diff options
52 files changed, 569 insertions, 291 deletions
diff --git a/Documentation/networking/generic_netlink.rst b/Documentation/networking/generic_netlink.rst index 59e04ccf80c1..d960dbd7e80e 100644 --- a/Documentation/networking/generic_netlink.rst +++ b/Documentation/networking/generic_netlink.rst @@ -6,4 +6,4 @@ Generic Netlink A wiki document on how to use Generic Netlink can be found here: - * http://www.linuxfoundation.org/collaborate/workgroups/networking/generic_netlink_howto + * https://wiki.linuxfoundation.org/networking/generic_netlink_howto diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index 24150c933fcb..dc3253b318da 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -113,6 +113,7 @@ static int com20020_probe(struct pcmcia_device *p_dev) struct com20020_dev *info; struct net_device *dev; struct arcnet_local *lp; + int ret = -ENOMEM; dev_dbg(&p_dev->dev, "com20020_attach()\n"); @@ -142,12 +143,18 @@ static int com20020_probe(struct pcmcia_device *p_dev) info->dev = dev; p_dev->priv = info; - return com20020_config(p_dev); + ret = com20020_config(p_dev); + if (ret) + goto fail_config; + + return 0; +fail_config: + free_arcdev(dev); fail_alloc_dev: kfree(info); fail_alloc_info: - return -ENOMEM; + return ret; } /* com20020_attach */ static void com20020_detach(struct pcmcia_device *link) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 11d15cd03600..77d4cb4ad782 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -795,16 +795,20 @@ static void bnx2x_vf_enable_traffic(struct bnx2x *bp, struct bnx2x_virtf *vf) static u8 bnx2x_vf_is_pcie_pending(struct bnx2x *bp, u8 abs_vfid) { - struct pci_dev *dev; struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid); + struct pci_dev *dev; + bool pending; if (!vf) return false; dev = pci_get_domain_bus_and_slot(vf->domain, vf->bus, vf->devfn); - if (dev) - return bnx2x_is_pcie_pending(dev); - return false; + if (!dev) + return false; + pending = bnx2x_is_pcie_pending(dev); + pci_dev_put(dev); + + return pending; } int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid) diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c index a523ddda7609..de7105a84747 100644 --- a/drivers/net/ethernet/davicom/dm9051.c +++ b/drivers/net/ethernet/davicom/dm9051.c @@ -798,8 +798,10 @@ static int dm9051_loop_rx(struct board_info *db) } ret = dm9051_stop_mrcmd(db); - if (ret) + if (ret) { + dev_kfree_skb(skb); return ret; + } skb->protocol = eth_type_trans(skb, db->ndev); if (db->ndev->features & NETIF_F_RXCSUM) diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 48fb391951dd..13d5ff4e0e02 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -542,6 +542,27 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) return (budget != 0); } +static bool tsnep_tx_pending(struct tsnep_tx *tx) +{ + unsigned long flags; + struct tsnep_tx_entry *entry; + bool pending = false; + + spin_lock_irqsave(&tx->lock, flags); + + if (tx->read != tx->write) { + entry = &tx->entry[tx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_TX_DESC_OWNER_MASK) == + (entry->properties & TSNEP_TX_DESC_OWNER_MASK)) + pending = true; + } + + spin_unlock_irqrestore(&tx->lock, flags); + + return pending; +} + static int tsnep_tx_open(struct tsnep_adapter *adapter, void __iomem *addr, int queue_index, struct tsnep_tx *tx) { @@ -821,6 +842,19 @@ static int tsnep_rx_poll(struct tsnep_rx *rx, struct napi_struct *napi, return done; } +static bool tsnep_rx_pending(struct tsnep_rx *rx) +{ + struct tsnep_rx_entry *entry; + + entry = &rx->entry[rx->read]; + if ((__le32_to_cpu(entry->desc_wb->properties) & + TSNEP_DESC_OWNER_COUNTER_MASK) == + (entry->properties & TSNEP_DESC_OWNER_COUNTER_MASK)) + return true; + + return false; +} + static int tsnep_rx_open(struct tsnep_adapter *adapter, void __iomem *addr, int queue_index, struct tsnep_rx *rx) { @@ -866,6 +900,17 @@ static void tsnep_rx_close(struct tsnep_rx *rx) tsnep_rx_ring_cleanup(rx); } +static bool tsnep_pending(struct tsnep_queue *queue) +{ + if (queue->tx && tsnep_tx_pending(queue->tx)) + return true; + + if (queue->rx && tsnep_rx_pending(queue->rx)) + return true; + + return false; +} + static int tsnep_poll(struct napi_struct *napi, int budget) { struct tsnep_queue *queue = container_of(napi, struct tsnep_queue, @@ -886,9 +931,19 @@ static int tsnep_poll(struct napi_struct *napi, int budget) if (!complete) return budget; - if (likely(napi_complete_done(napi, done))) + if (likely(napi_complete_done(napi, done))) { tsnep_enable_irq(queue->adapter, queue->irq_mask); + /* reschedule if work is already pending, prevent rotten packets + * which are transmitted or received after polling but before + * interrupt enable + */ + if (tsnep_pending(queue)) { + tsnep_disable_irq(queue->adapter, queue->irq_mask); + napi_schedule(napi); + } + } + return min(done, budget - 1); } diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 3f6187c16424..0d1bab4ac1b0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -298,7 +298,6 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) -#define IAVF_FLAG_INITIAL_MAC_SET BIT(23) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 3fc572341781..d7465296f650 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1087,12 +1087,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (ret) return ret; - /* If this is an initial set MAC during VF spawn do not wait */ - if (adapter->flags & IAVF_FLAG_INITIAL_MAC_SET) { - adapter->flags &= ~IAVF_FLAG_INITIAL_MAC_SET; - return 0; - } - ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, iavf_is_mac_set_handled(netdev, addr->sa_data), msecs_to_jiffies(2500)); @@ -2605,8 +2599,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - adapter->flags |= IAVF_FLAG_INITIAL_MAC_SET; - adapter->tx_desc_count = IAVF_DEFAULT_TXD; adapter->rx_desc_count = IAVF_DEFAULT_RXD; err = iavf_init_interrupt_scheme(adapter); @@ -2921,7 +2913,6 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) iavf_free_queues(adapter); memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); - adapter->netdev->flags &= ~IFF_UP; adapter->flags &= ~IAVF_FLAG_RESET_PENDING; iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); @@ -3021,6 +3012,11 @@ static void iavf_reset_task(struct work_struct *work) iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + if (netif_running(netdev)) { + rtnl_lock(); + dev_close(netdev); + rtnl_unlock(); + } return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3033,6 +3029,7 @@ continue_reset: if (running) { netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); adapter->link_up = false; iavf_napi_disable_all(adapter); } @@ -3172,6 +3169,16 @@ reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); + + if (netif_running(netdev)) { + /* Close device to ensure that Tx queues will not be started + * during netif_device_attach() at the end of the reset task. + */ + rtnl_lock(); + dev_close(netdev); + rtnl_unlock(); + } + dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); reset_finish: rtnl_lock(); @@ -5035,23 +5042,21 @@ static int __maybe_unused iavf_resume(struct device *dev_d) static void iavf_remove(struct pci_dev *pdev) { struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_cloud_filter *cf, *cftmp; struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; - struct iavf_cloud_filter *cf, *cftmp; - struct iavf_hw *hw = &adapter->hw; + struct net_device *netdev; + struct iavf_hw *hw; int err; - /* When reboot/shutdown is in progress no need to do anything - * as the adapter is already REMOVE state that was set during - * iavf_shutdown() callback. - */ - if (adapter->state == __IAVF_REMOVE) + netdev = adapter->netdev; + hw = &adapter->hw; + + if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return; - set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); /* Wait until port initialization is complete. * There are flows where register/unregister netdev may race. */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 0f6718719453..ca2898467dcb 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3145,15 +3145,15 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) */ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data) { - irqreturn_t ret = IRQ_HANDLED; struct ice_pf *pf = data; - bool irq_handled; - irq_handled = ice_ptp_process_ts(pf); - if (!irq_handled) - ret = IRQ_WAKE_THREAD; + if (ice_is_reset_in_progress(pf->state)) + return IRQ_HANDLED; - return ret; + while (!ice_ptp_process_ts(pf)) + usleep_range(50, 100); + + return IRQ_HANDLED; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 011b727ab190..0f668468d141 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -614,11 +614,14 @@ static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) * 2) extend the 40b timestamp value to get a 64bit timestamp * 3) send that timestamp to the stack * - * After looping, if we still have waiting SKBs, return true. This may cause us - * effectively poll even when not strictly necessary. We do this because it's - * possible a new timestamp was requested around the same time as the interrupt. - * In some cases hardware might not interrupt us again when the timestamp is - * captured. + * Returns true if all timestamps were handled, and false if any slots remain + * without a timestamp. + * + * After looping, if we still have waiting SKBs, return false. This may cause + * us effectively poll even when not strictly necessary. We do this because + * it's possible a new timestamp was requested around the same time as the + * interrupt. In some cases hardware might not interrupt us again when the + * timestamp is captured. * * Note that we only take the tracking lock when clearing the bit and when * checking if we need to re-queue this task. The only place where bits can be @@ -641,7 +644,7 @@ static bool ice_ptp_tx_tstamp(struct ice_ptp_tx *tx) u8 idx; if (!tx->init) - return false; + return true; ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); @@ -2381,10 +2384,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) */ bool ice_ptp_process_ts(struct ice_pf *pf) { - if (pf->ptp.port.tx.init) - return ice_ptp_tx_tstamp(&pf->ptp.port.tx); - - return false; + return ice_ptp_tx_tstamp(&pf->ptp.port.tx); } static void ice_ptp_periodic_work(struct kthread_work *work) diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index 6b4f640163f7..993ac180a5db 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -32,7 +32,6 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK - depends on MACSEC || !MACSEC depends on (64BIT && COMPILE_TEST) || ARM64 select DIMLIB depends on PCI diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 1d1f2342e3ec..1d36619c5ec9 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2378,8 +2378,10 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) data + NET_SKB_PAD + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dma_dev, - dma_addr))) + dma_addr))) { + skb_free_frag(data); return -ENOMEM; + } } rxd->rxd1 = (unsigned int)dma_addr; ring->data[i] = data; @@ -4145,13 +4147,13 @@ static int mtk_probe(struct platform_device *pdev) eth->soc->offload_version, i); if (!eth->ppe[i]) { err = -ENOMEM; - goto err_free_dev; + goto err_deinit_ppe; } } err = mtk_eth_offload_init(eth); if (err) - goto err_free_dev; + goto err_deinit_ppe; } for (i = 0; i < MTK_MAX_DEVS; i++) { @@ -4161,7 +4163,7 @@ static int mtk_probe(struct platform_device *pdev) err = register_netdev(eth->netdev[i]); if (err) { dev_err(eth->dev, "error bringing up device\n"); - goto err_deinit_mdio; + goto err_deinit_ppe; } else netif_info(eth, probe, eth->netdev[i], "mediatek frame engine at 0x%08lx, irq %d\n", @@ -4179,7 +4181,8 @@ static int mtk_probe(struct platform_device *pdev) return 0; -err_deinit_mdio: +err_deinit_ppe: + mtk_ppe_deinit(eth); mtk_mdio_cleanup(eth); err_free_dev: mtk_free_dev(eth); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 2d8ca99f2467..784ecb2dc9fb 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -737,7 +737,7 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, MTK_PPE_ENTRIES * soc->foe_entry_size, &ppe->foe_phys, GFP_KERNEL); if (!foe) - return NULL; + goto err_free_l2_flows; ppe->foe_table = foe; @@ -745,11 +745,26 @@ struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, sizeof(*ppe->foe_flow); ppe->foe_flow = devm_kzalloc(dev, foe_flow_size, GFP_KERNEL); if (!ppe->foe_flow) - return NULL; + goto err_free_l2_flows; mtk_ppe_debugfs_init(ppe, index); return ppe; + +err_free_l2_flows: + rhashtable_destroy(&ppe->l2_flows); + return NULL; +} + +void mtk_ppe_deinit(struct mtk_eth *eth) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(eth->ppe); i++) { + if (!eth->ppe[i]) + return; + rhashtable_destroy(ð->ppe[i]->l2_flows); + } } static void mtk_ppe_init_foe_table(struct mtk_ppe *ppe) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index 0b7a67a958e4..a09c32539bcc 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -304,6 +304,7 @@ struct mtk_ppe { struct mtk_ppe *mtk_ppe_init(struct mtk_eth *eth, void __iomem *base, int version, int index); +void mtk_ppe_deinit(struct mtk_eth *eth); void mtk_ppe_start(struct mtk_ppe *ppe); int mtk_ppe_stop(struct mtk_ppe *ppe); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 2e0d59ca62b5..74bd05e5dda2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,8 @@ #include "mlx5_core.h" #include "lib/eq.h" #include "lib/tout.h" +#define CREATE_TRACE_POINTS +#include "diag/cmd_tracepoint.h" enum { CMD_IF_REV = 5, @@ -785,27 +787,14 @@ EXPORT_SYMBOL(mlx5_cmd_out_err); static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out) { u16 opcode, op_mod; - u32 syndrome; - u8 status; u16 uid; - int err; - - syndrome = MLX5_GET(mbox_out, out, syndrome); - status = MLX5_GET(mbox_out, out, status); opcode = MLX5_GET(mbox_in, in, opcode); op_mod = MLX5_GET(mbox_in, in, op_mod); uid = MLX5_GET(mbox_in, in, uid); - err = cmd_status_to_err(status); - if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY) mlx5_cmd_out_err(dev, opcode, op_mod, out); - else - mlx5_core_dbg(dev, - "%s(0x%x) op_mod(0x%x) uid(%d) failed, status %s(0x%x), syndrome (0x%x), err(%d)\n", - mlx5_command_str(opcode), opcode, op_mod, uid, - cmd_status_str(status), status, syndrome, err); } int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out) @@ -1016,6 +1005,7 @@ static void cmd_work_handler(struct work_struct *work) cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); + cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* Skip sending command to fw if internal error */ if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) { ent->ret = -ENXIO; @@ -1023,7 +1013,6 @@ static void cmd_work_handler(struct work_struct *work) return; } - cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -1672,8 +1661,8 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force cmd_ent_put(ent); /* timeout work was canceled */ if (!forced || /* Real FW completion */ - pci_channel_offline(dev->pdev) || /* FW is inaccessible */ - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + mlx5_cmd_is_down(dev) || /* No real FW completion is expected */ + !opcode_allowed(cmd, ent->op)) cmd_ent_put(ent); ent->ts2 = ktime_get_ns(); @@ -1892,6 +1881,16 @@ out_in: return err; } +static void mlx5_cmd_err_trace(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out) +{ + u32 syndrome = MLX5_GET(mbox_out, out, syndrome); + u8 status = MLX5_GET(mbox_out, out, status); + + trace_mlx5_cmd(mlx5_command_str(opcode), opcode, op_mod, + cmd_status_str(status), status, syndrome, + cmd_status_to_err(status)); +} + static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, u32 syndrome, int err) { @@ -1914,7 +1913,7 @@ static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, } /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */ -static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out) +static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, u16 op_mod, void *out) { u32 syndrome = MLX5_GET(mbox_out, out, syndrome); u8 status = MLX5_GET(mbox_out, out, status); @@ -1922,8 +1921,10 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void * if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */ err = -EIO; - if (!err && status != MLX5_CMD_STAT_OK) + if (!err && status != MLX5_CMD_STAT_OK) { err = -EREMOTEIO; + mlx5_cmd_err_trace(dev, opcode, op_mod, out); + } cmd_status_log(dev, opcode, status, syndrome, err); return err; @@ -1951,9 +1952,9 @@ int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod); - err = cmd_status_err(dev, err, opcode, out); - return err; + return cmd_status_err(dev, err, opcode, op_mod, out); } EXPORT_SYMBOL(mlx5_cmd_do); @@ -1997,8 +1998,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true); u16 opcode = MLX5_GET(mbox_in, in, opcode); + u16 op_mod = MLX5_GET(mbox_in, in, op_mod); - err = cmd_status_err(dev, err, opcode, out); + err = cmd_status_err(dev, err, opcode, op_mod, out); return mlx5_cmd_check(dev, err, in, out); } EXPORT_SYMBOL(mlx5_cmd_exec_polling); @@ -2034,7 +2036,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) struct mlx5_async_ctx *ctx; ctx = work->ctx; - status = cmd_status_err(ctx->dev, status, work->opcode, work->out); + status = cmd_status_err(ctx->dev, status, work->opcode, work->op_mod, work->out); work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) complete(&ctx->inflight_done); @@ -2049,6 +2051,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, work->ctx = ctx; work->user_callback = callback; work->opcode = MLX5_GET(mbox_in, in, opcode); + work->op_mod = MLX5_GET(mbox_in, in, op_mod); work->out = out; if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) return -EIO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h new file mode 100644 index 000000000000..406ebe17405f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/cmd_tracepoint.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_CMD_TP_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_CMD_TP_H_ + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> + +TRACE_EVENT(mlx5_cmd, + TP_PROTO(const char *command_str, u16 opcode, u16 op_mod, + const char *status_str, u8 status, u32 syndrome, int err), + TP_ARGS(command_str, opcode, op_mod, status_str, status, syndrome, err), + TP_STRUCT__entry(__string(command_str, command_str) + __field(u16, opcode) + __field(u16, op_mod) + __string(status_str, status_str) + __field(u8, status) + __field(u32, syndrome) + __field(int, err) + ), + TP_fast_assign(__assign_str(command_str, command_str); + __entry->opcode = opcode; + __entry->op_mod = op_mod; + __assign_str(status_str, status_str); + __entry->status = status; + __entry->syndrome = syndrome; + __entry->err = err; + ), + TP_printk("%s(0x%x) op_mod(0x%x) failed, status %s(0x%x), syndrome (0x%x), err(%d)", + __get_str(command_str), __entry->opcode, __entry->op_mod, + __get_str(status_str), __entry->status, __entry->syndrome, + __entry->err) +); + +#endif /* _MLX5_CMD_TP_H_ */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ./diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE cmd_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 978a2bb8e122..21831386b26e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -638,7 +638,7 @@ static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer, trace_timestamp = (timestamp_event.timestamp & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); else - trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) | + trace_timestamp = ((timestamp_event.timestamp - 1) & MASK_52_7) | (str_frmt->timestamp & MASK_6_0); mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 5aff97914367..ff73d25bc6eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -224,15 +224,16 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, list_for_each_entry(flow, flow_list, tmp_list) { if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW)) continue; - spec = &flow->attr->parse_attr->spec; - - /* update from encap rule to slow path rule */ - rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; /* mark the flow's encap dest as non-valid */ esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; + esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL; + + /* update from encap rule to slow path rule */ + spec = &flow->attr->parse_attr->spec; + rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec); if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -251,6 +252,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, /* we know that the encap is valid */ e->flags &= ~MLX5_ENCAP_ENTRY_VALID; mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); + e->pkt_reformat = NULL; } static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow, @@ -762,8 +764,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid) + struct net_device **encap_dev) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -878,9 +879,8 @@ attach_flow: if (e->flags & MLX5_ENCAP_ENTRY_VALID) { attr->esw_attr->dests[out_index].pkt_reformat = e->pkt_reformat; attr->esw_attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; - *encap_valid = true; } else { - *encap_valid = false; + flow_flag_set(flow, SLOW); } mutex_unlock(&esw->offloads.encap_tbl_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h index d542b8476491..8ad273dde40e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.h @@ -17,8 +17,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct net_device *mirred_dev, int out_index, struct netlink_ext_ack *extack, - struct net_device **encap_dev, - bool *encap_valid); + struct net_device **encap_dev); int mlx5e_attach_decap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 2ef36cb9555a..3dc6c987b8da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -368,15 +368,15 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, obj_attrs.aso_pdn = macsec->aso.pdn; obj_attrs.epn_state = sa->epn_state; - if (is_tx) { - obj_attrs.ssci = cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci); - key = &ctx->sa.tx_sa->key; - } else { - obj_attrs.ssci = cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); - key = &ctx->sa.rx_sa->key; + key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key; + + if (sa->epn_state.epn_enabled) { + obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) : + cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); + + memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); } - memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); obj_attrs.replay_window = ctx->secy->replay_window; obj_attrs.replay_protect = ctx->secy->replay_protect; @@ -1155,7 +1155,7 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, continue; if (rx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, rx_sa, false, false); + err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false); if (err) goto out; } @@ -1536,6 +1536,8 @@ static void macsec_async_event(struct work_struct *work) async_work = container_of(work, struct mlx5e_macsec_async_work, work); macsec = async_work->macsec; + mutex_lock(&macsec->lock); + mdev = async_work->mdev; obj_id = async_work->obj_id; macsec_sa = get_macsec_tx_sa_from_obj_id(macsec, obj_id); @@ -1557,6 +1559,7 @@ static void macsec_async_event(struct work_struct *work) out_async_work: kfree(async_work); + mutex_unlock(&macsec->lock); } static int macsec_obj_change_event(struct notifier_block *nb, unsigned long event, void *data) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 24aa25da482b..1728e197558d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -35,7 +35,6 @@ #include "en.h" #include "en/port.h" #include "en/params.h" -#include "en/xsk/pool.h" #include "en/ptp.h" #include "lib/clock.h" #include "en/fs_ethtool.h" @@ -412,15 +411,8 @@ void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch) { mutex_lock(&priv->state_lock); - ch->max_combined = priv->max_nch; ch->combined_count = priv->channels.params.num_channels; - if (priv->xsk.refcnt) { - /* The upper half are XSK queues. */ - ch->max_combined *= 2; - ch->combined_count *= 2; - } - mutex_unlock(&priv->state_lock); } @@ -454,16 +446,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, mutex_lock(&priv->state_lock); - /* Don't allow changing the number of channels if there is an active - * XSK, because the numeration of the XSK and regular RQs will change. - */ - if (priv->xsk.refcnt) { - err = -EINVAL; - netdev_err(priv->netdev, "%s: AF_XDP is active, cannot change the number of channels\n", - __func__); - goto out; - } - /* Don't allow changing the number of channels if HTB offload is active, * because the numeration of the QoS SQs will change, while per-queue * qdiscs are attached. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e3a4f01bcceb..5e41dfdf79c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -206,10 +206,11 @@ static void mlx5e_disable_blocking_events(struct mlx5e_priv *priv) static u16 mlx5e_mpwrq_umr_octowords(u32 entries, enum mlx5e_mpwrq_umr_mode umr_mode) { u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode); + u32 sz; - WARN_ON_ONCE(entries * umr_entry_size % MLX5_OCTWORD); + sz = ALIGN(entries * umr_entry_size, MLX5_UMR_MTT_ALIGNMENT); - return entries * umr_entry_size / MLX5_OCTWORD; + return sz / MLX5_OCTWORD; } static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 5a6aa61ec82a..bd9936af4582 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1634,7 +1634,6 @@ set_encap_dests(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack, - bool *encap_valid, bool *vf_tun) { struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -1651,7 +1650,6 @@ set_encap_dests(struct mlx5e_priv *priv, parse_attr = attr->parse_attr; esw_attr = attr->esw_attr; *vf_tun = false; - *encap_valid = true; for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { struct net_device *out_dev; @@ -1668,7 +1666,7 @@ set_encap_dests(struct mlx5e_priv *priv, goto out; } err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index, - extack, &encap_dev, encap_valid); + extack, &encap_dev); dev_put(out_dev); if (err) goto out; @@ -1732,8 +1730,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; struct mlx5_esw_flow_attr *esw_attr; - bool vf_tun, encap_valid; u32 max_prio, max_chain; + bool vf_tun; int err = 0; parse_attr = attr->parse_attr; @@ -1823,7 +1821,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, esw_attr->int_port = int_port; } - err = set_encap_dests(priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(priv, flow, attr, extack, &vf_tun); if (err) goto err_out; @@ -1853,7 +1851,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, * (1) there's no error * (2) there's an encap action and we don't have valid neigh */ - if (!encap_valid || flow_flag_test(flow, SLOW)) + if (flow_flag_test(flow, SLOW)) flow->rule[0] = mlx5e_tc_offload_to_slow_path(esw, flow, &parse_attr->spec); else flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); @@ -3759,7 +3757,7 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) struct mlx5e_post_act *post_act = get_post_action(flow->priv); struct mlx5_flow_attr *attr, *next_attr = NULL; struct mlx5e_post_act_handle *handle; - bool vf_tun, encap_valid = true; + bool vf_tun; int err; /* This is going in reverse order as needed. @@ -3781,13 +3779,10 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) if (list_is_last(&attr->list, &flow->attrs)) break; - err = set_encap_dests(flow->priv, flow, attr, extack, &encap_valid, &vf_tun); + err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun); if (err) goto out_free; - if (!encap_valid) - flow_flag_set(flow, SLOW); - err = actions_prepare_mod_hdr_actions(flow->priv, flow, attr, extack); if (err) goto out_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 728ca9f2bb9d..3fda75fe168c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -433,7 +433,7 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f mlx5_lag_mpesw_is_activated(esw->dev)) dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK; } - if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) { + if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) { if (pkt_reformat) { flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; flow_act->pkt_reformat = esw_attr->dests[attr_idx].pkt_reformat; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 9d908a0ccfef..1e46f9afa40e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -9,7 +9,8 @@ enum { MLX5_FW_RESET_FLAGS_RESET_REQUESTED, MLX5_FW_RESET_FLAGS_NACK_RESET_REQUEST, MLX5_FW_RESET_FLAGS_PENDING_COMP, - MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS + MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, + MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED }; struct mlx5_fw_reset { @@ -406,7 +407,7 @@ static void mlx5_sync_reset_now_event(struct work_struct *work) err = mlx5_pci_link_toggle(dev); if (err) { mlx5_core_warn(dev, "mlx5_pci_link_toggle failed, no reset done, err %d\n", err); - goto done; + set_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags); } mlx5_enter_error_state(dev, true); @@ -482,6 +483,10 @@ int mlx5_fw_reset_wait_reset_done(struct mlx5_core_dev *dev) goto out; } err = fw_reset->ret; + if (test_and_clear_bit(MLX5_FW_RESET_FLAGS_RELOAD_REQUIRED, &fw_reset->reset_flags)) { + mlx5_unload_one_devl_locked(dev); + mlx5_load_one_devl_locked(dev, false); + } out: clear_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index a9f4ede4a9bf..be1307a63e6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -228,9 +228,8 @@ static void mlx5_ldev_free(struct kref *ref) if (ldev->nb.notifier_call) unregister_netdevice_notifier_net(&init_net, &ldev->nb); mlx5_lag_mp_cleanup(ldev); - mlx5_lag_mpesw_cleanup(ldev); - cancel_work_sync(&ldev->mpesw_work); destroy_workqueue(ldev->wq); + mlx5_lag_mpesw_cleanup(ldev); mutex_destroy(&ldev->lock); kfree(ldev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index ce2ce8ccbd70..f30ac2de639f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -50,6 +50,19 @@ struct lag_tracker { enum netdev_lag_hash hash_type; }; +enum mpesw_op { + MLX5_MPESW_OP_ENABLE, + MLX5_MPESW_OP_DISABLE, +}; + +struct mlx5_mpesw_work_st { + struct work_struct work; + struct mlx5_lag *lag; + enum mpesw_op op; + struct completion comp; + int result; +}; + /* LAG data of a ConnectX card. * It serves both its phys functions. */ @@ -66,7 +79,6 @@ struct mlx5_lag { struct lag_tracker tracker; struct workqueue_struct *wq; struct delayed_work bond_work; - struct work_struct mpesw_work; struct notifier_block nb; struct lag_mp lag_mp; struct mlx5_lag_port_sel port_sel; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index f643202b29c6..c17e8f1ec914 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -7,63 +7,95 @@ #include "eswitch.h" #include "lib/mlx5.h" -void mlx5_mpesw_work(struct work_struct *work) +static int add_mpesw_rule(struct mlx5_lag *ldev) { - struct mlx5_lag *ldev = container_of(work, struct mlx5_lag, mpesw_work); + struct mlx5_core_dev *dev = ldev->pf[MLX5_LAG_P1].dev; + int err; - mutex_lock(&ldev->lock); - mlx5_disable_lag(ldev); - mutex_unlock(&ldev->lock); -} + if (atomic_add_return(1, &ldev->lag_mpesw.mpesw_rule_count) != 1) + return 0; -static void mlx5_lag_disable_mpesw(struct mlx5_core_dev *dev) -{ - struct mlx5_lag *ldev = dev->priv.lag; + if (ldev->mode != MLX5_LAG_MODE_NONE) { + err = -EINVAL; + goto out_err; + } - if (!queue_work(ldev->wq, &ldev->mpesw_work)) - mlx5_core_warn(dev, "failed to queue work\n"); + err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false); + if (err) { + mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err); + goto out_err; + } + + return 0; + +out_err: + atomic_dec(&ldev->lag_mpesw.mpesw_rule_count); + return err; } -void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev) +static void del_mpesw_rule(struct mlx5_lag *ldev) { - struct mlx5_lag *ldev = dev->priv.lag; + if (!atomic_dec_return(&ldev->lag_mpesw.mpesw_rule_count) && + ldev->mode == MLX5_LAG_MODE_MPESW) + mlx5_disable_lag(ldev); +} - if (!ldev) - return; +static void mlx5_mpesw_work(struct work_struct *work) +{ + struct mlx5_mpesw_work_st *mpesww = container_of(work, struct mlx5_mpesw_work_st, work); + struct mlx5_lag *ldev = mpesww->lag; mutex_lock(&ldev->lock); - if (!atomic_dec_return(&ldev->lag_mpesw.mpesw_rule_count) && - ldev->mode == MLX5_LAG_MODE_MPESW) - mlx5_lag_disable_mpesw(dev); + if (mpesww->op == MLX5_MPESW_OP_ENABLE) + mpesww->result = add_mpesw_rule(ldev); + else if (mpesww->op == MLX5_MPESW_OP_DISABLE) + del_mpesw_rule(ldev); mutex_unlock(&ldev->lock); + + complete(&mpesww->comp); } -int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) +static int mlx5_lag_mpesw_queue_work(struct mlx5_core_dev *dev, + enum mpesw_op op) { struct mlx5_lag *ldev = dev->priv.lag; + struct mlx5_mpesw_work_st *work; int err = 0; if (!ldev) return 0; - mutex_lock(&ldev->lock); - if (atomic_add_return(1, &ldev->lag_mpesw.mpesw_rule_count) != 1) - goto out; + work = kzalloc(sizeof(*work), GFP_KERNEL); + if (!work) + return -ENOMEM; - if (ldev->mode != MLX5_LAG_MODE_NONE) { + INIT_WORK(&work->work, mlx5_mpesw_work); + init_completion(&work->comp); + work->op = op; + work->lag = ldev; + + if (!queue_work(ldev->wq, &work->work)) { + mlx5_core_warn(dev, "failed to queue mpesw work\n"); err = -EINVAL; goto out; } - - err = mlx5_activate_lag(ldev, NULL, MLX5_LAG_MODE_MPESW, false); - if (err) - mlx5_core_warn(dev, "Failed to create LAG in MPESW mode (%d)\n", err); - + wait_for_completion(&work->comp); + err = work->result; out: - mutex_unlock(&ldev->lock); + kfree(work); return err; } +void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev) +{ + mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_DISABLE); +} + +int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) +{ + return mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_ENABLE); +} + int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) { struct mlx5_lag *ldev = mdev->priv.lag; @@ -71,12 +103,9 @@ int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) if (!netif_is_bond_master(out_dev) || !ldev) return 0; - mutex_lock(&ldev->lock); - if (ldev->mode == MLX5_LAG_MODE_MPESW) { - mutex_unlock(&ldev->lock); + if (ldev->mode == MLX5_LAG_MODE_MPESW) return -EOPNOTSUPP; - } - mutex_unlock(&ldev->lock); + return 0; } @@ -90,11 +119,10 @@ bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev) void mlx5_lag_mpesw_init(struct mlx5_lag *ldev) { - INIT_WORK(&ldev->mpesw_work, mlx5_mpesw_work); atomic_set(&ldev->lag_mpesw.mpesw_rule_count, 0); } void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev) { - cancel_delayed_work_sync(&ldev->bond_work); + WARN_ON(atomic_read(&ldev->lag_mpesw.mpesw_rule_count)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h index be4abcb8fcd5..88e8daffcf92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h @@ -12,7 +12,6 @@ struct lag_mpesw { atomic_t mpesw_rule_count; }; -void mlx5_mpesw_work(struct work_struct *work); int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev); bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 283c4cc28944..e58775a7d955 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1798,7 +1798,8 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, res = state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; - mlx5_pci_trace(dev, "Exit, result = %d, %s\n", res, result2str(res)); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Exit, result = %d, %s\n", + __func__, dev->state, dev->pci_status, res, result2str(res)); return res; } @@ -1837,7 +1838,8 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); int err; - mlx5_pci_trace(dev, "Enter\n"); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Enter\n", + __func__, dev->state, dev->pci_status); err = mlx5_pci_enable_device(dev); if (err) { @@ -1859,7 +1861,8 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) res = PCI_ERS_RESULT_RECOVERED; out: - mlx5_pci_trace(dev, "Exit, err = %d, result = %d, %s\n", err, res, result2str(res)); + mlx5_core_info(dev, "%s Device state = %d pci_status: %d. Exit, err = %d, result = %d, %s\n", + __func__, dev->state, dev->pci_status, err, res, result2str(res)); return res; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index 7da012ff0d41..8e2abbab05f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -18,6 +18,10 @@ struct mlx5_sf_dev_table { phys_addr_t base_address; u64 sf_bar_length; struct notifier_block nb; + struct mutex table_lock; /* Serializes sf life cycle and vhca state change handler */ + struct workqueue_struct *active_wq; + struct work_struct work; + u8 stop_active_wq:1; struct mlx5_core_dev *dev; }; @@ -168,6 +172,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ return 0; sf_index = event->function_id - base_id; + mutex_lock(&table->table_lock); sf_dev = xa_load(&table->devices, sf_index); switch (event->new_vhca_state) { case MLX5_VHCA_STATE_INVALID: @@ -191,6 +196,7 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_ default: break; } + mutex_unlock(&table->table_lock); return 0; } @@ -215,6 +221,78 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table) return 0; } +static void mlx5_sf_dev_add_active_work(struct work_struct *work) +{ + struct mlx5_sf_dev_table *table = container_of(work, struct mlx5_sf_dev_table, work); + u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {}; + struct mlx5_core_dev *dev = table->dev; + u16 max_functions; + u16 function_id; + u16 sw_func_id; + int err = 0; + u8 state; + int i; + + max_functions = mlx5_sf_max_functions(dev); + function_id = MLX5_CAP_GEN(dev, sf_base_id); + for (i = 0; i < max_functions; i++, function_id++) { + if (table->stop_active_wq) + return; + err = mlx5_cmd_query_vhca_state(dev, function_id, out, sizeof(out)); + if (err) + /* A failure of specific vhca doesn't mean others will + * fail as well. + */ + continue; + state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); + if (state != MLX5_VHCA_STATE_ACTIVE) + continue; + + sw_func_id = MLX5_GET(query_vhca_state_out, out, vhca_state_context.sw_function_id); + mutex_lock(&table->table_lock); + /* Don't probe device which is already probe */ + if (!xa_load(&table->devices, i)) + mlx5_sf_dev_add(dev, i, function_id, sw_func_id); + /* There is a race where SF got inactive after the query + * above. e.g.: the query returns that the state of the + * SF is active, and after that the eswitch manager set it to + * inactive. + * This case cannot be managed in SW, since the probing of the + * SF is on one system, and the inactivation is on a different + * system. + * If the inactive is done after the SF perform init_hca(), + * the SF will fully probe and then removed. If it was + * done before init_hca(), the SF probe will fail. + */ + mutex_unlock(&table->table_lock); + } +} + +/* In case SFs are generated externally, probe active SFs */ +static int mlx5_sf_dev_queue_active_work(struct mlx5_sf_dev_table *table) +{ + if (MLX5_CAP_GEN(table->dev, eswitch_manager)) + return 0; /* the table is local */ + + /* Use a workqueue to probe active SFs, which are in large + * quantity and may take up to minutes to probe. + */ + table->active_wq = create_singlethread_workqueue("mlx5_active_sf"); + if (!table->active_wq) + return -ENOMEM; + INIT_WORK(&table->work, &mlx5_sf_dev_add_active_work); + queue_work(table->active_wq, &table->work); + return 0; +} + +static void mlx5_sf_dev_destroy_active_work(struct mlx5_sf_dev_table *table) +{ + if (table->active_wq) { + table->stop_active_wq = true; + destroy_workqueue(table->active_wq); + } +} + void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) { struct mlx5_sf_dev_table *table; @@ -240,11 +318,17 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) table->base_address = pci_resource_start(dev->pdev, 2); table->max_sfs = max_sfs; xa_init(&table->devices); + mutex_init(&table->table_lock); dev->priv.sf_dev_table = table; err = mlx5_vhca_event_notifier_register(dev, &table->nb); if (err) goto vhca_err; + + err = mlx5_sf_dev_queue_active_work(table); + if (err) + goto add_active_err; + err = mlx5_sf_dev_vhca_arm_all(table); if (err) goto arm_err; @@ -252,6 +336,8 @@ void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev) return; arm_err: + mlx5_sf_dev_destroy_active_work(table); +add_active_err: mlx5_vhca_event_notifier_unregister(dev, &table->nb); vhca_err: table->max_sfs = 0; @@ -279,7 +365,9 @@ void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev) if (!table) return; + mlx5_sf_dev_destroy_active_work(table); mlx5_vhca_event_notifier_unregister(dev, &table->nb); + mutex_destroy(&table->table_lock); /* Now that event handler is not running, it is safe to destroy * the sf device without race. diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index 19516ccad533..d078156581d5 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -104,7 +104,7 @@ static int sparx5_port_open(struct net_device *ndev) err = phylink_of_phy_connect(port->phylink, port->of_node, 0); if (err) { netdev_err(ndev, "Could not attach to PHY\n"); - return err; + goto err_connect; } phylink_start(port->phylink); @@ -116,10 +116,20 @@ static int sparx5_port_open(struct net_device *ndev) err = sparx5_serdes_set(port->sparx5, port, &port->conf); else err = phy_power_on(port->serdes); - if (err) + if (err) { netdev_err(ndev, "%s failed\n", __func__); + goto out_power; + } } + return 0; + +out_power: + phylink_stop(port->phylink); + phylink_disconnect_phy(port->phylink); +err_connect: + sparx5_port_enable(port, false); + return err; } diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c index 88fa29572e23..ddcc325ed570 100644 --- a/drivers/net/ethernet/sfc/ef100_netdev.c +++ b/drivers/net/ethernet/sfc/ef100_netdev.c @@ -218,6 +218,7 @@ netdev_tx_t __ef100_hard_start_xmit(struct sk_buff *skb, skb->len, skb->data_len, channel->channel); if (!efx->n_channels || !efx->n_tx_channels || !channel) { netif_stop_queue(net_dev); + dev_kfree_skb_any(skb); goto err; } diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 349b7b1dbbf2..d49965907561 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -870,8 +870,10 @@ static int at803x_probe(struct phy_device *phydev) .wolopts = 0, }; - if (ccr < 0) + if (ccr < 0) { + ret = ccr; goto err; + } mode_cfg = ccr & AT803X_MODE_CFG_MASK; switch (mode_cfg) { diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 8d5cbda33f66..0897fdb6254b 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1915,6 +1915,7 @@ static const struct driver_info cdc_ncm_zlp_info = { .status = cdc_ncm_status, .rx_fixup = cdc_ncm_rx_fixup, .tx_fixup = cdc_ncm_tx_fixup, + .set_rx_mode = usbnet_cdc_update_filter, }; /* Same as cdc_ncm_info, but with FLAG_WWAN */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index afd6faa4c2ec..554d4e2a84a4 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1423,6 +1423,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ + {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index d3d34d1c4704..5bf5a93937c9 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -249,7 +249,7 @@ static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev) if (object->integer.value == 3) sleep_state = IPC_PCIE_D3L2; - kfree(object); + ACPI_FREE(object); default_ret: return sleep_state; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index af2ceb4160bc..06cbad166225 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -981,6 +981,7 @@ struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; u16 opcode; /* cmd opcode */ + u16 op_mod; /* cmd op_mod */ void *out; /* pointer to the cmd output buffer */ }; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3af1e927247d..69174093078f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -281,7 +281,8 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in * sk_v6_rcv_saddr (ipv6) changes after it has been binded. The socket's * rcv_saddr field should already have been updated when this is called. */ -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk); +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family); +void inet_bhash2_reset_saddr(struct sock *sk); void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 713b7b8dad7e..b780827f5e0a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -45,11 +45,10 @@ static unsigned int dccp_v4_pernet_id __read_mostly; int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -91,26 +90,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) daddr = fl4->daddr; if (inet->inet_saddr == 0) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = - inet_bhashfn_portaddr(&dccp_hashinfo, sk, - sock_net(sk), - inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } inet->inet_dport = usin->sin_port; @@ -157,6 +143,7 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e57b43006074..602f3432d80b 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -934,26 +934,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (saddr == NULL) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(&dccp_hashinfo, - sk, sock_net(sk), - inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } - saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -985,6 +970,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); + inet_bhash2_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index c548ca3e9b0e..85e35c5e8890 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -279,8 +279,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4728087c42a5..0da679411330 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1230,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { - struct inet_bind_hashbucket *prev_addr_hashbucket; struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; @@ -1260,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; } - prev_addr_hashbucket = - inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk, - sock_net(sk), inet->inet_num); - - inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; - - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { - inet->inet_saddr = old_saddr; - inet->inet_rcv_saddr = old_saddr; ip_rt_put(rt); return err; } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c88bf856c443..74d403dbd2b4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 033bf3c2538f..3cec471a2cd2 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk) +static void inet_update_saddr(struct sock *sk, void *saddr, int family) +{ + if (family == AF_INET) { + inet_sk(sk)->inet_saddr = *(__be32 *)saddr; + sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr); + } +#if IS_ENABLED(CONFIG_IPV6) + else { + sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr; + } +#endif +} + +static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); - struct inet_bind_hashbucket *head2; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); + int bhash; + + if (!inet_csk(sk)->icsk_bind2_hash) { + /* Not bind()ed before. */ + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + return 0; + } /* Allocate a bind2 bucket ahead of time to avoid permanently putting * the bhash2 table in an inconsistent state if a new tb2 bucket * allocation fails. */ new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC); - if (!new_tb2) + if (!new_tb2) { + if (reset) { + /* The (INADDR_ANY, port) bucket might have already + * been freed, then we cannot fixup icsk_bind2_hash, + * so we give up and unlink sk from bhash/bhash2 not + * to leave inconsistency in bhash2. + */ + inet_put_port(sk); + inet_reset_saddr(sk); + } + return -ENOMEM; + } + bhash = inet_bhashfn(net, port, hinfo->bhash_size); + head = &hinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); - if (prev_saddr) { - spin_lock_bh(&prev_saddr->lock); - __sk_del_bind2_node(sk); - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - inet_csk(sk)->icsk_bind2_hash); - spin_unlock_bh(&prev_saddr->lock); - } + /* If we change saddr locklessly, another thread + * iterating over bhash might see corrupted address. + */ + spin_lock_bh(&head->lock); - spin_lock_bh(&head2->lock); + spin_lock(&head2->lock); + __sk_del_bind2_node(sk); + inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); + spin_unlock(&head2->lock); + + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + + head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); + + spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; @@ -893,15 +939,29 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc } sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; - spin_unlock_bh(&head2->lock); + spin_unlock(&head2->lock); + + spin_unlock_bh(&head->lock); if (tb2 != new_tb2) kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2); return 0; } + +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) +{ + return __inet_bhash2_update_saddr(sk, saddr, family, false); +} EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); +void inet_bhash2_reset_saddr(struct sock *sk) +{ + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + __inet_bhash2_update_saddr(sk, NULL, 0, true); +} +EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); + /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 54836a6b81d6..4f2205756cfe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 87d440f47a70..da46357f501b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { @@ -343,6 +331,7 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2a3f9296df1e..f0548dbcabd2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -292,24 +292,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ @@ -359,6 +346,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 754fdda8a5f5..9a1415fe3fa7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1474,11 +1474,12 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, } sk = sock->sk; - write_lock(&sk->sk_callback_lock); - + write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) - goto err_sock; + goto err_inval_sock; + rcu_assign_sk_user_data(sk, tunnel); + write_unlock_bh(&sk->sk_callback_lock); tunnel->l2tp_net = net; pn = l2tp_pernet(net); @@ -1507,8 +1508,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); - } else { - rcu_assign_sk_user_data(sk, tunnel); } tunnel->old_sk_destruct = sk->sk_destruct; @@ -1522,16 +1521,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, if (tunnel->fd >= 0) sockfd_put(sock); - write_unlock(&sk->sk_callback_lock); return 0; err_sock: + write_lock_bh(&sk->sk_callback_lock); + rcu_assign_sk_user_data(sk, NULL); +err_inval_sock: + write_unlock_bh(&sk->sk_callback_lock); + if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); - - write_unlock(&sk->sk_callback_lock); err: return ret; } diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index aa5e712adf07..3d36ea5701f0 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -279,8 +279,10 @@ void nci_rx_data_packet(struct nci_dev *ndev, struct sk_buff *skb) nci_plen(skb->data)); conn_info = nci_get_conn_info_by_conn_id(ndev, nci_conn_id(skb->data)); - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return; + } /* strip the nci data header */ skb_pull(skb, NCI_DATA_HDR_SIZE); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 1e8ab4749c6c..4662a6ce8a7e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -976,7 +976,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" - depends on NET_CLS_ACT && NF_CONNTRACK && NF_NAT && NF_FLOW_TABLE + depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE help Say Y here to allow sending the packets to conntrack module. diff --git a/net/tipc/discover.c b/net/tipc/discover.c index e8630707901e..e8dcdf267c0c 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -211,7 +211,10 @@ void tipc_disc_rcv(struct net *net, struct sk_buff *skb, u32 self; int err; - skb_linearize(skb); + if (skb_linearize(skb)) { + kfree_skb(skb); + return; + } hdr = buf_msg(skb); if (caps & TIPC_NODE_ID128) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d92ec92f0b71..e3b427a70398 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -176,7 +176,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -202,10 +202,12 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + conn_get(con); + spin_unlock_bh(&s->idr_lock); return con; } @@ -467,7 +469,7 @@ static void tipc_topsrv_accept(struct work_struct *work) ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -479,11 +481,11 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ newsk->sk_data_ready(newsk); + conn_put(con); } } @@ -577,17 +579,17 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.filter = filter; *(u64 *)&sub.usr_handle = (u64)port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); - if (rc >= 0) - return true; + if (rc) + conn_put(con); + conn_put(con); - return false; + return !rc; } void tipc_topsrv_kern_unsubscr(struct net *net, int conid) |