diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
37 files changed, 500 insertions, 287 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index b1cef7a0f7ca..e36bebcab3f2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2469,6 +2469,7 @@ err_comm_admin: kfree(priv->mfunc.master.slave_state); err_comm: iounmap(priv->mfunc.comm); + priv->mfunc.comm = NULL; err_vhcr: dma_free_coherent(&dev->persist->pdev->dev, PAGE_SIZE, priv->mfunc.vhcr, @@ -2537,6 +2538,13 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev) int slave; u32 slave_read; + /* If the comm channel has not yet been initialized, + * skip reporting the internal error event to all + * the communication channels. + */ + if (!priv->mfunc.comm) + return; + /* Report an internal error event to all * communication channels. */ @@ -2571,6 +2579,7 @@ void mlx4_multi_func_cleanup(struct mlx4_dev *dev) } iounmap(priv->mfunc.comm); + priv->mfunc.comm = NULL; } void mlx4_cmd_cleanup(struct mlx4_dev *dev, int cleanup_mask) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 08fc5fc56d43..a5fc46bbcbe2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -245,8 +245,11 @@ static u32 freq_to_shift(u16 freq) { u32 freq_khz = freq * 1000; u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC; + u64 tmp_rounded = + roundup_pow_of_two(max_val_cycles) > max_val_cycles ? + roundup_pow_of_two(max_val_cycles) - 1 : UINT_MAX; u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ? - max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1; + max_val_cycles : tmp_rounded; /* calculate max possible multiplier in order to fit in 64bit */ u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 132cea655920..e3be7e44ff51 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -127,7 +127,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, /* For TX we use the same irq per ring we assigned for the RX */ struct mlx4_en_cq *rx_cq; - + int xdp_index; + + /* The xdp tx irq must align with the rx ring that forwards to + * it, so reindex these from 0. This should only happen when + * tx_ring_num is not a multiple of rx_ring_num. + */ + xdp_index = (priv->xdp_ring_num - priv->tx_ring_num) + cq_idx; + if (xdp_index >= 0) + cq_idx = xdp_index; cq_idx = cq_idx % priv->rx_ring_num; rx_cq = priv->rx_cq[cq_idx]; cq->vector = rx_cq->vector; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 7e703bed7b82..fb8bb027b69c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -129,6 +129,9 @@ static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto) } }; +/* Must not acquire state_lock, as its corresponding work_sync + * is done under it. + */ static void mlx4_en_filter_work(struct work_struct *work) { struct mlx4_en_filter *filter = container_of(work, @@ -1733,6 +1736,13 @@ int mlx4_en_start_port(struct net_device *dev) udp_tunnel_get_rx_info(dev); priv->port_up = true; + + /* Process all completions if exist to prevent + * the queues freezing if they are full + */ + for (i = 0; i < priv->rx_ring_num; i++) + napi_schedule(&priv->rx_cq[i]->napi); + netif_tx_start_all_queues(dev); netif_device_attach(dev); @@ -1910,8 +1920,9 @@ static void mlx4_en_clear_stats(struct net_device *dev) struct mlx4_en_dev *mdev = priv->mdev; int i; - if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1)) - en_dbg(HW, priv, "Failed dumping statistics\n"); + if (!mlx4_is_slave(mdev->dev)) + if (mlx4_en_DUMP_ETH_STATS(mdev, priv->port, 1)) + en_dbg(HW, priv, "Failed dumping statistics\n"); memset(&priv->pstats, 0, sizeof(priv->pstats)); memset(&priv->pkstats, 0, sizeof(priv->pkstats)); @@ -2068,13 +2079,6 @@ err: return -ENOMEM; } -static void mlx4_en_shutdown(struct net_device *dev) -{ - rtnl_lock(); - netif_device_detach(dev); - mlx4_en_close(dev); - rtnl_unlock(); -} static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, struct mlx4_en_priv *src, @@ -2151,8 +2155,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - bool shutdown = mdev->dev->persist->interface_state & - MLX4_INTERFACE_STATE_SHUTDOWN; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2160,10 +2162,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) if (priv->registered) { devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, priv->port)); - if (shutdown) - mlx4_en_shutdown(dev); - else - unregister_netdev(dev); + unregister_netdev(dev); } if (priv->allocated) @@ -2181,19 +2180,18 @@ void mlx4_en_destroy_netdev(struct net_device *dev) mutex_lock(&mdev->state_lock); mdev->pndev[priv->port] = NULL; mdev->upper[priv->port] = NULL; - mutex_unlock(&mdev->state_lock); #ifdef CONFIG_RFS_ACCEL mlx4_en_cleanup_filters(priv); #endif mlx4_en_free_resources(priv); + mutex_unlock(&mdev->state_lock); kfree(priv->tx_ring); kfree(priv->tx_cq); - if (!shutdown) - free_netdev(dev); + free_netdev(dev); } static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 5aa8b751f417..59473a0ebcdf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -166,7 +166,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) return PTR_ERR(mailbox); err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0, MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B, - MLX4_CMD_WRAPPED); + MLX4_CMD_NATIVE); if (err) goto out; @@ -322,7 +322,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod | MLX4_DUMP_ETH_STATS_FLOW_CONTROL, 0, MLX4_CMD_DUMP_ETH_STATS, - MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED); + MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE); if (err) goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c index b66e03d9711f..c06346a82496 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c @@ -118,6 +118,29 @@ mlx4_en_test_loopback_exit: return !loopback_ok; } +static int mlx4_en_test_interrupts(struct mlx4_en_priv *priv) +{ + struct mlx4_en_dev *mdev = priv->mdev; + int err = 0; + int i = 0; + + err = mlx4_test_async(mdev->dev); + /* When not in MSI_X or slave, test only async */ + if (!(mdev->dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(mdev->dev)) + return err; + + /* A loop over all completion vectors of current port, + * for each vector check whether it works by mapping command + * completions to that vector and performing a NOP command + */ + for (i = 0; i < priv->rx_ring_num; i++) { + err = mlx4_test_interrupt(mdev->dev, priv->rx_cq[i]->vector); + if (err) + break; + } + + return err; +} static int mlx4_en_test_link(struct mlx4_en_priv *priv) { @@ -151,7 +174,6 @@ static int mlx4_en_test_speed(struct mlx4_en_priv *priv) void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf) { struct mlx4_en_priv *priv = netdev_priv(dev); - struct mlx4_en_dev *mdev = priv->mdev; int i, carrier_ok; memset(buf, 0, sizeof(u64) * MLX4_EN_NUM_SELF_TEST); @@ -177,7 +199,7 @@ void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf) netif_carrier_on(dev); } - buf[0] = mlx4_test_interrupts(mdev->dev); + buf[0] = mlx4_en_test_interrupts(priv); buf[1] = mlx4_en_test_link(priv); buf[2] = mlx4_en_test_speed(priv); diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index cf8f8a72a801..cd3638e6fe25 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -1361,53 +1361,49 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev) kfree(priv->eq_table.uar_map); } -/* A test that verifies that we can accept interrupts on all - * the irq vectors of the device. +/* A test that verifies that we can accept interrupts + * on the vector allocated for asynchronous events + */ +int mlx4_test_async(struct mlx4_dev *dev) +{ + return mlx4_NOP(dev); +} +EXPORT_SYMBOL(mlx4_test_async); + +/* A test that verifies that we can accept interrupts + * on the given irq vector of the tested port. * Interrupts are checked using the NOP command. */ -int mlx4_test_interrupts(struct mlx4_dev *dev) +int mlx4_test_interrupt(struct mlx4_dev *dev, int vector) { struct mlx4_priv *priv = mlx4_priv(dev); - int i; int err; - err = mlx4_NOP(dev); - /* When not in MSI_X, there is only one irq to check */ - if (!(dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(dev)) - return err; - - /* A loop over all completion vectors, for each vector we will check - * whether it works by mapping command completions to that vector - * and performing a NOP command - */ - for(i = 0; !err && (i < dev->caps.num_comp_vectors); ++i) { - /* Make sure request_irq was called */ - if (!priv->eq_table.eq[i].have_irq) - continue; - - /* Temporary use polling for command completions */ - mlx4_cmd_use_polling(dev); - - /* Map the new eq to handle all asynchronous events */ - err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0, - priv->eq_table.eq[i].eqn); - if (err) { - mlx4_warn(dev, "Failed mapping eq for interrupt test\n"); - mlx4_cmd_use_events(dev); - break; - } + /* Temporary use polling for command completions */ + mlx4_cmd_use_polling(dev); - /* Go back to using events */ - mlx4_cmd_use_events(dev); - err = mlx4_NOP(dev); + /* Map the new eq to handle all asynchronous events */ + err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0, + priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn); + if (err) { + mlx4_warn(dev, "Failed mapping eq for interrupt test\n"); + goto out; } + /* Go back to using events */ + mlx4_cmd_use_events(dev); + err = mlx4_NOP(dev); + /* Return to default */ + mlx4_cmd_use_polling(dev); +out: mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0, priv->eq_table.eq[MLX4_EQ_ASYNC].eqn); + mlx4_cmd_use_events(dev); + return err; } -EXPORT_SYMBOL(mlx4_test_interrupts); +EXPORT_SYMBOL(mlx4_test_interrupt); bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector) { diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index c41ab31a39f8..84bab9f0732e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -49,9 +49,9 @@ enum { extern void __buggy_use_of_MLX4_GET(void); extern void __buggy_use_of_MLX4_PUT(void); -static bool enable_qos = true; +static bool enable_qos; module_param(enable_qos, bool, 0444); -MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: on)"); +MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: off)"); #define MLX4_GET(dest, source, offset) \ do { \ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 7183ac4135d2..75d07fa9d0b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1102,6 +1102,14 @@ static int __set_port_type(struct mlx4_port_info *info, int i; int err = 0; + if ((port_type & mdev->caps.supported_type[info->port]) != port_type) { + mlx4_err(mdev, + "Requested port type for port %d is not supported on this HCA\n", + info->port); + err = -EINVAL; + goto err_sup; + } + mlx4_stop_sense(mdev); mutex_lock(&priv->port_mutex); info->tmp_type = port_type; @@ -1147,7 +1155,7 @@ static int __set_port_type(struct mlx4_port_info *info, out: mlx4_start_sense(mdev); mutex_unlock(&priv->port_mutex); - +err_sup: return err; } @@ -4139,11 +4147,8 @@ static void mlx4_shutdown(struct pci_dev *pdev) mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); - if (persist->interface_state & MLX4_INTERFACE_STATE_UP) { - /* Notify mlx4 clients that the kernel is being shut down */ - persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN; + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); - } mutex_unlock(&persist->interface_state_mutex); } diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index 94b891c118c1..1a670b681555 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1457,7 +1457,12 @@ EXPORT_SYMBOL_GPL(mlx4_multicast_detach); int mlx4_flow_steer_promisc_add(struct mlx4_dev *dev, u8 port, u32 qpn, enum mlx4_net_trans_promisc_mode mode) { - struct mlx4_net_trans_rule rule; + struct mlx4_net_trans_rule rule = { + .queue_mode = MLX4_NET_TRANS_Q_FIFO, + .exclusive = 0, + .allow_loopback = 1, + }; + u64 *regid_p; switch (mode) { diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index e4878f31e45d..88ee7d8a5923 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -145,9 +145,10 @@ enum mlx4_resource { RES_MTT, RES_MAC, RES_VLAN, - RES_EQ, + RES_NPORT_ID, RES_COUNTER, RES_FS_RULE, + RES_EQ, MLX4_NUM_OF_RESOURCE_TYPE }; @@ -1329,8 +1330,6 @@ int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_cmd_info *cmd); int mlx4_common_set_vlan_fltr(struct mlx4_dev *dev, int function, int port, void *buf); -int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave, u32 in_mod, - struct mlx4_cmd_mailbox *outbox); int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index c5b2064297a1..b656dd5772e5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -1728,24 +1728,13 @@ int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave, return err; } -int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave, - u32 in_mod, struct mlx4_cmd_mailbox *outbox) -{ - return mlx4_cmd_box(dev, 0, outbox->dma, in_mod, 0, - MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B, - MLX4_CMD_NATIVE); -} - int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, struct mlx4_cmd_mailbox *outbox, struct mlx4_cmd_info *cmd) { - if (slave != dev->caps.function) - return 0; - return mlx4_common_dump_eth_stats(dev, slave, - vhcr->in_modifier, outbox); + return 0; } int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 84d7857ccc27..c548beaaf910 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -1605,13 +1605,14 @@ static int eq_res_start_move_to(struct mlx4_dev *dev, int slave, int index, r->com.from_state = r->com.state; r->com.to_state = state; r->com.state = RES_EQ_BUSY; - if (eq) - *eq = r; } } spin_unlock_irq(mlx4_tlock(dev)); + if (!err && eq) + *eq = r; + return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index aae46884bf93..521cfdb7d11e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -18,8 +18,6 @@ config MLX5_CORE_EN default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. - Ethernet and Infiniband support in ConnectX-4 are currently mutually - exclusive. config MLX5_CORE_EN_DCB bool "Data Center Bridging (DCB) Support" diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 6cb38304669f..2c6e3c7b7417 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -41,6 +41,13 @@ #include "mlx5_core.h" +struct mlx5_db_pgdir { + struct list_head list; + unsigned long *bitmap; + __be32 *db_page; + dma_addr_t db_dma; +}; + /* Handling for queue buffers -- we allocate a bunch of memory and * register it in a memory region at HCA virtual address 0. */ @@ -102,17 +109,28 @@ EXPORT_SYMBOL_GPL(mlx5_buf_free); static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev, int node) { + u32 db_per_page = PAGE_SIZE / cache_line_size(); struct mlx5_db_pgdir *pgdir; pgdir = kzalloc(sizeof(*pgdir), GFP_KERNEL); if (!pgdir) return NULL; - bitmap_fill(pgdir->bitmap, MLX5_DB_PER_PAGE); + pgdir->bitmap = kcalloc(BITS_TO_LONGS(db_per_page), + sizeof(unsigned long), + GFP_KERNEL); + + if (!pgdir->bitmap) { + kfree(pgdir); + return NULL; + } + + bitmap_fill(pgdir->bitmap, db_per_page); pgdir->db_page = mlx5_dma_zalloc_coherent_node(dev, PAGE_SIZE, &pgdir->db_dma, node); if (!pgdir->db_page) { + kfree(pgdir->bitmap); kfree(pgdir); return NULL; } @@ -123,18 +141,19 @@ static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev, static int mlx5_alloc_db_from_pgdir(struct mlx5_db_pgdir *pgdir, struct mlx5_db *db) { + u32 db_per_page = PAGE_SIZE / cache_line_size(); int offset; int i; - i = find_first_bit(pgdir->bitmap, MLX5_DB_PER_PAGE); - if (i >= MLX5_DB_PER_PAGE) + i = find_first_bit(pgdir->bitmap, db_per_page); + if (i >= db_per_page) return -ENOMEM; __clear_bit(i, pgdir->bitmap); db->u.pgdir = pgdir; db->index = i; - offset = db->index * L1_CACHE_BYTES; + offset = db->index * cache_line_size(); db->db = pgdir->db_page + offset / sizeof(*pgdir->db_page); db->dma = pgdir->db_dma + offset; @@ -181,14 +200,16 @@ EXPORT_SYMBOL_GPL(mlx5_db_alloc); void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db) { + u32 db_per_page = PAGE_SIZE / cache_line_size(); mutex_lock(&dev->priv.pgdir_mutex); __set_bit(db->index, db->u.pgdir->bitmap); - if (bitmap_full(db->u.pgdir->bitmap, MLX5_DB_PER_PAGE)) { + if (bitmap_full(db->u.pgdir->bitmap, db_per_page)) { dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE, db->u.pgdir->db_page, db->u.pgdir->db_dma); list_del(&db->u.pgdir->list); + kfree(db->u.pgdir->bitmap); kfree(db->u.pgdir); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1e639f886021..bfe410e8a469 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -268,11 +268,6 @@ static void dump_buf(void *buf, int size, int data_only, int offset) pr_debug("\n"); } -enum { - MLX5_DRIVER_STATUS_ABORTED = 0xfe, - MLX5_DRIVER_SYND = 0xbadd00de, -}; - static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, u32 *synd, u8 *status) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 460363b66cb1..71382df59fc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -85,6 +85,9 @@ #define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128) #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ (64 * 1024) +#define MLX5E_DEFAULT_LRO_TIMEOUT 32 +#define MLX5E_LRO_TIMEOUT_ARR_SIZE 4 + #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC 0x10 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE 0x3 #define MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS 0x20 @@ -221,6 +224,7 @@ struct mlx5e_params { struct ieee_ets ets; #endif bool rx_am_enabled; + u32 lro_timeout; }; struct mlx5e_tstamp { @@ -237,7 +241,7 @@ struct mlx5e_tstamp { }; enum { - MLX5E_RQ_STATE_FLUSH, + MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, MLX5E_RQ_STATE_AM, }; @@ -390,7 +394,7 @@ struct mlx5e_sq_dma { }; enum { - MLX5E_SQ_STATE_FLUSH, + MLX5E_SQ_STATE_ENABLED, MLX5E_SQ_STATE_BF_ENABLE, }; @@ -888,5 +892,6 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev); struct rtnl_link_stats64 * mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout); #endif /* __MLX5_EN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 7eaf38020a8f..246d98ebb588 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -759,6 +759,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (err) goto err_destroy_rq; + set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY); if (err) goto err_disable_rq; @@ -773,6 +774,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, return 0; err_disable_rq: + clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); mlx5e_disable_rq(rq); err_destroy_rq: mlx5e_destroy_rq(rq); @@ -782,7 +784,7 @@ err_destroy_rq: static void mlx5e_close_rq(struct mlx5e_rq *rq) { - set_bit(MLX5E_RQ_STATE_FLUSH, &rq->state); + clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ cancel_work_sync(&rq->am.work); @@ -1006,7 +1008,6 @@ static int mlx5e_enable_sq(struct mlx5e_sq *sq, struct mlx5e_sq_param *param) MLX5_SET(sqc, sqc, min_wqe_inline_mode, sq->min_inline_mode); MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST); MLX5_SET(sqc, sqc, tis_lst_sz, param->type == MLX5E_SQ_ICO ? 0 : 1); - MLX5_SET(sqc, sqc, flush_in_error_en, 1); MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC); MLX5_SET(wq, wq, uar_page, sq->uar.index); @@ -1083,6 +1084,7 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, if (err) goto err_destroy_sq; + set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RST, MLX5_SQC_STATE_RDY, false, 0); if (err) @@ -1096,6 +1098,7 @@ static int mlx5e_open_sq(struct mlx5e_channel *c, return 0; err_disable_sq: + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); mlx5e_disable_sq(sq); err_destroy_sq: mlx5e_destroy_sq(sq); @@ -1112,7 +1115,7 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_close_sq(struct mlx5e_sq *sq) { - set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); /* prevent netif_tx_wake_queue */ napi_synchronize(&sq->channel->napi); @@ -1445,6 +1448,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); c->num_tc = priv->params.num_tc; + c->xdp = !!priv->xdp_prog; if (priv->params.rx_am_enabled) rx_cq_profile = mlx5e_am_get_def_profile(priv->params.rx_cq_period_mode); @@ -1468,6 +1472,12 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (err) goto err_close_tx_cqs; + /* XDP SQ CQ params are same as normal TXQ sq CQ params */ + err = c->xdp ? mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq, + priv->params.tx_cq_moderation) : 0; + if (err) + goto err_close_rx_cq; + napi_enable(&c->napi); err = mlx5e_open_sq(c, 0, &cparam->icosq, &c->icosq); @@ -1488,21 +1498,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, } } - if (priv->xdp_prog) { - /* XDP SQ CQ params are same as normal TXQ sq CQ params */ - err = mlx5e_open_cq(c, &cparam->tx_cq, &c->xdp_sq.cq, - priv->params.tx_cq_moderation); - if (err) - goto err_close_sqs; - - err = mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq); - if (err) { - mlx5e_close_cq(&c->xdp_sq.cq); - goto err_close_sqs; - } - } + err = c->xdp ? mlx5e_open_sq(c, 0, &cparam->xdp_sq, &c->xdp_sq) : 0; + if (err) + goto err_close_sqs; - c->xdp = !!priv->xdp_prog; err = mlx5e_open_rq(c, &cparam->rq, &c->rq); if (err) goto err_close_xdp_sq; @@ -1512,7 +1511,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, return 0; err_close_xdp_sq: - mlx5e_close_sq(&c->xdp_sq); + if (c->xdp) + mlx5e_close_sq(&c->xdp_sq); err_close_sqs: mlx5e_close_sqs(c); @@ -1522,6 +1522,10 @@ err_close_icosq: err_disable_napi: napi_disable(&c->napi); + if (c->xdp) + mlx5e_close_cq(&c->xdp_sq.cq); + +err_close_rx_cq: mlx5e_close_cq(&c->rq.cq); err_close_tx_cqs: @@ -1971,9 +1975,7 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv) MLX5_SET(tirc, tirc, lro_max_ip_payload_size, (priv->params.lro_wqe_sz - ROUGH_MAX_L2_L3_HDR_SZ) >> 8); - MLX5_SET(tirc, tirc, lro_timeout_period_usecs, - MLX5_CAP_ETH(priv->mdev, - lro_timer_supported_periods[2])); + MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout); } void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv) @@ -3093,7 +3095,7 @@ static void mlx5e_tx_timeout(struct net_device *dev) if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i))) continue; sched_work = true; - set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state); + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n", i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc); } @@ -3148,13 +3150,13 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) for (i = 0; i < priv->params.num_channels; i++) { struct mlx5e_channel *c = priv->channel[i]; - set_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state); + clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); napi_synchronize(&c->napi); /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */ old_prog = xchg(&c->rq.xdp_prog, prog); - clear_bit(MLX5E_RQ_STATE_FLUSH, &c->rq.state); + set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); /* napi_schedule in case we have missed anything */ set_bit(MLX5E_CHANNEL_NAPI_SCHED, &c->flags); napi_schedule(&c->napi); @@ -3401,6 +3403,18 @@ static void mlx5e_query_min_inline(struct mlx5_core_dev *mdev, } } +u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) +{ + int i; + + /* The supported periods are organized in ascending order */ + for (i = 0; i < MLX5E_LRO_TIMEOUT_ARR_SIZE - 1; i++) + if (MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]) >= wanted_timeout) + break; + + return MLX5_CAP_ETH(mdev, lro_timer_supported_periods[i]); +} + static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, struct net_device *netdev, const struct mlx5e_profile *profile, @@ -3419,6 +3433,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, priv->profile = profile; priv->ppriv = ppriv; + priv->params.lro_timeout = + mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); + priv->params.log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; /* set CQE compression */ @@ -4035,7 +4052,6 @@ void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv) const struct mlx5e_profile *profile = priv->profile; struct net_device *netdev = priv->netdev; - unregister_netdev(netdev); destroy_workqueue(priv->wq); if (profile->cleanup) profile->cleanup(priv); @@ -4052,6 +4068,7 @@ static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv) for (vport = 1; vport < total_vfs; vport++) mlx5_eswitch_unregister_vport_rep(esw, vport); + unregister_netdev(priv->netdev); mlx5e_detach(mdev, vpriv); mlx5e_destroy_netdev(mdev, priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 3c97da103d30..bf1c09ca73c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -308,7 +308,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->switchdev_ops = &mlx5e_rep_switchdev_ops; #endif - netdev->features |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC; + netdev->features |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL; netdev->hw_features |= NETIF_F_HW_TC; eth_hw_addr_random(netdev); @@ -457,6 +457,7 @@ void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5e_priv *priv = rep->priv_data; struct net_device *netdev = priv->netdev; + unregister_netdev(netdev); mlx5e_detach_netdev(esw->dev, netdev); mlx5e_destroy_netdev(esw->dev, priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index c6de6fba5843..33495d88aeb2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -340,7 +340,7 @@ static inline void mlx5e_post_umr_wqe(struct mlx5e_rq *rq, u16 ix) while ((pi = (sq->pc & wq->sz_m1)) > sq->edge) { sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_NOP; sq->db.ico_wqe[pi].num_wqebbs = 1; - mlx5e_send_nop(sq, true); + mlx5e_send_nop(sq, false); } wqe = mlx5_wq_cyc_get_wqe(wq, pi); @@ -412,7 +412,7 @@ void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq) clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state); - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) { + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) { mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]); return; } @@ -445,7 +445,7 @@ void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) } #define RQ_CANNOT_POST(rq) \ - (test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state) || \ + (!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state) || \ test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state)) bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) @@ -924,7 +924,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) struct mlx5e_sq *xdp_sq = &rq->channel->xdp_sq; int work_done = 0; - if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) + if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return 0; if (cq->decmprs_left) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ce8c54d18906..6bb21b31cfeb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -237,12 +237,15 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_VLAN, f->mask); - if (mask->vlan_id) { + if (mask->vlan_id || mask->vlan_priority) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, vlan_tag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, vlan_tag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id); MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 70a717382357..cfb68371c397 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -409,7 +409,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; npkts = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 5703f19a6a24..e5c12a732aa1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -56,7 +56,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) struct mlx5_cqe64 *cqe; u16 sqcc; - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return; cqe = mlx5e_get_cqe(cq); @@ -113,7 +113,7 @@ static inline bool mlx5e_poll_xdp_tx_cq(struct mlx5e_cq *cq) sq = container_of(cq, struct mlx5e_sq, cq); - if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state))) + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) return false; /* sq->cc must be updated only after mlx5_cqwq_update_db_record(), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index abbf2c369923..be1f7333ab7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -931,8 +931,8 @@ static void esw_vport_change_handler(struct work_struct *work) mutex_unlock(&esw->state_lock); } -static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_group *vlan_grp = NULL; @@ -949,9 +949,11 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, int table_size = 2; int err = 0; - if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support) || - !IS_ERR_OR_NULL(vport->egress.acl)) - return; + if (!MLX5_CAP_ESW_EGRESS_ACL(dev, ft_support)) + return -EOPNOTSUPP; + + if (!IS_ERR_OR_NULL(vport->egress.acl)) + return 0; esw_debug(dev, "Create vport[%d] egress ACL log_max_size(%d)\n", vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size)); @@ -959,12 +961,12 @@ static void esw_vport_enable_egress_acl(struct mlx5_eswitch *esw, root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS); if (!root_ns) { esw_warn(dev, "Failed to get E-Switch egress flow namespace\n"); - return; + return -EIO; } flow_group_in = mlx5_vzalloc(inlen); if (!flow_group_in) - return; + return -ENOMEM; acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport); if (IS_ERR(acl)) { @@ -1009,6 +1011,7 @@ out: mlx5_destroy_flow_group(vlan_grp); if (err && !IS_ERR_OR_NULL(acl)) mlx5_destroy_flow_table(acl); + return err; } static void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw, @@ -1041,8 +1044,8 @@ static void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw, vport->egress.acl = NULL; } -static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, - struct mlx5_vport *vport) +static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_core_dev *dev = esw->dev; @@ -1063,9 +1066,11 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, int table_size = 4; int err = 0; - if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support) || - !IS_ERR_OR_NULL(vport->ingress.acl)) - return; + if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support)) + return -EOPNOTSUPP; + + if (!IS_ERR_OR_NULL(vport->ingress.acl)) + return 0; esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n", vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size)); @@ -1073,12 +1078,12 @@ static void esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw, root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS); if (!root_ns) { esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n"); - return; + return -EIO; } flow_group_in = mlx5_vzalloc(inlen); if (!flow_group_in) - return; + return -ENOMEM; acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport); if (IS_ERR(acl)) { @@ -1167,6 +1172,7 @@ out: } kvfree(flow_group_in); + return err; } static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, @@ -1225,7 +1231,13 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, return 0; } - esw_vport_enable_ingress_acl(esw, vport); + err = esw_vport_enable_ingress_acl(esw, vport); + if (err) { + mlx5_core_warn(esw->dev, + "failed to enable ingress acl (%d) on vport[%d]\n", + err, vport->vport); + return err; + } esw_debug(esw->dev, "vport[%d] configure ingress rules, vlan(%d) qos(%d)\n", @@ -1299,7 +1311,13 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw, return 0; } - esw_vport_enable_egress_acl(esw, vport); + err = esw_vport_enable_egress_acl(esw, vport); + if (err) { + mlx5_core_warn(esw->dev, + "failed to enable egress acl (%d) on vport[%d]\n", + err, vport->vport); + return err; + } esw_debug(esw->dev, "vport[%d] configure egress rules, vlan(%d) qos(%d)\n", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index c55ad8d00c05..d239f5d0ea36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -57,7 +57,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (esw->mode != SRIOV_OFFLOADS) return ERR_PTR(-EOPNOTSUPP); - action = attr->action; + /* per flow vlan pop/push is emulated, don't set that into the firmware */ + action = attr->action & ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH | MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5da2cc878582..914e5466f729 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -436,6 +436,9 @@ static void del_flow_group(struct fs_node *node) fs_get_obj(ft, fg->node.parent); dev = get_dev(&ft->node); + if (ft->autogroup.active) + ft->autogroup.num_groups--; + if (mlx5_cmd_destroy_flow_group(dev, ft, fg->id)) mlx5_core_warn(dev, "flow steering can't destroy fg %d of ft %d\n", fg->id, ft->id); @@ -879,7 +882,7 @@ static struct mlx5_flow_group *create_flow_group_common(struct mlx5_flow_table * tree_init_node(&fg->node, !is_auto_fg, del_flow_group); tree_add_node(&fg->node, &ft->node); /* Add node to group list */ - list_add(&fg->node.list, ft->node.children.prev); + list_add(&fg->node.list, prev_fg); return fg; } @@ -893,7 +896,7 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft, return ERR_PTR(-EPERM); lock_ref_node(&ft->node); - fg = create_flow_group_common(ft, fg_in, &ft->node.children, false); + fg = create_flow_group_common(ft, fg_in, ft->node.children.prev, false); unlock_ref_node(&ft->node); return fg; @@ -1012,7 +1015,7 @@ static struct mlx5_flow_group *create_autogroup(struct mlx5_flow_table *ft, u32 *match_criteria) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct list_head *prev = &ft->node.children; + struct list_head *prev = ft->node.children.prev; unsigned int candidate_index = 0; struct mlx5_flow_group *fg; void *match_criteria_addr; @@ -1687,7 +1690,7 @@ static int init_root_ns(struct mlx5_flow_steering *steering) { steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX); - if (IS_ERR_OR_NULL(steering->root_ns)) + if (!steering->root_ns) goto cleanup; if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 3a9195b4169d..3b026c151cf2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -218,6 +218,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) goto err_out; if (aging) { + counter->cache.lastuse = jiffies; counter->aging = true; spin_lock(&fc_stats->addlist_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 1a05fb965c8d..5bcf93422ee0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -61,10 +61,15 @@ enum { enum { MLX5_NIC_IFC_FULL = 0, MLX5_NIC_IFC_DISABLED = 1, - MLX5_NIC_IFC_NO_DRAM_NIC = 2 + MLX5_NIC_IFC_NO_DRAM_NIC = 2, + MLX5_NIC_IFC_INVALID = 3 }; -static u8 get_nic_interface(struct mlx5_core_dev *dev) +enum { + MLX5_DROP_NEW_HEALTH_WORK, +}; + +static u8 get_nic_state(struct mlx5_core_dev *dev) { return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 3; } @@ -97,7 +102,7 @@ static int in_fatal(struct mlx5_core_dev *dev) struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - if (get_nic_interface(dev) == MLX5_NIC_IFC_DISABLED) + if (get_nic_state(dev) == MLX5_NIC_IFC_DISABLED) return 1; if (ioread32be(&h->fw_ver) == 0xffffffff) @@ -127,7 +132,7 @@ unlock: static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) { - u8 nic_interface = get_nic_interface(dev); + u8 nic_interface = get_nic_state(dev); switch (nic_interface) { case MLX5_NIC_IFC_FULL: @@ -149,8 +154,34 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev) mlx5_disable_device(dev); } +static void health_recover(struct work_struct *work) +{ + struct mlx5_core_health *health; + struct delayed_work *dwork; + struct mlx5_core_dev *dev; + struct mlx5_priv *priv; + u8 nic_state; + + dwork = container_of(work, struct delayed_work, work); + health = container_of(dwork, struct mlx5_core_health, recover_work); + priv = container_of(health, struct mlx5_priv, health); + dev = container_of(priv, struct mlx5_core_dev, priv); + + nic_state = get_nic_state(dev); + if (nic_state == MLX5_NIC_IFC_INVALID) { + dev_err(&dev->pdev->dev, "health recovery flow aborted since the nic state is invalid\n"); + return; + } + + dev_err(&dev->pdev->dev, "starting health recovery flow\n"); + mlx5_recover_device(dev); +} + +/* How much time to wait until health resetting the driver (in msecs) */ +#define MLX5_RECOVERY_DELAY_MSECS 60000 static void health_care(struct work_struct *work) { + unsigned long recover_delay = msecs_to_jiffies(MLX5_RECOVERY_DELAY_MSECS); struct mlx5_core_health *health; struct mlx5_core_dev *dev; struct mlx5_priv *priv; @@ -160,6 +191,14 @@ static void health_care(struct work_struct *work) dev = container_of(priv, struct mlx5_core_dev, priv); mlx5_core_warn(dev, "handling bad device here\n"); mlx5_handle_bad_state(dev); + + spin_lock(&health->wq_lock); + if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) + schedule_delayed_work(&health->recover_work, recover_delay); + else + dev_err(&dev->pdev->dev, + "new health works are not permitted at this stage\n"); + spin_unlock(&health->wq_lock); } static const char *hsynd_str(u8 synd) @@ -272,7 +311,13 @@ static void poll_health(unsigned long data) if (in_fatal(dev) && !health->sick) { health->sick = true; print_health_info(dev); - schedule_work(&health->work); + spin_lock(&health->wq_lock); + if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) + queue_work(health->wq, &health->work); + else + dev_err(&dev->pdev->dev, + "new health works are not permitted at this stage\n"); + spin_unlock(&health->wq_lock); } } @@ -281,6 +326,8 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) struct mlx5_core_health *health = &dev->priv.health; init_timer(&health->timer); + health->sick = 0; + clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -297,11 +344,22 @@ void mlx5_stop_health_poll(struct mlx5_core_dev *dev) del_timer_sync(&health->timer); } +void mlx5_drain_health_wq(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + + spin_lock(&health->wq_lock); + set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + spin_unlock(&health->wq_lock); + cancel_delayed_work_sync(&health->recover_work); + cancel_work_sync(&health->work); +} + void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; - flush_work(&health->work); + destroy_workqueue(health->wq); } int mlx5_health_init(struct mlx5_core_dev *dev) @@ -316,9 +374,13 @@ int mlx5_health_init(struct mlx5_core_dev *dev) strcpy(name, "mlx5_health"); strcat(name, dev_name(&dev->pdev->dev)); + health->wq = create_singlethread_workqueue(name); kfree(name); - + if (!health->wq) + return -ENOMEM; + spin_lock_init(&health->wq_lock); INIT_WORK(&health->work, health_care); + INIT_DELAYED_WORK(&health->recover_work, health_recover); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index d9c3c70b29e4..ada24e103b02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -46,7 +46,6 @@ #include <linux/mlx5/srq.h> #include <linux/debugfs.h> #include <linux/kmod.h> -#include <linux/delay.h> #include <linux/mlx5/mlx5_ifc.h> #ifdef CONFIG_RFS_ACCEL #include <linux/cpu_rmap.h> @@ -63,13 +62,13 @@ MODULE_DESCRIPTION("Mellanox Connect-IB, ConnectX-4 core driver"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_VERSION(DRIVER_VERSION); -int mlx5_core_debug_mask; -module_param_named(debug_mask, mlx5_core_debug_mask, int, 0644); +unsigned int mlx5_core_debug_mask; +module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644); MODULE_PARM_DESC(debug_mask, "debug mask: 1 = dump cmd data, 2 = dump cmd exec time, 3 = both. Default=0"); #define MLX5_DEFAULT_PROF 2 -static int prof_sel = MLX5_DEFAULT_PROF; -module_param_named(prof_sel, prof_sel, int, 0444); +static unsigned int prof_sel = MLX5_DEFAULT_PROF; +module_param_named(prof_sel, prof_sel, uint, 0444); MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2"); enum { @@ -733,13 +732,15 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) u8 status; mlx5_cmd_mbox_status(query_out, &status, &syndrome); - if (status == MLX5_CMD_STAT_BAD_OP_ERR) { - pr_debug("Only ISSI 0 is supported\n"); - return 0; + if (!status || syndrome == MLX5_DRIVER_SYND) { + mlx5_core_err(dev, "Failed to query ISSI err(%d) status(%d) synd(%d)\n", + err, status, syndrome); + return err; } - pr_err("failed to query ISSI err(%d)\n", err); - return err; + mlx5_core_warn(dev, "Query ISSI is not supported by FW, ISSI is 0\n"); + dev->issi = 0; + return 0; } sup_issi = MLX5_GET(query_issi_out, query_out, supported_issi_dw0); @@ -753,7 +754,8 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev) err = mlx5_cmd_exec(dev, set_in, sizeof(set_in), set_out, sizeof(set_out)); if (err) { - pr_err("failed to set ISSI=1 err(%d)\n", err); + mlx5_core_err(dev, "Failed to set ISSI to 1 err(%d)\n", + err); return err; } @@ -844,12 +846,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) struct pci_dev *pdev = dev->pdev; int err; - err = mlx5_query_hca_caps(dev); - if (err) { - dev_err(&pdev->dev, "query hca failed\n"); - goto out; - } - err = mlx5_query_board_id(dev); if (err) { dev_err(&pdev->dev, "query board id failed\n"); @@ -1023,6 +1019,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_start_health_poll(dev); + err = mlx5_query_hca_caps(dev); + if (err) { + dev_err(&pdev->dev, "query hca failed\n"); + goto err_stop_poll; + } + if (boot && mlx5_init_once(dev, priv)) { dev_err(&pdev->dev, "sw objs init failed\n"); goto err_stop_poll; @@ -1226,15 +1228,9 @@ static int init_one(struct pci_dev *pdev, pci_set_drvdata(pdev, dev); - if (prof_sel < 0 || prof_sel >= ARRAY_SIZE(profile)) { - mlx5_core_warn(dev, - "selected profile out of range, selecting default (%d)\n", - MLX5_DEFAULT_PROF); - prof_sel = MLX5_DEFAULT_PROF; - } - dev->profile = &profile[prof_sel]; dev->pdev = pdev; dev->event = mlx5_core_event; + dev->profile = &profile[prof_sel]; INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); @@ -1313,10 +1309,16 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, struct mlx5_priv *priv = &dev->priv; dev_info(&pdev->dev, "%s was called\n", __func__); + mlx5_enter_error_state(dev); mlx5_unload_one(dev, priv, false); - pci_save_state(pdev); - mlx5_pci_disable_device(dev); + /* In case of kernel call save the pci state and drain health wq */ + if (state) { + pci_save_state(pdev); + mlx5_drain_health_wq(dev); + mlx5_pci_disable_device(dev); + } + return state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; } @@ -1373,11 +1375,6 @@ static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) return PCI_ERS_RESULT_RECOVERED; } -void mlx5_disable_device(struct mlx5_core_dev *dev) -{ - mlx5_pci_err_detected(dev->pdev, 0); -} - static void mlx5_pci_resume(struct pci_dev *pdev) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); @@ -1427,6 +1424,18 @@ static const struct pci_device_id mlx5_core_pci_table[] = { MODULE_DEVICE_TABLE(pci, mlx5_core_pci_table); +void mlx5_disable_device(struct mlx5_core_dev *dev) +{ + mlx5_pci_err_detected(dev->pdev, 0); +} + +void mlx5_recover_device(struct mlx5_core_dev *dev) +{ + mlx5_pci_disable_device(dev); + if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED) + mlx5_pci_resume(dev->pdev); +} + static struct pci_driver mlx5_core_driver = { .name = DRIVER_NAME, .id_table = mlx5_core_pci_table, @@ -1437,10 +1446,22 @@ static struct pci_driver mlx5_core_driver = { .sriov_configure = mlx5_core_sriov_configure, }; +static void mlx5_core_verify_params(void) +{ + if (prof_sel >= ARRAY_SIZE(profile)) { + pr_warn("mlx5_core: WARNING: Invalid module parameter prof_sel %d, valid range 0-%zu, changing back to default(%d)\n", + prof_sel, + ARRAY_SIZE(profile) - 1, + MLX5_DEFAULT_PROF); + prof_sel = MLX5_DEFAULT_PROF; + } +} + static int __init init(void) { int err; + mlx5_core_verify_params(); mlx5_register_debugfs(); err = pci_register_driver(&mlx5_core_driver); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 3d0cfb9f18f9..63b9a0dba885 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -44,11 +44,11 @@ #define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs(mdev->pdev)) -extern int mlx5_core_debug_mask; +extern uint mlx5_core_debug_mask; #define mlx5_core_dbg(__dev, format, ...) \ - dev_dbg(&(__dev)->pdev->dev, "%s:%s:%d:(pid %d): " format, \ - (__dev)->priv.name, __func__, __LINE__, current->pid, \ + dev_dbg(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) #define mlx5_core_dbg_mask(__dev, mask, format, ...) \ @@ -63,8 +63,8 @@ do { \ ##__VA_ARGS__) #define mlx5_core_warn(__dev, format, ...) \ - dev_warn(&(__dev)->pdev->dev, "%s:%s:%d:(pid %d): " format, \ - (__dev)->priv.name, __func__, __LINE__, current->pid, \ + dev_warn(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format, \ + __func__, __LINE__, current->pid, \ ##__VA_ARGS__) #define mlx5_core_info(__dev, format, ...) \ @@ -75,6 +75,11 @@ enum { MLX5_CMD_TIME, /* print command execution time */ }; +enum { + MLX5_DRIVER_STATUS_ABORTED = 0xfe, + MLX5_DRIVER_SYND = 0xbadd00de, +}; + int mlx5_query_hca_caps(struct mlx5_core_dev *dev); int mlx5_query_board_id(struct mlx5_core_dev *dev); int mlx5_cmd_init_hca(struct mlx5_core_dev *dev); @@ -83,6 +88,7 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); void mlx5_enter_error_state(struct mlx5_core_dev *dev); void mlx5_disable_device(struct mlx5_core_dev *dev); +void mlx5_recover_device(struct mlx5_core_dev *dev); int mlx5_sriov_init(struct mlx5_core_dev *dev); void mlx5_sriov_cleanup(struct mlx5_core_dev *dev); int mlx5_sriov_attach(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index cc4fd61914d3..a57d5a81eb05 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -209,6 +209,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr) static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id) { struct page *page; + u64 zero_addr = 1; u64 addr; int err; int nid = dev_to_node(&dev->pdev->dev); @@ -218,26 +219,35 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u16 func_id) mlx5_core_warn(dev, "failed to allocate page\n"); return -ENOMEM; } +map: addr = dma_map_page(&dev->pdev->dev, page, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); if (dma_mapping_error(&dev->pdev->dev, addr)) { mlx5_core_warn(dev, "failed dma mapping page\n"); err = -ENOMEM; - goto out_alloc; + goto err_mapping; } + + /* Firmware doesn't support page with physical address 0 */ + if (addr == 0) { + zero_addr = addr; + goto map; + } + err = insert_page(dev, addr, page, func_id); if (err) { mlx5_core_err(dev, "failed to track allocated page\n"); - goto out_mapping; + dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, + DMA_BIDIRECTIONAL); } - return 0; - -out_mapping: - dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL); +err_mapping: + if (err) + __free_page(page); -out_alloc: - __free_page(page); + if (zero_addr == 0) + dma_unmap_page(&dev->pdev->dev, zero_addr, PAGE_SIZE, + DMA_BIDIRECTIONAL); return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index e742bd4e8894..912f71f84209 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1838,11 +1838,17 @@ static const struct mlxsw_bus mlxsw_pci_bus = { .cmd_exec = mlxsw_pci_cmd_exec, }; -static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci) +static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci, + const struct pci_device_id *id) { unsigned long end; mlxsw_pci_write32(mlxsw_pci, SW_RESET, MLXSW_PCI_SW_RESET_RST_BIT); + if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) { + msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); + return 0; + } + wmb(); /* reset needs to be written before we read control register */ end = jiffies + msecs_to_jiffies(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); do { @@ -1909,7 +1915,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) mlxsw_pci->pdev = pdev; pci_set_drvdata(pdev, mlxsw_pci); - err = mlxsw_pci_sw_reset(mlxsw_pci); + err = mlxsw_pci_sw_reset(mlxsw_pci, id); if (err) { dev_err(&pdev->dev, "Software reset failed\n"); goto err_sw_reset; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 1ec0a4ce3c46..dda5761e91bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -231,7 +231,7 @@ mlxsw_sp_span_entry_create(struct mlxsw_sp_port *port) span_entry->used = true; span_entry->id = index; - span_entry->ref_count = 0; + span_entry->ref_count = 1; span_entry->local_port = local_port; return span_entry; } @@ -270,6 +270,7 @@ static struct mlxsw_sp_span_entry span_entry = mlxsw_sp_span_entry_find(port); if (span_entry) { + /* Already exists, just take a reference */ span_entry->ref_count++; return span_entry; } @@ -280,6 +281,7 @@ static struct mlxsw_sp_span_entry static int mlxsw_sp_span_entry_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_span_entry *span_entry) { + WARN_ON(!span_entry->ref_count); if (--span_entry->ref_count == 0) mlxsw_sp_span_entry_destroy(mlxsw_sp, span_entry); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 9b22863a924b..97bbc1d21df8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -115,7 +115,7 @@ struct mlxsw_sp_rif { struct mlxsw_sp_mid { struct list_head list; unsigned char addr[ETH_ALEN]; - u16 vid; + u16 fid; u16 mid; unsigned int ref_count; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 78fc557d6dd7..e83072da6272 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -320,6 +320,8 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, lpm_tree); if (err) goto err_left_struct_set; + memcpy(&lpm_tree->prefix_usage, prefix_usage, + sizeof(lpm_tree->prefix_usage)); return lpm_tree; err_left_struct_set: @@ -343,7 +345,8 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, for (i = 0; i < MLXSW_SP_LPM_TREE_COUNT; i++) { lpm_tree = &mlxsw_sp->router.lpm_trees[i]; - if (lpm_tree->proto == proto && + if (lpm_tree->ref_count != 0 && + lpm_tree->proto == proto && mlxsw_sp_prefix_usage_eq(&lpm_tree->prefix_usage, prefix_usage)) goto inc_ref_count; @@ -591,21 +594,22 @@ static int mlxsw_sp_vrs_init(struct mlxsw_sp *mlxsw_sp) return 0; } +static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp); + static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp) { + mlxsw_sp_router_fib_flush(mlxsw_sp); kfree(mlxsw_sp->router.vrs); } struct mlxsw_sp_neigh_key { - unsigned char addr[sizeof(struct in6_addr)]; - struct net_device *dev; + struct neighbour *n; }; struct mlxsw_sp_neigh_entry { struct rhash_head ht_node; struct mlxsw_sp_neigh_key key; u16 rif; - struct neighbour *n; bool offloaded; struct delayed_work dw; struct mlxsw_sp_port *mlxsw_sp_port; @@ -643,19 +647,15 @@ mlxsw_sp_neigh_entry_remove(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work); static struct mlxsw_sp_neigh_entry * -mlxsw_sp_neigh_entry_create(const void *addr, size_t addr_len, - struct net_device *dev, u16 rif, - struct neighbour *n) +mlxsw_sp_neigh_entry_create(struct neighbour *n, u16 rif) { struct mlxsw_sp_neigh_entry *neigh_entry; neigh_entry = kzalloc(sizeof(*neigh_entry), GFP_ATOMIC); if (!neigh_entry) return NULL; - memcpy(neigh_entry->key.addr, addr, addr_len); - neigh_entry->key.dev = dev; + neigh_entry->key.n = n; neigh_entry->rif = rif; - neigh_entry->n = n; INIT_DELAYED_WORK(&neigh_entry->dw, mlxsw_sp_router_neigh_update_hw); INIT_LIST_HEAD(&neigh_entry->nexthop_list); return neigh_entry; @@ -668,13 +668,11 @@ mlxsw_sp_neigh_entry_destroy(struct mlxsw_sp_neigh_entry *neigh_entry) } static struct mlxsw_sp_neigh_entry * -mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, const void *addr, - size_t addr_len, struct net_device *dev) +mlxsw_sp_neigh_entry_lookup(struct mlxsw_sp *mlxsw_sp, struct neighbour *n) { - struct mlxsw_sp_neigh_key key = {{ 0 } }; + struct mlxsw_sp_neigh_key key; - memcpy(key.addr, addr, addr_len); - key.dev = dev; + key.n = n; return rhashtable_lookup_fast(&mlxsw_sp->router.neigh_ht, &key, mlxsw_sp_neigh_ht_params); } @@ -686,26 +684,20 @@ int mlxsw_sp_router_neigh_construct(struct net_device *dev, struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_neigh_entry *neigh_entry; struct mlxsw_sp_rif *r; - u32 dip; int err; if (n->tbl != &arp_tbl) return 0; - dip = ntohl(*((__be32 *) n->primary_key)); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip), - n->dev); - if (neigh_entry) { - WARN_ON(neigh_entry->n != n); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); + if (neigh_entry) return 0; - } r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev); if (WARN_ON(!r)) return -EINVAL; - neigh_entry = mlxsw_sp_neigh_entry_create(&dip, sizeof(dip), n->dev, - r->rif, n); + neigh_entry = mlxsw_sp_neigh_entry_create(n, r->rif); if (!neigh_entry) return -ENOMEM; err = mlxsw_sp_neigh_entry_insert(mlxsw_sp, neigh_entry); @@ -724,14 +716,11 @@ void mlxsw_sp_router_neigh_destroy(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_neigh_entry *neigh_entry; - u32 dip; if (n->tbl != &arp_tbl) return; - dip = ntohl(*((__be32 *) n->primary_key)); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &dip, sizeof(dip), - n->dev); + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); if (!neigh_entry) return; mlxsw_sp_neigh_entry_remove(mlxsw_sp, neigh_entry); @@ -814,6 +803,26 @@ static void mlxsw_sp_router_neigh_rec_process(struct mlxsw_sp *mlxsw_sp, } } +static bool mlxsw_sp_router_rauhtd_is_full(char *rauhtd_pl) +{ + u8 num_rec, last_rec_index, num_entries; + + num_rec = mlxsw_reg_rauhtd_num_rec_get(rauhtd_pl); + last_rec_index = num_rec - 1; + + if (num_rec < MLXSW_REG_RAUHTD_REC_MAX_NUM) + return false; + if (mlxsw_reg_rauhtd_rec_type_get(rauhtd_pl, last_rec_index) == + MLXSW_REG_RAUHTD_TYPE_IPV6) + return true; + + num_entries = mlxsw_reg_rauhtd_ipv4_rec_num_entries_get(rauhtd_pl, + last_rec_index); + if (++num_entries == MLXSW_REG_RAUHTD_IPV4_ENT_PER_REC) + return true; + return false; +} + static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) { char *rauhtd_pl; @@ -840,7 +849,7 @@ static int mlxsw_sp_router_neighs_update_rauhtd(struct mlxsw_sp *mlxsw_sp) for (i = 0; i < num_rec; i++) mlxsw_sp_router_neigh_rec_process(mlxsw_sp, rauhtd_pl, i); - } while (num_rec); + } while (mlxsw_sp_router_rauhtd_is_full(rauhtd_pl)); rtnl_unlock(); kfree(rauhtd_pl); @@ -859,7 +868,7 @@ static void mlxsw_sp_router_neighs_update_nh(struct mlxsw_sp *mlxsw_sp) * is active regardless of the traffic. */ if (!list_empty(&neigh_entry->nexthop_list)) - neigh_event_send(neigh_entry->n, NULL); + neigh_event_send(neigh_entry->key.n, NULL); } rtnl_unlock(); } @@ -905,9 +914,9 @@ static void mlxsw_sp_router_probe_unresolved_nexthops(struct work_struct *work) rtnl_lock(); list_for_each_entry(neigh_entry, &mlxsw_sp->router.nexthop_neighs_list, nexthop_neighs_list_node) { - if (!(neigh_entry->n->nud_state & NUD_VALID) && + if (!(neigh_entry->key.n->nud_state & NUD_VALID) && !list_empty(&neigh_entry->nexthop_list)) - neigh_event_send(neigh_entry->n, NULL); + neigh_event_send(neigh_entry->key.n, NULL); } rtnl_unlock(); @@ -924,7 +933,7 @@ static void mlxsw_sp_router_neigh_update_hw(struct work_struct *work) { struct mlxsw_sp_neigh_entry *neigh_entry = container_of(work, struct mlxsw_sp_neigh_entry, dw.work); - struct neighbour *n = neigh_entry->n; + struct neighbour *n = neigh_entry->key.n; struct mlxsw_sp_port *mlxsw_sp_port = neigh_entry->mlxsw_sp_port; struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char rauht_pl[MLXSW_REG_RAUHT_LEN]; @@ -1027,11 +1036,8 @@ int mlxsw_sp_router_netevent_event(struct notifier_block *unused, mlxsw_sp = mlxsw_sp_port->mlxsw_sp; dip = ntohl(*((__be32 *) n->primary_key)); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, - &dip, - sizeof(__be32), - dev); - if (WARN_ON(!neigh_entry) || WARN_ON(neigh_entry->n != n)) { + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); + if (WARN_ON(!neigh_entry)) { mlxsw_sp_port_dev_put(mlxsw_sp_port); return NOTIFY_DONE; } @@ -1340,33 +1346,26 @@ static int mlxsw_sp_nexthop_init(struct mlxsw_sp *mlxsw_sp, struct fib_nh *fib_nh) { struct mlxsw_sp_neigh_entry *neigh_entry; - u32 gwip = ntohl(fib_nh->nh_gw); struct net_device *dev = fib_nh->nh_dev; struct neighbour *n; u8 nud_state; - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip, - sizeof(gwip), dev); - if (!neigh_entry) { - __be32 gwipn = htonl(gwip); - - n = neigh_create(&arp_tbl, &gwipn, dev); + /* Take a reference of neigh here ensuring that neigh would + * not be detructed before the nexthop entry is finished. + * The reference is taken either in neigh_lookup() or + * in neith_create() in case n is not found. + */ + n = neigh_lookup(&arp_tbl, &fib_nh->nh_gw, dev); + if (!n) { + n = neigh_create(&arp_tbl, &fib_nh->nh_gw, dev); if (IS_ERR(n)) return PTR_ERR(n); neigh_event_send(n, NULL); - neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, &gwip, - sizeof(gwip), dev); - if (!neigh_entry) { - neigh_release(n); - return -EINVAL; - } - } else { - /* Take a reference of neigh here ensuring that neigh would - * not be detructed before the nexthop entry is finished. - * The second branch takes the reference in neith_create() - */ - n = neigh_entry->n; - neigh_clone(n); + } + neigh_entry = mlxsw_sp_neigh_entry_lookup(mlxsw_sp, n); + if (!neigh_entry) { + neigh_release(n); + return -EINVAL; } /* If that is the first nexthop connected to that neigh, add to @@ -1400,7 +1399,7 @@ static void mlxsw_sp_nexthop_fini(struct mlxsw_sp *mlxsw_sp, if (list_empty(&nh->neigh_entry->nexthop_list)) list_del(&nh->neigh_entry->nexthop_neighs_list_node); - neigh_release(neigh_entry->n); + neigh_release(neigh_entry->key.n); } static struct mlxsw_sp_nexthop_group * @@ -1460,11 +1459,11 @@ static bool mlxsw_sp_nexthop_match(struct mlxsw_sp_nexthop *nh, for (i = 0; i < fi->fib_nhs; i++) { struct fib_nh *fib_nh = &fi->fib_nh[i]; - u32 gwip = ntohl(fib_nh->nh_gw); + struct neighbour *n = nh->neigh_entry->key.n; - if (memcmp(nh->neigh_entry->key.addr, - &gwip, sizeof(u32)) == 0 && - nh->neigh_entry->key.dev == fib_nh->nh_dev) + if (memcmp(n->primary_key, &fib_nh->nh_gw, + sizeof(fib_nh->nh_gw)) == 0 && + n->dev == fib_nh->nh_dev) return true; } return false; @@ -1820,19 +1819,17 @@ err_fib_entry_insert: return err; } -static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, - struct fib_entry_notifier_info *fen_info) +static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, + struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib_entry *fib_entry; if (mlxsw_sp->router.aborted) - return 0; + return; fib_entry = mlxsw_sp_fib_entry_find(mlxsw_sp, fen_info); - if (!fib_entry) { - dev_warn(mlxsw_sp->bus_info->dev, "Failed to find FIB4 entry being removed.\n"); - return -ENOENT; - } + if (!fib_entry) + return; if (fib_entry->ref_count == 1) { mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry); @@ -1840,7 +1837,6 @@ static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, } mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry); - return 0; } static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) @@ -1862,7 +1858,8 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) if (err) return err; - mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4, 0); + mlxsw_reg_raltb_pack(raltb_pl, 0, MLXSW_REG_RALXX_PROTOCOL_IPV4, + MLXSW_SP_LPM_TREE_MIN); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); if (err) return err; @@ -1873,18 +1870,18 @@ static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } -static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) +static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_resources *resources; struct mlxsw_sp_fib_entry *fib_entry; struct mlxsw_sp_fib_entry *tmp; struct mlxsw_sp_vr *vr; int i; - int err; resources = mlxsw_core_resources_get(mlxsw_sp->core); for (i = 0; i < resources->max_virtual_routers; i++) { vr = &mlxsw_sp->router.vrs[i]; + if (!vr->used) continue; @@ -1900,6 +1897,13 @@ static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) break; } } +} + +static void mlxsw_sp_router_fib4_abort(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + mlxsw_sp_router_fib_flush(mlxsw_sp); mlxsw_sp->router.aborted = true; err = mlxsw_sp_router_set_abort_trap(mlxsw_sp); if (err) @@ -1957,6 +1961,9 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, struct fib_entry_notifier_info *fen_info = ptr; int err; + if (!net_eq(fen_info->info.net, &init_net)) + return NOTIFY_DONE; + switch (event) { case FIB_EVENT_ENTRY_ADD: err = mlxsw_sp_router_fib4_add(mlxsw_sp, fen_info); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 5e00c79e8133..1e2c8eca3af1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -929,12 +929,12 @@ static int mlxsw_sp_port_smid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid, static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp, const unsigned char *addr, - u16 vid) + u16 fid) { struct mlxsw_sp_mid *mid; list_for_each_entry(mid, &mlxsw_sp->br_mids.list, list) { - if (ether_addr_equal(mid->addr, addr) && mid->vid == vid) + if (ether_addr_equal(mid->addr, addr) && mid->fid == fid) return mid; } return NULL; @@ -942,7 +942,7 @@ static struct mlxsw_sp_mid *__mlxsw_sp_mc_get(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp, const unsigned char *addr, - u16 vid) + u16 fid) { struct mlxsw_sp_mid *mid; u16 mid_idx; @@ -958,7 +958,7 @@ static struct mlxsw_sp_mid *__mlxsw_sp_mc_alloc(struct mlxsw_sp *mlxsw_sp, set_bit(mid_idx, mlxsw_sp->br_mids.mapped); ether_addr_copy(mid->addr, addr); - mid->vid = vid; + mid->fid = fid; mid->mid = mid_idx; mid->ref_count = 0; list_add_tail(&mid->list, &mlxsw_sp->br_mids.list); @@ -991,9 +991,9 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port, if (switchdev_trans_ph_prepare(trans)) return 0; - mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, mdb->vid); + mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid); if (!mid) { - mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, mdb->vid); + mid = __mlxsw_sp_mc_alloc(mlxsw_sp, mdb->addr, fid); if (!mid) { netdev_err(dev, "Unable to allocate MC group\n"); return -ENOMEM; @@ -1137,7 +1137,7 @@ static int mlxsw_sp_port_mdb_del(struct mlxsw_sp_port *mlxsw_sp_port, u16 mid_idx; int err = 0; - mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, mdb->vid); + mid = __mlxsw_sp_mc_get(mlxsw_sp, mdb->addr, fid); if (!mid) { netdev_err(dev, "Unable to remove port from MC DB\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index c0c23e2f3275..92bda8703f87 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -1088,6 +1088,7 @@ err_port_stp_state_set: err_port_admin_status_set: err_port_mtu_set: err_port_speed_set: + mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT); err_port_swid_set: err_port_system_port_mapping_set: port_not_usable: |