf(version, ETHTOOL_FWVERS_LEN, "sp:%hu.%hu", + snprintf(version, ETHTOOL_FWVERS_LEN, "%hu.%hu", nfp_nsp_get_abi_ver_major(nsp), nfp_nsp_get_abi_ver_minor(nsp)); nfp_nsp_close(nsp); } -static void nfp_net_get_drvinfo(struct net_device *netdev, - struct ethtool_drvinfo *drvinfo) +static void +nfp_get_drvinfo(struct nfp_app *app, struct pci_dev *pdev, + const char *vnic_version, struct ethtool_drvinfo *drvinfo) { char nsp_version[ETHTOOL_FWVERS_LEN] = {}; - struct nfp_net *nn = netdev_priv(netdev); - strlcpy(drvinfo->driver, nn->pdev->driver->name, - sizeof(drvinfo->driver)); + strlcpy(drvinfo->driver, pdev->driver->name, sizeof(drvinfo->driver)); strlcpy(drvinfo->version, nfp_driver_version, sizeof(drvinfo->version)); - nfp_net_get_nspinfo(nn->app, nsp_version); + nfp_net_get_nspinfo(app, nsp_version); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%d.%d %s %s %s", + "%s %s %s %s", vnic_version, nsp_version, + nfp_app_mip_name(app), nfp_app_name(app)); +} + +static void +nfp_net_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +{ + char vnic_version[ETHTOOL_FWVERS_LEN] = {}; + struct nfp_net *nn = netdev_priv(netdev); + + snprintf(vnic_version, sizeof(vnic_version), "%d.%d.%d.%d", nn->fw_ver.resv, nn->fw_ver.class, - nn->fw_ver.major, nn->fw_ver.minor, nsp_version, - nfp_app_mip_name(nn->app), nfp_app_name(nn->app)); + nn->fw_ver.major, nn->fw_ver.minor); strlcpy(drvinfo->bus_info, pci_name(nn->pdev), sizeof(drvinfo->bus_info)); - drvinfo->n_stats = NN_ET_STATS_LEN; - drvinfo->regdump_len = NFP_NET_CFG_BAR_SZ; + nfp_get_drvinfo(nn->app, nn->pdev, vnic_version, drvinfo); +} + +static void +nfp_app_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) +{ + struct nfp_app *app; + + app = nfp_app_from_netdev(netdev); + if (!app) + return; + + nfp_get_drvinfo(app, app->pdev, "*", drvinfo); } /** @@ -346,132 +412,270 @@ static int nfp_net_set_ringparam(struct net_device *netdev, return nfp_net_set_ring_size(nn, rxd_cnt, txd_cnt); } -static void nfp_net_get_strings(struct net_device *netdev, - u32 stringset, u8 *data) +static __printf(2, 3) u8 *nfp_pr_et(u8 *data, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + vsnprintf(data, ETH_GSTRING_LEN, fmt, args); + va_end(args); + + return data + ETH_GSTRING_LEN; +} + +static unsigned int nfp_vnic_get_sw_stats_count(struct net_device *netdev) +{ + struct nfp_net *nn = netdev_priv(netdev); + + return NN_ET_RVEC_GATHER_STATS + nn->dp.num_r_vecs * 3; +} + +static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data) { struct nfp_net *nn = netdev_priv(netdev); - u8 *p = data; int i; - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < NN_ET_GLOBAL_STATS_LEN; i++) { - memcpy(p, nfp_net_et_stats[i].name, ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < nn->dp.num_r_vecs; i++) { - sprintf(p, "rvec_%u_rx_pkts", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rvec_%u_tx_pkts", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rvec_%u_tx_busy", i); - p += ETH_GSTRING_LEN; - } - strncpy(p, "hw_rx_csum_ok", ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - strncpy(p, "hw_rx_csum_inner_ok", ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - strncpy(p, "hw_rx_csum_err", ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - strncpy(p, "hw_tx_csum", ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - strncpy(p, "hw_tx_inner_csum", ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - strncpy(p, "tx_gather", ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - strncpy(p, "tx_lso", ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - for (i = 0; i < nn->dp.num_tx_rings; i++) { - sprintf(p, "txq_%u_pkts", i); - p += ETH_GSTRING_LEN; - sprintf(p, "txq_%u_bytes", i); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < nn->dp.num_rx_rings; i++) { - sprintf(p, "rxq_%u_pkts", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rxq_%u_bytes", i); - p += ETH_GSTRING_LEN; - } - break; + for (i = 0; i < nn->dp.num_r_vecs; i++) { + data = nfp_pr_et(data, "rvec_%u_rx_pkts", i); + data = nfp_pr_et(data, "rvec_%u_tx_pkts", i); + data = nfp_pr_et(data, "rvec_%u_tx_busy", i); } + + data = nfp_pr_et(data, "hw_rx_csum_ok"); + data = nfp_pr_et(data, "hw_rx_csum_inner_ok"); + data = nfp_pr_et(data, "hw_rx_csum_err"); + data = nfp_pr_et(data, "hw_tx_csum"); + data = nfp_pr_et(data, "hw_tx_inner_csum"); + data = nfp_pr_et(data, "tx_gather"); + data = nfp_pr_et(data, "tx_lso"); + + return data; } -static void nfp_net_get_stats(struct net_device *netdev, - struct ethtool_stats *stats, u64 *data) +static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) { u64 gathered_stats[NN_ET_RVEC_GATHER_STATS] = {}; struct nfp_net *nn = netdev_priv(netdev); - struct rtnl_link_stats64 *netdev_stats; - struct rtnl_link_stats64 temp = {}; u64 tmp[NN_ET_RVEC_GATHER_STATS]; - u8 __iomem *io_p; - int i, j, k; - u8 *p; - - netdev_stats = dev_get_stats(netdev, &temp); - - for (i = 0; i < NN_ET_GLOBAL_STATS_LEN; i++) { - switch (nfp_net_et_stats[i].type) { - case NETDEV_ET_STATS: - p = (char *)netdev_stats + nfp_net_et_stats[i].off; - data[i] = nfp_net_et_stats[i].sz == sizeof(u64) ? - *(u64 *)p : *(u32 *)p; - break; - - case NFP_NET_DEV_ET_STATS: - io_p = nn->dp.ctrl_bar + nfp_net_et_stats[i].off; - data[i] = readq(io_p); - break; - } - } - for (j = 0; j < nn->dp.num_r_vecs; j++) { + unsigned int i, j; + + for (i = 0; i < nn->dp.num_r_vecs; i++) { unsigned int start; do { - start = u64_stats_fetch_begin(&nn->r_vecs[j].rx_sync); - data[i++] = nn->r_vecs[j].rx_pkts; - tmp[0] = nn->r_vecs[j].hw_csum_rx_ok; - tmp[1] = nn->r_vecs[j].hw_csum_rx_inner_ok; - tmp[2] = nn->r_vecs[j].hw_csum_rx_error; - } while (u64_stats_fetch_retry(&nn->r_vecs[j].rx_sync, start)); + start = u64_stats_fetch_begin(&nn->r_vecs[i].rx_sync); + *data++ = nn->r_vecs[i].rx_pkts; + tmp[0] = nn->r_vecs[i].hw_csum_rx_ok; + tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok; + tmp[2] = nn->r_vecs[i].hw_csum_rx_error; + } while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start)); do { - start = u64_stats_fetch_begin(&nn->r_vecs[j].tx_sync); - data[i++] = nn->r_vecs[j].tx_pkts; - data[i++] = nn->r_vecs[j].tx_busy; - tmp[3] = nn->r_vecs[j].hw_csum_tx; - tmp[4] = nn->r_vecs[j].hw_csum_tx_inner; - tmp[5] = nn->r_vecs[j].tx_gather; - tmp[6] = nn->r_vecs[j].tx_lso; - } while (u64_stats_fetch_retry(&nn->r_vecs[j].tx_sync, start)); - - for (k = 0; k < NN_ET_RVEC_GATHER_STATS; k++) - gathered_stats[k] += tmp[k]; + start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync); + *data++ = nn->r_vecs[i].tx_pkts; + *data++ = nn->r_vecs[i].tx_busy; + tmp[3] = nn->r_vecs[i].hw_csum_tx; + tmp[4] = nn->r_vecs[i].hw_csum_tx_inner; + tmp[5] = nn->r_vecs[i].tx_gather; + tmp[6] = nn->r_vecs[i].tx_lso; + } while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start)); + + for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++) + gathered_stats[j] += tmp[j]; } + for (j = 0; j < NN_ET_RVEC_GATHER_STATS; j++) - data[i++] = gathered_stats[j]; - for (j = 0; j < nn->dp.num_tx_rings; j++) { - io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j); - data[i++] = readq(io_p); - io_p = nn->dp.ctrl_bar + NFP_NET_CFG_TXR_STATS(j) + 8; - data[i++] = readq(io_p); + *data++ = gathered_stats[j]; + + return data; +} + +static unsigned int +nfp_vnic_get_hw_stats_count(unsigned int rx_rings, unsigned int tx_rings) +{ + return NN_ET_GLOBAL_STATS_LEN + (rx_rings + tx_rings) * 2; +} + +static u8 * +nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings, + unsigned int tx_rings, bool repr) +{ + int swap_off, i; + + BUILD_BUG_ON(NN_ET_GLOBAL_STATS_LEN < NN_ET_SWITCH_STATS_LEN * 2); + /* If repr is true first add SWITCH_STATS_LEN and then subtract it + * effectively swapping the RX and TX statistics (giving us the RX + * and TX from perspective of the switch). + */ + swap_off = repr * NN_ET_SWITCH_STATS_LEN; + + for (i = 0; i < NN_ET_SWITCH_STATS_LEN; i++) + data = nfp_pr_et(data, nfp_net_et_stats[i + swap_off].name); + + for (i = NN_ET_SWITCH_STATS_LEN; i < NN_ET_SWITCH_STATS_LEN * 2; i++) + data = nfp_pr_et(data, nfp_net_et_stats[i - swap_off].name); + + for (i = NN_ET_SWITCH_STATS_LEN * 2; i < NN_ET_GLOBAL_STATS_LEN; i++) + data = nfp_pr_et(data, nfp_net_et_stats[i].name); + + for (i = 0; i < tx_rings; i++) { + data = nfp_pr_et(data, "txq_%u_pkts", i); + data = nfp_pr_et(data, "txq_%u_bytes", i); + } + + for (i = 0; i < rx_rings; i++) { + data = nfp_pr_et(data, "rxq_%u_pkts", i); + data = nfp_pr_et(data, "rxq_%u_bytes", i); + } + + return data; +} + +static u64 * +nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem, + unsigned int rx_rings, unsigned int tx_rings) +{ + unsigned int i; + + for (i = 0; i < NN_ET_GLOBAL_STATS_LEN; i++) + *data++ = readq(mem + nfp_net_et_stats[i].off); + + for (i = 0; i < tx_rings; i++) { + *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i)); + *data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8); + } + + for (i = 0; i < rx_rings; i++) { + *data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i)); + *data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i) + 8); } - for (j = 0; j < nn->dp.num_rx_rings; j++) { - io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j); - data[i++] = readq(io_p); - io_p = nn->dp.ctrl_bar + NFP_NET_CFG_RXR_STATS(j) + 8; - data[i++] = readq(io_p); + + return data; +} + +static unsigned int nfp_mac_get_stats_count(struct net_device *netdev) +{ + struct nfp_port *port; + + port = nfp_port_from_netdev(netdev); + if (!__nfp_port_get_eth_port(port) || !port->eth_stats) + return 0; + + return ARRAY_SIZE(nfp_mac_et_stats); +} + +static u8 *nfp_mac_get_stats_strings(struct net_device *netdev, u8 *data) +{ + struct nfp_port *port; + unsigned int i; + + port = nfp_port_from_netdev(netdev); + if (!__nfp_port_get_eth_port(port) || !port->eth_stats) + return data; + + for (i = 0; i < ARRAY_SIZE(nfp_mac_et_stats); i++) + data = nfp_pr_et(data, "mac.%s", nfp_mac_et_stats[i].name); + + return data; +} + +static u64 *nfp_mac_get_stats(struct net_device *netdev, u64 *data) +{ + struct nfp_port *port; + unsigned int i; + + port = nfp_port_from_netdev(netdev); + if (!__nfp_port_get_eth_port(port) || !port->eth_stats) + return data; + + for (i = 0; i < ARRAY_SIZE(nfp_mac_et_stats); i++) + *data++ = readq(port->eth_stats + nfp_mac_et_stats[i].off); + + return data; +} + +static void nfp_net_get_strings(struct net_device *netdev, + u32 stringset, u8 *data) +{ + struct nfp_net *nn = netdev_priv(netdev); + + switch (stringset) { + case ETH_SS_STATS: + data = nfp_vnic_get_sw_stats_strings(netdev, data); + data = nfp_vnic_get_hw_stats_strings(data, nn->dp.num_rx_rings, + nn->dp.num_tx_rings, + false); + data = nfp_mac_get_stats_strings(netdev, data); + break; } } +static void +nfp_net_get_stats(struct net_device *netdev, struct ethtool_stats *stats, + u64 *data) +{ + struct nfp_net *nn = netdev_priv(netdev); + + data = nfp_vnic_get_sw_stats(netdev, data); + data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar, + nn->dp.num_rx_rings, nn->dp.num_tx_rings); + data = nfp_mac_get_stats(netdev, data); +} + static int nfp_net_get_sset_count(struct net_device *netdev, int sset) { struct nfp_net *nn = netdev_priv(netdev); switch (sset) { case ETH_SS_STATS: - return NN_ET_STATS_LEN; + return nfp_vnic_get_sw_stats_count(netdev) + + nfp_vnic_get_hw_stats_count(nn->dp.num_rx_rings, + nn->dp.num_tx_rings) + + nfp_mac_get_stats_count(netdev); + default: + return -EOPNOTSUPP; + } +} + +static void nfp_port_get_strings(struct net_device *netdev, + u32 stringset, u8 *data) +{ + struct nfp_port *port = nfp_port_from_netdev(netdev); + + switch (stringset) { + case ETH_SS_STATS: + if (nfp_port_is_vnic(port)) + data = nfp_vnic_get_hw_stats_strings(data, 0, 0, true); + else + data = nfp_mac_get_stats_strings(netdev, data); + break; + } +} + +static void +nfp_port_get_stats(struct net_device *netdev, struct ethtool_stats *stats, + u64 *data) +{ + struct nfp_port *port = nfp_port_from_netdev(netdev); + + if (nfp_port_is_vnic(port)) + data = nfp_vnic_get_hw_stats(data, port->vnic, 0, 0); + else + data = nfp_mac_get_stats(netdev, data); +} + +static int nfp_port_get_sset_count(struct net_device *netdev, int sset) +{ + struct nfp_port *port = nfp_port_from_netdev(netdev); + unsigned int count; + + switch (sset) { + case ETH_SS_STATS: + if (nfp_port_is_vnic(port)) + count = nfp_vnic_get_hw_stats_count(0, 0); + else + count = nfp_mac_get_stats_count(netdev); + return count; default: return -EOPNOTSUPP; } @@ -708,18 +912,18 @@ static int nfp_net_get_coalesce(struct net_device *netdev, /* Other debug dumps */ static int -nfp_dump_nsp_diag(struct nfp_net *nn, struct ethtool_dump *dump, void *buffer) +nfp_dump_nsp_diag(struct nfp_app *app, struct ethtool_dump *dump, void *buffer) { struct nfp_resource *res; int ret; - if (!nn->app) + if (!app) return -EOPNOTSUPP; dump->version = 1; dump->flag = NFP_DUMP_NSP_DIAG; - res = nfp_resource_acquire(nn->app->cpp, NFP_RESOURCE_NSP_DIAG); + res = nfp_resource_acquire(app->cpp, NFP_RESOURCE_NSP_DIAG); if (IS_ERR(res)) return PTR_ERR(res); @@ -729,7 +933,7 @@ nfp_dump_nsp_diag(struct nfp_net *nn, struct ethtool_dump *dump, void *buffer) goto exit_release; } - ret = nfp_cpp_read(nn->app->cpp, nfp_resource_cpp_id(res), + ret = nfp_cpp_read(app->cpp, nfp_resource_cpp_id(res), nfp_resource_address(res), buffer, dump->len); if (ret != dump->len) @@ -746,32 +950,30 @@ exit_release: return ret; } -static int nfp_net_set_dump(struct net_device *netdev, struct ethtool_dump *val) +static int nfp_app_set_dump(struct net_device *netdev, struct ethtool_dump *val) { - struct nfp_net *nn = netdev_priv(netdev); + struct nfp_app *app = nfp_app_from_netdev(netdev); - if (!nn->app) + if (!app) return -EOPNOTSUPP; if (val->flag != NFP_DUMP_NSP_DIAG) return -EINVAL; - nn->ethtool_dump_flag = val->flag; - return 0; } static int -nfp_net_get_dump_flag(struct net_device *netdev, struct ethtool_dump *dump) +nfp_app_get_dump_flag(struct net_device *netdev, struct ethtool_dump *dump) { - return nfp_dump_nsp_diag(netdev_priv(netdev), dump, NULL); + return nfp_dump_nsp_diag(nfp_app_from_netdev(netdev), dump, NULL); } static int -nfp_net_get_dump_data(struct net_device *netdev, struct ethtool_dump *dump, +nfp_app_get_dump_data(struct net_device *netdev, struct ethtool_dump *dump, void *buffer) { - return nfp_dump_nsp_diag(netdev_priv(netdev), dump, buffer); + return nfp_dump_nsp_diag(nfp_app_from_netdev(netdev), dump, buffer); } static int nfp_net_set_coalesce(struct net_device *netdev, @@ -928,9 +1130,9 @@ static const struct ethtool_ops nfp_net_ethtool_ops = { .set_rxfh = nfp_net_set_rxfh, .get_regs_len = nfp_net_get_regs_len, .get_regs = nfp_net_get_regs, - .set_dump = nfp_net_set_dump, - .get_dump_flag = nfp_net_get_dump_flag, - .get_dump_data = nfp_net_get_dump_data, + .set_dump = nfp_app_set_dump, + .get_dump_flag = nfp_app_get_dump_flag, + .get_dump_data = nfp_app_get_dump_data, .get_coalesce = nfp_net_get_coalesce, .set_coalesce = nfp_net_set_coalesce, .get_channels = nfp_net_get_channels, @@ -939,6 +1141,17 @@ static const struct ethtool_ops nfp_net_ethtool_ops = { .set_link_ksettings = nfp_net_set_link_ksettings, }; +const struct ethtool_ops nfp_port_ethtool_ops = { + .get_drvinfo = nfp_app_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_strings = nfp_port_get_strings, + .get_ethtool_stats = nfp_port_get_stats, + .get_sset_count = nfp_port_get_sset_count, + .set_dump = nfp_app_set_dump, + .get_dump_flag = nfp_app_get_dump_flag, + .get_dump_data = nfp_app_get_dump_data, +}; + void nfp_net_set_ethtool_ops(struct net_device *netdev) { netdev->ethtool_ops = &nfp_net_ethtool_ops; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 34b985384d26..5abb9ba31e7d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -57,6 +57,7 @@ #include "nfpcore/nfp6000_pcie.h" #include "nfp_app.h" #include "nfp_net_ctrl.h" +#include "nfp_net_sriov.h" #include "nfp_net.h" #include "nfp_main.h" #include "nfp_port.h" @@ -160,6 +161,8 @@ nfp_net_pf_map_rtsym(struct nfp_pf *pf, const char *name, const char *sym_fmt, static void nfp_net_pf_free_vnic(struct nfp_pf *pf, struct nfp_net *nn) { + if (nfp_net_is_data_vnic(nn)) + nfp_app_vnic_free(pf->app, nn); nfp_port_free(nn->port); list_del(&nn->vnic_list); pf->num_vnics--; @@ -204,7 +207,7 @@ nfp_net_pf_alloc_vnic(struct nfp_pf *pf, bool needs_netdev, nn->stride_tx = stride; if (needs_netdev) { - err = nfp_app_vnic_init(pf->app, nn, id); + err = nfp_app_vnic_alloc(pf->app, nn, id); if (err) { nfp_net_free(nn); return ERR_PTR(err); @@ -242,8 +245,17 @@ nfp_net_pf_init_vnic(struct nfp_pf *pf, struct nfp_net *nn, unsigned int id) nfp_net_info(nn); + if (nfp_net_is_data_vnic(nn)) { + err = nfp_app_vnic_init(pf->app, nn); + if (err) + goto err_devlink_port_clean; + } + return 0; +err_devlink_port_clean: + if (nn->port) + nfp_devlink_port_unregister(nn->port); err_dfs_clean: nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_clean(nn); @@ -287,11 +299,12 @@ err_free_prev: static void nfp_net_pf_clean_vnic(struct nfp_pf *pf, struct nfp_net *nn) { + if (nfp_net_is_data_vnic(nn)) + nfp_app_vnic_clean(pf->app, nn); if (nn->port) nfp_devlink_port_unregister(nn->port); nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_clean(nn); - nfp_app_vnic_clean(pf->app, nn); } static int nfp_net_pf_alloc_irqs(struct nfp_pf *pf) @@ -388,7 +401,7 @@ nfp_net_pf_app_init(struct nfp_pf *pf, u8 __iomem *qc_bar, unsigned int stride) NFP_PF_CSR_SLICE_SIZE, &pf->ctrl_vnic_bar); if (IS_ERR(ctrl_bar)) { - nfp_err(pf->cpp, "Failed to find data vNIC memory symbol\n"); + nfp_err(pf->cpp, "Failed to find ctrl vNIC memory symbol\n"); err = PTR_ERR(ctrl_bar); goto err_app_clean; } @@ -456,10 +469,14 @@ static int nfp_net_pf_app_start(struct nfp_pf *pf) { int err; - err = nfp_app_start(pf->app, pf->ctrl_vnic); + err = nfp_net_pf_app_start_ctrl(pf); if (err) return err; + err = nfp_app_start(pf->app, pf->ctrl_vnic); + if (err) + goto err_ctrl_stop; + if (pf->num_vfs) { err = nfp_app_sriov_enable(pf->app, pf->num_vfs); if (err) @@ -470,6 +487,8 @@ static int nfp_net_pf_app_start(struct nfp_pf *pf) err_app_stop: nfp_app_stop(pf->app); +err_ctrl_stop: + nfp_net_pf_app_stop_ctrl(pf); return err; } @@ -478,10 +497,13 @@ static void nfp_net_pf_app_stop(struct nfp_pf *pf) if (pf->num_vfs) nfp_app_sriov_disable(pf->app); nfp_app_stop(pf->app); + nfp_net_pf_app_stop_ctrl(pf); } static void nfp_net_pci_unmap_mem(struct nfp_pf *pf) { + if (pf->vfcfg_tbl2_area) + nfp_cpp_area_release_free(pf->vfcfg_tbl2_area); if (pf->vf_cfg_bar) nfp_cpp_area_release_free(pf->vf_cfg_bar); if (pf->mac_stats_bar) @@ -497,7 +519,7 @@ static int nfp_net_pci_map_mem(struct nfp_pf *pf) int err; min_size = pf->max_data_vnics * NFP_PF_CSR_SLICE_SIZE; - mem = nfp_net_pf_map_rtsym(pf, "net.ctrl", "_pf%d_net_bar0", + mem = nfp_net_pf_map_rtsym(pf, "net.bar0", "_pf%d_net_bar0", min_size, &pf->data_vnic_bar); if (IS_ERR(mem)) { nfp_err(pf->cpp, "Failed to find data vNIC memory symbol\n"); @@ -528,17 +550,32 @@ static int nfp_net_pci_map_mem(struct nfp_pf *pf) pf->vf_cfg_mem = NULL; } + min_size = NFP_NET_VF_CFG_SZ * pf->limit_vfs + NFP_NET_VF_CFG_MB_SZ; + pf->vfcfg_tbl2 = nfp_net_pf_map_rtsym(pf, "net.vfcfg_tbl2", + "_pf%d_net_vf_cfg2", + min_size, &pf->vfcfg_tbl2_area); + if (IS_ERR(pf->vfcfg_tbl2)) { + if (PTR_ERR(pf->vfcfg_tbl2) != -ENOENT) { + err = PTR_ERR(pf->vfcfg_tbl2); + goto err_unmap_vf_cfg; + } + pf->vfcfg_tbl2 = NULL; + } + mem = nfp_cpp_map_area(pf->cpp, "net.qc", 0, 0, NFP_PCIE_QUEUE(0), NFP_QCP_QUEUE_AREA_SZ, &pf->qc_area); if (IS_ERR(mem)) { nfp_err(pf->cpp, "Failed to map Queue Controller area.\n"); err = PTR_ERR(mem); - goto err_unmap_vf_cfg; + goto err_unmap_vfcfg_tbl2; } return 0; +err_unmap_vfcfg_tbl2: + if (pf->vfcfg_tbl2_area) + nfp_cpp_area_release_free(pf->vfcfg_tbl2_area); err_unmap_vf_cfg: if (pf->vf_cfg_bar) nfp_cpp_area_release_free(pf->vf_cfg_bar); @@ -552,7 +589,7 @@ err_unmap_ctrl: static void nfp_net_pci_remove_finish(struct nfp_pf *pf) { - nfp_net_pf_app_stop_ctrl(pf); + nfp_net_pf_app_stop(pf); /* stop app first, to avoid double free of ctrl vNIC's ddir */ nfp_net_debugfs_dir_clean(&pf->ddir); @@ -683,7 +720,6 @@ int nfp_net_pci_probe(struct nfp_pf *pf) { struct nfp_net_fw_version fw_ver; u8 __iomem *ctrl_bar, *qc_bar; - struct nfp_net *nn; int stride; int err; @@ -698,7 +734,7 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (!pf->rtbl) { nfp_err(pf->cpp, "No %s, giving up.\n", pf->fw_loaded ? "symbol table" : "firmware found"); - return -EPROBE_DEFER; + return -EINVAL; } mutex_lock(&pf->lock); @@ -760,7 +796,7 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (err) goto err_free_vnics; - err = nfp_net_pf_app_start_ctrl(pf); + err = nfp_net_pf_app_start(pf); if (err) goto err_free_irqs; @@ -768,20 +804,12 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (err) goto err_stop_app; - err = nfp_net_pf_app_start(pf); - if (err) - goto err_clean_vnics; - mutex_unlock(&pf->lock); return 0; -err_clean_vnics: - list_for_each_entry(nn, &pf->vnics, vnic_list) - if (nfp_net_is_data_vnic(nn)) - nfp_net_pf_clean_vnic(pf, nn); err_stop_app: - nfp_net_pf_app_stop_ctrl(pf); + nfp_net_pf_app_stop(pf); err_free_irqs: nfp_net_pf_free_irqs(pf); err_free_vnics: @@ -805,8 +833,6 @@ void nfp_net_pci_remove(struct nfp_pf *pf) if (list_empty(&pf->vnics)) goto out; - nfp_net_pf_app_stop(pf); - list_for_each_entry(nn, &pf->vnics, vnic_list) if (nfp_net_is_data_vnic(nn)) nfp_net_pf_clean_vnic(pf, nn); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 8ec5474f4b18..d540a9dc77b3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -43,6 +43,7 @@ #include "nfp_main.h" #include "nfp_net_ctrl.h" #include "nfp_net_repr.h" +#include "nfp_net_sriov.h" #include "nfp_port.h" static void @@ -78,12 +79,10 @@ void nfp_repr_inc_rx_stats(struct net_device *netdev, unsigned int len) } static void -nfp_repr_phy_port_get_stats64(const struct nfp_app *app, u8 phy_port, +nfp_repr_phy_port_get_stats64(struct nfp_port *port, struct rtnl_link_stats64 *stats) { - u8 __iomem *mem; - - mem = app->pf->mac_stats_mem + phy_port * NFP_MAC_STATS_SIZE; + u8 __iomem *mem = port->eth_stats; /* TX and RX stats are flipped as we are returning the stats as seen * at the switch port corresponding to the phys port. @@ -98,67 +97,38 @@ nfp_repr_phy_port_get_stats64(const struct nfp_app *app, u8 phy_port, } static void -nfp_repr_vf_get_stats64(const struct nfp_app *app, u8 vf, - struct rtnl_link_stats64 *stats) +nfp_repr_vnic_get_stats64(struct nfp_port *port, + struct rtnl_link_stats64 *stats) { - u8 __iomem *mem; - - mem = app->pf->vf_cfg_mem + vf * NFP_NET_CFG_BAR_SZ; - /* TX and RX stats are flipped as we are returning the stats as seen * at the switch port corresponding to the VF. */ - stats->tx_packets = readq(mem + NFP_NET_CFG_STATS_RX_FRAMES); - stats->tx_bytes = readq(mem + NFP_NET_CFG_STATS_RX_OCTETS); - stats->tx_dropped = readq(mem + NFP_NET_CFG_STATS_RX_DISCARDS); - - stats->rx_packets = readq(mem + NFP_NET_CFG_STATS_TX_FRAMES); - stats->rx_bytes = readq(mem + NFP_NET_CFG_STATS_TX_OCTETS); - stats->rx_dropped = readq(mem + NFP_NET_CFG_STATS_TX_DISCARDS); -} - -static void -nfp_repr_pf_get_stats64(const struct nfp_app *app, u8 pf, - struct rtnl_link_stats64 *stats) -{ - u8 __iomem *mem; - - if (pf) - return; + stats->tx_packets = readq(port->vnic + NFP_NET_CFG_STATS_RX_FRAMES); + stats->tx_bytes = readq(port->vnic + NFP_NET_CFG_STATS_RX_OCTETS); + stats->tx_dropped = readq(port->vnic + NFP_NET_CFG_STATS_RX_DISCARDS); - mem = nfp_cpp_area_iomem(app->pf->data_vnic_bar); - - stats->tx_packets = readq(mem + NFP_NET_CFG_STATS_RX_FRAMES); - stats->tx_bytes = readq(mem + NFP_NET_CFG_STATS_RX_OCTETS); - stats->tx_dropped = readq(mem + NFP_NET_CFG_STATS_RX_DISCARDS); - - stats->rx_packets = readq(mem + NFP_NET_CFG_STATS_TX_FRAMES); - stats->rx_bytes = readq(mem + NFP_NET_CFG_STATS_TX_OCTETS); - stats->rx_dropped = readq(mem + NFP_NET_CFG_STATS_TX_DISCARDS); + stats->rx_packets = readq(port->vnic + NFP_NET_CFG_STATS_TX_FRAMES); + stats->rx_bytes = readq(port->vnic + NFP_NET_CFG_STATS_TX_OCTETS); + stats->rx_dropped = readq(port->vnic + NFP_NET_CFG_STATS_TX_DISCARDS); } static void nfp_repr_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { struct nfp_repr *repr = netdev_priv(netdev); - struct nfp_eth_table_port *eth_port; - struct nfp_app *app = repr->app; if (WARN_ON(!repr->port)) return; switch (repr->port->type) { case NFP_PORT_PHYS_PORT: - eth_port = __nfp_port_get_eth_port(repr->port); - if (!eth_port) + if (!__nfp_port_get_eth_port(repr->port)) break; - nfp_repr_phy_port_get_stats64(app, eth_port->index, stats); + nfp_repr_phy_port_get_stats64(repr->port, stats); break; case NFP_PORT_PF_PORT: - nfp_repr_pf_get_stats64(app, repr->port->pf_id, stats); - break; case NFP_PORT_VF_PORT: - nfp_repr_vf_get_stats64(app, repr->port->vf_id, stats); + nfp_repr_vnic_get_stats64(repr->port, stats); default: break; } @@ -239,15 +209,34 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev) static int nfp_repr_stop(struct net_device *netdev) { struct nfp_repr *repr = netdev_priv(netdev); + int err; + + err = nfp_app_repr_stop(repr->app, repr); + if (err) + return err; - return nfp_app_repr_stop(repr->app, repr); + nfp_port_configure(netdev, false); + return 0; } static int nfp_repr_open(struct net_device *netdev) { struct nfp_repr *repr = netdev_priv(netdev); + int err; + + err = nfp_port_configure(netdev, true); + if (err) + return err; - return nfp_app_repr_open(repr->app, repr); + err = nfp_app_repr_open(repr->app, repr); + if (err) + goto err_port_disable; + + return 0; + +err_port_disable: + nfp_port_configure(netdev, false); + return err; } const struct net_device_ops nfp_repr_netdev_ops = { @@ -259,6 +248,11 @@ const struct net_device_ops nfp_repr_netdev_ops = { .ndo_get_offload_stats = nfp_repr_get_offload_stats, .ndo_get_phys_port_name = nfp_port_get_phys_port_name, .ndo_setup_tc = nfp_port_setup_tc, + .ndo_set_vf_mac = nfp_app_set_vf_mac, + .ndo_set_vf_vlan = nfp_app_set_vf_vlan, + .ndo_set_vf_spoofchk = nfp_app_set_vf_spoofchk, + .ndo_get_vf_config = nfp_app_get_vf_config, + .ndo_set_vf_link_state = nfp_app_set_vf_link_state, }; static void nfp_repr_clean(struct nfp_repr *repr) @@ -301,6 +295,8 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, repr->dst->u.port_info.lower_dev = pf_netdev; netdev->netdev_ops = &nfp_repr_netdev_ops; + netdev->ethtool_ops = &nfp_port_ethtool_ops; + SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops); if (nfp_app_has_tc(app)) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c new file mode 100644 index 000000000000..e6d2e06b050c --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.c @@ -0,0 +1,243 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/bitfield.h> +#include <linux/errno.h> +#include <linux/etherdevice.h> +#include <linux/if_link.h> +#include <linux/if_ether.h> + +#include "nfpcore/nfp_cpp.h" +#include "nfp_app.h" +#include "nfp_main.h" +#include "nfp_net_ctrl.h" +#include "nfp_net.h" +#include "nfp_net_sriov.h" + +static int +nfp_net_sriov_check(struct nfp_app *app, int vf, u16 cap, const char *msg) +{ + u16 cap_vf; + + if (!app || !app->pf->vfcfg_tbl2) + return -EOPNOTSUPP; + + cap_vf = readw(app->pf->vfcfg_tbl2 + NFP_NET_VF_CFG_MB_CAP); + if ((cap_vf & cap) != cap) { + nfp_warn(app->pf->cpp, "ndo_set_vf_%s not supported\n", msg); + return -EOPNOTSUPP; + } + + if (vf < 0 || vf >= app->pf->num_vfs) { + nfp_warn(app->pf->cpp, "invalid VF id %d\n", vf); + return -EINVAL; + } + + return 0; +} + +static int +nfp_net_sriov_update(struct nfp_app *app, int vf, u16 update, const char *msg) +{ + struct nfp_net *nn; + int ret; + + /* Write update info to mailbox in VF config symbol */ + writeb(vf, app->pf->vfcfg_tbl2 + NFP_NET_VF_CFG_MB_VF_NUM); + writew(update, app->pf->vfcfg_tbl2 + NFP_NET_VF_CFG_MB_UPD); + + nn = list_first_entry(&app->pf->vnics, struct nfp_net, vnic_list); + /* Signal VF reconfiguration */ + ret = nfp_net_reconfig(nn, NFP_NET_CFG_UPDATE_VF); + if (ret) + return ret; + + ret = readw(app->pf->vfcfg_tbl2 + NFP_NET_VF_CFG_MB_RET); + if (ret) + nfp_warn(app->pf->cpp, + "FW refused VF %s update with errno: %d\n", msg, ret); + return -ret; +} + +int nfp_app_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) +{ + struct nfp_app *app = nfp_app_from_netdev(netdev); + unsigned int vf_offset; + int err; + + err = nfp_net_sriov_check(app, vf, NFP_NET_VF_CFG_MB_CAP_MAC, "mac"); + if (err) + return err; + + if (is_multicast_ether_addr(mac)) { + nfp_warn(app->pf->cpp, + "invalid Ethernet address %pM for VF id %d\n", + mac, vf); + return -EINVAL; + } + + /* Write MAC to VF entry in VF config symbol */ + vf_offset = NFP_NET_VF_CFG_MB_SZ + vf * NFP_NET_VF_CFG_SZ; + writel(get_unaligned_be32(mac), app->pf->vfcfg_tbl2 + vf_offset); + writew(get_unaligned_be16(mac + 4), + app->pf->vfcfg_tbl2 + vf_offset + NFP_NET_VF_CFG_MAC_LO); + + return nfp_net_sriov_update(app, vf, NFP_NET_VF_CFG_MB_UPD_MAC, "MAC"); +} + +int nfp_app_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) +{ + struct nfp_app *app = nfp_app_from_netdev(netdev); + unsigned int vf_offset; + u16 vlan_tci; + int err; + + err = nfp_net_sriov_check(app, vf, NFP_NET_VF_CFG_MB_CAP_VLAN, "vlan"); + if (err) + return err; + + if (vlan_proto != htons(ETH_P_8021Q)) + return -EOPNOTSUPP; + + if (vlan > 4095 || qos > 7) { + nfp_warn(app->pf->cpp, + "invalid vlan id or qos for VF id %d\n", vf); + return -EINVAL; + } + + /* Write VLAN tag to VF entry in VF config symbol */ + vlan_tci = FIELD_PREP(NFP_NET_VF_CFG_VLAN_VID, vlan) | + FIELD_PREP(NFP_NET_VF_CFG_VLAN_QOS, qos); + vf_offset = NFP_NET_VF_CFG_MB_SZ + vf * NFP_NET_VF_CFG_SZ; + writew(vlan_tci, app->pf->vfcfg_tbl2 + vf_offset + NFP_NET_VF_CFG_VLAN); + + return nfp_net_sriov_update(app, vf, NFP_NET_VF_CFG_MB_UPD_VLAN, + "vlan"); +} + +int nfp_app_set_vf_spoofchk(struct net_device *netdev, int vf, bool enable) +{ + struct nfp_app *app = nfp_app_from_netdev(netdev); + unsigned int vf_offset; + u8 vf_ctrl; + int err; + + err = nfp_net_sriov_check(app, vf, NFP_NET_VF_CFG_MB_CAP_SPOOF, + "spoofchk"); + if (err) + return err; + + /* Write spoof check control bit to VF entry in VF config symbol */ + vf_offset = NFP_NET_VF_CFG_MB_SZ + vf * NFP_NET_VF_CFG_SZ + + NFP_NET_VF_CFG_CTRL; + vf_ctrl = readb(app->pf->vfcfg_tbl2 + vf_offset); + vf_ctrl &= ~NFP_NET_VF_CFG_CTRL_SPOOF; + vf_ctrl |= FIELD_PREP(NFP_NET_VF_CFG_CTRL_SPOOF, enable); + writeb(vf_ctrl, app->pf->vfcfg_tbl2 + vf_offset); + + return nfp_net_sriov_update(app, vf, NFP_NET_VF_CFG_MB_UPD_SPOOF, + "spoofchk"); +} + +int nfp_app_set_vf_link_state(struct net_device *netdev, int vf, + int link_state) +{ + struct nfp_app *app = nfp_app_from_netdev(netdev); + unsigned int vf_offset; + u8 vf_ctrl; + int err; + + err = nfp_net_sriov_check(app, vf, NFP_NET_VF_CFG_MB_CAP_LINK_STATE, + "link_state"); + if (err) + return err; + + switch (link_state) { + case IFLA_VF_LINK_STATE_AUTO: + case IFLA_VF_LINK_STATE_ENABLE: + case IFLA_VF_LINK_STATE_DISABLE: + break; + default: + return -EINVAL; + } + + /* Write link state to VF entry in VF config symbol */ + vf_offset = NFP_NET_VF_CFG_MB_SZ + vf * NFP_NET_VF_CFG_SZ + + NFP_NET_VF_CFG_CTRL; + vf_ctrl = readb(app->pf->vfcfg_tbl2 + vf_offset); + vf_ctrl &= ~NFP_NET_VF_CFG_CTRL_LINK_STATE; + vf_ctrl |= FIELD_PREP(NFP_NET_VF_CFG_CTRL_LINK_STATE, link_state); + writeb(vf_ctrl, app->pf->vfcfg_tbl2 + vf_offset); + + return nfp_net_sriov_update(app, vf, NFP_NET_VF_CFG_MB_UPD_LINK_STATE, + "link state"); +} + +int nfp_app_get_vf_config(struct net_device *netdev, int vf, + struct ifla_vf_info *ivi) +{ + struct nfp_app *app = nfp_app_from_netdev(netdev); + unsigned int vf_offset; + u16 vlan_tci; + u32 mac_hi; + u16 mac_lo; + u8 flags; + int err; + + err = nfp_net_sriov_check(app, vf, 0, ""); + if (err) + return err; + + vf_offset = NFP_NET_VF_CFG_MB_SZ + vf * NFP_NET_VF_CFG_SZ; + + mac_hi = readl(app->pf->vfcfg_tbl2 + vf_offset); + mac_lo = readw(app->pf->vfcfg_tbl2 + vf_offset + NFP_NET_VF_CFG_MAC_LO); + + flags = readb(app->pf->vfcfg_tbl2 + vf_offset + NFP_NET_VF_CFG_CTRL); + vlan_tci = readw(app->pf->vfcfg_tbl2 + vf_offset + NFP_NET_VF_CFG_VLAN); + + memset(ivi, 0, sizeof(*ivi)); + ivi->vf = vf; + + put_unaligned_be32(mac_hi, &ivi->mac[0]); + put_unaligned_be16(mac_lo, &ivi->mac[4]); + + ivi->vlan = FIELD_GET(NFP_NET_VF_CFG_VLAN_VID, vlan_tci); + ivi->qos = FIELD_GET(NFP_NET_VF_CFG_VLAN_QOS, vlan_tci); + + ivi->spoofchk = FIELD_GET(NFP_NET_VF_CFG_CTRL_SPOOF, flags); + ivi->linkstate = FIELD_GET(NFP_NET_VF_CFG_CTRL_LINK_STATE, flags); + + return 0; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h new file mode 100644 index 000000000000..e9df9d1eab8e --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_sriov.h @@ -0,0 +1,86 @@ +/* + * Copyright (C) 2017 Netronome Systems, Inc. + * + * This software is dual licensed under the GNU General License Version 2, + * June 1991 as shown in the file COPYING in the top-level directory of this + * source tree or the BSD 2-Clause License provided below. You have the + * option to license this software under the complete terms of either license. + * + * The BSD 2-Clause License: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * 1. Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * 2. Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#ifndef _NFP_NET_SRIOV_H_ +#define _NFP_NET_SRIOV_H_ + +/** + * SRIOV VF configuration. + * The configuration memory begins with a mailbox region for communication with + * the firmware followed by individual VF entries. + */ +#define NFP_NET_VF_CFG_SZ 16 +#define NFP_NET_VF_CFG_MB_SZ 16 + +/* VF config mailbox */ +#define NFP_NET_VF_CFG_MB 0x0 +#define NFP_NET_VF_CFG_MB_CAP 0x0 +#define NFP_NET_VF_CFG_MB_CAP_MAC (0x1 << 0) +#define NFP_NET_VF_CFG_MB_CAP_VLAN (0x1 << 1) +#define NFP_NET_VF_CFG_MB_CAP_SPOOF (0x1 << 2) +#define NFP_NET_VF_CFG_MB_CAP_LINK_STATE (0x1 << 3) +#define NFP_NET_VF_CFG_MB_RET 0x2 +#define NFP_NET_VF_CFG_MB_UPD 0x4 +#define NFP_NET_VF_CFG_MB_UPD_MAC (0x1 << 0) +#define NFP_NET_VF_CFG_MB_UPD_VLAN (0x1 << 1) +#define NFP_NET_VF_CFG_MB_UPD_SPOOF (0x1 << 2) +#define NFP_NET_VF_CFG_MB_UPD_LINK_STATE (0x1 << 3) +#define NFP_NET_VF_CFG_MB_VF_NUM 0x7 + +/* VF config entry + * MAC_LO is set that the MAC address can be read in a single 6 byte read + * by the NFP + */ +#define NFP_NET_VF_CFG_MAC 0x0 +#define NFP_NET_VF_CFG_MAC_HI 0x0 +#define NFP_NET_VF_CFG_MAC_LO 0x6 +#define NFP_NET_VF_CFG_CTRL 0x4 +#define NFP_NET_VF_CFG_CTRL_SPOOF 0x4 +#define NFP_NET_VF_CFG_CTRL_LINK_STATE 0x3 +#define NFP_NET_VF_CFG_LS_MODE_AUTO 0 +#define NFP_NET_VF_CFG_LS_MODE_ENABLE 1 +#define NFP_NET_VF_CFG_LS_MODE_DISABLE 2 +#define NFP_NET_VF_CFG_VLAN 0x8 +#define NFP_NET_VF_CFG_VLAN_QOS 0xe000 +#define NFP_NET_VF_CFG_VLAN_VID 0x0fff + +int nfp_app_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); +int nfp_app_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto); +int nfp_app_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting); +int nfp_app_set_vf_link_state(struct net_device *netdev, int vf, + int link_state); +int nfp_app_get_vf_config(struct net_device *netdev, int vf, + struct ifla_vf_info *ivi); + +#endif /* _NFP_NET_SRIOV_H_ */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.c b/drivers/net/ethernet/netronome/nfp/nfp_port.c index e42644dbb865..34a6e035fe9a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.c @@ -88,19 +88,16 @@ const struct switchdev_ops nfp_port_switchdev_ops = { .switchdev_port_attr_get = nfp_port_attr_get, }; -int nfp_port_setup_tc(struct net_device *netdev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc) +int nfp_port_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) { struct nfp_port *port; - if (chain_index) - return -EOPNOTSUPP; - port = nfp_port_from_netdev(netdev); if (!port) return -EOPNOTSUPP; - return nfp_app_setup_tc(port->app, netdev, handle, proto, tc); + return nfp_app_setup_tc(port->app, netdev, type, type_data); } struct nfp_port * @@ -181,6 +178,33 @@ nfp_port_get_phys_port_name(struct net_device *netdev, char *name, size_t len) return 0; } +/** + * nfp_port_configure() - helper to set the interface configured bit + * @netdev: net_device instance + * @configed: Desired state + * + * Helper to set the ifup/ifdown state on the PHY only if there is a physical + * interface associated with the netdev. + * + * Return: + * 0 - configuration successful (or no change); + * -ERRNO - configuration failed. + */ +int nfp_port_configure(struct net_device *netdev, bool configed) +{ + struct nfp_eth_table_port *eth_port; + struct nfp_port *port; + int err; + + port = nfp_port_from_netdev(netdev); + eth_port = __nfp_port_get_eth_port(port); + if (!eth_port) + return 0; + + err = nfp_eth_set_configured(port->app->cpp, eth_port->index, configed); + return err < 0 && err != -EOPNOTSUPP ? err : 0; +} + int nfp_port_init_phy_port(struct nfp_pf *pf, struct nfp_app *app, struct nfp_port *port, unsigned int id) { @@ -201,6 +225,9 @@ int nfp_port_init_phy_port(struct nfp_pf *pf, struct nfp_app *app, port->eth_port = &pf->eth_tbl->ports[id]; port->eth_id = pf->eth_tbl->ports[id].index; + if (pf->mac_stats_mem) + port->eth_stats = + pf->mac_stats_mem + port->eth_id * NFP_MAC_STATS_SIZE; return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index a33d22e18f94..51dcb9c603ee 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -36,7 +36,6 @@ #include <net/devlink.h> -struct tc_to_netdev; struct net_device; struct nfp_app; struct nfp_pf; @@ -77,8 +76,10 @@ enum nfp_port_flags { * @dl_port: devlink port structure * @eth_id: for %NFP_PORT_PHYS_PORT port ID in NFP enumeration scheme * @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry + * @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available * @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3) * @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id + * @vnic: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT vNIC ctrl memory * @port_list: entry on pf's list of ports */ struct nfp_port { @@ -96,21 +97,29 @@ struct nfp_port { struct { unsigned int eth_id; struct nfp_eth_table_port *eth_port; + u8 __iomem *eth_stats; }; /* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */ struct { unsigned int pf_id; unsigned int vf_id; + u8 __iomem *vnic; }; }; struct list_head port_list; }; +extern const struct ethtool_ops nfp_port_ethtool_ops; extern const struct switchdev_ops nfp_port_switchdev_ops; -int nfp_port_setup_tc(struct net_device *netdev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc); +int nfp_port_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data); + +static inline bool nfp_port_is_vnic(const struct nfp_port *port) +{ + return port->type == NFP_PORT_PF_PORT || port->type == NFP_PORT_VF_PORT; +} struct nfp_port *nfp_port_from_netdev(struct net_device *netdev); struct nfp_port * @@ -120,6 +129,7 @@ struct nfp_eth_table_port *nfp_port_get_eth_port(struct nfp_port *port); int nfp_port_get_phys_port_name(struct net_device *netdev, char *name, size_t len); +int nfp_port_configure(struct net_device *netdev, bool configed); struct nfp_port * nfp_port_alloc(struct nfp_app *app, enum nfp_port_type type, @@ -144,31 +154,32 @@ void nfp_devlink_port_unregister(struct nfp_port *port); #define NFP_MAC_STATS_SIZE 0x0200 #define NFP_MAC_STATS_RX_IN_OCTETS (NFP_MAC_STATS_BASE + 0x000) + /* unused 0x008 */ #define NFP_MAC_STATS_RX_FRAME_TOO_LONG_ERRORS (NFP_MAC_STATS_BASE + 0x010) #define NFP_MAC_STATS_RX_RANGE_LENGTH_ERRORS (NFP_MAC_STATS_BASE + 0x018) #define NFP_MAC_STATS_RX_VLAN_REVEIVE_OK (NFP_MAC_STATS_BASE + 0x020) #define NFP_MAC_STATS_RX_IN_ERRORS (NFP_MAC_STATS_BASE + 0x028) #define NFP_MAC_STATS_RX_IN_BROADCAST_PKTS (NFP_MAC_STATS_BASE + 0x030) -#define NFP_MAC_STATS_RX_STATS_DROP_EVENTS (NFP_MAC_STATS_BASE + 0x038) +#define NFP_MAC_STATS_RX_DROP_EVENTS (NFP_MAC_STATS_BASE + 0x038) #define NFP_MAC_STATS_RX_ALIGNMENT_ERRORS (NFP_MAC_STATS_BASE + 0x040) #define NFP_MAC_STATS_RX_PAUSE_MAC_CTRL_FRAMES (NFP_MAC_STATS_BASE + 0x048) #define NFP_MAC_STATS_RX_FRAMES_RECEIVED_OK (NFP_MAC_STATS_BASE + 0x050) #define NFP_MAC_STATS_RX_FRAME_CHECK_SEQUENCE_ERRORS (NFP_MAC_STATS_BASE + 0x058) #define NFP_MAC_STATS_RX_UNICAST_PKTS (NFP_MAC_STATS_BASE + 0x060) #define NFP_MAC_STATS_RX_MULTICAST_PKTS (NFP_MAC_STATS_BASE + 0x068) -#define NFP_MAC_STATS_RX_STATS_PKTS (NFP_MAC_STATS_BASE + 0x070) -#define NFP_MAC_STATS_RX_STATS_UNDERSIZE_PKTS (NFP_MAC_STATS_BASE + 0x078) -#define NFP_MAC_STATS_RX_STATS_PKTS_64_OCTETS (NFP_MAC_STATS_BASE + 0x080) -#define NFP_MAC_STATS_RX_STATS_PKTS_65_TO_127_OCTETS (NFP_MAC_STATS_BASE + 0x088) -#define NFP_MAC_STATS_RX_STATS_PKTS_512_TO_1023_OCTETS (NFP_MAC_STATS_BASE + 0x090) -#define NFP_MAC_STATS_RX_STATS_PKTS_1024_TO_1518_OCTETS (NFP_MAC_STATS_BASE + 0x098) -#define NFP_MAC_STATS_RX_STATS_JABBERS (NFP_MAC_STATS_BASE + 0x0a0) -#define NFP_MAC_STATS_RX_STATS_FRAGMENTS (NFP_MAC_STATS_BASE + 0x0a8) +#define NFP_MAC_STATS_RX_PKTS (NFP_MAC_STATS_BASE + 0x070) +#define NFP_MAC_STATS_RX_UNDERSIZE_PKTS (NFP_MAC_STATS_BASE + 0x078) +#define NFP_MAC_STATS_RX_PKTS_64_OCTETS (NFP_MAC_STATS_BASE + 0x080) +#define NFP_MAC_STATS_RX_PKTS_65_TO_127_OCTETS (NFP_MAC_STATS_BASE + 0x088) +#define NFP_MAC_STATS_RX_PKTS_512_TO_1023_OCTETS (NFP_MAC_STATS_BASE + 0x090) +#define NFP_MAC_STATS_RX_PKTS_1024_TO_1518_OCTETS (NFP_MAC_STATS_BASE + 0x098) +#define NFP_MAC_STATS_RX_JABBERS (NFP_MAC_STATS_BASE + 0x0a0) +#define NFP_MAC_STATS_RX_FRAGMENTS (NFP_MAC_STATS_BASE + 0x0a8) #define NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS2 (NFP_MAC_STATS_BASE + 0x0b0) #define NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS3 (NFP_MAC_STATS_BASE + 0x0b8) -#define NFP_MAC_STATS_RX_STATS_PKTS_128_TO_255_OCTETS (NFP_MAC_STATS_BASE + 0x0c0) -#define NFP_MAC_STATS_RX_STATS_PKTS_256_TO_511_OCTETS (NFP_MAC_STATS_BASE + 0x0c8) -#define NFP_MAC_STATS_RX_STATS_PKTS_1519_TO_MAX_OCTETS (NFP_MAC_STATS_BASE + 0x0d0) +#define NFP_MAC_STATS_RX_PKTS_128_TO_255_OCTETS (NFP_MAC_STATS_BASE + 0x0c0) +#define NFP_MAC_STATS_RX_PKTS_256_TO_511_OCTETS (NFP_MAC_STATS_BASE + 0x0c8) +#define NFP_MAC_STATS_RX_PKTS_1519_TO_MAX_OCTETS (NFP_MAC_STATS_BASE + 0x0d0) #define NFP_MAC_STATS_RX_OVERSIZE_PKTS (NFP_MAC_STATS_BASE + 0x0d8) #define NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS0 (NFP_MAC_STATS_BASE + 0x0e0) #define NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS1 (NFP_MAC_STATS_BASE + 0x0e8) @@ -178,9 +189,12 @@ void nfp_devlink_port_unregister(struct nfp_port *port); #define NFP_MAC_STATS_RX_PAUSE_FRAMES_CLASS7 (NFP_MAC_STATS_BASE + 0x108) #define NFP_MAC_STATS_RX_MAC_CTRL_FRAMES_RECEIVED (NFP_MAC_STATS_BASE + 0x110) #define NFP_MAC_STATS_RX_MAC_HEAD_DROP (NFP_MAC_STATS_BASE + 0x118) - + /* unused 0x120 */ + /* unused 0x128 */ + /* unused 0x130 */ #define NFP_MAC_STATS_TX_QUEUE_DROP (NFP_MAC_STATS_BASE + 0x138) #define NFP_MAC_STATS_TX_OUT_OCTETS (NFP_MAC_STATS_BASE + 0x140) + /* unused 0x148 */ #define NFP_MAC_STATS_TX_VLAN_TRANSMITTED_OK (NFP_MAC_STATS_BASE + 0x150) #define NFP_MAC_STATS_TX_OUT_ERRORS (NFP_MAC_STATS_BASE + 0x158) #define NFP_MAC_STATS_TX_BROADCAST_PKTS (NFP_MAC_STATS_BASE + 0x160) @@ -192,8 +206,16 @@ void nfp_devlink_port_unregister(struct nfp_port *port); #define NFP_MAC_STATS_TX_UNICAST_PKTS (NFP_MAC_STATS_BASE + 0x190) #define NFP_MAC_STATS_TX_MULTICAST_PKTS (NFP_MAC_STATS_BASE + 0x198) #define NFP_MAC_STATS_TX_PKTS_65_TO_127_OCTETS (NFP_MAC_STATS_BASE + 0x1a0) -#define NFP_MAC_STATS_TX_PKTS_127_TO_512_OCTETS (NFP_MAC_STATS_BASE + 0x1a8) -#define NFP_MAC_STATS_TX_PKTS_128_TO_1518_OCTETS (NFP_MAC_STATS_BASE + 0x1b0) -#define NFP_MAC_STATS_TX_PKTS_1518_TO_MAX_OCTETS (NFP_MAC_STATS_BASE + 0x1b8) +#define NFP_MAC_STATS_TX_PKTS_128_TO_255_OCTETS (NFP_MAC_STATS_BASE + 0x1a8) +#define NFP_MAC_STATS_TX_PKTS_1024_TO_1518_OCTETS (NFP_MAC_STATS_BASE + 0x1b0) +#define NFP_MAC_STATS_TX_PKTS_1519_TO_MAX_OCTETS (NFP_MAC_STATS_BASE + 0x1b8) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS0 (NFP_MAC_STATS_BASE + 0x1c0) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS1 (NFP_MAC_STATS_BASE + 0x1c8) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS4 (NFP_MAC_STATS_BASE + 0x1d0) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS5 (NFP_MAC_STATS_BASE + 0x1d8) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS2 (NFP_MAC_STATS_BASE + 0x1e0) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS3 (NFP_MAC_STATS_BASE + 0x1e8) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS6 (NFP_MAC_STATS_BASE + 0x1f0) +#define NFP_MAC_STATS_TX_PAUSE_FRAMES_CLASS7 (NFP_MAC_STATS_BASE + 0x1f8) #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c index c2bc36e8649f..f6f7c085f8e0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c @@ -391,7 +391,10 @@ int nfp_eth_config_commit_end(struct nfp_nsp *nsp) * Enable or disable PHY module (this usually means setting the TX lanes * disable bits). * - * Return: 0 or -ERRNO. + * Return: + * 0 - configuration successful; + * 1 - no changes were needed; + * -ERRNO - configuration failed. */ int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable) { @@ -427,7 +430,10 @@ int nfp_eth_set_mod_enable(struct nfp_cpp *cpp, unsigned int idx, bool enable) * * Set the ifup/ifdown state on the PHY. * - * Return: 0 or -ERRNO. + * Return: + * 0 - configuration successful; + * 1 - no changes were needed; + * -ERRNO - configuration failed. */ int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, bool configed) { @@ -439,6 +445,14 @@ int nfp_eth_set_configured(struct nfp_cpp *cpp, unsigned int idx, bool configed) if (IS_ERR(nsp)) return PTR_ERR(nsp); + /* Older ABI versions did support this feature, however this has only + * been reliable since ABI 20. + */ + if (nfp_nsp_get_abi_ver_minor(nsp) < 20) { + nfp_eth_config_cleanup_end(nsp); + return -EOPNOTSUPP; + } + entries = nfp_nsp_config_entries(nsp); /* Check if we are already in requested state */ diff --git a/drivers/net/ethernet/netronome/nfp/nic/main.c b/drivers/net/ethernet/netronome/nfp/nic/main.c index 520684242b7d..d5b587fccaa3 100644 --- a/drivers/net/ethernet/netronome/nfp/nic/main.c +++ b/drivers/net/ethernet/netronome/nfp/nic/main.c @@ -49,10 +49,22 @@ static int nfp_nic_init(struct nfp_app *app) return 0; } +static int nfp_nic_sriov_enable(struct nfp_app *app, int num_vfs) +{ + return 0; +} + +static void nfp_nic_sriov_disable(struct nfp_app *app) +{ +} + const struct nfp_app_type app_nic = { .id = NFP_APP_CORE_NIC, .name = "nic", .init = nfp_nic_init, - .vnic_init = nfp_app_nic_vnic_init, + .vnic_alloc = nfp_app_nic_vnic_alloc, + + .sriov_enable = nfp_nic_sriov_enable, + .sriov_disable = nfp_nic_sriov_disable, }; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index aa912f43e15f..994a83a1f0a5 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -5629,9 +5629,8 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id) setup_timer(&np->oom_kick, nv_do_rx_refill, (unsigned long)dev); setup_timer(&np->nic_poll, nv_do_nic_poll, (unsigned long)dev); - init_timer_deferrable(&np->stats_poll); - np->stats_poll.data = (unsigned long) dev; - np->stats_poll.function = nv_do_stats_poll; /* timer handler */ + setup_deferrable_timer(&np->stats_poll, nv_do_stats_poll, + (unsigned long)dev); err = pci_enable_device(pci_dev); if (err) diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 827de838389f..f2e8de607119 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -2828,7 +2828,7 @@ netxen_show_bridged_mode(struct device *dev, return sprintf(buf, "%d\n", bridged_mode); } -static struct device_attribute dev_attr_bridged_mode = { +static const struct device_attribute dev_attr_bridged_mode = { .attr = {.name = "bridged_mode", .mode = (S_IRUGO | S_IWUSR)}, .show = netxen_show_bridged_mode, .store = netxen_store_bridged_mode, @@ -2860,7 +2860,7 @@ netxen_show_diag_mode(struct device *dev, !!(adapter->flags & NETXEN_NIC_DIAG_ENABLED)); } -static struct device_attribute dev_attr_diag_mode = { +static const struct device_attribute dev_attr_diag_mode = { .attr = {.name = "diag_mode", .mode = (S_IRUGO | S_IWUSR)}, .show = netxen_show_diag_mode, .store = netxen_store_diag_mode, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 6c87bed13bd2..58a689fb04db 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1684,6 +1684,8 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) "Load request was sent. Load code: 0x%x\n", load_code); + qed_mcp_set_capabilities(p_hwfn, p_hwfn->p_main_ptt); + qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt); p_hwfn->first_on_engine = (load_code == @@ -2472,6 +2474,7 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u32 port_cfg_addr, link_temp, nvm_cfg_addr, device_capabilities; u32 nvm_cfg1_offset, mf_mode, addr, generic_cont0, core_cfg; + struct qed_mcp_link_capabilities *p_caps; struct qed_mcp_link_params *link; /* Read global nvm_cfg address */ @@ -2534,6 +2537,7 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) /* Read default link configuration */ link = &p_hwfn->mcp_info->link_input; + p_caps = &p_hwfn->mcp_info->link_capabilities; port_cfg_addr = MCP_REG_SCRATCH + nvm_cfg1_offset + offsetof(struct nvm_cfg1, port[MFW_PORT(p_hwfn)]); link_temp = qed_rd(p_hwfn, p_ptt, @@ -2588,10 +2592,45 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX); link->loopback_mode = 0; - DP_VERBOSE(p_hwfn, NETIF_MSG_LINK, - "Read default link: Speed 0x%08x, Adv. Speed 0x%08x, AN: 0x%02x, PAUSE AN: 0x%02x\n", - link->speed.forced_speed, link->speed.advertised_speeds, - link->speed.autoneg, link->pause.autoneg); + if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) { + link_temp = qed_rd(p_hwfn, p_ptt, port_cfg_addr + + offsetof(struct nvm_cfg1_port, ext_phy)); + link_temp &= NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_MASK; + link_temp >>= NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_OFFSET; + p_caps->default_eee = QED_MCP_EEE_ENABLED; + link->eee.enable = true; + switch (link_temp) { + case NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_DISABLED: + p_caps->default_eee = QED_MCP_EEE_DISABLED; + link->eee.enable = false; + break; + case NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_BALANCED: + p_caps->eee_lpi_timer = EEE_TX_TIMER_USEC_BALANCED_TIME; + break; + case NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_AGGRESSIVE: + p_caps->eee_lpi_timer = + EEE_TX_TIMER_USEC_AGGRESSIVE_TIME; + break; + case NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_LOW_LATENCY: + p_caps->eee_lpi_timer = EEE_TX_TIMER_USEC_LATENCY_TIME; + break; + } + + link->eee.tx_lpi_timer = p_caps->eee_lpi_timer; + link->eee.tx_lpi_enable = link->eee.enable; + link->eee.adv_caps = QED_EEE_1G_ADV | QED_EEE_10G_ADV; + } else { + p_caps->default_eee = QED_MCP_EEE_UNSUPPORTED; + } + + DP_VERBOSE(p_hwfn, + NETIF_MSG_LINK, + "Read default link: Speed 0x%08x, Adv. Speed 0x%08x, AN: 0x%02x, PAUSE AN: 0x%02x EEE: %02x [%08x usec]\n", + link->speed.forced_speed, + link->speed.advertised_speeds, + link->speed.autoneg, + link->pause.autoneg, + p_caps->default_eee, p_caps->eee_lpi_timer); /* Read Multi-function information from shmem */ addr = MCP_REG_SCRATCH + nvm_cfg1_offset + @@ -2751,6 +2790,27 @@ static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) qed_hw_info_port_num_ah(p_hwfn, p_ptt); } +static void qed_get_eee_caps(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + struct qed_mcp_link_capabilities *p_caps; + u32 eee_status; + + p_caps = &p_hwfn->mcp_info->link_capabilities; + if (p_caps->default_eee == QED_MCP_EEE_UNSUPPORTED) + return; + + p_caps->eee_speed_caps = 0; + eee_status = qed_rd(p_hwfn, p_ptt, p_hwfn->mcp_info->port_addr + + offsetof(struct public_port, eee_status)); + eee_status = (eee_status & EEE_SUPPORTED_SPEED_MASK) >> + EEE_SUPPORTED_SPEED_OFFSET; + + if (eee_status & EEE_1G_SUPPORTED) + p_caps->eee_speed_caps |= QED_EEE_1G_ADV; + if (eee_status & EEE_10G_ADV) + p_caps->eee_speed_caps |= QED_EEE_10G_ADV; +} + static int qed_get_hw_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -2767,6 +2827,8 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, qed_hw_info_port_num(p_hwfn, p_ptt); + qed_mcp_get_capabilities(p_hwfn, p_ptt); + qed_hw_get_nvm_info(p_hwfn, p_ptt); rc = qed_int_igu_read_cam(p_hwfn, p_ptt); @@ -2785,6 +2847,8 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, p_hwfn->mcp_info->func_info.ovlan; qed_mcp_cmd_port_init(p_hwfn, p_ptt); + + qed_get_eee_caps(p_hwfn, p_ptt); } if (qed_mcp_is_init(p_hwfn)) { @@ -3630,7 +3694,7 @@ static int qed_set_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, } p_coal_timeset = p_eth_qzone; - memset(p_coal_timeset, 0, eth_qzone_size); + memset(p_eth_qzone, 0, eth_qzone_size); SET_FIELD(p_coal_timeset->value, COALESCING_TIMESET_TIMESET, timeset); SET_FIELD(p_coal_timeset->value, COALESCING_TIMESET_VALID, 1); qed_memcpy_to(p_hwfn, p_ptt, hw_addr, p_eth_qzone, eth_qzone_size); @@ -3638,12 +3702,46 @@ static int qed_set_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, return 0; } -int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, - u16 coalesce, u16 qid, u16 sb_id) +int qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle) +{ + struct qed_queue_cid *p_cid = p_handle; + struct qed_hwfn *p_hwfn; + struct qed_ptt *p_ptt; + int rc = 0; + + p_hwfn = p_cid->p_owner; + + if (IS_VF(p_hwfn->cdev)) + return qed_vf_pf_set_coalesce(p_hwfn, rx_coal, tx_coal, p_cid); + + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EAGAIN; + + if (rx_coal) { + rc = qed_set_rxq_coalesce(p_hwfn, p_ptt, rx_coal, p_cid); + if (rc) + goto out; + p_hwfn->cdev->rx_coalesce_usecs = rx_coal; + } + + if (tx_coal) { + rc = qed_set_txq_coalesce(p_hwfn, p_ptt, tx_coal, p_cid); + if (rc) + goto out; + p_hwfn->cdev->tx_coalesce_usecs = tx_coal; + } +out: + qed_ptt_release(p_hwfn, p_ptt); + return rc; +} + +int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u16 coalesce, struct qed_queue_cid *p_cid) { struct ustorm_eth_queue_zone eth_qzone; u8 timeset, timer_res; - u16 fw_qid = 0; u32 address; int rc; @@ -3660,32 +3758,29 @@ int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, } timeset = (u8)(coalesce >> timer_res); - rc = qed_fw_l2_queue(p_hwfn, qid, &fw_qid); - if (rc) - return rc; - - rc = qed_int_set_timer_res(p_hwfn, p_ptt, timer_res, sb_id, false); + rc = qed_int_set_timer_res(p_hwfn, p_ptt, timer_res, + p_cid->sb_igu_id, false); if (rc) goto out; - address = BAR0_MAP_REG_USDM_RAM + USTORM_ETH_QUEUE_ZONE_OFFSET(fw_qid); + address = BAR0_MAP_REG_USDM_RAM + + USTORM_ETH_QUEUE_ZONE_OFFSET(p_cid->abs.queue_id); rc = qed_set_coalesce(p_hwfn, p_ptt, address, ð_qzone, sizeof(struct ustorm_eth_queue_zone), timeset); if (rc) goto out; - p_hwfn->cdev->rx_coalesce_usecs = coalesce; out: return rc; } -int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, - u16 coalesce, u16 qid, u16 sb_id) +int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u16 coalesce, struct qed_queue_cid *p_cid) { struct xstorm_eth_queue_zone eth_qzone; u8 timeset, timer_res; - u16 fw_qid = 0; u32 address; int rc; @@ -3702,22 +3797,16 @@ int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, } timeset = (u8)(coalesce >> timer_res); - rc = qed_fw_l2_queue(p_hwfn, qid, &fw_qid); - if (rc) - return rc; - - rc = qed_int_set_timer_res(p_hwfn, p_ptt, timer_res, sb_id, true); + rc = qed_int_set_timer_res(p_hwfn, p_ptt, timer_res, + p_cid->sb_igu_id, true); if (rc) goto out; - address = BAR0_MAP_REG_XSDM_RAM + XSTORM_ETH_QUEUE_ZONE_OFFSET(fw_qid); + address = BAR0_MAP_REG_XSDM_RAM + + XSTORM_ETH_QUEUE_ZONE_OFFSET(p_cid->abs.queue_id); rc = qed_set_coalesce(p_hwfn, p_ptt, address, ð_qzone, sizeof(struct xstorm_eth_queue_zone), timeset); - if (rc) - goto out; - - p_hwfn->cdev->tx_coalesce_usecs = coalesce; out: return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index 1f1df1bf127c..defdda1ffaa2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -443,38 +443,35 @@ int qed_final_cleanup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 id, bool is_vf); /** - * @brief qed_set_rxq_coalesce - Configure coalesce parameters for an Rx queue - * The fact that we can configure coalescing to up to 511, but on varying - * accuracy [the bigger the value the less accurate] up to a mistake of 3usec - * for the highest values. + * @brief qed_get_queue_coalesce - Retrieve coalesce value for a given queue. * * @param p_hwfn - * @param p_ptt - * @param coalesce - Coalesce value in micro seconds. - * @param qid - Queue index. - * @param qid - SB Id + * @param p_coal - store coalesce value read from the hardware. + * @param p_handle * * @return int - */ -int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, - u16 coalesce, u16 qid, u16 sb_id); + **/ +int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *coal, void *handle); /** - * @brief qed_set_txq_coalesce - Configure coalesce parameters for a Tx queue - * While the API allows setting coalescing per-qid, all tx queues sharing a - * SB should be in same range [i.e., either 0-0x7f, 0x80-0xff or 0x100-0x1ff] - * otherwise configuration would break. + * @brief qed_set_queue_coalesce - Configure coalesce parameters for Rx and + * Tx queue. The fact that we can configure coalescing to up to 511, but on + * varying accuracy [the bigger the value the less accurate] up to a mistake + * of 3usec for the highest values. + * While the API allows setting coalescing per-qid, all queues sharing a SB + * should be in same range [i.e., either 0-0x7f, 0x80-0xff or 0x100-0x1ff] + * otherwise configuration would break. * - * @param p_hwfn - * @param p_ptt - * @param coalesce - Coalesce value in micro seconds. - * @param qid - Queue index. - * @param qid - SB Id + * + * @param rx_coal - Rx Coalesce value in micro seconds. + * @param tx_coal - TX Coalesce value in micro seconds. + * @param p_handle * * @return int - */ -int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, - u16 coalesce, u16 qid, u16 sb_id); + **/ +int +qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle); + const char *qed_hw_get_resc_name(enum qed_resources res_id); #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 31fb0bffa098..3427fe7049b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -10825,6 +10825,17 @@ struct eth_phy_cfg { #define ETH_LOOPBACK_EXT (3) #define ETH_LOOPBACK_MAC (4) + u32 eee_cfg; +#define EEE_CFG_EEE_ENABLED BIT(0) +#define EEE_CFG_TX_LPI BIT(1) +#define EEE_CFG_ADV_SPEED_1G BIT(2) +#define EEE_CFG_ADV_SPEED_10G BIT(3) +#define EEE_TX_TIMER_USEC_MASK (0xfffffff0) +#define EEE_TX_TIMER_USEC_OFFSET 4 +#define EEE_TX_TIMER_USEC_BALANCED_TIME (0xa00) +#define EEE_TX_TIMER_USEC_AGGRESSIVE_TIME (0x100) +#define EEE_TX_TIMER_USEC_LATENCY_TIME (0x6000) + u32 feature_config_flags; #define ETH_EEE_MODE_ADV_LPI (1 << 0) }; @@ -11242,6 +11253,25 @@ struct public_port { u32 wol_pkt_len; u32 wol_pkt_details; struct dcb_dscp_map dcb_dscp_map; + + u32 eee_status; +#define EEE_ACTIVE_BIT BIT(0) +#define EEE_LD_ADV_STATUS_MASK 0x000000f0 +#define EEE_LD_ADV_STATUS_OFFSET 4 +#define EEE_1G_ADV BIT(1) +#define EEE_10G_ADV BIT(2) +#define EEE_LP_ADV_STATUS_MASK 0x00000f00 +#define EEE_LP_ADV_STATUS_OFFSET 8 +#define EEE_SUPPORTED_SPEED_MASK 0x0000f000 +#define EEE_SUPPORTED_SPEED_OFFSET 12 +#define EEE_1G_SUPPORTED BIT(1) +#define EEE_10G_SUPPORTED BIT(2) + + u32 eee_remote; +#define EEE_REMOTE_TW_TX_MASK 0x0000ffff +#define EEE_REMOTE_TW_TX_OFFSET 0 +#define EEE_REMOTE_TW_RX_MASK 0xffff0000 +#define EEE_REMOTE_TW_RX_OFFSET 16 }; struct public_func { @@ -11570,6 +11600,9 @@ struct public_drv_mb { #define DRV_MSG_CODE_GET_PF_RDMA_PROTOCOL 0x002b0000 #define DRV_MSG_CODE_OS_WOL 0x002e0000 +#define DRV_MSG_CODE_FEATURE_SUPPORT 0x00300000 +#define DRV_MSG_CODE_GET_MFW_FEATURE_SUPPORT 0x00310000 + #define DRV_MSG_SEQ_NUMBER_MASK 0x0000ffff u32 drv_mb_param; @@ -11653,6 +11686,10 @@ struct public_drv_mb { #define DRV_MB_PARAM_BIST_TEST_IMAGE_INDEX_SHIFT 8 #define DRV_MB_PARAM_BIST_TEST_IMAGE_INDEX_MASK 0x0000FF00 +#define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_MASK 0x0000FFFF +#define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_OFFSET 0 +#define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE 0x00000002 + u32 fw_mb_header; #define FW_MSG_CODE_MASK 0xffff0000 #define FW_MSG_CODE_UNSUPPORTED 0x00000000 @@ -11696,6 +11733,9 @@ struct public_drv_mb { #define FW_MB_PARAM_GET_PF_RDMA_IWARP 0x2 #define FW_MB_PARAM_GET_PF_RDMA_BOTH 0x3 +/* get MFW feature support response */ +#define FW_MB_PARAM_FEATURE_SUPPORT_EEE 0x00000002 + #define FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR (1 << 0) u32 drv_pulse_mb; @@ -11891,7 +11931,16 @@ struct nvm_cfg1_port { #define NVM_CFG1_PORT_DRV_FLOW_CONTROL_TX 0x4 u32 phy_cfg; u32 mgmt_traffic; + u32 ext_phy; + /* EEE power saving mode */ +#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_MASK 0x00FF0000 +#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_OFFSET 16 +#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_DISABLED 0x0 +#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_BALANCED 0x1 +#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_AGGRESSIVE 0x2 +#define NVM_CFG1_PORT_EEE_POWER_SAVING_MODE_LOW_LATENCY 0x3 + u32 mba_cfg1; u32 mba_cfg2; u32 vf_cfg; diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 0ba5ec8a9814..085338990f49 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2047,6 +2047,106 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, return qed_spq_post(p_hwfn, p_ent, NULL); } +int qed_get_rxq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_queue_cid *p_cid, u16 *p_rx_coal) +{ + u32 coalesce, address, is_valid; + struct cau_sb_entry sb_entry; + u8 timer_res; + int rc; + + rc = qed_dmae_grc2host(p_hwfn, p_ptt, CAU_REG_SB_VAR_MEMORY + + p_cid->sb_igu_id * sizeof(u64), + (u64)(uintptr_t)&sb_entry, 2, 0); + if (rc) { + DP_ERR(p_hwfn, "dmae_grc2host failed %d\n", rc); + return rc; + } + + timer_res = GET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES0); + + address = BAR0_MAP_REG_USDM_RAM + + USTORM_ETH_QUEUE_ZONE_OFFSET(p_cid->abs.queue_id); + coalesce = qed_rd(p_hwfn, p_ptt, address); + + is_valid = GET_FIELD(coalesce, COALESCING_TIMESET_VALID); + if (!is_valid) + return -EINVAL; + + coalesce = GET_FIELD(coalesce, COALESCING_TIMESET_TIMESET); + *p_rx_coal = (u16)(coalesce << timer_res); + + return 0; +} + +int qed_get_txq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_queue_cid *p_cid, u16 *p_tx_coal) +{ + u32 coalesce, address, is_valid; + struct cau_sb_entry sb_entry; + u8 timer_res; + int rc; + + rc = qed_dmae_grc2host(p_hwfn, p_ptt, CAU_REG_SB_VAR_MEMORY + + p_cid->sb_igu_id * sizeof(u64), + (u64)(uintptr_t)&sb_entry, 2, 0); + if (rc) { + DP_ERR(p_hwfn, "dmae_grc2host failed %d\n", rc); + return rc; + } + + timer_res = GET_FIELD(sb_entry.params, CAU_SB_ENTRY_TIMER_RES1); + + address = BAR0_MAP_REG_XSDM_RAM + + XSTORM_ETH_QUEUE_ZONE_OFFSET(p_cid->abs.queue_id); + coalesce = qed_rd(p_hwfn, p_ptt, address); + + is_valid = GET_FIELD(coalesce, COALESCING_TIMESET_VALID); + if (!is_valid) + return -EINVAL; + + coalesce = GET_FIELD(coalesce, COALESCING_TIMESET_TIMESET); + *p_tx_coal = (u16)(coalesce << timer_res); + + return 0; +} + +int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *p_coal, void *handle) +{ + struct qed_queue_cid *p_cid = handle; + struct qed_ptt *p_ptt; + int rc = 0; + + if (IS_VF(p_hwfn->cdev)) { + rc = qed_vf_pf_get_coalesce(p_hwfn, p_coal, p_cid); + if (rc) + DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n"); + + return rc; + } + + p_ptt = qed_ptt_acquire(p_hwfn); + if (!p_ptt) + return -EAGAIN; + + if (p_cid->b_is_rx) { + rc = qed_get_rxq_coalesce(p_hwfn, p_ptt, p_cid, p_coal); + if (rc) + goto out; + } else { + rc = qed_get_txq_coalesce(p_hwfn, p_ptt, p_cid, p_coal); + if (rc) + goto out; + } + +out: + qed_ptt_release(p_hwfn, p_ptt); + + return rc; +} + static int qed_fill_eth_dev_info(struct qed_dev *cdev, struct qed_dev_eth_info *info) { @@ -2696,6 +2796,20 @@ static int qed_ntuple_arfs_filter_config(struct qed_dev *cdev, void *cookie, return rc; } +static int qed_get_coalesce(struct qed_dev *cdev, u16 *coal, void *handle) +{ + struct qed_queue_cid *p_cid = handle; + struct qed_hwfn *p_hwfn; + int rc; + + p_hwfn = p_cid->p_owner; + rc = qed_get_queue_coalesce(p_hwfn, coal, handle); + if (rc) + DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n"); + + return rc; +} + static int qed_fp_cqe_completion(struct qed_dev *dev, u8 rss_id, struct eth_slow_path_rx_cqe *cqe) { @@ -2739,6 +2853,7 @@ static const struct qed_eth_ops qed_eth_ops_pass = { .tunn_config = &qed_tunn_configure, .ntuple_filter_config = &qed_ntuple_arfs_filter_config, .configure_arfs_searcher = &qed_configure_arfs_searcher, + .get_coalesce = &qed_get_coalesce, }; const struct qed_eth_ops *qed_get_eth_ops(void) diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index f8f09aadced7..cc1f248551c9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -400,4 +400,20 @@ qed_eth_txq_start_ramrod(struct qed_hwfn *p_hwfn, u8 qed_mcast_bin_from_mac(u8 *mac); -#endif /* _QED_L2_H */ +int qed_set_rxq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u16 coalesce, struct qed_queue_cid *p_cid); + +int qed_set_txq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u16 coalesce, struct qed_queue_cid *p_cid); + +int qed_get_rxq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_queue_cid *p_cid, u16 *p_hw_coal); + +int qed_get_txq_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_queue_cid *p_cid, u16 *p_hw_coal); + +#endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index b11399606990..27832885a87f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -954,9 +954,7 @@ static int qed_slowpath_start(struct qed_dev *cdev, struct qed_tunnel_info tunn_info; const u8 *data = NULL; struct qed_hwfn *hwfn; -#ifdef CONFIG_RFS_ACCEL struct qed_ptt *p_ptt; -#endif int rc = -EINVAL; if (qed_iov_wq_start(cdev)) @@ -972,7 +970,6 @@ static int qed_slowpath_start(struct qed_dev *cdev, goto err; } -#ifdef CONFIG_RFS_ACCEL if (cdev->num_hwfns == 1) { p_ptt = qed_ptt_acquire(QED_LEADING_HWFN(cdev)); if (p_ptt) { @@ -983,7 +980,6 @@ static int qed_slowpath_start(struct qed_dev *cdev, goto err; } } -#endif } cdev->rx_coalesce_usecs = QED_DEFAULT_RX_USECS; @@ -1091,12 +1087,10 @@ err: if (IS_PF(cdev)) release_firmware(cdev->firmware); -#ifdef CONFIG_RFS_ACCEL if (IS_PF(cdev) && (cdev->num_hwfns == 1) && QED_LEADING_HWFN(cdev)->p_arfs_ptt) qed_ptt_release(QED_LEADING_HWFN(cdev), QED_LEADING_HWFN(cdev)->p_arfs_ptt); -#endif qed_iov_wq_stop(cdev, false); @@ -1111,11 +1105,9 @@ static int qed_slowpath_stop(struct qed_dev *cdev) qed_ll2_dealloc_if(cdev); if (IS_PF(cdev)) { -#ifdef CONFIG_RFS_ACCEL if (cdev->num_hwfns == 1) qed_ptt_release(QED_LEADING_HWFN(cdev), QED_LEADING_HWFN(cdev)->p_arfs_ptt); -#endif qed_free_stream_mem(cdev); if (IS_QED_ETH_IF(cdev)) qed_sriov_disable(cdev, true); @@ -1305,6 +1297,10 @@ static int qed_set_link(struct qed_dev *cdev, struct qed_link_params *params) } } + if (params->override_flags & QED_LINK_OVERRIDE_EEE_CONFIG) + memcpy(&link_params->eee, ¶ms->eee, + sizeof(link_params->eee)); + rc = qed_mcp_set_link(hwfn, ptt, params->link_up); qed_ptt_release(hwfn, ptt); @@ -1491,6 +1487,21 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if (link.partner_adv_pause == QED_LINK_PARTNER_ASYMMETRIC_PAUSE || link.partner_adv_pause == QED_LINK_PARTNER_BOTH_PAUSE) if_link->lp_caps |= QED_LM_Asym_Pause_BIT; + + if (link_caps.default_eee == QED_MCP_EEE_UNSUPPORTED) { + if_link->eee_supported = false; + } else { + if_link->eee_supported = true; + if_link->eee_active = link.eee_active; + if_link->sup_caps = link_caps.eee_speed_caps; + /* MFW clears adv_caps on eee disable; use configured value */ + if_link->eee.adv_caps = link.eee_adv_caps ? link.eee_adv_caps : + params.eee.adv_caps; + if_link->eee.lp_adv_caps = link.eee_lp_adv_caps; + if_link->eee.enable = params.eee.enable; + if_link->eee.tx_lpi_enable = params.eee.tx_lpi_enable; + if_link->eee.tx_lpi_timer = params.eee.tx_lpi_timer; + } } static void qed_get_current_link(struct qed_dev *cdev, @@ -1557,36 +1568,10 @@ static int qed_nvm_get_image(struct qed_dev *cdev, enum qed_nvm_images type, return rc; } -static void qed_get_coalesce(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal) -{ - *rx_coal = cdev->rx_coalesce_usecs; - *tx_coal = cdev->tx_coalesce_usecs; -} - static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, - u16 qid, u16 sb_id) + void *handle) { - struct qed_hwfn *hwfn; - struct qed_ptt *ptt; - int hwfn_index; - int status = 0; - - hwfn_index = qid % cdev->num_hwfns; - hwfn = &cdev->hwfns[hwfn_index]; - ptt = qed_ptt_acquire(hwfn); - if (!ptt) - return -EAGAIN; - - status = qed_set_rxq_coalesce(hwfn, ptt, rx_coal, - qid / cdev->num_hwfns, sb_id); - if (status) - goto out; - status = qed_set_txq_coalesce(hwfn, ptt, tx_coal, - qid / cdev->num_hwfns, sb_id); -out: - qed_ptt_release(hwfn, ptt); - - return status; + return qed_set_queue_coalesce(rx_coal, tx_coal, handle); } static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode) @@ -1735,7 +1720,6 @@ const struct qed_common_ops qed_common_ops_pass = { .chain_alloc = &qed_chain_alloc, .chain_free = &qed_chain_free, .nvm_get_image = &qed_nvm_get_image, - .get_coalesce = &qed_get_coalesce, .set_coalesce = &qed_set_coalesce, .set_led = &qed_set_led, .update_drv_state = &qed_update_drv_state, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 3eb241657368..376485d99357 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1097,6 +1097,31 @@ static void qed_mcp_handle_transceiver_change(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "Transceiver is unplugged.\n"); } +static void qed_mcp_read_eee_config(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_mcp_link_state *p_link) +{ + u32 eee_status, val; + + p_link->eee_adv_caps = 0; + p_link->eee_lp_adv_caps = 0; + eee_status = qed_rd(p_hwfn, + p_ptt, + p_hwfn->mcp_info->port_addr + + offsetof(struct public_port, eee_status)); + p_link->eee_active = !!(eee_status & EEE_ACTIVE_BIT); + val = (eee_status & EEE_LD_ADV_STATUS_MASK) >> EEE_LD_ADV_STATUS_OFFSET; + if (val & EEE_1G_ADV) + p_link->eee_adv_caps |= QED_EEE_1G_ADV; + if (val & EEE_10G_ADV) + p_link->eee_adv_caps |= QED_EEE_10G_ADV; + val = (eee_status & EEE_LP_ADV_STATUS_MASK) >> EEE_LP_ADV_STATUS_OFFSET; + if (val & EEE_1G_ADV) + p_link->eee_lp_adv_caps |= QED_EEE_1G_ADV; + if (val & EEE_10G_ADV) + p_link->eee_lp_adv_caps |= QED_EEE_10G_ADV; +} + static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_reset) { @@ -1228,6 +1253,9 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, p_link->sfp_tx_fault = !!(status & LINK_STATUS_SFP_TX_FAULT); + if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) + qed_mcp_read_eee_config(p_hwfn, p_ptt, p_link); + qed_link_update(p_hwfn); out: spin_unlock_bh(&p_hwfn->mcp_info->link_lock); @@ -1251,6 +1279,19 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up) phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0; phy_cfg.adv_speed = params->speed.advertised_speeds; phy_cfg.loopback_mode = params->loopback_mode; + if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) { + if (params->eee.enable) + phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; + if (params->eee.tx_lpi_enable) + phy_cfg.eee_cfg |= EEE_CFG_TX_LPI; + if (params->eee.adv_caps & QED_EEE_1G_ADV) + phy_cfg.eee_cfg |= EEE_CFG_ADV_SPEED_1G; + if (params->eee.adv_caps & QED_EEE_10G_ADV) + phy_cfg.eee_cfg |= EEE_CFG_ADV_SPEED_10G; + phy_cfg.eee_cfg |= (params->eee.tx_lpi_timer << + EEE_TX_TIMER_USEC_OFFSET) & + EEE_TX_TIMER_USEC_MASK; + } p_hwfn->b_drv_link_init = b_up; @@ -2822,3 +2863,28 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, p_unlock->resource = resource; } } + +int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + u32 mcp_resp; + int rc; + + rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_GET_MFW_FEATURE_SUPPORT, + 0, &mcp_resp, &p_hwfn->mcp_info->capabilities); + if (!rc) + DP_VERBOSE(p_hwfn, (QED_MSG_SP | NETIF_MSG_PROBE), + "MFW supported features: %08x\n", + p_hwfn->mcp_info->capabilities); + + return rc; +} + +int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + u32 mcp_resp, mcp_param, features; + + features = DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE; + + return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_FEATURE_SUPPORT, + features, &mcp_resp, &mcp_param); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index af03b3651411..c7ec2395d1ce 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -53,15 +53,25 @@ struct qed_mcp_link_pause_params { bool forced_tx; }; +enum qed_mcp_eee_mode { + QED_MCP_EEE_DISABLED, + QED_MCP_EEE_ENABLED, + QED_MCP_EEE_UNSUPPORTED +}; + struct qed_mcp_link_params { - struct qed_mcp_link_speed_params speed; - struct qed_mcp_link_pause_params pause; - u32 loopback_mode; + struct qed_mcp_link_speed_params speed; + struct qed_mcp_link_pause_params pause; + u32 loopback_mode; + struct qed_link_eee_params eee; }; struct qed_mcp_link_capabilities { u32 speed_capabilities; bool default_speed_autoneg; + enum qed_mcp_eee_mode default_eee; + u32 eee_lpi_timer; + u8 eee_speed_caps; }; struct qed_mcp_link_state { @@ -102,6 +112,9 @@ struct qed_mcp_link_state { u8 partner_adv_pause; bool sfp_tx_fault; + bool eee_active; + u8 eee_adv_caps; + u8 eee_lp_adv_caps; }; struct qed_mcp_function_info { @@ -546,6 +559,9 @@ struct qed_mcp_info { u8 *mfw_mb_shadow; u16 mfw_mb_length; u32 mcp_hist; + + /* Capabilties negotiated with the MFW */ + u32 capabilities; }; struct qed_mcp_mb_params { @@ -925,5 +941,20 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, struct qed_resc_unlock_params *p_unlock, enum qed_resc_lock resource, bool b_is_permanent); +/** + * @brief Learn of supported MFW features; To be done during early init + * + * @param p_hwfn + * @param p_ptt + */ +int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); +/** + * @brief Inform MFW of set of features supported by driver. Should be done + * inside the content of the LOAD_REQ. + * + * @param p_hwfn + * @param p_ptt + */ +int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 2cfd3bd9a031..3f40b1de7957 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -3400,6 +3400,157 @@ static void qed_iov_vf_mbx_release(struct qed_hwfn *p_hwfn, length, status); } +static void qed_iov_vf_pf_get_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_vf_info *p_vf) +{ + struct qed_iov_vf_mbx *mbx = &p_vf->vf_mbx; + struct pfvf_read_coal_resp_tlv *p_resp; + struct vfpf_read_coal_req_tlv *req; + u8 status = PFVF_STATUS_FAILURE; + struct qed_vf_queue *p_queue; + struct qed_queue_cid *p_cid; + u16 coal = 0, qid, i; + bool b_is_rx; + int rc = 0; + + mbx->offset = (u8 *)mbx->reply_virt; + req = &mbx->req_virt->read_coal_req; + + qid = req->qid; + b_is_rx = req->is_rx ? true : false; + + if (b_is_rx) { + if (!qed_iov_validate_rxq(p_hwfn, p_vf, qid, + QED_IOV_VALIDATE_Q_ENABLE)) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF[%d]: Invalid Rx queue_id = %d\n", + p_vf->abs_vf_id, qid); + goto send_resp; + } + + p_cid = qed_iov_get_vf_rx_queue_cid(&p_vf->vf_queues[qid]); + rc = qed_get_rxq_coalesce(p_hwfn, p_ptt, p_cid, &coal); + if (rc) + goto send_resp; + } else { + if (!qed_iov_validate_txq(p_hwfn, p_vf, qid, + QED_IOV_VALIDATE_Q_ENABLE)) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF[%d]: Invalid Tx queue_id = %d\n", + p_vf->abs_vf_id, qid); + goto send_resp; + } + for (i = 0; i < MAX_QUEUES_PER_QZONE; i++) { + p_queue = &p_vf->vf_queues[qid]; + if ((!p_queue->cids[i].p_cid) || + (!p_queue->cids[i].b_is_tx)) + continue; + + p_cid = p_queue->cids[i].p_cid; + + rc = qed_get_txq_coalesce(p_hwfn, p_ptt, p_cid, &coal); + if (rc) + goto send_resp; + break; + } + } + + status = PFVF_STATUS_SUCCESS; + +send_resp: + p_resp = qed_add_tlv(p_hwfn, &mbx->offset, CHANNEL_TLV_COALESCE_READ, + sizeof(*p_resp)); + p_resp->coal = coal; + + qed_add_tlv(p_hwfn, &mbx->offset, CHANNEL_TLV_LIST_END, + sizeof(struct channel_list_end_tlv)); + + qed_iov_send_response(p_hwfn, p_ptt, p_vf, sizeof(*p_resp), status); +} + +static void qed_iov_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_vf_info *vf) +{ + struct qed_iov_vf_mbx *mbx = &vf->vf_mbx; + struct vfpf_update_coalesce *req; + u8 status = PFVF_STATUS_FAILURE; + struct qed_queue_cid *p_cid; + u16 rx_coal, tx_coal; + int rc = 0, i; + u16 qid; + + req = &mbx->req_virt->update_coalesce; + + rx_coal = req->rx_coal; + tx_coal = req->tx_coal; + qid = req->qid; + + if (!qed_iov_validate_rxq(p_hwfn, vf, qid, + QED_IOV_VALIDATE_Q_ENABLE) && rx_coal) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF[%d]: Invalid Rx queue_id = %d\n", + vf->abs_vf_id, qid); + goto out; + } + + if (!qed_iov_validate_txq(p_hwfn, vf, qid, + QED_IOV_VALIDATE_Q_ENABLE) && tx_coal) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF[%d]: Invalid Tx queue_id = %d\n", + vf->abs_vf_id, qid); + goto out; + } + + DP_VERBOSE(p_hwfn, + QED_MSG_IOV, + "VF[%d]: Setting coalesce for VF rx_coal = %d, tx_coal = %d at queue = %d\n", + vf->abs_vf_id, rx_coal, tx_coal, qid); + + if (rx_coal) { + p_cid = qed_iov_get_vf_rx_queue_cid(&vf->vf_queues[qid]); + + rc = qed_set_rxq_coalesce(p_hwfn, p_ptt, rx_coal, p_cid); + if (rc) { + DP_VERBOSE(p_hwfn, + QED_MSG_IOV, + "VF[%d]: Unable to set rx queue = %d coalesce\n", + vf->abs_vf_id, vf->vf_queues[qid].fw_rx_qid); + goto out; + } + vf->rx_coal = rx_coal; + } + + if (tx_coal) { + struct qed_vf_queue *p_queue = &vf->vf_queues[qid]; + + for (i = 0; i < MAX_QUEUES_PER_QZONE; i++) { + if (!p_queue->cids[i].p_cid) + continue; + + if (!p_queue->cids[i].b_is_tx) + continue; + + rc = qed_set_txq_coalesce(p_hwfn, p_ptt, tx_coal, + p_queue->cids[i].p_cid); + + if (rc) { + DP_VERBOSE(p_hwfn, + QED_MSG_IOV, + "VF[%d]: Unable to set tx queue coalesce\n", + vf->abs_vf_id); + goto out; + } + } + vf->tx_coal = tx_coal; + } + + status = PFVF_STATUS_SUCCESS; +out: + qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_COALESCE_UPDATE, + sizeof(struct pfvf_def_resp_tlv), status); +} static int qed_iov_vf_flr_poll_dorq(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf, struct qed_ptt *p_ptt) @@ -3725,6 +3876,12 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn, case CHANNEL_TLV_UPDATE_TUNN_PARAM: qed_iov_vf_mbx_update_tunn_param(p_hwfn, p_ptt, p_vf); break; + case CHANNEL_TLV_COALESCE_UPDATE: + qed_iov_vf_pf_set_coalesce(p_hwfn, p_ptt, p_vf); + break; + case CHANNEL_TLV_COALESCE_READ: + qed_iov_vf_pf_get_coalesce(p_hwfn, p_ptt, p_vf); + break; } } else if (qed_iov_tlv_supported(mbx->first_tlv.tl.type)) { DP_VERBOSE(p_hwfn, QED_MSG_IOV, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h index c2e44bce398c..3955929ba892 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h @@ -217,6 +217,9 @@ struct qed_vf_info { u8 num_rxqs; u8 num_txqs; + u16 rx_coal; + u16 tx_coal; + u8 num_sbs; u8 num_mac_filters; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 1926d1ed439f..91b5e9f02a62 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1343,6 +1343,81 @@ exit: return rc; } +int qed_vf_pf_get_coalesce(struct qed_hwfn *p_hwfn, + u16 *p_coal, struct qed_queue_cid *p_cid) +{ + struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; + struct pfvf_read_coal_resp_tlv *resp; + struct vfpf_read_coal_req_tlv *req; + int rc; + + /* clear mailbox and prep header tlv */ + req = qed_vf_pf_prep(p_hwfn, CHANNEL_TLV_COALESCE_READ, sizeof(*req)); + req->qid = p_cid->rel.queue_id; + req->is_rx = p_cid->b_is_rx ? 1 : 0; + + qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_LIST_END, + sizeof(struct channel_list_end_tlv)); + resp = &p_iov->pf2vf_reply->read_coal_resp; + + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + if (rc) + goto exit; + + if (resp->hdr.status != PFVF_STATUS_SUCCESS) + goto exit; + + *p_coal = resp->coal; +exit: + qed_vf_pf_req_end(p_hwfn, rc); + + return rc; +} + +int +qed_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn, + u16 rx_coal, u16 tx_coal, struct qed_queue_cid *p_cid) +{ + struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; + struct vfpf_update_coalesce *req; + struct pfvf_def_resp_tlv *resp; + int rc; + + /* clear mailbox and prep header tlv */ + req = qed_vf_pf_prep(p_hwfn, CHANNEL_TLV_COALESCE_UPDATE, sizeof(*req)); + + req->rx_coal = rx_coal; + req->tx_coal = tx_coal; + req->qid = p_cid->rel.queue_id; + + DP_VERBOSE(p_hwfn, + QED_MSG_IOV, + "Setting coalesce rx_coal = %d, tx_coal = %d at queue = %d\n", + rx_coal, tx_coal, req->qid); + + /* add list termination tlv */ + qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_LIST_END, + sizeof(struct channel_list_end_tlv)); + + resp = &p_iov->pf2vf_reply->default_resp; + rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + if (rc) + goto exit; + + if (resp->hdr.status != PFVF_STATUS_SUCCESS) + goto exit; + + if (rx_coal) + p_hwfn->cdev->rx_coalesce_usecs = rx_coal; + + if (tx_coal) + p_hwfn->cdev->tx_coalesce_usecs = tx_coal; + +exit: + qed_vf_pf_req_end(p_hwfn, rc); + return rc; +} + u16 qed_vf_get_igu_sb_id(struct qed_hwfn *p_hwfn, u16 sb_id) { struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 34d9b882a780..97d44dfb38ca 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -497,6 +497,27 @@ struct tlv_buffer_size { u8 tlv_buffer[TLV_BUFFER_SIZE]; }; +struct vfpf_update_coalesce { + struct vfpf_first_tlv first_tlv; + u16 rx_coal; + u16 tx_coal; + u16 qid; + u8 padding[2]; +}; + +struct vfpf_read_coal_req_tlv { + struct vfpf_first_tlv first_tlv; + u16 qid; + u8 is_rx; + u8 padding[5]; +}; + +struct pfvf_read_coal_resp_tlv { + struct pfvf_tlv hdr; + u16 coal; + u8 padding[6]; +}; + union vfpf_tlvs { struct vfpf_first_tlv first_tlv; struct vfpf_acquire_tlv acquire; @@ -509,7 +530,8 @@ union vfpf_tlvs { struct vfpf_vport_update_tlv vport_update; struct vfpf_ucast_filter_tlv ucast_filter; struct vfpf_update_tunn_param_tlv tunn_param_update; - struct channel_list_end_tlv list_end; + struct vfpf_update_coalesce update_coalesce; + struct vfpf_read_coal_req_tlv read_coal_req; struct tlv_buffer_size tlv_buf_size; }; @@ -519,6 +541,7 @@ union pfvf_tlvs { struct tlv_buffer_size tlv_buf_size; struct pfvf_start_queue_resp_tlv queue_start; struct pfvf_update_tunn_param_tlv tunn_param_resp; + struct pfvf_read_coal_resp_tlv read_coal_resp; }; enum qed_bulletin_bit { @@ -624,8 +647,9 @@ enum { CHANNEL_TLV_VPORT_UPDATE_ACCEPT_ANY_VLAN, CHANNEL_TLV_VPORT_UPDATE_SGE_TPA, CHANNEL_TLV_UPDATE_TUNN_PARAM, - CHANNEL_TLV_RESERVED, + CHANNEL_TLV_COALESCE_UPDATE, CHANNEL_TLV_QID, + CHANNEL_TLV_COALESCE_READ, CHANNEL_TLV_MAX, /* Required for iterating over vport-update tlvs. @@ -677,6 +701,31 @@ struct qed_vf_iov { bool b_doorbell_bar; }; +/** + * @brief VF - Set Rx/Tx coalesce per VF's relative queue. + * Coalesce value '0' will omit the configuration. + * + * @param p_hwfn + * @param rx_coal - coalesce value in micro second for rx queue + * @param tx_coal - coalesce value in micro second for tx queue + * @param p_cid - queue cid + * + **/ +int qed_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn, + u16 rx_coal, + u16 tx_coal, struct qed_queue_cid *p_cid); + +/** + * @brief VF - Get coalesce per VF's relative queue. + * + * @param p_hwfn + * @param p_coal - coalesce value in micro second for VF queues. + * @param p_cid - queue cid + * + **/ +int qed_vf_pf_get_coalesce(struct qed_hwfn *p_hwfn, + u16 *p_coal, struct qed_queue_cid *p_cid); + #ifdef CONFIG_QED_SRIOV /** * @brief Read the VF bulletin and act on it if needed diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 4dfb238221f9..adb700512baa 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -160,6 +160,8 @@ struct qede_rdma_dev { struct qede_ptp; +#define QEDE_RFS_MAX_FLTR 256 + struct qede_dev { struct qed_dev *cdev; struct net_device *ndev; @@ -241,9 +243,7 @@ struct qede_dev { u16 vxlan_dst_port; u16 geneve_dst_port; -#ifdef CONFIG_RFS_ACCEL struct qede_arfs *arfs; -#endif bool wol_enabled; struct qede_rdma_dev rdma_info; @@ -447,16 +447,21 @@ struct qede_fastpath { #ifdef CONFIG_RFS_ACCEL int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, u16 rxq_index, u32 flow_id); +#define QEDE_SP_ARFS_CONFIG 4 +#define QEDE_SP_TASK_POLL_DELAY (5 * HZ) +#endif + void qede_process_arfs_filters(struct qede_dev *edev, bool free_fltr); void qede_poll_for_freeing_arfs_filters(struct qede_dev *edev); void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc); void qede_free_arfs(struct qede_dev *edev); int qede_alloc_arfs(struct qede_dev *edev); - -#define QEDE_SP_ARFS_CONFIG 4 -#define QEDE_SP_TASK_POLL_DELAY (5 * HZ) -#define QEDE_RFS_MAX_FLTR 256 -#endif +int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info); +int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info); +int qede_get_cls_rule_entry(struct qede_dev *edev, struct ethtool_rxnfc *cmd); +int qede_get_cls_rule_all(struct qede_dev *edev, struct ethtool_rxnfc *info, + u32 *rule_locs); +int qede_get_arfs_filter_count(struct qede_dev *edev); struct qede_reload_args { void (*func)(struct qede_dev *edev, struct qede_reload_args *args); diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 6a03d3e66cff..dae741270022 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -702,24 +702,62 @@ static u32 qede_get_link(struct net_device *dev) static int qede_get_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) { + void *rx_handle = NULL, *tx_handle = NULL; struct qede_dev *edev = netdev_priv(dev); - u16 rxc, txc; + u16 rx_coal, tx_coal, i, rc = 0; + struct qede_fastpath *fp; + + rx_coal = QED_DEFAULT_RX_USECS; + tx_coal = QED_DEFAULT_TX_USECS; memset(coal, 0, sizeof(struct ethtool_coalesce)); - edev->ops->common->get_coalesce(edev->cdev, &rxc, &txc); - coal->rx_coalesce_usecs = rxc; - coal->tx_coalesce_usecs = txc; + __qede_lock(edev); + if (edev->state == QEDE_STATE_OPEN) { + for_each_queue(i) { + fp = &edev->fp_array[i]; - return 0; + if (fp->type & QEDE_FASTPATH_RX) { + rx_handle = fp->rxq->handle; + break; + } + } + + rc = edev->ops->get_coalesce(edev->cdev, &rx_coal, rx_handle); + if (rc) { + DP_INFO(edev, "Read Rx coalesce error\n"); + goto out; + } + + for_each_queue(i) { + fp = &edev->fp_array[i]; + if (fp->type & QEDE_FASTPATH_TX) { + tx_handle = fp->txq->handle; + break; + } + } + + rc = edev->ops->get_coalesce(edev->cdev, &tx_coal, tx_handle); + if (rc) + DP_INFO(edev, "Read Tx coalesce error\n"); + } + +out: + __qede_unlock(edev); + + coal->rx_coalesce_usecs = rx_coal; + coal->tx_coalesce_usecs = tx_coal; + + return rc; } static int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal) { struct qede_dev *edev = netdev_priv(dev); + struct qede_fastpath *fp; int i, rc = 0; - u16 rxc, txc, sb_id; + u16 rxc, txc; if (!netif_running(dev)) { DP_INFO(edev, "Interface is down\n"); @@ -730,21 +768,36 @@ static int qede_set_coalesce(struct net_device *dev, coal->tx_coalesce_usecs > QED_COALESCE_MAX) { DP_INFO(edev, "Can't support requested %s coalesce value [max supported value %d]\n", - coal->rx_coalesce_usecs > QED_COALESCE_MAX ? "rx" - : "tx", - QED_COALESCE_MAX); + coal->rx_coalesce_usecs > QED_COALESCE_MAX ? "rx" : + "tx", QED_COALESCE_MAX); return -EINVAL; } rxc = (u16)coal->rx_coalesce_usecs; txc = (u16)coal->tx_coalesce_usecs; for_each_queue(i) { - sb_id = edev->fp_array[i].sb_info->igu_sb_id; - rc = edev->ops->common->set_coalesce(edev->cdev, rxc, txc, - (u16)i, sb_id); - if (rc) { - DP_INFO(edev, "Set coalesce error, rc = %d\n", rc); - return rc; + fp = &edev->fp_array[i]; + + if (edev->fp_array[i].type & QEDE_FASTPATH_RX) { + rc = edev->ops->common->set_coalesce(edev->cdev, + rxc, 0, + fp->rxq->handle); + if (rc) { + DP_INFO(edev, + "Set RX coalesce error, rc = %d\n", rc); + return rc; + } + } + + if (edev->fp_array[i].type & QEDE_FASTPATH_TX) { + rc = edev->ops->common->set_coalesce(edev->cdev, + 0, txc, + fp->txq->handle); + if (rc) { + DP_INFO(edev, + "Set TX coalesce error, rc = %d\n", rc); + return rc; + } } } @@ -1045,20 +1098,34 @@ static int qede_get_rss_flags(struct qede_dev *edev, struct ethtool_rxnfc *info) } static int qede_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, - u32 *rules __always_unused) + u32 *rule_locs) { struct qede_dev *edev = netdev_priv(dev); + int rc = 0; switch (info->cmd) { case ETHTOOL_GRXRINGS: info->data = QEDE_RSS_COUNT(edev); - return 0; + break; case ETHTOOL_GRXFH: - return qede_get_rss_flags(edev, info); + rc = qede_get_rss_flags(edev, info); + break; + case ETHTOOL_GRXCLSRLCNT: + info->rule_cnt = qede_get_arfs_filter_count(edev); + info->data = QEDE_RFS_MAX_FLTR; + break; + case ETHTOOL_GRXCLSRULE: + rc = qede_get_cls_rule_entry(edev, info); + break; + case ETHTOOL_GRXCLSRLALL: + rc = qede_get_cls_rule_all(edev, info, rule_locs); + break; default: DP_ERR(edev, "Command parameters not supported\n"); - return -EOPNOTSUPP; + rc = -EOPNOTSUPP; } + + return rc; } static int qede_set_rss_flags(struct qede_dev *edev, struct ethtool_rxnfc *info) @@ -1168,14 +1235,24 @@ static int qede_set_rss_flags(struct qede_dev *edev, struct ethtool_rxnfc *info) static int qede_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) { struct qede_dev *edev = netdev_priv(dev); + int rc; switch (info->cmd) { case ETHTOOL_SRXFH: - return qede_set_rss_flags(edev, info); + rc = qede_set_rss_flags(edev, info); + break; + case ETHTOOL_SRXCLSRLINS: + rc = qede_add_cls_rule(edev, info); + break; + case ETHTOOL_SRXCLSRLDEL: + rc = qede_del_cls_rule(edev, info); + break; default: DP_INFO(edev, "Command parameters not supported\n"); - return -EOPNOTSUPP; + rc = -EOPNOTSUPP; } + + return rc; } static u32 qede_get_rxfh_indir_size(struct net_device *dev) @@ -1607,6 +1684,87 @@ static int qede_get_tunable(struct net_device *dev, return 0; } +static int qede_get_eee(struct net_device *dev, struct ethtool_eee *edata) +{ + struct qede_dev *edev = netdev_priv(dev); + struct qed_link_output current_link; + + memset(¤t_link, 0, sizeof(current_link)); + edev->ops->common->get_link(edev->cdev, ¤t_link); + + if (!current_link.eee_supported) { + DP_INFO(edev, "EEE is not supported\n"); + return -EOPNOTSUPP; + } + + if (current_link.eee.adv_caps & QED_EEE_1G_ADV) + edata->advertised = ADVERTISED_1000baseT_Full; + if (current_link.eee.adv_caps & QED_EEE_10G_ADV) + edata->advertised |= ADVERTISED_10000baseT_Full; + if (current_link.sup_caps & QED_EEE_1G_ADV) + edata->supported = ADVERTISED_1000baseT_Full; + if (current_link.sup_caps & QED_EEE_10G_ADV) + edata->supported |= ADVERTISED_10000baseT_Full; + if (current_link.eee.lp_adv_caps & QED_EEE_1G_ADV) + edata->lp_advertised = ADVERTISED_1000baseT_Full; + if (current_link.eee.lp_adv_caps & QED_EEE_10G_ADV) + edata->lp_advertised |= ADVERTISED_10000baseT_Full; + + edata->tx_lpi_timer = current_link.eee.tx_lpi_timer; + edata->eee_enabled = current_link.eee.enable; + edata->tx_lpi_enabled = current_link.eee.tx_lpi_enable; + edata->eee_active = current_link.eee_active; + + return 0; +} + +static int qede_set_eee(struct net_device *dev, struct ethtool_eee *edata) +{ + struct qede_dev *edev = netdev_priv(dev); + struct qed_link_output current_link; + struct qed_link_params params; + + if (!edev->ops->common->can_link_change(edev->cdev)) { + DP_INFO(edev, "Link settings are not allowed to be changed\n"); + return -EOPNOTSUPP; + } + + memset(¤t_link, 0, sizeof(current_link)); + edev->ops->common->get_link(edev->cdev, ¤t_link); + + if (!current_link.eee_supported) { + DP_INFO(edev, "EEE is not supported\n"); + return -EOPNOTSUPP; + } + + memset(¶ms, 0, sizeof(params)); + params.override_flags |= QED_LINK_OVERRIDE_EEE_CONFIG; + + if (!(edata->advertised & (ADVERTISED_1000baseT_Full | + ADVERTISED_10000baseT_Full)) || + ((edata->advertised & (ADVERTISED_1000baseT_Full | + ADVERTISED_10000baseT_Full)) != + edata->advertised)) { + DP_VERBOSE(edev, QED_MSG_DEBUG, + "Invalid advertised capabilities %d\n", + edata->advertised); + return -EINVAL; + } + + if (edata->advertised & ADVERTISED_1000baseT_Full) + params.eee.adv_caps = QED_EEE_1G_ADV; + if (edata->advertised & ADVERTISED_10000baseT_Full) + params.eee.adv_caps |= QED_EEE_10G_ADV; + params.eee.enable = edata->eee_enabled; + params.eee.tx_lpi_enable = edata->tx_lpi_enabled; + params.eee.tx_lpi_timer = edata->tx_lpi_timer; + + params.link_up = true; + edev->ops->common->set_link(edev->cdev, ¶ms); + + return 0; +} + static const struct ethtool_ops qede_ethtool_ops = { .get_link_ksettings = qede_get_link_ksettings, .set_link_ksettings = qede_set_link_ksettings, @@ -1640,6 +1798,9 @@ static const struct ethtool_ops qede_ethtool_ops = { .get_channels = qede_get_channels, .set_channels = qede_set_channels, .self_test = qede_self_test, + .get_eee = qede_get_eee, + .set_eee = qede_set_eee, + .get_tunable = qede_get_tunable, .set_tunable = qede_set_tunable, }; @@ -1650,6 +1811,8 @@ static const struct ethtool_ops qede_vf_ethtool_ops = { .get_msglevel = qede_get_msglevel, .set_msglevel = qede_set_msglevel, .get_link = qede_get_link, + .get_coalesce = qede_get_coalesce, + .set_coalesce = qede_set_coalesce, .get_ringparam = qede_get_ringparam, .set_ringparam = qede_set_ringparam, .get_strings = qede_get_strings, diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index f939db5bac5f..f79e36e4060a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -38,7 +38,6 @@ #include <linux/qed/qed_if.h> #include "qede.h" -#ifdef CONFIG_RFS_ACCEL struct qede_arfs_tuple { union { __be32 src_ipv4; @@ -76,10 +75,12 @@ struct qede_arfs_fltr_node { u16 next_rxq_id; bool filter_op; bool used; + u8 fw_rc; struct hlist_node node; }; struct qede_arfs { +#define QEDE_ARFS_BUCKET_HEAD(edev, idx) (&(edev)->arfs->arfs_hl_head[idx]) #define QEDE_ARFS_POLL_COUNT 100 #define QEDE_RFS_FLW_BITSHIFT (4) #define QEDE_RFS_FLW_MASK ((1 << QEDE_RFS_FLW_BITSHIFT) - 1) @@ -121,11 +122,56 @@ qede_free_arfs_filter(struct qede_dev *edev, struct qede_arfs_fltr_node *fltr) kfree(fltr); } +static int +qede_enqueue_fltr_and_config_searcher(struct qede_dev *edev, + struct qede_arfs_fltr_node *fltr, + u16 bucket_idx) +{ + fltr->mapping = dma_map_single(&edev->pdev->dev, fltr->data, + fltr->buf_len, DMA_TO_DEVICE); + if (dma_mapping_error(&edev->pdev->dev, fltr->mapping)) { + DP_NOTICE(edev, "Failed to map DMA memory for rule\n"); + qede_free_arfs_filter(edev, fltr); + return -ENOMEM; + } + + INIT_HLIST_NODE(&fltr->node); + hlist_add_head(&fltr->node, + QEDE_ARFS_BUCKET_HEAD(edev, bucket_idx)); + edev->arfs->filter_count++; + + if (edev->arfs->filter_count == 1 && !edev->arfs->enable) { + edev->ops->configure_arfs_searcher(edev->cdev, true); + edev->arfs->enable = true; + } + + return 0; +} + +static void +qede_dequeue_fltr_and_config_searcher(struct qede_dev *edev, + struct qede_arfs_fltr_node *fltr) +{ + hlist_del(&fltr->node); + dma_unmap_single(&edev->pdev->dev, fltr->mapping, + fltr->buf_len, DMA_TO_DEVICE); + + qede_free_arfs_filter(edev, fltr); + edev->arfs->filter_count--; + + if (!edev->arfs->filter_count && edev->arfs->enable) { + edev->arfs->enable = false; + edev->ops->configure_arfs_searcher(edev->cdev, false); + } +} + void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc) { struct qede_arfs_fltr_node *fltr = filter; struct qede_dev *edev = dev; + fltr->fw_rc = fw_rc; + if (fw_rc) { DP_NOTICE(edev, "Failed arfs filter configuration fw_rc=%d, flow_id=%d, sw_id=%d, src_port=%d, dst_port=%d, rxq=%d\n", @@ -185,18 +231,17 @@ void qede_process_arfs_filters(struct qede_dev *edev, bool free_fltr) if ((!test_bit(QEDE_FLTR_VALID, &fltr->state) && !fltr->used) || free_fltr) { - hlist_del(&fltr->node); - dma_unmap_single(&edev->pdev->dev, - fltr->mapping, - fltr->buf_len, DMA_TO_DEVICE); - qede_free_arfs_filter(edev, fltr); - edev->arfs->filter_count--; + qede_dequeue_fltr_and_config_searcher(edev, + fltr); } else { - if ((rps_may_expire_flow(edev->ndev, - fltr->rxq_id, - fltr->flow_id, - fltr->sw_id) || del) && - !free_fltr) + bool flow_exp = false; +#ifdef CONFIG_RFS_ACCEL + flow_exp = rps_may_expire_flow(edev->ndev, + fltr->rxq_id, + fltr->flow_id, + fltr->sw_id); +#endif + if ((flow_exp || del) && !free_fltr) qede_configure_arfs_fltr(edev, fltr, fltr->rxq_id, false); @@ -213,10 +258,12 @@ void qede_process_arfs_filters(struct qede_dev *edev, bool free_fltr) edev->arfs->enable = false; edev->ops->configure_arfs_searcher(edev->cdev, false); } +#ifdef CONFIG_RFS_ACCEL } else { set_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags); schedule_delayed_work(&edev->sp_task, QEDE_SP_TASK_POLL_DELAY); +#endif } spin_unlock_bh(&edev->arfs->arfs_list_lock); @@ -258,25 +305,26 @@ int qede_alloc_arfs(struct qede_dev *edev) spin_lock_init(&edev->arfs->arfs_list_lock); for (i = 0; i <= QEDE_RFS_FLW_MASK; i++) - INIT_HLIST_HEAD(&edev->arfs->arfs_hl_head[i]); + INIT_HLIST_HEAD(QEDE_ARFS_BUCKET_HEAD(edev, i)); - edev->ndev->rx_cpu_rmap = alloc_irq_cpu_rmap(QEDE_RSS_COUNT(edev)); - if (!edev->ndev->rx_cpu_rmap) { + edev->arfs->arfs_fltr_bmap = vzalloc(BITS_TO_LONGS(QEDE_RFS_MAX_FLTR) * + sizeof(long)); + if (!edev->arfs->arfs_fltr_bmap) { vfree(edev->arfs); edev->arfs = NULL; return -ENOMEM; } - edev->arfs->arfs_fltr_bmap = vzalloc(BITS_TO_LONGS(QEDE_RFS_MAX_FLTR) * - sizeof(long)); - if (!edev->arfs->arfs_fltr_bmap) { - free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap); - edev->ndev->rx_cpu_rmap = NULL; +#ifdef CONFIG_RFS_ACCEL + edev->ndev->rx_cpu_rmap = alloc_irq_cpu_rmap(QEDE_RSS_COUNT(edev)); + if (!edev->ndev->rx_cpu_rmap) { + vfree(edev->arfs->arfs_fltr_bmap); + edev->arfs->arfs_fltr_bmap = NULL; vfree(edev->arfs); edev->arfs = NULL; return -ENOMEM; } - +#endif return 0; } @@ -285,16 +333,19 @@ void qede_free_arfs(struct qede_dev *edev) if (!edev->arfs) return; +#ifdef CONFIG_RFS_ACCEL if (edev->ndev->rx_cpu_rmap) free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap); edev->ndev->rx_cpu_rmap = NULL; +#endif vfree(edev->arfs->arfs_fltr_bmap); edev->arfs->arfs_fltr_bmap = NULL; vfree(edev->arfs); edev->arfs = NULL; } +#ifdef CONFIG_RFS_ACCEL static bool qede_compare_ip_addr(struct qede_arfs_fltr_node *tpos, const struct sk_buff *skb) { @@ -394,9 +445,8 @@ int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, spin_lock_bh(&edev->arfs->arfs_list_lock); - n = qede_arfs_htbl_key_search(&edev->arfs->arfs_hl_head[tbl_idx], + n = qede_arfs_htbl_key_search(QEDE_ARFS_BUCKET_HEAD(edev, tbl_idx), skb, ports[0], ports[1], ip_proto); - if (n) { /* Filter match */ n->next_rxq_id = rxq_index; @@ -448,23 +498,9 @@ int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, n->tuple.ip_proto = ip_proto; memcpy(n->data + ETH_HLEN, skb->data, skb_headlen(skb)); - n->mapping = dma_map_single(&edev->pdev->dev, n->data, - n->buf_len, DMA_TO_DEVICE); - if (dma_mapping_error(&edev->pdev->dev, n->mapping)) { - DP_NOTICE(edev, "Failed to map DMA memory for arfs\n"); - qede_free_arfs_filter(edev, n); - rc = -ENOMEM; + rc = qede_enqueue_fltr_and_config_searcher(edev, n, tbl_idx); + if (rc) goto ret_unlock; - } - - INIT_HLIST_NODE(&n->node); - hlist_add_head(&n->node, &edev->arfs->arfs_hl_head[tbl_idx]); - edev->arfs->filter_count++; - - if (edev->arfs->filter_count == 1 && !edev->arfs->enable) { - edev->ops->configure_arfs_searcher(edev->cdev, true); - edev->arfs->enable = true; - } qede_configure_arfs_fltr(edev, n, n->rxq_id, true); @@ -472,6 +508,7 @@ int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, set_bit(QEDE_SP_ARFS_CONFIG, &edev->sp_flags); schedule_delayed_work(&edev->sp_task, 0); + return n->sw_id; ret_unlock: @@ -1263,3 +1300,371 @@ void qede_config_rx_mode(struct net_device *ndev) out: kfree(uc_macs); } + +static struct qede_arfs_fltr_node * +qede_get_arfs_fltr_by_loc(struct hlist_head *head, u32 location) +{ + struct qede_arfs_fltr_node *fltr; + + hlist_for_each_entry(fltr, head, node) + if (location == fltr->sw_id) + return fltr; + + return NULL; +} + +static bool +qede_compare_user_flow_ips(struct qede_arfs_fltr_node *tpos, + struct ethtool_rx_flow_spec *fsp, + __be16 proto) +{ + if (proto == htons(ETH_P_IP)) { + struct ethtool_tcpip4_spec *ip; + + ip = &fsp->h_u.tcp_ip4_spec; + + if (tpos->tuple.src_ipv4 == ip->ip4src && + tpos->tuple.dst_ipv4 == ip->ip4dst) + return true; + else + return false; + } else { + struct ethtool_tcpip6_spec *ip6; + struct in6_addr *src; + + ip6 = &fsp->h_u.tcp_ip6_spec; + src = &tpos->tuple.src_ipv6; + + if (!memcmp(src, &ip6->ip6src, sizeof(struct in6_addr)) && + !memcmp(&tpos->tuple.dst_ipv6, &ip6->ip6dst, + sizeof(struct in6_addr))) + return true; + else + return false; + } + return false; +} + +int qede_get_cls_rule_all(struct qede_dev *edev, struct ethtool_rxnfc *info, + u32 *rule_locs) +{ + struct qede_arfs_fltr_node *fltr; + struct hlist_head *head; + int cnt = 0, rc = 0; + + info->data = QEDE_RFS_MAX_FLTR; + + __qede_lock(edev); + + if (!edev->arfs) { + rc = -EPERM; + goto unlock; + } + + head = QEDE_ARFS_BUCKET_HEAD(edev, 0); + + hlist_for_each_entry(fltr, head, node) { + if (cnt == info->rule_cnt) { + rc = -EMSGSIZE; + goto unlock; + } + + rule_locs[cnt] = fltr->sw_id; + cnt++; + } + + info->rule_cnt = cnt; + +unlock: + __qede_unlock(edev); + return rc; +} + +int qede_get_cls_rule_entry(struct qede_dev *edev, struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = &cmd->fs; + struct qede_arfs_fltr_node *fltr = NULL; + int rc = 0; + + cmd->data = QEDE_RFS_MAX_FLTR; + + __qede_lock(edev); + + if (!edev->arfs) { + rc = -EPERM; + goto unlock; + } + + fltr = qede_get_arfs_fltr_by_loc(QEDE_ARFS_BUCKET_HEAD(edev, 0), + fsp->location); + if (!fltr) { + DP_NOTICE(edev, "Rule not found - location=0x%x\n", + fsp->location); + rc = -EINVAL; + goto unlock; + } + + if (fltr->tuple.eth_proto == htons(ETH_P_IP)) { + if (fltr->tuple.ip_proto == IPPROTO_TCP) + fsp->flow_type = TCP_V4_FLOW; + else + fsp->flow_type = UDP_V4_FLOW; + + fsp->h_u.tcp_ip4_spec.psrc = fltr->tuple.src_port; + fsp->h_u.tcp_ip4_spec.pdst = fltr->tuple.dst_port; + fsp->h_u.tcp_ip4_spec.ip4src = fltr->tuple.src_ipv4; + fsp->h_u.tcp_ip4_spec.ip4dst = fltr->tuple.dst_ipv4; + } else { + if (fltr->tuple.ip_proto == IPPROTO_TCP) + fsp->flow_type = TCP_V6_FLOW; + else + fsp->flow_type = UDP_V6_FLOW; + fsp->h_u.tcp_ip6_spec.psrc = fltr->tuple.src_port; + fsp->h_u.tcp_ip6_spec.pdst = fltr->tuple.dst_port; + memcpy(&fsp->h_u.tcp_ip6_spec.ip6src, + &fltr->tuple.src_ipv6, sizeof(struct in6_addr)); + memcpy(&fsp->h_u.tcp_ip6_spec.ip6dst, + &fltr->tuple.dst_ipv6, sizeof(struct in6_addr)); + } + + fsp->ring_cookie = fltr->rxq_id; + +unlock: + __qede_unlock(edev); + return rc; +} + +static int +qede_validate_and_check_flow_exist(struct qede_dev *edev, + struct ethtool_rx_flow_spec *fsp, + int *min_hlen) +{ + __be16 src_port = 0x0, dst_port = 0x0; + struct qede_arfs_fltr_node *fltr; + struct hlist_node *temp; + struct hlist_head *head; + __be16 eth_proto; + u8 ip_proto; + + if (fsp->location >= QEDE_RFS_MAX_FLTR || + fsp->ring_cookie >= QEDE_RSS_COUNT(edev)) + return -EINVAL; + + if (fsp->flow_type == TCP_V4_FLOW) { + *min_hlen += sizeof(struct iphdr) + + sizeof(struct tcphdr); + eth_proto = htons(ETH_P_IP); + ip_proto = IPPROTO_TCP; + } else if (fsp->flow_type == UDP_V4_FLOW) { + *min_hlen += sizeof(struct iphdr) + + sizeof(struct udphdr); + eth_proto = htons(ETH_P_IP); + ip_proto = IPPROTO_UDP; + } else if (fsp->flow_type == TCP_V6_FLOW) { + *min_hlen += sizeof(struct ipv6hdr) + + sizeof(struct tcphdr); + eth_proto = htons(ETH_P_IPV6); + ip_proto = IPPROTO_TCP; + } else if (fsp->flow_type == UDP_V6_FLOW) { + *min_hlen += sizeof(struct ipv6hdr) + + sizeof(struct udphdr); + eth_proto = htons(ETH_P_IPV6); + ip_proto = IPPROTO_UDP; + } else { + DP_NOTICE(edev, "Unsupported flow type = 0x%x\n", + fsp->flow_type); + return -EPROTONOSUPPORT; + } + + if (eth_proto == htons(ETH_P_IP)) { + src_port = fsp->h_u.tcp_ip4_spec.psrc; + dst_port = fsp->h_u.tcp_ip4_spec.pdst; + } else { + src_port = fsp->h_u.tcp_ip6_spec.psrc; + dst_port = fsp->h_u.tcp_ip6_spec.pdst; + } + + head = QEDE_ARFS_BUCKET_HEAD(edev, 0); + hlist_for_each_entry_safe(fltr, temp, head, node) { + if ((fltr->tuple.ip_proto == ip_proto && + fltr->tuple.eth_proto == eth_proto && + qede_compare_user_flow_ips(fltr, fsp, eth_proto) && + fltr->tuple.src_port == src_port && + fltr->tuple.dst_port == dst_port) || + fltr->sw_id == fsp->location) + return -EEXIST; + } + + return 0; +} + +static int +qede_poll_arfs_filter_config(struct qede_dev *edev, + struct qede_arfs_fltr_node *fltr) +{ + int count = QEDE_ARFS_POLL_COUNT; + + while (fltr->used && count) { + msleep(20); + count--; + } + + if (count == 0 || fltr->fw_rc) { + qede_dequeue_fltr_and_config_searcher(edev, fltr); + return -EIO; + } + + return fltr->fw_rc; +} + +int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info) +{ + struct ethtool_rx_flow_spec *fsp = &info->fs; + struct qede_arfs_fltr_node *n; + int min_hlen = ETH_HLEN, rc; + struct ethhdr *eth; + struct iphdr *ip; + __be16 *ports; + + __qede_lock(edev); + + if (!edev->arfs) { + rc = -EPERM; + goto unlock; + } + + rc = qede_validate_and_check_flow_exist(edev, fsp, &min_hlen); + if (rc) + goto unlock; + + n = kzalloc(sizeof(*n), GFP_KERNEL); + if (!n) { + rc = -ENOMEM; + goto unlock; + } + + n->data = kzalloc(min_hlen, GFP_KERNEL); + if (!n->data) { + kfree(n); + rc = -ENOMEM; + goto unlock; + } + + n->sw_id = fsp->location; + set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap); + n->buf_len = min_hlen; + n->rxq_id = fsp->ring_cookie; + n->next_rxq_id = n->rxq_id; + eth = (struct ethhdr *)n->data; + + if (info->fs.flow_type == TCP_V4_FLOW || + info->fs.flow_type == UDP_V4_FLOW) { + ports = (__be16 *)(n->data + ETH_HLEN + + sizeof(struct iphdr)); + eth->h_proto = htons(ETH_P_IP); + n->tuple.eth_proto = htons(ETH_P_IP); + n->tuple.src_ipv4 = info->fs.h_u.tcp_ip4_spec.ip4src; + n->tuple.dst_ipv4 = info->fs.h_u.tcp_ip4_spec.ip4dst; + n->tuple.src_port = info->fs.h_u.tcp_ip4_spec.psrc; + n->tuple.dst_port = info->fs.h_u.tcp_ip4_spec.pdst; + ports[0] = n->tuple.src_port; + ports[1] = n->tuple.dst_port; + ip = (struct iphdr *)(n->data + ETH_HLEN); + ip->saddr = info->fs.h_u.tcp_ip4_spec.ip4src; + ip->daddr = info->fs.h_u.tcp_ip4_spec.ip4dst; + ip->version = 0x4; + ip->ihl = 0x5; + + if (info->fs.flow_type == TCP_V4_FLOW) { + n->tuple.ip_proto = IPPROTO_TCP; + ip->protocol = IPPROTO_TCP; + } else { + n->tuple.ip_proto = IPPROTO_UDP; + ip->protocol = IPPROTO_UDP; + } + ip->tot_len = cpu_to_be16(min_hlen - ETH_HLEN); + } else { + struct ipv6hdr *ip6; + + ip6 = (struct ipv6hdr *)(n->data + ETH_HLEN); + ports = (__be16 *)(n->data + ETH_HLEN + + sizeof(struct ipv6hdr)); + eth->h_proto = htons(ETH_P_IPV6); + n->tuple.eth_proto = htons(ETH_P_IPV6); + memcpy(&n->tuple.src_ipv6, &info->fs.h_u.tcp_ip6_spec.ip6src, + sizeof(struct in6_addr)); + memcpy(&n->tuple.dst_ipv6, &info->fs.h_u.tcp_ip6_spec.ip6dst, + sizeof(struct in6_addr)); + n->tuple.src_port = info->fs.h_u.tcp_ip6_spec.psrc; + n->tuple.dst_port = info->fs.h_u.tcp_ip6_spec.pdst; + ports[0] = n->tuple.src_port; + ports[1] = n->tuple.dst_port; + memcpy(&ip6->saddr, &n->tuple.src_ipv6, + sizeof(struct in6_addr)); + memcpy(&ip6->daddr, &n->tuple.dst_ipv6, + sizeof(struct in6_addr)); + ip6->version = 0x6; + + if (info->fs.flow_type == TCP_V6_FLOW) { + n->tuple.ip_proto = IPPROTO_TCP; + ip6->nexthdr = NEXTHDR_TCP; + ip6->payload_len = cpu_to_be16(sizeof(struct tcphdr)); + } else { + n->tuple.ip_proto = IPPROTO_UDP; + ip6->nexthdr = NEXTHDR_UDP; + ip6->payload_len = cpu_to_be16(sizeof(struct udphdr)); + } + } + + rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0); + if (rc) + goto unlock; + + qede_configure_arfs_fltr(edev, n, n->rxq_id, true); + rc = qede_poll_arfs_filter_config(edev, n); +unlock: + __qede_unlock(edev); + return rc; +} + +int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info) +{ + struct ethtool_rx_flow_spec *fsp = &info->fs; + struct qede_arfs_fltr_node *fltr = NULL; + int rc = -EPERM; + + __qede_lock(edev); + if (!edev->arfs) + goto unlock; + + fltr = qede_get_arfs_fltr_by_loc(QEDE_ARFS_BUCKET_HEAD(edev, 0), + fsp->location); + if (!fltr) + goto unlock; + + qede_configure_arfs_fltr(edev, fltr, fltr->rxq_id, false); + + rc = qede_poll_arfs_filter_config(edev, fltr); + if (rc == 0) + qede_dequeue_fltr_and_config_searcher(edev, fltr); + +unlock: + __qede_unlock(edev); + return rc; +} + +int qede_get_arfs_filter_count(struct qede_dev *edev) +{ + int count = 0; + + __qede_lock(edev); + + if (!edev->arfs) + goto unlock; + + count = edev->arfs->filter_count; + +unlock: + __qede_unlock(edev); + return count; +} diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 06ca13dd9ddb..e5ee9f274a71 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -873,9 +873,7 @@ static void qede_update_pf_params(struct qed_dev *cdev) */ pf_params.eth_pf_params.num_vf_cons = 48; -#ifdef CONFIG_RFS_ACCEL pf_params.eth_pf_params.num_arfs_filters = QEDE_RFS_MAX_FLTR; -#endif qed_ops->common->update_pf_params(cdev, &pf_params); } @@ -1984,12 +1982,12 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, qede_vlan_mark_nonconfigured(edev); edev->ops->fastpath_stop(edev->cdev); -#ifdef CONFIG_RFS_ACCEL + if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { qede_poll_for_freeing_arfs_filters(edev); qede_free_arfs(edev); } -#endif + /* Release the interrupts */ qede_sync_free_irqs(edev); edev->ops->common->set_fp_int(edev->cdev, 0); @@ -2041,13 +2039,12 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, if (rc) goto err2; -#ifdef CONFIG_RFS_ACCEL if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { rc = qede_alloc_arfs(edev); if (rc) DP_NOTICE(edev, "aRFS memory allocation failed\n"); } -#endif + qede_napi_add_enable(edev); DP_INFO(edev, "Napi added and enabled\n"); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c index be41e4c77b65..c48a0e2d4d7e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_init.c @@ -592,13 +592,9 @@ qlcnic_receive_peg_ready(struct qlcnic_adapter *adapter) } while (--retries); - if (!retries) { - dev_err(&adapter->pdev->dev, "Receive Peg initialization not " - "complete, state: 0x%x.\n", val); - return -EIO; - } - - return 0; + dev_err(&adapter->pdev->dev, "Receive Peg initialization not complete, state: 0x%x.\n", + val); + return -EIO; } int diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index 0844b7c75767..afa10a163da1 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -1285,7 +1285,7 @@ flash_temp: int qlcnic_dump_fw(struct qlcnic_adapter *adapter) { struct qlcnic_fw_dump *fw_dump = &adapter->ahw->fw_dump; - static const struct qlcnic_dump_operations *fw_dump_ops; + const struct qlcnic_dump_operations *fw_dump_ops; struct qlcnic_83xx_dump_template_hdr *hdr_83xx; u32 entry_offset, dump, no_entries, buf_offset = 0; int i, k, ops_cnt, ops_index, dump_size = 0; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 73027a6c06c7..287d89dd086f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -1174,19 +1174,19 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp, return size; } -static struct device_attribute dev_attr_bridged_mode = { +static const struct device_attribute dev_attr_bridged_mode = { .attr = {.name = "bridged_mode", .mode = (S_IRUGO | S_IWUSR)}, .show = qlcnic_show_bridged_mode, .store = qlcnic_store_bridged_mode, }; -static struct device_attribute dev_attr_diag_mode = { +static const struct device_attribute dev_attr_diag_mode = { .attr = {.name = "diag_mode", .mode = (S_IRUGO | S_IWUSR)}, .show = qlcnic_show_diag_mode, .store = qlcnic_store_diag_mode, }; -static struct device_attribute dev_attr_beacon = { +static const struct device_attribute dev_attr_beacon = { .attr = {.name = "beacon", .mode = (S_IRUGO | S_IWUSR)}, .show = qlcnic_show_beacon, .store = qlcnic_store_beacon, @@ -1248,7 +1248,7 @@ static const struct bin_attribute bin_attr_pm_config = { .write = qlcnic_sysfs_write_pm_config, }; -static struct bin_attribute bin_attr_flash = { +static const struct bin_attribute bin_attr_flash = { .attr = {.name = "flash", .mode = (S_IRUGO | S_IWUSR)}, .size = 0, .read = qlcnic_83xx_sysfs_flash_read_handler, diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c index e3223f2fe2ff..fe2599b83d09 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c @@ -144,42 +144,23 @@ static int ql_get_serdes_regs(struct ql_adapter *qdev, xaui_direct_valid = xaui_indirect_valid = 1; /* The XAUI needs to be read out per port */ - if (qdev->func & 1) { - /* We are NIC 2 */ - status = ql_read_other_func_serdes_reg(qdev, - XG_SERDES_XAUI_HSS_PCS_START, &temp); - if (status) - temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; - if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == - XG_SERDES_ADDR_XAUI_PWR_DOWN) - xaui_indirect_valid = 0; + status = ql_read_other_func_serdes_reg(qdev, + XG_SERDES_XAUI_HSS_PCS_START, &temp); + if (status) + temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; - status = ql_read_serdes_reg(qdev, - XG_SERDES_XAUI_HSS_PCS_START, &temp); - if (status) - temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; + if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == + XG_SERDES_ADDR_XAUI_PWR_DOWN) + xaui_indirect_valid = 0; - if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == - XG_SERDES_ADDR_XAUI_PWR_DOWN) - xaui_direct_valid = 0; - } else { - /* We are NIC 1 */ - status = ql_read_other_func_serdes_reg(qdev, - XG_SERDES_XAUI_HSS_PCS_START, &temp); - if (status) - temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; - if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == - XG_SERDES_ADDR_XAUI_PWR_DOWN) - xaui_indirect_valid = 0; + status = ql_read_serdes_reg(qdev, XG_SERDES_XAUI_HSS_PCS_START, &temp); - status = ql_read_serdes_reg(qdev, - XG_SERDES_XAUI_HSS_PCS_START, &temp); - if (status) - temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; - if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == - XG_SERDES_ADDR_XAUI_PWR_DOWN) - xaui_direct_valid = 0; - } + if (status) + temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; + + if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == + XG_SERDES_ADDR_XAUI_PWR_DOWN) + xaui_direct_valid = 0; /* * XFI register is shared so only need to read one diff --git a/drivers/net/ethernet/qualcomm/Kconfig b/drivers/net/ethernet/qualcomm/Kconfig index 877675a27b9f..f5200712718d 100644 --- a/drivers/net/ethernet/qualcomm/Kconfig +++ b/drivers/net/ethernet/qualcomm/Kconfig @@ -59,4 +59,6 @@ config QCOM_EMAC low power, Receive-Side Scaling (RSS), and IEEE 1588-2008 Precision Clock Synchronization Protocol. +source "drivers/net/ethernet/qualcomm/rmnet/Kconfig" + endif # NET_VENDOR_QUALCOMM diff --git a/drivers/net/ethernet/qualcomm/Makefile b/drivers/net/ethernet/qualcomm/Makefile index 92fa7c4da90a..1847350f48a7 100644 --- a/drivers/net/ethernet/qualcomm/Makefile +++ b/drivers/net/ethernet/qualcomm/Makefile @@ -9,3 +9,5 @@ obj-$(CONFIG_QCA7000_UART) += qcauart.o qcauart-objs := qca_uart.o obj-y += emac/ + +obj-$(CONFIG_RMNET) += rmnet/ diff --git a/drivers/net/ethernet/qualcomm/rmnet/Kconfig b/drivers/net/ethernet/qualcomm/rmnet/Kconfig new file mode 100644 index 000000000000..6e2587af47a4 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/Kconfig @@ -0,0 +1,12 @@ +# +# RMNET MAP driver +# + +menuconfig RMNET + tristate "RmNet MAP driver" + default n + ---help--- + If you select this, you will enable the RMNET module which is used + for handling data in the multiplexing and aggregation protocol (MAP) + format in the embedded data path. RMNET devices can be attached to + any IP mode physical device. diff --git a/drivers/net/ethernet/qualcomm/rmnet/Makefile b/drivers/net/ethernet/qualcomm/rmnet/Makefile new file mode 100644 index 000000000000..01bddf207cac --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/Makefile @@ -0,0 +1,10 @@ +# +# Makefile for the RMNET module +# + +rmnet-y := rmnet_config.o +rmnet-y += rmnet_vnd.o +rmnet-y += rmnet_handlers.o +rmnet-y += rmnet_map_data.o +rmnet-y += rmnet_map_command.o +obj-$(CONFIG_RMNET) += rmnet.o diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c new file mode 100644 index 000000000000..98f22551eb45 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -0,0 +1,356 @@ +/* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * RMNET configuration engine + * + */ + +#include <net/sock.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netdevice.h> +#include "rmnet_config.h" +#include "rmnet_handlers.h" +#include "rmnet_vnd.h" +#include "rmnet_private.h" + +/* Locking scheme - + * The shared resource which needs to be protected is realdev->rx_handler_data. + * For the writer path, this is using rtnl_lock(). The writer paths are + * rmnet_newlink(), rmnet_dellink() and rmnet_force_unassociate_device(). These + * paths are already called with rtnl_lock() acquired in. There is also an + * ASSERT_RTNL() to ensure that we are calling with rtnl acquired. For + * dereference here, we will need to use rtnl_dereference(). Dev list writing + * needs to happen with rtnl_lock() acquired for netdev_master_upper_dev_link(). + * For the reader path, the real_dev->rx_handler_data is called in the TX / RX + * path. We only need rcu_read_lock() for these scenarios. In these cases, + * the rcu_read_lock() is held in __dev_queue_xmit() and + * netif_receive_skb_internal(), so readers need to use rcu_dereference_rtnl() + * to get the relevant information. For dev list reading, we again acquire + * rcu_read_lock() in rmnet_dellink() for netdev_master_upper_dev_get_rcu(). + * We also use unregister_netdevice_many() to free all rmnet devices in + * rmnet_force_unassociate_device() so we dont lose the rtnl_lock() and free in + * same context. + */ + +/* Local Definitions and Declarations */ + +struct rmnet_walk_data { + struct net_device *real_dev; + struct list_head *head; + struct rmnet_port *port; +}; + +static int rmnet_is_real_dev_registered(const struct net_device *real_dev) +{ + rx_handler_func_t *rx_handler; + + rx_handler = rcu_dereference(real_dev->rx_handler); + return (rx_handler == rmnet_rx_handler); +} + +/* Needs rtnl lock */ +static struct rmnet_port* +rmnet_get_port_rtnl(const struct net_device *real_dev) +{ + return rtnl_dereference(real_dev->rx_handler_data); +} + +static struct rmnet_endpoint* +rmnet_get_endpoint(struct net_device *dev, int config_id) +{ + struct rmnet_endpoint *ep; + struct rmnet_port *port; + + if (!rmnet_is_real_dev_registered(dev)) { + ep = rmnet_vnd_get_endpoint(dev); + } else { + port = rmnet_get_port_rtnl(dev); + + ep = &port->muxed_ep[config_id]; + } + + return ep; +} + +static int rmnet_unregister_real_device(struct net_device *real_dev, + struct rmnet_port *port) +{ + if (port->nr_rmnet_devs) + return -EINVAL; + + kfree(port); + + netdev_rx_handler_unregister(real_dev); + + /* release reference on real_dev */ + dev_put(real_dev); + + netdev_dbg(real_dev, "Removed from rmnet\n"); + return 0; +} + +static int rmnet_register_real_device(struct net_device *real_dev) +{ + struct rmnet_port *port; + int rc; + + ASSERT_RTNL(); + + if (rmnet_is_real_dev_registered(real_dev)) + return 0; + + port = kzalloc(sizeof(*port), GFP_ATOMIC); + if (!port) + return -ENOMEM; + + port->dev = real_dev; + rc = netdev_rx_handler_register(real_dev, rmnet_rx_handler, port); + if (rc) { + kfree(port); + return -EBUSY; + } + + /* hold on to real dev for MAP data */ + dev_hold(real_dev); + + netdev_dbg(real_dev, "registered with rmnet\n"); + return 0; +} + +static void rmnet_set_endpoint_config(struct net_device *dev, + u8 mux_id, u8 rmnet_mode, + struct net_device *egress_dev) +{ + struct rmnet_endpoint *ep; + + netdev_dbg(dev, "id %d mode %d dev %s\n", + mux_id, rmnet_mode, egress_dev->name); + + ep = rmnet_get_endpoint(dev, mux_id); + /* This config is cleared on every set, so its ok to not + * clear it on a device delete. + */ + memset(ep, 0, sizeof(struct rmnet_endpoint)); + ep->rmnet_mode = rmnet_mode; + ep->egress_dev = egress_dev; + ep->mux_id = mux_id; +} + +static int rmnet_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + int ingress_format = RMNET_INGRESS_FORMAT_DEMUXING | + RMNET_INGRESS_FORMAT_DEAGGREGATION | + RMNET_INGRESS_FORMAT_MAP; + int egress_format = RMNET_EGRESS_FORMAT_MUXING | + RMNET_EGRESS_FORMAT_MAP; + struct net_device *real_dev; + int mode = RMNET_EPMODE_VND; + struct rmnet_port *port; + int err = 0; + u16 mux_id; + + real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + if (!real_dev || !dev) + return -ENODEV; + + if (!data[IFLA_VLAN_ID]) + return -EINVAL; + + mux_id = nla_get_u16(data[IFLA_VLAN_ID]); + + err = rmnet_register_real_device(real_dev); + if (err) + goto err0; + + port = rmnet_get_port_rtnl(real_dev); + err = rmnet_vnd_newlink(mux_id, dev, port, real_dev); + if (err) + goto err1; + + err = netdev_master_upper_dev_link(dev, real_dev, NULL, NULL); + if (err) + goto err2; + + netdev_dbg(dev, "data format [ingress 0x%08X] [egress 0x%08X]\n", + ingress_format, egress_format); + port->egress_data_format = egress_format; + port->ingress_data_format = ingress_format; + + rmnet_set_endpoint_config(real_dev, mux_id, mode, dev); + rmnet_set_endpoint_config(dev, mux_id, mode, real_dev); + return 0; + +err2: + rmnet_vnd_dellink(mux_id, port); +err1: + rmnet_unregister_real_device(real_dev, port); +err0: + return err; +} + +static void rmnet_dellink(struct net_device *dev, struct list_head *head) +{ + struct net_device *real_dev; + struct rmnet_port *port; + u8 mux_id; + + rcu_read_lock(); + real_dev = netdev_master_upper_dev_get_rcu(dev); + rcu_read_unlock(); + + if (!real_dev || !rmnet_is_real_dev_registered(real_dev)) + return; + + port = rmnet_get_port_rtnl(real_dev); + + mux_id = rmnet_vnd_get_mux(dev); + rmnet_vnd_dellink(mux_id, port); + netdev_upper_dev_unlink(dev, real_dev); + rmnet_unregister_real_device(real_dev, port); + + unregister_netdevice_queue(dev, head); +} + +static int rmnet_dev_walk_unreg(struct net_device *rmnet_dev, void *data) +{ + struct rmnet_walk_data *d = data; + u8 mux_id; + + mux_id = rmnet_vnd_get_mux(rmnet_dev); + + rmnet_vnd_dellink(mux_id, d->port); + netdev_upper_dev_unlink(rmnet_dev, d->real_dev); + unregister_netdevice_queue(rmnet_dev, d->head); + + return 0; +} + +static void rmnet_force_unassociate_device(struct net_device *dev) +{ + struct net_device *real_dev = dev; + struct rmnet_walk_data d; + struct rmnet_port *port; + LIST_HEAD(list); + + if (!rmnet_is_real_dev_registered(real_dev)) + return; + + ASSERT_RTNL(); + + d.real_dev = real_dev; + d.head = &list; + + port = rmnet_get_port_rtnl(dev); + d.port = port; + + rcu_read_lock(); + netdev_walk_all_lower_dev_rcu(real_dev, rmnet_dev_walk_unreg, &d); + rcu_read_unlock(); + unregister_netdevice_many(&list); + + rmnet_unregister_real_device(real_dev, port); +} + +static int rmnet_config_notify_cb(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct net_device *dev = netdev_notifier_info_to_dev(data); + + if (!dev) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_UNREGISTER: + netdev_dbg(dev, "Kernel unregister\n"); + rmnet_force_unassociate_device(dev); + break; + + default: + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block rmnet_dev_notifier __read_mostly = { + .notifier_call = rmnet_config_notify_cb, +}; + +static int rmnet_rtnl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + u16 mux_id; + + if (!data || !data[IFLA_VLAN_ID]) + return -EINVAL; + + mux_id = nla_get_u16(data[IFLA_VLAN_ID]); + if (mux_id > (RMNET_MAX_LOGICAL_EP - 1)) + return -ERANGE; + + return 0; +} + +static size_t rmnet_get_size(const struct net_device *dev) +{ + return nla_total_size(2); /* IFLA_VLAN_ID */ +} + +struct rtnl_link_ops rmnet_link_ops __read_mostly = { + .kind = "rmnet", + .maxtype = __IFLA_VLAN_MAX, + .priv_size = sizeof(struct rmnet_priv), + .setup = rmnet_vnd_setup, + .validate = rmnet_rtnl_validate, + .newlink = rmnet_newlink, + .dellink = rmnet_dellink, + .get_size = rmnet_get_size, +}; + +/* Needs either rcu_read_lock() or rtnl lock */ +struct rmnet_port *rmnet_get_port(struct net_device *real_dev) +{ + if (rmnet_is_real_dev_registered(real_dev)) + return rcu_dereference_rtnl(real_dev->rx_handler_data); + else + return NULL; +} + +/* Startup/Shutdown */ + +static int __init rmnet_init(void) +{ + int rc; + + rc = register_netdevice_notifier(&rmnet_dev_notifier); + if (rc != 0) + return rc; + + rc = rtnl_link_register(&rmnet_link_ops); + if (rc != 0) { + unregister_netdevice_notifier(&rmnet_dev_notifier); + return rc; + } + return rc; +} + +static void __exit rmnet_exit(void) +{ + unregister_netdevice_notifier(&rmnet_dev_notifier); + rtnl_link_unregister(&rmnet_link_ops); +} + +module_init(rmnet_init) +module_exit(rmnet_exit) +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h new file mode 100644 index 000000000000..dde4e9f14f4a --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -0,0 +1,55 @@ +/* Copyright (c) 2013-2014, 2016-2017 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * RMNET Data configuration engine + * + */ + +#include <linux/skbuff.h> + +#ifndef _RMNET_CONFIG_H_ +#define _RMNET_CONFIG_H_ + +#define RMNET_MAX_LOGICAL_EP 255 + +/* Information about the next device to deliver the packet to. + * Exact usage of this parameter depends on the rmnet_mode. + */ +struct rmnet_endpoint { + u8 rmnet_mode; + u8 mux_id; + struct net_device *egress_dev; +}; + +/* One instance of this structure is instantiated for each real_dev associated + * with rmnet. + */ +struct rmnet_port { + struct net_device *dev; + struct rmnet_endpoint local_ep; + struct rmnet_endpoint muxed_ep[RMNET_MAX_LOGICAL_EP]; + u32 ingress_data_format; + u32 egress_data_format; + struct net_device *rmnet_devices[RMNET_MAX_LOGICAL_EP]; + u8 nr_rmnet_devs; +}; + +extern struct rtnl_link_ops rmnet_link_ops; + +struct rmnet_priv { + struct rmnet_endpoint local_ep; + u8 mux_id; + struct net_device *real_dev; +}; + +struct rmnet_port *rmnet_get_port(struct net_device *real_dev); + +#endif /* _RMNET_CONFIG_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c new file mode 100644 index 000000000000..540c7622dcb1 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -0,0 +1,271 @@ +/* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * RMNET Data ingress/egress handler + * + */ + +#include <linux/netdevice.h> +#include <linux/netdev_features.h> +#include "rmnet_private.h" +#include "rmnet_config.h" +#include "rmnet_vnd.h" +#include "rmnet_map.h" +#include "rmnet_handlers.h" + +#define RMNET_IP_VERSION_4 0x40 +#define RMNET_IP_VERSION_6 0x60 + +/* Helper Functions */ + +static void rmnet_set_skb_proto(struct sk_buff *skb) +{ + switch (skb->data[0] & 0xF0) { + case RMNET_IP_VERSION_4: + skb->protocol = htons(ETH_P_IP); + break; + case RMNET_IP_VERSION_6: + skb->protocol = htons(ETH_P_IPV6); + break; + default: + skb->protocol = htons(ETH_P_MAP); + break; + } +} + +/* Generic handler */ + +static rx_handler_result_t +rmnet_bridge_handler(struct sk_buff *skb, struct rmnet_endpoint *ep) +{ + if (!ep->egress_dev) + kfree_skb(skb); + else + rmnet_egress_handler(skb, ep); + + return RX_HANDLER_CONSUMED; +} + +static rx_handler_result_t +rmnet_deliver_skb(struct sk_buff *skb, struct rmnet_endpoint *ep) +{ + switch (ep->rmnet_mode) { + case RMNET_EPMODE_NONE: + return RX_HANDLER_PASS; + + case RMNET_EPMODE_BRIDGE: + return rmnet_bridge_handler(skb, ep); + + case RMNET_EPMODE_VND: + skb_reset_transport_header(skb); + skb_reset_network_header(skb); + rmnet_vnd_rx_fixup(skb, skb->dev); + + skb->pkt_type = PACKET_HOST; + skb_set_mac_header(skb, 0); + netif_receive_skb(skb); + return RX_HANDLER_CONSUMED; + + default: + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } +} + +static rx_handler_result_t +rmnet_ingress_deliver_packet(struct sk_buff *skb, + struct rmnet_port *port) +{ + if (!port) { + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } + + skb->dev = port->local_ep.egress_dev; + + return rmnet_deliver_skb(skb, &port->local_ep); +} + +/* MAP handler */ + +static rx_handler_result_t +__rmnet_map_ingress_handler(struct sk_buff *skb, + struct rmnet_port *port) +{ + struct rmnet_endpoint *ep; + u8 mux_id; + u16 len; + + if (RMNET_MAP_GET_CD_BIT(skb)) { + if (port->ingress_data_format + & RMNET_INGRESS_FORMAT_MAP_COMMANDS) + return rmnet_map_command(skb, port); + + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } + + mux_id = RMNET_MAP_GET_MUX_ID(skb); + len = RMNET_MAP_GET_LENGTH(skb) - RMNET_MAP_GET_PAD(skb); + + if (mux_id >= RMNET_MAX_LOGICAL_EP) { + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } + + ep = &port->muxed_ep[mux_id]; + + if (port->ingress_data_format & RMNET_INGRESS_FORMAT_DEMUXING) + skb->dev = ep->egress_dev; + + /* Subtract MAP header */ + skb_pull(skb, sizeof(struct rmnet_map_header)); + skb_trim(skb, len); + rmnet_set_skb_proto(skb); + return rmnet_deliver_skb(skb, ep); +} + +static rx_handler_result_t +rmnet_map_ingress_handler(struct sk_buff *skb, + struct rmnet_port *port) +{ + struct sk_buff *skbn; + int rc; + + if (port->ingress_data_format & RMNET_INGRESS_FORMAT_DEAGGREGATION) { + while ((skbn = rmnet_map_deaggregate(skb)) != NULL) + __rmnet_map_ingress_handler(skbn, port); + + consume_skb(skb); + rc = RX_HANDLER_CONSUMED; + } else { + rc = __rmnet_map_ingress_handler(skb, port); + } + + return rc; +} + +static int rmnet_map_egress_handler(struct sk_buff *skb, + struct rmnet_port *port, + struct rmnet_endpoint *ep, + struct net_device *orig_dev) +{ + int required_headroom, additional_header_len; + struct rmnet_map_header *map_header; + + additional_header_len = 0; + required_headroom = sizeof(struct rmnet_map_header); + + if (skb_headroom(skb) < required_headroom) { + if (pskb_expand_head(skb, required_headroom, 0, GFP_KERNEL)) + return RMNET_MAP_CONSUMED; + } + + map_header = rmnet_map_add_map_header(skb, additional_header_len, 0); + if (!map_header) + return RMNET_MAP_CONSUMED; + + if (port->egress_data_format & RMNET_EGRESS_FORMAT_MUXING) { + if (ep->mux_id == 0xff) + map_header->mux_id = 0; + else + map_header->mux_id = ep->mux_id; + } + + skb->protocol = htons(ETH_P_MAP); + + return RMNET_MAP_SUCCESS; +} + +/* Ingress / Egress Entry Points */ + +/* Processes packet as per ingress data format for receiving device. Logical + * endpoint is determined from packet inspection. Packet is then sent to the + * egress device listed in the logical endpoint configuration. + */ +rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb) +{ + struct rmnet_port *port; + struct sk_buff *skb = *pskb; + struct net_device *dev; + int rc; + + if (!skb) + return RX_HANDLER_CONSUMED; + + dev = skb->dev; + port = rmnet_get_port(dev); + + if (port->ingress_data_format & RMNET_INGRESS_FORMAT_MAP) { + rc = rmnet_map_ingress_handler(skb, port); + } else { + switch (ntohs(skb->protocol)) { + case ETH_P_MAP: + if (port->local_ep.rmnet_mode == + RMNET_EPMODE_BRIDGE) { + rc = rmnet_ingress_deliver_packet(skb, port); + } else { + kfree_skb(skb); + rc = RX_HANDLER_CONSUMED; + } + break; + + case ETH_P_IP: + case ETH_P_IPV6: + rc = rmnet_ingress_deliver_packet(skb, port); + break; + + default: + rc = RX_HANDLER_PASS; + } + } + + return rc; +} + +/* Modifies packet as per logical endpoint configuration and egress data format + * for egress device configured in logical endpoint. Packet is then transmitted + * on the egress device. + */ +void rmnet_egress_handler(struct sk_buff *skb, + struct rmnet_endpoint *ep) +{ + struct net_device *orig_dev; + struct rmnet_port *port; + + orig_dev = skb->dev; + skb->dev = ep->egress_dev; + + port = rmnet_get_port(skb->dev); + if (!port) { + kfree_skb(skb); + return; + } + + if (port->egress_data_format & RMNET_EGRESS_FORMAT_MAP) { + switch (rmnet_map_egress_handler(skb, port, ep, orig_dev)) { + case RMNET_MAP_CONSUMED: + return; + + case RMNET_MAP_SUCCESS: + break; + + default: + kfree_skb(skb); + return; + } + } + + if (ep->rmnet_mode == RMNET_EPMODE_VND) + rmnet_vnd_tx_fixup(skb, orig_dev); + + dev_queue_xmit(skb); +} diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h new file mode 100644 index 000000000000..f2638cf5693c --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.h @@ -0,0 +1,26 @@ +/* Copyright (c) 2013, 2016-2017 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * RMNET Data ingress/egress handler + * + */ + +#ifndef _RMNET_HANDLERS_H_ +#define _RMNET_HANDLERS_H_ + +#include "rmnet_config.h" + +void rmnet_egress_handler(struct sk_buff *skb, + struct rmnet_endpoint *ep); + +rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb); + +#endif /* _RMNET_HANDLERS_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h new file mode 100644 index 000000000000..ce2302c25b12 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h @@ -0,0 +1,86 @@ +/* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _RMNET_MAP_H_ +#define _RMNET_MAP_H_ + +struct rmnet_map_control_command { + u8 command_name; + u8 cmd_type:2; + u8 reserved:6; + u16 reserved2; + u32 transaction_id; + union { + struct { + u16 ip_family:2; + u16 reserved:14; + u16 flow_control_seq_num; + u32 qos_id; + } flow_control; + u8 data[0]; + }; +} __aligned(1); + +enum rmnet_map_results { + RMNET_MAP_SUCCESS, + RMNET_MAP_CONSUMED, + RMNET_MAP_GENERAL_FAILURE, + RMNET_MAP_NOT_ENABLED, + RMNET_MAP_FAILED_AGGREGATION, + RMNET_MAP_FAILED_MUX +}; + +enum rmnet_map_commands { + RMNET_MAP_COMMAND_NONE, + RMNET_MAP_COMMAND_FLOW_DISABLE, + RMNET_MAP_COMMAND_FLOW_ENABLE, + /* These should always be the last 2 elements */ + RMNET_MAP_COMMAND_UNKNOWN, + RMNET_MAP_COMMAND_ENUM_LENGTH +}; + +struct rmnet_map_header { + u8 pad_len:6; + u8 reserved_bit:1; + u8 cd_bit:1; + u8 mux_id; + u16 pkt_len; +} __aligned(1); + +#define RMNET_MAP_GET_MUX_ID(Y) (((struct rmnet_map_header *) \ + (Y)->data)->mux_id) +#define RMNET_MAP_GET_CD_BIT(Y) (((struct rmnet_map_header *) \ + (Y)->data)->cd_bit) +#define RMNET_MAP_GET_PAD(Y) (((struct rmnet_map_header *) \ + (Y)->data)->pad_len) +#define RMNET_MAP_GET_CMD_START(Y) ((struct rmnet_map_control_command *) \ + ((Y)->data + \ + sizeof(struct rmnet_map_header))) +#define RMNET_MAP_GET_LENGTH(Y) (ntohs(((struct rmnet_map_header *) \ + (Y)->data)->pkt_len)) + +#define RMNET_MAP_COMMAND_REQUEST 0 +#define RMNET_MAP_COMMAND_ACK 1 +#define RMNET_MAP_COMMAND_UNSUPPORTED 2 +#define RMNET_MAP_COMMAND_INVALID 3 + +#define RMNET_MAP_NO_PAD_BYTES 0 +#define RMNET_MAP_ADD_PAD_BYTES 1 + +u8 rmnet_map_demultiplex(struct sk_buff *skb); +struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb); +struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb, + int hdrlen, int pad); +rx_handler_result_t rmnet_map_command(struct sk_buff *skb, + struct rmnet_port *port); + +#endif /* _RMNET_MAP_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c new file mode 100644 index 000000000000..d1ea5e21b982 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c @@ -0,0 +1,106 @@ +/* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/netdevice.h> +#include "rmnet_config.h" +#include "rmnet_map.h" +#include "rmnet_private.h" +#include "rmnet_vnd.h" + +static u8 rmnet_map_do_flow_control(struct sk_buff *skb, + struct rmnet_port *rdinfo, + int enable) +{ + struct rmnet_map_control_command *cmd; + struct rmnet_endpoint *ep; + struct net_device *vnd; + u16 ip_family; + u16 fc_seq; + u32 qos_id; + u8 mux_id; + int r; + + mux_id = RMNET_MAP_GET_MUX_ID(skb); + cmd = RMNET_MAP_GET_CMD_START(skb); + + if (mux_id >= RMNET_MAX_LOGICAL_EP) { + kfree_skb(skb); + return RX_HANDLER_CONSUMED; + } + + ep = &rdinfo->muxed_ep[mux_id]; + vnd = ep->egress_dev; + + ip_family = cmd->flow_control.ip_family; + fc_seq = ntohs(cmd->flow_control.flow_control_seq_num); + qos_id = ntohl(cmd->flow_control.qos_id); + + /* Ignore the ip family and pass the sequence number for both v4 and v6 + * sequence. User space does not support creating dedicated flows for + * the 2 protocols + */ + r = rmnet_vnd_do_flow_control(vnd, enable); + if (r) { + kfree_skb(skb); + return RMNET_MAP_COMMAND_UNSUPPORTED; + } else { + return RMNET_MAP_COMMAND_ACK; + } +} + +static void rmnet_map_send_ack(struct sk_buff *skb, + unsigned char type) +{ + struct rmnet_map_control_command *cmd; + int xmit_status; + + skb->protocol = htons(ETH_P_MAP); + + cmd = RMNET_MAP_GET_CMD_START(skb); + cmd->cmd_type = type & 0x03; + + netif_tx_lock(skb->dev); + xmit_status = skb->dev->netdev_ops->ndo_start_xmit(skb, skb->dev); + netif_tx_unlock(skb->dev); +} + +/* Process MAP command frame and send N/ACK message as appropriate. Message cmd + * name is decoded here and appropriate handler is called. + */ +rx_handler_result_t rmnet_map_command(struct sk_buff *skb, + struct rmnet_port *port) +{ + struct rmnet_map_control_command *cmd; + unsigned char command_name; + unsigned char rc = 0; + + cmd = RMNET_MAP_GET_CMD_START(skb); + command_name = cmd->command_name; + + switch (command_name) { + case RMNET_MAP_COMMAND_FLOW_ENABLE: + rc = rmnet_map_do_flow_control(skb, port, 1); + break; + + case RMNET_MAP_COMMAND_FLOW_DISABLE: + rc = rmnet_map_do_flow_control(skb, port, 0); + break; + + default: + rc = RMNET_MAP_COMMAND_UNSUPPORTED; + kfree_skb(skb); + break; + } + if (rc == RMNET_MAP_COMMAND_ACK) + rmnet_map_send_ack(skb, rc); + return RX_HANDLER_CONSUMED; +} diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c new file mode 100644 index 000000000000..557c9bf1a469 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -0,0 +1,104 @@ +/* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * RMNET Data MAP protocol + * + */ + +#include <linux/netdevice.h> +#include "rmnet_config.h" +#include "rmnet_map.h" +#include "rmnet_private.h" + +#define RMNET_MAP_DEAGGR_SPACING 64 +#define RMNET_MAP_DEAGGR_HEADROOM (RMNET_MAP_DEAGGR_SPACING / 2) + +/* Adds MAP header to front of skb->data + * Padding is calculated and set appropriately in MAP header. Mux ID is + * initialized to 0. + */ +struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb, + int hdrlen, int pad) +{ + struct rmnet_map_header *map_header; + u32 padding, map_datalen; + u8 *padbytes; + + if (skb_headroom(skb) < sizeof(struct rmnet_map_header)) + return NULL; + + map_datalen = skb->len - hdrlen; + map_header = (struct rmnet_map_header *) + skb_push(skb, sizeof(struct rmnet_map_header)); + memset(map_header, 0, sizeof(struct rmnet_map_header)); + + if (pad == RMNET_MAP_NO_PAD_BYTES) { + map_header->pkt_len = htons(map_datalen); + return map_header; + } + + padding = ALIGN(map_datalen, 4) - map_datalen; + + if (padding == 0) + goto done; + + if (skb_tailroom(skb) < padding) + return NULL; + + padbytes = (u8 *)skb_put(skb, padding); + memset(padbytes, 0, padding); + +done: + map_header->pkt_len = htons(map_datalen + padding); + map_header->pad_len = padding & 0x3F; + + return map_header; +} + +/* Deaggregates a single packet + * A whole new buffer is allocated for each portion of an aggregated frame. + * Caller should keep calling deaggregate() on the source skb until 0 is + * returned, indicating that there are no more packets to deaggregate. Caller + * is responsible for freeing the original skb. + */ +struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb) +{ + struct rmnet_map_header *maph; + struct sk_buff *skbn; + u32 packet_len; + + if (skb->len == 0) + return NULL; + + maph = (struct rmnet_map_header *)skb->data; + packet_len = ntohs(maph->pkt_len) + sizeof(struct rmnet_map_header); + + if (((int)skb->len - (int)packet_len) < 0) + return NULL; + + skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC); + if (!skbn) + return NULL; + + skbn->dev = skb->dev; + skb_reserve(skbn, RMNET_MAP_DEAGGR_HEADROOM); + skb_put(skbn, packet_len); + memcpy(skbn->data, skb->data, packet_len); + skb_pull(skb, packet_len); + + /* Some hardware can send us empty frames. Catch them */ + if (ntohs(maph->pkt_len) == 0) { + kfree_skb(skb); + return NULL; + } + + return skbn; +} diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h new file mode 100644 index 000000000000..7967198fdd90 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_private.h @@ -0,0 +1,44 @@ +/* Copyright (c) 2013-2014, 2016-2017 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _RMNET_PRIVATE_H_ +#define _RMNET_PRIVATE_H_ + +#define RMNET_MAX_PACKET_SIZE 16384 +#define RMNET_DFLT_PACKET_SIZE 1500 +#define RMNET_NEEDED_HEADROOM 16 +#define RMNET_TX_QUEUE_LEN 1000 + +/* Constants */ +#define RMNET_EGRESS_FORMAT__RESERVED__ BIT(0) +#define RMNET_EGRESS_FORMAT_MAP BIT(1) +#define RMNET_EGRESS_FORMAT_AGGREGATION BIT(2) +#define RMNET_EGRESS_FORMAT_MUXING BIT(3) +#define RMNET_EGRESS_FORMAT_MAP_CKSUMV3 BIT(4) +#define RMNET_EGRESS_FORMAT_MAP_CKSUMV4 BIT(5) + +#define RMNET_INGRESS_FIX_ETHERNET BIT(0) +#define RMNET_INGRESS_FORMAT_MAP BIT(1) +#define RMNET_INGRESS_FORMAT_DEAGGREGATION BIT(2) +#define RMNET_INGRESS_FORMAT_DEMUXING BIT(3) +#define RMNET_INGRESS_FORMAT_MAP_COMMANDS BIT(4) +#define RMNET_INGRESS_FORMAT_MAP_CKSUMV3 BIT(5) +#define RMNET_INGRESS_FORMAT_MAP_CKSUMV4 BIT(6) + +/* Pass the frame up the stack with no modifications to skb->dev */ +#define RMNET_EPMODE_NONE (0) +/* Replace skb->dev to a virtual rmnet device and pass up the stack */ +#define RMNET_EPMODE_VND (1) +/* Pass the frame directly to another device with dev_queue_xmit() */ +#define RMNET_EPMODE_BRIDGE (2) + +#endif /* _RMNET_PRIVATE_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c new file mode 100644 index 000000000000..7f90d5587653 --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -0,0 +1,174 @@ +/* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * + * RMNET Data virtual network driver + * + */ + +#include <linux/etherdevice.h> +#include <linux/if_arp.h> +#include <net/pkt_sched.h> +#include "rmnet_config.h" +#include "rmnet_handlers.h" +#include "rmnet_private.h" +#include "rmnet_map.h" +#include "rmnet_vnd.h" + +/* RX/TX Fixup */ + +void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev) +{ + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; +} + +void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev) +{ + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; +} + +/* Network Device Operations */ + +static netdev_tx_t rmnet_vnd_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct rmnet_priv *priv; + + priv = netdev_priv(dev); + if (priv->local_ep.egress_dev) { + rmnet_egress_handler(skb, &priv->local_ep); + } else { + dev->stats.tx_dropped++; + kfree_skb(skb); + } + return NETDEV_TX_OK; +} + +static int rmnet_vnd_change_mtu(struct net_device *rmnet_dev, int new_mtu) +{ + if (new_mtu < 0 || new_mtu > RMNET_MAX_PACKET_SIZE) + return -EINVAL; + + rmnet_dev->mtu = new_mtu; + return 0; +} + +static int rmnet_vnd_get_iflink(const struct net_device *dev) +{ + struct rmnet_priv *priv = netdev_priv(dev); + + return priv->real_dev->ifindex; +} + +static const struct net_device_ops rmnet_vnd_ops = { + .ndo_start_xmit = rmnet_vnd_start_xmit, + .ndo_change_mtu = rmnet_vnd_change_mtu, + .ndo_get_iflink = rmnet_vnd_get_iflink, +}; + +/* Called by kernel whenever a new rmnet<n> device is created. Sets MTU, + * flags, ARP type, needed headroom, etc... + */ +void rmnet_vnd_setup(struct net_device *rmnet_dev) +{ + rmnet_dev->netdev_ops = &rmnet_vnd_ops; + rmnet_dev->mtu = RMNET_DFLT_PACKET_SIZE; + rmnet_dev->needed_headroom = RMNET_NEEDED_HEADROOM; + random_ether_addr(rmnet_dev->dev_addr); + rmnet_dev->tx_queue_len = RMNET_TX_QUEUE_LEN; + + /* Raw IP mode */ + rmnet_dev->header_ops = NULL; /* No header */ + rmnet_dev->type = ARPHRD_RAWIP; + rmnet_dev->hard_header_len = 0; + rmnet_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); + + rmnet_dev->needs_free_netdev = true; +} + +/* Exposed API */ + +int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, + struct rmnet_port *port, + struct net_device *real_dev) +{ + struct rmnet_priv *priv; + int rc; + + if (port->rmnet_devices[id]) + return -EINVAL; + + rc = register_netdevice(rmnet_dev); + if (!rc) { + port->rmnet_devices[id] = rmnet_dev; + port->nr_rmnet_devs++; + + rmnet_dev->rtnl_link_ops = &rmnet_link_ops; + + priv = netdev_priv(rmnet_dev); + priv->mux_id = id; + priv->real_dev = real_dev; + + netdev_dbg(rmnet_dev, "rmnet dev created\n"); + } + + return rc; +} + +int rmnet_vnd_dellink(u8 id, struct rmnet_port *port) +{ + if (id >= RMNET_MAX_LOGICAL_EP || !port->rmnet_devices[id]) + return -EINVAL; + + port->rmnet_devices[id] = NULL; + port->nr_rmnet_devs--; + return 0; +} + +u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev) +{ + struct rmnet_priv *priv; + + priv = netdev_priv(rmnet_dev); + return priv->mux_id; +} + +/* Gets the logical endpoint configuration for a RmNet virtual network device + * node. Caller should confirm that devices is a RmNet VND before calling. + */ +struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *rmnet_dev) +{ + struct rmnet_priv *priv; + + if (!rmnet_dev) + return NULL; + + priv = netdev_priv(rmnet_dev); + + return &priv->local_ep; +} + +int rmnet_vnd_do_flow_control(struct net_device *rmnet_dev, int enable) +{ + netdev_dbg(rmnet_dev, "Setting VND TX queue state to %d\n", enable); + /* Although we expect similar number of enable/disable + * commands, optimize for the disable. That is more + * latency sensitive than enable + */ + if (unlikely(enable)) + netif_wake_queue(rmnet_dev); + else + netif_stop_queue(rmnet_dev); + + return 0; +} diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h new file mode 100644 index 000000000000..8a4042f0f6bf --- /dev/null +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.h @@ -0,0 +1,29 @@ +/* Copyright (c) 2013-2017, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * RMNET Data Virtual Network Device APIs + * + */ + +#ifndef _RMNET_VND_H_ +#define _RMNET_VND_H_ + +int rmnet_vnd_do_flow_control(struct net_device *dev, int enable); +struct rmnet_endpoint *rmnet_vnd_get_endpoint(struct net_device *dev); +int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, + struct rmnet_port *port, + struct net_device *real_dev); +int rmnet_vnd_dellink(u8 id, struct rmnet_port *port); +void rmnet_vnd_rx_fixup(struct sk_buff *skb, struct net_device *dev); +void rmnet_vnd_tx_fixup(struct sk_buff *skb, struct net_device *dev); +u8 rmnet_vnd_get_mux(struct net_device *rmnet_dev); +void rmnet_vnd_setup(struct net_device *dev); +#endif /* _RMNET_VND_H_ */ diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 0525bd696d5d..96a27b00c90e 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -991,6 +991,7 @@ struct ravb_private { struct net_device *ndev; struct platform_device *pdev; void __iomem *addr; + struct clk *clk; struct mdiobb_ctrl mdiobb; u32 num_rx_ring[NUM_RX_QUEUE]; u32 num_tx_ring[NUM_TX_QUEUE]; @@ -1033,6 +1034,7 @@ struct ravb_private { unsigned no_avb_link:1; unsigned avb_link_active_low:1; + unsigned wol_enabled:1; }; static inline u32 ravb_read(struct net_device *ndev, enum ravb_reg reg) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 5931e859876c..fdf30bfa403b 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -680,6 +680,9 @@ static void ravb_emac_interrupt_unlocked(struct net_device *ndev) ecsr = ravb_read(ndev, ECSR); ravb_write(ndev, ecsr, ECSR); /* clear interrupt */ + + if (ecsr & ECSR_MPD) + pm_wakeup_event(&priv->pdev->dev, 0); if (ecsr & ECSR_ICD) ndev->stats.tx_carrier_errors++; if (ecsr & ECSR_LCHNG) { @@ -1330,6 +1333,33 @@ static int ravb_get_ts_info(struct net_device *ndev, return 0; } +static void ravb_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) +{ + struct ravb_private *priv = netdev_priv(ndev); + + wol->supported = 0; + wol->wolopts = 0; + + if (priv->clk) { + wol->supported = WAKE_MAGIC; + wol->wolopts = priv->wol_enabled ? WAKE_MAGIC : 0; + } +} + +static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) +{ + struct ravb_private *priv = netdev_priv(ndev); + + if (!priv->clk || wol->wolopts & ~WAKE_MAGIC) + return -EOPNOTSUPP; + + priv->wol_enabled = !!(wol->wolopts & WAKE_MAGIC); + + device_set_wakeup_enable(&priv->pdev->dev, priv->wol_enabled); + + return 0; +} + static const struct ethtool_ops ravb_ethtool_ops = { .nway_reset = ravb_nway_reset, .get_msglevel = ravb_get_msglevel, @@ -1343,6 +1373,8 @@ static const struct ethtool_ops ravb_ethtool_ops = { .get_ts_info = ravb_get_ts_info, .get_link_ksettings = ravb_get_link_ksettings, .set_link_ksettings = ravb_set_link_ksettings, + .get_wol = ravb_get_wol, + .set_wol = ravb_set_wol, }; static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler, @@ -2041,6 +2073,11 @@ static int ravb_probe(struct platform_device *pdev) priv->chip_id = chip_id; + /* Get clock, if not found that's OK but Wake-On-Lan is unavailable */ + priv->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(priv->clk)) + priv->clk = NULL; + /* Set function */ ndev->netdev_ops = &ravb_netdev_ops; ndev->ethtool_ops = &ravb_ethtool_ops; @@ -2107,6 +2144,9 @@ static int ravb_probe(struct platform_device *pdev) if (error) goto out_napi_del; + if (priv->clk) + device_set_wakeup_capable(&pdev->dev, 1); + /* Print device information */ netdev_info(ndev, "Base address at %#x, %pM, IRQ %d.\n", (u32)ndev->base_addr, ndev->dev_addr, ndev->irq); @@ -2160,15 +2200,66 @@ static int ravb_remove(struct platform_device *pdev) return 0; } +static int ravb_wol_setup(struct net_device *ndev) +{ + struct ravb_private *priv = netdev_priv(ndev); + + /* Disable interrupts by clearing the interrupt masks. */ + ravb_write(ndev, 0, RIC0); + ravb_write(ndev, 0, RIC2); + ravb_write(ndev, 0, TIC); + + /* Only allow ECI interrupts */ + synchronize_irq(priv->emac_irq); + napi_disable(&priv->napi[RAVB_NC]); + napi_disable(&priv->napi[RAVB_BE]); + ravb_write(ndev, ECSIPR_MPDIP, ECSIPR); + + /* Enable MagicPacket */ + ravb_modify(ndev, ECMR, ECMR_MPDE, ECMR_MPDE); + + /* Increased clock usage so device won't be suspended */ + clk_enable(priv->clk); + + return enable_irq_wake(priv->emac_irq); +} + +static int ravb_wol_restore(struct net_device *ndev) +{ + struct ravb_private *priv = netdev_priv(ndev); + int ret; + + napi_enable(&priv->napi[RAVB_NC]); + napi_enable(&priv->napi[RAVB_BE]); + + /* Disable MagicPacket */ + ravb_modify(ndev, ECMR, ECMR_MPDE, 0); + + ret = ravb_close(ndev); + if (ret < 0) + return ret; + + /* Restore clock usage count */ + clk_disable(priv->clk); + + return disable_irq_wake(priv->emac_irq); +} + static int __maybe_unused ravb_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); - int ret = 0; + struct ravb_private *priv = netdev_priv(ndev); + int ret; - if (netif_running(ndev)) { - netif_device_detach(ndev); + if (!netif_running(ndev)) + return 0; + + netif_device_detach(ndev); + + if (priv->wol_enabled) + ret = ravb_wol_setup(ndev); + else ret = ravb_close(ndev); - } return ret; } @@ -2179,6 +2270,33 @@ static int __maybe_unused ravb_resume(struct device *dev) struct ravb_private *priv = netdev_priv(ndev); int ret = 0; + if (priv->wol_enabled) { + /* Reduce the usecount of the clock to zero and then + * restore it to its original value. This is done to force + * the clock to be re-enabled which is a workaround + * for renesas-cpg-mssr driver which do not enable clocks + * when resuming from PSCI suspend/resume. + * + * Without this workaround the driver fails to communicate + * with the hardware if WoL was enabled when the system + * entered PSCI suspend. This is due to that if WoL is enabled + * we explicitly keep the clock from being turned off when + * suspending, but in PSCI sleep power is cut so the clock + * is disabled anyhow, the clock driver is not aware of this + * so the clock is not turned back on when resuming. + * + * TODO: once the renesas-cpg-mssr suspend/resume is working + * this clock dance should be removed. + */ + clk_disable(priv->clk); + clk_disable(priv->clk); + clk_enable(priv->clk); + clk_enable(priv->clk); + + /* Set reset mode to rearm the WoL logic */ + ravb_write(ndev, CCC_OPC_RESET, CCC); + } + /* All register have been reset to default values. * Restore all registers which where setup at probe time and * reopen device if it was running before system suspended. @@ -2202,6 +2320,11 @@ static int __maybe_unused ravb_resume(struct device *dev) ravb_write(ndev, priv->desc_bat_dma, DBAT); if (netif_running(ndev)) { + if (priv->wol_enabled) { + ret = ravb_wol_restore(ndev); + if (ret) + return ret; + } ret = ravb_open(ndev); if (ret < 0) return ret; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index d2dc0a8ef305..d2e88a30f57b 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3402,7 +3402,7 @@ static const struct dev_pm_ops sh_eth_dev_pm_ops = { #define SH_ETH_PM_OPS NULL #endif -static struct platform_device_id sh_eth_id_table[] = { +static const struct platform_device_id sh_eth_id_table[] = { { "sh7619-ether", (kernel_ulong_t)&sh7619_data }, { "sh771x-ether", (kernel_ulong_t)&sh771x_data }, { "sh7724-ether", (kernel_ulong_t)&sh7724_data }, diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index b1e5c07099fa..fc8f8bdf6579 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -34,6 +34,7 @@ #include <net/netevent.h> #include <net/arp.h> #include <net/fib_rules.h> +#include <net/fib_notifier.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <generated/utsrelease.h> @@ -2191,6 +2192,10 @@ static int rocker_router_fib_event(struct notifier_block *nb, { struct rocker *rocker = container_of(nb, struct rocker, fib_nb); struct rocker_fib_event_work *fib_work; + struct fib_notifier_info *info = ptr; + + if (info->family != AF_INET) + return NOTIFY_DONE; fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC); if (WARN_ON(!fib_work)) diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index 600e30e8f0be..0653b70723a3 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -1177,7 +1177,7 @@ static int ofdpa_group_l2_fan_out(struct ofdpa_port *ofdpa_port, entry->group_id = group_id; entry->group_count = group_count; - entry->group_ids = kcalloc(flags, group_count, sizeof(u32)); + entry->group_ids = kcalloc(group_count, sizeof(u32), GFP_KERNEL); if (!entry->group_ids) { kfree(entry); return -ENOMEM; @@ -1456,7 +1456,7 @@ static int ofdpa_port_vlan_flood_group(struct ofdpa_port *ofdpa_port, int err = 0; int i; - group_ids = kcalloc(flags, port_count, sizeof(u32)); + group_ids = kcalloc(port_count, sizeof(u32), GFP_KERNEL); if (!group_ids) return -ENOMEM; @@ -2761,7 +2761,7 @@ static int ofdpa_fib4_add(struct rocker *rocker, fen_info->tb_id, 0); if (err) return err; - fib_info_offload_inc(fen_info->fi); + fen_info->fi->fib_nh->nh_flags |= RTNH_F_OFFLOAD; return 0; } @@ -2776,7 +2776,7 @@ static int ofdpa_fib4_del(struct rocker *rocker, ofdpa_port = ofdpa_port_dev_lower_find(fen_info->fi->fib_dev, rocker); if (!ofdpa_port) return 0; - fib_info_offload_dec(fen_info->fi); + fen_info->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD; return ofdpa_port_fib_ipv4(ofdpa_port, htonl(fen_info->dst), fen_info->dst_len, fen_info->fi, fen_info->tb_id, OFDPA_OP_FLAG_REMOVE); @@ -2803,7 +2803,7 @@ static void ofdpa_fib4_abort(struct rocker *rocker) rocker); if (!ofdpa_port) continue; - fib_info_offload_dec(flow_entry->fi); + flow_entry->fi->fib_nh->nh_flags &= ~RTNH_F_OFFLOAD; ofdpa_flow_tbl_del(ofdpa_port, OFDPA_OP_FLAG_REMOVE, flow_entry); } diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index fcea9371ab7f..d407adf59610 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -32,8 +32,8 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); -int efx_setup_tc(struct net_device *net_dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc); +int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type, + void *type_data); unsigned int efx_tx_max_skb_descs(struct efx_nic *efx); extern unsigned int efx_piobuf_size; extern bool efx_separate_tx_channels; diff --git a/drivers/net/ethernet/sfc/falcon/efx.h b/drivers/net/ethernet/sfc/falcon/efx.h index e5a7a40cc8b6..4f3bb30661ea 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.h +++ b/drivers/net/ethernet/sfc/falcon/efx.h @@ -32,8 +32,8 @@ netdev_tx_t ef4_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); netdev_tx_t ef4_enqueue_skb(struct ef4_tx_queue *tx_queue, struct sk_buff *skb); void ef4_xmit_done(struct ef4_tx_queue *tx_queue, unsigned int index); -int ef4_setup_tc(struct net_device *net_dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc); +int ef4_setup_tc(struct net_device *net_dev, enum tc_setup_type type, + void *type_data); unsigned int ef4_tx_max_skb_descs(struct ef4_nic *efx); extern bool ef4_separate_tx_channels; diff --git a/drivers/net/ethernet/sfc/falcon/tx.c b/drivers/net/ethernet/sfc/falcon/tx.c index f1520a404ac6..6a75f4140a4b 100644 --- a/drivers/net/ethernet/sfc/falcon/tx.c +++ b/drivers/net/ethernet/sfc/falcon/tx.c @@ -425,24 +425,25 @@ void ef4_init_tx_queue_core_txq(struct ef4_tx_queue *tx_queue) efx->n_tx_channels : 0)); } -int ef4_setup_tc(struct net_device *net_dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *ntc) +int ef4_setup_tc(struct net_device *net_dev, enum tc_setup_type type, + void *type_data) { struct ef4_nic *efx = netdev_priv(net_dev); + struct tc_mqprio_qopt *mqprio = type_data; struct ef4_channel *channel; struct ef4_tx_queue *tx_queue; unsigned tc, num_tc; int rc; - if (ntc->type != TC_SETUP_MQPRIO) - return -EINVAL; + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - num_tc = ntc->mqprio->num_tc; + num_tc = mqprio->num_tc; if (ef4_nic_rev(efx) < EF4_REV_FALCON_B0 || num_tc > EF4_MAX_TX_TC) return -EINVAL; - ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; if (num_tc == net_dev->num_tc) return 0; diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c index 990a63d7fcb7..c7407d129c7d 100644 --- a/drivers/net/ethernet/sfc/mcdi_port.c +++ b/drivers/net/ethernet/sfc/mcdi_port.c @@ -746,59 +746,171 @@ static const char *efx_mcdi_phy_test_name(struct efx_nic *efx, return NULL; } -#define SFP_PAGE_SIZE 128 -#define SFP_NUM_PAGES 2 -static int efx_mcdi_phy_get_module_eeprom(struct efx_nic *efx, - struct ethtool_eeprom *ee, u8 *data) +#define SFP_PAGE_SIZE 128 +#define SFF_DIAG_TYPE_OFFSET 92 +#define SFF_DIAG_ADDR_CHANGE BIT(2) +#define SFF_8079_NUM_PAGES 2 +#define SFF_8472_NUM_PAGES 4 +#define SFF_8436_NUM_PAGES 5 +#define SFF_DMT_LEVEL_OFFSET 94 + +/** efx_mcdi_phy_get_module_eeprom_page() - Get a single page of module eeprom + * @efx: NIC context + * @page: EEPROM page number + * @data: Destination data pointer + * @offset: Offset in page to copy from in to data + * @space: Space available in data + * + * Return: + * >=0 - amount of data copied + * <0 - error + */ +static int efx_mcdi_phy_get_module_eeprom_page(struct efx_nic *efx, + unsigned int page, + u8 *data, ssize_t offset, + ssize_t space) { MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX); MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_PHY_MEDIA_INFO_IN_LEN); size_t outlen; - int rc; unsigned int payload_len; - unsigned int space_remaining = ee->len; - unsigned int page; - unsigned int page_off; unsigned int to_copy; - u8 *user_data = data; + int rc; - BUILD_BUG_ON(SFP_PAGE_SIZE * SFP_NUM_PAGES != ETH_MODULE_SFF_8079_LEN); + if (offset > SFP_PAGE_SIZE) + return -EINVAL; - page_off = ee->offset % SFP_PAGE_SIZE; - page = ee->offset / SFP_PAGE_SIZE; + to_copy = min(space, SFP_PAGE_SIZE - offset); - while (space_remaining && (page < SFP_NUM_PAGES)) { - MCDI_SET_DWORD(inbuf, GET_PHY_MEDIA_INFO_IN_PAGE, page); + MCDI_SET_DWORD(inbuf, GET_PHY_MEDIA_INFO_IN_PAGE, page); + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_PHY_MEDIA_INFO, + inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), + &outlen); - rc = efx_mcdi_rpc(efx, MC_CMD_GET_PHY_MEDIA_INFO, - inbuf, sizeof(inbuf), - outbuf, sizeof(outbuf), - &outlen); - if (rc) - return rc; + if (rc) + return rc; + + if (outlen < (MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST + + SFP_PAGE_SIZE)) + return -EIO; + + payload_len = MCDI_DWORD(outbuf, GET_PHY_MEDIA_INFO_OUT_DATALEN); + if (payload_len != SFP_PAGE_SIZE) + return -EIO; - if (outlen < (MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST + - SFP_PAGE_SIZE)) - return -EIO; + memcpy(data, MCDI_PTR(outbuf, GET_PHY_MEDIA_INFO_OUT_DATA) + offset, + to_copy); - payload_len = MCDI_DWORD(outbuf, - GET_PHY_MEDIA_INFO_OUT_DATALEN); - if (payload_len != SFP_PAGE_SIZE) - return -EIO; + return to_copy; +} - /* Copy as much as we can into data */ - payload_len -= page_off; - to_copy = (space_remaining < payload_len) ? - space_remaining : payload_len; +static int efx_mcdi_phy_get_module_eeprom_byte(struct efx_nic *efx, + unsigned int page, + u8 byte) +{ + int rc; + u8 data; - memcpy(user_data, - MCDI_PTR(outbuf, GET_PHY_MEDIA_INFO_OUT_DATA) + page_off, - to_copy); + rc = efx_mcdi_phy_get_module_eeprom_page(efx, page, &data, byte, 1); + if (rc == 1) + return data; + + return rc; +} + +static int efx_mcdi_phy_diag_type(struct efx_nic *efx) +{ + /* Page zero of the EEPROM includes the diagnostic type at byte 92. */ + return efx_mcdi_phy_get_module_eeprom_byte(efx, 0, + SFF_DIAG_TYPE_OFFSET); +} - space_remaining -= to_copy; - user_data += to_copy; - page_off = 0; - page++; +static int efx_mcdi_phy_sff_8472_level(struct efx_nic *efx) +{ + /* Page zero of the EEPROM includes the DMT level at byte 94. */ + return efx_mcdi_phy_get_module_eeprom_byte(efx, 0, + SFF_DMT_LEVEL_OFFSET); +} + +static u32 efx_mcdi_phy_module_type(struct efx_nic *efx) +{ + struct efx_mcdi_phy_data *phy_data = efx->phy_data; + + if (phy_data->media != MC_CMD_MEDIA_QSFP_PLUS) + return phy_data->media; + + /* A QSFP+ NIC may actually have an SFP+ module attached. + * The ID is page 0, byte 0. + */ + switch (efx_mcdi_phy_get_module_eeprom_byte(efx, 0, 0)) { + case 0x3: + return MC_CMD_MEDIA_SFP_PLUS; + case 0xc: + case 0xd: + return MC_CMD_MEDIA_QSFP_PLUS; + default: + return 0; + } +} + +static int efx_mcdi_phy_get_module_eeprom(struct efx_nic *efx, + struct ethtool_eeprom *ee, u8 *data) +{ + int rc; + ssize_t space_remaining = ee->len; + unsigned int page_off; + bool ignore_missing; + int num_pages; + int page; + + switch (efx_mcdi_phy_module_type(efx)) { + case MC_CMD_MEDIA_SFP_PLUS: + num_pages = efx_mcdi_phy_sff_8472_level(efx) > 0 ? + SFF_8472_NUM_PAGES : SFF_8079_NUM_PAGES; + page = 0; + ignore_missing = false; + break; + case MC_CMD_MEDIA_QSFP_PLUS: + num_pages = SFF_8436_NUM_PAGES; + page = -1; /* We obtain the lower page by asking for -1. */ + ignore_missing = true; /* Ignore missing pages after page 0. */ + break; + default: + return -EOPNOTSUPP; + } + + page_off = ee->offset % SFP_PAGE_SIZE; + page += ee->offset / SFP_PAGE_SIZE; + + while (space_remaining && (page < num_pages)) { + rc = efx_mcdi_phy_get_module_eeprom_page(efx, page, + data, page_off, + space_remaining); + + if (rc > 0) { + space_remaining -= rc; + data += rc; + page_off = 0; + page++; + } else if (rc == 0) { + space_remaining = 0; + } else if (ignore_missing && (page > 0)) { + int intended_size = SFP_PAGE_SIZE - page_off; + + space_remaining -= intended_size; + if (space_remaining < 0) { + space_remaining = 0; + } else { + memset(data, 0, intended_size); + data += intended_size; + page_off = 0; + page++; + rc = 0; + } + } else { + return rc; + } } return 0; @@ -807,16 +919,42 @@ static int efx_mcdi_phy_get_module_eeprom(struct efx_nic *efx, static int efx_mcdi_phy_get_module_info(struct efx_nic *efx, struct ethtool_modinfo *modinfo) { - struct efx_mcdi_phy_data *phy_cfg = efx->phy_data; + int sff_8472_level; + int diag_type; - switch (phy_cfg->media) { + switch (efx_mcdi_phy_module_type(efx)) { case MC_CMD_MEDIA_SFP_PLUS: - modinfo->type = ETH_MODULE_SFF_8079; - modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; - return 0; + sff_8472_level = efx_mcdi_phy_sff_8472_level(efx); + + /* If we can't read the diagnostics level we have none. */ + if (sff_8472_level < 0) + return -EOPNOTSUPP; + + /* Check if this module requires the (unsupported) address + * change operation. + */ + diag_type = efx_mcdi_phy_diag_type(efx); + + if ((sff_8472_level == 0) || + (diag_type & SFF_DIAG_ADDR_CHANGE)) { + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else { + modinfo->type = ETH_MODULE_SFF_8472; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + } + break; + + case MC_CMD_MEDIA_QSFP_PLUS: + modinfo->type = ETH_MODULE_SFF_8436; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + break; + default: return -EOPNOTSUPP; } + + return 0; } static const struct efx_phy_operations efx_mcdi_phy_ops = { diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 02d41eb4a8e9..32bf1fecf864 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -653,24 +653,25 @@ void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue) efx->n_tx_channels : 0)); } -int efx_setup_tc(struct net_device *net_dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *ntc) +int efx_setup_tc(struct net_device *net_dev, enum tc_setup_type type, + void *type_data) { struct efx_nic *efx = netdev_priv(net_dev); + struct tc_mqprio_qopt *mqprio = type_data; struct efx_channel *channel; struct efx_tx_queue *tx_queue; unsigned tc, num_tc; int rc; - if (ntc->type != TC_SETUP_MQPRIO) - return -EINVAL; + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - num_tc = ntc->mqprio->num_tc; + num_tc = mqprio->num_tc; if (num_tc > EFX_MAX_TX_TC) return -EINVAL; - ntc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; if (num_tc == net_dev->num_tc) return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 85c0e41f8021..97035766c291 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -45,6 +45,15 @@ config DWMAC_GENERIC platform specific code to function or is using platform data for setup. +config DWMAC_ANARION + tristate "Adaptrum Anarion GMAC support" + default ARC + depends on OF && (ARC || COMPILE_TEST) + help + Support for Adaptrum Anarion GMAC Ethernet controller. + + This selects the Anarion SoC glue layer support for the stmmac driver. + config DWMAC_IPQ806X tristate "QCA IPQ806x DWMAC support" default ARCH_QCOM diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index fd4937a7fcab..238307fadcdb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -7,6 +7,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \ # Ordering matters. Generic driver must be last. obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o +obj-$(CONFIG_DWMAC_ANARION) += dwmac-anarion.o obj-$(CONFIG_DWMAC_IPQ806X) += dwmac-ipq806x.o obj-$(CONFIG_DWMAC_LPC18XX) += dwmac-lpc18xx.o obj-$(CONFIG_DWMAC_MESON) += dwmac-meson.o dwmac-meson8b.o diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c new file mode 100644 index 000000000000..85ce80c600c7 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c @@ -0,0 +1,152 @@ +/* + * Adaptrum Anarion DWMAC glue layer + * + * Copyright (C) 2017, Adaptrum, Inc. + * (Written by Alexandru Gagniuc <alex.g at adaptrum.com> for Adaptrum, Inc.) + * Licensed under the GPLv2 or (at your option) any later version. + */ + +#include <linux/io.h> +#include <linux/of.h> +#include <linux/of_net.h> +#include <linux/stmmac.h> + +#include "stmmac.h" +#include "stmmac_platform.h" + +#define GMAC_RESET_CONTROL_REG 0 +#define GMAC_SW_CONFIG_REG 4 +#define GMAC_CONFIG_INTF_SEL_MASK (0x7 << 0) +#define GMAC_CONFIG_INTF_RGMII (0x1 << 0) + +struct anarion_gmac { + uintptr_t ctl_block; + uint32_t phy_intf_sel; +}; + +static uint32_t gmac_read_reg(struct anarion_gmac *gmac, uint8_t reg) +{ + return readl((void *)(gmac->ctl_block + reg)); +}; + +static void gmac_write_reg(struct anarion_gmac *gmac, uint8_t reg, uint32_t val) +{ + writel(val, (void *)(gmac->ctl_block + reg)); +} + +static int anarion_gmac_init(struct platform_device *pdev, void *priv) +{ + uint32_t sw_config; + struct anarion_gmac *gmac = priv; + + /* Reset logic, configure interface mode, then release reset. SIMPLE! */ + gmac_write_reg(gmac, GMAC_RESET_CONTROL_REG, 1); + + sw_config = gmac_read_reg(gmac, GMAC_SW_CONFIG_REG); + sw_config &= ~GMAC_CONFIG_INTF_SEL_MASK; + sw_config |= (gmac->phy_intf_sel & GMAC_CONFIG_INTF_SEL_MASK); + gmac_write_reg(gmac, GMAC_SW_CONFIG_REG, sw_config); + + gmac_write_reg(gmac, GMAC_RESET_CONTROL_REG, 0); + + return 0; +} + +static void anarion_gmac_exit(struct platform_device *pdev, void *priv) +{ + struct anarion_gmac *gmac = priv; + + gmac_write_reg(gmac, GMAC_RESET_CONTROL_REG, 1); +} + +static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev) +{ + int phy_mode; + struct resource *res; + void __iomem *ctl_block; + struct anarion_gmac *gmac; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + ctl_block = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ctl_block)) { + dev_err(&pdev->dev, "Cannot get reset region (%ld)!\n", + PTR_ERR(ctl_block)); + return ctl_block; + } + + gmac = devm_kzalloc(&pdev->dev, sizeof(*gmac), GFP_KERNEL); + if (!gmac) + return ERR_PTR(-ENOMEM); + + gmac->ctl_block = (uintptr_t)ctl_block; + + phy_mode = of_get_phy_mode(pdev->dev.of_node); + switch (phy_mode) { + case PHY_INTERFACE_MODE_RGMII: /* Fall through */ + case PHY_INTERFACE_MODE_RGMII_ID /* Fall through */: + case PHY_INTERFACE_MODE_RGMII_RXID: /* Fall through */ + case PHY_INTERFACE_MODE_RGMII_TXID: + gmac->phy_intf_sel = GMAC_CONFIG_INTF_RGMII; + break; + default: + dev_err(&pdev->dev, "Unsupported phy-mode (%d)\n", + phy_mode); + return ERR_PTR(-ENOTSUPP); + } + + return gmac; +} + +static int anarion_dwmac_probe(struct platform_device *pdev) +{ + int ret; + struct anarion_gmac *gmac; + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; + + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return ret; + + gmac = anarion_config_dt(pdev); + if (IS_ERR(gmac)) + return PTR_ERR(gmac); + + plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac); + if (IS_ERR(plat_dat)) + return PTR_ERR(plat_dat); + + plat_dat->init = anarion_gmac_init; + plat_dat->exit = anarion_gmac_exit; + anarion_gmac_init(pdev, gmac); + plat_dat->bsp_priv = gmac; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) { + stmmac_remove_config_dt(pdev, plat_dat); + return ret; + } + + return 0; +} + +static const struct of_device_id anarion_dwmac_match[] = { + { .compatible = "adaptrum,anarion-gmac" }, + { } +}; +MODULE_DEVICE_TABLE(of, anarion_dwmac_match); + +static struct platform_driver anarion_dwmac_driver = { + .probe = anarion_dwmac_probe, + .remove = stmmac_pltfr_remove, + .driver = { + .name = "anarion-dwmac", + .pm = &stmmac_pltfr_pm_ops, + .of_match_table = anarion_dwmac_match, + }, +}; +module_platform_driver(anarion_dwmac_driver); + +MODULE_DESCRIPTION("Adaptrum Anarion DWMAC specific glue layer"); +MODULE_AUTHOR("Alexandru Gagniuc <mr.nuke.me@gmail.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 9685555932ea..4404650b32c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -89,7 +89,7 @@ static int meson8b_init_clk(struct meson8b_dwmac *dwmac) char clk_name[32]; const char *clk_div_parents[1]; const char *mux_parent_names[MUX_CLK_NUM_PARENTS]; - static struct clk_div_table clk_25m_div_table[] = { + static const struct clk_div_table clk_25m_div_table[] = { { .val = 0, .div = 5 }, { .val = 1, .div = 10 }, { /* sentinel */ }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index f0df5193f047..99823f54696a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -41,6 +41,7 @@ struct rk_gmac_ops { void (*set_to_rmii)(struct rk_priv_data *bsp_priv); void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed); void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed); + void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv); }; struct rk_priv_data { @@ -52,6 +53,7 @@ struct rk_priv_data { bool clk_enabled; bool clock_input; + bool integrated_phy; struct clk *clk_mac; struct clk *gmac_clkin; @@ -61,6 +63,9 @@ struct rk_priv_data { struct clk *clk_mac_refout; struct clk *aclk_mac; struct clk *pclk_mac; + struct clk *clk_phy; + + struct reset_control *phy_reset; int tx_delay; int rx_delay; @@ -81,6 +86,8 @@ struct rk_priv_data { #define RK3228_GRF_MAC_CON0 0x0900 #define RK3228_GRF_MAC_CON1 0x0904 +#define RK3228_GRF_CON_MUX 0x50 + /* RK3228_GRF_MAC_CON0 */ #define RK3228_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) #define RK3228_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) @@ -106,6 +113,9 @@ struct rk_priv_data { #define RK3228_GMAC_RXCLK_DLY_ENABLE GRF_BIT(1) #define RK3228_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(1) +/* RK3228_GRF_COM_MUX */ +#define RK3228_GRF_CON_MUX_GMAC_INTEGRATED_PHY GRF_BIT(15) + static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { @@ -186,11 +196,18 @@ static void rk3228_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) dev_err(dev, "unknown speed value for RMII! speed=%d", speed); } +static void rk3228_integrated_phy_powerup(struct rk_priv_data *priv) +{ + regmap_write(priv->grf, RK3228_GRF_CON_MUX, + RK3228_GRF_CON_MUX_GMAC_INTEGRATED_PHY); +} + static const struct rk_gmac_ops rk3228_ops = { .set_to_rgmii = rk3228_set_to_rgmii, .set_to_rmii = rk3228_set_to_rmii, .set_rgmii_speed = rk3228_set_rgmii_speed, .set_rmii_speed = rk3228_set_rmii_speed, + .integrated_phy_powerup = rk3228_integrated_phy_powerup, }; #define RK3288_GRF_SOC_CON1 0x0248 @@ -306,6 +323,8 @@ static const struct rk_gmac_ops rk3288_ops = { #define RK3328_GRF_MAC_CON0 0x0900 #define RK3328_GRF_MAC_CON1 0x0904 +#define RK3328_GRF_MAC_CON2 0x0908 +#define RK3328_GRF_MACPHY_CON1 0xb04 /* RK3328_GRF_MAC_CON0 */ #define RK3328_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) @@ -332,6 +351,9 @@ static const struct rk_gmac_ops rk3288_ops = { #define RK3328_GMAC_RXCLK_DLY_ENABLE GRF_BIT(1) #define RK3328_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(0) +/* RK3328_GRF_MACPHY_CON1 */ +#define RK3328_MACPHY_RMII_MODE GRF_BIT(9) + static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { @@ -356,18 +378,19 @@ static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3328_set_to_rmii(struct rk_priv_data *bsp_priv) { struct device *dev = &bsp_priv->pdev->dev; + unsigned int reg; if (IS_ERR(bsp_priv->grf)) { dev_err(dev, "Missing rockchip,grf property\n"); return; } - regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, + reg = bsp_priv->integrated_phy ? RK3328_GRF_MAC_CON2 : + RK3328_GRF_MAC_CON1; + + regmap_write(bsp_priv->grf, reg, RK3328_GMAC_PHY_INTF_SEL_RMII | RK3328_GMAC_RMII_MODE); - - /* set MAC to RMII mode */ - regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, GRF_BIT(11)); } static void rk3328_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) @@ -395,29 +418,40 @@ static void rk3328_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed) static void rk3328_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) { struct device *dev = &bsp_priv->pdev->dev; + unsigned int reg; if (IS_ERR(bsp_priv->grf)) { dev_err(dev, "Missing rockchip,grf property\n"); return; } + reg = bsp_priv->integrated_phy ? RK3328_GRF_MAC_CON2 : + RK3328_GRF_MAC_CON1; + if (speed == 10) - regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, + regmap_write(bsp_priv->grf, reg, RK3328_GMAC_RMII_CLK_2_5M | RK3328_GMAC_SPEED_10M); else if (speed == 100) - regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, + regmap_write(bsp_priv->grf, reg, RK3328_GMAC_RMII_CLK_25M | RK3328_GMAC_SPEED_100M); else dev_err(dev, "unknown speed value for RMII! speed=%d", speed); } +static void rk3328_integrated_phy_powerup(struct rk_priv_data *priv) +{ + regmap_write(priv->grf, RK3328_GRF_MACPHY_CON1, + RK3328_MACPHY_RMII_MODE); +} + static const struct rk_gmac_ops rk3328_ops = { .set_to_rgmii = rk3328_set_to_rgmii, .set_to_rmii = rk3328_set_to_rmii, .set_rgmii_speed = rk3328_set_rgmii_speed, .set_rmii_speed = rk3328_set_rmii_speed, + .integrated_phy_powerup = rk3328_integrated_phy_powerup, }; #define RK3366_GRF_SOC_CON6 0x0418 @@ -753,9 +787,107 @@ static const struct rk_gmac_ops rk3399_ops = { .set_rmii_speed = rk3399_set_rmii_speed, }; -static int gmac_clk_init(struct rk_priv_data *bsp_priv) +#define RV1108_GRF_GMAC_CON0 0X0900 + +/* RV1108_GRF_GMAC_CON0 */ +#define RV1108_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \ + GRF_BIT(6)) +#define RV1108_GMAC_FLOW_CTRL GRF_BIT(3) +#define RV1108_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) +#define RV1108_GMAC_SPEED_10M GRF_CLR_BIT(2) +#define RV1108_GMAC_SPEED_100M GRF_BIT(2) +#define RV1108_GMAC_RMII_CLK_25M GRF_BIT(7) +#define RV1108_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(7) + +static void rv1108_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "%s: Missing rockchip,grf property\n", __func__); + return; + } + + regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0, + RV1108_GMAC_PHY_INTF_SEL_RMII); +} + +static void rv1108_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "%s: Missing rockchip,grf property\n", __func__); + return; + } + + if (speed == 10) { + regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0, + RV1108_GMAC_RMII_CLK_2_5M | + RV1108_GMAC_SPEED_10M); + } else if (speed == 100) { + regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0, + RV1108_GMAC_RMII_CLK_25M | + RV1108_GMAC_SPEED_100M); + } else { + dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + } +} + +static const struct rk_gmac_ops rv1108_ops = { + .set_to_rmii = rv1108_set_to_rmii, + .set_rmii_speed = rv1108_set_rmii_speed, +}; + +#define RK_GRF_MACPHY_CON0 0xb00 +#define RK_GRF_MACPHY_CON1 0xb04 +#define RK_GRF_MACPHY_CON2 0xb08 +#define RK_GRF_MACPHY_CON3 0xb0c + +#define RK_MACPHY_ENABLE GRF_BIT(0) +#define RK_MACPHY_DISABLE GRF_CLR_BIT(0) +#define RK_MACPHY_CFG_CLK_50M GRF_BIT(14) +#define RK_GMAC2PHY_RMII_MODE (GRF_BIT(6) | GRF_CLR_BIT(7)) +#define RK_GRF_CON2_MACPHY_ID HIWORD_UPDATE(0x1234, 0xffff, 0) +#define RK_GRF_CON3_MACPHY_ID HIWORD_UPDATE(0x35, 0x3f, 0) + +static void rk_gmac_integrated_phy_powerup(struct rk_priv_data *priv) +{ + if (priv->ops->integrated_phy_powerup) + priv->ops->integrated_phy_powerup(priv); + + regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_CFG_CLK_50M); + regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_GMAC2PHY_RMII_MODE); + + regmap_write(priv->grf, RK_GRF_MACPHY_CON2, RK_GRF_CON2_MACPHY_ID); + regmap_write(priv->grf, RK_GRF_MACPHY_CON3, RK_GRF_CON3_MACPHY_ID); + + if (priv->phy_reset) { + /* PHY needs to be disabled before trying to reset it */ + regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE); + if (priv->phy_reset) + reset_control_assert(priv->phy_reset); + usleep_range(10, 20); + if (priv->phy_reset) + reset_control_deassert(priv->phy_reset); + usleep_range(10, 20); + regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_ENABLE); + msleep(30); + } +} + +static void rk_gmac_integrated_phy_powerdown(struct rk_priv_data *priv) +{ + regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE); + if (priv->phy_reset) + reset_control_assert(priv->phy_reset); +} + +static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat) { + struct rk_priv_data *bsp_priv = plat->bsp_priv; struct device *dev = &bsp_priv->pdev->dev; + int ret; bsp_priv->clk_enabled = false; @@ -806,6 +938,16 @@ static int gmac_clk_init(struct rk_priv_data *bsp_priv) clk_set_rate(bsp_priv->clk_mac, 50000000); } + if (plat->phy_node && bsp_priv->integrated_phy) { + bsp_priv->clk_phy = of_clk_get(plat->phy_node, 0); + if (IS_ERR(bsp_priv->clk_phy)) { + ret = PTR_ERR(bsp_priv->clk_phy); + dev_err(dev, "Cannot get PHY clock: %d\n", ret); + return -EINVAL; + } + clk_set_rate(bsp_priv->clk_phy, 50000000); + } + return 0; } @@ -829,6 +971,9 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable) bsp_priv->clk_mac_refout); } + if (!IS_ERR(bsp_priv->clk_phy)) + clk_prepare_enable(bsp_priv->clk_phy); + if (!IS_ERR(bsp_priv->aclk_mac)) clk_prepare_enable(bsp_priv->aclk_mac); @@ -861,6 +1006,9 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable) bsp_priv->clk_mac_refout); } + if (!IS_ERR(bsp_priv->clk_phy)) + clk_disable_unprepare(bsp_priv->clk_phy); + if (!IS_ERR(bsp_priv->aclk_mac)) clk_disable_unprepare(bsp_priv->aclk_mac); @@ -905,6 +1053,7 @@ static int phy_power_on(struct rk_priv_data *bsp_priv, bool enable) } static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, + struct plat_stmmacenet_data *plat, const struct rk_gmac_ops *ops) { struct rk_priv_data *bsp_priv; @@ -967,9 +1116,22 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, bsp_priv->grf = syscon_regmap_lookup_by_phandle(dev->of_node, "rockchip,grf"); - bsp_priv->pdev = pdev; - gmac_clk_init(bsp_priv); + if (plat->phy_node) { + bsp_priv->integrated_phy = of_property_read_bool(plat->phy_node, + "phy-is-integrated"); + if (bsp_priv->integrated_phy) { + bsp_priv->phy_reset = of_reset_control_get(plat->phy_node, NULL); + if (IS_ERR(bsp_priv->phy_reset)) { + dev_err(&pdev->dev, "No PHY reset control found.\n"); + bsp_priv->phy_reset = NULL; + } + } + } + dev_info(dev, "integrated PHY? (%s).\n", + bsp_priv->integrated_phy ? "yes" : "no"); + + bsp_priv->pdev = pdev; return bsp_priv; } @@ -1017,6 +1179,9 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) pm_runtime_enable(dev); pm_runtime_get_sync(dev); + if (bsp_priv->integrated_phy) + rk_gmac_integrated_phy_powerup(bsp_priv); + return 0; } @@ -1024,6 +1189,9 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac) { struct device *dev = &gmac->pdev->dev; + if (gmac->integrated_phy) + rk_gmac_integrated_phy_powerdown(gmac); + pm_runtime_put_sync(dev); pm_runtime_disable(dev); @@ -1075,12 +1243,16 @@ static int rk_gmac_probe(struct platform_device *pdev) plat_dat->has_gmac = true; plat_dat->fix_mac_speed = rk_fix_speed; - plat_dat->bsp_priv = rk_gmac_setup(pdev, data); + plat_dat->bsp_priv = rk_gmac_setup(pdev, plat_dat, data); if (IS_ERR(plat_dat->bsp_priv)) { ret = PTR_ERR(plat_dat->bsp_priv); goto err_remove_config_dt; } + ret = rk_gmac_clk_init(plat_dat); + if (ret) + return ret; + ret = rk_gmac_powerup(plat_dat->bsp_priv); if (ret) goto err_remove_config_dt; @@ -1147,6 +1319,7 @@ static const struct of_device_id rk_gmac_dwmac_match[] = { { .compatible = "rockchip,rk3366-gmac", .data = &rk3366_ops }, { .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops }, { .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops }, + { .compatible = "rockchip,rv1108-gmac", .data = &rv1108_ops }, { } }; MODULE_DEVICE_TABLE(of, rk_gmac_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 72ec711fcba2..f5f37bfa1d58 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -248,9 +248,6 @@ int stmmac_mdio_register(struct net_device *ndev) found = 0; for (addr = 0; addr < PHY_MAX_ADDR; addr++) { struct phy_device *phydev = mdiobus_get_phy(new_bus, addr); - int act = 0; - char irq_num[4]; - char *irq_str; if (!phydev) continue; @@ -273,19 +270,6 @@ int stmmac_mdio_register(struct net_device *ndev) if (priv->plat->phy_addr == -1) priv->plat->phy_addr = addr; - act = (priv->plat->phy_addr == addr); - switch (phydev->irq) { - case PHY_POLL: - irq_str = "POLL"; - break; - case PHY_IGNORE_INTERRUPT: - irq_str = "IGNORE"; - break; - default: - sprintf(irq_num, "%d", phydev->irq); - irq_str = irq_num; - break; - } phy_attached_info(phydev); found = 1; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index d71bd80c5b5b..e471a903c654 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -152,7 +152,7 @@ static int stmmac_enable(struct ptp_clock_info *ptp, } /* structure describing a PTP hardware clock */ -static struct ptp_clock_info stmmac_ptp_clock_ops = { +static const struct ptp_clock_info stmmac_ptp_clock_ops = { .owner = THIS_MODULE, .name = "stmmac_ptp_clock", .max_adj = 62500000, diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index 8603e397097e..5b56c24b6ed2 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -248,7 +248,7 @@ static struct net_device *vsw_alloc_netdev(u8 hwaddr[], dev->ethtool_ops = &vsw_ethtool_ops; dev->watchdog_timeo = VSW_TX_TIMEOUT; - dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG; + dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG; dev->features = dev->hw_features; /* MTU range: 68 - 65535 */ diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 4bb04aaf9650..6a4e8e1bbd90 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9221,8 +9221,7 @@ static int niu_get_of_props(struct niu *np) phy_type = of_get_property(dp, "phy-type", &prop_len); if (!phy_type) { - netdev_err(dev, "%s: OF node lacks phy-type property\n", - dp->full_name); + netdev_err(dev, "%pOF: OF node lacks phy-type property\n", dp); return -EINVAL; } @@ -9232,26 +9231,25 @@ static int niu_get_of_props(struct niu *np) strcpy(np->vpd.phy_type, phy_type); if (niu_phy_type_prop_decode(np, np->vpd.phy_type)) { - netdev_err(dev, "%s: Illegal phy string [%s]\n", - dp->full_name, np->vpd.phy_type); + netdev_err(dev, "%pOF: Illegal phy string [%s]\n", + dp, np->vpd.phy_type); return -EINVAL; } mac_addr = of_get_property(dp, "local-mac-address", &prop_len); if (!mac_addr) { - netdev_err(dev, "%s: OF node lacks local-mac-address property\n", - dp->full_name); + netdev_err(dev, "%pOF: OF node lacks local-mac-address property\n", + dp); return -EINVAL; } if (prop_len != dev->addr_len) { - netdev_err(dev, "%s: OF MAC address prop len (%d) is wrong\n", - dp->full_name, prop_len); + netdev_err(dev, "%pOF: OF MAC address prop len (%d) is wrong\n", + dp, prop_len); } memcpy(dev->dev_addr, mac_addr, dev->addr_len); if (!is_valid_ether_addr(&dev->dev_addr[0])) { - netdev_err(dev, "%s: OF MAC address is invalid\n", - dp->full_name); - netdev_err(dev, "%s: [ %pM ]\n", dp->full_name, dev->dev_addr); + netdev_err(dev, "%pOF: OF MAC address is invalid\n", dp); + netdev_err(dev, "%pOF: [ %pM ]\n", dp, dev->dev_addr); return -EINVAL; } @@ -10027,8 +10025,8 @@ static int niu_of_probe(struct platform_device *op) reg = of_get_property(op->dev.of_node, "reg", NULL); if (!reg) { - dev_err(&op->dev, "%s: No 'reg' property, aborting\n", - op->dev.of_node->full_name); + dev_err(&op->dev, "%pOF: No 'reg' property, aborting\n", + op->dev.of_node); return -ENODEV; } diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 75b167e3fe98..0b95105f7060 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -312,7 +312,7 @@ static struct vnet *vnet_new(const u64 *local_mac, dev->watchdog_timeo = VNET_TX_TIMEOUT; dev->hw_features = NETIF_F_TSO | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | - NETIF_F_IP_CSUM | NETIF_F_SG; + NETIF_F_HW_CSUM | NETIF_F_SG; dev->features = dev->hw_features; /* MTU range: 68 - 65535 */ diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index 9e86833249d4..ecf456c7b6d1 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -303,7 +303,7 @@ static struct sk_buff *alloc_and_align_skb(struct net_device *dev, return skb; } -static inline void vnet_fullcsum(struct sk_buff *skb) +static inline void vnet_fullcsum_ipv4(struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); int offset = skb_transport_offset(skb); @@ -335,6 +335,40 @@ static inline void vnet_fullcsum(struct sk_buff *skb) } } +#if IS_ENABLED(CONFIG_IPV6) +static inline void vnet_fullcsum_ipv6(struct sk_buff *skb) +{ + struct ipv6hdr *ip6h = ipv6_hdr(skb); + int offset = skb_transport_offset(skb); + + if (skb->protocol != htons(ETH_P_IPV6)) + return; + if (ip6h->nexthdr != IPPROTO_TCP && + ip6h->nexthdr != IPPROTO_UDP) + return; + skb->ip_summed = CHECKSUM_NONE; + skb->csum_level = 1; + skb->csum = 0; + if (ip6h->nexthdr == IPPROTO_TCP) { + struct tcphdr *ptcp = tcp_hdr(skb); + + ptcp->check = 0; + skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + ptcp->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - offset, IPPROTO_TCP, + skb->csum); + } else if (ip6h->nexthdr == IPPROTO_UDP) { + struct udphdr *pudp = udp_hdr(skb); + + pudp->check = 0; + skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + pudp->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + skb->len - offset, IPPROTO_UDP, + skb->csum); + } +} +#endif + static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc) { struct net_device *dev = VNET_PORT_TO_NET_DEVICE(port); @@ -394,9 +428,14 @@ static int vnet_rx_one(struct vnet_port *port, struct vio_net_desc *desc) struct iphdr *iph = ip_hdr(skb); int ihl = iph->ihl * 4; - skb_reset_transport_header(skb); skb_set_transport_header(skb, ihl); - vnet_fullcsum(skb); + vnet_fullcsum_ipv4(skb); +#if IS_ENABLED(CONFIG_IPV6) + } else if (skb->protocol == htons(ETH_P_IPV6)) { + skb_set_transport_header(skb, + sizeof(struct ipv6hdr)); + vnet_fullcsum_ipv6(skb); +#endif } } if (dext->flags & VNET_PKT_HCK_IPV4_HDRCKSUM_OK) { @@ -1115,24 +1154,47 @@ static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies) if (skb->ip_summed == CHECKSUM_PARTIAL) start = skb_checksum_start_offset(skb); if (start) { - struct iphdr *iph = ip_hdr(nskb); int offset = start + nskb->csum_offset; + /* copy the headers, no csum here */ if (skb_copy_bits(skb, 0, nskb->data, start)) { dev_kfree_skb(nskb); dev_kfree_skb(skb); return NULL; } + + /* copy the rest, with csum calculation */ *(__sum16 *)(skb->data + offset) = 0; csum = skb_copy_and_csum_bits(skb, start, nskb->data + start, skb->len - start, 0); - if (iph->protocol == IPPROTO_TCP || - iph->protocol == IPPROTO_UDP) { - csum = csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - start, - iph->protocol, csum); + + /* add in the header checksums */ + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = ip_hdr(nskb); + + if (iph->protocol == IPPROTO_TCP || + iph->protocol == IPPROTO_UDP) { + csum = csum_tcpudp_magic(iph->saddr, + iph->daddr, + skb->len - start, + iph->protocol, + csum); + } + } else if (skb->protocol == htons(ETH_P_IPV6)) { + struct ipv6hdr *ip6h = ipv6_hdr(nskb); + + if (ip6h->nexthdr == IPPROTO_TCP || + ip6h->nexthdr == IPPROTO_UDP) { + csum = csum_ipv6_magic(&ip6h->saddr, + &ip6h->daddr, + skb->len - start, + ip6h->nexthdr, + csum); + } } + + /* save the final result */ *(__sum16 *)(nskb->data + offset) = csum; nskb->ip_summed = CHECKSUM_NONE; @@ -1318,8 +1380,14 @@ int sunvnet_start_xmit_common(struct sk_buff *skb, struct net_device *dev, if (unlikely(!skb)) goto out_dropped; - if (skb->ip_summed == CHECKSUM_PARTIAL) - vnet_fullcsum(skb); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (skb->protocol == htons(ETH_P_IP)) + vnet_fullcsum_ipv4(skb); +#if IS_ENABLED(CONFIG_IPV6) + else if (skb->protocol == htons(ETH_P_IPV6)) + vnet_fullcsum_ipv6(skb); +#endif + } dr = &port->vio.drings[VIO_DRIVER_TX_RING]; i = skb_get_queue_mapping(skb); diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c index 3b91257683bc..e1b55b8fb8e0 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c @@ -17,6 +17,7 @@ #include <linux/netdevice.h> #include <linux/tcp.h> +#include <linux/interrupt.h> #include "dwc-xlgmac.h" #include "dwc-xlgmac-reg.h" diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index badd0a8caeb9..db8a4bcfc6c7 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1321,8 +1321,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) phy = of_phy_connect(priv->ndev, slave->data->phy_node, &cpsw_adjust_link, 0, slave->data->phy_if); if (!phy) { - dev_err(priv->dev, "phy \"%s\" not found on slave %d\n", - slave->data->phy_node->full_name, + dev_err(priv->dev, "phy \"%pOF\" not found on slave %d\n", + slave->data->phy_node, slave->slave_num); return; } @@ -2670,8 +2670,8 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, parp = of_get_property(slave_node, "phy_id", &lenp); if (slave_data->phy_node) { dev_dbg(&pdev->dev, - "slave[%d] using phy-handle=\"%s\"\n", - i, slave_data->phy_node->full_name); + "slave[%d] using phy-handle=\"%pOF\"\n", + i, slave_data->phy_node); } else if (of_phy_is_fixed_link(slave_node)) { /* In the case of a fixed PHY, the DT node associated * to the PHY is the Ethernet MAC DT node. @@ -2827,7 +2827,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv) #define CPSW_QUIRK_IRQ BIT(0) -static struct platform_device_id cpsw_devtype[] = { +static const struct platform_device_id cpsw_devtype[] = { { /* keep it for existing comaptibles */ .name = "cpsw", diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index c2121d214f08..e7b76f6b4f67 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -298,7 +298,7 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp) return (long)delay; } -static struct ptp_clock_info cpts_info = { +static const struct ptp_clock_info cpts_info = { .owner = THIS_MODULE, .name = "CTPS timer", .max_adj = 1000000, diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 64d5527feb2a..4bb561856af5 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1480,8 +1480,8 @@ static int emac_dev_open(struct net_device *ndev) phydev = of_phy_connect(ndev, priv->phy_node, &emac_adjust_link, 0, 0); if (!phydev) { - dev_err(emac_dev, "could not connect to phy %s\n", - priv->phy_node->full_name); + dev_err(emac_dev, "could not connect to phy %pOF\n", + priv->phy_node); ret = -ENODEV; goto err; } diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c index 33df340db1f1..3c33f4504d8e 100644 --- a/drivers/net/ethernet/ti/davinci_mdio.c +++ b/drivers/net/ethernet/ti/davinci_mdio.c @@ -159,8 +159,10 @@ static int davinci_mdio_reset(struct mii_bus *bus) /* dump hardware version info */ ver = __raw_readl(&data->regs->version); - dev_info(data->dev, "davinci mdio revision %d.%d\n", - (ver >> 8) & 0xff, ver & 0xff); + dev_info(data->dev, + "davinci mdio revision %d.%d, bus freq %ld\n", + (ver >> 8) & 0xff, ver & 0xff, + data->pdata.bus_freq); if (data->skip_scan) goto done; @@ -198,8 +200,10 @@ static inline int wait_for_user_access(struct davinci_mdio_data *data) return 0; reg = __raw_readl(®s->control); - if ((reg & CONTROL_IDLE) == 0) + if ((reg & CONTROL_IDLE) == 0) { + usleep_range(100, 200); continue; + } /* * An emac soft_reset may have clobbered the mdio controller's diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 9d52c3a78621..eb96a6913235 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1877,20 +1877,21 @@ static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb, return 0; } -static int netcp_setup_tc(struct net_device *dev, u32 handle, u32 chain_index, - __be16 proto, struct tc_to_netdev *tc) +static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { + struct tc_mqprio_qopt *mqprio = type_data; u8 num_tc; int i; /* setup tc must be called under rtnl lock */ ASSERT_RTNL(); - if (tc->type != TC_SETUP_MQPRIO) - return -EINVAL; + if (type != TC_SETUP_MQPRIO) + return -EOPNOTSUPP; - tc->mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - num_tc = tc->mqprio->num_tc; + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + num_tc = mqprio->num_tc; /* Sanity-check the number of traffic classes requested */ if ((dev->real_num_tx_queues <= 1) || diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index aec95382ea5c..c00102b8145a 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -873,7 +873,7 @@ static int ptp_mpipe_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } -static struct ptp_clock_info ptp_mpipe_caps = { +static const struct ptp_clock_info ptp_mpipe_caps = { .owner = THIS_MODULE, .name = "mPIPE clock", .max_adj = 999999999, diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index d73da8afe08e..60abc9250f56 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1089,7 +1089,7 @@ static int temac_of_probe(struct platform_device *op) lp->phy_node = of_parse_phandle(op->dev.of_node, "phy-handle", 0); if (lp->phy_node) - dev_dbg(lp->dev, "using PHY node %s (%p)\n", np->full_name, np); + dev_dbg(lp->dev, "using PHY node %pOF (%p)\n", np, np); /* Add the device attributes */ rc = sysfs_create_group(&lp->dev->kobj, &temac_attr_group); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index af27f7d1cbf3..5ef626331f85 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -389,7 +389,7 @@ struct axidma_bd { * @dma_err_tasklet: Tasklet structure to process Axi DMA errors * @tx_irq: Axidma TX IRQ number * @rx_irq: Axidma RX IRQ number - * @phy_type: Phy type to identify between MII/GMII/RGMII/SGMII/1000 Base-X + * @phy_mode: Phy type to identify between MII/GMII/RGMII/SGMII/1000 Base-X * @options: AxiEthernet option word * @last_link: Phy link state in which the PHY was negotiated earlier * @features: Stores the extended features supported by the axienet hw @@ -432,7 +432,7 @@ struct axienet_local { int tx_irq; int rx_irq; - u32 phy_type; + phy_interface_t phy_mode; u32 options; /* Current options word */ u32 last_link; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 33c595f4691d..e74e1e897864 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -531,11 +531,11 @@ static void axienet_adjust_link(struct net_device *ndev) link_state = phy->speed | (phy->duplex << 1) | phy->link; if (lp->last_link != link_state) { if ((phy->speed == SPEED_10) || (phy->speed == SPEED_100)) { - if (lp->phy_type == XAE_PHY_TYPE_1000BASE_X) + if (lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) setspeed = 0; } else { if ((phy->speed == SPEED_1000) && - (lp->phy_type == XAE_PHY_TYPE_MII)) + (lp->phy_mode == PHY_INTERFACE_MODE_MII)) setspeed = 0; } @@ -935,15 +935,8 @@ static int axienet_open(struct net_device *ndev) return ret; if (lp->phy_node) { - if (lp->phy_type == XAE_PHY_TYPE_GMII) { - phydev = of_phy_connect(lp->ndev, lp->phy_node, - axienet_adjust_link, 0, - PHY_INTERFACE_MODE_GMII); - } else if (lp->phy_type == XAE_PHY_TYPE_RGMII_2_0) { - phydev = of_phy_connect(lp->ndev, lp->phy_node, - axienet_adjust_link, 0, - PHY_INTERFACE_MODE_RGMII_ID); - } + phydev = of_phy_connect(lp->ndev, lp->phy_node, + axienet_adjust_link, 0, lp->phy_mode); if (!phydev) dev_err(lp->dev, "of_phy_connect() failed\n"); @@ -1539,7 +1532,38 @@ static int axienet_probe(struct platform_device *pdev) * the device-tree and accordingly set flags. */ of_property_read_u32(pdev->dev.of_node, "xlnx,rxmem", &lp->rxmem); - of_property_read_u32(pdev->dev.of_node, "xlnx,phy-type", &lp->phy_type); + + /* Start with the proprietary, and broken phy_type */ + ret = of_property_read_u32(pdev->dev.of_node, "xlnx,phy-type", &value); + if (!ret) { + netdev_warn(ndev, "Please upgrade your device tree binary blob to use phy-mode"); + switch (value) { + case XAE_PHY_TYPE_MII: + lp->phy_mode = PHY_INTERFACE_MODE_MII; + break; + case XAE_PHY_TYPE_GMII: + lp->phy_mode = PHY_INTERFACE_MODE_GMII; + break; + case XAE_PHY_TYPE_RGMII_2_0: + lp->phy_mode = PHY_INTERFACE_MODE_RGMII_ID; + break; + case XAE_PHY_TYPE_SGMII: + lp->phy_mode = PHY_INTERFACE_MODE_SGMII; + break; + case XAE_PHY_TYPE_1000BASE_X: + lp->phy_mode = PHY_INTERFACE_MODE_1000BASEX; + break; + default: + ret = -EINVAL; + goto free_netdev; + } + } else { + lp->phy_mode = of_get_phy_mode(pdev->dev.of_node); + if (lp->phy_mode < 0) { + ret = -EINVAL; + goto free_netdev; + } + } /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0); diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index f71883264cc0..fd5288ff53b5 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -1781,7 +1781,7 @@ static int __init setup_xirc2ps_cs(char *str) */ int ints[10] = { -1 }; - str = get_options(str, 9, ints); + str = get_options(str, ARRAY_SIZE(ints), ints); #define MAYBE_SET(X,Y) if (ints[0] >= Y && ints[Y] != -1) { X = ints[Y]; } MAYBE_SET(if_port, 3); |