diff options
102 files changed, 965 insertions, 400 deletions
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index d3e5dd26db12..e3abfbd32f71 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -706,9 +706,9 @@ num_unsol_na unsolicited IPv6 Neighbor Advertisements) to be issued after a failover event. As soon as the link is up on the new slave (possibly immediately) a peer notification is sent on the - bonding device and each VLAN sub-device. This is repeated at - each link monitor interval (arp_interval or miimon, whichever - is active) if the number is greater than 1. + bonding device and each VLAN sub-device. This is repeated at + the rate specified by peer_notif_delay if the number is + greater than 1. The valid range is 0 - 255; the default value is 1. These options affect only the active-backup mode. These options were added for @@ -727,6 +727,16 @@ packets_per_slave The valid range is 0 - 65535; the default value is 1. This option has effect only in balance-rr mode. +peer_notif_delay + + Specify the delay, in milliseconds, between each peer + notification (gratuitous ARP and unsolicited IPv6 Neighbor + Advertisement) when they are issued after a failover event. + This delay should be a multiple of the link monitor interval + (arp_interval or miimon, whichever is active). The default + value is 0 which means to match the value of the link monitor + interval. + primary A string (eth0, eth2, etc) specifying which slave is the diff --git a/MAINTAINERS b/MAINTAINERS index 500cdb68ccbc..2d766db67bb0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3108,9 +3108,9 @@ S: Maintained F: arch/riscv/net/ BPF JIT for S390 +M: Ilya Leoshkevich <iii@linux.ibm.com> M: Heiko Carstens <heiko.carstens@de.ibm.com> M: Vasily Gorbik <gor@linux.ibm.com> -M: Christian Borntraeger <borntraeger@de.ibm.com> L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Maintained @@ -14873,6 +14873,7 @@ F: Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt SOCIONEXT (SNI) NETSEC NETWORK DRIVER M: Jassi Brar <jaswinder.singh@linaro.org> +M: Ilias Apalodimas <ilias.apalodimas@linaro.org> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/socionext/netsec.c diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 43a14579e80e..df51680e8931 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1379,7 +1379,6 @@ init_tsq(struct idt77252_dev *card) printk("%s: can't allocate TSQ.\n", card->name); return -1; } - memset(card->tsq.base, 0, TSQSIZE); card->tsq.last = card->tsq.base + TSQ_NUM_ENTRIES - 1; card->tsq.next = card->tsq.last; diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 4c99739b937e..0e224232f746 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -1955,6 +1955,9 @@ hfcsusb_probe(struct usb_interface *intf, const struct usb_device_id *id) /* get endpoint base */ idx = ((ep_addr & 0x7f) - 1) * 2; + if (idx > 15) + return -EIO; + if (ep_addr & 0x80) idx++; attr = ep->desc.bmAttributes; diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c index b2f10b6ad6e5..bbb2575d4728 100644 --- a/drivers/net/caif/caif_hsi.c +++ b/drivers/net/caif/caif_hsi.c @@ -1455,7 +1455,7 @@ static void __exit cfhsi_exit_module(void) rtnl_lock(); list_for_each_safe(list_node, n, &cfhsi_list) { cfhsi = list_entry(list_node, struct cfhsi, list); - unregister_netdev(cfhsi->ndev); + unregister_netdevice(cfhsi->ndev); } rtnl_unlock(); } diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 72a57c6cd254..8b69d0d7e726 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -35,6 +35,7 @@ #include <linux/regmap.h> #include <linux/reset.h> #include <linux/clk.h> +#include <linux/io.h> /* For our NAPI weight bigger does *NOT* mean better - it means more * D-cache misses and lots more wasted cycles than we'll ever @@ -1724,17 +1725,19 @@ static int ag71xx_probe(struct platform_device *pdev) ag->stop_desc = dmam_alloc_coherent(&pdev->dev, sizeof(struct ag71xx_desc), &ag->stop_desc_dma, GFP_KERNEL); - if (!ag->stop_desc) + if (!ag->stop_desc) { + err = -ENOMEM; goto err_free; + } ag->stop_desc->data = 0; ag->stop_desc->ctrl = 0; ag->stop_desc->next = (u32)ag->stop_desc_dma; mac_addr = of_get_mac_address(np); - if (mac_addr) + if (!IS_ERR(mac_addr)) memcpy(ndev->dev_addr, mac_addr, ETH_ALEN); - if (!mac_addr || !is_valid_ether_addr(ndev->dev_addr)) { + if (IS_ERR(mac_addr) || !is_valid_ether_addr(ndev->dev_addr)) { netif_err(ag, probe, ndev, "invalid MAC address, using random address\n"); eth_random_addr(ndev->dev_addr); } diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index 7c767ce9aafa..b5c6dc914720 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1060,8 +1060,6 @@ static s32 atl1_setup_ring_resources(struct atl1_adapter *adapter) goto err_nomem; } - memset(ring_header->desc, 0, ring_header->size); - /* init TPD ring */ tpd_ring->dma = ring_header->dma; offset = (tpd_ring->dma & 0x7) ? (8 - (ring_header->dma & 0x7)) : 0; diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index 3a3fb5ce0fee..3aba38322717 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -291,7 +291,6 @@ static s32 atl2_setup_ring_resources(struct atl2_adapter *adapter) &adapter->ring_dma); if (!adapter->ring_vir_addr) return -ENOMEM; - memset(adapter->ring_vir_addr, 0, adapter->ring_size); /* Init TXD Ring */ adapter->txd_dma = adapter->ring_dma ; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 3f632028eff0..7134d2c3eb1c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2677,8 +2677,6 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) mapping = txr->tx_push_mapping + sizeof(struct tx_push_bd); txr->data_mapping = cpu_to_le64(mapping); - - memset(txr->tx_push, 0, sizeof(struct tx_push_bd)); } qidx = bp->tc_to_qidx[j]; ring->queue_id = bp->q_info[qidx].queue_id; @@ -3077,7 +3075,7 @@ static int bnxt_alloc_vnics(struct bnxt *bp) int num_vnics = 1; #ifdef CONFIG_RFS_ACCEL - if (bp->flags & BNXT_FLAG_RFS) + if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS) num_vnics += bp->rx_nr_rings; #endif @@ -7188,6 +7186,9 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp) #ifdef CONFIG_RFS_ACCEL int i, rc = 0; + if (bp->flags & BNXT_FLAG_CHIP_P5) + return 0; + for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_vnic_info *vnic; u16 vnic_id = i + 1; @@ -9647,7 +9648,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, return -ENOMEM; vnics = 1; - if (bp->flags & BNXT_FLAG_RFS) + if ((bp->flags & (BNXT_FLAG_RFS | BNXT_FLAG_CHIP_P5)) == BNXT_FLAG_RFS) vnics += rx_rings; if (bp->flags & BNXT_FLAG_AGG_RINGS) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 34466b827dde..a2b57807453b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3083,39 +3083,42 @@ static void bcmgenet_timeout(struct net_device *dev) netif_tx_wake_all_queues(dev); } -#define MAX_MC_COUNT 16 +#define MAX_MDF_FILTER 17 static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv, unsigned char *addr, - int *i, - int *mc) + int *i) { - u32 reg; - bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1], UMAC_MDF_ADDR + (*i * 4)); bcmgenet_umac_writel(priv, addr[2] << 24 | addr[3] << 16 | addr[4] << 8 | addr[5], UMAC_MDF_ADDR + ((*i + 1) * 4)); - reg = bcmgenet_umac_readl(priv, UMAC_MDF_CTRL); - reg |= (1 << (MAX_MC_COUNT - *mc)); - bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL); *i += 2; - (*mc)++; } static void bcmgenet_set_rx_mode(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); struct netdev_hw_addr *ha; - int i, mc; + int i, nfilter; u32 reg; netif_dbg(priv, hw, dev, "%s: %08X\n", __func__, dev->flags); - /* Promiscuous mode */ + /* Number of filters needed */ + nfilter = netdev_uc_count(dev) + netdev_mc_count(dev) + 2; + + /* + * Turn on promicuous mode for three scenarios + * 1. IFF_PROMISC flag is set + * 2. IFF_ALLMULTI flag is set + * 3. The number of filters needed exceeds the number filters + * supported by the hardware. + */ reg = bcmgenet_umac_readl(priv, UMAC_CMD); - if (dev->flags & IFF_PROMISC) { + if ((dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) || + (nfilter > MAX_MDF_FILTER)) { reg |= CMD_PROMISC; bcmgenet_umac_writel(priv, reg, UMAC_CMD); bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL); @@ -3125,32 +3128,24 @@ static void bcmgenet_set_rx_mode(struct net_device *dev) bcmgenet_umac_writel(priv, reg, UMAC_CMD); } - /* UniMac doesn't support ALLMULTI */ - if (dev->flags & IFF_ALLMULTI) { - netdev_warn(dev, "ALLMULTI is not supported\n"); - return; - } - /* update MDF filter */ i = 0; - mc = 0; /* Broadcast */ - bcmgenet_set_mdf_addr(priv, dev->broadcast, &i, &mc); + bcmgenet_set_mdf_addr(priv, dev->broadcast, &i); /* my own address.*/ - bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i, &mc); - /* Unicast list*/ - if (netdev_uc_count(dev) > (MAX_MC_COUNT - mc)) - return; + bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i); - if (!netdev_uc_empty(dev)) - netdev_for_each_uc_addr(ha, dev) - bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); - /* Multicast */ - if (netdev_mc_empty(dev) || netdev_mc_count(dev) >= (MAX_MC_COUNT - mc)) - return; + /* Unicast */ + netdev_for_each_uc_addr(ha, dev) + bcmgenet_set_mdf_addr(priv, ha->addr, &i); + /* Multicast */ netdev_for_each_mc_addr(ha, dev) - bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); + bcmgenet_set_mdf_addr(priv, ha->addr, &i); + + /* Enable filters */ + reg = GENMASK(MAX_MDF_FILTER - 1, MAX_MDF_FILTER - nfilter); + bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL); } /* Set the hardware MAC address. */ diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index fcf20a8f92d9..032224178b64 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -218,15 +218,13 @@ int octeon_setup_iq(struct octeon_device *oct, return 0; } oct->instr_queue[iq_no] = - vmalloc_node(sizeof(struct octeon_instr_queue), numa_node); + vzalloc_node(sizeof(struct octeon_instr_queue), numa_node); if (!oct->instr_queue[iq_no]) oct->instr_queue[iq_no] = - vmalloc(sizeof(struct octeon_instr_queue)); + vzalloc(sizeof(struct octeon_instr_queue)); if (!oct->instr_queue[iq_no]) return 1; - memset(oct->instr_queue[iq_no], 0, - sizeof(struct octeon_instr_queue)); oct->instr_queue[iq_no]->q_index = q_index; oct->instr_queue[iq_no]->app_ctx = app_ctx; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index ba6c153ee45c..60218dc676a8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -207,7 +207,6 @@ static int t4_sched_queue_bind(struct port_info *pi, struct ch_sched_queue *p) goto out_err; /* Bind queue to specified class */ - memset(qe, 0, sizeof(*qe)); qe->cntxt_id = qid; memcpy(&qe->param, p, sizeof(qe->param)); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 82015c8a5ed7..b7a246b33599 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4697,8 +4697,12 @@ int be_update_queues(struct be_adapter *adapter) struct net_device *netdev = adapter->netdev; int status; - if (netif_running(netdev)) + if (netif_running(netdev)) { + /* device cannot transmit now, avoid dev_watchdog timeouts */ + netif_carrier_off(netdev); + be_close(netdev); + } be_cancel_worker(adapter); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 9d459ccf251d..e5610a4da539 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3144,8 +3144,6 @@ static int fec_enet_init(struct net_device *ndev) return -ENOMEM; } - memset(cbd_base, 0, bd_size); - /* Get the Ethernet address */ fec_get_mac(ndev); /* make sure MAC we just acquired is programmed into the hw */ diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 24f16e3368cd..497298752381 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -232,7 +232,7 @@ abort_with_mgmt_vector: abort_with_msix_enabled: pci_disable_msix(priv->pdev); abort_with_msix_vectors: - kfree(priv->msix_vectors); + kvfree(priv->msix_vectors); priv->msix_vectors = NULL; return err; } @@ -256,7 +256,7 @@ static void gve_free_notify_blocks(struct gve_priv *priv) priv->ntfy_blocks = NULL; free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); pci_disable_msix(priv->pdev); - kfree(priv->msix_vectors); + kvfree(priv->msix_vectors); priv->msix_vectors = NULL; } @@ -445,12 +445,12 @@ static int gve_alloc_rings(struct gve_priv *priv) return 0; free_rx: - kfree(priv->rx); + kvfree(priv->rx); priv->rx = NULL; free_tx_queue: gve_tx_free_rings(priv); free_tx: - kfree(priv->tx); + kvfree(priv->tx); priv->tx = NULL; return err; } @@ -500,7 +500,7 @@ static void gve_free_rings(struct gve_priv *priv) gve_remove_napi(priv, ntfy_idx); } gve_tx_free_rings(priv); - kfree(priv->tx); + kvfree(priv->tx); priv->tx = NULL; } if (priv->rx) { @@ -509,7 +509,7 @@ static void gve_free_rings(struct gve_priv *priv) gve_remove_napi(priv, ntfy_idx); } gve_rx_free_rings(priv); - kfree(priv->rx); + kvfree(priv->rx); priv->rx = NULL; } } @@ -592,9 +592,9 @@ static void gve_free_queue_page_list(struct gve_priv *priv, gve_free_page(&priv->pdev->dev, qpl->pages[i], qpl->page_buses[i], gve_qpl_dma_dir(priv, id)); - kfree(qpl->page_buses); + kvfree(qpl->page_buses); free_pages: - kfree(qpl->pages); + kvfree(qpl->pages); priv->num_registered_pages -= qpl->num_entries; } @@ -635,7 +635,7 @@ static int gve_alloc_qpls(struct gve_priv *priv) free_qpls: for (j = 0; j <= i; j++) gve_free_queue_page_list(priv, j); - kfree(priv->qpls); + kvfree(priv->qpls); return err; } @@ -644,12 +644,12 @@ static void gve_free_qpls(struct gve_priv *priv) int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv); int i; - kfree(priv->qpl_cfg.qpl_id_map); + kvfree(priv->qpl_cfg.qpl_id_map); for (i = 0; i < num_qpls; i++) gve_free_queue_page_list(priv, i); - kfree(priv->qpls); + kvfree(priv->qpls); } /* Use this to schedule a reset when the device is capable of continuing @@ -1192,7 +1192,6 @@ abort_with_enabled: pci_disable_device(pdev); return -ENXIO; } -EXPORT_SYMBOL(gve_probe); static void gve_remove(struct pci_dev *pdev) { diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index c1aeabd1c594..1914b8350da7 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -35,7 +35,7 @@ static void gve_rx_free_ring(struct gve_priv *priv, int idx) gve_unassign_qpl(priv, rx->data.qpl->id); rx->data.qpl = NULL; - kfree(rx->data.page_info); + kvfree(rx->data.page_info); slots = rx->data.mask + 1; bytes = sizeof(*rx->data.data_ring) * slots; @@ -168,7 +168,7 @@ abort_with_q_resources: rx->q_resources, rx->q_resources_bus); rx->q_resources = NULL; abort_filled: - kfree(rx->data.page_info); + kvfree(rx->data.page_info); abort_with_slots: bytes = sizeof(*rx->data.data_ring) * slots; dma_free_coherent(hdev, bytes, rx->data.data_ring, rx->data.data_bus); diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 76b7b7b85e35..0b668357db4d 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -582,11 +582,6 @@ jme_setup_tx_resources(struct jme_adapter *jme) if (unlikely(!(txring->bufinf))) goto err_free_txring; - /* - * Initialize Transmit Descriptors - */ - memset(txring->alloc, 0, TX_RING_ALLOC_SIZE(jme->tx_ring_size)); - return 0; err_free_txring: diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 35a92fd2cf39..9ac854c2b371 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -2558,8 +2558,6 @@ static int skge_up(struct net_device *dev) goto free_pci_mem; } - memset(skge->mem, 0, skge->mem_size); - err = skge_ring_alloc(&skge->rx_ring, skge->mem, skge->dma); if (err) goto free_pci_mem; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index fe518c854d1f..f518312ffe69 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4917,6 +4917,13 @@ static const struct dmi_system_id msi_blacklist[] = { DMI_MATCH(DMI_PRODUCT_NAME, "P-79"), }, }, + { + .ident = "ASUS P5W DH Deluxe", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTEK COMPUTER INC"), + DMI_MATCH(DMI_PRODUCT_NAME, "P5W DH Deluxe"), + }, + }, {} }; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index b20b3a5a1ebb..c39d7f4ab1d4 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2548,8 +2548,10 @@ static int mtk_probe(struct platform_device *pdev) continue; err = mtk_add_mac(eth, mac_np); - if (err) + if (err) { + of_node_put(mac_np); goto err_deinit_hw; + } } if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index a5be27772b8e..c790a5fcea73 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -1013,8 +1013,6 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent, dma_list[i] = t; eq->page_list[i].map = t; - - memset(eq->page_list[i].buf, 0, PAGE_SIZE); } eq->eqn = mlx4_bitmap_alloc(&priv->eq_table.bitmap); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 2d6436257f9d..cc096f6011d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1499,7 +1499,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_NONE; if (dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | + ~(BIT(FLOW_DISSECTOR_KEY_META) | + BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | BIT(FLOW_DISSECTOR_KEY_VLAN) | @@ -1522,11 +1523,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) || - flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) || - flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID) || - flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) || - flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) { + if (mlx5e_get_tc_tun(filter_dev)) { if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level)) return -EOPNOTSUPP; @@ -2647,6 +2644,10 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, family = ip_tunnel_info_af(tun_info); key.ip_tun_key = &tun_info->key; key.tc_tunnel = mlx5e_get_tc_tun(mirred_dev); + if (!key.tc_tunnel) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported tunnel"); + return -EOPNOTSUPP; + } hash_key = hash_encap_info(&key); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 3b04d8927fb1..1f3891fde2eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2450,7 +2450,6 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, MLX5_SET(query_vport_counter_in, in, vport_number, vport->vport); MLX5_SET(query_vport_counter_in, in, other_vport, 1); - memset(out, 0, outlen); err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen); if (err) goto free_out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 957d9b09dc3f..089ae4d48a82 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1134,7 +1134,6 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) } /* create send-to-vport group */ - memset(flow_group_in, 0, inlen); MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_MISC_PARAMETERS); @@ -1293,8 +1292,6 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports) return -ENOMEM; /* create vport rx group */ - memset(flow_group_in, 0, inlen); - esw_set_flow_group_source_port(esw, flow_group_in); MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 2fe6923f7ce0..9314777d99e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -597,7 +597,7 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, err = devlink_fmsg_arr_pair_nest_end(fmsg); free_data: - kfree(cr_data); + kvfree(cr_data); return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 051b19388a81..615455a21567 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -847,7 +847,6 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox, &mem_item->mapaddr); if (!mem_item->buf) return -ENOMEM; - memset(mem_item->buf, 0, mem_item->size); q->elem_info = kcalloc(q->count, sizeof(*q->elem_info), GFP_KERNEL); if (!q->elem_info) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index a252b080dda9..131f62ce9297 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -830,6 +830,7 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port, struct tc_prio_qopt_offload *p); /* spectrum_fid.c */ +bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index); bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid); struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp, u16 fid_index); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c index b25048c6c761..21296fa7f7fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c @@ -408,14 +408,6 @@ static int mlxsw_sp_port_dcb_app_update(struct mlxsw_sp_port *mlxsw_sp_port) have_dscp = mlxsw_sp_port_dcb_app_prio_dscp_map(mlxsw_sp_port, &prio_map); - if (!have_dscp) { - err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port, - MLXSW_REG_QPTS_TRUST_STATE_PCP); - if (err) - netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L2\n"); - return err; - } - mlxsw_sp_port_dcb_app_dscp_prio_map(mlxsw_sp_port, default_prio, &dscp_map); err = mlxsw_sp_port_dcb_app_update_qpdpm(mlxsw_sp_port, @@ -432,6 +424,14 @@ static int mlxsw_sp_port_dcb_app_update(struct mlxsw_sp_port *mlxsw_sp_port) return err; } + if (!have_dscp) { + err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port, + MLXSW_REG_QPTS_TRUST_STATE_PCP); + if (err) + netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L2\n"); + return err; + } + err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port, MLXSW_REG_QPTS_TRUST_STATE_DSCP); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c index 46baf3b44309..8df3cb21baa6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c @@ -126,6 +126,16 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = { [MLXSW_SP_FLOOD_TYPE_MC] = mlxsw_sp_sfgc_mc_packet_types, }; +bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index) +{ + enum mlxsw_sp_fid_type fid_type = MLXSW_SP_FID_TYPE_DUMMY; + struct mlxsw_sp_fid_family *fid_family; + + fid_family = mlxsw_sp->fid_core->fid_family_arr[fid_type]; + + return fid_family->start_index == fid_index; +} + bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid) { return fid->fid_family->lag_vid_valid; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 50111f228d77..5ecb45118400 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2468,6 +2468,9 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, goto just_remove; } + if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid)) + goto just_remove; + mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid); if (!mlxsw_sp_port_vlan) { netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n"); @@ -2527,6 +2530,9 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, goto just_remove; } + if (mlxsw_sp_fid_is_dummy(mlxsw_sp, fid)) + goto just_remove; + mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_fid(mlxsw_sp_port, fid); if (!mlxsw_sp_port_vlan) { netdev_err(mlxsw_sp_port->dev, "Failed to find a matching {Port, VID} following FDB notification\n"); diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 58bde1a9eacb..2451d4a96490 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -291,8 +291,10 @@ static int mscc_ocelot_probe(struct platform_device *pdev) continue; err = ocelot_probe_port(ocelot, port, regs, phy); - if (err) + if (err) { + of_node_put(portnp); return err; + } phy_mode = of_get_phy_mode(portnp); if (phy_mode < 0) @@ -318,6 +320,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) dev_err(ocelot->dev, "invalid phy mode for port%d, (Q)SGMII only\n", port); + of_node_put(portnp); return -EINVAL; } diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 3b2ae1a21678..e0b2bf327905 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -747,7 +747,6 @@ static int init_shared_mem(struct s2io_nic *nic) return -ENOMEM; } mem_allocated += size; - memset(tmp_v_addr, 0, size); size = sizeof(struct rxd_info) * rxd_count[nic->rxd_mode]; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c index 433052f734ed..5e9f8ee99800 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ctx.c @@ -442,10 +442,8 @@ nx_fw_cmd_create_tx_ctx(struct netxen_adapter *adapter) goto out_free_rq; } - memset(rq_addr, 0, rq_size); prq = rq_addr; - memset(rsp_addr, 0, rsp_size); prsp = rsp_addr; prq->host_rsp_dma_addr = cpu_to_le64(rsp_phys_addr); @@ -755,7 +753,6 @@ int netxen_alloc_hw_resources(struct netxen_adapter *adapter) return -ENOMEM; } - memset(addr, 0, sizeof(struct netxen_ring_ctx)); recv_ctx->hwctx = addr; recv_ctx->hwctx->ctx_id = cpu_to_le32(port); recv_ctx->hwctx->cmd_consumer_offset = diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index efef5453b94f..0637c6752a78 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4667,6 +4667,143 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp) /* disable aspm and clock request before access ephy */ rtl_hw_aspm_clkreq_enable(tp, false); rtl_ephy_init(tp, e_info_8411_2); + + /* The following Realtek-provided magic fixes an issue with the RX unit + * getting confused after the PHY having been powered-down. + */ + r8168_mac_ocp_write(tp, 0xFC28, 0x0000); + r8168_mac_ocp_write(tp, 0xFC2A, 0x0000); + r8168_mac_ocp_write(tp, 0xFC2C, 0x0000); + r8168_mac_ocp_write(tp, 0xFC2E, 0x0000); + r8168_mac_ocp_write(tp, 0xFC30, 0x0000); + r8168_mac_ocp_write(tp, 0xFC32, 0x0000); + r8168_mac_ocp_write(tp, 0xFC34, 0x0000); + r8168_mac_ocp_write(tp, 0xFC36, 0x0000); + mdelay(3); + r8168_mac_ocp_write(tp, 0xFC26, 0x0000); + + r8168_mac_ocp_write(tp, 0xF800, 0xE008); + r8168_mac_ocp_write(tp, 0xF802, 0xE00A); + r8168_mac_ocp_write(tp, 0xF804, 0xE00C); + r8168_mac_ocp_write(tp, 0xF806, 0xE00E); + r8168_mac_ocp_write(tp, 0xF808, 0xE027); + r8168_mac_ocp_write(tp, 0xF80A, 0xE04F); + r8168_mac_ocp_write(tp, 0xF80C, 0xE05E); + r8168_mac_ocp_write(tp, 0xF80E, 0xE065); + r8168_mac_ocp_write(tp, 0xF810, 0xC602); + r8168_mac_ocp_write(tp, 0xF812, 0xBE00); + r8168_mac_ocp_write(tp, 0xF814, 0x0000); + r8168_mac_ocp_write(tp, 0xF816, 0xC502); + r8168_mac_ocp_write(tp, 0xF818, 0xBD00); + r8168_mac_ocp_write(tp, 0xF81A, 0x074C); + r8168_mac_ocp_write(tp, 0xF81C, 0xC302); + r8168_mac_ocp_write(tp, 0xF81E, 0xBB00); + r8168_mac_ocp_write(tp, 0xF820, 0x080A); + r8168_mac_ocp_write(tp, 0xF822, 0x6420); + r8168_mac_ocp_write(tp, 0xF824, 0x48C2); + r8168_mac_ocp_write(tp, 0xF826, 0x8C20); + r8168_mac_ocp_write(tp, 0xF828, 0xC516); + r8168_mac_ocp_write(tp, 0xF82A, 0x64A4); + r8168_mac_ocp_write(tp, 0xF82C, 0x49C0); + r8168_mac_ocp_write(tp, 0xF82E, 0xF009); + r8168_mac_ocp_write(tp, 0xF830, 0x74A2); + r8168_mac_ocp_write(tp, 0xF832, 0x8CA5); + r8168_mac_ocp_write(tp, 0xF834, 0x74A0); + r8168_mac_ocp_write(tp, 0xF836, 0xC50E); + r8168_mac_ocp_write(tp, 0xF838, 0x9CA2); + r8168_mac_ocp_write(tp, 0xF83A, 0x1C11); + r8168_mac_ocp_write(tp, 0xF83C, 0x9CA0); + r8168_mac_ocp_write(tp, 0xF83E, 0xE006); + r8168_mac_ocp_write(tp, 0xF840, 0x74F8); + r8168_mac_ocp_write(tp, 0xF842, 0x48C4); + r8168_mac_ocp_write(tp, 0xF844, 0x8CF8); + r8168_mac_ocp_write(tp, 0xF846, 0xC404); + r8168_mac_ocp_write(tp, 0xF848, 0xBC00); + r8168_mac_ocp_write(tp, 0xF84A, 0xC403); + r8168_mac_ocp_write(tp, 0xF84C, 0xBC00); + r8168_mac_ocp_write(tp, 0xF84E, 0x0BF2); + r8168_mac_ocp_write(tp, 0xF850, 0x0C0A); + r8168_mac_ocp_write(tp, 0xF852, 0xE434); + r8168_mac_ocp_write(tp, 0xF854, 0xD3C0); + r8168_mac_ocp_write(tp, 0xF856, 0x49D9); + r8168_mac_ocp_write(tp, 0xF858, 0xF01F); + r8168_mac_ocp_write(tp, 0xF85A, 0xC526); + r8168_mac_ocp_write(tp, 0xF85C, 0x64A5); + r8168_mac_ocp_write(tp, 0xF85E, 0x1400); + r8168_mac_ocp_write(tp, 0xF860, 0xF007); + r8168_mac_ocp_write(tp, 0xF862, 0x0C01); + r8168_mac_ocp_write(tp, 0xF864, 0x8CA5); + r8168_mac_ocp_write(tp, 0xF866, 0x1C15); + r8168_mac_ocp_write(tp, 0xF868, 0xC51B); + r8168_mac_ocp_write(tp, 0xF86A, 0x9CA0); + r8168_mac_ocp_write(tp, 0xF86C, 0xE013); + r8168_mac_ocp_write(tp, 0xF86E, 0xC519); + r8168_mac_ocp_write(tp, 0xF870, 0x74A0); + r8168_mac_ocp_write(tp, 0xF872, 0x48C4); + r8168_mac_ocp_write(tp, 0xF874, 0x8CA0); + r8168_mac_ocp_write(tp, 0xF876, 0xC516); + r8168_mac_ocp_write(tp, 0xF878, 0x74A4); + r8168_mac_ocp_write(tp, 0xF87A, 0x48C8); + r8168_mac_ocp_write(tp, 0xF87C, 0x48CA); + r8168_mac_ocp_write(tp, 0xF87E, 0x9CA4); + r8168_mac_ocp_write(tp, 0xF880, 0xC512); + r8168_mac_ocp_write(tp, 0xF882, 0x1B00); + r8168_mac_ocp_write(tp, 0xF884, 0x9BA0); + r8168_mac_ocp_write(tp, 0xF886, 0x1B1C); + r8168_mac_ocp_write(tp, 0xF888, 0x483F); + r8168_mac_ocp_write(tp, 0xF88A, 0x9BA2); + r8168_mac_ocp_write(tp, 0xF88C, 0x1B04); + r8168_mac_ocp_write(tp, 0xF88E, 0xC508); + r8168_mac_ocp_write(tp, 0xF890, 0x9BA0); + r8168_mac_ocp_write(tp, 0xF892, 0xC505); + r8168_mac_ocp_write(tp, 0xF894, 0xBD00); + r8168_mac_ocp_write(tp, 0xF896, 0xC502); + r8168_mac_ocp_write(tp, 0xF898, 0xBD00); + r8168_mac_ocp_write(tp, 0xF89A, 0x0300); + r8168_mac_ocp_write(tp, 0xF89C, 0x051E); + r8168_mac_ocp_write(tp, 0xF89E, 0xE434); + r8168_mac_ocp_write(tp, 0xF8A0, 0xE018); + r8168_mac_ocp_write(tp, 0xF8A2, 0xE092); + r8168_mac_ocp_write(tp, 0xF8A4, 0xDE20); + r8168_mac_ocp_write(tp, 0xF8A6, 0xD3C0); + r8168_mac_ocp_write(tp, 0xF8A8, 0xC50F); + r8168_mac_ocp_write(tp, 0xF8AA, 0x76A4); + r8168_mac_ocp_write(tp, 0xF8AC, 0x49E3); + r8168_mac_ocp_write(tp, 0xF8AE, 0xF007); + r8168_mac_ocp_write(tp, 0xF8B0, 0x49C0); + r8168_mac_ocp_write(tp, 0xF8B2, 0xF103); + r8168_mac_ocp_write(tp, 0xF8B4, 0xC607); + r8168_mac_ocp_write(tp, 0xF8B6, 0xBE00); + r8168_mac_ocp_write(tp, 0xF8B8, 0xC606); + r8168_mac_ocp_write(tp, 0xF8BA, 0xBE00); + r8168_mac_ocp_write(tp, 0xF8BC, 0xC602); + r8168_mac_ocp_write(tp, 0xF8BE, 0xBE00); + r8168_mac_ocp_write(tp, 0xF8C0, 0x0C4C); + r8168_mac_ocp_write(tp, 0xF8C2, 0x0C28); + r8168_mac_ocp_write(tp, 0xF8C4, 0x0C2C); + r8168_mac_ocp_write(tp, 0xF8C6, 0xDC00); + r8168_mac_ocp_write(tp, 0xF8C8, 0xC707); + r8168_mac_ocp_write(tp, 0xF8CA, 0x1D00); + r8168_mac_ocp_write(tp, 0xF8CC, 0x8DE2); + r8168_mac_ocp_write(tp, 0xF8CE, 0x48C1); + r8168_mac_ocp_write(tp, 0xF8D0, 0xC502); + r8168_mac_ocp_write(tp, 0xF8D2, 0xBD00); + r8168_mac_ocp_write(tp, 0xF8D4, 0x00AA); + r8168_mac_ocp_write(tp, 0xF8D6, 0xE0C0); + r8168_mac_ocp_write(tp, 0xF8D8, 0xC502); + r8168_mac_ocp_write(tp, 0xF8DA, 0xBD00); + r8168_mac_ocp_write(tp, 0xF8DC, 0x0132); + + r8168_mac_ocp_write(tp, 0xFC26, 0x8000); + + r8168_mac_ocp_write(tp, 0xFC2A, 0x0743); + r8168_mac_ocp_write(tp, 0xFC2C, 0x0801); + r8168_mac_ocp_write(tp, 0xFC2E, 0x0BE9); + r8168_mac_ocp_write(tp, 0xFC30, 0x02FD); + r8168_mac_ocp_write(tp, 0xFC32, 0x0C25); + r8168_mac_ocp_write(tp, 0xFC34, 0x00A9); + r8168_mac_ocp_write(tp, 0xFC36, 0x012D); + rtl_hw_aspm_clkreq_enable(tp, true); } diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index aba6eea72f15..6e07f5ebacfc 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -262,7 +262,7 @@ static int sis900_get_mac_addr(struct pci_dev *pci_dev, /* check to see if we have sane EEPROM */ signature = (u16) read_eeprom(ioaddr, EEPROMSignature); if (signature == 0xffff || signature == 0x0000) { - printk (KERN_WARNING "%s: Error EERPOM read %x\n", + printk (KERN_WARNING "%s: Error EEPROM read %x\n", pci_name(pci_dev), signature); return 0; } @@ -359,9 +359,9 @@ static int sis635_get_mac_addr(struct pci_dev *pci_dev, * * SiS962 or SiS963 model, use EEPROM to store MAC address. And EEPROM * is shared by - * LAN and 1394. When access EEPROM, send EEREQ signal to hardware first + * LAN and 1394. When accessing EEPROM, send EEREQ signal to hardware first * and wait for EEGNT. If EEGNT is ON, EEPROM is permitted to be accessed - * by LAN, otherwise is not. After MAC address is read from EEPROM, send + * by LAN, otherwise it is not. After MAC address is read from EEPROM, send * EEDONE signal to refuse EEPROM access by LAN. * The EEPROM map of SiS962 or SiS963 is different to SiS900. * The signature field in SiS962 or SiS963 spec is meaningless. diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index f320f9a0de8b..32a89744972d 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2570,7 +2570,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, ret = PTR_ERR(slave_data->ifphy); dev_err(&pdev->dev, "%d: Error retrieving port phy: %d\n", i, ret); - return ret; + goto err_node_put; } slave_data->slave_node = slave_node; @@ -2589,7 +2589,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, if (ret) { if (ret != -EPROBE_DEFER) dev_err(&pdev->dev, "failed to register fixed-link phy: %d\n", ret); - return ret; + goto err_node_put; } slave_data->phy_node = of_node_get(slave_node); } else if (parp) { @@ -2607,7 +2607,8 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, of_node_put(mdio_node); if (!mdio) { dev_err(&pdev->dev, "Missing mdio platform device\n"); - return -EINVAL; + ret = -EINVAL; + goto err_node_put; } snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); @@ -2622,7 +2623,8 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, if (slave_data->phy_if < 0) { dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", i); - return slave_data->phy_if; + ret = slave_data->phy_if; + goto err_node_put; } no_phy_slave: @@ -2633,7 +2635,7 @@ no_phy_slave: ret = ti_cm_get_macid(&pdev->dev, i, slave_data->mac_addr); if (ret) - return ret; + goto err_node_put; } if (data->dual_emac) { if (of_property_read_u32(slave_node, "dual_emac_res_vlan", @@ -2648,11 +2650,17 @@ no_phy_slave: } i++; - if (i == data->slaves) - break; + if (i == data->slaves) { + ret = 0; + goto err_node_put; + } } return 0; + +err_node_put: + of_node_put(slave_node); + return ret; } static void cpsw_remove_dt(struct platform_device *pdev) @@ -2675,8 +2683,10 @@ static void cpsw_remove_dt(struct platform_device *pdev) of_node_put(slave_data->phy_node); i++; - if (i == data->slaves) + if (i == data->slaves) { + of_node_put(slave_node); break; + } } of_platform_depopulate(&pdev->dev); diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index b4ab1a5f6cd0..78f0f2d59e22 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -855,7 +855,6 @@ static int tlan_init(struct net_device *dev) dev->name); return -ENOMEM; } - memset(priv->dma_storage, 0, dma_size); priv->rx_list = (struct tlan_list *) ALIGN((unsigned long)priv->dma_storage, 8); priv->rx_list_dma = ALIGN(priv->dma_storage_dma, 8); diff --git a/drivers/net/hippi/rrunner.c b/drivers/net/hippi/rrunner.c index 7b9350dbebdd..2a6ec5394966 100644 --- a/drivers/net/hippi/rrunner.c +++ b/drivers/net/hippi/rrunner.c @@ -1196,7 +1196,6 @@ static int rr_open(struct net_device *dev) goto error; } rrpriv->rx_ctrl_dma = dma_addr; - memset(rrpriv->rx_ctrl, 0, 256*sizeof(struct ring_ctrl)); rrpriv->info = pci_alloc_consistent(pdev, sizeof(struct rr_info), &dma_addr); @@ -1205,7 +1204,6 @@ static int rr_open(struct net_device *dev) goto error; } rrpriv->info_dma = dma_addr; - memset(rrpriv->info, 0, sizeof(struct rr_info)); wmb(); spin_lock_irqsave(&rrpriv->lock, flags); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 8b4ad10cf940..69e0a2acfcb0 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1292,6 +1292,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x2001, 0x7e16, 3)}, /* D-Link DWM-221 */ {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ {QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */ + {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ {QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */ diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 3f48f05dd2a6..2a1918f25e47 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -3430,7 +3430,6 @@ vmxnet3_probe_device(struct pci_dev *pdev, err = -ENOMEM; goto err_ver; } - memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf)); adapter->coal_conf->coalMode = VMXNET3_COALESCE_DISABLED; adapter->default_coal_mode = true; } diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index e43a566eef77..0606416dc971 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -7541,6 +7541,8 @@ static int ath10k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, &vht_nss, true); update_bitrate_mask = false; + } else { + vht_pfr = 0; } mutex_lock(&ar->conf_mutex); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index 93526dfaf791..1f500cddb3a7 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -80,7 +80,9 @@ #define IWL_22000_QU_B_HR_B_FW_PRE "iwlwifi-Qu-b0-hr-b0-" #define IWL_22000_HR_B_FW_PRE "iwlwifi-QuQnj-b0-hr-b0-" #define IWL_22000_HR_A0_FW_PRE "iwlwifi-QuQnj-a0-hr-a0-" +#define IWL_QU_C_HR_B_FW_PRE "iwlwifi-Qu-c0-hr-b0-" #define IWL_QU_B_JF_B_FW_PRE "iwlwifi-Qu-b0-jf-b0-" +#define IWL_QU_C_JF_B_FW_PRE "iwlwifi-Qu-c0-jf-b0-" #define IWL_QUZ_A_HR_B_FW_PRE "iwlwifi-QuZ-a0-hr-b0-" #define IWL_QUZ_A_JF_B_FW_PRE "iwlwifi-QuZ-a0-jf-b0-" #define IWL_QNJ_B_JF_B_FW_PRE "iwlwifi-QuQnj-b0-jf-b0-" @@ -109,6 +111,8 @@ IWL_QUZ_A_HR_B_FW_PRE __stringify(api) ".ucode" #define IWL_QUZ_A_JF_B_MODULE_FIRMWARE(api) \ IWL_QUZ_A_JF_B_FW_PRE __stringify(api) ".ucode" +#define IWL_QU_C_HR_B_MODULE_FIRMWARE(api) \ + IWL_QU_C_HR_B_FW_PRE __stringify(api) ".ucode" #define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \ IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode" #define IWL_QNJ_B_JF_B_MODULE_FIRMWARE(api) \ @@ -256,6 +260,30 @@ const struct iwl_cfg iwl_ax201_cfg_qu_hr = { .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, }; +const struct iwl_cfg iwl_ax101_cfg_qu_c0_hr_b0 = { + .name = "Intel(R) Wi-Fi 6 AX101", + .fw_name_pre = IWL_QU_C_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + +const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0 = { + .name = "Intel(R) Wi-Fi 6 AX201 160MHz", + .fw_name_pre = IWL_QU_C_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + const struct iwl_cfg iwl_ax101_cfg_quz_hr = { .name = "Intel(R) Wi-Fi 6 AX101", .fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE, @@ -372,6 +400,30 @@ const struct iwl_cfg iwl9560_2ac_160_cfg_qu_b0_jf_b0 = { IWL_DEVICE_22500, }; +const struct iwl_cfg iwl9461_2ac_cfg_qu_c0_jf_b0 = { + .name = "Intel(R) Wireless-AC 9461", + .fw_name_pre = IWL_QU_C_JF_B_FW_PRE, + IWL_DEVICE_22500, +}; + +const struct iwl_cfg iwl9462_2ac_cfg_qu_c0_jf_b0 = { + .name = "Intel(R) Wireless-AC 9462", + .fw_name_pre = IWL_QU_C_JF_B_FW_PRE, + IWL_DEVICE_22500, +}; + +const struct iwl_cfg iwl9560_2ac_cfg_qu_c0_jf_b0 = { + .name = "Intel(R) Wireless-AC 9560", + .fw_name_pre = IWL_QU_C_JF_B_FW_PRE, + IWL_DEVICE_22500, +}; + +const struct iwl_cfg iwl9560_2ac_160_cfg_qu_c0_jf_b0 = { + .name = "Intel(R) Wireless-AC 9560 160MHz", + .fw_name_pre = IWL_QU_C_JF_B_FW_PRE, + IWL_DEVICE_22500, +}; + const struct iwl_cfg iwl9560_2ac_cfg_qnj_jf_b0 = { .name = "Intel(R) Wireless-AC 9560 160MHz", .fw_name_pre = IWL_QNJ_B_JF_B_FW_PRE, @@ -590,6 +642,7 @@ MODULE_FIRMWARE(IWL_22000_HR_A_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_HR_B_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_QU_C_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_QUZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_QUZ_A_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index bc267bd2c3b0..1c1bf1b281cd 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -565,10 +565,13 @@ extern const struct iwl_cfg iwl22000_2ac_cfg_hr; extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb; extern const struct iwl_cfg iwl22000_2ac_cfg_jf; extern const struct iwl_cfg iwl_ax101_cfg_qu_hr; +extern const struct iwl_cfg iwl_ax101_cfg_qu_c0_hr_b0; extern const struct iwl_cfg iwl_ax101_cfg_quz_hr; extern const struct iwl_cfg iwl22000_2ax_cfg_hr; extern const struct iwl_cfg iwl_ax200_cfg_cc; extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; +extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; +extern const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0; extern const struct iwl_cfg iwl_ax201_cfg_quz_hr; extern const struct iwl_cfg iwl_ax1650i_cfg_quz_hr; extern const struct iwl_cfg iwl_ax1650s_cfg_quz_hr; @@ -580,6 +583,10 @@ extern const struct iwl_cfg iwl9461_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg iwl9462_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg iwl9560_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg iwl9560_2ac_160_cfg_qu_b0_jf_b0; +extern const struct iwl_cfg iwl9461_2ac_cfg_qu_c0_jf_b0; +extern const struct iwl_cfg iwl9462_2ac_cfg_qu_c0_jf_b0; +extern const struct iwl_cfg iwl9560_2ac_cfg_qu_c0_jf_b0; +extern const struct iwl_cfg iwl9560_2ac_160_cfg_qu_c0_jf_b0; extern const struct iwl_cfg killer1550i_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg killer1550s_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg iwl22000_2ax_cfg_jf; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index 93da96a7247c..cb4c5514a556 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -328,6 +328,8 @@ enum { #define CSR_HW_REV_TYPE_NONE (0x00001F0) #define CSR_HW_REV_TYPE_QNJ (0x0000360) #define CSR_HW_REV_TYPE_QNJ_B0 (0x0000364) +#define CSR_HW_REV_TYPE_QU_B0 (0x0000334) +#define CSR_HW_REV_TYPE_QU_C0 (0x0000338) #define CSR_HW_REV_TYPE_QUZ (0x0000354) #define CSR_HW_REV_TYPE_HR_CDB (0x0000340) #define CSR_HW_REV_TYPE_SO (0x0000370) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index ccc83fd74649..ea2a03d4bf55 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -604,6 +604,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x6014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x8010, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_160_cfg)}, @@ -971,6 +972,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x7A70, 0x0310, iwlax211_2ax_cfg_so_gf_a0)}, {IWL_PCI_DEVICE(0x7A70, 0x0510, iwlax211_2ax_cfg_so_gf_a0)}, {IWL_PCI_DEVICE(0x7A70, 0x0A10, iwlax211_2ax_cfg_so_gf_a0)}, + {IWL_PCI_DEVICE(0x7AF0, 0x0090, iwlax211_2ax_cfg_so_gf_a0)}, {IWL_PCI_DEVICE(0x7AF0, 0x0310, iwlax211_2ax_cfg_so_gf_a0)}, {IWL_PCI_DEVICE(0x7AF0, 0x0510, iwlax211_2ax_cfg_so_gf_a0)}, {IWL_PCI_DEVICE(0x7AF0, 0x0A10, iwlax211_2ax_cfg_so_gf_a0)}, @@ -1037,6 +1039,27 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } iwl_trans->cfg = cfg; } + + /* + * This is a hack to switch from Qu B0 to Qu C0. We need to + * do this for all cfgs that use Qu B0. All this code is in + * urgent need for a refactor, but for now this is the easiest + * thing to do to support Qu C-step. + */ + if (iwl_trans->hw_rev == CSR_HW_REV_TYPE_QU_C0) { + if (iwl_trans->cfg == &iwl_ax101_cfg_qu_hr) + iwl_trans->cfg = &iwl_ax101_cfg_qu_c0_hr_b0; + else if (iwl_trans->cfg == &iwl_ax201_cfg_qu_hr) + iwl_trans->cfg = &iwl_ax201_cfg_qu_c0_hr_b0; + else if (iwl_trans->cfg == &iwl9461_2ac_cfg_qu_b0_jf_b0) + iwl_trans->cfg = &iwl9461_2ac_cfg_qu_c0_jf_b0; + else if (iwl_trans->cfg == &iwl9462_2ac_cfg_qu_b0_jf_b0) + iwl_trans->cfg = &iwl9462_2ac_cfg_qu_c0_jf_b0; + else if (iwl_trans->cfg == &iwl9560_2ac_cfg_qu_b0_jf_b0) + iwl_trans->cfg = &iwl9560_2ac_cfg_qu_c0_jf_b0; + else if (iwl_trans->cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0) + iwl_trans->cfg = &iwl9560_2ac_160_cfg_qu_c0_jf_b0; + } #endif pci_set_drvdata(pdev, iwl_trans); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c index 67b81c7221c4..7e3a621b9c0d 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c @@ -372,15 +372,10 @@ static void rt2x00usb_interrupt_rxdone(struct urb *urb) struct queue_entry *entry = (struct queue_entry *)urb->context; struct rt2x00_dev *rt2x00dev = entry->queue->rt2x00dev; - if (!test_and_clear_bit(ENTRY_OWNER_DEVICE_DATA, &entry->flags)) + if (!test_bit(ENTRY_OWNER_DEVICE_DATA, &entry->flags)) return; /* - * Report the frame as DMA done - */ - rt2x00lib_dmadone(entry); - - /* * Check if the received data is simply too small * to be actually valid, or if the urb is signaling * a problem. @@ -389,6 +384,11 @@ static void rt2x00usb_interrupt_rxdone(struct urb *urb) set_bit(ENTRY_DATA_IO_FAILED, &entry->flags); /* + * Report the frame as DMA done + */ + rt2x00lib_dmadone(entry); + + /* * Schedule the delayed work for reading the RX status * from the device. */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 6d944369ca87..ff65d22cf336 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -747,7 +747,7 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) return size <= size_default && (size & (size - 1)) == 0; } -#define bpf_ctx_wide_store_ok(off, size, type, field) \ +#define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ diff --git a/include/net/tcp.h b/include/net/tcp.h index cca3c59b98bf..f42d300f0cfa 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1064,7 +1064,8 @@ void tcp_get_default_congestion_control(struct net *net, char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); -int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit); +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, + bool reinit, bool cap_net_admin); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 82699845ef79..fa1c753dcdbc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3248,7 +3248,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3260,7 +3260,7 @@ struct bpf_sock_addr { __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __bpf_md_ptr(struct bpf_sock *, sk); diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 1f623252abe8..18f185299f47 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1174,7 +1174,7 @@ enum { TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */ TCA_TAPRIO_ATTR_FLAGS, /* u32 */ - TCA_TAPRIO_ATTR_TXTIME_DELAY, /* s32 */ + TCA_TAPRIO_ATTR_TXTIME_DELAY, /* u32 */ __TCA_TAPRIO_ATTR_MAX, }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 546ebee39e2a..5fcc7a17eb5a 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1073,11 +1073,18 @@ const struct btf_type *btf_type_id_size(const struct btf *btf, !btf_type_is_var(size_type))) return NULL; - size = btf->resolved_sizes[size_type_id]; size_type_id = btf->resolved_ids[size_type_id]; size_type = btf_type_by_id(btf, size_type_id); if (btf_type_nosize_or_null(size_type)) return NULL; + else if (btf_type_has_size(size_type)) + size = size_type->size; + else if (btf_type_is_array(size_type)) + size = btf->resolved_sizes[size_type_id]; + else if (btf_type_is_ptr(size_type)) + size = sizeof(void *); + else + return NULL; } *type_id = size_type_id; @@ -1602,7 +1609,6 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, const struct btf_type *next_type; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size = 0; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { @@ -1620,7 +1626,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, * save us a few type-following when we use it later (e.g. in * pretty print). */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (!btf_type_id_size(btf, &next_type_id, NULL)) { if (env_type_is_resolved(env, next_type_id)) next_type = btf_type_id_resolve(btf, &next_type_id); @@ -1633,7 +1639,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, } } - env_stack_pop_resolved(env, next_type_id, next_type_size); + env_stack_pop_resolved(env, next_type_id, 0); return 0; } @@ -1645,7 +1651,6 @@ static int btf_var_resolve(struct btf_verifier_env *env, const struct btf_type *t = v->t; u32 next_type_id = t->type; struct btf *btf = env->btf; - u32 next_type_size; next_type = btf_type_by_id(btf, next_type_id); if (!next_type || btf_type_is_resolve_source_only(next_type)) { @@ -1675,12 +1680,12 @@ static int btf_var_resolve(struct btf_verifier_env *env, * forward types or similar that would resolve to size of * zero is allowed. */ - if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) { + if (!btf_type_id_size(btf, &next_type_id, NULL)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } - env_stack_pop_resolved(env, next_type_id, next_type_size); + env_stack_pop_resolved(env, next_type_id, 0); return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a2e763703c30..5900cbb966b1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1519,9 +1519,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, return -EFAULT; } *stack_mask |= 1ull << spi; - } else if (class == BPF_STX) { + } else if (class == BPF_STX || class == BPF_ST) { if (*reg_mask & dreg) - /* stx shouldn't be using _scalar_ dst_reg + /* stx & st shouldn't be using _scalar_ dst_reg * to access memory. It means backtracking * encountered a case of pointer subtraction. */ @@ -1540,7 +1540,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (!(*stack_mask & (1ull << spi))) return 0; *stack_mask &= ~(1ull << spi); - *reg_mask |= sreg; + if (class == BPF_STX) + *reg_mask |= sreg; } else if (class == BPF_JMP || class == BPF_JMP32) { if (opcode == BPF_CALL) { if (insn->src_reg == BPF_PSEUDO_CALL) @@ -1569,10 +1570,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, if (mode == BPF_IND || mode == BPF_ABS) /* to be analyzed */ return -ENOTSUPP; - } else if (class == BPF_ST) { - if (*reg_mask & dreg) - /* likely pointer subtraction */ - return -ENOTSUPP; } return 0; } @@ -6106,11 +6103,13 @@ static int check_return_code(struct bpf_verifier_env *env) if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG) range = tnum_range(1, 1); + break; case BPF_PROG_TYPE_CGROUP_SKB: if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) { range = tnum_range(0, 3); enforce_attach_type_range = tnum_range(2, 3); } + break; case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: diff --git a/net/core/filter.c b/net/core/filter.c index 47f6386fb17a..4e2a79b2fd77 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4335,7 +4335,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, TCP_CA_NAME_MAX-1)); name[TCP_CA_NAME_MAX-1] = 0; ret = tcp_set_congestion_control(sk, name, false, - reinit); + reinit, true); } else { struct tcp_sock *tp = tcp_sk(sk); @@ -6884,20 +6884,30 @@ static bool sock_addr_is_valid_access(int off, int size, case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): - /* Only narrow read access allowed for now. */ if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); + + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + user_ip6)) + return true; + + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + msg_src_ip6)) + return true; + if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } else { - if (bpf_ctx_wide_store_ok(off, size, - struct bpf_sock_addr, - user_ip6)) + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + user_ip6)) return true; - if (bpf_ctx_wide_store_ok(off, size, - struct bpf_sock_addr, - msg_src_ip6)) + if (bpf_ctx_wide_access_ok(off, size, + struct bpf_sock_addr, + msg_src_ip6)) return true; if (size != size_default) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 26da97359d5b..f79e61c570ea 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1124,6 +1124,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); + neigh_del_timer(neigh); neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), @@ -1140,6 +1141,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) } } else if (neigh->nud_state & NUD_STALE) { neigh_dbg(2, "neigh %p is delayed\n", neigh); + neigh_del_timer(neigh); neigh->nud_state = NUD_DELAY; neigh->updated = jiffies; neigh_add_timer(neigh, jiffies + diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6f1e31f674a3..0338820ee0ec 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -762,7 +762,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) printk("%sdev name=%s feat=0x%pNF\n", level, dev->name, &dev->features); if (sk) - printk("%ssk family=%hu type=%hu proto=%hu\n", + printk("%ssk family=%hu type=%u proto=%u\n", level, sk->sk_family, sk->sk_type, sk->sk_protocol); if (full_pkt && headroom) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 1d96c9d4a8e9..26363d72d25b 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -216,6 +216,7 @@ static struct sk_buff if (!skb) { dev_err_ratelimited(dp->ds->dev, "Failed to copy stampable skb\n"); + spin_unlock(&sp->data->meta_lock); return NULL; } sja1105_transfer_meta(skb, meta); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 317339cd7f03..e8bc939b56dd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -388,6 +388,11 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); + /* This is not common, loopback packets retain skb_dst so normally they + * would not even hit this slow path. + */ + dev_match = dev_match || (res.type == RTN_LOCAL && + dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7846afacdf0b..776905899ac0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2785,7 +2785,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, name[val] = 0; lock_sock(sk); - err = tcp_set_congestion_control(sk, name, true, true); + err = tcp_set_congestion_control(sk, name, true, true, + ns_capable(sock_net(sk)->user_ns, + CAP_NET_ADMIN)); release_sock(sk); return err; } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index e1862b64a90f..c445a81d144e 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -333,7 +333,8 @@ out: * tcp_reinit_congestion_control (if the current congestion control was * already initialized. */ -int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit) +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, + bool reinit, bool cap_net_admin) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; @@ -369,8 +370,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, boo } else { err = -EBUSY; } - } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || - ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) { + } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) { err = -EPERM; } else if (!try_module_get(ca->owner)) { err = -EBUSY; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c21862ba9c02..d88821c794fb 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2170,7 +2170,7 @@ start_lookup: /* Initialize UDP checksum. If exited with zero value (success), * CHECKSUM_UNNECESSARY means, that no more checks are required. - * Otherwise, csum completion requires chacksumming packet body, + * Otherwise, csum completion requires checksumming packet body, * including udp header and folding it to skb->csum. */ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 49884f96232b..87f47bc55c5e 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1151,8 +1151,24 @@ add: err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, rt, extack); - if (err) + if (err) { + struct fib6_info *sibling, *next_sibling; + + /* If the route has siblings, then it first + * needs to be unlinked from them. + */ + if (!rt->fib6_nsiblings) + return err; + + list_for_each_entry_safe(sibling, next_sibling, + &rt->fib6_siblings, + fib6_siblings) + sibling->fib6_nsiblings--; + rt->fib6_nsiblings = 0; + list_del_init(&rt->fib6_siblings); + rt6_multipath_rebalance(next_sibling); return err; + } } rcu_assign_pointer(rt->fib6_next, iter); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8b0c33fb19a2..e49fec767a10 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2563,7 +2563,7 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, { u32 rt_cookie = 0; - if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) || + if (!from || !fib6_get_cookie_safe(from, &rt_cookie) || rt_cookie != cookie) return NULL; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 80610899a323..b2ccbc473127 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -900,12 +900,17 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0, sock_net_uid(tunnel->net, NULL)); - rt = ip_route_output_flow(tunnel->net, &fl4, NULL); - if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; - goto tx_error_icmp; + rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr); + if (!rt) { + rt = ip_route_output_flow(tunnel->net, &fl4, NULL); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } + if (rt->rt_type != RTN_UNICAST) { ip_rt_put(rt); dev->stats.tx_carrier_errors++; diff --git a/net/rds/ib.h b/net/rds/ib.h index 66c03c7665b2..303c6ee8bdb7 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -156,6 +156,7 @@ struct rds_ib_connection { /* To control the number of wrs from fastreg */ atomic_t i_fastreg_wrs; + atomic_t i_fastreg_inuse_count; /* interrupt handling */ struct tasklet_struct i_send_tasklet; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index c36d89cd14a1..fddaa09f7b0d 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -40,6 +40,7 @@ #include "rds_single_path.h" #include "rds.h" #include "ib.h" +#include "ib_mr.h" /* * Set the selected protocol version @@ -526,7 +527,6 @@ static int rds_ib_setup_qp(struct rds_connection *conn) attr.qp_type = IB_QPT_RC; attr.send_cq = ic->i_send_cq; attr.recv_cq = ic->i_recv_cq; - atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR); /* * XXX this can fail if max_*_wr is too large? Are we supposed @@ -993,6 +993,11 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp) ic->i_cm_id, err); } + /* kick off "flush_worker" for all pools in order to reap + * all FRMR registrations that are still marked "FRMR_IS_INUSE" + */ + rds_ib_flush_mrs(); + /* * We want to wait for tx and rx completion to finish * before we tear down the connection, but we have to be @@ -1005,6 +1010,7 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp) wait_event(rds_ib_ring_empty_wait, rds_ib_ring_empty(&ic->i_recv_ring) && (atomic_read(&ic->i_signaled_sends) == 0) && + (atomic_read(&ic->i_fastreg_inuse_count) == 0) && (atomic_read(&ic->i_fastreg_wrs) == RDS_IB_DEFAULT_FR_WR)); tasklet_kill(&ic->i_send_tasklet); tasklet_kill(&ic->i_recv_tasklet); @@ -1132,6 +1138,7 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) spin_lock_init(&ic->i_ack_lock); #endif atomic_set(&ic->i_signaled_sends, 0); + atomic_set(&ic->i_fastreg_wrs, RDS_IB_DEFAULT_FR_WR); /* * rds_ib_conn_shutdown() waits for these to be emptied so they diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 32ae26ed58a0..06ecf9d2d4bf 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -32,6 +32,24 @@ #include "ib_mr.h" +static inline void +rds_transition_frwr_state(struct rds_ib_mr *ibmr, + enum rds_ib_fr_state old_state, + enum rds_ib_fr_state new_state) +{ + if (cmpxchg(&ibmr->u.frmr.fr_state, + old_state, new_state) == old_state && + old_state == FRMR_IS_INUSE) { + /* enforce order of ibmr->u.frmr.fr_state update + * before decrementing i_fastreg_inuse_count + */ + smp_mb__before_atomic(); + atomic_dec(&ibmr->ic->i_fastreg_inuse_count); + if (waitqueue_active(&rds_ib_ring_empty_wait)) + wake_up(&rds_ib_ring_empty_wait); + } +} + static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev, int npages) { @@ -75,6 +93,8 @@ static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev, pool->max_items_soft = pool->max_items; frmr->fr_state = FRMR_IS_FREE; + init_waitqueue_head(&frmr->fr_inv_done); + init_waitqueue_head(&frmr->fr_reg_done); return ibmr; out_no_cigar: @@ -116,13 +136,19 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) if (unlikely(ret != ibmr->sg_len)) return ret < 0 ? ret : -EINVAL; + if (cmpxchg(&frmr->fr_state, + FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) + return -EBUSY; + + atomic_inc(&ibmr->ic->i_fastreg_inuse_count); + /* Perform a WR for the fast_reg_mr. Each individual page * in the sg list is added to the fast reg page list and placed * inside the fast_reg_mr WR. The key used is a rolling 8bit * counter, which should guarantee uniqueness. */ ib_update_fast_reg_key(frmr->mr, ibmr->remap_count++); - frmr->fr_state = FRMR_IS_INUSE; + frmr->fr_reg = true; memset(®_wr, 0, sizeof(reg_wr)); reg_wr.wr.wr_id = (unsigned long)(void *)ibmr; @@ -138,12 +164,23 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr) ret = ib_post_send(ibmr->ic->i_cm_id->qp, ®_wr.wr, NULL); if (unlikely(ret)) { /* Failure here can be because of -ENOMEM as well */ - frmr->fr_state = FRMR_IS_STALE; + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); + atomic_inc(&ibmr->ic->i_fastreg_wrs); if (printk_ratelimit()) pr_warn("RDS/IB: %s returned error(%d)\n", __func__, ret); + goto out; } + + /* Wait for the registration to complete in order to prevent an invalid + * access error resulting from a race between the memory region already + * being accessed while registration is still pending. + */ + wait_event(frmr->fr_reg_done, !frmr->fr_reg); + +out: + return ret; } @@ -255,12 +292,29 @@ static int rds_ib_post_inv(struct rds_ib_mr *ibmr) ret = ib_post_send(i_cm_id->qp, s_wr, NULL); if (unlikely(ret)) { - frmr->fr_state = FRMR_IS_STALE; + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); frmr->fr_inv = false; + /* enforce order of frmr->fr_inv update + * before incrementing i_fastreg_wrs + */ + smp_mb__before_atomic(); atomic_inc(&ibmr->ic->i_fastreg_wrs); pr_err("RDS/IB: %s returned error(%d)\n", __func__, ret); goto out; } + + /* Wait for the FRMR_IS_FREE (or FRMR_IS_STALE) transition in order to + * 1) avoid a silly bouncing between "clean_list" and "drop_list" + * triggered by function "rds_ib_reg_frmr" as it is releases frmr + * regions whose state is not "FRMR_IS_FREE" right away. + * 2) prevents an invalid access error in a race + * from a pending "IB_WR_LOCAL_INV" operation + * with a teardown ("dma_unmap_sg", "put_page") + * and de-registration ("ib_dereg_mr") of the corresponding + * memory region. + */ + wait_event(frmr->fr_inv_done, frmr->fr_state != FRMR_IS_INUSE); + out: return ret; } @@ -271,7 +325,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc) struct rds_ib_frmr *frmr = &ibmr->u.frmr; if (wc->status != IB_WC_SUCCESS) { - frmr->fr_state = FRMR_IS_STALE; + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE); if (rds_conn_up(ic->conn)) rds_ib_conn_error(ic->conn, "frmr completion <%pI4,%pI4> status %u(%s), vendor_err 0x%x, disconnecting and reconnecting\n", @@ -283,10 +337,20 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc) } if (frmr->fr_inv) { - frmr->fr_state = FRMR_IS_FREE; + rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_FREE); frmr->fr_inv = false; + wake_up(&frmr->fr_inv_done); } + if (frmr->fr_reg) { + frmr->fr_reg = false; + wake_up(&frmr->fr_reg_done); + } + + /* enforce order of frmr->{fr_reg,fr_inv} update + * before incrementing i_fastreg_wrs + */ + smp_mb__before_atomic(); atomic_inc(&ic->i_fastreg_wrs); } @@ -295,14 +359,18 @@ void rds_ib_unreg_frmr(struct list_head *list, unsigned int *nfreed, { struct rds_ib_mr *ibmr, *next; struct rds_ib_frmr *frmr; - int ret = 0; + int ret = 0, ret2; unsigned int freed = *nfreed; /* String all ib_mr's onto one list and hand them to ib_unmap_fmr */ list_for_each_entry(ibmr, list, unmap_list) { - if (ibmr->sg_dma_len) - ret |= rds_ib_post_inv(ibmr); + if (ibmr->sg_dma_len) { + ret2 = rds_ib_post_inv(ibmr); + if (ret2 && !ret) + ret = ret2; + } } + if (ret) pr_warn("RDS/IB: %s failed (err=%d)\n", __func__, ret); diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 5da12c248431..9045a8c0edff 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -57,6 +57,9 @@ struct rds_ib_frmr { struct ib_mr *mr; enum rds_ib_fr_state fr_state; bool fr_inv; + wait_queue_head_t fr_inv_done; + bool fr_reg; + wait_queue_head_t fr_reg_done; struct ib_send_wr fr_wr; unsigned int dma_npages; unsigned int sg_byte_len; @@ -97,6 +100,7 @@ struct rds_ib_mr_pool { struct llist_head free_list; /* unused MRs */ struct llist_head clean_list; /* unused & unmapped MRs */ wait_queue_head_t flush_wait; + spinlock_t clean_lock; /* "clean_list" concurrency */ atomic_t free_pinned; /* memory pinned by free MRs */ unsigned long max_items; diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index 0b347f46b2f4..c8c1e3ae8d84 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -40,9 +40,6 @@ struct workqueue_struct *rds_ib_mr_wq; -static DEFINE_PER_CPU(unsigned long, clean_list_grace); -#define CLEAN_LIST_BUSY_BIT 0 - static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr) { struct rds_ib_device *rds_ibdev; @@ -195,12 +192,11 @@ struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool) { struct rds_ib_mr *ibmr = NULL; struct llist_node *ret; - unsigned long *flag; + unsigned long flags; - preempt_disable(); - flag = this_cpu_ptr(&clean_list_grace); - set_bit(CLEAN_LIST_BUSY_BIT, flag); + spin_lock_irqsave(&pool->clean_lock, flags); ret = llist_del_first(&pool->clean_list); + spin_unlock_irqrestore(&pool->clean_lock, flags); if (ret) { ibmr = llist_entry(ret, struct rds_ib_mr, llnode); if (pool->pool_type == RDS_IB_MR_8K_POOL) @@ -209,23 +205,9 @@ struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool) rds_ib_stats_inc(s_ib_rdma_mr_1m_reused); } - clear_bit(CLEAN_LIST_BUSY_BIT, flag); - preempt_enable(); return ibmr; } -static inline void wait_clean_list_grace(void) -{ - int cpu; - unsigned long *flag; - - for_each_online_cpu(cpu) { - flag = &per_cpu(clean_list_grace, cpu); - while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) - cpu_relax(); - } -} - void rds_ib_sync_mr(void *trans_private, int direction) { struct rds_ib_mr *ibmr = trans_private; @@ -324,8 +306,7 @@ static unsigned int llist_append_to_list(struct llist_head *llist, * of clusters. Each cluster has linked llist nodes of * MR_CLUSTER_SIZE mrs that are ready for reuse. */ -static void list_to_llist_nodes(struct rds_ib_mr_pool *pool, - struct list_head *list, +static void list_to_llist_nodes(struct list_head *list, struct llist_node **nodes_head, struct llist_node **nodes_tail) { @@ -402,8 +383,13 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, */ dirty_to_clean = llist_append_to_list(&pool->drop_list, &unmap_list); dirty_to_clean += llist_append_to_list(&pool->free_list, &unmap_list); - if (free_all) + if (free_all) { + unsigned long flags; + + spin_lock_irqsave(&pool->clean_lock, flags); llist_append_to_list(&pool->clean_list, &unmap_list); + spin_unlock_irqrestore(&pool->clean_lock, flags); + } free_goal = rds_ib_flush_goal(pool, free_all); @@ -416,27 +402,20 @@ int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, rds_ib_unreg_fmr(&unmap_list, &nfreed, &unpinned, free_goal); if (!list_empty(&unmap_list)) { - /* we have to make sure that none of the things we're about - * to put on the clean list would race with other cpus trying - * to pull items off. The llist would explode if we managed to - * remove something from the clean list and then add it back again - * while another CPU was spinning on that same item in llist_del_first. - * - * This is pretty unlikely, but just in case wait for an llist grace period - * here before adding anything back into the clean list. - */ - wait_clean_list_grace(); - - list_to_llist_nodes(pool, &unmap_list, &clean_nodes, &clean_tail); + unsigned long flags; + + list_to_llist_nodes(&unmap_list, &clean_nodes, &clean_tail); if (ibmr_ret) { *ibmr_ret = llist_entry(clean_nodes, struct rds_ib_mr, llnode); clean_nodes = clean_nodes->next; } /* more than one entry in llist nodes */ - if (clean_nodes) + if (clean_nodes) { + spin_lock_irqsave(&pool->clean_lock, flags); llist_add_batch(clean_nodes, clean_tail, &pool->clean_list); - + spin_unlock_irqrestore(&pool->clean_lock, flags); + } } atomic_sub(unpinned, &pool->free_pinned); @@ -471,7 +450,7 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) rds_ib_stats_inc(s_ib_rdma_mr_8k_pool_depleted); else rds_ib_stats_inc(s_ib_rdma_mr_1m_pool_depleted); - return ERR_PTR(-EAGAIN); + break; } /* We do have some empty MRs. Flush them out. */ @@ -485,7 +464,7 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool) return ibmr; } - return ibmr; + return NULL; } static void rds_ib_mr_pool_flush_worker(struct work_struct *work) @@ -610,6 +589,7 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_ibdev, init_llist_head(&pool->free_list); init_llist_head(&pool->drop_list); init_llist_head(&pool->clean_list); + spin_lock_init(&pool->clean_lock); mutex_init(&pool->flush_lock); init_waitqueue_head(&pool->flush_wait); INIT_DELAYED_WORK(&pool->flush_worker, rds_ib_mr_pool_flush_worker); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index dd55b9ac3a66..afd2ba157a13 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -942,7 +942,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK + depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 278014e26aec..d144233423c5 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2152,6 +2152,7 @@ replay: tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false, rtnl_held); tfilter_put(tp, fh); + q->flags &= ~TCQ_F_CAN_BYPASS; } errout: diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index e2faf33d282b..d59fbcc745d1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -596,8 +596,6 @@ static unsigned long fq_codel_find(struct Qdisc *sch, u32 classid) static unsigned long fq_codel_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { - /* we cannot bypass queue discipline anymore */ - sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 420bd8411677..68404a9d2ce4 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -824,8 +824,6 @@ static unsigned long sfq_find(struct Qdisc *sch, u32 classid) static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { - /* we cannot bypass queue discipline anymore */ - sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 388750ddc57a..c39db507ba3f 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -75,7 +75,7 @@ struct taprio_sched { struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; - int txtime_delay; + u32 txtime_delay; }; static ktime_t sched_base_time(const struct sched_gate_list *sched) @@ -1113,7 +1113,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto unlock; } - q->txtime_delay = nla_get_s32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]); + q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]); } if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) && @@ -1430,7 +1430,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) goto options_error; if (q->txtime_delay && - nla_put_s32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) + nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) goto options_error; if (oper && dump_schedule(skb, oper)) diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index ed39396b9bba..36bd8a6e82df 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2582,8 +2582,7 @@ do_addr_param: case SCTP_PARAM_STATE_COOKIE: asoc->peer.cookie_len = ntohs(param.p->length) - sizeof(struct sctp_paramhdr); - if (asoc->peer.cookie) - kfree(asoc->peer.cookie); + kfree(asoc->peer.cookie); asoc->peer.cookie = kmemdup(param.cookie->body, asoc->peer.cookie_len, gfp); if (!asoc->peer.cookie) retval = 0; @@ -2648,8 +2647,7 @@ do_addr_param: goto fall_through; /* Save peer's random parameter */ - if (asoc->peer.peer_random) - kfree(asoc->peer.peer_random); + kfree(asoc->peer.peer_random); asoc->peer.peer_random = kmemdup(param.p, ntohs(param.p->length), gfp); if (!asoc->peer.peer_random) { @@ -2663,8 +2661,7 @@ do_addr_param: goto fall_through; /* Save peer's HMAC list */ - if (asoc->peer.peer_hmacs) - kfree(asoc->peer.peer_hmacs); + kfree(asoc->peer.peer_hmacs); asoc->peer.peer_hmacs = kmemdup(param.p, ntohs(param.p->length), gfp); if (!asoc->peer.peer_hmacs) { @@ -2680,8 +2677,7 @@ do_addr_param: if (!ep->auth_enable) goto fall_through; - if (asoc->peer.peer_chunks) - kfree(asoc->peer.peer_chunks); + kfree(asoc->peer.peer_chunks); asoc->peer.peer_chunks = kmemdup(param.p, ntohs(param.p->length), gfp); if (!asoc->peer.peer_chunks) diff --git a/net/tipc/node.c b/net/tipc/node.c index 324a1f91b394..3a5be1d7e572 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1807,6 +1807,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) __skb_queue_head_init(&xmitq); /* Ensure message is well-formed before touching the header */ + TIPC_SKB_CB(skb)->validated = false; if (unlikely(!tipc_msg_validate(&skb))) goto discard; hdr = buf_msg(skb); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 20c91f02d3d8..83de74ca729a 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -87,21 +87,20 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, struct netdev_bpf bpf; int err = 0; + ASSERT_RTNL(); + force_zc = flags & XDP_ZEROCOPY; force_copy = flags & XDP_COPY; if (force_zc && force_copy) return -EINVAL; - rtnl_lock(); - if (xdp_get_umem_from_qid(dev, queue_id)) { - err = -EBUSY; - goto out_rtnl_unlock; - } + if (xdp_get_umem_from_qid(dev, queue_id)) + return -EBUSY; err = xdp_reg_umem_at_qid(dev, umem, queue_id); if (err) - goto out_rtnl_unlock; + return err; umem->dev = dev; umem->queue_id = queue_id; @@ -110,7 +109,7 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, if (force_copy) /* For copy-mode, we are done. */ - goto out_rtnl_unlock; + return 0; if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) { @@ -125,7 +124,6 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, err = dev->netdev_ops->ndo_bpf(dev, &bpf); if (err) goto err_unreg_umem; - rtnl_unlock(); umem->zc = true; return 0; @@ -135,8 +133,6 @@ err_unreg_umem: err = 0; /* fallback to copy mode */ if (err) xdp_clear_umem_at_qid(dev, queue_id); -out_rtnl_unlock: - rtnl_unlock(); return err; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index d4d6f10aa936..59b57d708697 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -240,6 +240,9 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, mutex_lock(&xs->mutex); + if (xs->queue_id >= xs->dev->real_num_tx_queues) + goto out; + while (xskq_peek_desc(xs->tx, &desc)) { char *buffer; u64 addr; @@ -250,12 +253,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, goto out; } - if (xskq_reserve_addr(xs->umem->cq)) - goto out; - - if (xs->queue_id >= xs->dev->real_num_tx_queues) - goto out; - len = desc.len; skb = sock_alloc_send_skb(sk, len, 1, &err); if (unlikely(!skb)) { @@ -267,7 +264,7 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, addr = desc.addr; buffer = xdp_umem_get_data(xs->umem, addr); err = skb_store_bits(skb, 0, buffer, len); - if (unlikely(err)) { + if (unlikely(err) || xskq_reserve_addr(xs->umem->cq)) { kfree_skb(skb); goto out; } @@ -433,6 +430,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY)) return -EINVAL; + rtnl_lock(); mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { err = -EBUSY; @@ -518,6 +516,7 @@ out_unlock: xs->state = XSK_BOUND; out_release: mutex_unlock(&xs->mutex); + rtnl_unlock(); return err; } diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index f90daadfbc89..1d9be26b4edd 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -284,7 +284,7 @@ $(obj)/%.o: $(src)/%.c $(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \ -I$(srctree)/tools/testing/selftests/bpf/ \ -D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \ - -D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \ + -D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \ -Wno-gnu-variable-sized-type-not-at-end \ -Wno-address-of-packed-member -Wno-tautological-compare \ -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \ diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 3ef0d9051e10..7031a4bf87a0 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -74,6 +74,7 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable", [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 17e2b1713702..4e455018da65 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -3245,7 +3245,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3257,7 +3257,7 @@ struct bpf_sock_addr { __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __bpf_md_ptr(struct bpf_sock *, sk); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ed07789b3e62..794dd5064ae8 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -4126,8 +4126,8 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, } attr.size = sizeof(attr); attr.type = type; - attr.config1 = (uint64_t)(void *)name; /* kprobe_func or uprobe_path */ - attr.config2 = offset; /* kprobe_addr or probe_offset */ + attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */ + attr.config2 = offset; /* kprobe_addr or probe_offset */ /* pid filter is meaningful only for uprobes */ pfd = syscall(__NR_perf_event_open, &attr, diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index b33740221b7e..5007b5d4fd2c 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -517,7 +517,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, err = -errno; goto out_socket; } - strncpy(xsk->ifname, ifname, IFNAMSIZ); + strncpy(xsk->ifname, ifname, IFNAMSIZ - 1); + xsk->ifname[IFNAMSIZ - 1] = '\0'; err = xsk_set_xdp_socket_config(&xsk->config, usr_config); if (err) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 2620406a53ec..11c9c62c3362 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -1,4 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +include ../../../../scripts/Kbuild.include +include ../../../scripts/Makefile.arch LIBDIR := ../../../lib BPFDIR := $(LIBDIR)/bpf @@ -81,13 +83,14 @@ all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c $(CC) -o $@ $< -Wl,--build-id -$(OUTPUT)/test_maps: map_tests/*.c +$(OUTPUT)/test_stub.o: test_stub.c + $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) -c -o $@ $< BPFOBJ := $(OUTPUT)/libbpf.a -$(TEST_GEN_PROGS): test_stub.o $(BPFOBJ) +$(TEST_GEN_PROGS): $(OUTPUT)/test_stub.o $(BPFOBJ) -$(TEST_GEN_PROGS_EXTENDED): test_stub.o $(OUTPUT)/libbpf.a +$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(OUTPUT)/libbpf.a $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c @@ -138,7 +141,8 @@ CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ $(CLANG_SYS_INCLUDES) \ - -Wno-compare-distinct-pointer-types + -Wno-compare-distinct-pointer-types \ + -D__TARGET_ARCH_$(SRCARCH) $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline @@ -172,6 +176,7 @@ endif endif TEST_PROGS_CFLAGS := -I. -I$(OUTPUT) +TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier ifneq ($(SUBREG_CODEGEN),) @@ -180,12 +185,12 @@ TEST_CUSTOM_PROGS += $(ALU32_BUILD_DIR)/test_progs_32 $(ALU32_BUILD_DIR): mkdir -p $@ -$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read +$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read | $(ALU32_BUILD_DIR) cp $< $@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\ - $(ALU32_BUILD_DIR) \ - $(ALU32_BUILD_DIR)/urandom_read + $(ALU32_BUILD_DIR)/urandom_read \ + | $(ALU32_BUILD_DIR) $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \ -o $(ALU32_BUILD_DIR)/test_progs_32 \ test_progs.c test_stub.c trace_helpers.c prog_tests/*.c \ @@ -194,10 +199,10 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\ $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H) $(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c -$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \ - $(ALU32_BUILD_DIR)/test_progs_32 - $(CLANG) $(CLANG_FLAGS) \ - -O2 -target bpf -emit-llvm -c $< -o - | \ +$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR)/test_progs_32 \ + | $(ALU32_BUILD_DIR) + ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \ + echo "clang failed") | \ $(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \ -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) @@ -208,32 +213,30 @@ endif # Have one program compiled without "-target bpf" to test whether libbpf loads # it successfully $(OUTPUT)/test_xdp.o: progs/test_xdp.c - $(CLANG) $(CLANG_FLAGS) \ - -O2 -emit-llvm -c $< -o - | \ + ($(CLANG) $(CLANG_FLAGS) -O2 -emit-llvm -c $< -o - || \ + echo "clang failed") | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif $(OUTPUT)/%.o: progs/%.c - $(CLANG) $(CLANG_FLAGS) \ - -O2 -target bpf -emit-llvm -c $< -o - | \ + ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \ + echo "clang failed") | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif -PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h -test_progs.c: $(PROG_TESTS_H) -$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) -$(OUTPUT)/test_progs: prog_tests/*.c - PROG_TESTS_DIR = $(OUTPUT)/prog_tests $(PROG_TESTS_DIR): mkdir -p $@ - +PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h PROG_TESTS_FILES := $(wildcard prog_tests/*.c) -$(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) +test_progs.c: $(PROG_TESTS_H) +$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS) +$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES) +$(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR) $(shell ( cd prog_tests/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef DECLARE'; \ @@ -246,15 +249,15 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES) echo '#endif' \ ) > $(PROG_TESTS_H)) -TEST_MAPS_CFLAGS := -I. -I$(OUTPUT) MAP_TESTS_DIR = $(OUTPUT)/map_tests $(MAP_TESTS_DIR): mkdir -p $@ MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h +MAP_TESTS_FILES := $(wildcard map_tests/*.c) test_maps.c: $(MAP_TESTS_H) $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS) -MAP_TESTS_FILES := $(wildcard map_tests/*.c) -$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES) +$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES) +$(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR) $(shell ( cd map_tests/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef DECLARE'; \ @@ -267,16 +270,15 @@ $(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES) echo '#endif' \ ) > $(MAP_TESTS_H)) -VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h -test_verifier.c: $(VERIFIER_TESTS_H) -$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) - VERIFIER_TESTS_DIR = $(OUTPUT)/verifier $(VERIFIER_TESTS_DIR): mkdir -p $@ - +VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h VERIFIER_TEST_FILES := $(wildcard verifier/*.c) -$(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES) +test_verifier.c: $(VERIFIER_TESTS_H) +$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS) +$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H) +$(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR) $(shell ( cd verifier/; \ echo '/* Generated header, do not edit */'; \ echo '#ifdef FILL_ARRAY'; \ diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 5a3d92c8bec8..f804f210244e 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -315,8 +315,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #if defined(__TARGET_ARCH_x86) #define bpf_target_x86 #define bpf_target_defined -#elif defined(__TARGET_ARCH_s930x) - #define bpf_target_s930x +#elif defined(__TARGET_ARCH_s390) + #define bpf_target_s390 #define bpf_target_defined #elif defined(__TARGET_ARCH_arm) #define bpf_target_arm @@ -341,8 +341,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #ifndef bpf_target_defined #if defined(__x86_64__) #define bpf_target_x86 -#elif defined(__s390x__) - #define bpf_target_s930x +#elif defined(__s390__) + #define bpf_target_s390 #elif defined(__arm__) #define bpf_target_arm #elif defined(__aarch64__) @@ -358,6 +358,7 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #if defined(bpf_target_x86) +#ifdef __KERNEL__ #define PT_REGS_PARM1(x) ((x)->di) #define PT_REGS_PARM2(x) ((x)->si) #define PT_REGS_PARM3(x) ((x)->dx) @@ -368,19 +369,49 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #define PT_REGS_RC(x) ((x)->ax) #define PT_REGS_SP(x) ((x)->sp) #define PT_REGS_IP(x) ((x)->ip) +#else +#ifdef __i386__ +/* i386 kernel is built with -mregparm=3 */ +#define PT_REGS_PARM1(x) ((x)->eax) +#define PT_REGS_PARM2(x) ((x)->edx) +#define PT_REGS_PARM3(x) ((x)->ecx) +#define PT_REGS_PARM4(x) 0 +#define PT_REGS_PARM5(x) 0 +#define PT_REGS_RET(x) ((x)->esp) +#define PT_REGS_FP(x) ((x)->ebp) +#define PT_REGS_RC(x) ((x)->eax) +#define PT_REGS_SP(x) ((x)->esp) +#define PT_REGS_IP(x) ((x)->eip) +#else +#define PT_REGS_PARM1(x) ((x)->rdi) +#define PT_REGS_PARM2(x) ((x)->rsi) +#define PT_REGS_PARM3(x) ((x)->rdx) +#define PT_REGS_PARM4(x) ((x)->rcx) +#define PT_REGS_PARM5(x) ((x)->r8) +#define PT_REGS_RET(x) ((x)->rsp) +#define PT_REGS_FP(x) ((x)->rbp) +#define PT_REGS_RC(x) ((x)->rax) +#define PT_REGS_SP(x) ((x)->rsp) +#define PT_REGS_IP(x) ((x)->rip) +#endif +#endif -#elif defined(bpf_target_s390x) +#elif defined(bpf_target_s390) -#define PT_REGS_PARM1(x) ((x)->gprs[2]) -#define PT_REGS_PARM2(x) ((x)->gprs[3]) -#define PT_REGS_PARM3(x) ((x)->gprs[4]) -#define PT_REGS_PARM4(x) ((x)->gprs[5]) -#define PT_REGS_PARM5(x) ((x)->gprs[6]) -#define PT_REGS_RET(x) ((x)->gprs[14]) -#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->gprs[2]) -#define PT_REGS_SP(x) ((x)->gprs[15]) -#define PT_REGS_IP(x) ((x)->psw.addr) +/* s390 provides user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_S390 const volatile user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3]) +#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4]) +#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5]) +#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6]) +#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11]) +#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2]) +#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15]) +#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr) #elif defined(bpf_target_arm) @@ -397,16 +428,20 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #elif defined(bpf_target_arm64) -#define PT_REGS_PARM1(x) ((x)->regs[0]) -#define PT_REGS_PARM2(x) ((x)->regs[1]) -#define PT_REGS_PARM3(x) ((x)->regs[2]) -#define PT_REGS_PARM4(x) ((x)->regs[3]) -#define PT_REGS_PARM5(x) ((x)->regs[4]) -#define PT_REGS_RET(x) ((x)->regs[30]) -#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */ -#define PT_REGS_RC(x) ((x)->regs[0]) -#define PT_REGS_SP(x) ((x)->sp) -#define PT_REGS_IP(x) ((x)->pc) +/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */ +struct pt_regs; +#define PT_REGS_ARM64 const volatile struct user_pt_regs +#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1]) +#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2]) +#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3]) +#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4]) +#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30]) +/* Works only with CONFIG_FRAME_POINTER */ +#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29]) +#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0]) +#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp) +#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc) #elif defined(bpf_target_mips) @@ -452,10 +487,10 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode, #endif -#ifdef bpf_target_powerpc +#if defined(bpf_target_powerpc) #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#elif bpf_target_sparc +#elif defined(bpf_target_sparc) #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP #else diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index a4686395522c..5ecc267d98b0 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -21,12 +21,6 @@ ssize_t get_base_addr() { return -EINVAL; } -#ifdef __x86_64__ -#define SYS_KPROBE_NAME "__x64_sys_nanosleep" -#else -#define SYS_KPROBE_NAME "sys_nanosleep" -#endif - void test_attach_probe(void) { const char *kprobe_name = "kprobe/sys_nanosleep"; @@ -84,7 +78,7 @@ void test_attach_probe(void) kprobe_link = bpf_program__attach_kprobe(kprobe_prog, false /* retprobe */, - SYS_KPROBE_NAME); + SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", "err %ld\n", PTR_ERR(kprobe_link))) { kprobe_link = NULL; @@ -92,7 +86,7 @@ void test_attach_probe(void) } kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog, true /* retprobe */, - SYS_KPROBE_NAME); + SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe", "err %ld\n", PTR_ERR(kretprobe_link))) { kretprobe_link = NULL; diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index 3f1ef95865ff..3003fddc0613 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -5,12 +5,6 @@ #include <sys/socket.h> #include <test_progs.h> -#ifdef __x86_64__ -#define SYS_KPROBE_NAME "__x64_sys_nanosleep" -#else -#define SYS_KPROBE_NAME "sys_nanosleep" -#endif - static void on_sample(void *ctx, int cpu, void *data, __u32 size) { int cpu_data = *(int *)data, duration = 0; @@ -56,7 +50,7 @@ void test_perf_buffer(void) /* attach kprobe */ link = bpf_program__attach_kprobe(prog, false /* retprobe */, - SYS_KPROBE_NAME); + SYS_NANOSLEEP_KPROBE_NAME); if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link))) goto out_close; diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 67cea1686305..54218ee3c004 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -173,6 +173,18 @@ static int test_send_signal_tracepoint(void) return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint"); } +static int test_send_signal_perf(void) +{ + struct perf_event_attr attr = { + .sample_period = 1, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_CPU_CLOCK, + }; + + return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, + "perf_sw_event"); +} + static int test_send_signal_nmi(void) { struct perf_event_attr attr = { @@ -181,8 +193,26 @@ static int test_send_signal_nmi(void) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, }; + int pmu_fd; + + /* Some setups (e.g. virtual machines) might run with hardware + * perf events disabled. If this is the case, skip this test. + */ + pmu_fd = syscall(__NR_perf_event_open, &attr, 0 /* pid */, + -1 /* cpu */, -1 /* group_fd */, 0 /* flags */); + if (pmu_fd == -1) { + if (errno == ENOENT) { + printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", + __func__); + return 0; + } + /* Let the test fail with a more informative message */ + } else { + close(pmu_fd); + } - return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, "perf_event"); + return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, + "perf_hw_event"); } void test_send_signal(void) @@ -190,6 +220,7 @@ void test_send_signal(void) int ret = 0; ret |= test_send_signal_tracepoint(); + ret |= test_send_signal_perf(); ret |= test_send_signal_nmi(); if (!ret) printf("test_send_signal:OK\n"); diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c index dea395af9ea9..7cdb7f878310 100644 --- a/tools/testing/selftests/bpf/progs/loop1.c +++ b/tools/testing/selftests/bpf/progs/loop1.c @@ -18,7 +18,7 @@ int nested_loops(volatile struct pt_regs* ctx) for (j = 0; j < 300; j++) for (i = 0; i < j; i++) { if (j & 1) - m = ctx->rax; + m = PT_REGS_RC(ctx); else m = j; sum += i * m; diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c index 0637bd8e8bcf..9b2f808a2863 100644 --- a/tools/testing/selftests/bpf/progs/loop2.c +++ b/tools/testing/selftests/bpf/progs/loop2.c @@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx) int i = 0; while (true) { - if (ctx->rax & 1) + if (PT_REGS_RC(ctx) & 1) i += 3; else i += 7; diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c index 30a0f6cba080..d727657d51e2 100644 --- a/tools/testing/selftests/bpf/progs/loop3.c +++ b/tools/testing/selftests/bpf/progs/loop3.c @@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx) __u64 i = 0, sum = 0; do { i++; - sum += ctx->rax; + sum += PT_REGS_RC(ctx); } while (i < 0x100000000ULL); return sum; } diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index d06b47a09097..33254b771384 100644 --- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c @@ -47,11 +47,12 @@ struct { * issue and avoid complicated C programming massaging. * This is an acceptable workaround since there is one entry here. */ +typedef __u64 raw_stack_trace_t[2 * MAX_STACK_RAWTP]; struct { __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); __uint(max_entries, 1); __type(key, __u32); - __u64 (*value)[2 * MAX_STACK_RAWTP]; + __type(value, raw_stack_trace_t); } rawdata_map SEC(".maps"); SEC("tracepoint/raw_syscalls/sys_enter") diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index bbfc8337b6f0..f5638e26865d 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c @@ -36,8 +36,7 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 128); __type(key, __u32); - /* there seems to be a bug in kernel not handling typedef properly */ - struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH]; + __type(value, stack_trace_t); } stack_amap SEC(".maps"); /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */ diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index 803c15dc109d..fa0be3e10a10 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -35,7 +35,7 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 16384); __type(key, __u32); - __u64 (*value)[PERF_MAX_STACK_DEPTH]; + __type(value, stack_trace_t); } stack_amap SEC(".maps"); /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index dad8a7e33eaa..e88d7b9d65ab 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c @@ -14,6 +14,7 @@ #include <linux/tcp.h> #include <linux/udp.h> #include "bpf_helpers.h" +#include "bpf_endian.h" static __u32 rol32(__u32 word, unsigned int shift) { @@ -305,7 +306,7 @@ bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval, ip6h->nexthdr = IPPROTO_IPV6; ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0]; ip6h->payload_len = - __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr)); + bpf_htons(pkt_bytes + sizeof(struct ipv6hdr)); ip6h->hop_limit = 4; ip6h->saddr.in6_u.u6_addr32[0] = 1; @@ -322,7 +323,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, struct real_definition *dst, __u32 pkt_bytes) { - __u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]); + __u32 ip_suffix = bpf_ntohs(pckt->flow.port16[0]); struct eth_hdr *new_eth; struct eth_hdr *old_eth; __u16 *next_iph_u16; @@ -352,7 +353,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval, iph->protocol = IPPROTO_IPIP; iph->check = 0; iph->tos = 1; - iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr)); + iph->tot_len = bpf_htons(pkt_bytes + sizeof(struct iphdr)); /* don't update iph->daddr, since it will overwrite old eth_proto * and multiple iterations of bpf_prog_run() will fail */ @@ -639,7 +640,7 @@ static int process_l3_headers_v6(struct packet_description *pckt, iph_len = sizeof(struct ipv6hdr); *protocol = ip6h->nexthdr; pckt->flow.proto = *protocol; - *pkt_bytes = __builtin_bswap16(ip6h->payload_len); + *pkt_bytes = bpf_ntohs(ip6h->payload_len); off += iph_len; if (*protocol == 45) { return XDP_DROP; @@ -671,7 +672,7 @@ static int process_l3_headers_v4(struct packet_description *pckt, return XDP_DROP; *protocol = iph->protocol; pckt->flow.proto = *protocol; - *pkt_bytes = __builtin_bswap16(iph->tot_len); + *pkt_bytes = bpf_ntohs(iph->tot_len); off += 20; if (iph->frag_off & 65343) return XDP_DROP; @@ -808,10 +809,10 @@ int balancer_ingress(struct xdp_md *ctx) nh_off = sizeof(struct eth_hdr); if (data + nh_off > data_end) return XDP_DROP; - eth_proto = eth->eth_proto; - if (eth_proto == 8) + eth_proto = bpf_ntohs(eth->eth_proto); + if (eth_proto == ETH_P_IP) return process_packet(data, nh_off, data_end, 0, ctx); - else if (eth_proto == 56710) + else if (eth_proto == ETH_P_IPV6) return process_packet(data, nh_off, data_end, 1, ctx); else return XDP_DROP; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 8351cb5f4a20..3d617e806054 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -3417,6 +3417,94 @@ static struct btf_raw_test raw_tests[] = { .value_type_id = 1, .max_entries = 4, }, +/* + * typedef int arr_t[16]; + * struct s { + * arr_t *a; + * }; + */ +{ + .descr = "struct->ptr->typedef->array->int size resolution", + .raw_types = { + BTF_STRUCT_ENC(NAME_TBD, 1, 8), /* [1] */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + BTF_PTR_ENC(3), /* [2] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_TYPE_ARRAY_ENC(5, 5, 16), /* [4] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [5] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0a\0arr_t"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "ptr_mod_chain_size_resolve_map", + .key_size = sizeof(int), + .value_size = sizeof(int) * 16, + .key_type_id = 5 /* int */, + .value_type_id = 3 /* arr_t */, + .max_entries = 4, +}, +/* + * typedef int arr_t[16][8][4]; + * struct s { + * arr_t *a; + * }; + */ +{ + .descr = "struct->ptr->typedef->multi-array->int size resolution", + .raw_types = { + BTF_STRUCT_ENC(NAME_TBD, 1, 8), /* [1] */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + BTF_PTR_ENC(3), /* [2] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_TYPE_ARRAY_ENC(5, 7, 16), /* [4] */ + BTF_TYPE_ARRAY_ENC(6, 7, 8), /* [5] */ + BTF_TYPE_ARRAY_ENC(7, 7, 4), /* [6] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0a\0arr_t"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "multi_arr_size_resolve_map", + .key_size = sizeof(int), + .value_size = sizeof(int) * 16 * 8 * 4, + .key_type_id = 7 /* int */, + .value_type_id = 3 /* arr_t */, + .max_entries = 4, +}, +/* + * typedef int int_t; + * typedef int_t arr3_t[4]; + * typedef arr3_t arr2_t[8]; + * typedef arr2_t arr1_t[16]; + * struct s { + * arr1_t *a; + * }; + */ +{ + .descr = "typedef/multi-arr mix size resolution", + .raw_types = { + BTF_STRUCT_ENC(NAME_TBD, 1, 8), /* [1] */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + BTF_PTR_ENC(3), /* [2] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_TYPE_ARRAY_ENC(5, 10, 16), /* [4] */ + BTF_TYPEDEF_ENC(NAME_TBD, 6), /* [5] */ + BTF_TYPE_ARRAY_ENC(7, 10, 8), /* [6] */ + BTF_TYPEDEF_ENC(NAME_TBD, 8), /* [7] */ + BTF_TYPE_ARRAY_ENC(9, 10, 4), /* [8] */ + BTF_TYPEDEF_ENC(NAME_TBD, 10), /* [9] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [10] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0s\0a\0arr1_t\0arr2_t\0arr3_t\0int_t"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "typedef_arra_mix_size_resolve_map", + .key_size = sizeof(int), + .value_size = sizeof(int) * 16 * 8 * 4, + .key_type_id = 10 /* int */, + .value_type_id = 3 /* arr_t */, + .max_entries = 4, +}, }; /* struct btf_raw_test raw_tests[] */ diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index f095e1d4c657..49e0f7d85643 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -92,3 +92,11 @@ int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); int extract_build_id(char *build_id, size_t size); void *spin_lock_thread(void *arg); + +#ifdef __x86_64__ +#define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" +#elif defined(__s390x__) +#define SYS_NANOSLEEP_KPROBE_NAME "__s390x_sys_nanosleep" +#else +#define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep" +#endif diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index b0773291012a..84135d5f4b35 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -86,7 +86,7 @@ struct bpf_test { int fixup_sk_storage_map[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; - uint32_t retval, retval_unpriv, insn_processed; + uint32_t insn_processed; int prog_len; enum { UNDEF, @@ -95,16 +95,20 @@ struct bpf_test { } result, result_unpriv; enum bpf_prog_type prog_type; uint8_t flags; - __u8 data[TEST_DATA_LEN]; void (*fill_helper)(struct bpf_test *self); uint8_t runs; - struct { - uint32_t retval, retval_unpriv; - union { - __u8 data[TEST_DATA_LEN]; - __u64 data64[TEST_DATA_LEN / 8]; - }; - } retvals[MAX_TEST_RUNS]; +#define bpf_testdata_struct_t \ + struct { \ + uint32_t retval, retval_unpriv; \ + union { \ + __u8 data[TEST_DATA_LEN]; \ + __u64 data64[TEST_DATA_LEN / 8]; \ + }; \ + } + union { + bpf_testdata_struct_t; + bpf_testdata_struct_t retvals[MAX_TEST_RUNS]; + }; enum bpf_attach_type expected_attach_type; }; @@ -949,17 +953,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, uint32_t expected_val; int i; - if (!test->runs) { - expected_val = unpriv && test->retval_unpriv ? - test->retval_unpriv : test->retval; - - err = do_prog_test_run(fd_prog, unpriv, expected_val, - test->data, sizeof(test->data)); - if (err) - run_errs++; - else - run_successes++; - } + if (!test->runs) + test->runs = 1; for (i = 0; i < test->runs; i++) { if (unpriv && test->retvals[i].retval_unpriv) diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c index bcb83196e459..f3c33e128709 100644 --- a/tools/testing/selftests/bpf/verifier/array_access.c +++ b/tools/testing/selftests/bpf/verifier/array_access.c @@ -226,7 +226,7 @@ BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), BPF_EXIT_INSN(), }, .fixup_map_array_ro = { 3 }, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index c3de1a2c9dc5..a53d99cebd9f 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -183,7 +183,7 @@ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), BPF_EXIT_INSN(), - BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3), BPF_MOV64_IMM(BPF_REG_2, 0), BPF_MOV64_IMM(BPF_REG_3, 0x100000), diff --git a/tools/testing/selftests/bpf/verifier/wide_access.c b/tools/testing/selftests/bpf/verifier/wide_access.c new file mode 100644 index 000000000000..ccade9312d21 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/wide_access.c @@ -0,0 +1,73 @@ +#define BPF_SOCK_ADDR_STORE(field, off, res, err) \ +{ \ + "wide store to bpf_sock_addr." #field "[" #off "]", \ + .insns = { \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \ + offsetof(struct bpf_sock_addr, field[off])), \ + BPF_EXIT_INSN(), \ + }, \ + .result = res, \ + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ + .errstr = err, \ +} + +/* user_ip6[0] is u64 aligned */ +BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT, + NULL), +BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT, + "invalid bpf_context access off=12 size=8"), +BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT, + NULL), +BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT, + "invalid bpf_context access off=20 size=8"), + +/* msg_src_ip6[0] is _not_ u64 aligned */ +BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT, + "invalid bpf_context access off=44 size=8"), +BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT, + NULL), +BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT, + "invalid bpf_context access off=52 size=8"), +BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT, + "invalid bpf_context access off=56 size=8"), + +#undef BPF_SOCK_ADDR_STORE + +#define BPF_SOCK_ADDR_LOAD(field, off, res, err) \ +{ \ + "wide load from bpf_sock_addr." #field "[" #off "]", \ + .insns = { \ + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, \ + offsetof(struct bpf_sock_addr, field[off])), \ + BPF_MOV64_IMM(BPF_REG_0, 1), \ + BPF_EXIT_INSN(), \ + }, \ + .result = res, \ + .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ + .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ + .errstr = err, \ +} + +/* user_ip6[0] is u64 aligned */ +BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT, + NULL), +BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT, + "invalid bpf_context access off=12 size=8"), +BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT, + NULL), +BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT, + "invalid bpf_context access off=20 size=8"), + +/* msg_src_ip6[0] is _not_ u64 aligned */ +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT, + "invalid bpf_context access off=44 size=8"), +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT, + NULL), +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT, + "invalid bpf_context access off=52 size=8"), +BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT, + "invalid bpf_context access off=56 size=8"), + +#undef BPF_SOCK_ADDR_LOAD diff --git a/tools/testing/selftests/bpf/verifier/wide_store.c b/tools/testing/selftests/bpf/verifier/wide_store.c deleted file mode 100644 index 8fe99602ded4..000000000000 --- a/tools/testing/selftests/bpf/verifier/wide_store.c +++ /dev/null @@ -1,36 +0,0 @@ -#define BPF_SOCK_ADDR(field, off, res, err) \ -{ \ - "wide store to bpf_sock_addr." #field "[" #off "]", \ - .insns = { \ - BPF_MOV64_IMM(BPF_REG_0, 1), \ - BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \ - offsetof(struct bpf_sock_addr, field[off])), \ - BPF_EXIT_INSN(), \ - }, \ - .result = res, \ - .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ - .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ - .errstr = err, \ -} - -/* user_ip6[0] is u64 aligned */ -BPF_SOCK_ADDR(user_ip6, 0, ACCEPT, - NULL), -BPF_SOCK_ADDR(user_ip6, 1, REJECT, - "invalid bpf_context access off=12 size=8"), -BPF_SOCK_ADDR(user_ip6, 2, ACCEPT, - NULL), -BPF_SOCK_ADDR(user_ip6, 3, REJECT, - "invalid bpf_context access off=20 size=8"), - -/* msg_src_ip6[0] is _not_ u64 aligned */ -BPF_SOCK_ADDR(msg_src_ip6, 0, REJECT, - "invalid bpf_context access off=44 size=8"), -BPF_SOCK_ADDR(msg_src_ip6, 1, ACCEPT, - NULL), -BPF_SOCK_ADDR(msg_src_ip6, 2, REJECT, - "invalid bpf_context access off=52 size=8"), -BPF_SOCK_ADDR(msg_src_ip6, 3, REJECT, - "invalid bpf_context access off=56 size=8"), - -#undef BPF_SOCK_ADDR diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 9457aaeae092..4465fc2dae14 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,12 +9,13 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw" +TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter" VERBOSE=0 PAUSE_ON_FAIL=no PAUSE=no IP="ip -netns ns1" +NS_EXEC="ip netns exec ns1" log_test() { @@ -433,6 +434,37 @@ fib_carrier_test() fib_carrier_unicast_test } +fib_rp_filter_test() +{ + echo + echo "IPv4 rp_filter tests" + + setup + + set -e + $IP link set dev lo address 52:54:00:6a:c7:5e + $IP link set dummy0 address 52:54:00:6a:c7:5e + $IP link add dummy1 type dummy + $IP link set dummy1 address 52:54:00:6a:c7:5e + $IP link set dev dummy1 up + $NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1 + $NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1 + $NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1 + + $NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel + $NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo + $NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo + set +e + + run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1" + log_test $? 0 "rp_filter passes local packets" + + run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1" + log_test $? 0 "rp_filter passes loopback packets" + + cleanup +} + ################################################################################ # Tests on nexthop spec @@ -1557,6 +1589,7 @@ do fib_unreg_test|unregister) fib_unreg_test;; fib_down_test|down) fib_down_test;; fib_carrier_test|carrier) fib_carrier_test;; + fib_rp_filter_test|rp_filter) fib_rp_filter_test;; fib_nexthop_test|nexthop) fib_nexthop_test;; ipv6_route_test|ipv6_rt) ipv6_route_test;; ipv4_route_test|ipv4_rt) ipv4_route_test;; |