diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-24 14:16:40 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-24 14:16:40 -0700 |
commit | 24cac7009cb1b211f1c793ecb6a462c03dc35818 (patch) | |
tree | 3c1e77363ed730b38a9c4bd842a187a8250d34b7 | |
parent | 6d08b06e67cd117f6992c46611dfb4ce267cd71e (diff) | |
parent | d19efb729f10339f91c35003d480dc718cae3b3c (diff) | |
download | linux-24cac7009cb1b211f1c793ecb6a462c03dc35818.tar.gz linux-24cac7009cb1b211f1c793ecb6a462c03dc35818.tar.bz2 linux-24cac7009cb1b211f1c793ecb6a462c03dc35818.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
1) Fix rtnl deadlock in ipvs, from Julian Anastasov.
2) s390 qeth fixes from Julian Wiedmann (control IO completion stalls,
bad MAC address update sequence, request side races on command IO
timeouts).
3) Handle seq_file overflow properly in l2tp, from Guillaume Nault.
4) Fix VLAN priority mappings in cpsw driver, from Ivan Khoronzhuk.
5) Packet scheduler ife action fixes (malformed TLV lengths, etc.) from
Alexander Aring.
6) Fix out of bounds access in tcp md5 option parser, from Jann Horn.
7) Missing netlink attribute policies in rtm_ipv6_policy table, from
Eric Dumazet.
8) Missing socket address length checks in l2tp and pppoe connect, from
Guillaume Nault.
9) Fix netconsole over team and bonding, from Xin Long.
10) Fix race with AF_PACKET socket state bitfields, from Willem de
Bruijn.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (51 commits)
ice: Fix insufficient memory issue in ice_aq_manage_mac_read
sfc: ARFS filter IDs
net: ethtool: Add missing kernel doc for FEC parameters
packet: fix bitfield update race
ice: Do not check INTEVENT bit for OICR interrupts
ice: Fix incorrect comment for action type
ice: Fix initialization for num_nodes_added
igb: Fix the transmission mode of queue 0 for Qav mode
ixgbevf: ensure xdp_ring resources are free'd on error exit
team: fix netconsole setup over team
amd-xgbe: Only use the SFP supported transceiver signals
amd-xgbe: Improve KR auto-negotiation and training
amd-xgbe: Add pre/post auto-negotiation phy hooks
pppoe: check sockaddr length in pppoe_connect()
l2tp: check sockaddr length in pppol2tp_connect()
net: phy: marvell: clear wol event before setting it
ipv6: add RTA_TABLE and RTA_PREFSRC to rtm_ipv6_policy
bonding: do not set slave_dev npinfo before slave_enable_netpoll in bond_enslave
tcp: don't read out-of-bounds opsize
ibmvnic: Clean actual number of RX or TX pools
...
64 files changed, 1163 insertions, 463 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index b7b113018853..718e4914e3a0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1660,8 +1660,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, } /* switch(bond_mode) */ #ifdef CONFIG_NET_POLL_CONTROLLER - slave_dev->npinfo = bond->dev->npinfo; - if (slave_dev->npinfo) { + if (bond->dev->npinfo) { if (slave_enable_netpoll(new_slave)) { netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n"); res = -EBUSY; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 7ea72ef11a55..d272dc6984ac 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -1321,6 +1321,10 @@ #define MDIO_VEND2_AN_STAT 0x8002 #endif +#ifndef MDIO_VEND2_PMA_CDR_CONTROL +#define MDIO_VEND2_PMA_CDR_CONTROL 0x8056 +#endif + #ifndef MDIO_CTRL1_SPEED1G #define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100) #endif @@ -1369,6 +1373,10 @@ #define XGBE_AN_CL37_TX_CONFIG_MASK 0x08 #define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100 +#define XGBE_PMA_CDR_TRACK_EN_MASK 0x01 +#define XGBE_PMA_CDR_TRACK_EN_OFF 0x00 +#define XGBE_PMA_CDR_TRACK_EN_ON 0x01 + /* Bit setting and getting macros * The get macro will extract the current bit field value from within * the variable diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index 7d128be61310..b91143947ed2 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata) "debugfs_create_file failed\n"); } + if (pdata->vdata->an_cdr_workaround) { + pfile = debugfs_create_bool("an_cdr_workaround", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_workaround); + if (!pfile) + netdev_err(pdata->netdev, + "debugfs_create_bool failed\n"); + + pfile = debugfs_create_bool("an_cdr_track_early", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_track_early); + if (!pfile) + netdev_err(pdata->netdev, + "debugfs_create_bool failed\n"); + } + kfree(buf); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index 795e556d4a3f..441d0973957b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata) XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1); /* Call MDIO/PHY initialization routine */ + pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround; ret = pdata->phy_if.phy_init(pdata); if (ret) return ret; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 072b9f664597..1b45cd73a258 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -432,11 +432,16 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata) xgbe_an73_set(pdata, false, false); xgbe_an73_disable_interrupts(pdata); + pdata->an_start = 0; + netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n"); } static void xgbe_an_restart(struct xgbe_prv_data *pdata) { + if (pdata->phy_if.phy_impl.an_pre) + pdata->phy_if.phy_impl.an_pre(pdata); + switch (pdata->an_mode) { case XGBE_AN_MODE_CL73: case XGBE_AN_MODE_CL73_REDRV: @@ -453,6 +458,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata) static void xgbe_an_disable(struct xgbe_prv_data *pdata) { + if (pdata->phy_if.phy_impl.an_post) + pdata->phy_if.phy_impl.an_post(pdata); + switch (pdata->an_mode) { case XGBE_AN_MODE_CL73: case XGBE_AN_MODE_CL73_REDRV: @@ -505,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata, XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg); - if (pdata->phy_if.phy_impl.kr_training_post) - pdata->phy_if.phy_impl.kr_training_post(pdata); - netif_dbg(pdata, link, pdata->netdev, "KR training initiated\n"); + + if (pdata->phy_if.phy_impl.kr_training_post) + pdata->phy_if.phy_impl.kr_training_post(pdata); } return XGBE_AN_PAGE_RECEIVED; @@ -637,11 +645,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata) return XGBE_AN_NO_LINK; } - xgbe_an73_disable(pdata); + xgbe_an_disable(pdata); xgbe_switch_mode(pdata); - xgbe_an73_restart(pdata); + xgbe_an_restart(pdata); return XGBE_AN_INCOMPAT_LINK; } @@ -820,6 +828,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata) pdata->an_result = pdata->an_state; pdata->an_state = XGBE_AN_READY; + if (pdata->phy_if.phy_impl.an_post) + pdata->phy_if.phy_impl.an_post(pdata); + netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n", xgbe_state_as_string(pdata->an_result)); } @@ -903,6 +914,9 @@ again: pdata->kx_state = XGBE_RX_BPA; pdata->an_start = 0; + if (pdata->phy_if.phy_impl.an_post) + pdata->phy_if.phy_impl.an_post(pdata); + netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n", xgbe_state_as_string(pdata->an_result)); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index eb23f9ba1a9a..82d1f416ee2a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = { .irq_reissue_support = 1, .tx_desc_prefetch = 5, .rx_desc_prefetch = 5, + .an_cdr_workaround = 1, }; static const struct xgbe_version_data xgbe_v2b = { @@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = { .irq_reissue_support = 1, .tx_desc_prefetch = 5, .rx_desc_prefetch = 5, + .an_cdr_workaround = 1, }; static const struct pci_device_id xgbe_pci_table[] = { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 3304a291aa96..aac884314000 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -147,6 +147,14 @@ /* Rate-change complete wait/retry count */ #define XGBE_RATECHANGE_COUNT 500 +/* CDR delay values for KR support (in usec) */ +#define XGBE_CDR_DELAY_INIT 10000 +#define XGBE_CDR_DELAY_INC 10000 +#define XGBE_CDR_DELAY_MAX 100000 + +/* RRC frequency during link status check */ +#define XGBE_RRC_FREQUENCY 10 + enum xgbe_port_mode { XGBE_PORT_MODE_RSVD = 0, XGBE_PORT_MODE_BACKPLANE, @@ -245,6 +253,10 @@ enum xgbe_sfp_speed { #define XGBE_SFP_BASE_VENDOR_SN 4 #define XGBE_SFP_BASE_VENDOR_SN_LEN 16 +#define XGBE_SFP_EXTD_OPT1 1 +#define XGBE_SFP_EXTD_OPT1_RX_LOS BIT(1) +#define XGBE_SFP_EXTD_OPT1_TX_FAULT BIT(3) + #define XGBE_SFP_EXTD_DIAG 28 #define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2) @@ -324,6 +336,7 @@ struct xgbe_phy_data { unsigned int sfp_gpio_address; unsigned int sfp_gpio_mask; + unsigned int sfp_gpio_inputs; unsigned int sfp_gpio_rx_los; unsigned int sfp_gpio_tx_fault; unsigned int sfp_gpio_mod_absent; @@ -355,6 +368,10 @@ struct xgbe_phy_data { unsigned int redrv_addr; unsigned int redrv_lane; unsigned int redrv_model; + + /* KR AN support */ + unsigned int phy_cdr_notrack; + unsigned int phy_cdr_delay; }; /* I2C, MDIO and GPIO lines are muxed, so only one device at a time */ @@ -974,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata) phy_data->sfp_phy_avail = 1; } +static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data) +{ + u8 *sfp_extd = phy_data->sfp_eeprom.extd; + + if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS)) + return false; + + if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) + return false; + + if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los)) + return true; + + return false; +} + +static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data) +{ + u8 *sfp_extd = phy_data->sfp_eeprom.extd; + + if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT)) + return false; + + if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) + return false; + + if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault)) + return true; + + return false; +} + +static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data) +{ + if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) + return false; + + if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent)) + return true; + + return false; +} + static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -1019,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata) if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP) return; + /* Update transceiver signals (eeprom extd/options) */ + phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data); + phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data); + if (xgbe_phy_sfp_parse_quirks(pdata)) return; @@ -1184,7 +1248,6 @@ put: static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; - unsigned int gpio_input; u8 gpio_reg, gpio_ports[2]; int ret; @@ -1199,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata) return; } - gpio_input = (gpio_ports[1] << 8) | gpio_ports[0]; - - if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) { - /* No GPIO, just assume the module is present for now */ - phy_data->sfp_mod_absent = 0; - } else { - if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent))) - phy_data->sfp_mod_absent = 0; - } - - if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) && - (gpio_input & (1 << phy_data->sfp_gpio_rx_los))) - phy_data->sfp_rx_los = 1; + phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0]; - if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) && - (gpio_input & (1 << phy_data->sfp_gpio_tx_fault))) - phy_data->sfp_tx_fault = 1; + phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data); } static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata) @@ -2361,7 +2410,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) return 1; /* No link, attempt a receiver reset cycle */ - if (phy_data->rrc_count++) { + if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) { phy_data->rrc_count = 0; xgbe_phy_rrc(pdata); } @@ -2669,6 +2718,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata) return true; } +static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + if (!pdata->debugfs_an_cdr_workaround) + return; + + if (!phy_data->phy_cdr_notrack) + return; + + usleep_range(phy_data->phy_cdr_delay, + phy_data->phy_cdr_delay + 500); + + XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL, + XGBE_PMA_CDR_TRACK_EN_MASK, + XGBE_PMA_CDR_TRACK_EN_ON); + + phy_data->phy_cdr_notrack = 0; +} + +static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + if (!pdata->debugfs_an_cdr_workaround) + return; + + if (phy_data->phy_cdr_notrack) + return; + + XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL, + XGBE_PMA_CDR_TRACK_EN_MASK, + XGBE_PMA_CDR_TRACK_EN_OFF); + + xgbe_phy_rrc(pdata); + + phy_data->phy_cdr_notrack = 1; +} + +static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata) +{ + if (!pdata->debugfs_an_cdr_track_early) + xgbe_phy_cdr_track(pdata); +} + +static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata) +{ + if (pdata->debugfs_an_cdr_track_early) + xgbe_phy_cdr_track(pdata); +} + +static void xgbe_phy_an_post(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + switch (pdata->an_mode) { + case XGBE_AN_MODE_CL73: + case XGBE_AN_MODE_CL73_REDRV: + if (phy_data->cur_mode != XGBE_MODE_KR) + break; + + xgbe_phy_cdr_track(pdata); + + switch (pdata->an_result) { + case XGBE_AN_READY: + case XGBE_AN_COMPLETE: + break; + default: + if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX) + phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC; + else + phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT; + break; + } + break; + default: + break; + } +} + +static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + switch (pdata->an_mode) { + case XGBE_AN_MODE_CL73: + case XGBE_AN_MODE_CL73_REDRV: + if (phy_data->cur_mode != XGBE_MODE_KR) + break; + + xgbe_phy_cdr_notrack(pdata); + break; + default: + break; + } +} + static void xgbe_phy_stop(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -2680,6 +2826,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata) xgbe_phy_sfp_reset(phy_data); xgbe_phy_sfp_mod_absent(pdata); + /* Reset CDR support */ + xgbe_phy_cdr_track(pdata); + /* Power off the PHY */ xgbe_phy_power_off(pdata); @@ -2712,6 +2861,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata) /* Start in highest supported mode */ xgbe_phy_set_mode(pdata, phy_data->start_mode); + /* Reset CDR support */ + xgbe_phy_cdr_track(pdata); + /* After starting the I2C controller, we can check for an SFP */ switch (phy_data->port_mode) { case XGBE_PORT_MODE_SFP: @@ -3019,6 +3171,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) } } + phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT; + /* Register for driving external PHYs */ mii = devm_mdiobus_alloc(pdata->dev); if (!mii) { @@ -3071,4 +3225,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if) phy_impl->an_advertising = xgbe_phy_an_advertising; phy_impl->an_outcome = xgbe_phy_an_outcome; + + phy_impl->an_pre = xgbe_phy_an_pre; + phy_impl->an_post = xgbe_phy_an_post; + + phy_impl->kr_training_pre = xgbe_phy_kr_training_pre; + phy_impl->kr_training_post = xgbe_phy_kr_training_post; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index ad102c8bac7b..95d4b56448c6 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -833,6 +833,7 @@ struct xgbe_hw_if { /* This structure represents implementation specific routines for an * implementation of a PHY. All routines are required unless noted below. * Optional routines: + * an_pre, an_post * kr_training_pre, kr_training_post */ struct xgbe_phy_impl_if { @@ -875,6 +876,10 @@ struct xgbe_phy_impl_if { /* Process results of auto-negotiation */ enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *); + /* Pre/Post auto-negotiation support */ + void (*an_pre)(struct xgbe_prv_data *); + void (*an_post)(struct xgbe_prv_data *); + /* Pre/Post KR training enablement support */ void (*kr_training_pre)(struct xgbe_prv_data *); void (*kr_training_post)(struct xgbe_prv_data *); @@ -989,6 +994,7 @@ struct xgbe_version_data { unsigned int irq_reissue_support; unsigned int tx_desc_prefetch; unsigned int rx_desc_prefetch; + unsigned int an_cdr_workaround; }; struct xgbe_vxlan_data { @@ -1257,6 +1263,9 @@ struct xgbe_prv_data { unsigned int debugfs_xprop_reg; unsigned int debugfs_xi2c_reg; + + bool debugfs_an_cdr_workaround; + bool debugfs_an_cdr_track_early; }; /* Function prototypes*/ diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 2df01ad98df7..6e8d6a6f6aaf 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1128,7 +1128,7 @@ static void clean_rx_pools(struct ibmvnic_adapter *adapter) if (!adapter->rx_pool) return; - rx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_rxadd_subcrqs); + rx_scrqs = adapter->num_active_rx_pools; rx_entries = adapter->req_rx_add_entries_per_subcrq; /* Free any remaining skbs in the rx buffer pools */ @@ -1177,7 +1177,7 @@ static void clean_tx_pools(struct ibmvnic_adapter *adapter) if (!adapter->tx_pool || !adapter->tso_pool) return; - tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); + tx_scrqs = adapter->num_active_tx_pools; /* Free any remaining skbs in the tx buffer pools */ for (i = 0; i < tx_scrqs; i++) { diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 5b13ca1bd85f..7dc5f045e969 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -586,7 +586,7 @@ struct ice_sw_rule_lg_act { #define ICE_LG_ACT_MIRROR_VSI_ID_S 3 #define ICE_LG_ACT_MIRROR_VSI_ID_M (0x3FF << ICE_LG_ACT_MIRROR_VSI_ID_S) - /* Action type = 5 - Large Action */ + /* Action type = 5 - Generic Value */ #define ICE_LG_ACT_GENERIC 0x5 #define ICE_LG_ACT_GENERIC_VALUE_S 3 #define ICE_LG_ACT_GENERIC_VALUE_M (0xFFFF << ICE_LG_ACT_GENERIC_VALUE_S) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 21977ec984c4..71d032cc5fa7 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -78,6 +78,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, struct ice_aq_desc desc; enum ice_status status; u16 flags; + u8 i; cmd = &desc.params.mac_read; @@ -98,8 +99,16 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, return ICE_ERR_CFG; } - ether_addr_copy(hw->port_info->mac.lan_addr, resp->mac_addr); - ether_addr_copy(hw->port_info->mac.perm_addr, resp->mac_addr); + /* A single port can report up to two (LAN and WoL) addresses */ + for (i = 0; i < cmd->num_addr; i++) + if (resp[i].addr_type == ICE_AQC_MAN_MAC_ADDR_TYPE_LAN) { + ether_addr_copy(hw->port_info->mac.lan_addr, + resp[i].mac_addr); + ether_addr_copy(hw->port_info->mac.perm_addr, + resp[i].mac_addr); + break; + } + return 0; } @@ -464,9 +473,12 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; - /* Get port MAC information */ - mac_buf_len = sizeof(struct ice_aqc_manage_mac_read_resp); - mac_buf = devm_kzalloc(ice_hw_to_dev(hw), mac_buf_len, GFP_KERNEL); + /* Get MAC information */ + /* A single port can report up to two (LAN and WoL) addresses */ + mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2, + sizeof(struct ice_aqc_manage_mac_read_resp), + GFP_KERNEL); + mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp); if (!mac_buf) { status = ICE_ERR_NO_MEMORY; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 1b9e2ef48a9d..499904874b3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -121,8 +121,6 @@ #define PFINT_FW_CTL_CAUSE_ENA_S 30 #define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S) #define PFINT_OICR 0x0016CA00 -#define PFINT_OICR_INTEVENT_S 0 -#define PFINT_OICR_INTEVENT_M BIT(PFINT_OICR_INTEVENT_S) #define PFINT_OICR_HLP_RDY_S 14 #define PFINT_OICR_HLP_RDY_M BIT(PFINT_OICR_HLP_RDY_S) #define PFINT_OICR_CPM_RDY_S 15 diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 210b7910f1cd..5299caf55a7f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1722,9 +1722,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); - if (!(oicr & PFINT_OICR_INTEVENT_M)) - goto ena_intr; - if (oicr & PFINT_OICR_GRST_M) { u32 reset; /* we have a reset warning */ @@ -1782,7 +1779,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) } ret = IRQ_HANDLED; -ena_intr: /* re-enable interrupt causes that are not handled during this pass */ wr32(hw, PFINT_OICR_ENA, ena_mask); if (!test_bit(__ICE_DOWN, pf->state)) { diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index f16ff3e4a840..2e6c1d92cc88 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -751,14 +751,14 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, u16 num_added = 0; u32 temp; + *num_nodes_added = 0; + if (!num_nodes) return status; if (!parent || layer < hw->sw_entry_point_layer) return ICE_ERR_PARAM; - *num_nodes_added = 0; - /* max children per node per layer */ max_child_nodes = le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c1c0bc30a16d..cce7ada89255 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1700,7 +1700,22 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue, WARN_ON(hw->mac.type != e1000_i210); WARN_ON(queue < 0 || queue > 1); - if (enable) { + if (enable || queue == 0) { + /* i210 does not allow the queue 0 to be in the Strict + * Priority mode while the Qav mode is enabled, so, + * instead of disabling strict priority mode, we give + * queue 0 the maximum of credits possible. + * + * See section 8.12.19 of the i210 datasheet, "Note: + * Queue0 QueueMode must be set to 1b when + * TransmitMode is set to Qav." + */ + if (queue == 0 && !enable) { + /* max "linkspeed" idleslope in kbps */ + idleslope = 1000000; + hicredit = ETH_FRAME_LEN; + } + set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH); set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 3d9033f26eff..e3d04f226d57 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3420,7 +3420,7 @@ static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter) if (!err) continue; hw_dbg(&adapter->hw, "Allocation for XDP Queue %u failed\n", j); - break; + goto err_setup_tx; } return 0; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 83ce229f4eb7..63036d9bf3e6 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3999,29 +3999,6 @@ static void efx_ef10_prepare_flr(struct efx_nic *efx) atomic_set(&efx->active_queues, 0); } -static bool efx_ef10_filter_equal(const struct efx_filter_spec *left, - const struct efx_filter_spec *right) -{ - if ((left->match_flags ^ right->match_flags) | - ((left->flags ^ right->flags) & - (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX))) - return false; - - return memcmp(&left->outer_vid, &right->outer_vid, - sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) == 0; -} - -static unsigned int efx_ef10_filter_hash(const struct efx_filter_spec *spec) -{ - BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3); - return jhash2((const u32 *)&spec->outer_vid, - (sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) / 4, - 0); - /* XXX should we randomise the initval? */ -} - /* Decide whether a filter should be exclusive or else should allow * delivery to additional recipients. Currently we decide that * filters for specific local unicast MAC and IP addresses are @@ -4346,7 +4323,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx, goto out_unlock; match_pri = rc; - hash = efx_ef10_filter_hash(spec); + hash = efx_filter_spec_hash(spec); is_mc_recip = efx_filter_is_mc_recipient(spec); if (is_mc_recip) bitmap_zero(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT); @@ -4378,7 +4355,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx, if (!saved_spec) { if (ins_index < 0) ins_index = i; - } else if (efx_ef10_filter_equal(spec, saved_spec)) { + } else if (efx_filter_spec_equal(spec, saved_spec)) { if (spec->priority < saved_spec->priority && spec->priority != EFX_FILTER_PRI_AUTO) { rc = -EPERM; @@ -4762,27 +4739,62 @@ static s32 efx_ef10_filter_get_rx_ids(struct efx_nic *efx, static bool efx_ef10_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id, unsigned int filter_idx) { + struct efx_filter_spec *spec, saved_spec; struct efx_ef10_filter_table *table; - struct efx_filter_spec *spec; - bool ret; + struct efx_arfs_rule *rule = NULL; + bool ret = true, force = false; + u16 arfs_id; down_read(&efx->filter_sem); table = efx->filter_state; down_write(&table->lock); spec = efx_ef10_filter_entry_spec(table, filter_idx); - if (!spec || spec->priority != EFX_FILTER_PRI_HINT) { - ret = true; + if (!spec || spec->priority != EFX_FILTER_PRI_HINT) goto out_unlock; - } - if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, 0)) { - ret = false; - goto out_unlock; + spin_lock_bh(&efx->rps_hash_lock); + if (!efx->rps_hash_table) { + /* In the absence of the table, we always return 0 to ARFS. */ + arfs_id = 0; + } else { + rule = efx_rps_hash_find(efx, spec); + if (!rule) + /* ARFS table doesn't know of this filter, so remove it */ + goto expire; + arfs_id = rule->arfs_id; + ret = efx_rps_check_rule(rule, filter_idx, &force); + if (force) + goto expire; + if (!ret) { + spin_unlock_bh(&efx->rps_hash_lock); + goto out_unlock; + } } - + if (!rps_may_expire_flow(efx->net_dev, spec->dmaq_id, flow_id, arfs_id)) + ret = false; + else if (rule) + rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING; +expire: + saved_spec = *spec; /* remove operation will kfree spec */ + spin_unlock_bh(&efx->rps_hash_lock); + /* At this point (since we dropped the lock), another thread might queue + * up a fresh insertion request (but the actual insertion will be held + * up by our possession of the filter table lock). In that case, it + * will set rule->filter_id to EFX_ARFS_FILTER_ID_PENDING, meaning that + * the rule is not removed by efx_rps_hash_del() below. + */ ret = efx_ef10_filter_remove_internal(efx, 1U << spec->priority, filter_idx, true) == 0; + /* While we can't safely dereference rule (we dropped the lock), we can + * still test it for NULL. + */ + if (ret && rule) { + /* Expiring, so remove entry from ARFS table */ + spin_lock_bh(&efx->rps_hash_lock); + efx_rps_hash_del(efx, &saved_spec); + spin_unlock_bh(&efx->rps_hash_lock); + } out_unlock: up_write(&table->lock); up_read(&efx->filter_sem); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 692dd729ee2a..a4ebd8715494 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -3027,6 +3027,10 @@ static int efx_init_struct(struct efx_nic *efx, mutex_init(&efx->mac_lock); #ifdef CONFIG_RFS_ACCEL mutex_init(&efx->rps_mutex); + spin_lock_init(&efx->rps_hash_lock); + /* Failure to allocate is not fatal, but may degrade ARFS performance */ + efx->rps_hash_table = kcalloc(EFX_ARFS_HASH_TABLE_SIZE, + sizeof(*efx->rps_hash_table), GFP_KERNEL); #endif efx->phy_op = &efx_dummy_phy_operations; efx->mdio.dev = net_dev; @@ -3070,6 +3074,10 @@ static void efx_fini_struct(struct efx_nic *efx) { int i; +#ifdef CONFIG_RFS_ACCEL + kfree(efx->rps_hash_table); +#endif + for (i = 0; i < EFX_MAX_CHANNELS; i++) kfree(efx->channel[i]); @@ -3092,6 +3100,141 @@ void efx_update_sw_stats(struct efx_nic *efx, u64 *stats) stats[GENERIC_STAT_rx_noskb_drops] = atomic_read(&efx->n_rx_noskb_drops); } +bool efx_filter_spec_equal(const struct efx_filter_spec *left, + const struct efx_filter_spec *right) +{ + if ((left->match_flags ^ right->match_flags) | + ((left->flags ^ right->flags) & + (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX))) + return false; + + return memcmp(&left->outer_vid, &right->outer_vid, + sizeof(struct efx_filter_spec) - + offsetof(struct efx_filter_spec, outer_vid)) == 0; +} + +u32 efx_filter_spec_hash(const struct efx_filter_spec *spec) +{ + BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3); + return jhash2((const u32 *)&spec->outer_vid, + (sizeof(struct efx_filter_spec) - + offsetof(struct efx_filter_spec, outer_vid)) / 4, + 0); +} + +#ifdef CONFIG_RFS_ACCEL +bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx, + bool *force) +{ + if (rule->filter_id == EFX_ARFS_FILTER_ID_PENDING) { + /* ARFS is currently updating this entry, leave it */ + return false; + } + if (rule->filter_id == EFX_ARFS_FILTER_ID_ERROR) { + /* ARFS tried and failed to update this, so it's probably out + * of date. Remove the filter and the ARFS rule entry. + */ + rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING; + *force = true; + return true; + } else if (WARN_ON(rule->filter_id != filter_idx)) { /* can't happen */ + /* ARFS has moved on, so old filter is not needed. Since we did + * not mark the rule with EFX_ARFS_FILTER_ID_REMOVING, it will + * not be removed by efx_rps_hash_del() subsequently. + */ + *force = true; + return true; + } + /* Remove it iff ARFS wants to. */ + return true; +} + +struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx, + const struct efx_filter_spec *spec) +{ + u32 hash = efx_filter_spec_hash(spec); + + WARN_ON(!spin_is_locked(&efx->rps_hash_lock)); + if (!efx->rps_hash_table) + return NULL; + return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE]; +} + +struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx, + const struct efx_filter_spec *spec) +{ + struct efx_arfs_rule *rule; + struct hlist_head *head; + struct hlist_node *node; + + head = efx_rps_hash_bucket(efx, spec); + if (!head) + return NULL; + hlist_for_each(node, head) { + rule = container_of(node, struct efx_arfs_rule, node); + if (efx_filter_spec_equal(spec, &rule->spec)) + return rule; + } + return NULL; +} + +struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx, + const struct efx_filter_spec *spec, + bool *new) +{ + struct efx_arfs_rule *rule; + struct hlist_head *head; + struct hlist_node *node; + + head = efx_rps_hash_bucket(efx, spec); + if (!head) + return NULL; + hlist_for_each(node, head) { + rule = container_of(node, struct efx_arfs_rule, node); + if (efx_filter_spec_equal(spec, &rule->spec)) { + *new = false; + return rule; + } + } + rule = kmalloc(sizeof(*rule), GFP_ATOMIC); + *new = true; + if (rule) { + memcpy(&rule->spec, spec, sizeof(rule->spec)); + hlist_add_head(&rule->node, head); + } + return rule; +} + +void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec) +{ + struct efx_arfs_rule *rule; + struct hlist_head *head; + struct hlist_node *node; + + head = efx_rps_hash_bucket(efx, spec); + if (WARN_ON(!head)) + return; + hlist_for_each(node, head) { + rule = container_of(node, struct efx_arfs_rule, node); + if (efx_filter_spec_equal(spec, &rule->spec)) { + /* Someone already reused the entry. We know that if + * this check doesn't fire (i.e. filter_id == REMOVING) + * then the REMOVING mark was put there by our caller, + * because caller is holding a lock on filter table and + * only holders of that lock set REMOVING. + */ + if (rule->filter_id != EFX_ARFS_FILTER_ID_REMOVING) + return; + hlist_del(node); + kfree(rule); + return; + } + } + /* We didn't find it. */ + WARN_ON(1); +} +#endif + /* RSS contexts. We're using linked lists and crappy O(n) algorithms, because * (a) this is an infrequent control-plane operation and (b) n is small (max 64) */ diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index a3140e16fcef..3f759ebdcf10 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -186,6 +186,27 @@ static inline void efx_filter_rfs_expire(struct work_struct *data) {} #endif bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec); +bool efx_filter_spec_equal(const struct efx_filter_spec *left, + const struct efx_filter_spec *right); +u32 efx_filter_spec_hash(const struct efx_filter_spec *spec); + +#ifdef CONFIG_RFS_ACCEL +bool efx_rps_check_rule(struct efx_arfs_rule *rule, unsigned int filter_idx, + bool *force); + +struct efx_arfs_rule *efx_rps_hash_find(struct efx_nic *efx, + const struct efx_filter_spec *spec); + +/* @new is written to indicate if entry was newly added (true) or if an old + * entry was found and returned (false). + */ +struct efx_arfs_rule *efx_rps_hash_add(struct efx_nic *efx, + const struct efx_filter_spec *spec, + bool *new); + +void efx_rps_hash_del(struct efx_nic *efx, const struct efx_filter_spec *spec); +#endif + /* RSS contexts */ struct efx_rss_context *efx_alloc_rss_context_entry(struct efx_nic *efx); struct efx_rss_context *efx_find_rss_context_entry(struct efx_nic *efx, u32 id); diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 7174ef5e5c5e..c72adf8b52ea 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -2905,18 +2905,45 @@ bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id, { struct efx_farch_filter_state *state = efx->filter_state; struct efx_farch_filter_table *table; - bool ret = false; + bool ret = false, force = false; + u16 arfs_id; down_write(&state->lock); + spin_lock_bh(&efx->rps_hash_lock); table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP]; if (test_bit(index, table->used_bitmap) && - table->spec[index].priority == EFX_FILTER_PRI_HINT && - rps_may_expire_flow(efx->net_dev, table->spec[index].dmaq_id, - flow_id, 0)) { - efx_farch_filter_table_clear_entry(efx, table, index); - ret = true; + table->spec[index].priority == EFX_FILTER_PRI_HINT) { + struct efx_arfs_rule *rule = NULL; + struct efx_filter_spec spec; + + efx_farch_filter_to_gen_spec(&spec, &table->spec[index]); + if (!efx->rps_hash_table) { + /* In the absence of the table, we always returned 0 to + * ARFS, so use the same to query it. + */ + arfs_id = 0; + } else { + rule = efx_rps_hash_find(efx, &spec); + if (!rule) { + /* ARFS table doesn't know of this filter, remove it */ + force = true; + } else { + arfs_id = rule->arfs_id; + if (!efx_rps_check_rule(rule, index, &force)) + goto out_unlock; + } + } + if (force || rps_may_expire_flow(efx->net_dev, spec.dmaq_id, + flow_id, arfs_id)) { + if (rule) + rule->filter_id = EFX_ARFS_FILTER_ID_REMOVING; + efx_rps_hash_del(efx, &spec); + efx_farch_filter_table_clear_entry(efx, table, index); + ret = true; + } } - +out_unlock: + spin_unlock_bh(&efx->rps_hash_lock); up_write(&state->lock); return ret; } diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index eea3808b3f25..65568925c3ef 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -734,6 +734,35 @@ struct efx_rss_context { }; #ifdef CONFIG_RFS_ACCEL +/* Order of these is important, since filter_id >= %EFX_ARFS_FILTER_ID_PENDING + * is used to test if filter does or will exist. + */ +#define EFX_ARFS_FILTER_ID_PENDING -1 +#define EFX_ARFS_FILTER_ID_ERROR -2 +#define EFX_ARFS_FILTER_ID_REMOVING -3 +/** + * struct efx_arfs_rule - record of an ARFS filter and its IDs + * @node: linkage into hash table + * @spec: details of the filter (used as key for hash table). Use efx->type to + * determine which member to use. + * @rxq_index: channel to which the filter will steer traffic. + * @arfs_id: filter ID which was returned to ARFS + * @filter_id: index in software filter table. May be + * %EFX_ARFS_FILTER_ID_PENDING if filter was not inserted yet, + * %EFX_ARFS_FILTER_ID_ERROR if filter insertion failed, or + * %EFX_ARFS_FILTER_ID_REMOVING if expiry is currently removing the filter. + */ +struct efx_arfs_rule { + struct hlist_node node; + struct efx_filter_spec spec; + u16 rxq_index; + u16 arfs_id; + s32 filter_id; +}; + +/* Size chosen so that the table is one page (4kB) */ +#define EFX_ARFS_HASH_TABLE_SIZE 512 + /** * struct efx_async_filter_insertion - Request to asynchronously insert a filter * @net_dev: Reference to the netdevice @@ -873,6 +902,10 @@ struct efx_async_filter_insertion { * @rps_expire_channel's @rps_flow_id * @rps_slot_map: bitmap of in-flight entries in @rps_slot * @rps_slot: array of ARFS insertion requests for efx_filter_rfs_work() + * @rps_hash_lock: Protects ARFS filter mapping state (@rps_hash_table and + * @rps_next_id). + * @rps_hash_table: Mapping between ARFS filters and their various IDs + * @rps_next_id: next arfs_id for an ARFS filter * @active_queues: Count of RX and TX queues that haven't been flushed and drained. * @rxq_flush_pending: Count of number of receive queues that need to be flushed. * Decremented when the efx_flush_rx_queue() is called. @@ -1029,6 +1062,9 @@ struct efx_nic { unsigned int rps_expire_index; unsigned long rps_slot_map; struct efx_async_filter_insertion rps_slot[EFX_RPS_MAX_IN_FLIGHT]; + spinlock_t rps_hash_lock; + struct hlist_head *rps_hash_table; + u32 rps_next_id; #endif atomic_t active_queues; diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 9c593c661cbf..64a94f242027 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -834,9 +834,29 @@ static void efx_filter_rfs_work(struct work_struct *data) struct efx_nic *efx = netdev_priv(req->net_dev); struct efx_channel *channel = efx_get_channel(efx, req->rxq_index); int slot_idx = req - efx->rps_slot; + struct efx_arfs_rule *rule; + u16 arfs_id = 0; int rc; rc = efx->type->filter_insert(efx, &req->spec, true); + if (efx->rps_hash_table) { + spin_lock_bh(&efx->rps_hash_lock); + rule = efx_rps_hash_find(efx, &req->spec); + /* The rule might have already gone, if someone else's request + * for the same spec was already worked and then expired before + * we got around to our work. In that case we have nothing + * tying us to an arfs_id, meaning that as soon as the filter + * is considered for expiry it will be removed. + */ + if (rule) { + if (rc < 0) + rule->filter_id = EFX_ARFS_FILTER_ID_ERROR; + else + rule->filter_id = rc; + arfs_id = rule->arfs_id; + } + spin_unlock_bh(&efx->rps_hash_lock); + } if (rc >= 0) { /* Remember this so we can check whether to expire the filter * later. @@ -848,18 +868,18 @@ static void efx_filter_rfs_work(struct work_struct *data) if (req->spec.ether_type == htons(ETH_P_IP)) netif_info(efx, rx_status, efx->net_dev, - "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n", + "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d id %u]\n", (req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP", req->spec.rem_host, ntohs(req->spec.rem_port), req->spec.loc_host, ntohs(req->spec.loc_port), - req->rxq_index, req->flow_id, rc); + req->rxq_index, req->flow_id, rc, arfs_id); else netif_info(efx, rx_status, efx->net_dev, - "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n", + "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d id %u]\n", (req->spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP", req->spec.rem_host, ntohs(req->spec.rem_port), req->spec.loc_host, ntohs(req->spec.loc_port), - req->rxq_index, req->flow_id, rc); + req->rxq_index, req->flow_id, rc, arfs_id); } /* Release references */ @@ -872,8 +892,10 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, { struct efx_nic *efx = netdev_priv(net_dev); struct efx_async_filter_insertion *req; + struct efx_arfs_rule *rule; struct flow_keys fk; int slot_idx; + bool new; int rc; /* find a free slot */ @@ -926,12 +948,42 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, req->spec.rem_port = fk.ports.src; req->spec.loc_port = fk.ports.dst; + if (efx->rps_hash_table) { + /* Add it to ARFS hash table */ + spin_lock(&efx->rps_hash_lock); + rule = efx_rps_hash_add(efx, &req->spec, &new); + if (!rule) { + rc = -ENOMEM; + goto out_unlock; + } + if (new) + rule->arfs_id = efx->rps_next_id++ % RPS_NO_FILTER; + rc = rule->arfs_id; + /* Skip if existing or pending filter already does the right thing */ + if (!new && rule->rxq_index == rxq_index && + rule->filter_id >= EFX_ARFS_FILTER_ID_PENDING) + goto out_unlock; + rule->rxq_index = rxq_index; + rule->filter_id = EFX_ARFS_FILTER_ID_PENDING; + spin_unlock(&efx->rps_hash_lock); + } else { + /* Without an ARFS hash table, we just use arfs_id 0 for all + * filters. This means if multiple flows hash to the same + * flow_id, all but the most recently touched will be eligible + * for expiry. + */ + rc = 0; + } + + /* Queue the request */ dev_hold(req->net_dev = net_dev); INIT_WORK(&req->work, efx_filter_rfs_work); req->rxq_index = rxq_index; req->flow_id = flow_id; schedule_work(&req->work); - return 0; + return rc; +out_unlock: + spin_unlock(&efx->rps_hash_lock); out_clear: clear_bit(slot_idx, &efx->rps_slot_map); return rc; diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 30371274409d..74f828412055 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -129,7 +129,7 @@ do { \ #define RX_PRIORITY_MAPPING 0x76543210 #define TX_PRIORITY_MAPPING 0x33221100 -#define CPDMA_TX_PRIORITY_MAP 0x01234567 +#define CPDMA_TX_PRIORITY_MAP 0x76543210 #define CPSW_VLAN_AWARE BIT(1) #define CPSW_RX_VLAN_ENCAP BIT(2) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index c22e8e383247..25e2a099b71c 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1393,6 +1393,15 @@ static int m88e1318_set_wol(struct phy_device *phydev, if (err < 0) goto error; + /* If WOL event happened once, the LED[2] interrupt pin + * will not be cleared unless we reading the interrupt status + * register. If interrupts are in use, the normal interrupt + * handling will clear the WOL event. Clear the WOL event + * before enabling it if !phy_interrupt_is_valid() + */ + if (!phy_interrupt_is_valid(phydev)) + phy_read(phydev, MII_M1011_IEVENT); + /* Enable the WOL interrupt */ err = __phy_modify(phydev, MII_88E1318S_PHY_CSIER, 0, MII_88E1318S_PHY_CSIER_WOL_EIE); diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 1483bc7b01e1..7df07337d69c 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); error = -EINVAL; + + if (sockaddr_len != sizeof(struct sockaddr_pppox)) + goto end; + if (sp->sa_protocol != PX_PROTO_OE) goto end; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index acbe84967834..ddb6bf85a59c 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1072,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port) } #ifdef CONFIG_NET_POLL_CONTROLLER -static int team_port_enable_netpoll(struct team *team, struct team_port *port) +static int __team_port_enable_netpoll(struct team_port *port) { struct netpoll *np; int err; - if (!team->dev->npinfo) - return 0; - np = kzalloc(sizeof(*np), GFP_KERNEL); if (!np) return -ENOMEM; @@ -1093,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port) return err; } +static int team_port_enable_netpoll(struct team_port *port) +{ + if (!port->team->dev->npinfo) + return 0; + + return __team_port_enable_netpoll(port); +} + static void team_port_disable_netpoll(struct team_port *port) { struct netpoll *np = port->np; @@ -1107,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port) kfree(np); } #else -static int team_port_enable_netpoll(struct team *team, struct team_port *port) +static int team_port_enable_netpoll(struct team_port *port) { return 0; } @@ -1221,7 +1226,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev, goto err_vids_add; } - err = team_port_enable_netpoll(team, port); + err = team_port_enable_netpoll(port); if (err) { netdev_err(dev, "Failed to enable netpoll on device %s\n", portname); @@ -1918,7 +1923,7 @@ static int team_netpoll_setup(struct net_device *dev, mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { - err = team_port_enable_netpoll(team, port); + err = __team_port_enable_netpoll(port); if (err) { __team_netpoll_cleanup(team); break; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 4326715dc13e..78b98b3e7efa 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -557,7 +557,6 @@ enum qeth_prot_versions { enum qeth_cmd_buffer_state { BUF_STATE_FREE, BUF_STATE_LOCKED, - BUF_STATE_PROCESSED, }; enum qeth_cq { @@ -601,7 +600,6 @@ struct qeth_channel { struct qeth_cmd_buffer iob[QETH_CMD_BUFFER_NO]; atomic_t irq_pending; int io_buf_no; - int buf_no; }; /** diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 04fefa5bb08d..dffd820731f2 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -706,7 +706,6 @@ void qeth_clear_ipacmd_list(struct qeth_card *card) qeth_put_reply(reply); } spin_unlock_irqrestore(&card->lock, flags); - atomic_set(&card->write.irq_pending, 0); } EXPORT_SYMBOL_GPL(qeth_clear_ipacmd_list); @@ -818,7 +817,6 @@ void qeth_clear_cmd_buffers(struct qeth_channel *channel) for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) qeth_release_buffer(channel, &channel->iob[cnt]); - channel->buf_no = 0; channel->io_buf_no = 0; } EXPORT_SYMBOL_GPL(qeth_clear_cmd_buffers); @@ -924,7 +922,6 @@ static int qeth_setup_channel(struct qeth_channel *channel) kfree(channel->iob[cnt].data); return -ENOMEM; } - channel->buf_no = 0; channel->io_buf_no = 0; atomic_set(&channel->irq_pending, 0); spin_lock_init(&channel->iob_lock); @@ -1100,16 +1097,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, { int rc; int cstat, dstat; - struct qeth_cmd_buffer *buffer; + struct qeth_cmd_buffer *iob = NULL; struct qeth_channel *channel; struct qeth_card *card; - struct qeth_cmd_buffer *iob; - __u8 index; - - if (__qeth_check_irb_error(cdev, intparm, irb)) - return; - cstat = irb->scsw.cmd.cstat; - dstat = irb->scsw.cmd.dstat; card = CARD_FROM_CDEV(cdev); if (!card) @@ -1127,6 +1117,19 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, channel = &card->data; QETH_CARD_TEXT(card, 5, "data"); } + + if (qeth_intparm_is_iob(intparm)) + iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm); + + if (__qeth_check_irb_error(cdev, intparm, irb)) { + /* IO was terminated, free its resources. */ + if (iob) + qeth_release_buffer(iob->channel, iob); + atomic_set(&channel->irq_pending, 0); + wake_up(&card->wait_q); + return; + } + atomic_set(&channel->irq_pending, 0); if (irb->scsw.cmd.fctl & (SCSW_FCTL_CLEAR_FUNC)) @@ -1150,6 +1153,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, /* we don't have to handle this further */ intparm = 0; } + + cstat = irb->scsw.cmd.cstat; + dstat = irb->scsw.cmd.dstat; + if ((dstat & DEV_STAT_UNIT_EXCEP) || (dstat & DEV_STAT_UNIT_CHECK) || (cstat)) { @@ -1182,25 +1189,15 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, channel->state = CH_STATE_RCD_DONE; goto out; } - if (intparm) { - buffer = (struct qeth_cmd_buffer *) __va((addr_t)intparm); - buffer->state = BUF_STATE_PROCESSED; - } if (channel == &card->data) return; if (channel == &card->read && channel->state == CH_STATE_UP) __qeth_issue_next_read(card); - iob = channel->iob; - index = channel->buf_no; - while (iob[index].state == BUF_STATE_PROCESSED) { - if (iob[index].callback != NULL) - iob[index].callback(channel, iob + index); + if (iob && iob->callback) + iob->callback(iob->channel, iob); - index = (index + 1) % QETH_CMD_BUFFER_NO; - } - channel->buf_no = index; out: wake_up(&card->wait_q); return; @@ -1870,8 +1867,8 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); - rc = ccw_device_start(channel->ccwdev, - &channel->ccw, (addr_t) iob, 0, 0); + rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw, + (addr_t) iob, 0, 0, QETH_TIMEOUT); spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); if (rc) { @@ -1888,7 +1885,6 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel, if (channel->state != CH_STATE_UP) { rc = -ETIME; QETH_DBF_TEXT_(SETUP, 2, "3err%d", rc); - qeth_clear_cmd_buffers(channel); } else rc = 0; return rc; @@ -1942,8 +1938,8 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); - rc = ccw_device_start(channel->ccwdev, - &channel->ccw, (addr_t) iob, 0, 0); + rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw, + (addr_t) iob, 0, 0, QETH_TIMEOUT); spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); if (rc) { @@ -1964,7 +1960,6 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel, QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n", dev_name(&channel->ccwdev->dev)); QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME); - qeth_clear_cmd_buffers(channel); return -ETIME; } return qeth_idx_activate_get_answer(channel, idx_reply_cb); @@ -2166,8 +2161,8 @@ int qeth_send_control_data(struct qeth_card *card, int len, QETH_CARD_TEXT(card, 6, "noirqpnd"); spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags); - rc = ccw_device_start(card->write.ccwdev, &card->write.ccw, - (addr_t) iob, 0, 0); + rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw, + (addr_t) iob, 0, 0, event_timeout); spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags); if (rc) { QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: " @@ -2199,8 +2194,6 @@ int qeth_send_control_data(struct qeth_card *card, int len, } } - if (reply->rc == -EIO) - goto error; rc = reply->rc; qeth_put_reply(reply); return rc; @@ -2211,10 +2204,6 @@ time_err: list_del_init(&reply->list); spin_unlock_irqrestore(&reply->card->lock, flags); atomic_inc(&reply->received); -error: - atomic_set(&card->write.irq_pending, 0); - qeth_release_buffer(iob->channel, iob); - card->write.buf_no = (card->write.buf_no + 1) % QETH_CMD_BUFFER_NO; rc = reply->rc; qeth_put_reply(reply); return rc; @@ -3033,28 +3022,23 @@ static int qeth_send_startlan(struct qeth_card *card) return rc; } -static int qeth_default_setadapterparms_cb(struct qeth_card *card, - struct qeth_reply *reply, unsigned long data) +static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd) { - struct qeth_ipa_cmd *cmd; - - QETH_CARD_TEXT(card, 4, "defadpcb"); - - cmd = (struct qeth_ipa_cmd *) data; - if (cmd->hdr.return_code == 0) + if (!cmd->hdr.return_code) cmd->hdr.return_code = cmd->data.setadapterparms.hdr.return_code; - return 0; + return cmd->hdr.return_code; } static int qeth_query_setadapterparms_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; QETH_CARD_TEXT(card, 3, "quyadpcb"); + if (qeth_setadpparms_inspect_rc(cmd)) + return 0; - cmd = (struct qeth_ipa_cmd *) data; if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) { card->info.link_type = cmd->data.setadapterparms.data.query_cmds_supp.lan_type; @@ -3062,7 +3046,7 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card, } card->options.adp.supported_funcs = cmd->data.setadapterparms.data.query_cmds_supp.supported_cmds; - return qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd); + return 0; } static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card, @@ -3154,22 +3138,20 @@ EXPORT_SYMBOL_GPL(qeth_query_ipassists); static int qeth_query_switch_attributes_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; - struct qeth_switch_info *sw_info; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; struct qeth_query_switch_attributes *attrs; + struct qeth_switch_info *sw_info; QETH_CARD_TEXT(card, 2, "qswiatcb"); - cmd = (struct qeth_ipa_cmd *) data; - sw_info = (struct qeth_switch_info *)reply->param; - if (cmd->data.setadapterparms.hdr.return_code == 0) { - attrs = &cmd->data.setadapterparms.data.query_switch_attributes; - sw_info->capabilities = attrs->capabilities; - sw_info->settings = attrs->settings; - QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities, - sw_info->settings); - } - qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd); + if (qeth_setadpparms_inspect_rc(cmd)) + return 0; + sw_info = (struct qeth_switch_info *)reply->param; + attrs = &cmd->data.setadapterparms.data.query_switch_attributes; + sw_info->capabilities = attrs->capabilities; + sw_info->settings = attrs->settings; + QETH_CARD_TEXT_(card, 2, "%04x%04x", sw_info->capabilities, + sw_info->settings); return 0; } @@ -4207,16 +4189,13 @@ EXPORT_SYMBOL_GPL(qeth_do_send_packet); static int qeth_setadp_promisc_mode_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; struct qeth_ipacmd_setadpparms *setparms; QETH_CARD_TEXT(card, 4, "prmadpcb"); - cmd = (struct qeth_ipa_cmd *) data; setparms = &(cmd->data.setadapterparms); - - qeth_default_setadapterparms_cb(card, reply, (unsigned long)cmd); - if (cmd->hdr.return_code) { + if (qeth_setadpparms_inspect_rc(cmd)) { QETH_CARD_TEXT_(card, 4, "prmrc%x", cmd->hdr.return_code); setparms->data.mode = SET_PROMISC_MODE_OFF; } @@ -4286,18 +4265,18 @@ EXPORT_SYMBOL_GPL(qeth_get_stats); static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; QETH_CARD_TEXT(card, 4, "chgmaccb"); + if (qeth_setadpparms_inspect_rc(cmd)) + return 0; - cmd = (struct qeth_ipa_cmd *) data; if (!card->options.layer2 || !(card->info.mac_bits & QETH_LAYER2_MAC_READ)) { ether_addr_copy(card->dev->dev_addr, cmd->data.setadapterparms.data.change_addr.addr); card->info.mac_bits |= QETH_LAYER2_MAC_READ; } - qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd); return 0; } @@ -4328,13 +4307,15 @@ EXPORT_SYMBOL_GPL(qeth_setadpparms_change_macaddr); static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; struct qeth_set_access_ctrl *access_ctrl_req; int fallback = *(int *)reply->param; QETH_CARD_TEXT(card, 4, "setaccb"); + if (cmd->hdr.return_code) + return 0; + qeth_setadpparms_inspect_rc(cmd); - cmd = (struct qeth_ipa_cmd *) data; access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl; QETH_DBF_TEXT_(SETUP, 2, "setaccb"); QETH_DBF_TEXT_(SETUP, 2, "%s", card->gdev->dev.kobj.name); @@ -4407,7 +4388,6 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, card->options.isolation = card->options.prev_isolation; break; } - qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd); return 0; } @@ -4695,14 +4675,15 @@ out: static int qeth_setadpparms_query_oat_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data; struct qeth_qoat_priv *priv; char *resdata; int resdatalen; QETH_CARD_TEXT(card, 3, "qoatcb"); + if (qeth_setadpparms_inspect_rc(cmd)) + return 0; - cmd = (struct qeth_ipa_cmd *)data; priv = (struct qeth_qoat_priv *)reply->param; resdatalen = cmd->data.setadapterparms.hdr.cmdlength; resdata = (char *)data + 28; @@ -4796,21 +4777,18 @@ out: static int qeth_query_card_info_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct carrier_info *carrier_info = (struct carrier_info *)reply->param; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data; struct qeth_query_card_info *card_info; - struct carrier_info *carrier_info; QETH_CARD_TEXT(card, 2, "qcrdincb"); - carrier_info = (struct carrier_info *)reply->param; - cmd = (struct qeth_ipa_cmd *)data; - card_info = &cmd->data.setadapterparms.data.card_info; - if (cmd->data.setadapterparms.hdr.return_code == 0) { - carrier_info->card_type = card_info->card_type; - carrier_info->port_mode = card_info->port_mode; - carrier_info->port_speed = card_info->port_speed; - } + if (qeth_setadpparms_inspect_rc(cmd)) + return 0; - qeth_default_setadapterparms_cb(card, reply, (unsigned long) cmd); + card_info = &cmd->data.setadapterparms.data.card_info; + carrier_info->card_type = card_info->card_type; + carrier_info->port_mode = card_info->port_mode; + carrier_info->port_speed = card_info->port_speed; return 0; } @@ -4857,7 +4835,7 @@ int qeth_vm_request_mac(struct qeth_card *card) goto out; } - ccw_device_get_id(CARD_DDEV(card), &id); + ccw_device_get_id(CARD_RDEV(card), &id); request->resp_buf_len = sizeof(*response); request->resp_version = DIAG26C_VERSION2; request->op_code = DIAG26C_GET_MAC; @@ -6563,10 +6541,14 @@ static int __init qeth_core_init(void) mutex_init(&qeth_mod_mutex); qeth_wq = create_singlethread_workqueue("qeth_wq"); + if (!qeth_wq) { + rc = -ENOMEM; + goto out_err; + } rc = qeth_register_dbf_views(); if (rc) - goto out_err; + goto dbf_err; qeth_core_root_dev = root_device_register("qeth"); rc = PTR_ERR_OR_ZERO(qeth_core_root_dev); if (rc) @@ -6603,6 +6585,8 @@ slab_err: root_device_unregister(qeth_core_root_dev); register_err: qeth_unregister_dbf_views(); +dbf_err: + destroy_workqueue(qeth_wq); out_err: pr_err("Initializing the qeth device driver failed\n"); return rc; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 619f897b4bb0..f4d1ec0b8f5a 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -35,6 +35,18 @@ extern unsigned char IPA_PDU_HEADER[]; #define QETH_HALT_CHANNEL_PARM -11 #define QETH_RCD_PARM -12 +static inline bool qeth_intparm_is_iob(unsigned long intparm) +{ + switch (intparm) { + case QETH_CLEAR_CHANNEL_PARM: + case QETH_HALT_CHANNEL_PARM: + case QETH_RCD_PARM: + case 0: + return false; + } + return true; +} + /*****************************************************************************/ /* IP Assist related definitions */ /*****************************************************************************/ diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 2ad6f12f3d49..b8079f2a65b3 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -121,13 +121,10 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac) QETH_CARD_TEXT(card, 2, "L2Setmac"); rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_SETVMAC); if (rc == 0) { - card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED; - ether_addr_copy(card->dev->dev_addr, mac); dev_info(&card->gdev->dev, - "MAC address %pM successfully registered on device %s\n", - card->dev->dev_addr, card->dev->name); + "MAC address %pM successfully registered on device %s\n", + mac, card->dev->name); } else { - card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED; switch (rc) { case -EEXIST: dev_warn(&card->gdev->dev, @@ -142,19 +139,6 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac) return rc; } -static int qeth_l2_send_delmac(struct qeth_card *card, __u8 *mac) -{ - int rc; - - QETH_CARD_TEXT(card, 2, "L2Delmac"); - if (!(card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)) - return 0; - rc = qeth_l2_send_setdelmac(card, mac, IPA_CMD_DELVMAC); - if (rc == 0) - card->info.mac_bits &= ~QETH_LAYER2_MAC_REGISTERED; - return rc; -} - static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) { enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ? @@ -519,6 +503,7 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) { struct sockaddr *addr = p; struct qeth_card *card = dev->ml_priv; + u8 old_addr[ETH_ALEN]; int rc = 0; QETH_CARD_TEXT(card, 3, "setmac"); @@ -530,14 +515,35 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) return -EOPNOTSUPP; } QETH_CARD_HEX(card, 3, addr->sa_data, ETH_ALEN); + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) { QETH_CARD_TEXT(card, 3, "setmcREC"); return -ERESTARTSYS; } - rc = qeth_l2_send_delmac(card, &card->dev->dev_addr[0]); - if (!rc || (rc == -ENOENT)) - rc = qeth_l2_send_setmac(card, addr->sa_data); - return rc ? -EINVAL : 0; + + if (!qeth_card_hw_is_reachable(card)) { + ether_addr_copy(dev->dev_addr, addr->sa_data); + return 0; + } + + /* don't register the same address twice */ + if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) && + (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)) + return 0; + + /* add the new address, switch over, drop the old */ + rc = qeth_l2_send_setmac(card, addr->sa_data); + if (rc) + return rc; + ether_addr_copy(old_addr, dev->dev_addr); + ether_addr_copy(dev->dev_addr, addr->sa_data); + + if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED) + qeth_l2_remove_mac(card, old_addr); + card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED; + return 0; } static void qeth_promisc_to_bridge(struct qeth_card *card) @@ -1067,8 +1073,9 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) goto out_remove; } - if (card->info.type != QETH_CARD_TYPE_OSN) - qeth_l2_send_setmac(card, &card->dev->dev_addr[0]); + if (card->info.type != QETH_CARD_TYPE_OSN && + !qeth_l2_send_setmac(card, card->dev->dev_addr)) + card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED; if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) { if (card->info.hwtrap && @@ -1338,8 +1345,8 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len, qeth_prepare_control_data(card, len, iob); QETH_CARD_TEXT(card, 6, "osnoirqp"); spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags); - rc = ccw_device_start(card->write.ccwdev, &card->write.ccw, - (addr_t) iob, 0, 0); + rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw, + (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT); spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags); if (rc) { QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: " diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 95a7abd0ee92..486e65e3db26 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -339,8 +339,8 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, struct bpf_prog *old_prog); int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, - __u32 __user *prog_ids, u32 request_cnt, - __u32 __user *prog_cnt); + u32 *prog_ids, u32 request_cnt, + u32 *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index ebe41811ed34..b32cd2062f18 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -310,6 +310,8 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS * instead of the latter), any change to them will be overwritten * by kernel. Returns a negative error code or zero. + * @get_fecparam: Get the network device Forward Error Correction parameters. + * @set_fecparam: Set the network device Forward Error Correction parameters. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must diff --git a/include/net/ife.h b/include/net/ife.h index 44b9c00f7223..e117617e3c34 100644 --- a/include/net/ife.h +++ b/include/net/ife.h @@ -12,7 +12,8 @@ void *ife_encode(struct sk_buff *skb, u16 metalen); void *ife_decode(struct sk_buff *skb, u16 *metalen); -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen); +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen); int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval); diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index 5c40f118c0fa..df528a623548 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb) struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); +void llc_sk_stop_all_timers(struct sock *sk, bool sync); void llc_sk_free(struct sock *sk); void llc_sk_reset(struct sock *sk); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index d315b393abdd..ba03ec39efb3 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1572,13 +1572,32 @@ int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) return cnt; } +static bool bpf_prog_array_copy_core(struct bpf_prog **prog, + u32 *prog_ids, + u32 request_cnt) +{ + int i = 0; + + for (; *prog; prog++) { + if (*prog == &dummy_bpf_prog.prog) + continue; + prog_ids[i] = (*prog)->aux->id; + if (++i == request_cnt) { + prog++; + break; + } + } + + return !!(*prog); +} + int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, __u32 __user *prog_ids, u32 cnt) { struct bpf_prog **prog; unsigned long err = 0; - u32 i = 0, *ids; bool nospc; + u32 *ids; /* users of this function are doing: * cnt = bpf_prog_array_length(); @@ -1595,16 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, return -ENOMEM; rcu_read_lock(); prog = rcu_dereference(progs)->progs; - for (; *prog; prog++) { - if (*prog == &dummy_bpf_prog.prog) - continue; - ids[i] = (*prog)->aux->id; - if (++i == cnt) { - prog++; - break; - } - } - nospc = !!(*prog); + nospc = bpf_prog_array_copy_core(prog, ids, cnt); rcu_read_unlock(); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); @@ -1683,22 +1693,25 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, } int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, - __u32 __user *prog_ids, u32 request_cnt, - __u32 __user *prog_cnt) + u32 *prog_ids, u32 request_cnt, + u32 *prog_cnt) { + struct bpf_prog **prog; u32 cnt = 0; if (array) cnt = bpf_prog_array_length(array); - if (copy_to_user(prog_cnt, &cnt, sizeof(cnt))) - return -EFAULT; + *prog_cnt = cnt; /* return early if user requested only program count or nothing to copy */ if (!request_cnt || !cnt) return 0; - return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt); + /* this function is called under trace/bpf_trace.c: bpf_event_mutex */ + prog = rcu_dereference_check(array, 1)->progs; + return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC + : 0; } static void bpf_prog_free_deferred(struct work_struct *work) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 8dd9210d7db7..a3b21385e947 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -1442,9 +1442,6 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); - if (attr->value_size > KMALLOC_MAX_SIZE) - return ERR_PTR(-E2BIG); - err = bpf_tcp_ulp_register(); if (err && err != -EEXIST) return ERR_PTR(err); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d88e96d4e12c..56ba0f2a01db 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -977,6 +977,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; + u32 *ids, prog_cnt, ids_len; int ret; if (!capable(CAP_SYS_ADMIN)) @@ -985,16 +986,32 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) return -EINVAL; if (copy_from_user(&query, uquery, sizeof(query))) return -EFAULT; - if (query.ids_len > BPF_TRACE_MAX_PROGS) + + ids_len = query.ids_len; + if (ids_len > BPF_TRACE_MAX_PROGS) return -E2BIG; + ids = kcalloc(ids_len, sizeof(u32), GFP_USER | __GFP_NOWARN); + if (!ids) + return -ENOMEM; + /* + * The above kcalloc returns ZERO_SIZE_PTR when ids_len = 0, which + * is required when user only wants to check for uquery->prog_cnt. + * There is no need to check for it since the case is handled + * gracefully in bpf_prog_array_copy_info. + */ mutex_lock(&bpf_event_mutex); ret = bpf_prog_array_copy_info(event->tp_event->prog_array, - uquery->ids, - query.ids_len, - &uquery->prog_cnt); + ids, + ids_len, + &prog_cnt); mutex_unlock(&bpf_event_mutex); + if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || + copy_to_user(uquery->ids, ids, ids_len * sizeof(u32))) + ret = -EFAULT; + + kfree(ids); return ret; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 032e0fe45940..28a4c3490359 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1825,13 +1825,14 @@ static int compat_table_info(const struct ebt_table_info *info, { unsigned int size = info->entries_size; const void *entries = info->entries; - int ret; newinfo->entries_size = size; - - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); - if (ret) - return ret; + if (info->nentries) { + int ret = xt_compat_init_offsets(NFPROTO_BRIDGE, + info->nentries); + if (ret) + return ret; + } return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); diff --git a/net/ife/ife.c b/net/ife/ife.c index 7d1ec76e7f43..13bbf8cb6a39 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) int total_pull; u16 ifehdrln; + if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN)) + return NULL; + ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len); ifehdrln = ntohs(ifehdr->metalen); total_pull = skb->dev->hard_header_len + ifehdrln; @@ -92,12 +95,43 @@ struct meta_tlvhdr { __be16 len; }; +static bool __ife_tlv_meta_valid(const unsigned char *skbdata, + const unsigned char *ifehdr_end) +{ + const struct meta_tlvhdr *tlv; + u16 tlvlen; + + if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end)) + return false; + + tlv = (const struct meta_tlvhdr *)skbdata; + tlvlen = ntohs(tlv->len); + + /* tlv length field is inc header, check on minimum */ + if (tlvlen < NLA_HDRLEN) + return false; + + /* overflow by NLA_ALIGN check */ + if (NLA_ALIGN(tlvlen) < tlvlen) + return false; + + if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end)) + return false; + + return true; +} + /* Caller takes care of presenting data in network order */ -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen) +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen) { - struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + struct meta_tlvhdr *tlv; + + if (!__ife_tlv_meta_valid(skbdata, ifehdr_end)) + return NULL; + tlv = (struct meta_tlvhdr *)skbdata; *dlen = ntohs(tlv->len) - NLA_HDRLEN; *attrtype = ntohs(tlv->type); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 367def6ddeda..e51c644484dc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3868,11 +3868,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); - /* If the TCP option is too short, we can short cut */ - if (length < TCPOLEN_MD5SIG) - return NULL; - - while (length > 0) { + /* If not enough data remaining, we can short cut */ + while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index ccbfa83e4bb0..ce77bcc2490c 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -48,6 +48,34 @@ config NFT_CHAIN_ROUTE_IPV6 fields such as the source, destination, flowlabel, hop-limit and the packet mark. +if NF_NAT_IPV6 + +config NFT_CHAIN_NAT_IPV6 + tristate "IPv6 nf_tables nat chain support" + help + This option enables the "nat" chain for IPv6 in nf_tables. This + chain type is used to perform Network Address Translation (NAT) + packet transformations such as the source, destination address and + source and destination ports. + +config NFT_MASQ_IPV6 + tristate "IPv6 masquerade support for nf_tables" + depends on NFT_MASQ + select NF_NAT_MASQUERADE_IPV6 + help + This is the expression that provides IPv4 masquerading support for + nf_tables. + +config NFT_REDIR_IPV6 + tristate "IPv6 redirect support for nf_tables" + depends on NFT_REDIR + select NF_NAT_REDIRECT + help + This is the expression that provides IPv4 redirect support for + nf_tables. + +endif # NF_NAT_IPV6 + config NFT_REJECT_IPV6 select NF_REJECT_IPV6 default NFT_REJECT @@ -107,39 +135,12 @@ config NF_NAT_IPV6 if NF_NAT_IPV6 -config NFT_CHAIN_NAT_IPV6 - depends on NF_TABLES_IPV6 - tristate "IPv6 nf_tables nat chain support" - help - This option enables the "nat" chain for IPv6 in nf_tables. This - chain type is used to perform Network Address Translation (NAT) - packet transformations such as the source, destination address and - source and destination ports. - config NF_NAT_MASQUERADE_IPV6 tristate "IPv6 masquerade support" help This is the kernel functionality to provide NAT in the masquerade flavour (automatic source address selection) for IPv6. -config NFT_MASQ_IPV6 - tristate "IPv6 masquerade support for nf_tables" - depends on NF_TABLES_IPV6 - depends on NFT_MASQ - select NF_NAT_MASQUERADE_IPV6 - help - This is the expression that provides IPv4 masquerading support for - nf_tables. - -config NFT_REDIR_IPV6 - tristate "IPv6 redirect support for nf_tables" - depends on NF_TABLES_IPV6 - depends on NFT_REDIR - select NF_NAT_REDIRECT - help - This is the expression that provides IPv4 redirect support for - nf_tables. - endif # NF_NAT_IPV6 config IP6_NF_IPTABLES diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 49b954d6d0fa..cde7d8251377 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3975,6 +3975,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, @@ -3986,6 +3987,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index f343e6f0fc95..5fe139484919 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b8f9d45bfeb1..7f1e842ef05a 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -106,8 +106,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) return; /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */ - if (pd->tunnel) + if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); + pd->tunnel = NULL; + pd->session = NULL; + } } static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 7d0c963680e6..1fd9e145076a 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -619,6 +619,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); error = -EINVAL; + + if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6)) + goto end; + if (sp->sa_protocol != PX_PROTO_OL2TP) goto end; @@ -1618,8 +1625,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v) return; /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */ - if (pd->tunnel) + if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); + pd->tunnel = NULL; + pd->session = NULL; + } } static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 6d29b2b94e84..cb80ebb38311 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -189,7 +189,6 @@ static int llc_ui_release(struct socket *sock) { struct sock *sk = sock->sk; struct llc_sock *llc; - struct llc_sap *sap; if (unlikely(sk == NULL)) goto out; @@ -200,15 +199,19 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); - sap = llc->sap; - /* Hold this for release_sock(), so that llc_backlog_rcv() could still - * use it. - */ - llc_sap_hold(sap); - if (!sock_flag(sk, SOCK_ZAPPED)) + if (!sock_flag(sk, SOCK_ZAPPED)) { + struct llc_sap *sap = llc->sap; + + /* Hold this for release_sock(), so that llc_backlog_rcv() + * could still use it. + */ + llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); - release_sock(sk); - llc_sap_put(sap); + release_sock(sk); + llc_sap_put(sap); + } else { + release_sock(sk); + } if (llc->dev) dev_put(llc->dev); sock_put(sk); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 163121192aca..4d78375f9872 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1099,14 +1099,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb) int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb) { - struct llc_sock *llc = llc_sk(sk); - - del_timer(&llc->pf_cycle_timer.timer); - del_timer(&llc->ack_timer.timer); - del_timer(&llc->rej_sent_timer.timer); - del_timer(&llc->busy_state_timer.timer); - llc->ack_must_be_send = 0; - llc->ack_pf = 0; + llc_sk_stop_all_timers(sk, false); return 0; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 110e32bcb399..c0ac522b48a1 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -961,6 +961,26 @@ out: return sk; } +void llc_sk_stop_all_timers(struct sock *sk, bool sync) +{ + struct llc_sock *llc = llc_sk(sk); + + if (sync) { + del_timer_sync(&llc->pf_cycle_timer.timer); + del_timer_sync(&llc->ack_timer.timer); + del_timer_sync(&llc->rej_sent_timer.timer); + del_timer_sync(&llc->busy_state_timer.timer); + } else { + del_timer(&llc->pf_cycle_timer.timer); + del_timer(&llc->ack_timer.timer); + del_timer(&llc->rej_sent_timer.timer); + del_timer(&llc->busy_state_timer.timer); + } + + llc->ack_must_be_send = 0; + llc->ack_pf = 0; +} + /** * llc_sk_free - Frees a LLC socket * @sk - socket to free @@ -973,7 +993,7 @@ void llc_sk_free(struct sock *sk) llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ - llc_conn_ac_stop_all_timers(sk, NULL); + llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 704b3832dbad..44d8a55e9721 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -594,6 +594,7 @@ config NFT_QUOTA config NFT_REJECT default m if NETFILTER_ADVANCED=n tristate "Netfilter nf_tables reject support" + depends on !NF_TABLES_INET || (IPV6!=m || m) help This option adds the "reject" expression that you can use to explicitly deny and notify via TCP reset/ICMP informational errors diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 5ebde4b15810..f36098887ad0 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2384,11 +2384,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) strlcpy(cfg.mcast_ifn, dm->mcast_ifn, sizeof(cfg.mcast_ifn)); cfg.syncid = dm->syncid; - rtnl_lock(); - mutex_lock(&ipvs->sync_mutex); ret = start_sync_thread(ipvs, &cfg, dm->state); - mutex_unlock(&ipvs->sync_mutex); - rtnl_unlock(); } else { mutex_lock(&ipvs->sync_mutex); ret = stop_sync_thread(ipvs, dm->state); @@ -3481,12 +3477,8 @@ static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) if (ipvs->mixed_address_family_dests > 0) return -EINVAL; - rtnl_lock(); - mutex_lock(&ipvs->sync_mutex); ret = start_sync_thread(ipvs, &c, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); - mutex_unlock(&ipvs->sync_mutex); - rtnl_unlock(); return ret; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index fbaf3bd05b2e..001501e25625 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -49,6 +49,7 @@ #include <linux/kthread.h> #include <linux/wait.h> #include <linux/kernel.h> +#include <linux/sched/signal.h> #include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */ @@ -1360,15 +1361,9 @@ static void set_mcast_pmtudisc(struct sock *sk, int val) /* * Specifiy default interface for outgoing multicasts */ -static int set_mcast_if(struct sock *sk, char *ifname) +static int set_mcast_if(struct sock *sk, struct net_device *dev) { - struct net_device *dev; struct inet_sock *inet = inet_sk(sk); - struct net *net = sock_net(sk); - - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1396,19 +1391,14 @@ static int set_mcast_if(struct sock *sk, char *ifname) * in the in_addr structure passed in as a parameter. */ static int -join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) +join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev) { - struct net *net = sock_net(sk); struct ip_mreqn mreq; - struct net_device *dev; int ret; memset(&mreq, 0, sizeof(mreq)); memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr)); - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1423,15 +1413,10 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) #ifdef CONFIG_IP_VS_IPV6 static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, - char *ifname) + struct net_device *dev) { - struct net *net = sock_net(sk); - struct net_device *dev; int ret; - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -1443,24 +1428,18 @@ static int join_mcast_group6(struct sock *sk, struct in6_addr *addr, } #endif -static int bind_mcastif_addr(struct socket *sock, char *ifname) +static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) { - struct net *net = sock_net(sock->sk); - struct net_device *dev; __be32 addr; struct sockaddr_in sin; - dev = __dev_get_by_name(net, ifname); - if (!dev) - return -ENODEV; - addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); if (!addr) pr_err("You probably need to specify IP address on " "multicast interface.\n"); IP_VS_DBG(7, "binding socket with (%s) %pI4\n", - ifname, &addr); + dev->name, &addr); /* Now bind the socket with the address of multicast interface */ sin.sin_family = AF_INET; @@ -1493,7 +1472,8 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, /* * Set up sending multicast socket over UDP */ -static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) +static int make_send_sock(struct netns_ipvs *ipvs, int id, + struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1505,9 +1485,10 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); - return ERR_PTR(result); + goto error; } - result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn); + *sock_ret = sock; + result = set_mcast_if(sock->sk, dev); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; @@ -1522,7 +1503,7 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) set_sock_size(sock->sk, 1, result); if (AF_INET == ipvs->mcfg.mcast_af) - result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn); + result = bind_mcastif_addr(sock, dev); else result = 0; if (result < 0) { @@ -1538,19 +1519,18 @@ static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) goto error; } - return sock; + return 0; error: - sock_release(sock); - return ERR_PTR(result); + return result; } /* * Set up receiving multicast socket over UDP */ -static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, - int ifindex) +static int make_receive_sock(struct netns_ipvs *ipvs, int id, + struct net_device *dev, struct socket **sock_ret) { /* multicast addr */ union ipvs_sockaddr mcast_addr; @@ -1562,8 +1542,9 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); - return ERR_PTR(result); + goto error; } + *sock_ret = sock; /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = SK_CAN_REUSE; result = sysctl_sync_sock_size(ipvs); @@ -1571,7 +1552,7 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, set_sock_size(sock->sk, 0, result); get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); - sock->sk->sk_bound_dev_if = ifindex; + sock->sk->sk_bound_dev_if = dev->ifindex; result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); @@ -1582,21 +1563,20 @@ static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id, #ifdef CONFIG_IP_VS_IPV6 if (ipvs->bcfg.mcast_af == AF_INET6) result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr, - ipvs->bcfg.mcast_ifn); + dev); else #endif result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr, - ipvs->bcfg.mcast_ifn); + dev); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; } - return sock; + return 0; error: - sock_release(sock); - return ERR_PTR(result); + return result; } @@ -1778,13 +1758,12 @@ static int sync_thread_backup(void *data) int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { - struct ip_vs_sync_thread_data *tinfo; + struct ip_vs_sync_thread_data *tinfo = NULL; struct task_struct **array = NULL, *task; - struct socket *sock; struct net_device *dev; char *name; int (*threadfn)(void *data); - int id, count, hlen; + int id = 0, count, hlen; int result = -ENOMEM; u16 mtu, min_mtu; @@ -1792,6 +1771,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + /* Do not hold one mutex and then to block on another */ + for (;;) { + rtnl_lock(); + if (mutex_trylock(&ipvs->sync_mutex)) + break; + rtnl_unlock(); + mutex_lock(&ipvs->sync_mutex); + if (rtnl_trylock()) + break; + mutex_unlock(&ipvs->sync_mutex); + } + if (!ipvs->sync_state) { count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX); ipvs->threads_mask = count - 1; @@ -1810,7 +1801,8 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, dev = __dev_get_by_name(ipvs->net, c->mcast_ifn); if (!dev) { pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); - return -ENODEV; + result = -ENODEV; + goto out_early; } hlen = (AF_INET6 == c->mcast_af) ? sizeof(struct ipv6hdr) + sizeof(struct udphdr) : @@ -1827,26 +1819,30 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, c->sync_maxlen = mtu - hlen; if (state == IP_VS_STATE_MASTER) { + result = -EEXIST; if (ipvs->ms) - return -EEXIST; + goto out_early; ipvs->mcfg = *c; name = "ipvs-m:%d:%d"; threadfn = sync_thread_master; } else if (state == IP_VS_STATE_BACKUP) { + result = -EEXIST; if (ipvs->backup_threads) - return -EEXIST; + goto out_early; ipvs->bcfg = *c; name = "ipvs-b:%d:%d"; threadfn = sync_thread_backup; } else { - return -EINVAL; + result = -EINVAL; + goto out_early; } if (state == IP_VS_STATE_MASTER) { struct ipvs_master_sync_state *ms; + result = -ENOMEM; ipvs->ms = kcalloc(count, sizeof(ipvs->ms[0]), GFP_KERNEL); if (!ipvs->ms) goto out; @@ -1862,39 +1858,38 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, } else { array = kcalloc(count, sizeof(struct task_struct *), GFP_KERNEL); + result = -ENOMEM; if (!array) goto out; } - tinfo = NULL; for (id = 0; id < count; id++) { - if (state == IP_VS_STATE_MASTER) - sock = make_send_sock(ipvs, id); - else - sock = make_receive_sock(ipvs, id, dev->ifindex); - if (IS_ERR(sock)) { - result = PTR_ERR(sock); - goto outtinfo; - } + result = -ENOMEM; tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) - goto outsocket; + goto out; tinfo->ipvs = ipvs; - tinfo->sock = sock; + tinfo->sock = NULL; if (state == IP_VS_STATE_BACKUP) { tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, GFP_KERNEL); if (!tinfo->buf) - goto outtinfo; + goto out; } else { tinfo->buf = NULL; } tinfo->id = id; + if (state == IP_VS_STATE_MASTER) + result = make_send_sock(ipvs, id, dev, &tinfo->sock); + else + result = make_receive_sock(ipvs, id, dev, &tinfo->sock); + if (result < 0) + goto out; task = kthread_run(threadfn, tinfo, name, ipvs->gen, id); if (IS_ERR(task)) { result = PTR_ERR(task); - goto outtinfo; + goto out; } tinfo = NULL; if (state == IP_VS_STATE_MASTER) @@ -1911,20 +1906,20 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, ipvs->sync_state |= state; spin_unlock_bh(&ipvs->sync_buff_lock); + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); + /* increase the module use count */ ip_vs_use_count_inc(); return 0; -outsocket: - sock_release(sock); - -outtinfo: - if (tinfo) { - sock_release(tinfo->sock); - kfree(tinfo->buf); - kfree(tinfo); - } +out: + /* We do not need RTNL lock anymore, release it here so that + * sock_release below and in the kthreads can use rtnl_lock + * to leave the mcast group. + */ + rtnl_unlock(); count = id; while (count-- > 0) { if (state == IP_VS_STATE_MASTER) @@ -1932,13 +1927,23 @@ outtinfo: else kthread_stop(array[count]); } - kfree(array); - -out: if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) { kfree(ipvs->ms); ipvs->ms = NULL; } + mutex_unlock(&ipvs->sync_mutex); + if (tinfo) { + if (tinfo->sock) + sock_release(tinfo->sock); + kfree(tinfo->buf); + kfree(tinfo); + } + kfree(array); + return result; + +out_early: + mutex_unlock(&ipvs->sync_mutex); + rtnl_unlock(); return result; } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 8ef21d9f9a00..4b2b3d53acfc 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -252,7 +252,7 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { - return a->master == b->master && a->class == b->class && + return a->master == b->master && nf_ct_tuple_equal(&a->tuple, &b->tuple) && nf_ct_tuple_mask_equal(&a->mask, &b->mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && @@ -421,6 +421,9 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { if (expect_matches(i, expect)) { + if (i->class != expect->class) + return -EALREADY; + if (nf_ct_remove_expect(i)) break; } else if (expect_clash(i, expect)) { diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index 9fe0ddc333fb..277bbfe26478 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -9,6 +9,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> +#include <linux/kmemleak.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/rcupdate.h> @@ -71,6 +72,7 @@ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) rcu_read_unlock(); alloc = max(newlen, NF_CT_EXT_PREALLOC); + kmemleak_not_leak(old); new = __krealloc(old, alloc, gfp); if (!new) return NULL; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 4dbb5bad4363..908e51e2dc2b 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -938,11 +938,19 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, datalen, rtp_exp, rtcp_exp, mediaoff, medialen, daddr); else { - if (nf_ct_expect_related(rtp_exp) == 0) { - if (nf_ct_expect_related(rtcp_exp) != 0) - nf_ct_unexpect_related(rtp_exp); - else + /* -EALREADY handling works around end-points that send + * SDP messages with identical port but different media type, + * we pretend expectation was set up. + */ + int errp = nf_ct_expect_related(rtp_exp); + + if (errp == 0 || errp == -EALREADY) { + int errcp = nf_ct_expect_related(rtcp_exp); + + if (errcp == 0 || errcp == -EALREADY) ret = NF_ACCEPT; + else if (errp == 0) + nf_ct_unexpect_related(rtp_exp); } } nf_ct_expect_put(rtcp_exp); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 9134cc429ad4..04d4e3772584 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2361,41 +2361,46 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { - if (nft_is_active_next(net, old_rule)) { - trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, - old_rule); - if (trans == NULL) { - err = -ENOMEM; - goto err2; - } - nft_deactivate_next(net, old_rule); - chain->use--; - list_add_tail_rcu(&rule->list, &old_rule->list); - } else { + if (!nft_is_active_next(net, old_rule)) { err = -ENOENT; goto err2; } - } else if (nlh->nlmsg_flags & NLM_F_APPEND) - if (old_rule) - list_add_rcu(&rule->list, &old_rule->list); - else - list_add_tail_rcu(&rule->list, &chain->rules); - else { - if (old_rule) - list_add_tail_rcu(&rule->list, &old_rule->list); - else - list_add_rcu(&rule->list, &chain->rules); - } + trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, + old_rule); + if (trans == NULL) { + err = -ENOMEM; + goto err2; + } + nft_deactivate_next(net, old_rule); + chain->use--; - if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { - err = -ENOMEM; - goto err3; + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + list_add_tail_rcu(&rule->list, &old_rule->list); + } else { + if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { + err = -ENOMEM; + goto err2; + } + + if (nlh->nlmsg_flags & NLM_F_APPEND) { + if (old_rule) + list_add_rcu(&rule->list, &old_rule->list); + else + list_add_tail_rcu(&rule->list, &chain->rules); + } else { + if (old_rule) + list_add_tail_rcu(&rule->list, &old_rule->list); + else + list_add_rcu(&rule->list, &chain->rules); + } } chain->use++; return 0; -err3: - list_del_rcu(&rule->list); err2: nf_tables_rule_destroy(&ctx, rule); err1: @@ -3207,18 +3212,20 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, err = ops->init(set, &desc, nla); if (err < 0) - goto err2; + goto err3; err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err3; + goto err4; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err3: +err4: ops->destroy(set); +err3: + kfree(set->name); err2: kvfree(set); err1: @@ -5738,7 +5745,7 @@ static void nft_chain_commit_update(struct nft_trans *trans) struct nft_base_chain *basechain; if (nft_trans_chain_name(trans)) - strcpy(trans->ctx.chain->name, nft_trans_chain_name(trans)); + swap(trans->ctx.chain->name, nft_trans_chain_name(trans)); if (!nft_is_base_chain(trans->ctx.chain)) return; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index 773da82190dc..94df000abb92 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -36,11 +36,10 @@ MODULE_ALIAS("ipt_connmark"); MODULE_ALIAS("ip6t_connmark"); static unsigned int -connmark_tg_shift(struct sk_buff *skb, - const struct xt_connmark_tginfo1 *info, - u8 shift_bits, u8 shift_dir) +connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) { enum ip_conntrack_info ctinfo; + u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; @@ -51,34 +50,39 @@ connmark_tg_shift(struct sk_buff *skb, switch (info->mode) { case XT_CONNMARK_SET: newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + if (info->shift_dir == D_SHIFT_RIGHT) + newmark >>= info->shift_bits; else - newmark <<= shift_bits; + newmark <<= info->shift_bits; + if (ct->mark != newmark) { ct->mark = newmark; nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_SAVE: - newmark = (ct->mark & ~info->ctmask) ^ - (skb->mark & info->nfmask); - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + new_targetmark = (skb->mark & info->nfmask); + if (info->shift_dir == D_SHIFT_RIGHT) + new_targetmark >>= info->shift_bits; else - newmark <<= shift_bits; + new_targetmark <<= info->shift_bits; + + newmark = (ct->mark & ~info->ctmask) ^ + new_targetmark; if (ct->mark != newmark) { ct->mark = newmark; nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - newmark = (skb->mark & ~info->nfmask) ^ - (ct->mark & info->ctmask); - if (shift_dir == D_SHIFT_RIGHT) - newmark >>= shift_bits; + new_targetmark = (ct->mark & info->ctmask); + if (info->shift_dir == D_SHIFT_RIGHT) + new_targetmark >>= info->shift_bits; else - newmark <<= shift_bits; + new_targetmark <<= info->shift_bits; + + newmark = (skb->mark & ~info->nfmask) ^ + new_targetmark; skb->mark = newmark; break; } @@ -89,8 +93,14 @@ static unsigned int connmark_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo1 *info = par->targinfo; - - return connmark_tg_shift(skb, info, 0, 0); + const struct xt_connmark_tginfo2 info2 = { + .ctmark = info->ctmark, + .ctmask = info->ctmask, + .nfmask = info->nfmask, + .mode = info->mode, + }; + + return connmark_tg_shift(skb, &info2); } static unsigned int @@ -98,8 +108,7 @@ connmark_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_connmark_tginfo2 *info = par->targinfo; - return connmark_tg_shift(skb, (const struct xt_connmark_tginfo1 *)info, - info->shift_bits, info->shift_dir); + return connmark_tg_shift(skb, info); } static int connmark_tg_check(const struct xt_tgchk_param *par) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c31b0687396a..01f3515cada0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -329,11 +329,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) skb_set_queue_mapping(skb, queue_index); } -/* register_prot_hook must be invoked with the po->bind_lock held, +/* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ -static void register_prot_hook(struct sock *sk) +static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); @@ -348,8 +348,13 @@ static void register_prot_hook(struct sock *sk) } } -/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock - * held. If the sync parameter is true, we will temporarily drop +static void register_prot_hook(struct sock *sk) +{ + lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); + __register_prot_hook(sk); +} + +/* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the @@ -359,6 +364,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); + lockdep_assert_held_once(&po->bind_lock); + po->running = 0; if (po->fanout) @@ -3252,7 +3259,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, if (proto) { po->prot_hook.type = proto; - register_prot_hook(sk); + __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); @@ -3732,12 +3739,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_loss = !!val; - return 0; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_loss = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_AUXDATA: { @@ -3748,7 +3761,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->auxdata = !!val; + release_sock(sk); return 0; } case PACKET_ORIGDEV: @@ -3760,7 +3775,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->origdev = !!val; + release_sock(sk); return 0; } case PACKET_VNET_HDR: @@ -3769,15 +3786,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (sock->type != SOCK_RAW) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->has_vnet_hdr = !!val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->has_vnet_hdr = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_TIMESTAMP: { @@ -3815,11 +3837,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_tx_has_off = !!val; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_tx_has_off = !!val; + ret = 0; + } + release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: diff --git a/net/packet/internal.h b/net/packet/internal.h index a1d2b2319ae9..3bb7c5fb3bff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -112,10 +112,12 @@ struct packet_sock { int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; - unsigned int running:1, /* prot_hook is attached*/ - auxdata:1, + unsigned int running; /* bind_lock must be held */ + unsigned int auxdata:1, /* writer must hold sock lock */ origdev:1, - has_vnet_hdr:1; + has_vnet_hdr:1, + tp_loss:1, + tp_tx_has_off:1; int pressure; int ifindex; /* bound device */ __be16 num; @@ -125,8 +127,6 @@ struct packet_sock { enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; - unsigned int tp_loss:1; - unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index a5994cf0512b..8527cfdc446d 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -652,7 +652,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, } } - return 0; + return -ENOENT; } static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, @@ -682,7 +682,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u16 mtype; u16 dlen; - curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); + curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, + &dlen, NULL); + if (!curr_data) { + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); + return TC_ACT_SHOT; + } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 805b139756db..092bebc70048 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err) static void strp_start_timer(struct strparser *strp, long timeo) { - if (timeo) + if (timeo && timeo != LONG_MAX) mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo); } diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 9cf83f895d98..5e1ab2f0eb79 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -12,3 +12,6 @@ test_tcpbpf_user test_verifier_log feature test_libbpf_open +test_sock +test_sock_addr +urandom_read diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 73bb20cfb9b7..f4d99fabc56d 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -13,6 +13,7 @@ #include <bpf/bpf.h> #include "cgroup_helpers.h" +#include "bpf_rlimit.h" #ifndef ARRAY_SIZE # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index d488f20926e8..2950f80ba7fb 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -15,6 +15,7 @@ #include <bpf/libbpf.h> #include "cgroup_helpers.h" +#include "bpf_rlimit.h" #define CG_PATH "/foo" #define CONNECT4_PROG_PATH "./connect4_prog.o" diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh index c6e1dcf992c4..9832a875a828 100755 --- a/tools/testing/selftests/bpf/test_sock_addr.sh +++ b/tools/testing/selftests/bpf/test_sock_addr.sh @@ -4,7 +4,7 @@ set -eu ping_once() { - ping -q -c 1 -W 1 ${1%%/*} >/dev/null 2>&1 + ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1 } wait_for_ip() @@ -13,7 +13,7 @@ wait_for_ip() echo -n "Wait for testing IPv4/IPv6 to become available " for _i in $(seq ${MAX_PING_TRIES}); do echo -n "." - if ping_once ${TEST_IPv4} && ping_once ${TEST_IPv6}; then + if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then echo " OK" return fi |