diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx5')
38 files changed, 3465 insertions, 799 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index aae46884bf93..ddb4ca4ff930 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -14,12 +14,10 @@ config MLX5_CORE config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE - select PTP_1588_CLOCK + imply PTP_1588_CLOCK 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/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 0343725d7f44..9f43beb86250 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -8,6 +8,6 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ mlx5_core-$(CONFIG_MLX5_CORE_EN) += wq.o eswitch.o eswitch_offloads.o \ en_main.o en_common.o en_fs.o en_ethtool.o en_tx.o \ en_rx.o en_rx_am.o en_txrx.o en_clock.o vxlan.o \ - en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o + en_tc.o en_arfs.o en_rep.o en_fs_ethtool.o en_selftest.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 6cb38304669f..66bd213f35ce 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. */ @@ -99,20 +106,88 @@ void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_buf *buf) } EXPORT_SYMBOL_GPL(mlx5_buf_free); +int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, + struct mlx5_frag_buf *buf, int node) +{ + int i; + + buf->size = size; + buf->npages = 1 << get_order(size); + buf->page_shift = PAGE_SHIFT; + buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list), + GFP_KERNEL); + if (!buf->frags) + goto err_out; + + for (i = 0; i < buf->npages; i++) { + struct mlx5_buf_list *frag = &buf->frags[i]; + int frag_sz = min_t(int, size, PAGE_SIZE); + + frag->buf = mlx5_dma_zalloc_coherent_node(dev, frag_sz, + &frag->map, node); + if (!frag->buf) + goto err_free_buf; + if (frag->map & ((1 << buf->page_shift) - 1)) { + dma_free_coherent(&dev->pdev->dev, frag_sz, + buf->frags[i].buf, buf->frags[i].map); + mlx5_core_warn(dev, "unexpected map alignment: %pad, page_shift=%d\n", + &frag->map, buf->page_shift); + goto err_free_buf; + } + size -= frag_sz; + } + + return 0; + +err_free_buf: + while (i--) + dma_free_coherent(&dev->pdev->dev, PAGE_SIZE, buf->frags[i].buf, + buf->frags[i].map); + kfree(buf->frags); +err_out: + return -ENOMEM; +} + +void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf) +{ + int size = buf->size; + int i; + + for (i = 0; i < buf->npages; i++) { + int frag_sz = min_t(int, size, PAGE_SIZE); + + dma_free_coherent(&dev->pdev->dev, frag_sz, buf->frags[i].buf, + buf->frags[i].map); + size -= frag_sz; + } + kfree(buf->frags); +} + 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 +198,19 @@ 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 +257,16 @@ 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); } @@ -209,3 +287,12 @@ void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas) } } EXPORT_SYMBOL_GPL(mlx5_fill_page_array); + +void mlx5_fill_page_frag_array(struct mlx5_frag_buf *buf, __be64 *pas) +{ + int i; + + for (i = 0; i < buf->npages; i++) + pas[i] = cpu_to_be64(buf->frags[i].map); +} +EXPORT_SYMBOL_GPL(mlx5_fill_page_frag_array); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1e639f886021..3797cc7c1288 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -54,14 +54,6 @@ enum { }; enum { - NUM_LONG_LISTS = 2, - NUM_MED_LISTS = 64, - LONG_LIST_SIZE = (2ULL * 1024 * 1024 * 1024 / PAGE_SIZE) * 8 + 16 + - MLX5_CMD_DATA_BLOCK_SIZE, - MED_LIST_SIZE = 16 + MLX5_CMD_DATA_BLOCK_SIZE, -}; - -enum { MLX5_CMD_DELIVERY_STAT_OK = 0x0, MLX5_CMD_DELIVERY_STAT_SIGNAT_ERR = 0x1, MLX5_CMD_DELIVERY_STAT_TOK_ERR = 0x2, @@ -268,11 +260,6 @@ 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) { @@ -318,6 +305,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY: case MLX5_CMD_OP_SET_FLOW_TABLE_ROOT: case MLX5_CMD_OP_DEALLOC_ENCAP_HEADER: + case MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT: + case MLX5_CMD_OP_DESTROY_QOS_PARA_VPORT: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -419,11 +408,14 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_FLOW_TABLE: case MLX5_CMD_OP_CREATE_FLOW_GROUP: case MLX5_CMD_OP_QUERY_FLOW_GROUP: - case MLX5_CMD_OP_QUERY_FLOW_TABLE_ENTRY: case MLX5_CMD_OP_ALLOC_FLOW_COUNTER: case MLX5_CMD_OP_QUERY_FLOW_COUNTER: case MLX5_CMD_OP_ALLOC_ENCAP_HEADER: + case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT: + case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT: + case MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT: + case MLX5_CMD_OP_CREATE_QOS_PARA_VPORT: *status = MLX5_DRIVER_STATUS_ABORTED; *synd = MLX5_DRIVER_SYND; return -EIO; @@ -580,6 +572,12 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(MODIFY_FLOW_TABLE); MLX5_COMMAND_STR_CASE(ALLOC_ENCAP_HEADER); MLX5_COMMAND_STR_CASE(DEALLOC_ENCAP_HEADER); + MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT); + MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT); + MLX5_COMMAND_STR_CASE(QUERY_SCHEDULING_ELEMENT); + MLX5_COMMAND_STR_CASE(MODIFY_SCHEDULING_ELEMENT); + MLX5_COMMAND_STR_CASE(CREATE_QOS_PARA_VPORT); + MLX5_COMMAND_STR_CASE(DESTROY_QOS_PARA_VPORT); default: return "unknown command opcode"; } } @@ -1063,14 +1061,13 @@ static struct mlx5_cmd_mailbox *alloc_cmd_box(struct mlx5_core_dev *dev, if (!mailbox) return ERR_PTR(-ENOMEM); - mailbox->buf = pci_pool_alloc(dev->cmd.pool, flags, - &mailbox->dma); + mailbox->buf = pci_pool_zalloc(dev->cmd.pool, flags, + &mailbox->dma); if (!mailbox->buf) { mlx5_core_dbg(dev, "failed allocation\n"); kfree(mailbox); return ERR_PTR(-ENOMEM); } - memset(mailbox->buf, 0, sizeof(struct mlx5_cmd_prot_block)); mailbox->next = NULL; return mailbox; @@ -1361,10 +1358,10 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg) { unsigned long flags; - if (msg->cache) { - spin_lock_irqsave(&msg->cache->lock, flags); - list_add_tail(&msg->list, &msg->cache->head); - spin_unlock_irqrestore(&msg->cache->lock, flags); + if (msg->parent) { + spin_lock_irqsave(&msg->parent->lock, flags); + list_add_tail(&msg->list, &msg->parent->head); + spin_unlock_irqrestore(&msg->parent->lock, flags); } else { mlx5_free_cmd_msg(dev, msg); } @@ -1461,30 +1458,37 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size, gfp_t gfp) { struct mlx5_cmd_msg *msg = ERR_PTR(-ENOMEM); + struct cmd_msg_cache *ch = NULL; struct mlx5_cmd *cmd = &dev->cmd; - struct cache_ent *ent = NULL; - - if (in_size > MED_LIST_SIZE && in_size <= LONG_LIST_SIZE) - ent = &cmd->cache.large; - else if (in_size > 16 && in_size <= MED_LIST_SIZE) - ent = &cmd->cache.med; - - if (ent) { - spin_lock_irq(&ent->lock); - if (!list_empty(&ent->head)) { - msg = list_entry(ent->head.next, typeof(*msg), list); - /* For cached lists, we must explicitly state what is - * the real size - */ - msg->len = in_size; - list_del(&msg->list); + int i; + + if (in_size <= 16) + goto cache_miss; + + for (i = 0; i < MLX5_NUM_COMMAND_CACHES; i++) { + ch = &cmd->cache[i]; + if (in_size > ch->max_inbox_size) + continue; + spin_lock_irq(&ch->lock); + if (list_empty(&ch->head)) { + spin_unlock_irq(&ch->lock); + continue; } - spin_unlock_irq(&ent->lock); + msg = list_entry(ch->head.next, typeof(*msg), list); + /* For cached lists, we must explicitly state what is + * the real size + */ + msg->len = in_size; + list_del(&msg->list); + spin_unlock_irq(&ch->lock); + break; } - if (IS_ERR(msg)) - msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0); + if (!IS_ERR(msg)) + return msg; +cache_miss: + msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0); return msg; } @@ -1582,58 +1586,56 @@ EXPORT_SYMBOL(mlx5_cmd_exec_cb); static void destroy_msg_cache(struct mlx5_core_dev *dev) { - struct mlx5_cmd *cmd = &dev->cmd; + struct cmd_msg_cache *ch; struct mlx5_cmd_msg *msg; struct mlx5_cmd_msg *n; + int i; - list_for_each_entry_safe(msg, n, &cmd->cache.large.head, list) { - list_del(&msg->list); - mlx5_free_cmd_msg(dev, msg); - } - - list_for_each_entry_safe(msg, n, &cmd->cache.med.head, list) { - list_del(&msg->list); - mlx5_free_cmd_msg(dev, msg); + for (i = 0; i < MLX5_NUM_COMMAND_CACHES; i++) { + ch = &dev->cmd.cache[i]; + list_for_each_entry_safe(msg, n, &ch->head, list) { + list_del(&msg->list); + mlx5_free_cmd_msg(dev, msg); + } } } -static int create_msg_cache(struct mlx5_core_dev *dev) +static unsigned cmd_cache_num_ent[MLX5_NUM_COMMAND_CACHES] = { + 512, 32, 16, 8, 2 +}; + +static unsigned cmd_cache_ent_size[MLX5_NUM_COMMAND_CACHES] = { + 16 + MLX5_CMD_DATA_BLOCK_SIZE, + 16 + MLX5_CMD_DATA_BLOCK_SIZE * 2, + 16 + MLX5_CMD_DATA_BLOCK_SIZE * 16, + 16 + MLX5_CMD_DATA_BLOCK_SIZE * 256, + 16 + MLX5_CMD_DATA_BLOCK_SIZE * 512, +}; + +static void create_msg_cache(struct mlx5_core_dev *dev) { struct mlx5_cmd *cmd = &dev->cmd; + struct cmd_msg_cache *ch; struct mlx5_cmd_msg *msg; - int err; int i; - - spin_lock_init(&cmd->cache.large.lock); - INIT_LIST_HEAD(&cmd->cache.large.head); - spin_lock_init(&cmd->cache.med.lock); - INIT_LIST_HEAD(&cmd->cache.med.head); - - for (i = 0; i < NUM_LONG_LISTS; i++) { - msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0); - if (IS_ERR(msg)) { - err = PTR_ERR(msg); - goto ex_err; + int k; + + /* Initialize and fill the caches with initial entries */ + for (k = 0; k < MLX5_NUM_COMMAND_CACHES; k++) { + ch = &cmd->cache[k]; + spin_lock_init(&ch->lock); + INIT_LIST_HEAD(&ch->head); + ch->num_ent = cmd_cache_num_ent[k]; + ch->max_inbox_size = cmd_cache_ent_size[k]; + for (i = 0; i < ch->num_ent; i++) { + msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL | __GFP_NOWARN, + ch->max_inbox_size, 0); + if (IS_ERR(msg)) + break; + msg->parent = ch; + list_add_tail(&msg->list, &ch->head); } - msg->cache = &cmd->cache.large; - list_add_tail(&msg->list, &cmd->cache.large.head); } - - for (i = 0; i < NUM_MED_LISTS; i++) { - msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0); - if (IS_ERR(msg)) { - err = PTR_ERR(msg); - goto ex_err; - } - msg->cache = &cmd->cache.med; - list_add_tail(&msg->list, &cmd->cache.med.head); - } - - return 0; - -ex_err: - destroy_msg_cache(dev); - return err; } static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd) @@ -1756,11 +1758,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) cmd->mode = CMD_MODE_POLLING; - err = create_msg_cache(dev); - if (err) { - dev_err(&dev->pdev->dev, "failed to create command cache\n"); - goto err_free_page; - } + create_msg_cache(dev); set_wqname(dev); cmd->wq = create_singlethread_workqueue(cmd->wq_name); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 460363b66cb1..951dbd58594d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -77,14 +77,17 @@ MLX5_MPWRQ_WQE_PAGE_ORDER) #define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) -#define MLX5E_REQUIRED_MTTS(rqs, wqes)\ - (rqs * wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8)) -#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX) +#define MLX5E_REQUIRED_MTTS(wqes) \ + (wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8)) +#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) - 1 <= U16_MAX) #define MLX5_UMR_ALIGN (2048) #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 @@ -147,12 +150,6 @@ static inline int mlx5_max_log_rq_size(int wq_type) } } -enum { - MLX5E_INLINE_MODE_L2, - MLX5E_INLINE_MODE_VPORT_CONTEXT, - MLX5_INLINE_MODE_NOT_REQUIRED, -}; - struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; @@ -170,22 +167,28 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_data_seg data; }; +extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; + static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = { "rx_cqe_moder", + "rx_cqe_compress", }; enum mlx5e_priv_flag { MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0), + MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 1), }; -#define MLX5E_SET_PRIV_FLAG(priv, pflag, enable) \ - do { \ - if (enable) \ - priv->pflags |= pflag; \ - else \ - priv->pflags &= ~pflag; \ +#define MLX5E_SET_PFLAG(priv, pflag, enable) \ + do { \ + if (enable) \ + (priv)->params.pflags |= (pflag); \ + else \ + (priv)->params.pflags &= ~(pflag); \ } while (0) +#define MLX5E_GET_PFLAG(priv, pflag) (!!((priv)->params.pflags & (pflag))) + #ifdef CONFIG_MLX5_CORE_EN_DCB #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */ #endif @@ -204,8 +207,7 @@ struct mlx5e_params { u16 num_channels; u8 num_tc; u8 rx_cq_period_mode; - bool rx_cqe_compress_admin; - bool rx_cqe_compress; + bool rx_cqe_compress_def; struct mlx5e_cq_moder rx_cq_moderation; struct mlx5e_cq_moder tx_cq_moderation; u16 min_rx_wqes; @@ -217,12 +219,35 @@ struct mlx5e_params { u8 toeplitz_hash_key[40]; u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE]; bool vlan_strip_disable; -#ifdef CONFIG_MLX5_CORE_EN_DCB - struct ieee_ets ets; -#endif bool rx_am_enabled; + u32 lro_timeout; + u32 pflags; +}; + +#ifdef CONFIG_MLX5_CORE_EN_DCB +struct mlx5e_cee_config { + /* bw pct for priority group */ + u8 pg_bw_pct[CEE_DCBX_MAX_PGS]; + u8 prio_to_pg_map[CEE_DCBX_MAX_PRIO]; + bool pfc_setting[CEE_DCBX_MAX_PRIO]; + bool pfc_enable; }; +enum { + MLX5_DCB_CHG_RESET, + MLX5_DCB_NO_CHG, + MLX5_DCB_CHG_NO_RESET, +}; + +struct mlx5e_dcbx { + enum mlx5_dcbx_oper_mode mode; + struct mlx5e_cee_config cee_cfg; /* pending configuration */ + + /* The only setting that cannot be read from FW */ + u8 tc_tsa[IEEE_8021QAZ_MAX_TCS]; +}; +#endif + struct mlx5e_tstamp { rwlock_t lock; struct cyclecounter cycles; @@ -237,7 +262,7 @@ struct mlx5e_tstamp { }; enum { - MLX5E_RQ_STATE_FLUSH, + MLX5E_RQ_STATE_ENABLED, MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, MLX5E_RQ_STATE_AM, }; @@ -261,7 +286,7 @@ struct mlx5e_cq { u16 decmprs_wqe_counter; /* control */ - struct mlx5_wq_ctrl wq_ctrl; + struct mlx5_frag_wq_ctrl wq_ctrl; } ____cacheline_aligned_in_smp; struct mlx5e_rq; @@ -322,7 +347,6 @@ struct mlx5e_rq { struct { struct mlx5e_mpw_info *info; void *mtt_no_align; - u32 mtt_offset; } mpwqe; }; struct { @@ -357,6 +381,7 @@ struct mlx5e_rq { u32 rqn; struct mlx5e_channel *channel; struct mlx5e_priv *priv; + struct mlx5_core_mkey umr_mkey; } ____cacheline_aligned_in_smp; struct mlx5e_umr_dma_info { @@ -390,7 +415,7 @@ struct mlx5e_sq_dma { }; enum { - MLX5E_SQ_STATE_FLUSH, + MLX5E_SQ_STATE_ENABLED, MLX5E_SQ_STATE_BF_ENABLE, }; @@ -520,7 +545,7 @@ struct mlx5e_vxlan_db { struct mlx5e_l2_rule { u8 addr[ETH_ALEN + 2]; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; }; struct mlx5e_flow_table { @@ -541,10 +566,10 @@ struct mlx5e_tc_table { struct mlx5e_vlan_table { struct mlx5e_flow_table ft; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - struct mlx5_flow_rule *active_vlans_rule[VLAN_N_VID]; - struct mlx5_flow_rule *untagged_rule; - struct mlx5_flow_rule *any_vlan_rule; - bool filter_disabled; + struct mlx5_flow_handle *active_vlans_rule[VLAN_N_VID]; + struct mlx5_flow_handle *untagged_rule; + struct mlx5_flow_handle *any_vlan_rule; + bool filter_disabled; }; struct mlx5e_l2_table { @@ -562,14 +587,14 @@ struct mlx5e_l2_table { /* L3/L4 traffic type classifier */ struct mlx5e_ttc_table { struct mlx5e_flow_table ft; - struct mlx5_flow_rule *rules[MLX5E_NUM_TT]; + struct mlx5_flow_handle *rules[MLX5E_NUM_TT]; }; #define ARFS_HASH_SHIFT BITS_PER_BYTE #define ARFS_HASH_SIZE BIT(BITS_PER_BYTE) struct arfs_table { struct mlx5e_flow_table ft; - struct mlx5_flow_rule *default_rule; + struct mlx5_flow_handle *default_rule; struct hlist_head rules_hash[ARFS_HASH_SIZE]; }; @@ -664,7 +689,6 @@ struct mlx5e_priv { unsigned long state; struct mutex state_lock; /* Protects Interface state */ - struct mlx5_core_mkey umr_mkey; struct mlx5e_rq drop_rq; struct mlx5e_channel **channel; @@ -684,12 +708,15 @@ struct mlx5e_priv { struct work_struct tx_timeout_work; struct delayed_work update_stats_work; - u32 pflags; struct mlx5_core_dev *mdev; struct net_device *netdev; struct mlx5e_stats stats; struct mlx5e_tstamp tstamp; u16 q_counter; +#ifdef CONFIG_MLX5_CORE_EN_DCB + struct mlx5e_dcbx dcbx; +#endif + const struct mlx5e_profile *profile; void *ppriv; }; @@ -731,6 +758,9 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); void mlx5e_init_l2_addr(struct mlx5e_priv *priv); void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft); +int mlx5e_self_test_num(struct mlx5e_priv *priv); +void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, + u64 *buf); int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info, int location); int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, @@ -807,8 +837,7 @@ static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) static inline u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix) { - return rq->mpwqe.mtt_offset + - wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8); + return wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8); } static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) @@ -821,6 +850,7 @@ extern const struct ethtool_ops mlx5e_ethtool_ops; #ifdef CONFIG_MLX5_CORE_EN_DCB extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops; int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets); +void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv); #endif #ifndef CONFIG_RFS_ACCEL @@ -856,7 +886,8 @@ void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir); int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev); void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); -int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev); +int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev, + bool enable_uc_lb); struct mlx5_eswitch_rep; int mlx5e_vport_rep_load(struct mlx5_eswitch *esw, @@ -870,6 +901,7 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv); void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv); int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr); void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); +void mlx5e_update_hw_rep_counters(struct mlx5e_priv *priv); int mlx5e_create_direct_rqts(struct mlx5e_priv *priv); void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); @@ -886,7 +918,16 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, struct mlx5e_priv *priv); 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); +void mlx5e_add_vxlan_port(struct net_device *netdev, + struct udp_tunnel_info *ti); +void mlx5e_del_vxlan_port(struct net_device *netdev, + struct udp_tunnel_info *ti); + +int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, + void *sp); +bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id); + +bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv); +bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv); #endif /* __MLX5_EN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index a8cb38789774..68419a01db36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -56,7 +56,7 @@ struct arfs_tuple { struct arfs_rule { struct mlx5e_priv *priv; struct work_struct arfs_work; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; struct hlist_node hlist; int rxq; /* Flow ID passed to ndo_rx_flow_steer */ @@ -104,7 +104,7 @@ static int arfs_disable(struct mlx5e_priv *priv) tt = arfs_get_tt(i); /* Modify ttc rules destination to bypass the aRFS tables*/ err = mlx5_modify_rule_destination(priv->fs.ttc.rules[tt], - &dest); + &dest, NULL); if (err) { netdev_err(priv->netdev, "%s: modify ttc destination failed\n", @@ -137,7 +137,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv) tt = arfs_get_tt(i); /* Modify ttc rules destination to point on the aRFS FTs */ err = mlx5_modify_rule_destination(priv->fs.ttc.rules[tt], - &dest); + &dest, NULL); if (err) { netdev_err(priv->netdev, "%s: modify ttc destination failed err=%d\n", @@ -151,7 +151,7 @@ int mlx5e_arfs_enable(struct mlx5e_priv *priv) static void arfs_destroy_table(struct arfs_table *arfs_t) { - mlx5_del_flow_rule(arfs_t->default_rule); + mlx5_del_flow_rules(arfs_t->default_rule); mlx5e_destroy_flow_table(&arfs_t->ft); } @@ -174,6 +174,11 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv, enum arfs_type type) { struct arfs_table *arfs_t = &priv->fs.arfs.arfs_tables[type]; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, + .encap_id = 0, + }; struct mlx5_flow_destination dest; struct mlx5e_tir *tir = priv->indir_tir; struct mlx5_flow_spec *spec; @@ -205,10 +210,9 @@ static int arfs_add_default_rule(struct mlx5e_priv *priv, goto out; } - arfs_t->default_rule = mlx5_add_flow_rule(arfs_t->ft.t, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - MLX5_FS_DEFAULT_FLOW_TAG, - &dest); + arfs_t->default_rule = mlx5_add_flow_rules(arfs_t->ft.t, spec, + &flow_act, + &dest, 1); if (IS_ERR(arfs_t->default_rule)) { err = PTR_ERR(arfs_t->default_rule); arfs_t->default_rule = NULL; @@ -324,7 +328,7 @@ static int arfs_create_table(struct mlx5e_priv *priv, int err; ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_ARFS_TABLE_SIZE, MLX5E_ARFS_FT_LEVEL); + MLX5E_ARFS_TABLE_SIZE, MLX5E_ARFS_FT_LEVEL, 0); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); ft->t = NULL; @@ -396,7 +400,7 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv) spin_unlock_bh(&priv->fs.arfs.arfs_lock); hlist_for_each_entry_safe(arfs_rule, htmp, &del_list, hlist) { if (arfs_rule->rule) - mlx5_del_flow_rule(arfs_rule->rule); + mlx5_del_flow_rules(arfs_rule->rule); hlist_del(&arfs_rule->hlist); kfree(arfs_rule); } @@ -420,7 +424,7 @@ static void arfs_del_rules(struct mlx5e_priv *priv) hlist_for_each_entry_safe(rule, htmp, &del_list, hlist) { cancel_work_sync(&rule->arfs_work); if (rule->rule) - mlx5_del_flow_rule(rule->rule); + mlx5_del_flow_rules(rule->rule); hlist_del(&rule->hlist); kfree(rule); } @@ -462,12 +466,17 @@ static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs, return NULL; } -static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv, - struct arfs_rule *arfs_rule) +static struct mlx5_flow_handle *arfs_add_rule(struct mlx5e_priv *priv, + struct arfs_rule *arfs_rule) { + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, + .encap_id = 0, + }; struct mlx5e_arfs_tables *arfs = &priv->fs.arfs; struct arfs_tuple *tuple = &arfs_rule->tuple; - struct mlx5_flow_rule *rule = NULL; + struct mlx5_flow_handle *rule = NULL; struct mlx5_flow_destination dest; struct arfs_table *arfs_table; struct mlx5_flow_spec *spec; @@ -544,9 +553,7 @@ static struct mlx5_flow_rule *arfs_add_rule(struct mlx5e_priv *priv, } dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; dest.tir_num = priv->direct_tir[arfs_rule->rxq].tirn; - rule = mlx5_add_flow_rule(ft, spec, MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - MLX5_FS_DEFAULT_FLOW_TAG, - &dest); + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); netdev_err(priv->netdev, "%s: add rule(filter id=%d, rq idx=%d) failed, err=%d\n", @@ -559,14 +566,14 @@ out: } static void arfs_modify_rule_rq(struct mlx5e_priv *priv, - struct mlx5_flow_rule *rule, u16 rxq) + struct mlx5_flow_handle *rule, u16 rxq) { struct mlx5_flow_destination dst; int err = 0; dst.type = MLX5_FLOW_DESTINATION_TYPE_TIR; dst.tir_num = priv->direct_tir[rxq].tirn; - err = mlx5_modify_rule_destination(rule, &dst); + err = mlx5_modify_rule_destination(rule, &dst, NULL); if (err) netdev_warn(priv->netdev, "Failed to modfiy aRFS rule destination to rq=%d\n", rxq); @@ -578,7 +585,7 @@ static void arfs_handle_work(struct work_struct *work) struct arfs_rule, arfs_work); struct mlx5e_priv *priv = arfs_rule->priv; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; mutex_lock(&priv->state_lock); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c index 13dc388667b6..2cd8e56a573b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c @@ -94,7 +94,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr) switch (config.rx_filter) { case HWTSTAMP_FILTER_NONE: /* Reset CQE compression to Admin default */ - mlx5e_modify_rx_cqe_compression(priv, priv->params.rx_cqe_compress_admin); + mlx5e_modify_rx_cqe_compression(priv, priv->params.rx_cqe_compress_def); break; case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_SOME: @@ -111,6 +111,7 @@ int mlx5e_hwstamp_set(struct net_device *dev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: /* Disable CQE compression */ + netdev_warn(dev, "Disabling cqe compression"); mlx5e_modify_rx_cqe_compression(priv, false); config.rx_filter = HWTSTAMP_FILTER_ALL; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 029e856f72a0..f175518ff07a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -137,7 +137,8 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) mlx5_unmap_free_uar(mdev, &res->cq_uar); } -int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev) +int mlx5e_refresh_tirs_self_loopback(struct mlx5_core_dev *mdev, + bool enable_uc_lb) { struct mlx5e_tir *tir; void *in; @@ -149,6 +150,10 @@ int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5_core_dev *mdev) if (!in) return -ENOMEM; + if (enable_uc_lb) + MLX5_SET(modify_tir_in, in, ctx.self_lb_block, + MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_); + MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 762af16ed021..7f6c225666c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -38,16 +38,77 @@ #define MLX5E_100MB (100000) #define MLX5E_1GB (1000000) +#define MLX5E_CEE_STATE_UP 1 +#define MLX5E_CEE_STATE_DOWN 0 + +/* If dcbx mode is non-host set the dcbx mode to host. + */ +static int mlx5e_dcbnl_set_dcbx_mode(struct mlx5e_priv *priv, + enum mlx5_dcbx_oper_mode mode) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u32 param[MLX5_ST_SZ_DW(dcbx_param)]; + int err; + + err = mlx5_query_port_dcbx_param(mdev, param); + if (err) + return err; + + MLX5_SET(dcbx_param, param, version_admin, mode); + if (mode != MLX5E_DCBX_PARAM_VER_OPER_HOST) + MLX5_SET(dcbx_param, param, willing_admin, 1); + + return mlx5_set_port_dcbx_param(mdev, param); +} + +static int mlx5e_dcbnl_switch_to_host_mode(struct mlx5e_priv *priv) +{ + struct mlx5e_dcbx *dcbx = &priv->dcbx; + int err; + + if (!MLX5_CAP_GEN(priv->mdev, dcbx)) + return 0; + + if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_HOST) + return 0; + + err = mlx5e_dcbnl_set_dcbx_mode(priv, MLX5E_DCBX_PARAM_VER_OPER_HOST); + if (err) + return err; + + dcbx->mode = MLX5E_DCBX_PARAM_VER_OPER_HOST; + return 0; +} + static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev, struct ieee_ets *ets) { struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + int err = 0; + int i; if (!MLX5_CAP_GEN(priv->mdev, ets)) return -ENOTSUPP; - memcpy(ets, &priv->params.ets, sizeof(*ets)); - return 0; + ets->ets_cap = mlx5_max_tc(priv->mdev) + 1; + for (i = 0; i < ets->ets_cap; i++) { + err = mlx5_query_port_prio_tc(mdev, i, &ets->prio_tc[i]); + if (err) + return err; + } + + for (i = 0; i < ets->ets_cap; i++) { + err = mlx5_query_port_tc_bw_alloc(mdev, i, &ets->tc_tx_bw[i]); + if (err) + return err; + if (ets->tc_tx_bw[i] < MLX5E_MAX_BW_ALLOC) + priv->dcbx.tc_tsa[i] = IEEE_8021QAZ_TSA_ETS; + } + + memcpy(ets->tc_tsa, priv->dcbx.tc_tsa, sizeof(ets->tc_tsa)); + + return err; } enum { @@ -110,9 +171,6 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) int max_tc = mlx5_max_tc(mdev); int err; - if (!MLX5_CAP_GEN(mdev, ets)) - return -ENOTSUPP; - mlx5e_build_tc_group(ets, tc_group, max_tc); mlx5e_build_tc_tx_bw(ets, tc_tx_bw, tc_group, max_tc); @@ -124,7 +182,14 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) if (err) return err; - return mlx5_set_port_tc_bw_alloc(mdev, tc_tx_bw); + err = mlx5_set_port_tc_bw_alloc(mdev, tc_tx_bw); + + if (err) + return err; + + memcpy(priv->dcbx.tc_tsa, ets->tc_tsa, sizeof(ets->tc_tsa)); + + return err; } static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, @@ -170,6 +235,9 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, struct mlx5e_priv *priv = netdev_priv(netdev); int err; + if (!MLX5_CAP_GEN(priv->mdev, ets)) + return -ENOTSUPP; + err = mlx5e_dbcnl_validate_ets(netdev, ets); if (err) return err; @@ -178,9 +246,6 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, if (err) return err; - memcpy(&priv->params.ets, ets, sizeof(*ets)); - priv->params.ets.ets_cap = mlx5_max_tc(priv->mdev) + 1; - return 0; } @@ -222,13 +287,39 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, static u8 mlx5e_dcbnl_getdcbx(struct net_device *dev) { - return DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_dcbx *dcbx = &priv->dcbx; + u8 mode = DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_VER_CEE; + + if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_HOST) + mode |= DCB_CAP_DCBX_HOST; + + return mode; } static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) { + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_dcbx *dcbx = &priv->dcbx; + + if ((!mode) && MLX5_CAP_GEN(priv->mdev, dcbx)) { + if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_AUTO) + return 0; + + /* set dcbx to fw controlled */ + if (!mlx5e_dcbnl_set_dcbx_mode(priv, MLX5E_DCBX_PARAM_VER_OPER_AUTO)) { + dcbx->mode = MLX5E_DCBX_PARAM_VER_OPER_AUTO; + return 0; + } + + return 1; + } + + if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev))) + return 1; + if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || - (mode & DCB_CAP_DCBX_VER_CEE) || + !(mode & DCB_CAP_DCBX_VER_CEE) || !(mode & DCB_CAP_DCBX_VER_IEEE) || !(mode & DCB_CAP_DCBX_HOST)) return 1; @@ -304,6 +395,284 @@ static int mlx5e_dcbnl_ieee_setmaxrate(struct net_device *netdev, return mlx5_modify_port_ets_rate_limit(mdev, max_bw_value, max_bw_unit); } +static u8 mlx5e_dcbnl_setall(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_cee_config *cee_cfg = &priv->dcbx.cee_cfg; + struct mlx5_core_dev *mdev = priv->mdev; + struct ieee_ets ets; + struct ieee_pfc pfc; + int err = -ENOTSUPP; + int i; + + if (!MLX5_CAP_GEN(mdev, ets)) + goto out; + + memset(&ets, 0, sizeof(ets)); + memset(&pfc, 0, sizeof(pfc)); + + ets.ets_cap = IEEE_8021QAZ_MAX_TCS; + for (i = 0; i < CEE_DCBX_MAX_PGS; i++) { + ets.tc_tx_bw[i] = cee_cfg->pg_bw_pct[i]; + ets.tc_rx_bw[i] = cee_cfg->pg_bw_pct[i]; + ets.tc_tsa[i] = IEEE_8021QAZ_TSA_ETS; + ets.prio_tc[i] = cee_cfg->prio_to_pg_map[i]; + } + + err = mlx5e_dbcnl_validate_ets(netdev, &ets); + if (err) { + netdev_err(netdev, + "%s, Failed to validate ETS: %d\n", __func__, err); + goto out; + } + + err = mlx5e_dcbnl_ieee_setets_core(priv, &ets); + if (err) { + netdev_err(netdev, + "%s, Failed to set ETS: %d\n", __func__, err); + goto out; + } + + /* Set PFC */ + pfc.pfc_cap = mlx5_max_tc(mdev) + 1; + if (!cee_cfg->pfc_enable) + pfc.pfc_en = 0; + else + for (i = 0; i < CEE_DCBX_MAX_PRIO; i++) + pfc.pfc_en |= cee_cfg->pfc_setting[i] << i; + + err = mlx5e_dcbnl_ieee_setpfc(netdev, &pfc); + if (err) { + netdev_err(netdev, + "%s, Failed to set PFC: %d\n", __func__, err); + goto out; + } +out: + return err ? MLX5_DCB_NO_CHG : MLX5_DCB_CHG_RESET; +} + +static u8 mlx5e_dcbnl_getstate(struct net_device *netdev) +{ + return MLX5E_CEE_STATE_UP; +} + +static void mlx5e_dcbnl_getpermhwaddr(struct net_device *netdev, + u8 *perm_addr) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + if (!perm_addr) + return; + + mlx5_query_nic_vport_mac_address(priv->mdev, 0, perm_addr); +} + +static void mlx5e_dcbnl_setpgtccfgtx(struct net_device *netdev, + int priority, u8 prio_type, + u8 pgid, u8 bw_pct, u8 up_map) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_cee_config *cee_cfg = &priv->dcbx.cee_cfg; + + if (priority >= CEE_DCBX_MAX_PRIO) { + netdev_err(netdev, + "%s, priority is out of range\n", __func__); + return; + } + + if (pgid >= CEE_DCBX_MAX_PGS) { + netdev_err(netdev, + "%s, priority group is out of range\n", __func__); + return; + } + + cee_cfg->prio_to_pg_map[priority] = pgid; +} + +static void mlx5e_dcbnl_setpgbwgcfgtx(struct net_device *netdev, + int pgid, u8 bw_pct) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_cee_config *cee_cfg = &priv->dcbx.cee_cfg; + + if (pgid >= CEE_DCBX_MAX_PGS) { + netdev_err(netdev, + "%s, priority group is out of range\n", __func__); + return; + } + + cee_cfg->pg_bw_pct[pgid] = bw_pct; +} + +static void mlx5e_dcbnl_getpgtccfgtx(struct net_device *netdev, + int priority, u8 *prio_type, + u8 *pgid, u8 *bw_pct, u8 *up_map) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + + if (priority >= CEE_DCBX_MAX_PRIO) { + netdev_err(netdev, + "%s, priority is out of range\n", __func__); + return; + } + + *prio_type = 0; + *bw_pct = 0; + *up_map = 0; + + if (mlx5_query_port_prio_tc(mdev, priority, pgid)) + *pgid = 0; +} + +static void mlx5e_dcbnl_getpgbwgcfgtx(struct net_device *netdev, + int pgid, u8 *bw_pct) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + + if (pgid >= CEE_DCBX_MAX_PGS) { + netdev_err(netdev, + "%s, priority group is out of range\n", __func__); + return; + } + + if (mlx5_query_port_tc_bw_alloc(mdev, pgid, bw_pct)) + *bw_pct = 0; +} + +static void mlx5e_dcbnl_setpfccfg(struct net_device *netdev, + int priority, u8 setting) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_cee_config *cee_cfg = &priv->dcbx.cee_cfg; + + if (priority >= CEE_DCBX_MAX_PRIO) { + netdev_err(netdev, + "%s, priority is out of range\n", __func__); + return; + } + + if (setting > 1) + return; + + cee_cfg->pfc_setting[priority] = setting; +} + +static int +mlx5e_dcbnl_get_priority_pfc(struct net_device *netdev, + int priority, u8 *setting) +{ + struct ieee_pfc pfc; + int err; + + err = mlx5e_dcbnl_ieee_getpfc(netdev, &pfc); + + if (err) + *setting = 0; + else + *setting = (pfc.pfc_en >> priority) & 0x01; + + return err; +} + +static void mlx5e_dcbnl_getpfccfg(struct net_device *netdev, + int priority, u8 *setting) +{ + if (priority >= CEE_DCBX_MAX_PRIO) { + netdev_err(netdev, + "%s, priority is out of range\n", __func__); + return; + } + + if (!setting) + return; + + mlx5e_dcbnl_get_priority_pfc(netdev, priority, setting); +} + +static u8 mlx5e_dcbnl_getcap(struct net_device *netdev, + int capid, u8 *cap) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + u8 rval = 0; + + switch (capid) { + case DCB_CAP_ATTR_PG: + *cap = true; + break; + case DCB_CAP_ATTR_PFC: + *cap = true; + break; + case DCB_CAP_ATTR_UP2TC: + *cap = false; + break; + case DCB_CAP_ATTR_PG_TCS: + *cap = 1 << mlx5_max_tc(mdev); + break; + case DCB_CAP_ATTR_PFC_TCS: + *cap = 1 << mlx5_max_tc(mdev); + break; + case DCB_CAP_ATTR_GSP: + *cap = false; + break; + case DCB_CAP_ATTR_BCN: + *cap = false; + break; + case DCB_CAP_ATTR_DCBX: + *cap = (DCB_CAP_DCBX_LLD_MANAGED | + DCB_CAP_DCBX_VER_CEE | + DCB_CAP_DCBX_STATIC); + break; + default: + *cap = 0; + rval = 1; + break; + } + + return rval; +} + +static int mlx5e_dcbnl_getnumtcs(struct net_device *netdev, + int tcs_id, u8 *num) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + + switch (tcs_id) { + case DCB_NUMTCS_ATTR_PG: + case DCB_NUMTCS_ATTR_PFC: + *num = mlx5_max_tc(mdev) + 1; + break; + default: + return -EINVAL; + } + + return 0; +} + +static u8 mlx5e_dcbnl_getpfcstate(struct net_device *netdev) +{ + struct ieee_pfc pfc; + + if (mlx5e_dcbnl_ieee_getpfc(netdev, &pfc)) + return MLX5E_CEE_STATE_DOWN; + + return pfc.pfc_en ? MLX5E_CEE_STATE_UP : MLX5E_CEE_STATE_DOWN; +} + +static void mlx5e_dcbnl_setpfcstate(struct net_device *netdev, u8 state) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_cee_config *cee_cfg = &priv->dcbx.cee_cfg; + + if ((state != MLX5E_CEE_STATE_UP) && (state != MLX5E_CEE_STATE_DOWN)) + return; + + cee_cfg->pfc_enable = state; +} + const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = { .ieee_getets = mlx5e_dcbnl_ieee_getets, .ieee_setets = mlx5e_dcbnl_ieee_setets, @@ -313,4 +682,70 @@ const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops = { .ieee_setpfc = mlx5e_dcbnl_ieee_setpfc, .getdcbx = mlx5e_dcbnl_getdcbx, .setdcbx = mlx5e_dcbnl_setdcbx, + +/* CEE interfaces */ + .setall = mlx5e_dcbnl_setall, + .getstate = mlx5e_dcbnl_getstate, + .getpermhwaddr = mlx5e_dcbnl_getpermhwaddr, + + .setpgtccfgtx = mlx5e_dcbnl_setpgtccfgtx, + .setpgbwgcfgtx = mlx5e_dcbnl_setpgbwgcfgtx, + .getpgtccfgtx = mlx5e_dcbnl_getpgtccfgtx, + .getpgbwgcfgtx = mlx5e_dcbnl_getpgbwgcfgtx, + + .setpfccfg = mlx5e_dcbnl_setpfccfg, + .getpfccfg = mlx5e_dcbnl_getpfccfg, + .getcap = mlx5e_dcbnl_getcap, + .getnumtcs = mlx5e_dcbnl_getnumtcs, + .getpfcstate = mlx5e_dcbnl_getpfcstate, + .setpfcstate = mlx5e_dcbnl_setpfcstate, }; + +static void mlx5e_dcbnl_query_dcbx_mode(struct mlx5e_priv *priv, + enum mlx5_dcbx_oper_mode *mode) +{ + u32 out[MLX5_ST_SZ_DW(dcbx_param)]; + + *mode = MLX5E_DCBX_PARAM_VER_OPER_HOST; + + if (!mlx5_query_port_dcbx_param(priv->mdev, out)) + *mode = MLX5_GET(dcbx_param, out, version_oper); + + /* From driver's point of view, we only care if the mode + * is host (HOST) or non-host (AUTO) + */ + if (*mode != MLX5E_DCBX_PARAM_VER_OPER_HOST) + *mode = MLX5E_DCBX_PARAM_VER_OPER_AUTO; +} + +static void mlx5e_ets_init(struct mlx5e_priv *priv) +{ + int i; + struct ieee_ets ets; + + memset(&ets, 0, sizeof(ets)); + ets.ets_cap = mlx5_max_tc(priv->mdev) + 1; + for (i = 0; i < ets.ets_cap; i++) { + ets.tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; + ets.tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR; + ets.prio_tc[i] = i; + } + + memcpy(priv->dcbx.tc_tsa, ets.tc_tsa, sizeof(ets.tc_tsa)); + + /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ + ets.prio_tc[0] = 1; + ets.prio_tc[1] = 0; + + mlx5e_dcbnl_ieee_setets_core(priv, &ets); +} + +void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) +{ + struct mlx5e_dcbx *dcbx = &priv->dcbx; + + if (MLX5_CAP_GEN(priv->mdev, dcbx)) + mlx5e_dcbnl_query_dcbx_mode(priv, &dcbx->mode); + + mlx5e_ets_init(priv); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 27ff401cec20..352462af8d51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -171,11 +171,17 @@ static int mlx5e_get_sset_count(struct net_device *dev, int sset) return NUM_SW_COUNTERS + MLX5E_NUM_Q_CNTRS(priv) + NUM_VPORT_COUNTERS + NUM_PPORT_COUNTERS + + NUM_PCIE_COUNTERS + MLX5E_NUM_RQ_STATS(priv) + MLX5E_NUM_SQ_STATS(priv) + - MLX5E_NUM_PFC_COUNTERS(priv); + MLX5E_NUM_PFC_COUNTERS(priv) + + ARRAY_SIZE(mlx5e_pme_status_desc) + + ARRAY_SIZE(mlx5e_pme_error_desc); + case ETH_SS_PRIV_FLAGS: return ARRAY_SIZE(mlx5e_priv_flags); + case ETH_SS_TEST: + return mlx5e_self_test_num(priv); /* fallthrough */ default: return -EOPNOTSUPP; @@ -213,6 +219,14 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) strcpy(data + (idx++) * ETH_GSTRING_LEN, pport_2819_stats_desc[i].format); + for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + pcie_perf_stats_desc[i].format); + + for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + pcie_tas_stats_desc[i].format); + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++) sprintf(data + (idx++) * ETH_GSTRING_LEN, @@ -237,6 +251,13 @@ static void mlx5e_fill_stats_strings(struct mlx5e_priv *priv, uint8_t *data) } } + /* port module event counters */ + for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_status_desc[i].format); + + for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, mlx5e_pme_error_desc[i].format); + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return; @@ -267,6 +288,9 @@ static void mlx5e_get_strings(struct net_device *dev, break; case ETH_SS_TEST: + for (i = 0; i < mlx5e_self_test_num(priv); i++) + strcpy(data + i * ETH_GSTRING_LEN, + mlx5e_self_tests[i]); break; case ETH_SS_STATS: @@ -279,6 +303,7 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_priv *mlx5_priv; int i, j, tc, prio, idx = 0; unsigned long pfc_combined; @@ -314,6 +339,14 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev, data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.RFC_2819_counters, pport_2819_stats_desc, i); + for (i = 0; i < NUM_PCIE_PERF_COUNTERS; i++) + data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_perf_counters, + pcie_perf_stats_desc, i); + + for (i = 0; i < NUM_PCIE_TAS_COUNTERS; i++) + data[idx++] = MLX5E_READ_CTR32_BE(&priv->stats.pcie.pcie_tas_counters, + pcie_tas_stats_desc, i); + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { for (i = 0; i < NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS; i++) data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[prio], @@ -335,6 +368,16 @@ static void mlx5e_get_ethtool_stats(struct net_device *dev, } } + /* port module event counters */ + mlx5_priv = &priv->mdev->priv; + for (i = 0; i < ARRAY_SIZE(mlx5e_pme_status_desc); i++) + data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters, + mlx5e_pme_status_desc, i); + + for (i = 0; i < ARRAY_SIZE(mlx5e_pme_error_desc); i++) + data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters, + mlx5e_pme_error_desc, i); + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return; @@ -456,8 +499,7 @@ static int mlx5e_set_ringparam(struct net_device *dev, return -EINVAL; } - num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels, - rx_pending_wqes); + num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes); if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && !MLX5E_VALID_NUM_MTTS(num_mtts)) { netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n", @@ -522,7 +564,6 @@ static int mlx5e_set_channels(struct net_device *dev, unsigned int count = ch->combined_count; bool arfs_enabled; bool was_opened; - u32 num_mtts; int err = 0; if (!count) { @@ -541,14 +582,6 @@ static int mlx5e_set_channels(struct net_device *dev, return -EINVAL; } - num_mtts = MLX5E_REQUIRED_MTTS(count, BIT(priv->params.log_rq_size)); - if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ && - !MLX5E_VALID_NUM_MTTS(num_mtts)) { - netdev_info(dev, "%s: rx count (%d) request can't be satisfied, try to reduce.\n", - __func__, count); - return -EINVAL; - } - if (priv->params.num_channels == count) return 0; @@ -1438,6 +1471,35 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable) return err; } +static int set_pflag_rx_cqe_compress(struct net_device *netdev, + bool enable) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; + int err = 0; + bool reset; + + if (!MLX5_CAP_GEN(mdev, cqe_compression)) + return -ENOTSUPP; + + if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) { + netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n"); + return -EINVAL; + } + + reset = test_bit(MLX5E_STATE_OPENED, &priv->state); + + if (reset) + mlx5e_close_locked(netdev); + + MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, enable); + priv->params.rx_cqe_compress_def = enable; + + if (reset) + err = mlx5e_open_locked(netdev); + return err; +} + static int mlx5e_handle_pflag(struct net_device *netdev, u32 wanted_flags, enum mlx5e_priv_flag flag, @@ -1445,7 +1507,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); bool enable = !!(wanted_flags & flag); - u32 changes = wanted_flags ^ priv->pflags; + u32 changes = wanted_flags ^ priv->params.pflags; int err; if (!(changes & flag)) @@ -1458,7 +1520,7 @@ static int mlx5e_handle_pflag(struct net_device *netdev, return err; } - MLX5E_SET_PRIV_FLAG(priv, flag, enable); + MLX5E_SET_PFLAG(priv, flag, enable); return 0; } @@ -1468,20 +1530,26 @@ static int mlx5e_set_priv_flags(struct net_device *netdev, u32 pflags) int err; mutex_lock(&priv->state_lock); - err = mlx5e_handle_pflag(netdev, pflags, MLX5E_PFLAG_RX_CQE_BASED_MODER, set_pflag_rx_cqe_based_moder); + if (err) + goto out; + + err = mlx5e_handle_pflag(netdev, pflags, + MLX5E_PFLAG_RX_CQE_COMPRESS, + set_pflag_rx_cqe_compress); +out: mutex_unlock(&priv->state_lock); - return err ? -EINVAL : 0; + return err; } static u32 mlx5e_get_priv_flags(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); - return priv->pflags; + return priv->params.pflags; } static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) @@ -1535,5 +1603,6 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_module_info = mlx5e_get_module_info, .get_module_eeprom = mlx5e_get_module_eeprom, .get_priv_flags = mlx5e_get_priv_flags, - .set_priv_flags = mlx5e_set_priv_flags + .set_priv_flags = mlx5e_set_priv_flags, + .self_test = mlx5e_self_test, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 36fbc6b21a33..1fe80de5d68f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -158,9 +158,14 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv, enum mlx5e_vlan_rule_type rule_type, u16 vid, struct mlx5_flow_spec *spec) { + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, + .encap_id = 0, + }; struct mlx5_flow_table *ft = priv->fs.vlan.ft.t; struct mlx5_flow_destination dest; - struct mlx5_flow_rule **rule_p; + struct mlx5_flow_handle **rule_p; int err = 0; dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; @@ -187,10 +192,7 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv, break; } - *rule_p = mlx5_add_flow_rule(ft, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - MLX5_FS_DEFAULT_FLOW_TAG, - &dest); + *rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(*rule_p)) { err = PTR_ERR(*rule_p); @@ -229,20 +231,20 @@ static void mlx5e_del_vlan_rule(struct mlx5e_priv *priv, switch (rule_type) { case MLX5E_VLAN_RULE_TYPE_UNTAGGED: if (priv->fs.vlan.untagged_rule) { - mlx5_del_flow_rule(priv->fs.vlan.untagged_rule); + mlx5_del_flow_rules(priv->fs.vlan.untagged_rule); priv->fs.vlan.untagged_rule = NULL; } break; case MLX5E_VLAN_RULE_TYPE_ANY_VID: if (priv->fs.vlan.any_vlan_rule) { - mlx5_del_flow_rule(priv->fs.vlan.any_vlan_rule); + mlx5_del_flow_rules(priv->fs.vlan.any_vlan_rule); priv->fs.vlan.any_vlan_rule = NULL; } break; case MLX5E_VLAN_RULE_TYPE_MATCH_VID: mlx5e_vport_context_update_vlans(priv); if (priv->fs.vlan.active_vlans_rule[vid]) { - mlx5_del_flow_rule(priv->fs.vlan.active_vlans_rule[vid]); + mlx5_del_flow_rules(priv->fs.vlan.active_vlans_rule[vid]); priv->fs.vlan.active_vlans_rule[vid] = NULL; } mlx5e_vport_context_update_vlans(priv); @@ -560,7 +562,7 @@ static void mlx5e_cleanup_ttc_rules(struct mlx5e_ttc_table *ttc) for (i = 0; i < MLX5E_NUM_TT; i++) { if (!IS_ERR_OR_NULL(ttc->rules[i])) { - mlx5_del_flow_rule(ttc->rules[i]); + mlx5_del_flow_rules(ttc->rules[i]); ttc->rules[i] = NULL; } } @@ -616,13 +618,19 @@ static struct { }, }; -static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv, - struct mlx5_flow_table *ft, - struct mlx5_flow_destination *dest, - u16 etype, - u8 proto) +static struct mlx5_flow_handle * +mlx5e_generate_ttc_rule(struct mlx5e_priv *priv, + struct mlx5_flow_table *ft, + struct mlx5_flow_destination *dest, + u16 etype, + u8 proto) { - struct mlx5_flow_rule *rule; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, + .encap_id = 0, + }; + struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; int err = 0; @@ -643,10 +651,7 @@ static struct mlx5_flow_rule *mlx5e_generate_ttc_rule(struct mlx5e_priv *priv, MLX5_SET(fte_match_param, spec->match_value, outer_headers.ethertype, etype); } - rule = mlx5_add_flow_rule(ft, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - MLX5_FS_DEFAULT_FLOW_TAG, - dest); + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); netdev_err(priv->netdev, "%s: add rule failed\n", __func__); @@ -660,7 +665,7 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv) { struct mlx5_flow_destination dest; struct mlx5e_ttc_table *ttc; - struct mlx5_flow_rule **rules; + struct mlx5_flow_handle **rules; struct mlx5_flow_table *ft; int tt; int err; @@ -776,7 +781,7 @@ static int mlx5e_create_ttc_table(struct mlx5e_priv *priv) int err; ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_TTC_TABLE_SIZE, MLX5E_TTC_FT_LEVEL); + MLX5E_TTC_TABLE_SIZE, MLX5E_TTC_FT_LEVEL, 0); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); ft->t = NULL; @@ -801,7 +806,7 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv, struct mlx5e_l2_rule *ai) { if (!IS_ERR_OR_NULL(ai->rule)) { - mlx5_del_flow_rule(ai->rule); + mlx5_del_flow_rules(ai->rule); ai->rule = NULL; } } @@ -809,6 +814,11 @@ static void mlx5e_del_l2_flow_rule(struct mlx5e_priv *priv, static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv, struct mlx5e_l2_rule *ai, int type) { + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, + .encap_id = 0, + }; struct mlx5_flow_table *ft = priv->fs.l2.ft.t; struct mlx5_flow_destination dest; struct mlx5_flow_spec *spec; @@ -847,9 +857,7 @@ static int mlx5e_add_l2_flow_rule(struct mlx5e_priv *priv, break; } - ai->rule = mlx5_add_flow_rule(ft, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - MLX5_FS_DEFAULT_FLOW_TAG, &dest); + ai->rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(ai->rule)) { netdev_err(priv->netdev, "%s: add l2 rule(mac:%pM) failed\n", __func__, mv_dmac); @@ -947,7 +955,7 @@ static int mlx5e_create_l2_table(struct mlx5e_priv *priv) ft->num_groups = 0; ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_L2_TABLE_SIZE, MLX5E_L2_FT_LEVEL); + MLX5E_L2_TABLE_SIZE, MLX5E_L2_FT_LEVEL, 0); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); @@ -1037,7 +1045,7 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv) ft->num_groups = 0; ft->t = mlx5_create_flow_table(priv->fs.ns, MLX5E_NIC_PRIO, - MLX5E_VLAN_TABLE_SIZE, MLX5E_VLAN_FT_LEVEL); + MLX5E_VLAN_TABLE_SIZE, MLX5E_VLAN_FT_LEVEL, 0); if (IS_ERR(ft->t)) { err = PTR_ERR(ft->t); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index d17c24227900..3691451c728c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -36,7 +36,7 @@ struct mlx5e_ethtool_rule { struct list_head list; struct ethtool_rx_flow_spec flow_spec; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; struct mlx5e_ethtool_table *eth_ft; }; @@ -99,7 +99,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv, MLX5E_ETHTOOL_NUM_ENTRIES); ft = mlx5_create_auto_grouped_flow_table(ns, prio, table_size, - MLX5E_ETHTOOL_NUM_GROUPS, 0); + MLX5E_ETHTOOL_NUM_GROUPS, 0, 0); if (IS_ERR(ft)) return (void *)ft; @@ -284,15 +284,16 @@ static bool outer_header_zero(u32 *match_criteria) size - 1); } -static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv, - struct mlx5_flow_table *ft, - struct ethtool_rx_flow_spec *fs) +static struct mlx5_flow_handle * +add_ethtool_flow_rule(struct mlx5e_priv *priv, + struct mlx5_flow_table *ft, + struct ethtool_rx_flow_spec *fs) { struct mlx5_flow_destination *dst = NULL; + struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_spec *spec; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; int err = 0; - u32 action; spec = mlx5_vzalloc(sizeof(*spec)); if (!spec) @@ -303,7 +304,7 @@ static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv, goto free; if (fs->ring_cookie == RX_CLS_FLOW_DISC) { - action = MLX5_FLOW_CONTEXT_ACTION_DROP; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; } else { dst = kzalloc(sizeof(*dst), GFP_KERNEL); if (!dst) { @@ -313,12 +314,12 @@ static struct mlx5_flow_rule *add_ethtool_flow_rule(struct mlx5e_priv *priv, dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR; dst->tir_num = priv->direct_tir[fs->ring_cookie].tirn; - action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; } spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria)); - rule = mlx5_add_flow_rule(ft, spec, action, - MLX5_FS_DEFAULT_FLOW_TAG, dst); + flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); netdev_err(priv->netdev, "%s: failed to add ethtool steering rule: %d\n", @@ -335,7 +336,7 @@ static void del_ethtool_rule(struct mlx5e_priv *priv, struct mlx5e_ethtool_rule *eth_rule) { if (eth_rule->rule) - mlx5_del_flow_rule(eth_rule->rule); + mlx5_del_flow_rules(eth_rule->rule); list_del(ð_rule->list); priv->fs.ethtool.tot_num_rules--; put_flow_table(eth_rule->eth_ft); @@ -475,7 +476,7 @@ int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, { struct mlx5e_ethtool_table *eth_ft; struct mlx5e_ethtool_rule *eth_rule; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; int num_tuples; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 7eaf38020a8f..cbfa38fc72c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -84,7 +84,8 @@ static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type) switch (priv->params.rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: priv->params.log_rq_size = MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW; - priv->params.mpwqe_log_stride_sz = priv->params.rx_cqe_compress ? + priv->params.mpwqe_log_stride_sz = + MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) ? MLX5_MPWRQ_LOG_STRIDE_SIZE_CQE_COMPRESS : MLX5_MPWRQ_LOG_STRIDE_SIZE; priv->params.mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - @@ -101,7 +102,7 @@ static void mlx5e_set_rq_type_params(struct mlx5e_priv *priv, u8 rq_type) priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ, BIT(priv->params.log_rq_size), BIT(priv->params.mpwqe_log_stride_sz), - priv->params.rx_cqe_compress_admin); + MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS)); } static void mlx5e_set_rq_priv_params(struct mlx5e_priv *priv) @@ -290,12 +291,36 @@ static void mlx5e_update_q_counter(struct mlx5e_priv *priv) &qcnt->rx_out_of_buffer); } +static void mlx5e_update_pcie_counters(struct mlx5e_priv *priv) +{ + struct mlx5e_pcie_stats *pcie_stats = &priv->stats.pcie; + struct mlx5_core_dev *mdev = priv->mdev; + int sz = MLX5_ST_SZ_BYTES(mpcnt_reg); + void *out; + u32 *in; + + in = mlx5_vzalloc(sz); + if (!in) + return; + + out = pcie_stats->pcie_perf_counters; + MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_PERFORMANCE_COUNTERS_GROUP); + mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0); + + out = pcie_stats->pcie_tas_counters; + MLX5_SET(mpcnt_reg, in, grp, MLX5_PCIE_TIMERS_AND_STATES_COUNTERS_GROUP); + mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0); + + kvfree(in); +} + void mlx5e_update_stats(struct mlx5e_priv *priv) { mlx5e_update_q_counter(priv); mlx5e_update_vport_counters(priv); mlx5e_update_pport_counters(priv); mlx5e_update_sw_counters(priv); + mlx5e_update_pcie_counters(priv); } void mlx5e_update_stats_work(struct work_struct *work) @@ -446,14 +471,50 @@ static void mlx5e_rq_free_mpwqe_info(struct mlx5e_rq *rq) kfree(rq->mpwqe.info); } -static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) +static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv, + u64 npages, u8 page_shift, + struct mlx5_core_mkey *umr_mkey) { - struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv; + struct mlx5_core_dev *mdev = priv->mdev; + int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + void *mkc; + u32 *in; + int err; - if (rep && rep->vport != FDB_UPLINK_VPORT) - return true; + if (!MLX5E_VALID_NUM_MTTS(npages)) + return -EINVAL; - return false; + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + + MLX5_SET(mkc, mkc, free, 1); + MLX5_SET(mkc, mkc, umr_en, 1); + MLX5_SET(mkc, mkc, lw, 1); + MLX5_SET(mkc, mkc, lr, 1); + MLX5_SET(mkc, mkc, access_mode, MLX5_MKC_ACCESS_MODE_MTT); + + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn); + MLX5_SET64(mkc, mkc, len, npages << page_shift); + MLX5_SET(mkc, mkc, translations_octword_size, + MLX5_MTT_OCTW(npages)); + MLX5_SET(mkc, mkc, log_page_size, page_shift); + + err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen); + + kvfree(in); + return err; +} + +static int mlx5e_create_rq_umr_mkey(struct mlx5e_rq *rq) +{ + struct mlx5e_priv *priv = rq->priv; + u64 num_mtts = MLX5E_REQUIRED_MTTS(BIT(priv->params.log_rq_size)); + + return mlx5e_create_umr_mkey(priv, num_mtts, PAGE_SHIFT, &rq->umr_mkey); } static int mlx5e_create_rq(struct mlx5e_channel *c, @@ -489,7 +550,13 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, rq->channel = c; rq->ix = c->ix; rq->priv = c->priv; - rq->xdp_prog = priv->xdp_prog; + + rq->xdp_prog = priv->xdp_prog ? bpf_prog_inc(priv->xdp_prog) : NULL; + if (IS_ERR(rq->xdp_prog)) { + err = PTR_ERR(rq->xdp_prog); + rq->xdp_prog = NULL; + goto err_rq_wq_destroy; + } rq->buff.map_dir = DMA_FROM_DEVICE; if (rq->xdp_prog) @@ -506,18 +573,20 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, rq->alloc_wqe = mlx5e_alloc_rx_mpwqe; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; - rq->mpwqe.mtt_offset = c->ix * - MLX5E_REQUIRED_MTTS(1, BIT(priv->params.log_rq_size)); - rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz); rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides); rq->buff.wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides; byte_count = rq->buff.wqe_sz; - rq->mkey_be = cpu_to_be32(c->priv->umr_mkey.key); - err = mlx5e_rq_alloc_mpwqe_info(rq, c); + + err = mlx5e_create_rq_umr_mkey(rq); if (err) goto err_rq_wq_destroy; + rq->mkey_be = cpu_to_be32(rq->umr_mkey.key); + + err = mlx5e_rq_alloc_mpwqe_info(rq, c); + if (err) + goto err_destroy_umr_mkey; break; default: /* MLX5_WQ_TYPE_LINKED_LIST */ rq->dma_info = kzalloc_node(wq_sz * sizeof(*rq->dma_info), @@ -566,12 +635,14 @@ static int mlx5e_create_rq(struct mlx5e_channel *c, rq->page_cache.head = 0; rq->page_cache.tail = 0; - if (rq->xdp_prog) - bpf_prog_add(rq->xdp_prog, 1); - return 0; +err_destroy_umr_mkey: + mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); + err_rq_wq_destroy: + if (rq->xdp_prog) + bpf_prog_put(rq->xdp_prog); mlx5_wq_destroy(&rq->wq_ctrl); return err; @@ -587,6 +658,7 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq) switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: mlx5e_rq_free_mpwqe_info(rq); + mlx5_core_destroy_mkey(rq->priv->mdev, &rq->umr_mkey); break; default: /* MLX5_WQ_TYPE_LINKED_LIST */ kfree(rq->dma_info); @@ -759,6 +831,7 @@ 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 +846,7 @@ 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 +856,7 @@ 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); @@ -938,7 +1012,7 @@ static int mlx5e_create_sq(struct mlx5e_channel *c, sq->bf_buf_size = (1 << MLX5_CAP_GEN(mdev, log_bf_reg_size)) / 2; sq->max_inline = param->max_inline; sq->min_inline_mode = - MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5E_INLINE_MODE_VPORT_CONTEXT ? + MLX5_CAP_ETH(mdev, wqe_inline_mode) == MLX5_CAP_INLINE_MODE_VPORT_CONTEXT ? param->min_inline_mode : 0; err = mlx5e_alloc_sq_db(sq, cpu_to_node(c->cpu)); @@ -1006,7 +1080,6 @@ 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 +1156,7 @@ 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 +1170,7 @@ 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 +1187,7 @@ 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); @@ -1181,7 +1256,7 @@ static int mlx5e_create_cq(struct mlx5e_channel *c, static void mlx5e_destroy_cq(struct mlx5e_cq *cq) { - mlx5_wq_destroy(&cq->wq_ctrl); + mlx5_cqwq_destroy(&cq->wq_ctrl); } static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) @@ -1198,7 +1273,7 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) int err; inlen = MLX5_ST_SZ_BYTES(create_cq_in) + - sizeof(u64) * cq->wq_ctrl.buf.npages; + sizeof(u64) * cq->wq_ctrl.frag_buf.npages; in = mlx5_vzalloc(inlen); if (!in) return -ENOMEM; @@ -1207,15 +1282,15 @@ static int mlx5e_enable_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param) memcpy(cqc, param->cqc, sizeof(param->cqc)); - mlx5_fill_page_array(&cq->wq_ctrl.buf, - (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); + mlx5_fill_page_frag_array(&cq->wq_ctrl.frag_buf, + (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas)); mlx5_vector2eqn(mdev, param->eq_ix, &eqn, &irqn_not_used); MLX5_SET(cqc, cqc, cq_period_mode, param->cq_period_mode); MLX5_SET(cqc, cqc, c_eqn, eqn); MLX5_SET(cqc, cqc, uar_page, mcq->uar->index); - MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - + MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.frag_buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); @@ -1445,6 +1520,7 @@ 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 +1544,12 @@ 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 +1570,10 @@ 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 +1583,8 @@ 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 +1594,10 @@ 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: @@ -1532,7 +1608,6 @@ err_close_icosq_cq: err_napi_del: netif_napi_del(&c->napi); - napi_hash_del(&c->napi); kfree(c); return err; @@ -1553,9 +1628,6 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) mlx5e_close_cq(&c->icosq.cq); netif_napi_del(&c->napi); - napi_hash_del(&c->napi); - synchronize_rcu(); - kfree(c); } @@ -1648,7 +1720,7 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, } MLX5_SET(cqc, cqc, log_cq_size, log_cq_size); - if (priv->params.rx_cqe_compress) { + if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS)) { MLX5_SET(cqc, cqc, mini_cqe_res_format, MLX5_CQE_FORMAT_CSUM); MLX5_SET(cqc, cqc, cqe_comp_en, 1); } @@ -1971,9 +2043,7 @@ 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) @@ -2122,7 +2192,7 @@ int mlx5e_open_locked(struct net_device *netdev) goto err_clear_state_opened_flag; } - err = mlx5e_refresh_tirs_self_loopback_enable(priv->mdev); + err = mlx5e_refresh_tirs_self_loopback(priv->mdev, false); if (err) { netdev_err(netdev, "%s: mlx5e_refresh_tirs_self_loopback_enable failed, %d\n", __func__, err); @@ -2640,7 +2710,7 @@ mqprio: return mlx5e_setup_tc(dev, tc->tc); } -struct rtnl_link_stats64 * +static struct rtnl_link_stats64 * mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -2648,13 +2718,20 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; - stats->rx_packets = sstats->rx_packets; - stats->rx_bytes = sstats->rx_bytes; - stats->tx_packets = sstats->tx_packets; - stats->tx_bytes = sstats->tx_bytes; + if (mlx5e_is_uplink_rep(priv)) { + stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok); + stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok); + stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok); + stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok); + } else { + stats->rx_packets = sstats->rx_packets; + stats->rx_bytes = sstats->rx_bytes; + stats->tx_packets = sstats->tx_packets; + stats->tx_bytes = sstats->tx_bytes; + stats->tx_dropped = sstats->tx_queue_dropped; + } stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer; - stats->tx_dropped = sstats->tx_queue_dropped; stats->rx_length_errors = PPORT_802_3_GET(pstats, a_in_range_length_errors) + @@ -2851,31 +2928,13 @@ static int mlx5e_set_features(struct net_device *netdev, return err ? -EINVAL : 0; } -#define MXL5_HW_MIN_MTU 64 -#define MXL5E_MIN_MTU (MXL5_HW_MIN_MTU + ETH_FCS_LEN) - static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) { struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5_core_dev *mdev = priv->mdev; bool was_opened; - u16 max_mtu; - u16 min_mtu; int err = 0; bool reset; - mlx5_query_port_max_mtu(mdev, &max_mtu, 1); - - max_mtu = MLX5E_HW2SW_MTU(max_mtu); - min_mtu = MLX5E_HW2SW_MTU(MXL5E_MIN_MTU); - - if (new_mtu > max_mtu || new_mtu < min_mtu) { - netdev_err(netdev, - "%s: Bad MTU (%d), valid range is: [%d..%d]\n", - __func__, new_mtu, min_mtu, max_mtu); - return -EINVAL; - } - mutex_lock(&priv->state_lock); reset = !priv->params.lro_en && @@ -2945,6 +3004,20 @@ static int mlx5e_set_vf_trust(struct net_device *dev, int vf, bool setting) return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting); } + +static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, + int max_tx_rate) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_core_dev *mdev = priv->mdev; + + if (min_tx_rate) + return -EOPNOTSUPP; + + return mlx5_eswitch_set_vport_rate(mdev->priv.eswitch, vf + 1, + max_tx_rate); +} + static int mlx5_vport_link2ifla(u8 esw_link) { switch (esw_link) { @@ -3001,8 +3074,8 @@ static int mlx5e_get_vf_stats(struct net_device *dev, vf_stats); } -static void mlx5e_add_vxlan_port(struct net_device *netdev, - struct udp_tunnel_info *ti) +void mlx5e_add_vxlan_port(struct net_device *netdev, + struct udp_tunnel_info *ti) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3015,8 +3088,8 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev, mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1); } -static void mlx5e_del_vxlan_port(struct net_device *netdev, - struct udp_tunnel_info *ti) +void mlx5e_del_vxlan_port(struct net_device *netdev, + struct udp_tunnel_info *ti) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3093,7 +3166,7 @@ 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); } @@ -3110,6 +3183,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) bool reset, was_opened; int i; + if (prog && prog->xdp_adjust_head) { + netdev_err(netdev, "Does not support bpf_xdp_adjust_head()\n"); + return -EOPNOTSUPP; + } + mutex_lock(&priv->state_lock); if ((netdev->features & NETIF_F_LRO) && prog) { @@ -3124,11 +3202,21 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) if (was_opened && reset) mlx5e_close_locked(netdev); + if (was_opened && !reset) { + /* num_channels is invariant here, so we can take the + * batched reference right upfront. + */ + prog = bpf_prog_add(prog, priv->params.num_channels); + if (IS_ERR(prog)) { + err = PTR_ERR(prog); + goto unlock; + } + } - /* exchange programs */ + /* exchange programs, extra prog reference we got from caller + * as long as we don't fail from this point onwards. + */ old_prog = xchg(&priv->xdp_prog, prog); - if (prog) - bpf_prog_add(prog, 1); if (old_prog) bpf_prog_put(old_prog); @@ -3144,17 +3232,16 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) /* exchanging programs w/o reset, we update ref counts on behalf * of the channels RQs here. */ - bpf_prog_add(prog, priv->params.num_channels); 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); @@ -3252,6 +3339,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { .ndo_set_vf_vlan = mlx5e_set_vf_vlan, .ndo_set_vf_spoofchk = mlx5e_set_vf_spoofchk, .ndo_set_vf_trust = mlx5e_set_vf_trust, + .ndo_set_vf_rate = mlx5e_set_vf_rate, .ndo_get_vf_config = mlx5e_get_vf_config, .ndo_set_vf_link_state = mlx5e_set_vf_link_state, .ndo_get_vf_stats = mlx5e_get_vf_stats, @@ -3260,6 +3348,8 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = mlx5e_netpoll, #endif + .ndo_has_offload_stats = mlx5e_has_offload_stats, + .ndo_get_offload_stats = mlx5e_get_offload_stats, }; static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) @@ -3296,24 +3386,6 @@ u16 mlx5e_get_max_inline_cap(struct mlx5_core_dev *mdev) 2 /*sizeof(mlx5e_tx_wqe.inline_hdr_start)*/; } -#ifdef CONFIG_MLX5_CORE_EN_DCB -static void mlx5e_ets_init(struct mlx5e_priv *priv) -{ - int i; - - priv->params.ets.ets_cap = mlx5_max_tc(priv->mdev) + 1; - for (i = 0; i < priv->params.ets.ets_cap; i++) { - priv->params.ets.tc_tx_bw[i] = MLX5E_MAX_BW_ALLOC; - priv->params.ets.tc_tsa[i] = IEEE_8021QAZ_TSA_VENDOR; - priv->params.ets.prio_tc[i] = i; - } - - /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ - priv->params.ets.prio_tc[0] = 1; - priv->params.ets.prio_tc[1] = 0; -} -#endif - void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev, u32 *indirection_rqt, int len, int num_channels) @@ -3388,19 +3460,30 @@ static void mlx5e_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline_mode) { switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) { - case MLX5E_INLINE_MODE_L2: + case MLX5_CAP_INLINE_MODE_L2: *min_inline_mode = MLX5_INLINE_MODE_L2; break; - case MLX5E_INLINE_MODE_VPORT_CONTEXT: - mlx5_query_nic_vport_min_inline(mdev, - min_inline_mode); + case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: + mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode); break; - case MLX5_INLINE_MODE_NOT_REQUIRED: + case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: *min_inline_mode = MLX5_INLINE_MODE_NONE; break; } } +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, @@ -3419,20 +3502,22 @@ 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 */ - priv->params.rx_cqe_compress_admin = false; + priv->params.rx_cqe_compress_def = false; if (MLX5_CAP_GEN(mdev, cqe_compression) && MLX5_CAP_GEN(mdev, vport_group_manager)) { mlx5e_get_max_linkspeed(mdev, &link_speed); mlx5e_get_pci_bw(mdev, &pci_bw); mlx5_core_dbg(mdev, "Max link speed = %d, PCI BW = %d\n", link_speed, pci_bw); - priv->params.rx_cqe_compress_admin = + priv->params.rx_cqe_compress_def = cqe_compress_heuristic(link_speed, pci_bw); } - priv->params.rx_cqe_compress = priv->params.rx_cqe_compress_admin; mlx5e_set_rq_priv_params(priv); if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) @@ -3463,12 +3548,9 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /* Initialize pflags */ - MLX5E_SET_PRIV_FLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER, - priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE); - -#ifdef CONFIG_MLX5_CORE_EN_DCB - mlx5e_ets_init(priv); -#endif + MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_BASED_MODER, + priv->params.rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE); + MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, priv->params.rx_cqe_compress_def); mutex_init(&priv->state_lock); @@ -3506,7 +3588,8 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (MLX5_CAP_GEN(mdev, vport_group_manager)) { netdev->netdev_ops = &mlx5e_netdev_ops_sriov; #ifdef CONFIG_MLX5_CORE_EN_DCB - netdev->dcbnl_ops = &mlx5e_dcbnl_ops; + if (MLX5_CAP_GEN(mdev, qos)) + netdev->dcbnl_ops = &mlx5e_dcbnl_ops; #endif } else { netdev->netdev_ops = &mlx5e_netdev_ops_basic; @@ -3602,43 +3685,6 @@ static void mlx5e_destroy_q_counter(struct mlx5e_priv *priv) mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter); } -static int mlx5e_create_umr_mkey(struct mlx5e_priv *priv) -{ - struct mlx5_core_dev *mdev = priv->mdev; - u64 npages = MLX5E_REQUIRED_MTTS(priv->profile->max_nch(mdev), - BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW)); - int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); - void *mkc; - u32 *in; - int err; - - in = mlx5_vzalloc(inlen); - if (!in) - return -ENOMEM; - - mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); - - npages = min_t(u32, ALIGN(U16_MAX, 4) * 2, npages); - - MLX5_SET(mkc, mkc, free, 1); - MLX5_SET(mkc, mkc, umr_en, 1); - MLX5_SET(mkc, mkc, lw, 1); - MLX5_SET(mkc, mkc, lr, 1); - MLX5_SET(mkc, mkc, access_mode, MLX5_MKC_ACCESS_MODE_MTT); - - MLX5_SET(mkc, mkc, qpn, 0xffffff); - MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.pdn); - MLX5_SET64(mkc, mkc, len, npages << PAGE_SHIFT); - MLX5_SET(mkc, mkc, translations_octword_size, - MLX5_MTT_OCTW(npages)); - MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT); - - err = mlx5_core_create_mkey(mdev, &priv->umr_mkey, in, inlen); - - kvfree(in); - return err; -} - static void mlx5e_nic_init(struct mlx5_core_dev *mdev, struct net_device *netdev, const struct mlx5e_profile *profile, @@ -3660,6 +3706,9 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) if (MLX5_CAP_GEN(mdev, vport_group_manager)) mlx5_eswitch_unregister_vport_rep(esw, 0); + + if (priv->xdp_prog) + bpf_prog_put(priv->xdp_prog); } static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) @@ -3742,7 +3791,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) } #ifdef CONFIG_MLX5_CORE_EN_DCB - mlx5e_dcbnl_ieee_setets_core(priv, &priv->params.ets); + mlx5e_dcbnl_initialize(priv); #endif return 0; } @@ -3770,7 +3819,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) rep.load = mlx5e_nic_rep_load; rep.unload = mlx5e_nic_rep_unload; rep.vport = FDB_UPLINK_VPORT; - rep.priv_data = priv; + rep.netdev = netdev; mlx5_eswitch_register_vport_rep(esw, 0, &rep); } } @@ -3835,21 +3884,16 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) { const struct mlx5e_profile *profile; struct mlx5e_priv *priv; + u16 max_mtu; int err; priv = netdev_priv(netdev); profile = priv->profile; clear_bit(MLX5E_STATE_DESTROYING, &priv->state); - err = mlx5e_create_umr_mkey(priv); - if (err) { - mlx5_core_err(mdev, "create umr mkey failed, %d\n", err); - goto out; - } - err = profile->init_tx(priv); if (err) - goto err_destroy_umr_mkey; + goto out; err = mlx5e_open_drop_rq(priv); if (err) { @@ -3865,6 +3909,11 @@ int mlx5e_attach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) mlx5e_init_l2_addr(priv); + /* MTU range: 68 - hw-specific max */ + netdev->min_mtu = ETH_MIN_MTU; + mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1); + netdev->max_mtu = MLX5E_HW2SW_MTU(max_mtu); + mlx5e_set_dev_port_mtu(netdev); if (profile->enable) @@ -3884,9 +3933,6 @@ err_close_drop_rq: err_cleanup_tx: profile->cleanup_tx(priv); -err_destroy_umr_mkey: - mlx5_core_destroy_mkey(mdev, &priv->umr_mkey); - out: return err; } @@ -3935,7 +3981,6 @@ void mlx5e_detach_netdev(struct mlx5_core_dev *mdev, struct net_device *netdev) profile->cleanup_rx(priv); mlx5e_close_drop_rq(priv); profile->cleanup_tx(priv); - mlx5_core_destroy_mkey(priv->mdev, &priv->umr_mkey); cancel_delayed_work_sync(&priv->update_stats_work); } @@ -4035,7 +4080,6 @@ 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 +4096,7 @@ 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..850378893b25 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -72,7 +72,29 @@ static void mlx5e_rep_get_strings(struct net_device *dev, } } -static void mlx5e_update_sw_rep_counters(struct mlx5e_priv *priv) +static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_eswitch_rep *rep = priv->ppriv; + struct rtnl_link_stats64 *vport_stats; + struct ifla_vf_stats vf_stats; + int err; + + err = mlx5_eswitch_get_vport_stats(esw, rep->vport, &vf_stats); + if (err) { + pr_warn("vport %d error %d reading stats\n", rep->vport, err); + return; + } + + vport_stats = &priv->stats.vf_vport; + /* flip tx/rx as we are reporting the counters for the switch vport */ + vport_stats->rx_packets = vf_stats.tx_packets; + vport_stats->rx_bytes = vf_stats.tx_bytes; + vport_stats->tx_packets = vf_stats.rx_packets; + vport_stats->tx_bytes = vf_stats.rx_bytes; +} + +static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv) { struct mlx5e_sw_stats *s = &priv->stats.sw; struct mlx5e_rq_stats *rq_stats; @@ -95,6 +117,12 @@ static void mlx5e_update_sw_rep_counters(struct mlx5e_priv *priv) } } +static void mlx5e_rep_update_stats(struct mlx5e_priv *priv) +{ + mlx5e_rep_update_sw_counters(priv); + mlx5e_rep_update_hw_counters(priv); +} + static void mlx5e_rep_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { @@ -106,7 +134,7 @@ static void mlx5e_rep_get_ethtool_stats(struct net_device *dev, mutex_lock(&priv->state_lock); if (test_bit(MLX5E_STATE_OPENED, &priv->state)) - mlx5e_update_sw_rep_counters(priv); + mlx5e_rep_update_sw_counters(priv); mutex_unlock(&priv->state_lock); for (i = 0; i < NUM_VPORT_REP_COUNTERS; i++) @@ -180,7 +208,8 @@ int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) int mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = rep->priv_data; + struct net_device *netdev = rep->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); if (test_bit(MLX5E_STATE_OPENED, &priv->state)) return mlx5e_add_sqs_fwd_rules(priv); @@ -198,7 +227,8 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = rep->priv_data; + struct net_device *netdev = rep->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); if (test_bit(MLX5E_STATE_OPENED, &priv->state)) mlx5e_remove_sqs_fwd_rules(priv); @@ -208,6 +238,35 @@ void mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, mlx5e_tc_init(priv); } +static int mlx5e_rep_open(struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_eswitch_rep *rep = priv->ppriv; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + int err; + + err = mlx5e_open(dev); + if (err) + return err; + + err = mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP); + if (!err) + netif_carrier_on(dev); + + return 0; +} + +static int mlx5e_rep_close(struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5_eswitch_rep *rep = priv->ppriv; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + (void)mlx5_eswitch_set_vport_state(esw, rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN); + + return mlx5e_close(dev); +} + static int mlx5e_rep_get_phys_port_name(struct net_device *dev, char *buf, size_t len) { @@ -230,6 +289,14 @@ static int mlx5e_rep_ndo_setup_tc(struct net_device *dev, u32 handle, if (TC_H_MAJ(handle) != TC_H_MAJ(TC_H_INGRESS)) return -EOPNOTSUPP; + if (tc->egress_dev) { + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct net_device *uplink_dev = mlx5_eswitch_get_uplink_netdev(esw); + + return uplink_dev->netdev_ops->ndo_setup_tc(uplink_dev, handle, + proto, tc); + } + switch (tc->type) { case TC_SETUP_CLSFLOWER: switch (tc->cls_flower->command) { @@ -245,17 +312,92 @@ static int mlx5e_rep_ndo_setup_tc(struct net_device *dev, u32 handle, } } +bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + if (rep && rep->vport == FDB_UPLINK_VPORT && esw->mode == SRIOV_OFFLOADS) + return true; + + return false; +} + +bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv) +{ + struct mlx5_eswitch_rep *rep = (struct mlx5_eswitch_rep *)priv->ppriv; + + if (rep && rep->vport != FDB_UPLINK_VPORT) + return true; + + return false; +} + +bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + switch (attr_id) { + case IFLA_OFFLOAD_XSTATS_CPU_HIT: + if (mlx5e_is_vf_vport_rep(priv) || mlx5e_is_uplink_rep(priv)) + return true; + } + + return false; +} + +static int +mlx5e_get_sw_stats64(const struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_sw_stats *sstats = &priv->stats.sw; + + stats->rx_packets = sstats->rx_packets; + stats->rx_bytes = sstats->rx_bytes; + stats->tx_packets = sstats->tx_packets; + stats->tx_bytes = sstats->tx_bytes; + + stats->tx_dropped = sstats->tx_queue_dropped; + + return 0; +} + +int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, + void *sp) +{ + switch (attr_id) { + case IFLA_OFFLOAD_XSTATS_CPU_HIT: + return mlx5e_get_sw_stats64(dev, sp); + } + + return -EINVAL; +} + +static struct rtnl_link_stats64 * +mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + memcpy(stats, &priv->stats.vf_vport, sizeof(*stats)); + return stats; +} + static const struct switchdev_ops mlx5e_rep_switchdev_ops = { .switchdev_port_attr_get = mlx5e_attr_get, }; static const struct net_device_ops mlx5e_netdev_ops_rep = { - .ndo_open = mlx5e_open, - .ndo_stop = mlx5e_close, + .ndo_open = mlx5e_rep_open, + .ndo_stop = mlx5e_rep_close, .ndo_start_xmit = mlx5e_xmit, .ndo_get_phys_port_name = mlx5e_rep_get_phys_port_name, .ndo_setup_tc = mlx5e_rep_ndo_setup_tc, - .ndo_get_stats64 = mlx5e_get_stats, + .ndo_get_stats64 = mlx5e_rep_get_stats, + .ndo_udp_tunnel_add = mlx5e_add_vxlan_port, + .ndo_udp_tunnel_del = mlx5e_del_vxlan_port, + .ndo_has_offload_stats = mlx5e_has_offload_stats, + .ndo_get_offload_stats = mlx5e_get_offload_stats, }; static void mlx5e_build_rep_netdev_priv(struct mlx5_core_dev *mdev, @@ -308,7 +450,7 @@ 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); @@ -328,7 +470,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_eswitch_rep *rep = priv->ppriv; struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5_flow_rule *flow_rule; + struct mlx5_flow_handle *flow_rule; int err; int i; @@ -360,7 +502,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) return 0; err_del_flow_rule: - mlx5_del_flow_rule(rep->vport_rx_rule); + mlx5_del_flow_rules(rep->vport_rx_rule); err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_direct_rqts: @@ -375,7 +517,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) int i; mlx5e_tc_cleanup(priv); - mlx5_del_flow_rule(rep->vport_rx_rule); + mlx5_del_flow_rules(rep->vport_rx_rule); mlx5e_destroy_direct_tirs(priv); for (i = 0; i < priv->params.num_channels; i++) mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt); @@ -405,7 +547,7 @@ static struct mlx5e_profile mlx5e_rep_profile = { .cleanup_rx = mlx5e_cleanup_rep_rx, .init_tx = mlx5e_init_rep_tx, .cleanup_tx = mlx5e_cleanup_nic_tx, - .update_stats = mlx5e_update_sw_rep_counters, + .update_stats = mlx5e_rep_update_stats, .max_nch = mlx5e_get_rep_max_num_channels, .max_tc = 1, }; @@ -423,7 +565,7 @@ int mlx5e_vport_rep_load(struct mlx5_eswitch *esw, return -EINVAL; } - rep->priv_data = netdev_priv(netdev); + rep->netdev = netdev; err = mlx5e_attach_netdev(esw->dev, netdev); if (err) { @@ -445,7 +587,7 @@ err_detach_netdev: mlx5e_detach_netdev(esw->dev, netdev); err_destroy_netdev: - mlx5e_destroy_netdev(esw->dev, rep->priv_data); + mlx5e_destroy_netdev(esw->dev, netdev_priv(netdev)); return err; @@ -454,9 +596,9 @@ err_destroy_netdev: void mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = rep->priv_data; - struct net_device *netdev = priv->netdev; + struct net_device *netdev = rep->netdev; + unregister_netdev(netdev); mlx5e_detach_netdev(esw->dev, netdev); - mlx5e_destroy_netdev(esw->dev, priv); + mlx5e_destroy_netdev(esw->dev, netdev_priv(netdev)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index c6de6fba5843..0e2fb3ed1790 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -164,14 +164,14 @@ void mlx5e_modify_rx_cqe_compression(struct mlx5e_priv *priv, bool val) mutex_lock(&priv->state_lock); - if (priv->params.rx_cqe_compress == val) + if (MLX5E_GET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS) == val) goto unlock; was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state); if (was_opened) mlx5e_close_locked(priv->netdev); - priv->params.rx_cqe_compress = val; + MLX5E_SET_PFLAG(priv, MLX5E_PFLAG_RX_CQE_COMPRESS, val); if (was_opened) mlx5e_open_locked(priv->netdev); @@ -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) @@ -737,10 +737,10 @@ static inline struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, u16 wqe_counter, u32 cqe_bcnt) { - struct bpf_prog *xdp_prog = READ_ONCE(rq->xdp_prog); struct mlx5e_dma_info *di; struct sk_buff *skb; void *va, *data; + bool consumed; di = &rq->dma_info[wqe_counter]; va = page_address(di->page); @@ -759,7 +759,11 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, return NULL; } - if (mlx5e_xdp_handle(rq, xdp_prog, di, data, cqe_bcnt)) + rcu_read_lock(); + consumed = mlx5e_xdp_handle(rq, READ_ONCE(rq->xdp_prog), di, data, + cqe_bcnt); + rcu_read_unlock(); + if (consumed) return NULL; /* page/packet was consumed by XDP */ skb = build_skb(va, RQ_PAGE_SIZE(rq)); @@ -924,7 +928,7 @@ 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_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c new file mode 100644 index 000000000000..65442c36a6e1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -0,0 +1,352 @@ +/* + * Copyright (c) 2016, Mellanox Technologies, Ltd. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <linux/ip.h> +#include <linux/udp.h> +#include <net/udp.h> +#include "en.h" + +enum { + MLX5E_ST_LINK_STATE, + MLX5E_ST_LINK_SPEED, + MLX5E_ST_HEALTH_INFO, +#ifdef CONFIG_INET + MLX5E_ST_LOOPBACK, +#endif + MLX5E_ST_NUM, +}; + +const char mlx5e_self_tests[MLX5E_ST_NUM][ETH_GSTRING_LEN] = { + "Link Test", + "Speed Test", + "Health Test", +#ifdef CONFIG_INET + "Loopback Test", +#endif +}; + +int mlx5e_self_test_num(struct mlx5e_priv *priv) +{ + return ARRAY_SIZE(mlx5e_self_tests); +} + +static int mlx5e_test_health_info(struct mlx5e_priv *priv) +{ + struct mlx5_core_health *health = &priv->mdev->priv.health; + + return health->sick ? 1 : 0; +} + +static int mlx5e_test_link_state(struct mlx5e_priv *priv) +{ + u8 port_state; + + if (!netif_carrier_ok(priv->netdev)) + return 1; + + port_state = mlx5_query_vport_state(priv->mdev, MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0); + return port_state == VPORT_STATE_UP ? 0 : 1; +} + +static int mlx5e_test_link_speed(struct mlx5e_priv *priv) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + u32 eth_proto_oper; + int i; + + if (!netif_carrier_ok(priv->netdev)) + return 1; + + if (mlx5_query_port_ptys(priv->mdev, out, sizeof(out), MLX5_PTYS_EN, 1)) + return 1; + + eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); + for (i = 0; i < MLX5E_LINK_MODES_NUMBER; i++) { + if (eth_proto_oper & MLX5E_PROT_MASK(i)) + return 0; + } + return 1; +} + +#ifdef CONFIG_INET +/* loopback test */ +#define MLX5E_TEST_PKT_SIZE (MLX5_MPWRQ_SMALL_PACKET_THRESHOLD - NET_IP_ALIGN) +static const char mlx5e_test_text[ETH_GSTRING_LEN] = "MLX5E SELF TEST"; +#define MLX5E_TEST_MAGIC 0x5AEED15C001ULL + +struct mlx5ehdr { + __be32 version; + __be64 magic; + char text[ETH_GSTRING_LEN]; +}; + +static struct sk_buff *mlx5e_test_get_udp_skb(struct mlx5e_priv *priv) +{ + struct sk_buff *skb = NULL; + struct mlx5ehdr *mlxh; + struct ethhdr *ethh; + struct udphdr *udph; + struct iphdr *iph; + int datalen, iplen; + + datalen = MLX5E_TEST_PKT_SIZE - + (sizeof(*ethh) + sizeof(*iph) + sizeof(*udph)); + + skb = netdev_alloc_skb(priv->netdev, MLX5E_TEST_PKT_SIZE); + if (!skb) { + netdev_err(priv->netdev, "\tFailed to alloc loopback skb\n"); + return NULL; + } + + prefetchw(skb->data); + skb_reserve(skb, NET_IP_ALIGN); + + /* Reserve for ethernet and IP header */ + ethh = (struct ethhdr *)skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + + skb_set_network_header(skb, skb->len); + iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); + + /* Fill ETH header */ + ether_addr_copy(ethh->h_dest, priv->netdev->dev_addr); + eth_zero_addr(ethh->h_source); + ethh->h_proto = htons(ETH_P_IP); + + /* Fill UDP header */ + udph->source = htons(9); + udph->dest = htons(9); /* Discard Protocol */ + udph->len = htons(datalen + sizeof(struct udphdr)); + udph->check = 0; + + /* Fill IP header */ + iph->ihl = 5; + iph->ttl = 32; + iph->version = 4; + iph->protocol = IPPROTO_UDP; + iplen = sizeof(struct iphdr) + sizeof(struct udphdr) + datalen; + iph->tot_len = htons(iplen); + iph->frag_off = 0; + iph->saddr = 0; + iph->daddr = 0; + iph->tos = 0; + iph->id = 0; + ip_send_check(iph); + + /* Fill test header and data */ + mlxh = (struct mlx5ehdr *)skb_put(skb, sizeof(*mlxh)); + mlxh->version = 0; + mlxh->magic = cpu_to_be64(MLX5E_TEST_MAGIC); + strlcpy(mlxh->text, mlx5e_test_text, sizeof(mlxh->text)); + datalen -= sizeof(*mlxh); + memset(skb_put(skb, datalen), 0, datalen); + + skb->csum = 0; + skb->ip_summed = CHECKSUM_PARTIAL; + udp4_hwcsum(skb, iph->saddr, iph->daddr); + + skb->protocol = htons(ETH_P_IP); + skb->pkt_type = PACKET_HOST; + skb->dev = priv->netdev; + + return skb; +} + +struct mlx5e_lbt_priv { + struct packet_type pt; + struct completion comp; + bool loopback_ok; +}; + +static int +mlx5e_test_loopback_validate(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt, + struct net_device *orig_ndev) +{ + struct mlx5e_lbt_priv *lbtp = pt->af_packet_priv; + struct mlx5ehdr *mlxh; + struct ethhdr *ethh; + struct udphdr *udph; + struct iphdr *iph; + + /* We are only going to peek, no need to clone the SKB */ + if (skb->protocol != htons(ETH_P_IP)) + goto out; + + if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb)) + goto out; + + ethh = (struct ethhdr *)skb_mac_header(skb); + if (!ether_addr_equal(ethh->h_dest, orig_ndev->dev_addr)) + goto out; + + iph = ip_hdr(skb); + if (iph->protocol != IPPROTO_UDP) + goto out; + + udph = udp_hdr(skb); + if (udph->dest != htons(9)) + goto out; + + mlxh = (struct mlx5ehdr *)((char *)udph + sizeof(*udph)); + if (mlxh->magic != cpu_to_be64(MLX5E_TEST_MAGIC)) + goto out; /* so close ! */ + + /* bingo */ + lbtp->loopback_ok = true; + complete(&lbtp->comp); +out: + kfree_skb(skb); + return 0; +} + +static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, + struct mlx5e_lbt_priv *lbtp) +{ + int err = 0; + + err = mlx5e_refresh_tirs_self_loopback(priv->mdev, true); + if (err) { + netdev_err(priv->netdev, + "\tFailed to enable UC loopback err(%d)\n", err); + return err; + } + + lbtp->loopback_ok = false; + init_completion(&lbtp->comp); + + lbtp->pt.type = htons(ETH_P_ALL); + lbtp->pt.func = mlx5e_test_loopback_validate; + lbtp->pt.dev = priv->netdev; + lbtp->pt.af_packet_priv = lbtp; + dev_add_pack(&lbtp->pt); + return err; +} + +static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv, + struct mlx5e_lbt_priv *lbtp) +{ + dev_remove_pack(&lbtp->pt); + mlx5e_refresh_tirs_self_loopback(priv->mdev, false); +} + +#define MLX5E_LB_VERIFY_TIMEOUT (msecs_to_jiffies(200)) +static int mlx5e_test_loopback(struct mlx5e_priv *priv) +{ + struct mlx5e_lbt_priv *lbtp; + struct sk_buff *skb = NULL; + int err; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + netdev_err(priv->netdev, + "\tCan't perform loobpack test while device is down\n"); + return -ENODEV; + } + + lbtp = kzalloc(sizeof(*lbtp), GFP_KERNEL); + if (!lbtp) + return -ENOMEM; + lbtp->loopback_ok = false; + + err = mlx5e_test_loopback_setup(priv, lbtp); + if (err) + goto out; + + skb = mlx5e_test_get_udp_skb(priv); + if (!skb) { + err = -ENOMEM; + goto cleanup; + } + + skb_set_queue_mapping(skb, 0); + err = dev_queue_xmit(skb); + if (err) { + netdev_err(priv->netdev, + "\tFailed to xmit loopback packet err(%d)\n", + err); + goto cleanup; + } + + wait_for_completion_timeout(&lbtp->comp, MLX5E_LB_VERIFY_TIMEOUT); + err = !lbtp->loopback_ok; + +cleanup: + mlx5e_test_loopback_cleanup(priv, lbtp); +out: + kfree(lbtp); + return err; +} +#endif + +static int (*mlx5e_st_func[MLX5E_ST_NUM])(struct mlx5e_priv *) = { + mlx5e_test_link_state, + mlx5e_test_link_speed, + mlx5e_test_health_info, +#ifdef CONFIG_INET + mlx5e_test_loopback, +#endif +}; + +void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, + u64 *buf) +{ + struct mlx5e_priv *priv = netdev_priv(ndev); + int i; + + memset(buf, 0, sizeof(u64) * MLX5E_ST_NUM); + + mutex_lock(&priv->state_lock); + netdev_info(ndev, "Self test begin..\n"); + + for (i = 0; i < MLX5E_ST_NUM; i++) { + netdev_info(ndev, "\t[%d] %s start..\n", + i, mlx5e_self_tests[i]); + buf[i] = mlx5e_st_func[i](priv); + netdev_info(ndev, "\t[%d] %s end: result(%lld)\n", + i, mlx5e_self_tests[i], buf[i]); + } + + mutex_unlock(&priv->state_lock); + + for (i = 0; i < MLX5E_ST_NUM; i++) { + if (buf[i]) { + etest->flags |= ETH_TEST_FL_FAILED; + break; + } + } + netdev_info(ndev, "Self test out: status flags(0x%x)\n", + etest->flags); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 57452fdc5154..f202f872f57f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -39,7 +39,7 @@ #define MLX5E_READ_CTR32_CPU(ptr, dsc, i) \ (*(u32 *)((char *)ptr + dsc[i].offset)) #define MLX5E_READ_CTR32_BE(ptr, dsc, i) \ - be64_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset)) + be32_to_cpu(*(__be32 *)((char *)ptr + dsc[i].offset)) #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld) #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld) @@ -276,6 +276,32 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = { { "rx_%s_pause_transition", PPORT_PER_PRIO_OFF(rx_pause_transition) }, }; +#define PCIE_PERF_OFF(c) \ + MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_perf_cntrs_grp_data_layout.c) +#define PCIE_PERF_GET(pcie_stats, c) \ + MLX5_GET(mpcnt_reg, pcie_stats->pcie_perf_counters, \ + counter_set.pcie_perf_cntrs_grp_data_layout.c) +#define PCIE_TAS_OFF(c) \ + MLX5_BYTE_OFF(mpcnt_reg, counter_set.pcie_tas_cntrs_grp_data_layout.c) +#define PCIE_TAS_GET(pcie_stats, c) \ + MLX5_GET(mpcnt_reg, pcie_stats->pcie_tas_counters, \ + counter_set.pcie_tas_cntrs_grp_data_layout.c) + +struct mlx5e_pcie_stats { + __be64 pcie_perf_counters[MLX5_ST_SZ_QW(mpcnt_reg)]; + __be64 pcie_tas_counters[MLX5_ST_SZ_QW(mpcnt_reg)]; +}; + +static const struct counter_desc pcie_perf_stats_desc[] = { + { "rx_pci_signal_integrity", PCIE_PERF_OFF(rx_errors) }, + { "tx_pci_signal_integrity", PCIE_PERF_OFF(tx_errors) }, +}; + +static const struct counter_desc pcie_tas_stats_desc[] = { + { "tx_pci_transport_nonfatal_msg", PCIE_TAS_OFF(non_fatal_err_msg_sent) }, + { "tx_pci_transport_fatal_msg", PCIE_TAS_OFF(fatal_err_msg_sent) }, +}; + struct mlx5e_rq_stats { u64 packets; u64 bytes; @@ -360,6 +386,8 @@ static const struct counter_desc sq_stats_desc[] = { #define NUM_PPORT_802_3_COUNTERS ARRAY_SIZE(pport_802_3_stats_desc) #define NUM_PPORT_2863_COUNTERS ARRAY_SIZE(pport_2863_stats_desc) #define NUM_PPORT_2819_COUNTERS ARRAY_SIZE(pport_2819_stats_desc) +#define NUM_PCIE_PERF_COUNTERS ARRAY_SIZE(pcie_perf_stats_desc) +#define NUM_PCIE_TAS_COUNTERS ARRAY_SIZE(pcie_tas_stats_desc) #define NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS \ ARRAY_SIZE(pport_per_prio_traffic_stats_desc) #define NUM_PPORT_PER_PRIO_PFC_COUNTERS \ @@ -369,6 +397,7 @@ static const struct counter_desc sq_stats_desc[] = { NUM_PPORT_2819_COUNTERS + \ NUM_PPORT_PER_PRIO_TRAFFIC_COUNTERS * \ NUM_PPORT_PRIO) +#define NUM_PCIE_COUNTERS (NUM_PCIE_PERF_COUNTERS + NUM_PCIE_TAS_COUNTERS) #define NUM_RQ_STATS ARRAY_SIZE(rq_stats_desc) #define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc) @@ -377,6 +406,25 @@ struct mlx5e_stats { struct mlx5e_qcounter_stats qcnt; struct mlx5e_vport_stats vport; struct mlx5e_pport_stats pport; + struct mlx5e_pcie_stats pcie; + struct rtnl_link_stats64 vf_vport; +}; + +static const struct counter_desc mlx5e_pme_status_desc[] = { + { "module_plug", 0 }, + { "module_unplug", 8 }, +}; + +static const struct counter_desc mlx5e_pme_error_desc[] = { + { "module_pwr_budget_exd", 0 }, /* power budget exceed */ + { "module_long_range", 8 }, /* long range for non MLNX cable */ + { "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */ + { "module_no_eeprom", 24 }, /* no eeprom/retry time out */ + { "module_enforce_part", 32 }, /* enforce part number list */ + { "module_unknown_id", 40 }, /* unknown identifier */ + { "module_high_temp", 48 }, /* high temperature */ + { "module_bad_shorted", 56 }, /* bad or shorted cable/module */ + { "module_unknown_status", 64 }, }; #endif /* __MLX5_EN_STATS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ce8c54d18906..f8829b517156 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -31,6 +31,7 @@ */ #include <net/flow_dissector.h> +#include <net/sch_generic.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_skbedit.h> @@ -40,28 +41,43 @@ #include <net/switchdev.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_vlan.h> +#include <net/tc_act/tc_tunnel_key.h> +#include <net/vxlan.h> #include "en.h" #include "en_tc.h" #include "eswitch.h" +#include "vxlan.h" struct mlx5e_tc_flow { struct rhash_head node; u64 cookie; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; + struct list_head encap; /* flows sharing the same encap */ struct mlx5_esw_flow_attr *attr; }; +enum { + MLX5_HEADER_TYPE_VXLAN = 0x0, + MLX5_HEADER_TYPE_NVGRE = 0x1, +}; + #define MLX5E_TC_TABLE_NUM_ENTRIES 1024 #define MLX5E_TC_TABLE_NUM_GROUPS 4 -static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - u32 action, u32 flow_tag) +static struct mlx5_flow_handle * +mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + u32 action, u32 flow_tag) { struct mlx5_core_dev *dev = priv->mdev; struct mlx5_flow_destination dest = { 0 }; + struct mlx5_flow_act flow_act = { + .action = action, + .flow_tag = flow_tag, + .encap_id = 0, + }; struct mlx5_fc *counter = NULL; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; bool table_created = false; if (action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { @@ -82,7 +98,7 @@ static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, MLX5E_TC_PRIO, MLX5E_TC_TABLE_NUM_ENTRIES, MLX5E_TC_TABLE_NUM_GROUPS, - 0); + 0, 0); if (IS_ERR(priv->fs.tc.t)) { netdev_err(priv->netdev, "Failed to create tc offload table\n"); @@ -94,9 +110,7 @@ static struct mlx5_flow_rule *mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, } spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; - rule = mlx5_add_flow_rule(priv->fs.tc.t, spec, - action, flow_tag, - &dest); + rule = mlx5_add_flow_rules(priv->fs.tc.t, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) goto err_add_rule; @@ -114,9 +128,10 @@ err_create_ft: return rule; } -static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct mlx5_esw_flow_attr *attr) +static struct mlx5_flow_handle * +mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct mlx5_esw_flow_attr *attr) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int err; @@ -128,19 +143,39 @@ static struct mlx5_flow_rule *mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, return mlx5_eswitch_add_offloaded_rule(esw, spec, attr); } +static void mlx5e_detach_encap(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow) { + struct list_head *next = flow->encap.next; + + list_del(&flow->encap); + if (list_empty(next)) { + struct mlx5_encap_entry *e; + + e = list_entry(next, struct mlx5_encap_entry, flows); + if (e->n) { + mlx5_encap_dealloc(priv->mdev, e->encap_id); + neigh_release(e->n); + } + hlist_del_rcu(&e->encap_hlist); + kfree(e); + } +} + static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, - struct mlx5_flow_rule *rule, - struct mlx5_esw_flow_attr *attr) + struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_fc *counter = NULL; - counter = mlx5_flow_rule_counter(rule); + counter = mlx5_flow_rule_counter(flow->rule); - if (esw && esw->mode == SRIOV_OFFLOADS) - mlx5_eswitch_del_vlan_action(esw, attr); + mlx5_del_flow_rules(flow->rule); - mlx5_del_flow_rule(rule); + if (esw && esw->mode == SRIOV_OFFLOADS) { + mlx5_eswitch_del_vlan_action(esw, flow->attr); + if (flow->attr->action & MLX5_FLOW_CONTEXT_ACTION_ENCAP) + mlx5e_detach_encap(priv, flow); + } mlx5_fc_destroy(priv->mdev, counter); @@ -150,8 +185,125 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, } } -static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, - struct tc_cls_flower_offload *f) +static void parse_vxlan_attr(struct mlx5_flow_spec *spec, + struct tc_cls_flower_offload *f) +{ + void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + outer_headers); + void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers); + void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + misc_parameters); + void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters); + + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP); + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_dissector_key_keyid *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->key); + struct flow_dissector_key_keyid *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_KEYID, + f->mask); + MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni, + be32_to_cpu(mask->keyid)); + MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, + be32_to_cpu(key->keyid)); + } +} + +static int parse_tunnel_attr(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct tc_cls_flower_offload *f) +{ + void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + outer_headers); + void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, + outer_headers); + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { + struct flow_dissector_key_ports *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + f->key); + struct flow_dissector_key_ports *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_PORTS, + f->mask); + + /* Full udp dst port must be given */ + if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) + return -EOPNOTSUPP; + + /* udp src port isn't supported */ + if (memchr_inv(&mask->src, 0, sizeof(mask->src))) + return -EOPNOTSUPP; + + if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->dst)) && + MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) + parse_vxlan_attr(spec, f); + else + return -EOPNOTSUPP; + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + udp_dport, ntohs(mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + udp_dport, ntohs(key->dst)); + + } else { /* udp dst port must be given */ + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_dissector_key_ipv4_addrs *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, + f->key); + struct flow_dissector_key_ipv4_addrs *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, + f->mask); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + src_ipv4_src_ipv6.ipv4_layout.ipv4, + ntohl(mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + src_ipv4_src_ipv6.ipv4_layout.ipv4, + ntohl(key->src)); + + MLX5_SET(fte_match_set_lyr_2_4, headers_c, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4, + ntohl(mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, + dst_ipv4_dst_ipv6.ipv4_layout.ipv4, + ntohl(key->dst)); + } + + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); + + /* Enforce DMAC when offloading incoming tunneled flows. + * Flow counters require a match on the DMAC. + */ + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, dmac_47_16); + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, dmac_15_0); + ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, + dmac_47_16), priv->netdev->dev_addr); + + /* let software handle IP fragments */ + MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, 0); + + return 0; +} + +static int __parse_cls_flower(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct tc_cls_flower_offload *f, + u8 *min_inline) { void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); @@ -160,6 +312,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec u16 addr_type = 0; u8 ip_proto = 0; + *min_inline = MLX5_INLINE_MODE_L2; + if (f->dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | @@ -167,18 +321,61 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec BIT(FLOW_DISSECTOR_KEY_VLAN) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS))) { + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | + BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | + BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL))) { netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", f->dissector->used_keys); return -EOPNOTSUPP; } + if ((dissector_uses_key(f->dissector, + FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) || + dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) || + dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) && + dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_dissector_key_control *key = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL, + f->key); + switch (key->addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + if (parse_tunnel_attr(priv, spec, f)) + return -EOPNOTSUPP; + break; + default: + return -EOPNOTSUPP; + } + + /* In decap flow, header pointers should point to the inner + * headers, outer header were already set by parse_tunnel_attr + */ + headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + inner_headers); + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, + inner_headers); + } + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_dissector_key_control *key = skb_flow_dissector_target(f->dissector, FLOW_DISSECTOR_KEY_CONTROL, f->key); + + struct flow_dissector_key_control *mask = + skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_CONTROL, + f->mask); addr_type = key->addr_type; + + if (mask->flags & FLOW_DIS_IS_FRAGMENT) { + MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, + key->flags & FLOW_DIS_IS_FRAGMENT); + } } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { @@ -201,6 +398,9 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec mask->ip_proto); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, key->ip_proto); + + if (mask->ip_proto) + *min_inline = MLX5_INLINE_MODE_IP; } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { @@ -237,12 +437,15 @@ 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); } } @@ -268,6 +471,9 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), &key->dst, sizeof(key->dst)); + + if (mask->src || mask->dst) + *min_inline = MLX5_INLINE_MODE_IP; } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { @@ -293,6 +499,10 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), &key->dst, sizeof(key->dst)); + + if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY || + ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY) + *min_inline = MLX5_INLINE_MODE_IP; } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { @@ -333,11 +543,39 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec "Only UDP and TCP transport are supported\n"); return -EINVAL; } + + if (mask->src || mask->dst) + *min_inline = MLX5_INLINE_MODE_TCP_UDP; } return 0; } +static int parse_cls_flower(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct tc_cls_flower_offload *f) +{ + struct mlx5_core_dev *dev = priv->mdev; + struct mlx5_eswitch *esw = dev->priv.eswitch; + struct mlx5_eswitch_rep *rep = priv->ppriv; + u8 min_inline; + int err; + + err = __parse_cls_flower(priv, spec, f, &min_inline); + + if (!err && esw->mode == SRIOV_OFFLOADS && + rep->vport != FDB_UPLINK_VPORT) { + if (min_inline > esw->offloads.inline_mode) { + netdev_warn(priv->netdev, + "Flow is not offloaded due to min inline setting, required %d actual %d\n", + min_inline, esw->offloads.inline_mode); + return -EOPNOTSUPP; + } + } + + return err; +} + static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, u32 *action, u32 *flow_tag) { @@ -384,11 +622,243 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, return 0; } +static inline int cmp_encap_info(struct mlx5_encap_info *a, + struct mlx5_encap_info *b) +{ + return memcmp(a, b, sizeof(*a)); +} + +static inline int hash_encap_info(struct mlx5_encap_info *info) +{ + return jhash(info, sizeof(*info), 0); +} + +static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct flowi4 *fl4, + struct neighbour **out_n, + __be32 *saddr, + int *out_ttl) +{ + struct rtable *rt; + struct neighbour *n = NULL; + int ttl; + +#if IS_ENABLED(CONFIG_INET) + rt = ip_route_output_key(dev_net(mirred_dev), fl4); + if (IS_ERR(rt)) { + pr_warn("%s: no route to %pI4\n", __func__, &fl4->daddr); + return -EOPNOTSUPP; + } +#else + return -EOPNOTSUPP; +#endif + + if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) { + pr_warn("%s: Can't offload the flow, netdevices aren't on the same HW e-switch\n", + __func__); + ip_rt_put(rt); + return -EOPNOTSUPP; + } + + ttl = ip4_dst_hoplimit(&rt->dst); + n = dst_neigh_lookup(&rt->dst, &fl4->daddr); + ip_rt_put(rt); + if (!n) + return -ENOMEM; + + *out_n = n; + *saddr = fl4->saddr; + *out_ttl = ttl; + *out_dev = rt->dst.dev; + + return 0; +} + +static int gen_vxlan_header_ipv4(struct net_device *out_dev, + char buf[], + unsigned char h_dest[ETH_ALEN], + int ttl, + __be32 daddr, + __be32 saddr, + __be16 udp_dst_port, + __be32 vx_vni) +{ + int encap_size = VXLAN_HLEN + sizeof(struct iphdr) + ETH_HLEN; + struct ethhdr *eth = (struct ethhdr *)buf; + struct iphdr *ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr)); + struct udphdr *udp = (struct udphdr *)((char *)ip + sizeof(struct iphdr)); + struct vxlanhdr *vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr)); + + memset(buf, 0, encap_size); + + ether_addr_copy(eth->h_dest, h_dest); + ether_addr_copy(eth->h_source, out_dev->dev_addr); + eth->h_proto = htons(ETH_P_IP); + + ip->daddr = daddr; + ip->saddr = saddr; + + ip->ttl = ttl; + ip->protocol = IPPROTO_UDP; + ip->version = 0x4; + ip->ihl = 0x5; + + udp->dest = udp_dst_port; + vxh->vx_flags = VXLAN_HF_VNI; + vxh->vx_vni = vxlan_vni_field(vx_vni); + + return encap_size; +} + +static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct mlx5_encap_entry *e, + struct net_device **out_dev) +{ + int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); + struct flowi4 fl4 = {}; + struct neighbour *n; + char *encap_header; + int encap_size; + __be32 saddr; + int ttl; + int err; + + encap_header = kzalloc(max_encap_size, GFP_KERNEL); + if (!encap_header) + return -ENOMEM; + + switch (e->tunnel_type) { + case MLX5_HEADER_TYPE_VXLAN: + fl4.flowi4_proto = IPPROTO_UDP; + fl4.fl4_dport = e->tun_info.tp_dst; + break; + default: + err = -EOPNOTSUPP; + goto out; + } + fl4.daddr = e->tun_info.daddr; + + err = mlx5e_route_lookup_ipv4(priv, mirred_dev, out_dev, + &fl4, &n, &saddr, &ttl); + if (err) + goto out; + + e->n = n; + e->out_dev = *out_dev; + + if (!(n->nud_state & NUD_VALID)) { + err = -ENOTSUPP; + goto out; + } + + neigh_ha_snapshot(e->h_dest, n, *out_dev); + + switch (e->tunnel_type) { + case MLX5_HEADER_TYPE_VXLAN: + encap_size = gen_vxlan_header_ipv4(*out_dev, encap_header, + e->h_dest, ttl, + e->tun_info.daddr, + saddr, e->tun_info.tp_dst, + e->tun_info.tun_id); + break; + default: + err = -EOPNOTSUPP; + goto out; + } + + err = mlx5_encap_alloc(priv->mdev, e->tunnel_type, + encap_size, encap_header, &e->encap_id); +out: + kfree(encap_header); + return err; +} + +static int mlx5e_attach_encap(struct mlx5e_priv *priv, + struct ip_tunnel_info *tun_info, + struct net_device *mirred_dev, + struct mlx5_esw_flow_attr *attr) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + unsigned short family = ip_tunnel_info_af(tun_info); + struct ip_tunnel_key *key = &tun_info->key; + struct mlx5_encap_info info; + struct mlx5_encap_entry *e; + struct net_device *out_dev; + uintptr_t hash_key; + bool found = false; + int tunnel_type; + int err; + + /* udp dst port must be given */ + if (!memchr_inv(&key->tp_dst, 0, sizeof(key->tp_dst))) + return -EOPNOTSUPP; + + if (mlx5e_vxlan_lookup_port(priv, be16_to_cpu(key->tp_dst)) && + MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) { + info.tp_dst = key->tp_dst; + info.tun_id = tunnel_id_to_key32(key->tun_id); + tunnel_type = MLX5_HEADER_TYPE_VXLAN; + } else { + return -EOPNOTSUPP; + } + + switch (family) { + case AF_INET: + info.daddr = key->u.ipv4.dst; + break; + default: + return -EOPNOTSUPP; + } + + hash_key = hash_encap_info(&info); + + hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, + encap_hlist, hash_key) { + if (!cmp_encap_info(&e->tun_info, &info)) { + found = true; + break; + } + } + + if (found) { + attr->encap = e; + return 0; + } + + e = kzalloc(sizeof(*e), GFP_KERNEL); + if (!e) + return -ENOMEM; + + e->tun_info = info; + e->tunnel_type = tunnel_type; + INIT_LIST_HEAD(&e->flows); + + err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e, &out_dev); + if (err) + goto out_err; + + attr->encap = e; + hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); + + return err; + +out_err: + kfree(e); + return err; +} + static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, - struct mlx5_esw_flow_attr *attr) + struct mlx5e_tc_flow *flow) { + struct mlx5_esw_flow_attr *attr = flow->attr; + struct ip_tunnel_info *info = NULL; const struct tc_action *a; LIST_HEAD(actions); + bool encap = false; + int err; if (tc_no_actions(exts)) return -EINVAL; @@ -404,22 +874,44 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, continue; } - if (is_tcf_mirred_redirect(a)) { + if (is_tcf_mirred_egress_redirect(a)) { int ifindex = tcf_mirred_ifindex(a); struct net_device *out_dev; struct mlx5e_priv *out_priv; out_dev = __dev_get_by_index(dev_net(priv->netdev), ifindex); - if (!switchdev_port_same_parent_id(priv->netdev, out_dev)) { + if (switchdev_port_same_parent_id(priv->netdev, + out_dev)) { + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + out_priv = netdev_priv(out_dev); + attr->out_rep = out_priv->ppriv; + } else if (encap) { + err = mlx5e_attach_encap(priv, info, + out_dev, attr); + if (err) + return err; + list_add(&flow->encap, &attr->encap->flows); + attr->action |= MLX5_FLOW_CONTEXT_ACTION_ENCAP | + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + out_priv = netdev_priv(attr->encap->out_dev); + attr->out_rep = out_priv->ppriv; + } else { pr_err("devices %s %s not on same switch HW, can't offload forwarding\n", priv->netdev->name, out_dev->name); return -EINVAL; } + continue; + } - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - out_priv = netdev_priv(out_dev); - attr->out_rep = out_priv->ppriv; + if (is_tcf_tunnel_set(a)) { + info = tcf_tunnel_info(a); + if (info) + encap = true; + else + return -EOPNOTSUPP; continue; } @@ -436,6 +928,11 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, continue; } + if (is_tcf_tunnel_release(a)) { + attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; + continue; + } + return -EINVAL; } return 0; @@ -450,25 +947,17 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, u32 flow_tag, action; struct mlx5e_tc_flow *flow; struct mlx5_flow_spec *spec; - struct mlx5_flow_rule *old = NULL; - struct mlx5_esw_flow_attr *old_attr = NULL; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; if (esw && esw->mode == SRIOV_OFFLOADS) fdb_flow = true; - flow = rhashtable_lookup_fast(&tc->ht, &f->cookie, - tc->ht_params); - if (flow) { - old = flow->rule; - old_attr = flow->attr; - } else { - if (fdb_flow) - flow = kzalloc(sizeof(*flow) + sizeof(struct mlx5_esw_flow_attr), - GFP_KERNEL); - else - flow = kzalloc(sizeof(*flow), GFP_KERNEL); - } + if (fdb_flow) + flow = kzalloc(sizeof(*flow) + + sizeof(struct mlx5_esw_flow_attr), + GFP_KERNEL); + else + flow = kzalloc(sizeof(*flow), GFP_KERNEL); spec = mlx5_vzalloc(sizeof(*spec)); if (!spec || !flow) { @@ -484,7 +973,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, if (fdb_flow) { flow->attr = (struct mlx5_esw_flow_attr *)(flow + 1); - err = parse_tc_fdb_actions(priv, f->exts, flow->attr); + err = parse_tc_fdb_actions(priv, f->exts, flow); if (err < 0) goto err_free; flow->rule = mlx5e_tc_add_fdb_flow(priv, spec, flow->attr); @@ -505,17 +994,13 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv, __be16 protocol, if (err) goto err_del_rule; - if (old) - mlx5e_tc_del_flow(priv, old, old_attr); - goto out; err_del_rule: - mlx5_del_flow_rule(flow->rule); + mlx5_del_flow_rules(flow->rule); err_free: - if (!old) - kfree(flow); + kfree(flow); out: kvfree(spec); return err; @@ -534,7 +1019,8 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv, rhashtable_remove_fast(&tc->ht, &flow->node, tc->ht_params); - mlx5e_tc_del_flow(priv, flow->rule, flow->attr); + mlx5e_tc_del_flow(priv, flow); + kfree(flow); @@ -591,7 +1077,7 @@ static void _mlx5e_tc_del_flow(void *ptr, void *arg) struct mlx5e_tc_flow *flow = ptr; struct mlx5e_priv *priv = arg; - mlx5e_tc_del_flow(priv, flow->rule, flow->attr); + mlx5e_tc_del_flow(priv, flow); kfree(flow); } 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/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index aaca09002ca6..8ffcc8808e50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -139,6 +139,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_PORT_CHANGE"; case MLX5_EVENT_TYPE_GPIO_EVENT: return "MLX5_EVENT_TYPE_GPIO_EVENT"; + case MLX5_EVENT_TYPE_PORT_MODULE_EVENT: + return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT"; case MLX5_EVENT_TYPE_REMOTE_CONFIG: return "MLX5_EVENT_TYPE_REMOTE_CONFIG"; case MLX5_EVENT_TYPE_DB_BF_CONGESTION: @@ -285,6 +287,11 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq) mlx5_eswitch_vport_event(dev->priv.eswitch, eqe); break; #endif + + case MLX5_EVENT_TYPE_PORT_MODULE_EVENT: + mlx5_port_module_event(dev, eqe); + break; + default: mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n", eqe->type, eq->eqn); @@ -469,7 +476,7 @@ void mlx5_eq_cleanup(struct mlx5_core_dev *dev) int mlx5_start_eqs(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = &dev->priv.eq_table; - u32 async_event_mask = MLX5_ASYNC_EVENT_MASK; + u64 async_event_mask = MLX5_ASYNC_EVENT_MASK; int err; if (MLX5_CAP_GEN(dev, pg)) @@ -480,6 +487,11 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev) mlx5_core_is_pf(dev)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE); + if (MLX5_CAP_GEN(dev, port_module_event)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_PORT_MODULE_EVENT); + else + mlx5_core_dbg(dev, "port_module_event is not set\n"); + err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD, MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD, "mlx5_cmd_eq", &dev->priv.uuari.uars[0]); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index abbf2c369923..d6807c3cc461 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -56,7 +56,7 @@ struct esw_uc_addr { /* E-Switch MC FDB table hash node */ struct esw_mc_addr { /* SRIOV only */ struct l2addr_node node; - struct mlx5_flow_rule *uplink_rule; /* Forward to uplink rule */ + struct mlx5_flow_handle *uplink_rule; /* Forward to uplink rule */ u32 refcnt; }; @@ -65,7 +65,7 @@ struct vport_addr { struct l2addr_node node; u8 action; u32 vport; - struct mlx5_flow_rule *flow_rule; /* SRIOV only */ + struct mlx5_flow_handle *flow_rule; /* SRIOV only */ /* A flag indicating that mac was added due to mc promiscuous vport */ bool mc_promisc; }; @@ -237,13 +237,14 @@ static void del_l2_table_entry(struct mlx5_core_dev *dev, u32 index) } /* E-Switch FDB */ -static struct mlx5_flow_rule * +static struct mlx5_flow_handle * __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN]) { int match_header = (is_zero_ether_addr(mac_c) ? 0 : MLX5_MATCH_OUTER_HEADERS); - struct mlx5_flow_rule *flow_rule = NULL; + struct mlx5_flow_handle *flow_rule = NULL; + struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_destination dest; struct mlx5_flow_spec *spec; void *mv_misc = NULL; @@ -285,10 +286,10 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, "\tFDB add rule dmac_v(%pM) dmac_c(%pM) -> vport(%d)\n", dmac_v, dmac_c, vport); spec->match_criteria_enable = match_header; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; flow_rule = - mlx5_add_flow_rule(esw->fdb_table.fdb, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - 0, &dest); + mlx5_add_flow_rules(esw->fdb_table.fdb, spec, + &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { esw_warn(esw->dev, "FDB: Failed to add flow rule: dmac_v(%pM) dmac_c(%pM) -> vport(%d), err(%ld)\n", @@ -300,7 +301,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, return flow_rule; } -static struct mlx5_flow_rule * +static struct mlx5_flow_handle * esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) { u8 mac_c[ETH_ALEN]; @@ -309,7 +310,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac); } -static struct mlx5_flow_rule * +static struct mlx5_flow_handle * esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) { u8 mac_c[ETH_ALEN]; @@ -322,7 +323,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) return __esw_fdb_set_vport_rule(esw, vport, false, mac_c, mac_v); } -static struct mlx5_flow_rule * +static struct mlx5_flow_handle * esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport) { u8 mac_c[ETH_ALEN]; @@ -361,7 +362,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports) memset(flow_group_in, 0, inlen); table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); - fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0); + fdb = mlx5_create_flow_table(root_ns, 0, table_size, 0, 0); if (IS_ERR(fdb)) { err = PTR_ERR(fdb); esw_warn(dev, "Failed to create FDB Table err %d\n", err); @@ -515,7 +516,7 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) del_l2_table_entry(esw->dev, esw_uc->table_index); if (vaddr->flow_rule) - mlx5_del_flow_rule(vaddr->flow_rule); + mlx5_del_flow_rules(vaddr->flow_rule); vaddr->flow_rule = NULL; l2addr_hash_del(esw_uc); @@ -562,7 +563,7 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, case MLX5_ACTION_DEL: if (!iter_vaddr) continue; - mlx5_del_flow_rule(iter_vaddr->flow_rule); + mlx5_del_flow_rules(iter_vaddr->flow_rule); l2addr_hash_del(iter_vaddr); break; } @@ -632,7 +633,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) esw_mc->uplink_rule); if (vaddr->flow_rule) - mlx5_del_flow_rule(vaddr->flow_rule); + mlx5_del_flow_rules(vaddr->flow_rule); vaddr->flow_rule = NULL; /* If the multicast mac is added as a result of mc promiscuous vport, @@ -645,7 +646,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) update_allmulti_vports(esw, vaddr, esw_mc); if (esw_mc->uplink_rule) - mlx5_del_flow_rule(esw_mc->uplink_rule); + mlx5_del_flow_rules(esw_mc->uplink_rule); l2addr_hash_del(esw_mc); return 0; @@ -828,14 +829,14 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, UPLINK_VPORT); allmulti_addr->refcnt++; } else if (vport->allmulti_rule) { - mlx5_del_flow_rule(vport->allmulti_rule); + mlx5_del_flow_rules(vport->allmulti_rule); vport->allmulti_rule = NULL; if (--allmulti_addr->refcnt > 0) goto promisc; if (allmulti_addr->uplink_rule) - mlx5_del_flow_rule(allmulti_addr->uplink_rule); + mlx5_del_flow_rules(allmulti_addr->uplink_rule); allmulti_addr->uplink_rule = NULL; } @@ -847,7 +848,7 @@ promisc: vport->promisc_rule = esw_fdb_set_vport_promisc_rule(esw, vport_num); } else if (vport->promisc_rule) { - mlx5_del_flow_rule(vport->promisc_rule); + mlx5_del_flow_rules(vport->promisc_rule); vport->promisc_rule = NULL; } } @@ -931,8 +932,8 @@ 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 +950,11 @@ 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 +962,12 @@ 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)) { @@ -1009,16 +1012,17 @@ 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, struct mlx5_vport *vport) { if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan)) - mlx5_del_flow_rule(vport->egress.allowed_vlan); + mlx5_del_flow_rules(vport->egress.allowed_vlan); if (!IS_ERR_OR_NULL(vport->egress.drop_rule)) - mlx5_del_flow_rule(vport->egress.drop_rule); + mlx5_del_flow_rules(vport->egress.drop_rule); vport->egress.allowed_vlan = NULL; vport->egress.drop_rule = NULL; @@ -1041,8 +1045,8 @@ 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 +1067,11 @@ 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 +1079,12 @@ 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)) { @@ -1167,16 +1173,17 @@ out: } kvfree(flow_group_in); + return err; } static void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { if (!IS_ERR_OR_NULL(vport->ingress.drop_rule)) - mlx5_del_flow_rule(vport->ingress.drop_rule); + mlx5_del_flow_rules(vport->ingress.drop_rule); if (!IS_ERR_OR_NULL(vport->ingress.allow_rule)) - mlx5_del_flow_rule(vport->ingress.allow_rule); + mlx5_del_flow_rules(vport->ingress.allow_rule); vport->ingress.drop_rule = NULL; vport->ingress.allow_rule = NULL; @@ -1206,6 +1213,7 @@ static void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, static int esw_vport_ingress_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { + struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_spec *spec; int err = 0; u8 *smac_v; @@ -1225,7 +1233,13 @@ 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", @@ -1252,10 +1266,10 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, } spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; vport->ingress.allow_rule = - mlx5_add_flow_rule(vport->ingress.acl, spec, - MLX5_FLOW_CONTEXT_ACTION_ALLOW, - 0, NULL); + mlx5_add_flow_rules(vport->ingress.acl, spec, + &flow_act, NULL, 0); if (IS_ERR(vport->ingress.allow_rule)) { err = PTR_ERR(vport->ingress.allow_rule); esw_warn(esw->dev, @@ -1266,10 +1280,10 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, } memset(spec, 0, sizeof(*spec)); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; vport->ingress.drop_rule = - mlx5_add_flow_rule(vport->ingress.acl, spec, - MLX5_FLOW_CONTEXT_ACTION_DROP, - 0, NULL); + mlx5_add_flow_rules(vport->ingress.acl, spec, + &flow_act, NULL, 0); if (IS_ERR(vport->ingress.drop_rule)) { err = PTR_ERR(vport->ingress.drop_rule); esw_warn(esw->dev, @@ -1289,6 +1303,7 @@ out: static int esw_vport_egress_config(struct mlx5_eswitch *esw, struct mlx5_vport *vport) { + struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_spec *spec; int err = 0; @@ -1299,7 +1314,13 @@ 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", @@ -1320,10 +1341,10 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw, MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vport->info.vlan); spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW; vport->egress.allowed_vlan = - mlx5_add_flow_rule(vport->egress.acl, spec, - MLX5_FLOW_CONTEXT_ACTION_ALLOW, - 0, NULL); + mlx5_add_flow_rules(vport->egress.acl, spec, + &flow_act, NULL, 0); if (IS_ERR(vport->egress.allowed_vlan)) { err = PTR_ERR(vport->egress.allowed_vlan); esw_warn(esw->dev, @@ -1335,10 +1356,10 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw, /* Drop others rule (star rule) */ memset(spec, 0, sizeof(*spec)); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; vport->egress.drop_rule = - mlx5_add_flow_rule(vport->egress.acl, spec, - MLX5_FLOW_CONTEXT_ACTION_DROP, - 0, NULL); + mlx5_add_flow_rules(vport->egress.acl, spec, + &flow_act, NULL, 0); if (IS_ERR(vport->egress.drop_rule)) { err = PTR_ERR(vport->egress.drop_rule); esw_warn(esw->dev, @@ -1351,6 +1372,147 @@ out: return err; } +/* Vport QoS management */ +static int esw_create_tsar(struct mlx5_eswitch *esw) +{ + u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; + struct mlx5_core_dev *dev = esw->dev; + int err; + + if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) + return 0; + + if (esw->qos.enabled) + return -EEXIST; + + err = mlx5_create_scheduling_element_cmd(dev, + SCHEDULING_HIERARCHY_E_SWITCH, + &tsar_ctx, + &esw->qos.root_tsar_id); + if (err) { + esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err); + return err; + } + + esw->qos.enabled = true; + return 0; +} + +static void esw_destroy_tsar(struct mlx5_eswitch *esw) +{ + int err; + + if (!esw->qos.enabled) + return; + + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + esw->qos.root_tsar_id); + if (err) + esw_warn(esw->dev, "E-Switch destroy TSAR failed (%d)\n", err); + + esw->qos.enabled = false; +} + +static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, + u32 initial_max_rate) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; + struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_core_dev *dev = esw->dev; + void *vport_elem; + int err = 0; + + if (!esw->qos.enabled || !MLX5_CAP_GEN(dev, qos) || + !MLX5_CAP_QOS(dev, esw_scheduling)) + return 0; + + if (vport->qos.enabled) + return -EEXIST; + + MLX5_SET(scheduling_context, &sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); + vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx, + element_attributes); + MLX5_SET(vport_element, vport_elem, vport_number, vport_num); + MLX5_SET(scheduling_context, &sched_ctx, parent_element_id, + esw->qos.root_tsar_id); + MLX5_SET(scheduling_context, &sched_ctx, max_average_bw, + initial_max_rate); + + err = mlx5_create_scheduling_element_cmd(dev, + SCHEDULING_HIERARCHY_E_SWITCH, + &sched_ctx, + &vport->qos.esw_tsar_ix); + if (err) { + esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n", + vport_num, err); + return err; + } + + vport->qos.enabled = true; + return 0; +} + +static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num) +{ + struct mlx5_vport *vport = &esw->vports[vport_num]; + int err = 0; + + if (!vport->qos.enabled) + return; + + err = mlx5_destroy_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + vport->qos.esw_tsar_ix); + if (err) + esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n", + vport_num, err); + + vport->qos.enabled = false; +} + +static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num, + u32 max_rate) +{ + u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; + struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_core_dev *dev = esw->dev; + void *vport_elem; + u32 bitmask = 0; + int err = 0; + + if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) + return -EOPNOTSUPP; + + if (!vport->qos.enabled) + return -EIO; + + MLX5_SET(scheduling_context, &sched_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); + vport_elem = MLX5_ADDR_OF(scheduling_context, &sched_ctx, + element_attributes); + MLX5_SET(vport_element, vport_elem, vport_number, vport_num); + MLX5_SET(scheduling_context, &sched_ctx, parent_element_id, + esw->qos.root_tsar_id); + MLX5_SET(scheduling_context, &sched_ctx, max_average_bw, + max_rate); + bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; + + err = mlx5_modify_scheduling_element_cmd(dev, + SCHEDULING_HIERARCHY_E_SWITCH, + &sched_ctx, + vport->qos.esw_tsar_ix, + bitmask); + if (err) { + esw_warn(esw->dev, "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n", + vport_num, err); + return err; + } + + return 0; +} + static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN]) { ((u8 *)node_guid)[7] = mac[0]; @@ -1386,6 +1548,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, esw_vport_egress_config(esw, vport); } } + static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, int enable_events) { @@ -1399,6 +1562,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, /* Restore old vport configuration */ esw_apply_vport_conf(esw, vport); + /* Attach vport to the eswitch rate limiter */ + if (esw_vport_enable_qos(esw, vport_num, vport->info.max_rate)) + esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num); + /* Sync with current vport context */ vport->enabled_events = enable_events; vport->enabled = true; @@ -1437,7 +1604,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) */ esw_vport_change_handle_locked(vport); vport->enabled_events = 0; - + esw_vport_disable_qos(esw, vport_num); if (vport_num && esw->mode == SRIOV_LEGACY) { mlx5_modify_vport_admin_state(esw->dev, MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT, @@ -1483,6 +1650,10 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) if (err) goto abort; + err = esw_create_tsar(esw); + if (err) + esw_warn(esw->dev, "Failed to create eswitch TSAR"); + enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : UC_ADDR_CHANGE; for (i = 0; i <= nvfs; i++) esw_enable_vport(esw, i, enabled_events); @@ -1517,7 +1688,9 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) esw_disable_vport(esw, i); if (mc_promisc && mc_promisc->uplink_rule) - mlx5_del_flow_rule(mc_promisc->uplink_rule); + mlx5_del_flow_rules(mc_promisc->uplink_rule); + + esw_destroy_tsar(esw); if (esw->mode == SRIOV_LEGACY) esw_destroy_legacy_fdb_table(esw); @@ -1609,6 +1782,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) goto abort; } + hash_init(esw->offloads.encap_tbl); mutex_init(&esw->state_lock); for (vport_num = 0; vport_num < total_vports; vport_num++) { @@ -1624,6 +1798,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->total_vports = total_vports; esw->enabled_vports = 0; esw->mode = SRIOV_NONE; + esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; dev->priv.eswitch = esw; return 0; @@ -1777,6 +1952,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, ivi->qos = evport->info.qos; ivi->spoofchk = evport->info.spoofchk; ivi->trusted = evport->info.trusted; + ivi->max_tx_rate = evport->info.max_rate; mutex_unlock(&esw->state_lock); return 0; @@ -1870,6 +2046,27 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, return 0; } +int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, + int vport, u32 max_rate) +{ + struct mlx5_vport *evport; + int err = 0; + + if (!ESW_ALLOWED(esw)) + return -EPERM; + if (!LEGAL_VPORT(esw, vport)) + return -EINVAL; + + mutex_lock(&esw->state_lock); + evport = &esw->vports[vport]; + err = esw_vport_qos_config(esw, vport, max_rate); + if (!err) + evport->info.max_rate = max_rate; + + mutex_unlock(&esw->state_lock); + return err; +} + int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, int vport, struct ifla_vf_stats *vf_stats) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 2e2938e08cda..8661dd3f542c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -97,16 +97,16 @@ struct vport_ingress { struct mlx5_flow_group *allow_spoofchk_only_grp; struct mlx5_flow_group *allow_untagged_only_grp; struct mlx5_flow_group *drop_grp; - struct mlx5_flow_rule *allow_rule; - struct mlx5_flow_rule *drop_rule; + struct mlx5_flow_handle *allow_rule; + struct mlx5_flow_handle *drop_rule; }; struct vport_egress { struct mlx5_flow_table *acl; struct mlx5_flow_group *allowed_vlans_grp; struct mlx5_flow_group *drop_grp; - struct mlx5_flow_rule *allowed_vlan; - struct mlx5_flow_rule *drop_rule; + struct mlx5_flow_handle *allowed_vlan; + struct mlx5_flow_handle *drop_rule; }; struct mlx5_vport_info { @@ -115,6 +115,7 @@ struct mlx5_vport_info { u8 qos; u64 node_guid; int link_state; + u32 max_rate; bool spoofchk; bool trusted; }; @@ -124,8 +125,8 @@ struct mlx5_vport { int vport; struct hlist_head uc_list[MLX5_L2_ADDR_HASH_SIZE]; struct hlist_head mc_list[MLX5_L2_ADDR_HASH_SIZE]; - struct mlx5_flow_rule *promisc_rule; - struct mlx5_flow_rule *allmulti_rule; + struct mlx5_flow_handle *promisc_rule; + struct mlx5_flow_handle *allmulti_rule; struct work_struct vport_change_handler; struct vport_ingress ingress; @@ -133,6 +134,11 @@ struct mlx5_vport { struct mlx5_vport_info info; + struct { + bool enabled; + u32 esw_tsar_ix; + } qos; + bool enabled; u16 enabled_events; }; @@ -156,7 +162,7 @@ struct mlx5_eswitch_fdb { struct mlx5_flow_table *fdb; struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *miss_grp; - struct mlx5_flow_rule *miss_rule; + struct mlx5_flow_handle *miss_rule; int vlan_push_pop_refcount; } offloads; }; @@ -169,7 +175,7 @@ enum { }; struct mlx5_esw_sq { - struct mlx5_flow_rule *send_to_vport_rule; + struct mlx5_flow_handle *send_to_vport_rule; struct list_head list; }; @@ -180,9 +186,9 @@ struct mlx5_eswitch_rep { struct mlx5_eswitch_rep *rep); u16 vport; u8 hw_id[ETH_ALEN]; - void *priv_data; + struct net_device *netdev; - struct mlx5_flow_rule *vport_rx_rule; + struct mlx5_flow_handle *vport_rx_rule; struct list_head vport_sqs_list; u16 vlan; u32 vlan_refcount; @@ -193,6 +199,8 @@ struct mlx5_esw_offload { struct mlx5_flow_table *ft_offloads; struct mlx5_flow_group *vport_rx_group; struct mlx5_eswitch_rep *vport_reps; + DECLARE_HASHTABLE(encap_tbl, 8); + u8 inline_mode; }; struct mlx5_eswitch { @@ -209,6 +217,12 @@ struct mlx5_eswitch { */ struct mutex state_lock; struct esw_mc_addr *mc_promisc; + + struct { + bool enabled; + u32 root_tsar_id; + } qos; + struct mlx5_esw_offload offloads; int mode; }; @@ -234,6 +248,8 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, int vport, bool spoofchk); int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, int vport_num, bool setting); +int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, + int vport, u32 max_rate); int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, int vport, struct ifla_vf_info *ivi); int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, @@ -243,11 +259,11 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, struct mlx5_flow_spec; struct mlx5_esw_flow_attr; -struct mlx5_flow_rule * +struct mlx5_flow_handle * mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_esw_flow_attr *attr); -struct mlx5_flow_rule * +struct mlx5_flow_handle * mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn); enum { @@ -258,6 +274,24 @@ enum { #define MLX5_FLOW_CONTEXT_ACTION_VLAN_POP 0x40 #define MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH 0x80 +struct mlx5_encap_info { + __be32 daddr; + __be32 tun_id; + __be16 tp_dst; +}; + +struct mlx5_encap_entry { + struct hlist_node encap_hlist; + struct list_head flows; + u32 encap_id; + struct neighbour *n; + struct mlx5_encap_info tun_info; + unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ + + struct net_device *out_dev; + int tunnel_type; +}; + struct mlx5_esw_flow_attr { struct mlx5_eswitch_rep *in_rep; struct mlx5_eswitch_rep *out_rep; @@ -265,6 +299,7 @@ struct mlx5_esw_flow_attr { int action; u16 vlan; bool vlan_handled; + struct mlx5_encap_entry *encap; }; int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw, @@ -275,11 +310,15 @@ void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw, int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode); int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode); +int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode); +int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode); +int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode); void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, int vport_index, struct mlx5_eswitch_rep *rep); void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, int vport_index); +struct net_device *mlx5_eswitch_get_uplink_netdev(struct mlx5_eswitch *esw); int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, struct mlx5_esw_flow_attr *attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index c55ad8d00c05..466e161010f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -43,32 +43,36 @@ enum { FDB_SLOW_PATH }; -struct mlx5_flow_rule * +struct mlx5_flow_handle * mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_esw_flow_attr *attr) { - struct mlx5_flow_destination dest = { 0 }; + struct mlx5_flow_destination dest[2] = {}; + struct mlx5_flow_act flow_act = {0}; struct mlx5_fc *counter = NULL; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; void *misc; - int action; + int i = 0; 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 */ + flow_act.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; - dest.vport_num = attr->out_rep->vport; - action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - } else if (action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; + dest[i].vport_num = attr->out_rep->vport; + i++; + } + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { counter = mlx5_fc_create(esw->dev, true); if (IS_ERR(counter)) return ERR_CAST(counter); - dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter = counter; + dest[i].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[i].counter = counter; + i++; } misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); @@ -79,10 +83,14 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS; + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) + spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; - rule = mlx5_add_flow_rule((struct mlx5_flow_table *)esw->fdb_table.fdb, - spec, action, 0, &dest); + if (attr->encap) + flow_act.encap_id = attr->encap->encap_id; + rule = mlx5_add_flow_rules((struct mlx5_flow_table *)esw->fdb_table.fdb, + spec, &flow_act, dest, i); if (IS_ERR(rule)) mlx5_fc_destroy(esw->dev, counter); @@ -269,11 +277,12 @@ out: return err; } -static struct mlx5_flow_rule * +static struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn) { + struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_destination dest; - struct mlx5_flow_rule *flow_rule; + struct mlx5_flow_handle *flow_rule; struct mlx5_flow_spec *spec; void *misc; @@ -295,10 +304,10 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport_num = vport; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - 0, &dest); + flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec, + &flow_act, &dest, 1); if (IS_ERR(flow_rule)) esw_warn(esw->dev, "FDB: Failed to add send to vport rule err %ld\n", PTR_ERR(flow_rule)); out: @@ -315,7 +324,7 @@ void mlx5_eswitch_sqs2vport_stop(struct mlx5_eswitch *esw, return; list_for_each_entry_safe(esw_sq, tmp, &rep->vport_sqs_list, list) { - mlx5_del_flow_rule(esw_sq->send_to_vport_rule); + mlx5_del_flow_rules(esw_sq->send_to_vport_rule); list_del(&esw_sq->list); kfree(esw_sq); } @@ -325,7 +334,7 @@ int mlx5_eswitch_sqs2vport_start(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep, u16 *sqns_array, int sqns_num) { - struct mlx5_flow_rule *flow_rule; + struct mlx5_flow_handle *flow_rule; struct mlx5_esw_sq *esw_sq; int err; int i; @@ -361,8 +370,9 @@ out_err: static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) { + struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_destination dest; - struct mlx5_flow_rule *flow_rule = NULL; + struct mlx5_flow_handle *flow_rule = NULL; struct mlx5_flow_spec *spec; int err = 0; @@ -375,10 +385,10 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; dest.vport_num = 0; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - 0, &dest); + flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.fdb, spec, + &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { err = PTR_ERR(flow_rule); esw_warn(esw->dev, "FDB: Failed to add miss flow rule err %d\n", err); @@ -405,6 +415,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports) u32 *flow_group_in; void *match_criteria; int table_size, ix, err = 0; + u32 flags = 0; flow_group_in = mlx5_vzalloc(inlen); if (!flow_group_in) @@ -419,9 +430,14 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports) esw_debug(dev, "Create offloads FDB table, log_max_size(%d)\n", MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size)); + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, encap) && + MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)) + flags |= MLX5_FLOW_TABLE_TUNNEL_EN; + fdb = mlx5_create_auto_grouped_flow_table(root_ns, FDB_FAST_PATH, ESW_OFFLOADS_NUM_ENTRIES, - ESW_OFFLOADS_NUM_GROUPS, 0); + ESW_OFFLOADS_NUM_GROUPS, 0, + flags); if (IS_ERR(fdb)) { err = PTR_ERR(fdb); esw_warn(dev, "Failed to create Fast path FDB Table err %d\n", err); @@ -430,7 +446,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports) esw->fdb_table.fdb = fdb; table_size = nvports + MAX_PF_SQ + 1; - fdb = mlx5_create_flow_table(root_ns, FDB_SLOW_PATH, table_size, 0); + fdb = mlx5_create_flow_table(root_ns, FDB_SLOW_PATH, table_size, 0, 0); if (IS_ERR(fdb)) { err = PTR_ERR(fdb); esw_warn(dev, "Failed to create slow path FDB Table err %d\n", err); @@ -501,7 +517,7 @@ static void esw_destroy_offloads_fdb_table(struct mlx5_eswitch *esw) return; esw_debug(esw->dev, "Destroy offloads FDB Table\n"); - mlx5_del_flow_rule(esw->fdb_table.offloads.miss_rule); + mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule); mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); @@ -522,7 +538,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) return -ENOMEM; } - ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0); + ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0, 0); if (IS_ERR(ft_offloads)) { err = PTR_ERR(ft_offloads); esw_warn(esw->dev, "Failed to create offloads table, err %d\n", err); @@ -585,11 +601,12 @@ static void esw_destroy_vport_rx_group(struct mlx5_eswitch *esw) mlx5_destroy_flow_group(esw->offloads.vport_rx_group); } -struct mlx5_flow_rule * +struct mlx5_flow_handle * mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn) { + struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_destination dest; - struct mlx5_flow_rule *flow_rule; + struct mlx5_flow_handle *flow_rule; struct mlx5_flow_spec *spec; void *misc; @@ -610,9 +627,9 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, int vport, u32 tirn) dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR; dest.tir_num = tirn; - flow_rule = mlx5_add_flow_rule(esw->offloads.ft_offloads, spec, - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, - 0, &dest); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec, + &flow_act, &dest, 1); if (IS_ERR(flow_rule)) { esw_warn(esw->dev, "fs offloads: Failed to add vport rx rule err %ld\n", PTR_ERR(flow_rule)); goto out; @@ -640,6 +657,14 @@ static int esw_offloads_start(struct mlx5_eswitch *esw) if (err1) esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err); } + if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { + if (mlx5_eswitch_inline_mode_get(esw, + num_vfs, + &esw->offloads.inline_mode)) { + esw->offloads.inline_mode = MLX5_INLINE_MODE_L2; + esw_warn(esw->dev, "Inline mode is different between vports\n"); + } + } return err; } @@ -754,6 +779,50 @@ static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode) return 0; } +static int esw_inline_mode_from_devlink(u8 mode, u8 *mlx5_mode) +{ + switch (mode) { + case DEVLINK_ESWITCH_INLINE_MODE_NONE: + *mlx5_mode = MLX5_INLINE_MODE_NONE; + break; + case DEVLINK_ESWITCH_INLINE_MODE_LINK: + *mlx5_mode = MLX5_INLINE_MODE_L2; + break; + case DEVLINK_ESWITCH_INLINE_MODE_NETWORK: + *mlx5_mode = MLX5_INLINE_MODE_IP; + break; + case DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT: + *mlx5_mode = MLX5_INLINE_MODE_TCP_UDP; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) +{ + switch (mlx5_mode) { + case MLX5_INLINE_MODE_NONE: + *mode = DEVLINK_ESWITCH_INLINE_MODE_NONE; + break; + case MLX5_INLINE_MODE_L2: + *mode = DEVLINK_ESWITCH_INLINE_MODE_LINK; + break; + case MLX5_INLINE_MODE_IP: + *mode = DEVLINK_ESWITCH_INLINE_MODE_NETWORK; + break; + case MLX5_INLINE_MODE_TCP_UDP: + *mode = DEVLINK_ESWITCH_INLINE_MODE_TRANSPORT; + break; + default: + return -EINVAL; + } + + return 0; +} + int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode) { struct mlx5_core_dev *dev; @@ -798,6 +867,95 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) return esw_mode_to_devlink(dev->priv.eswitch->mode, mode); } +int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_eswitch *esw = dev->priv.eswitch; + int num_vports = esw->enabled_vports; + int err; + int vport; + u8 mlx5_mode; + + if (!MLX5_CAP_GEN(dev, vport_group_manager)) + return -EOPNOTSUPP; + + if (esw->mode == SRIOV_NONE) + return -EOPNOTSUPP; + + if (MLX5_CAP_ETH(dev, wqe_inline_mode) != + MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) + return -EOPNOTSUPP; + + err = esw_inline_mode_from_devlink(mode, &mlx5_mode); + if (err) + goto out; + + for (vport = 1; vport < num_vports; vport++) { + err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode); + if (err) { + esw_warn(dev, "Failed to set min inline on vport %d\n", + vport); + goto revert_inline_mode; + } + } + + esw->offloads.inline_mode = mlx5_mode; + return 0; + +revert_inline_mode: + while (--vport > 0) + mlx5_modify_nic_vport_min_inline(dev, + vport, + esw->offloads.inline_mode); +out: + return err; +} + +int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_eswitch *esw = dev->priv.eswitch; + + if (!MLX5_CAP_GEN(dev, vport_group_manager)) + return -EOPNOTSUPP; + + if (esw->mode == SRIOV_NONE) + return -EOPNOTSUPP; + + if (MLX5_CAP_ETH(dev, wqe_inline_mode) != + MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) + return -EOPNOTSUPP; + + return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); +} + +int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode) +{ + struct mlx5_core_dev *dev = esw->dev; + int vport; + u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2; + + if (!MLX5_CAP_GEN(dev, vport_group_manager)) + return -EOPNOTSUPP; + + if (esw->mode == SRIOV_NONE) + return -EOPNOTSUPP; + + if (MLX5_CAP_ETH(dev, wqe_inline_mode) != + MLX5_CAP_INLINE_MODE_VPORT_CONTEXT) + return -EOPNOTSUPP; + + for (vport = 1; vport <= nvfs; vport++) { + mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode); + if (vport > 1 && prev_mlx5_mode != mlx5_mode) + return -EINVAL; + prev_mlx5_mode = mlx5_mode; + } + + *mode = mlx5_mode; + return 0; +} + void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, int vport_index, struct mlx5_eswitch_rep *__rep) @@ -812,7 +970,7 @@ void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, rep->load = __rep->load; rep->unload = __rep->unload; rep->vport = __rep->vport; - rep->priv_data = __rep->priv_data; + rep->netdev = __rep->netdev; ether_addr_copy(rep->hw_id, __rep->hw_id); INIT_LIST_HEAD(&rep->vport_sqs_list); @@ -832,3 +990,13 @@ void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, rep->valid = false; } + +struct net_device *mlx5_eswitch_get_uplink_netdev(struct mlx5_eswitch *esw) +{ +#define UPLINK_REP_INDEX 0 + struct mlx5_esw_offload *offloads = &esw->offloads; + struct mlx5_eswitch_rep *rep; + + rep = &offloads->vport_reps[UPLINK_REP_INDEX]; + return rep->netdev; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 113c32326333..c4478ecd8056 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -37,6 +37,7 @@ #include "fs_core.h" #include "fs_cmd.h" #include "mlx5_core.h" +#include "eswitch.h" int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft) @@ -61,8 +62,9 @@ int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, enum fs_flow_table_op_mod op_mod, enum fs_flow_table_type type, unsigned int level, unsigned int log_size, struct mlx5_flow_table - *next_ft, unsigned int *table_id) + *next_ft, unsigned int *table_id, u32 flags) { + int en_encap_decap = !!(flags & MLX5_FLOW_TABLE_TUNNEL_EN); u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {0}; u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {0}; int err; @@ -78,6 +80,9 @@ int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, MLX5_SET(create_flow_table_in, in, other_vport, 1); } + MLX5_SET(create_flow_table_in, in, decap_en, en_encap_decap); + MLX5_SET(create_flow_table_in, in, encap_en, en_encap_decap); + switch (op_mod) { case FS_FT_OP_MOD_NORMAL: if (next_ft) { @@ -243,6 +248,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(flow_context, in_flow_context, group_id, group_id); MLX5_SET(flow_context, in_flow_context, flow_tag, fte->flow_tag); MLX5_SET(flow_context, in_flow_context, action, fte->action); + MLX5_SET(flow_context, in_flow_context, encap_id, fte->encap_id); in_match_value = MLX5_ADDR_OF(flow_context, in_flow_context, match_value); memcpy(in_match_value, &fte->val, MLX5_ST_SZ_BYTES(fte_match_param)); @@ -453,27 +459,32 @@ void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, *bytes = MLX5_GET64(traffic_counter, stats, octets); } -#define MAX_ENCAP_SIZE (128) - -int mlx5_cmd_alloc_encap(struct mlx5_core_dev *dev, - int header_type, - size_t size, - void *encap_header, - u32 *encap_id) +int mlx5_encap_alloc(struct mlx5_core_dev *dev, + int header_type, + size_t size, + void *encap_header, + u32 *encap_id) { + int max_encap_size = MLX5_CAP_ESW(dev, max_encap_header_size); u32 out[MLX5_ST_SZ_DW(alloc_encap_header_out)]; - u32 in[MLX5_ST_SZ_DW(alloc_encap_header_in) + - (MAX_ENCAP_SIZE / sizeof(u32))]; - void *encap_header_in = MLX5_ADDR_OF(alloc_encap_header_in, in, - encap_header); - void *header = MLX5_ADDR_OF(encap_header_in, encap_header_in, - encap_header); - int inlen = header - (void *)in + size; + void *encap_header_in; + void *header; + int inlen; int err; + u32 *in; - if (size > MAX_ENCAP_SIZE) + if (size > MLX5_CAP_ESW(dev, max_encap_header_size)) return -EINVAL; + in = kzalloc(MLX5_ST_SZ_BYTES(alloc_encap_header_in) + max_encap_size, + GFP_KERNEL); + if (!in) + return -ENOMEM; + + encap_header_in = MLX5_ADDR_OF(alloc_encap_header_in, in, encap_header); + header = MLX5_ADDR_OF(encap_header_in, encap_header_in, encap_header); + inlen = header - (void *)in + size; + memset(in, 0, inlen); MLX5_SET(alloc_encap_header_in, in, opcode, MLX5_CMD_OP_ALLOC_ENCAP_HEADER); @@ -485,10 +496,11 @@ int mlx5_cmd_alloc_encap(struct mlx5_core_dev *dev, err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); *encap_id = MLX5_GET(alloc_encap_header_out, out, encap_id); + kfree(in); return err; } -void mlx5_cmd_dealloc_encap(struct mlx5_core_dev *dev, u32 encap_id) +void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id) { u32 in[MLX5_ST_SZ_DW(dealloc_encap_header_in)]; u32 out[MLX5_ST_SZ_DW(dealloc_encap_header_out)]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index c5bc4686c832..8fad80688536 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -38,7 +38,7 @@ int mlx5_cmd_create_flow_table(struct mlx5_core_dev *dev, enum fs_flow_table_op_mod op_mod, enum fs_flow_table_type type, unsigned int level, unsigned int log_size, struct mlx5_flow_table - *next_ft, unsigned int *table_id); + *next_ft, unsigned int *table_id, u32 flags); int mlx5_cmd_destroy_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft); @@ -89,11 +89,4 @@ void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b, u16 id, u64 *packets, u64 *bytes); -int mlx5_cmd_alloc_encap(struct mlx5_core_dev *dev, - int header_type, - size_t size, - void *encap_header, - u32 *encap_id); -void mlx5_cmd_dealloc_encap(struct mlx5_core_dev *dev, u32 encap_id); - #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5da2cc878582..a263d8904a4c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -153,6 +153,11 @@ static void del_rule(struct fs_node *node); static void del_flow_table(struct fs_node *node); static void del_flow_group(struct fs_node *node); static void del_fte(struct fs_node *node); +static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, + struct mlx5_flow_destination *d2); +static struct mlx5_flow_rule * +find_flow_rule(struct fs_fte *fte, + struct mlx5_flow_destination *dest); static void tree_init_node(struct fs_node *node, unsigned int refcount, @@ -369,6 +374,7 @@ static void del_rule(struct fs_node *node) struct mlx5_core_dev *dev = get_dev(node); int match_len = MLX5_ST_SZ_BYTES(fte_match_param); int err; + bool update_fte = false; match_value = mlx5_vzalloc(match_len); if (!match_value) { @@ -387,13 +393,23 @@ static void del_rule(struct fs_node *node) list_del(&rule->next_ft); mutex_unlock(&rule->dest_attr.ft->lock); } + + if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER && + --fte->dests_size) { + modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION); + fte->action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT; + update_fte = true; + goto out; + } + if ((fte->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && --fte->dests_size) { modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST), - err = mlx5_cmd_update_fte(dev, ft, - fg->id, - modify_mask, - fte); + update_fte = true; + } +out: + if (update_fte && fte->dests_size) { + err = mlx5_cmd_update_fte(dev, ft, fg->id, modify_mask, fte); if (err) mlx5_core_warn(dev, "%s can't del rule fg id=%d fte_index=%d\n", @@ -436,13 +452,15 @@ 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); } -static struct fs_fte *alloc_fte(u8 action, - u32 flow_tag, +static struct fs_fte *alloc_fte(struct mlx5_flow_act *flow_act, u32 *match_value, unsigned int index) { @@ -454,9 +472,10 @@ static struct fs_fte *alloc_fte(u8 action, memcpy(fte->val, match_value, sizeof(fte->val)); fte->node.type = FS_TYPE_FLOW_ENTRY; - fte->flow_tag = flow_tag; + fte->flow_tag = flow_act->flow_tag; fte->index = index; - fte->action = action; + fte->action = flow_act->action; + fte->encap_id = flow_act->encap_id; return fte; } @@ -486,7 +505,8 @@ static struct mlx5_flow_group *alloc_flow_group(u32 *create_fg_in) static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_fte, enum fs_flow_table_type table_type, - enum fs_flow_table_op_mod op_mod) + enum fs_flow_table_op_mod op_mod, + u32 flags) { struct mlx5_flow_table *ft; @@ -500,6 +520,7 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft ft->type = table_type; ft->vport = vport; ft->max_fte = max_fte; + ft->flags = flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); @@ -638,8 +659,8 @@ static int update_root_ft_create(struct mlx5_flow_table *ft, struct fs_prio return err; } -int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, - struct mlx5_flow_destination *dest) +static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, + struct mlx5_flow_destination *dest) { struct mlx5_flow_table *ft; struct mlx5_flow_group *fg; @@ -664,6 +685,28 @@ int mlx5_modify_rule_destination(struct mlx5_flow_rule *rule, return err; } +int mlx5_modify_rule_destination(struct mlx5_flow_handle *handle, + struct mlx5_flow_destination *new_dest, + struct mlx5_flow_destination *old_dest) +{ + int i; + + if (!old_dest) { + if (handle->num_rules != 1) + return -EINVAL; + return _mlx5_modify_rule_destination(handle->rule[0], + new_dest); + } + + for (i = 0; i < handle->num_rules; i++) { + if (mlx5_flow_dests_cmp(new_dest, &handle->rule[i]->dest_attr)) + return _mlx5_modify_rule_destination(handle->rule[i], + new_dest); + } + + return -EINVAL; +} + /* Modify/set FWD rules that point on old_next_ft to point on new_next_ft */ static int connect_fwd_rules(struct mlx5_core_dev *dev, struct mlx5_flow_table *new_next_ft, @@ -686,7 +729,7 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev, list_splice_init(&old_next_ft->fwd_rules, &new_next_ft->fwd_rules); mutex_unlock(&old_next_ft->lock); list_for_each_entry(iter, &new_next_ft->fwd_rules, next_ft) { - err = mlx5_modify_rule_destination(iter, &dest); + err = _mlx5_modify_rule_destination(iter, &dest); if (err) pr_err("mlx5_core: failed to modify rule to point on flow table %d\n", new_next_ft->id); @@ -736,7 +779,8 @@ static void list_add_flow_table(struct mlx5_flow_table *ft, static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespace *ns, enum fs_flow_table_op_mod op_mod, u16 vport, int prio, - int max_fte, u32 level) + int max_fte, u32 level, + u32 flags) { struct mlx5_flow_table *next_ft = NULL; struct mlx5_flow_table *ft; @@ -769,7 +813,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa vport, max_fte ? roundup_pow_of_two(max_fte) : 0, root->table_type, - op_mod); + op_mod, flags); if (!ft) { err = -ENOMEM; goto unlock_root; @@ -779,7 +823,8 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); err = mlx5_cmd_create_flow_table(root->dev, ft->vport, ft->op_mod, ft->type, - ft->level, log_table_sz, next_ft, &ft->id); + ft->level, log_table_sz, next_ft, &ft->id, + ft->flags); if (err) goto free_ft; @@ -804,10 +849,11 @@ unlock_root: struct mlx5_flow_table *mlx5_create_flow_table(struct mlx5_flow_namespace *ns, int prio, int max_fte, - u32 level) + u32 level, + u32 flags) { return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, 0, prio, - max_fte, level); + max_fte, level, flags); } struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace *ns, @@ -815,7 +861,7 @@ struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace u32 level, u16 vport) { return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_NORMAL, vport, prio, - max_fte, level); + max_fte, level, 0); } struct mlx5_flow_table *mlx5_create_lag_demux_flow_table( @@ -823,7 +869,7 @@ struct mlx5_flow_table *mlx5_create_lag_demux_flow_table( int prio, u32 level) { return __mlx5_create_flow_table(ns, FS_FT_OP_MOD_LAG_DEMUX, 0, prio, 0, - level); + level, 0); } EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table); @@ -831,14 +877,15 @@ struct mlx5_flow_table *mlx5_create_auto_grouped_flow_table(struct mlx5_flow_nam int prio, int num_flow_table_entries, int max_num_groups, - u32 level) + u32 level, + u32 flags) { struct mlx5_flow_table *ft; if (max_num_groups > num_flow_table_entries) return ERR_PTR(-EINVAL); - ft = mlx5_create_flow_table(ns, prio, num_flow_table_entries, level); + ft = mlx5_create_flow_table(ns, prio, num_flow_table_entries, level, flags); if (IS_ERR(ft)) return ft; @@ -879,7 +926,7 @@ 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 +940,7 @@ 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; @@ -915,55 +962,133 @@ static struct mlx5_flow_rule *alloc_rule(struct mlx5_flow_destination *dest) return rule; } -/* fte should not be deleted while calling this function */ -static struct mlx5_flow_rule *add_rule_fte(struct fs_fte *fte, - struct mlx5_flow_group *fg, - struct mlx5_flow_destination *dest) +static struct mlx5_flow_handle *alloc_handle(int num_rules) { + struct mlx5_flow_handle *handle; + + handle = kzalloc(sizeof(*handle) + sizeof(handle->rule[0]) * + num_rules, GFP_KERNEL); + if (!handle) + return NULL; + + handle->num_rules = num_rules; + + return handle; +} + +static void destroy_flow_handle(struct fs_fte *fte, + struct mlx5_flow_handle *handle, + struct mlx5_flow_destination *dest, + int i) +{ + for (; --i >= 0;) { + if (atomic_dec_and_test(&handle->rule[i]->node.refcount)) { + fte->dests_size--; + list_del(&handle->rule[i]->node.list); + kfree(handle->rule[i]); + } + } + kfree(handle); +} + +static struct mlx5_flow_handle * +create_flow_handle(struct fs_fte *fte, + struct mlx5_flow_destination *dest, + int dest_num, + int *modify_mask, + bool *new_rule) +{ + struct mlx5_flow_handle *handle; + struct mlx5_flow_rule *rule = NULL; + static int count = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS); + static int dst = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST); + int type; + int i = 0; + + handle = alloc_handle((dest_num) ? dest_num : 1); + if (!handle) + return ERR_PTR(-ENOMEM); + + do { + if (dest) { + rule = find_flow_rule(fte, dest + i); + if (rule) { + atomic_inc(&rule->node.refcount); + goto rule_found; + } + } + + *new_rule = true; + rule = alloc_rule(dest + i); + if (!rule) + goto free_rules; + + /* Add dest to dests list- we need flow tables to be in the + * end of the list for forward to next prio rules. + */ + tree_init_node(&rule->node, 1, del_rule); + if (dest && + dest[i].type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) + list_add(&rule->node.list, &fte->node.children); + else + list_add_tail(&rule->node.list, &fte->node.children); + if (dest) { + fte->dests_size++; + + type = dest[i].type == + MLX5_FLOW_DESTINATION_TYPE_COUNTER; + *modify_mask |= type ? count : dst; + } +rule_found: + handle->rule[i] = rule; + } while (++i < dest_num); + + return handle; + +free_rules: + destroy_flow_handle(fte, handle, dest, i); + return ERR_PTR(-ENOMEM); +} + +/* fte should not be deleted while calling this function */ +static struct mlx5_flow_handle * +add_rule_fte(struct fs_fte *fte, + struct mlx5_flow_group *fg, + struct mlx5_flow_destination *dest, + int dest_num, + bool update_action) +{ + struct mlx5_flow_handle *handle; struct mlx5_flow_table *ft; - struct mlx5_flow_rule *rule; int modify_mask = 0; int err; + bool new_rule = false; - rule = alloc_rule(dest); - if (!rule) - return ERR_PTR(-ENOMEM); - - fs_get_obj(ft, fg->node.parent); - /* Add dest to dests list- we need flow tables to be in the - * end of the list for forward to next prio rules. - */ - tree_init_node(&rule->node, 1, del_rule); - if (dest && dest->type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) - list_add(&rule->node.list, &fte->node.children); - else - list_add_tail(&rule->node.list, &fte->node.children); - if (dest) { - fte->dests_size++; + handle = create_flow_handle(fte, dest, dest_num, &modify_mask, + &new_rule); + if (IS_ERR(handle) || !new_rule) + goto out; - modify_mask |= dest->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER ? - BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS) : - BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST); - } + if (update_action) + modify_mask |= BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION); - if (fte->dests_size == 1 || !dest) + fs_get_obj(ft, fg->node.parent); + if (!(fte->status & FS_FTE_STATUS_EXISTING)) err = mlx5_cmd_create_fte(get_dev(&ft->node), ft, fg->id, fte); else err = mlx5_cmd_update_fte(get_dev(&ft->node), ft, fg->id, modify_mask, fte); if (err) - goto free_rule; + goto free_handle; fte->status |= FS_FTE_STATUS_EXISTING; - return rule; +out: + return handle; -free_rule: - list_del(&rule->node.list); - kfree(rule); - if (dest) - fte->dests_size--; +free_handle: + destroy_flow_handle(fte, handle, dest, handle->num_rules); return ERR_PTR(err); } @@ -992,15 +1117,14 @@ static unsigned int get_free_fte_index(struct mlx5_flow_group *fg, /* prev is output, prev->next = new_fte */ static struct fs_fte *create_fte(struct mlx5_flow_group *fg, u32 *match_value, - u8 action, - u32 flow_tag, + struct mlx5_flow_act *flow_act, struct list_head **prev) { struct fs_fte *fte; int index; index = get_free_fte_index(fg, prev); - fte = alloc_fte(action, flow_tag, match_value, index); + fte = alloc_fte(flow_act, match_value, index); if (IS_ERR(fte)) return fte; @@ -1012,7 +1136,7 @@ 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; @@ -1064,71 +1188,81 @@ out: return fg; } +static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, + struct mlx5_flow_destination *d2) +{ + if (d1->type == d2->type) { + if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT && + d1->vport_num == d2->vport_num) || + (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && + d1->ft == d2->ft) || + (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && + d1->tir_num == d2->tir_num)) + return true; + } + + return false; +} + static struct mlx5_flow_rule *find_flow_rule(struct fs_fte *fte, struct mlx5_flow_destination *dest) { struct mlx5_flow_rule *rule; list_for_each_entry(rule, &fte->node.children, node.list) { - if (rule->dest_attr.type == dest->type) { - if ((dest->type == MLX5_FLOW_DESTINATION_TYPE_VPORT && - dest->vport_num == rule->dest_attr.vport_num) || - (dest->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && - dest->ft == rule->dest_attr.ft) || - (dest->type == MLX5_FLOW_DESTINATION_TYPE_TIR && - dest->tir_num == rule->dest_attr.tir_num)) - return rule; - } + if (mlx5_flow_dests_cmp(&rule->dest_attr, dest)) + return rule; } return NULL; } -static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg, - u32 *match_value, - u8 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) +static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg, + u32 *match_value, + struct mlx5_flow_act *flow_act, + struct mlx5_flow_destination *dest, + int dest_num) { - struct fs_fte *fte; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *handle; struct mlx5_flow_table *ft; struct list_head *prev; + struct fs_fte *fte; + int i; nested_lock_ref_node(&fg->node, FS_MUTEX_PARENT); fs_for_each_fte(fte, fg) { nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); if (compare_match_value(&fg->mask, match_value, &fte->val) && - action == fte->action && flow_tag == fte->flow_tag) { - rule = find_flow_rule(fte, dest); - if (rule) { - atomic_inc(&rule->node.refcount); - unlock_ref_node(&fte->node); - unlock_ref_node(&fg->node); - return rule; + (flow_act->action & fte->action) && + flow_act->flow_tag == fte->flow_tag) { + int old_action = fte->action; + + fte->action |= flow_act->action; + handle = add_rule_fte(fte, fg, dest, dest_num, + old_action != flow_act->action); + if (IS_ERR(handle)) { + fte->action = old_action; + goto unlock_fte; + } else { + goto add_rules; } - rule = add_rule_fte(fte, fg, dest); - unlock_ref_node(&fte->node); - if (IS_ERR(rule)) - goto unlock_fg; - else - goto add_rule; } unlock_ref_node(&fte->node); } fs_get_obj(ft, fg->node.parent); if (fg->num_ftes >= fg->max_ftes) { - rule = ERR_PTR(-ENOSPC); + handle = ERR_PTR(-ENOSPC); goto unlock_fg; } - fte = create_fte(fg, match_value, action, flow_tag, &prev); + fte = create_fte(fg, match_value, flow_act, &prev); if (IS_ERR(fte)) { - rule = (void *)fte; + handle = (void *)fte; goto unlock_fg; } tree_init_node(&fte->node, 0, del_fte); - rule = add_rule_fte(fte, fg, dest); - if (IS_ERR(rule)) { + nested_lock_ref_node(&fte->node, FS_MUTEX_CHILD); + handle = add_rule_fte(fte, fg, dest, dest_num, false); + if (IS_ERR(handle)) { kfree(fte); goto unlock_fg; } @@ -1137,19 +1271,24 @@ static struct mlx5_flow_rule *add_rule_fg(struct mlx5_flow_group *fg, tree_add_node(&fte->node, &fg->node); list_add(&fte->node.list, prev); -add_rule: - tree_add_node(&rule->node, &fte->node); +add_rules: + for (i = 0; i < handle->num_rules; i++) { + if (atomic_read(&handle->rule[i]->node.refcount) == 1) + tree_add_node(&handle->rule[i]->node, &fte->node); + } +unlock_fte: + unlock_ref_node(&fte->node); unlock_fg: unlock_ref_node(&fg->node); - return rule; + return handle; } -struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_rule *rule) +struct mlx5_fc *mlx5_flow_rule_counter(struct mlx5_flow_handle *handle) { struct mlx5_flow_rule *dst; struct fs_fte *fte; - fs_get_obj(fte, rule->node.parent); + fs_get_obj(fte, handle->rule[0]->node.parent); fs_for_each_dst(dst, fte) { if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER) @@ -1167,8 +1306,8 @@ static bool counter_is_valid(struct mlx5_fc *counter, u32 action) if (!counter) return false; - /* Hardware support counter for a drop action only */ - return action == (MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT); + return (action & (MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST)); } static bool dest_is_valid(struct mlx5_flow_destination *dest, @@ -1188,18 +1327,22 @@ static bool dest_is_valid(struct mlx5_flow_destination *dest, return true; } -static struct mlx5_flow_rule * -_mlx5_add_flow_rule(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, - u32 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) +static struct mlx5_flow_handle * +_mlx5_add_flow_rules(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec, + struct mlx5_flow_act *flow_act, + struct mlx5_flow_destination *dest, + int dest_num) + { struct mlx5_flow_group *g; - struct mlx5_flow_rule *rule; + struct mlx5_flow_handle *rule; + int i; - if (!dest_is_valid(dest, action, ft)) - return ERR_PTR(-EINVAL); + for (i = 0; i < dest_num; i++) { + if (!dest_is_valid(&dest[i], flow_act->action, ft)) + return ERR_PTR(-EINVAL); + } nested_lock_ref_node(&ft->node, FS_MUTEX_GRANDPARENT); fs_for_each_fg(g, ft) @@ -1208,7 +1351,7 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft, g->mask.match_criteria, spec->match_criteria)) { rule = add_rule_fg(g, spec->match_value, - action, flow_tag, dest); + flow_act, dest, dest_num); if (!IS_ERR(rule) || PTR_ERR(rule) != -ENOSPC) goto unlock; } @@ -1220,8 +1363,7 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft, goto unlock; } - rule = add_rule_fg(g, spec->match_value, - action, flow_tag, dest); + rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num); if (IS_ERR(rule)) { /* Remove assumes refcount > 0 and autogroup creates a group * with a refcount = 0. @@ -1242,22 +1384,22 @@ static bool fwd_next_prio_supported(struct mlx5_flow_table *ft) (MLX5_CAP_FLOWTABLE(get_dev(&ft->node), nic_rx_multi_path_tirs))); } -struct mlx5_flow_rule * -mlx5_add_flow_rule(struct mlx5_flow_table *ft, - struct mlx5_flow_spec *spec, - u32 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) +struct mlx5_flow_handle * +mlx5_add_flow_rules(struct mlx5_flow_table *ft, + struct mlx5_flow_spec *spec, + struct mlx5_flow_act *flow_act, + struct mlx5_flow_destination *dest, + int dest_num) { struct mlx5_flow_root_namespace *root = find_root(&ft->node); struct mlx5_flow_destination gen_dest; struct mlx5_flow_table *next_ft = NULL; - struct mlx5_flow_rule *rule = NULL; - u32 sw_action = action; + struct mlx5_flow_handle *handle = NULL; + u32 sw_action = flow_act->action; struct fs_prio *prio; fs_get_obj(prio, ft->node.parent); - if (action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { + if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { if (!fwd_next_prio_supported(ft)) return ERR_PTR(-EOPNOTSUPP); if (dest) @@ -1268,34 +1410,40 @@ mlx5_add_flow_rule(struct mlx5_flow_table *ft, gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; gen_dest.ft = next_ft; dest = &gen_dest; - action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + dest_num = 1; + flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; } else { mutex_unlock(&root->chain_lock); return ERR_PTR(-EOPNOTSUPP); } } - rule = _mlx5_add_flow_rule(ft, spec, action, flow_tag, dest); + handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, dest_num); if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { - if (!IS_ERR_OR_NULL(rule) && - (list_empty(&rule->next_ft))) { + if (!IS_ERR_OR_NULL(handle) && + (list_empty(&handle->rule[0]->next_ft))) { mutex_lock(&next_ft->lock); - list_add(&rule->next_ft, &next_ft->fwd_rules); + list_add(&handle->rule[0]->next_ft, + &next_ft->fwd_rules); mutex_unlock(&next_ft->lock); - rule->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO; + handle->rule[0]->sw_action = MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO; } mutex_unlock(&root->chain_lock); } - return rule; + return handle; } -EXPORT_SYMBOL(mlx5_add_flow_rule); +EXPORT_SYMBOL(mlx5_add_flow_rules); -void mlx5_del_flow_rule(struct mlx5_flow_rule *rule) +void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) { - tree_remove_node(&rule->node); + int i; + + for (i = handle->num_rules - 1; i >= 0; i--) + tree_remove_node(&handle->rule[i]->node); + kfree(handle); } -EXPORT_SYMBOL(mlx5_del_flow_rule); +EXPORT_SYMBOL(mlx5_del_flow_rules); /* Assuming prio->node.children(flow tables) is sorted by level */ static struct mlx5_flow_table *find_next_ft(struct mlx5_flow_table *ft) @@ -1675,7 +1823,7 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering) ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR); if (!ns) return -EINVAL; - ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL); + ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL, 0); if (IS_ERR(ft)) { mlx5_core_err(steering->dev, "Failed to create last anchor flow table"); return PTR_ERR(ft); @@ -1687,7 +1835,7 @@ 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_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 71ff03bceabb..8e668c63f69e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -94,6 +94,11 @@ struct mlx5_flow_rule { u32 sw_action; }; +struct mlx5_flow_handle { + int num_rules; + struct mlx5_flow_rule *rule[]; +}; + /* Type of children is mlx5_flow_group */ struct mlx5_flow_table { struct fs_node node; @@ -112,6 +117,7 @@ struct mlx5_flow_table { struct mutex lock; /* FWD rules that point on this flow table */ struct list_head fwd_rules; + u32 flags; }; struct mlx5_fc_cache { @@ -145,6 +151,7 @@ struct fs_fte { u32 flow_tag; u32 index; u32 action; + u32 encap_id; enum fs_fte_status status; struct mlx5_fc *counter; }; 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..7b4c339a8a9a 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 { @@ -175,6 +174,41 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili) return err; } +static void mlx5_set_driver_version(struct mlx5_core_dev *dev) +{ + int driver_ver_sz = MLX5_FLD_SZ_BYTES(set_driver_version_in, + driver_version); + u8 in[MLX5_ST_SZ_BYTES(set_driver_version_in)] = {0}; + u8 out[MLX5_ST_SZ_BYTES(set_driver_version_out)] = {0}; + int remaining_size = driver_ver_sz; + char *string; + + if (!MLX5_CAP_GEN(dev, driver_version)) + return; + + string = MLX5_ADDR_OF(set_driver_version_in, in, driver_version); + + strncpy(string, "Linux", remaining_size); + + remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); + strncat(string, ",", remaining_size); + + remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); + strncat(string, DRIVER_NAME, remaining_size); + + remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); + strncat(string, ",", remaining_size); + + remaining_size = max_t(int, 0, driver_ver_sz - strlen(string)); + strncat(string, DRIVER_VERSION, remaining_size); + + /*Send the command*/ + MLX5_SET(set_driver_version_in, in, opcode, + MLX5_CMD_OP_SET_DRIVER_VERSION); + + mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + static int set_dma_caps(struct pci_dev *pdev) { int err; @@ -733,13 +767,15 @@ 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 +789,8 @@ 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 +881,6 @@ 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"); @@ -1021,8 +1052,16 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_pagealloc_stop; } + mlx5_set_driver_version(dev); + 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; @@ -1202,6 +1241,8 @@ static const struct devlink_ops mlx5_devlink_ops = { #ifdef CONFIG_MLX5_CORE_EN .eswitch_mode_set = mlx5_devlink_eswitch_mode_set, .eswitch_mode_get = mlx5_devlink_eswitch_mode_get, + .eswitch_inline_mode_set = mlx5_devlink_eswitch_inline_mode_set, + .eswitch_inline_mode_get = mlx5_devlink_eswitch_inline_mode_get, #endif }; @@ -1226,15 +1267,9 @@ 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 +1348,16 @@ 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 +1414,6 @@ 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); @@ -1422,11 +1458,24 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */ { PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */ { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */ + { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5, PCIe 4.0 VF */ { 0, } }; 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 +1486,22 @@ 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..e0a8fbdd1446 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, ...) \ @@ -75,14 +75,21 @@ 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); int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev); void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); +void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe); 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); @@ -91,6 +98,13 @@ int mlx5_core_sriov_configure(struct pci_dev *dev, int num_vfs); bool mlx5_sriov_is_enabled(struct mlx5_core_dev *dev); int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id); int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id); +int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, + void *context, u32 *element_id); +int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, + void *context, u32 element_id, + u32 modify_bitmask); +int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, + u32 element_id); int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); cycle_t mlx5_read_internal_timer(struct mlx5_core_dev *dev); u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx); @@ -113,6 +127,12 @@ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev); void mlx5_dev_list_lock(void); void mlx5_dev_list_unlock(void); int mlx5_dev_list_trylock(void); +int mlx5_encap_alloc(struct mlx5_core_dev *dev, + int header_type, + size_t size, + void *encap_header, + u32 *encap_id); +void mlx5_encap_dealloc(struct mlx5_core_dev *dev, u32 encap_id); bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv); 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/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 34e7184e23c9..d2ec9d232a70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -548,6 +548,26 @@ int mlx5_max_tc(struct mlx5_core_dev *mdev) return num_tc - 1; } +int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out) +{ + u32 in[MLX5_ST_SZ_DW(dcbx_param)] = {0}; + + MLX5_SET(dcbx_param, in, port_number, 1); + + return mlx5_core_access_reg(mdev, in, sizeof(in), out, + sizeof(in), MLX5_REG_DCBX_PARAM, 0, 0); +} + +int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in) +{ + u32 out[MLX5_ST_SZ_DW(dcbx_param)]; + + MLX5_SET(dcbx_param, in, port_number, 1); + + return mlx5_core_access_reg(mdev, in, sizeof(out), out, + sizeof(out), MLX5_REG_DCBX_PARAM, 0, 1); +} + int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc) { u32 in[MLX5_ST_SZ_DW(qtct_reg)] = {0}; @@ -572,6 +592,28 @@ int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc) } EXPORT_SYMBOL_GPL(mlx5_set_port_prio_tc); +int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev, + u8 prio, u8 *tc) +{ + u32 in[MLX5_ST_SZ_DW(qtct_reg)]; + u32 out[MLX5_ST_SZ_DW(qtct_reg)]; + int err; + + memset(in, 0, sizeof(in)); + memset(out, 0, sizeof(out)); + + MLX5_SET(qtct_reg, in, port_number, 1); + MLX5_SET(qtct_reg, in, prio, prio); + + err = mlx5_core_access_reg(mdev, in, sizeof(in), out, + sizeof(out), MLX5_REG_QTCT, 0, 0); + if (!err) + *tc = MLX5_GET(qtct_reg, out, tclass); + + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc); + static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in, int inlen) { @@ -625,6 +667,27 @@ int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw) } EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc); +int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev, + u8 tc, u8 *bw_pct) +{ + u32 out[MLX5_ST_SZ_DW(qetc_reg)]; + void *ets_tcn_conf; + int err; + + err = mlx5_query_port_qetcr_reg(mdev, out, sizeof(out)); + if (err) + return err; + + ets_tcn_conf = MLX5_ADDR_OF(qetc_reg, out, + tc_configuration[tc]); + + *bw_pct = MLX5_GET(ets_tcn_config_reg, ets_tcn_conf, + bw_allocation); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_query_port_tc_bw_alloc); + int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, u8 *max_bw_value, u8 *max_bw_units) @@ -746,3 +809,60 @@ void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported, *supported = !!(MLX5_GET(pcmr_reg, out, fcs_cap)); *enabled = !!(MLX5_GET(pcmr_reg, out, fcs_chk)); } + +static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = { + "Cable plugged", /* MLX5_MODULE_STATUS_PLUGGED = 0x1 */ + "Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED = 0x2 */ + "Cable error", /* MLX5_MODULE_STATUS_ERROR = 0x3 */ +}; + +static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = { + "Power budget exceeded", + "Long Range for non MLNX cable", + "Bus stuck(I2C or data shorted)", + "No EEPROM/retry timeout", + "Enforce part number list", + "Unknown identifier", + "High Temperature", + "Bad or shorted cable/module", + "Unknown status", +}; + +void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) +{ + enum port_module_event_status_type module_status; + enum port_module_event_error_type error_type; + struct mlx5_eqe_port_module *module_event_eqe; + struct mlx5_priv *priv = &dev->priv; + u8 module_num; + + module_event_eqe = &eqe->data.port_module; + module_num = module_event_eqe->module; + module_status = module_event_eqe->module_status & + PORT_MODULE_EVENT_MODULE_STATUS_MASK; + error_type = module_event_eqe->error_type & + PORT_MODULE_EVENT_ERROR_TYPE_MASK; + + if (module_status < MLX5_MODULE_STATUS_ERROR) { + priv->pme_stats.status_counters[module_status - 1]++; + } else if (module_status == MLX5_MODULE_STATUS_ERROR) { + if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN) + /* Unknown error type */ + error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN; + priv->pme_stats.error_counters[error_type]++; + } + + if (!printk_ratelimit()) + return; + + if (module_status < MLX5_MODULE_STATUS_ERROR) + mlx5_core_info(dev, + "Port module event: module %u, %s\n", + module_num, mlx5_pme_status[module_status - 1]); + + else if (module_status == MLX5_MODULE_STATUS_ERROR) + mlx5_core_info(dev, + "Port module event[error]: module %u, %s, %s\n", + module_num, mlx5_pme_status[module_status - 1], + mlx5_pme_error[error_type]); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c index 104902a93a0b..e651e4c02867 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c @@ -36,6 +36,71 @@ #include <linux/mlx5/cmd.h> #include "mlx5_core.h" +/* Scheduling element fw management */ +int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, + void *ctx, u32 *element_id) +{ + u32 in[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {0}; + void *schedc; + int err; + + schedc = MLX5_ADDR_OF(create_scheduling_element_in, in, + scheduling_context); + MLX5_SET(create_scheduling_element_in, in, opcode, + MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT); + MLX5_SET(create_scheduling_element_in, in, scheduling_hierarchy, + hierarchy); + memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context)); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *element_id = MLX5_GET(create_scheduling_element_out, out, + scheduling_element_id); + return 0; +} + +int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, + void *ctx, u32 element_id, + u32 modify_bitmask) +{ + u32 in[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {0}; + void *schedc; + + schedc = MLX5_ADDR_OF(modify_scheduling_element_in, in, + scheduling_context); + MLX5_SET(modify_scheduling_element_in, in, opcode, + MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT); + MLX5_SET(modify_scheduling_element_in, in, scheduling_element_id, + element_id); + MLX5_SET(modify_scheduling_element_in, in, modify_bitmask, + modify_bitmask); + MLX5_SET(modify_scheduling_element_in, in, scheduling_hierarchy, + hierarchy); + memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context)); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, + u32 element_id) +{ + u32 in[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {0}; + + MLX5_SET(destroy_scheduling_element_in, in, opcode, + MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT); + MLX5_SET(destroy_scheduling_element_in, in, scheduling_element_id, + element_id); + MLX5_SET(destroy_scheduling_element_in, in, scheduling_hierarchy, + hierarchy); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + /* Finds an entry where we can register the given rate * If the rate already exists, return the entry where it is registered, * otherwise return the first available entry. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 525f17af108e..269e4401c342 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -113,15 +113,17 @@ static int mlx5_modify_nic_vport_context(struct mlx5_core_dev *mdev, void *in, return mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); } -void mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, - u8 *min_inline_mode) +int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, + u16 vport, u8 *min_inline) { u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {0}; + int err; - mlx5_query_nic_vport_context(mdev, 0, out, sizeof(out)); - - *min_inline_mode = MLX5_GET(query_nic_vport_context_out, out, - nic_vport_context.min_wqe_inline_mode); + err = mlx5_query_nic_vport_context(mdev, vport, out, sizeof(out)); + if (!err) + *min_inline = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.min_wqe_inline_mode); + return err; } EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_min_inline); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 821a087c7ae2..921673c42bc9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -101,13 +101,15 @@ err_db_free: int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *cqc, struct mlx5_cqwq *wq, - struct mlx5_wq_ctrl *wq_ctrl) + struct mlx5_frag_wq_ctrl *wq_ctrl) { int err; - wq->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz); - wq->log_sz = MLX5_GET(cqc, cqc, log_cq_size); - wq->sz_m1 = (1 << wq->log_sz) - 1; + wq->log_stride = 6 + MLX5_GET(cqc, cqc, cqe_sz); + wq->log_sz = MLX5_GET(cqc, cqc, log_cq_size); + wq->sz_m1 = (1 << wq->log_sz) - 1; + wq->log_frag_strides = PAGE_SHIFT - wq->log_stride; + wq->frag_sz_m1 = (1 << wq->log_frag_strides) - 1; err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -115,14 +117,16 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, return err; } - err = mlx5_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq), - &wq_ctrl->buf, param->buf_numa_node); + err = mlx5_frag_buf_alloc_node(mdev, mlx5_cqwq_get_byte_size(wq), + &wq_ctrl->frag_buf, + param->buf_numa_node); if (err) { - mlx5_core_warn(mdev, "mlx5_buf_alloc_node() failed, %d\n", err); + mlx5_core_warn(mdev, "mlx5_frag_buf_alloc_node() failed, %d\n", + err); goto err_db_free; } - wq->buf = wq_ctrl->buf.direct.buf; + wq->frag_buf = wq_ctrl->frag_buf; wq->db = wq_ctrl->db.db; wq_ctrl->mdev = mdev; @@ -184,3 +188,9 @@ void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl) mlx5_buf_free(wq_ctrl->mdev, &wq_ctrl->buf); mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db); } + +void mlx5_cqwq_destroy(struct mlx5_frag_wq_ctrl *wq_ctrl) +{ + mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->frag_buf); + mlx5_db_free(wq_ctrl->mdev, &wq_ctrl->db); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 6c2a8f95093c..d8afed898c31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -47,6 +47,12 @@ struct mlx5_wq_ctrl { struct mlx5_db db; }; +struct mlx5_frag_wq_ctrl { + struct mlx5_core_dev *mdev; + struct mlx5_frag_buf frag_buf; + struct mlx5_db db; +}; + struct mlx5_wq_cyc { void *buf; __be32 *db; @@ -55,12 +61,14 @@ struct mlx5_wq_cyc { }; struct mlx5_cqwq { - void *buf; + struct mlx5_frag_buf frag_buf; __be32 *db; u32 sz_m1; + u32 frag_sz_m1; u32 cc; /* consumer counter */ u8 log_sz; u8 log_stride; + u8 log_frag_strides; }; struct mlx5_wq_ll { @@ -81,7 +89,7 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *cqc, struct mlx5_cqwq *wq, - struct mlx5_wq_ctrl *wq_ctrl); + struct mlx5_frag_wq_ctrl *wq_ctrl); u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq); int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, @@ -90,6 +98,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq); void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl); +void mlx5_cqwq_destroy(struct mlx5_frag_wq_ctrl *wq_ctrl); static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr) { @@ -116,7 +125,10 @@ static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq) static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix) { - return wq->buf + (ix << wq->log_stride); + unsigned int frag = (ix >> wq->log_frag_strides); + + return wq->frag_buf.frags[frag].buf + + ((wq->frag_sz_m1 & ix) << wq->log_stride); } static inline u32 mlx5_cqwq_get_wrap_cnt(struct mlx5_cqwq *wq) |