diff options
Diffstat (limited to 'drivers/net/ethernet/mellanox')
32 files changed, 576 insertions, 316 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1d91a0d0ab1d..2d1f4b3be9bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -69,12 +69,10 @@ enum { MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10, }; -static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, - struct mlx5_cmd_msg *in, - struct mlx5_cmd_msg *out, - void *uout, int uout_size, - mlx5_cmd_cbk_t cbk, - void *context, int page_queue) +static struct mlx5_cmd_work_ent * +cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, + struct mlx5_cmd_msg *out, void *uout, int uout_size, + mlx5_cmd_cbk_t cbk, void *context, int page_queue) { gfp_t alloc_flags = cbk ? GFP_ATOMIC : GFP_KERNEL; struct mlx5_cmd_work_ent *ent; @@ -83,6 +81,7 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, if (!ent) return ERR_PTR(-ENOMEM); + ent->idx = -EINVAL; ent->in = in; ent->out = out; ent->uout = uout; @@ -91,10 +90,16 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, ent->context = context; ent->cmd = cmd; ent->page_queue = page_queue; + refcount_set(&ent->refcnt, 1); return ent; } +static void cmd_free_ent(struct mlx5_cmd_work_ent *ent) +{ + kfree(ent); +} + static u8 alloc_token(struct mlx5_cmd *cmd) { u8 token; @@ -109,7 +114,7 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int alloc_ent(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd) { unsigned long flags; int ret; @@ -123,7 +128,7 @@ static int alloc_ent(struct mlx5_cmd *cmd) return ret < cmd->max_reg_cmds ? ret : -ENOMEM; } -static void free_ent(struct mlx5_cmd *cmd, int idx) +static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { unsigned long flags; @@ -132,6 +137,22 @@ static void free_ent(struct mlx5_cmd *cmd, int idx) spin_unlock_irqrestore(&cmd->alloc_lock, flags); } +static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) +{ + refcount_inc(&ent->refcnt); +} + +static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) +{ + if (!refcount_dec_and_test(&ent->refcnt)) + return; + + if (ent->idx >= 0) + cmd_free_index(ent->cmd, ent->idx); + + cmd_free_ent(ent); +} + static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) { return cmd->cmd_buf + (idx << cmd->log_stride); @@ -219,11 +240,6 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent) ent->ret = -ETIMEDOUT; } -static void free_cmd(struct mlx5_cmd_work_ent *ent) -{ - kfree(ent); -} - static int verify_signature(struct mlx5_cmd_work_ent *ent) { struct mlx5_cmd_mailbox *next = ent->out->next; @@ -837,11 +853,22 @@ static void cb_timeout_handler(struct work_struct *work) struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd); + mlx5_cmd_eq_recover(dev); + + /* Maybe got handled by eq recover ? */ + if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) { + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + goto out; /* phew, already handled */ + } + ent->ret = -ETIMEDOUT; - mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", - mlx5_command_str(msg_to_opcode(ent->in)), - msg_to_opcode(ent->in)); + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n", + ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + +out: + cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */ } static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg); @@ -856,6 +883,32 @@ static bool opcode_allowed(struct mlx5_cmd *cmd, u16 opcode) return cmd->allowed_opcode == opcode; } +static int cmd_alloc_index_retry(struct mlx5_cmd *cmd) +{ + unsigned long alloc_end = jiffies + msecs_to_jiffies(1000); + int idx; + +retry: + idx = cmd_alloc_index(cmd); + if (idx < 0 && time_before(jiffies, alloc_end)) { + /* Index allocation can fail on heavy load of commands. This is a temporary + * situation as the current command already holds the semaphore, meaning that + * another command completion is being handled and it is expected to release + * the entry index soon. + */ + cpu_relax(); + goto retry; + } + return idx; +} + +bool mlx5_cmd_is_down(struct mlx5_core_dev *dev) +{ + return pci_channel_offline(dev->pdev) || + dev->cmd.state != MLX5_CMDIF_STATE_UP || + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR; +} + static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); @@ -873,14 +926,14 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { - alloc_ret = alloc_ent(cmd); + alloc_ret = cmd_alloc_index_retry(cmd); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { ent->callback(-EAGAIN, ent->context); mlx5_free_cmd_msg(dev, ent->out); free_msg(dev, ent->in); - free_cmd(ent); + cmd_ent_put(ent); } else { ent->ret = -EAGAIN; complete(&ent->done); @@ -916,15 +969,12 @@ static void cmd_work_handler(struct work_struct *work) ent->ts1 = ktime_get_ns(); cmd_mode = cmd->mode; - if (ent->callback) - schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout)) + cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); /* Skip sending command to fw if internal error */ - if (pci_channel_offline(dev->pdev) || - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR || - cmd->state != MLX5_CMDIF_STATE_UP || - !opcode_allowed(&dev->cmd, ent->op)) { + if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) { u8 status = 0; u32 drv_synd; @@ -933,13 +983,10 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); - /* no doorbell, no need to keep the entry */ - free_ent(cmd, ent->idx); - if (ent->callback) - free_cmd(ent); return; } + cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -983,6 +1030,35 @@ static const char *deliv_status_to_str(u8 status) } } +enum { + MLX5_CMD_TIMEOUT_RECOVER_MSEC = 5 * 1000, +}; + +static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, + struct mlx5_cmd_work_ent *ent) +{ + unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_RECOVER_MSEC); + + mlx5_cmd_eq_recover(dev); + + /* Re-wait on the ent->done after executing the recovery flow. If the + * recovery flow (or any other recovery flow running simultaneously) + * has recovered an EQE, it should cause the entry to be completed by + * the command interface. + */ + if (wait_for_completion_timeout(&ent->done, timeout)) { + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + return; + } + + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + + ent->ret = -ETIMEDOUT; + mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); +} + static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); @@ -994,12 +1070,10 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) ent->ret = -ECANCELED; goto out_err; } - if (cmd->mode == CMD_MODE_POLLING || ent->polling) { + if (cmd->mode == CMD_MODE_POLLING || ent->polling) wait_for_completion(&ent->done); - } else if (!wait_for_completion_timeout(&ent->done, timeout)) { - ent->ret = -ETIMEDOUT; - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); - } + else if (!wait_for_completion_timeout(&ent->done, timeout)) + wait_func_handle_exec_timeout(dev, ent); out_err: err = ent->ret; @@ -1039,11 +1113,16 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (callback && page_queue) return -EINVAL; - ent = alloc_cmd(cmd, in, out, uout, uout_size, callback, context, - page_queue); + ent = cmd_alloc_ent(cmd, in, out, uout, uout_size, + callback, context, page_queue); if (IS_ERR(ent)) return PTR_ERR(ent); + /* put for this ent is when consumed, depending on the use case + * 1) (!callback) blocking flow: by caller after wait_func completes + * 2) (callback) flow: by mlx5_cmd_comp_handler() when ent is handled + */ + ent->token = token; ent->polling = force_polling; @@ -1062,12 +1141,10 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, } if (callback) - goto out; + goto out; /* mlx5_cmd_comp_handler() will put(ent) */ err = wait_func(dev, ent); - if (err == -ETIMEDOUT) - goto out; - if (err == -ECANCELED) + if (err == -ETIMEDOUT || err == -ECANCELED) goto out_free; ds = ent->ts2 - ent->ts1; @@ -1085,7 +1162,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, *status = ent->status; out_free: - free_cmd(ent); + cmd_ent_put(ent); out: return err; } @@ -1516,14 +1593,19 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force if (!forced) { mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n", ent->idx); - free_ent(cmd, ent->idx); - free_cmd(ent); + cmd_ent_put(ent); } continue; } - if (ent->callback) - cancel_delayed_work(&ent->cb_timeout_work); + if (ent->callback && cancel_delayed_work(&ent->cb_timeout_work)) + cmd_ent_put(ent); /* timeout work was canceled */ + + if (!forced || /* Real FW completion */ + pci_channel_offline(dev->pdev) || /* FW is inaccessible */ + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + cmd_ent_put(ent); + if (ent->page_queue) sem = &cmd->pages_sem; else @@ -1545,10 +1627,6 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force ent->ret, deliv_status_to_str(ent->status), ent->status); } - /* only real completion will free the entry slot */ - if (!forced) - free_ent(cmd, ent->idx); - if (ent->callback) { ds = ent->ts2 - ent->ts1; if (ent->op < MLX5_CMD_OP_MAX) { @@ -1576,10 +1654,13 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force free_msg(dev, ent->in); err = err ? err : ent->status; - if (!forced) - free_cmd(ent); + /* final consumer is done, release ent */ + cmd_ent_put(ent); callback(err, context); } else { + /* release wait_func() so mlx5_cmd_invoke() + * can make the final ent_put() + */ complete(&ent->done); } up(sem); @@ -1589,8 +1670,11 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) { + struct mlx5_cmd *cmd = &dev->cmd; + unsigned long bitmask; unsigned long flags; u64 vector; + int i; /* wait for pending handlers to complete */ mlx5_eq_synchronize_cmd_irq(dev); @@ -1599,11 +1683,20 @@ void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) if (!vector) goto no_trig; + bitmask = vector; + /* we must increment the allocated entries refcount before triggering the completions + * to guarantee pending commands will not get freed in the meanwhile. + * For that reason, it also has to be done inside the alloc_lock. + */ + for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + cmd_ent_get(cmd->ent_arr[i]); vector |= MLX5_TRIGGERED_CMD_COMP; spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); mlx5_core_dbg(dev, "vector 0x%llx\n", vector); mlx5_cmd_comp_handler(dev, vector, true); + for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + cmd_ent_put(cmd->ent_arr[i]); return; no_trig: @@ -1711,10 +1804,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, u8 token; opcode = MLX5_GET(mbox_in, in, opcode); - if (pci_channel_offline(dev->pdev) || - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR || - dev->cmd.state != MLX5_CMDIF_STATE_UP || - !opcode_allowed(&dev->cmd, opcode)) { + if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) { err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status); MLX5_SET(mbox_out, out, status, status); MLX5_SET(mbox_out, out, syndrome, drv_synd); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0cc2080fd847..356f5852955f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -91,7 +91,12 @@ struct page_pool; #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER) #define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) -#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8)) +/* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between + * WQEs, This page will absorb write overflow by the hardware, when + * receiving packets larger than MTU. These oversize packets are + * dropped by the driver at a later stage. + */ +#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8)) #define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS)) #define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS) #define MLX5E_MAX_RQ_NUM_MTTS \ @@ -600,7 +605,7 @@ struct mlx5e_rq { struct dim dim; /* Dynamic Interrupt Moderation */ /* XDP */ - struct bpf_prog *xdp_prog; + struct bpf_prog __rcu *xdp_prog; struct mlx5e_xdpsq *xdpsq; DECLARE_BITMAP(flags, 8); struct page_pool *page_pool; @@ -617,6 +622,7 @@ struct mlx5e_rq { u32 rqn; struct mlx5_core_dev *mdev; struct mlx5_core_mkey umr_mkey; + struct mlx5e_dma_info wqe_overflow; /* XDP read-mostly */ struct xdp_rxq_info xdp_rxq; @@ -1005,7 +1011,6 @@ int mlx5e_update_nic_rx(struct mlx5e_priv *priv); void mlx5e_update_carrier(struct mlx5e_priv *priv); int mlx5e_close(struct net_device *netdev); int mlx5e_open(struct net_device *netdev); -void mlx5e_update_ndo_stats(struct mlx5e_priv *priv); void mlx5e_queue_update_stats(struct mlx5e_priv *priv); int mlx5e_bits_invert(unsigned long a, int size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 8fe8b4d6ad1c..254c84739046 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -51,7 +51,7 @@ static void mlx5e_monitor_counters_work(struct work_struct *work) monitor_counters_work); mutex_lock(&priv->state_lock); - mlx5e_update_ndo_stats(priv); + mlx5e_stats_update_ndo_stats(priv); mutex_unlock(&priv->state_lock); mlx5e_monitor_counter_arm(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 5de1cb9f5330..308fd279669e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -490,11 +490,8 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy) int err; int i; - if (!MLX5_CAP_GEN(dev, pcam_reg)) - return -EOPNOTSUPP; - - if (!MLX5_CAP_PCAM_REG(dev, pplm)) - return -EOPNOTSUPP; + if (!MLX5_CAP_GEN(dev, pcam_reg) || !MLX5_CAP_PCAM_REG(dev, pplm)) + return false; MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); @@ -572,6 +569,9 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane) return -EOPNOTSUPP; + if (fec_policy && !mlx5e_fec_in_caps(dev, fec_policy)) + return -EOPNOTSUPP; + MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index 906292035088..58e27038c947 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -110,11 +110,25 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work) rtnl_unlock(); } +struct neigh_update_work { + struct work_struct work; + struct neighbour *n; + struct mlx5e_neigh_hash_entry *nhe; +}; + +static void mlx5e_release_neigh_update_work(struct neigh_update_work *update_work) +{ + neigh_release(update_work->n); + mlx5e_rep_neigh_entry_release(update_work->nhe); + kfree(update_work); +} + static void mlx5e_rep_neigh_update(struct work_struct *work) { - struct mlx5e_neigh_hash_entry *nhe = - container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work); - struct neighbour *n = nhe->n; + struct neigh_update_work *update_work = container_of(work, struct neigh_update_work, + work); + struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; + struct neighbour *n = update_work->n; struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; struct mlx5e_priv *priv; @@ -146,30 +160,42 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) mlx5e_rep_update_flows(priv, e, neigh_connected, ha); mlx5e_encap_put(priv, e); } - mlx5e_rep_neigh_entry_release(nhe); rtnl_unlock(); - neigh_release(n); + mlx5e_release_neigh_update_work(update_work); } -static void mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv, - struct mlx5e_neigh_hash_entry *nhe, - struct neighbour *n) +static struct neigh_update_work *mlx5e_alloc_neigh_update_work(struct mlx5e_priv *priv, + struct neighbour *n) { - /* Take a reference to ensure the neighbour and mlx5 encap - * entry won't be destructed until we drop the reference in - * delayed work. - */ - neigh_hold(n); + struct neigh_update_work *update_work; + struct mlx5e_neigh_hash_entry *nhe; + struct mlx5e_neigh m_neigh = {}; - /* This assignment is valid as long as the the neigh reference - * is taken - */ - nhe->n = n; + update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC); + if (WARN_ON(!update_work)) + return NULL; - if (!queue_work(priv->wq, &nhe->neigh_update_work)) { - mlx5e_rep_neigh_entry_release(nhe); - neigh_release(n); + m_neigh.dev = n->dev; + m_neigh.family = n->ops->family; + memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len); + + /* Obtain reference to nhe as last step in order not to release it in + * atomic context. + */ + rcu_read_lock(); + nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh); + rcu_read_unlock(); + if (!nhe) { + kfree(update_work); + return NULL; } + + INIT_WORK(&update_work->work, mlx5e_rep_neigh_update); + neigh_hold(n); + update_work->n = n; + update_work->nhe = nhe; + + return update_work; } static int mlx5e_rep_netevent_event(struct notifier_block *nb, @@ -181,7 +207,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_neigh_hash_entry *nhe = NULL; - struct mlx5e_neigh m_neigh = {}; + struct neigh_update_work *update_work; struct neigh_parms *p; struct neighbour *n; bool found = false; @@ -196,17 +222,11 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, #endif return NOTIFY_DONE; - m_neigh.dev = n->dev; - m_neigh.family = n->ops->family; - memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len); - - rcu_read_lock(); - nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh); - rcu_read_unlock(); - if (!nhe) + update_work = mlx5e_alloc_neigh_update_work(priv, n); + if (!update_work) return NOTIFY_DONE; - mlx5e_rep_queue_neigh_update_work(priv, nhe, n); + queue_work(priv->wq, &update_work->work); break; case NETEVENT_DELAY_PROBE_TIME_UPDATE: @@ -352,7 +372,6 @@ int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv, (*nhe)->priv = priv; memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh)); - INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update); spin_lock_init(&(*nhe)->encap_list_lock); INIT_LIST_HEAD(&(*nhe)->encap_list); refcount_set(&(*nhe)->refcnt, 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index c6bc9224c3b1..a8be40cbe325 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -246,8 +246,10 @@ mlx5_tc_ct_rule_to_tuple_nat(struct mlx5_ct_tuple *tuple, case FLOW_ACT_MANGLE_HDR_TYPE_IP6: ip6_offset = (offset - offsetof(struct ipv6hdr, saddr)); ip6_offset /= 4; - if (ip6_offset < 8) + if (ip6_offset < 4) tuple->ip.src_v6.s6_addr32[ip6_offset] = cpu_to_be32(val); + else if (ip6_offset < 8) + tuple->ip.dst_v6.s6_addr32[ip6_offset - 4] = cpu_to_be32(val); else return -EOPNOTSUPP; break; @@ -699,6 +701,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, err_rule: mlx5e_mod_hdr_detach(ct_priv->esw->dev, &esw->offloads.mod_hdr, zone_rule->mh); + mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); err_mod_hdr: kfree(spec); return err; @@ -958,12 +961,22 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, return 0; } +void mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) +{ + struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); + + if (!ct_priv || !ct_attr->ct_labels_id) + return; + + mapping_remove(ct_priv->labels_mapping, ct_attr->ct_labels_id); +} + int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack) +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack) { struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); struct flow_rule *rule = flow_cls_offload_flow_rule(f); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 3baef917a677..708c216325d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -87,12 +87,15 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv); void mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv); +void +mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr); + int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack); +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack); int mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec); @@ -130,12 +133,15 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv) { } +static inline void +mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) {} + static inline int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack) +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 9334c9c3e208..24336c60123a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -20,6 +20,11 @@ enum mlx5e_icosq_wqe_type { }; /* General */ +static inline bool mlx5e_skb_is_multicast(struct sk_buff *skb) +{ + return skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST; +} + void mlx5e_trigger_irq(struct mlx5e_icosq *sq); void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe); void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 0e6946fc121f..b28df21981a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -122,7 +122,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, u32 *len, struct xdp_buff *xdp) { - struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct bpf_prog *prog = rcu_dereference(rq->xdp_prog); u32 act; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index a33a1f762c70..40db27bf790b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, { struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk; u32 cqe_bcnt32 = cqe_bcnt; - bool consumed; /* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, xsk_buff_dma_sync_for_cpu(xdp); prefetch(xdp->data); - rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp); - rcu_read_unlock(); - /* Possible flows: * - XDP_REDIRECT to XSKMAP: * The page is owned by the userspace from now. @@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, * allocated first from the Reuse Ring, so it has enough space. */ - if (likely(consumed)) { + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) { if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ @@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, u32 cqe_bcnt) { struct xdp_buff *xdp = wi->di->xsk; - bool consumed; /* wi->offset is not used in this function, because xdp->data and the * DMA address point directly to the necessary place. Furthermore, the @@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, return NULL; } - rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp); - rcu_read_unlock(); - - if (likely(consumed)) + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp))) return NULL; /* page/packet was consumed by XDP */ /* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index dd9df519d383..55e65a438de7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -106,8 +106,7 @@ err_free_cparam: void mlx5e_close_xsk(struct mlx5e_channel *c) { clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state); - napi_synchronize(&c->napi); - synchronize_rcu(); /* Sync with the XSK wakeup. */ + synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */ mlx5e_close_rq(&c->xskrq); mlx5e_close_cq(&c->xskrq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index acf6d80a6bb7..6bbfcf18107d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -234,7 +234,7 @@ mlx5e_get_ktls_rx_priv_ctx(struct tls_context *tls_ctx) /* Re-sync */ /* Runs in work context */ -static struct mlx5_wqe_ctrl_seg * +static int resync_post_get_progress_params(struct mlx5e_icosq *sq, struct mlx5e_ktls_offload_context_rx *priv_rx) { @@ -258,15 +258,19 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) { err = -ENOMEM; - goto err_out; + goto err_free; } buf->priv_rx = priv_rx; BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); + + spin_lock(&sq->channel->async_icosq_lock); + if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { + spin_unlock(&sq->channel->async_icosq_lock); err = -ENOSPC; - goto err_out; + goto err_dma_unmap; } pi = mlx5e_icosq_get_next_pi(sq, 1); @@ -294,12 +298,18 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, }; icosq_fill_wi(sq, pi, &wi); sq->pc++; + mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); + spin_unlock(&sq->channel->async_icosq_lock); - return cseg; + return 0; +err_dma_unmap: + dma_unmap_single(pdev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); +err_free: + kfree(buf); err_out: priv_rx->stats->tls_resync_req_skip++; - return ERR_PTR(err); + return err; } /* Function is called with elevated refcount. @@ -309,10 +319,8 @@ static void resync_handle_work(struct work_struct *work) { struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; - struct mlx5_wqe_ctrl_seg *cseg; struct mlx5e_channel *c; struct mlx5e_icosq *sq; - struct mlx5_wq_cyc *wq; resync = container_of(work, struct mlx5e_ktls_rx_resync_ctx, work); priv_rx = container_of(resync, struct mlx5e_ktls_offload_context_rx, resync); @@ -324,18 +332,9 @@ static void resync_handle_work(struct work_struct *work) c = resync->priv->channels.c[priv_rx->rxq]; sq = &c->async_icosq; - wq = &sq->wq; - - spin_lock(&c->async_icosq_lock); - cseg = resync_post_get_progress_params(sq, priv_rx); - if (IS_ERR(cseg)) { + if (resync_post_get_progress_params(sq, priv_rx)) refcount_dec(&resync->refcnt); - goto unlock; - } - mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg); -unlock: - spin_unlock(&c->async_icosq_lock); } static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync, @@ -386,16 +385,17 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; u8 tracker_state, auth_state, *ctx; + struct device *dev; u32 hw_seq; priv_rx = buf->priv_rx; resync = &priv_rx->resync; - + dev = resync->priv->mdev->device; if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) goto out; - dma_sync_single_for_cpu(resync->priv->mdev->device, buf->dma_addr, - PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, + DMA_FROM_DEVICE); ctx = buf->progress.ctx; tracker_state = MLX5_GET(tls_progress_params, ctx, record_tracker_state); @@ -411,6 +411,7 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, priv_rx->stats->tls_resync_req_end++; out: refcount_dec(&resync->refcnt); + dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); kfree(buf); } @@ -659,7 +660,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) priv_rx = mlx5e_get_ktls_rx_priv_ctx(tls_ctx); set_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags); mlx5e_set_ktls_rx_priv_ctx(tls_ctx, NULL); - napi_synchronize(&priv->channels.c[priv_rx->rxq]->napi); + synchronize_rcu(); /* Sync with NAPI */ if (!cancel_work_sync(&priv_rx->rule.work)) /* completion is needed, as the priv_rx in the add flow * is maintained on the wqe info (wi), not on the socket. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c index 01468ec27446..b949b9a7538b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -35,7 +35,6 @@ #include <net/sock.h> #include "en.h" -#include "accel/tls.h" #include "fpga/sdk.h" #include "en_accel/tls.h" @@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc) +static bool is_tls_atomic_stats(struct mlx5e_priv *priv) +{ + return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev); +} + int mlx5e_tls_get_count(struct mlx5e_priv *priv) { - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; return NUM_TLS_SW_COUNTERS; @@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { unsigned int i, idx = 0; - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) @@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { int i, idx = 0; - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 64d002d92250..1f48f99c0997 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -217,6 +217,9 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv, break; } + if (WARN_ONCE(*rule_p, "VLAN rule already exists type %d", rule_type)) + return 0; + *rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(*rule_p)) { @@ -397,8 +400,7 @@ static void mlx5e_add_vlan_rules(struct mlx5e_priv *priv) for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID) mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i); - if (priv->fs.vlan.cvlan_filter_disabled && - !(priv->netdev->flags & IFF_PROMISC)) + if (priv->fs.vlan.cvlan_filter_disabled) mlx5e_add_any_vid_rules(priv); } @@ -415,8 +417,12 @@ static void mlx5e_del_vlan_rules(struct mlx5e_priv *priv) for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID) mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i); - if (priv->fs.vlan.cvlan_filter_disabled && - !(priv->netdev->flags & IFF_PROMISC)) + WARN_ON_ONCE(!(test_bit(MLX5E_STATE_DESTROYING, &priv->state))); + + /* must be called after DESTROY bit is set and + * set_rx_mode is called and flushed + */ + if (priv->fs.vlan.cvlan_filter_disabled) mlx5e_del_any_vid_rules(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index aebcf73f8546..42ec28e29834 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -158,16 +158,6 @@ static void mlx5e_update_carrier_work(struct work_struct *work) mutex_unlock(&priv->state_lock); } -void mlx5e_update_ndo_stats(struct mlx5e_priv *priv) -{ - int i; - - for (i = mlx5e_nic_stats_grps_num(priv) - 1; i >= 0; i--) - if (mlx5e_nic_stats_grps[i]->update_stats_mask & - MLX5E_NDO_UPDATE_STATS) - mlx5e_nic_stats_grps[i]->update_stats(priv); -} - static void mlx5e_update_stats_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, @@ -256,12 +246,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, u64 npages, u8 page_shift, - struct mlx5_core_mkey *umr_mkey) + struct mlx5_core_mkey *umr_mkey, + dma_addr_t filler_addr) { - int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + struct mlx5_mtt *mtt; + int inlen; void *mkc; u32 *in; int err; + int i; + + inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + sizeof(*mtt) * npages; in = kvzalloc(inlen, GFP_KERNEL); if (!in) @@ -281,6 +276,18 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, MLX5_SET(mkc, mkc, translations_octword_size, MLX5_MTT_OCTW(npages)); MLX5_SET(mkc, mkc, log_page_size, page_shift); + MLX5_SET(create_mkey_in, in, translations_octword_actual_size, + MLX5_MTT_OCTW(npages)); + + /* Initialize the mkey with all MTTs pointing to a default + * page (filler_addr). When the channels are activated, UMR + * WQEs will redirect the RX WQEs to the actual memory from + * the RQ's pool, while the gaps (wqe_overflow) remain mapped + * to the default page. + */ + mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); + for (i = 0 ; i < npages ; i++) + mtt[i].ptag = cpu_to_be64(filler_addr); err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen); @@ -292,7 +299,8 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq { u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq)); - return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey); + return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey, + rq->wqe_overflow.addr); } static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) @@ -360,6 +368,28 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work) mlx5e_reporter_rq_cqe_err(rq); } +static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq) +{ + rq->wqe_overflow.page = alloc_page(GFP_KERNEL); + if (!rq->wqe_overflow.page) + return -ENOMEM; + + rq->wqe_overflow.addr = dma_map_page(rq->pdev, rq->wqe_overflow.page, 0, + PAGE_SIZE, rq->buff.map_dir); + if (dma_mapping_error(rq->pdev, rq->wqe_overflow.addr)) { + __free_page(rq->wqe_overflow.page); + return -ENOMEM; + } + return 0; +} + +static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq) +{ + dma_unmap_page(rq->pdev, rq->wqe_overflow.addr, PAGE_SIZE, + rq->buff.map_dir); + __free_page(rq->wqe_overflow.page); +} + static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -399,16 +429,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (params->xdp_prog) bpf_prog_inc(params->xdp_prog); - rq->xdp_prog = params->xdp_prog; + RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog); rq_xdp_ix = rq->ix; if (xsk) rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK; err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix); if (err < 0) - goto err_rq_wq_destroy; + goto err_rq_xdp_prog; - rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk); pool_size = 1 << params->log_rq_mtu_frames; @@ -417,6 +447,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, &rq->wq_ctrl); if (err) + goto err_rq_xdp; + + err = mlx5e_alloc_mpwqe_rq_drop_page(rq); + if (err) goto err_rq_wq_destroy; rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; @@ -434,18 +468,18 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) - goto err_rq_wq_destroy; + goto err_rq_drop_page; rq->mkey_be = cpu_to_be32(rq->umr_mkey.key); err = mlx5e_rq_alloc_mpwqe_info(rq, c); if (err) - goto err_free; + goto err_rq_mkey; break; default: /* MLX5_WQ_TYPE_CYCLIC */ err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, &rq->wq_ctrl); if (err) - goto err_rq_wq_destroy; + goto err_rq_xdp; rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; @@ -460,19 +494,19 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->wqe.frags) { err = -ENOMEM; - goto err_free; + goto err_rq_wq_destroy; } err = mlx5e_init_di_list(rq, wq_sz, c->cpu); if (err) - goto err_free; + goto err_rq_frags; rq->mkey_be = c->mkey_be; } err = mlx5e_rq_set_handlers(rq, params, xsk); if (err) - goto err_free; + goto err_free_by_rq_type; if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, @@ -496,13 +530,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (IS_ERR(rq->page_pool)) { err = PTR_ERR(rq->page_pool); rq->page_pool = NULL; - goto err_free; + goto err_free_by_rq_type; } err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, rq->page_pool); } if (err) - goto err_free; + goto err_free_by_rq_type; for (i = 0; i < wq_sz; i++) { if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { @@ -552,38 +586,49 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, return 0; -err_free: +err_free_by_rq_type: switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); +err_rq_mkey: mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); +err_rq_drop_page: + mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ - kvfree(rq->wqe.frags); mlx5e_free_di_list(rq); +err_rq_frags: + kvfree(rq->wqe.frags); } - err_rq_wq_destroy: - if (rq->xdp_prog) - bpf_prog_put(rq->xdp_prog); - xdp_rxq_info_unreg(&rq->xdp_rxq); - page_pool_destroy(rq->page_pool); mlx5_wq_destroy(&rq->wq_ctrl); +err_rq_xdp: + xdp_rxq_info_unreg(&rq->xdp_rxq); +err_rq_xdp_prog: + if (params->xdp_prog) + bpf_prog_put(params->xdp_prog); return err; } static void mlx5e_free_rq(struct mlx5e_rq *rq) { + struct mlx5e_channel *c = rq->channel; + struct bpf_prog *old_prog = NULL; int i; - if (rq->xdp_prog) - bpf_prog_put(rq->xdp_prog); + /* drop_rq has neither channel nor xdp_prog. */ + if (c) + old_prog = rcu_dereference_protected(rq->xdp_prog, + lockdep_is_held(&c->priv->state_lock)); + if (old_prog) + bpf_prog_put(old_prog); switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey); + mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ kvfree(rq->wqe.frags); @@ -867,7 +912,7 @@ void mlx5e_activate_rq(struct mlx5e_rq *rq) void mlx5e_deactivate_rq(struct mlx5e_rq *rq) { clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ + synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */ } void mlx5e_close_rq(struct mlx5e_rq *rq) @@ -1312,12 +1357,10 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) { - struct mlx5e_channel *c = sq->channel; struct mlx5_wq_cyc *wq = &sq->wq; clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - /* prevent netif_tx_wake_queue */ - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */ mlx5e_tx_disable_queue(sq->txq); @@ -1392,10 +1435,8 @@ void mlx5e_activate_icosq(struct mlx5e_icosq *icosq) void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq) { - struct mlx5e_channel *c = icosq->channel; - clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */ } void mlx5e_close_icosq(struct mlx5e_icosq *sq) @@ -1474,7 +1515,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) struct mlx5e_channel *c = sq->channel; clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */ mlx5e_destroy_sq(c->mdev, sq->sqn); mlx5e_free_xdpsq_descs(sq); @@ -3567,6 +3608,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) s->rx_packets += rq_stats->packets + xskrq_stats->packets; s->rx_bytes += rq_stats->bytes + xskrq_stats->bytes; + s->multicast += rq_stats->mcast_packets + xskrq_stats->mcast_packets; for (j = 0; j < priv->max_opened_tc; j++) { struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; @@ -3582,7 +3624,6 @@ void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; /* In switchdev mode, monitor counters doesn't monitor @@ -3617,12 +3658,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors + stats->rx_frame_errors; stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; - - /* vport multicast also counts packets that are dropped due to steering - * or rx out of buffer - */ - stats->multicast = - VPORT_COUNTER_GET(vstats, received_eth_multicast.packets); } static void mlx5e_set_rx_mode(struct net_device *dev) @@ -4191,6 +4226,21 @@ int mlx5e_get_vf_stats(struct net_device *dev, } #endif +static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev, + struct sk_buff *skb) +{ + switch (skb->inner_protocol) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_TEB): + return true; + case htons(ETH_P_MPLS_UC): + case htons(ETH_P_MPLS_MC): + return MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre); + } + return false; +} + static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, struct sk_buff *skb, netdev_features_t features) @@ -4213,7 +4263,9 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: - return features; + if (mlx5e_gre_tunnel_inner_proto_offload_supported(priv->mdev, skb)) + return features; + break; case IPPROTO_IPIP: case IPPROTO_IPV6: if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP)) @@ -4330,6 +4382,16 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) return 0; } +static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog) +{ + struct bpf_prog *old_prog; + + old_prog = rcu_replace_pointer(rq->xdp_prog, prog, + lockdep_is_held(&rq->channel->priv->state_lock)); + if (old_prog) + bpf_prog_put(old_prog); +} + static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4388,29 +4450,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) */ for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; - bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); - - clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); - if (xsk_open) - clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); - napi_synchronize(&c->napi); - /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */ - - old_prog = xchg(&c->rq.xdp_prog, prog); - if (old_prog) - bpf_prog_put(old_prog); - - if (xsk_open) { - old_prog = xchg(&c->xskrq.xdp_prog, prog); - if (old_prog) - bpf_prog_put(old_prog); - } - set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); - if (xsk_open) - set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); - /* napi_schedule in case we have missed anything */ - napi_schedule(&c->napi); + mlx5e_rq_replace_xdp_prog(&c->rq, prog); + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + mlx5e_rq_replace_xdp_prog(&c->xskrq, prog); } unlock: @@ -5200,7 +5243,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .enable = mlx5e_nic_enable, .disable = mlx5e_nic_disable, .update_rx = mlx5e_update_nic_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_nic, .max_tc = MLX5E_MAX_NUM_TC, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index e13e5d1b3eae..e979bff64c49 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1171,7 +1171,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .cleanup_tx = mlx5e_cleanup_rep_tx, .enable = mlx5e_rep_enable, .update_rx = mlx5e_update_rep_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = 1, .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), @@ -1189,7 +1189,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { .enable = mlx5e_uplink_rep_enable, .disable = mlx5e_uplink_rep_disable, .update_rx = mlx5e_update_rep_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = MLX5E_MAX_NUM_TC, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 622c27ae4ac7..0d1562e20118 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -135,12 +135,6 @@ struct mlx5e_neigh_hash_entry { /* encap list sharing the same neigh */ struct list_head encap_list; - /* valid only when the neigh reference is taken during - * neigh_update_work workqueue callback. - */ - struct neighbour *n; - struct work_struct neigh_update_work; - /* neigh hash entry can be deleted only when the refcount is zero. * refcount is needed to avoid neigh hash entry removal by TC, while * it's used by the neigh notification call. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 65828af120b7..64c8ac5eabf6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -53,6 +53,7 @@ #include "en/xsk/rx.h" #include "en/health.h" #include "en/params.h" +#include "en/txrx.h" static struct sk_buff * mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, @@ -1080,6 +1081,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, mlx5e_enable_ecn(rq, skb); skb->protocol = eth_type_trans(skb, netdev); + + if (unlikely(mlx5e_skb_is_multicast(skb))) + stats->mcast_packets++; } static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq, @@ -1132,7 +1136,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct xdp_buff xdp; struct sk_buff *skb; void *va, *data; - bool consumed; u32 frag_size; va = page_address(di->page) + wi->offset; @@ -1144,11 +1147,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, prefetchw(va); /* xdp_frame data area */ prefetch(data); - rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp); - rcu_read_unlock(); - if (consumed) + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp)) return NULL; /* page/packet was consumed by XDP */ rx_headroom = xdp.data - xdp.data_hard_start; @@ -1438,7 +1438,6 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct sk_buff *skb; void *va, *data; u32 frag_size; - bool consumed; /* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -1455,11 +1454,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, prefetchw(va); /* xdp_frame data area */ prefetch(data); - rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp); - rcu_read_unlock(); - if (consumed) { + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e3b2f59408e6..f6383bc2bc3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -54,6 +54,18 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv) return total; } +void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv) +{ + mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps; + const unsigned int num_stats_grps = stats_grps_num(priv); + int i; + + for (i = num_stats_grps - 1; i >= 0; i--) + if (stats_grps[i]->update_stats && + stats_grps[i]->update_stats_mask & MLX5E_NDO_UPDATE_STATS) + stats_grps[i]->update_stats(priv); +} + void mlx5e_stats_update(struct mlx5e_priv *priv) { mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 2e1cca1923b9..562263d62141 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -103,6 +103,7 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv); void mlx5e_stats_update(struct mlx5e_priv *priv); void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx); void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data); +void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv); /* Concrete NIC Stats */ @@ -119,6 +120,7 @@ struct mlx5e_sw_stats { u64 tx_nop; u64 rx_lro_packets; u64 rx_lro_bytes; + u64 rx_mcast_packets; u64 rx_ecn_mark; u64 rx_removed_vlan_packets; u64 rx_csum_unnecessary; @@ -298,6 +300,7 @@ struct mlx5e_rq_stats { u64 csum_none; u64 lro_packets; u64 lro_bytes; + u64 mcast_packets; u64 ecn_mark; u64 removed_vlan_packets; u64 xdp_drop; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fd53d101d8fd..1c93f92d9210 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1290,11 +1290,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_put_flow_tunnel_id(flow); - if (flow_flag_test(flow, NOT_READY)) { + if (flow_flag_test(flow, NOT_READY)) remove_unready_flow(flow); - kvfree(attr->parse_attr); - return; - } if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) @@ -1315,6 +1312,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, } kvfree(attr->parse_attr); + mlx5_tc_ct_match_del(priv, &flow->esw_attr->ct_attr); + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); @@ -2625,6 +2624,22 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport), }; +static unsigned long mask_to_le(unsigned long mask, int size) +{ + __be32 mask_be32; + __be16 mask_be16; + + if (size == 32) { + mask_be32 = (__force __be32)(mask); + mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); + } else if (size == 16) { + mask_be32 = (__force __be32)(mask); + mask_be16 = *(__be16 *)&mask_be32; + mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); + } + + return mask; +} static int offload_pedit_fields(struct mlx5e_priv *priv, int namespace, struct pedit_headers_action *hdrs, @@ -2638,9 +2653,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; struct mlx5_fields *f; - unsigned long mask; - __be32 mask_be32; - __be16 mask_be16; + unsigned long mask, field_mask; int err; u8 cmd; @@ -2706,14 +2719,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (skip) continue; - if (f->field_bsize == 32) { - mask_be32 = (__force __be32)(mask); - mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); - } else if (f->field_bsize == 16) { - mask_be32 = (__force __be32)(mask); - mask_be16 = *(__be16 *)&mask_be32; - mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); - } + mask = mask_to_le(mask, f->field_bsize); first = find_first_bit(&mask, f->field_bsize); next_z = find_next_zero_bit(&mask, f->field_bsize, first); @@ -2744,9 +2750,10 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (cmd == MLX5_ACTION_TYPE_SET) { int start; + field_mask = mask_to_le(f->field_mask, f->field_bsize); + /* if field is bit sized it can start not from first bit */ - start = find_first_bit((unsigned long *)&f->field_mask, - f->field_bsize); + start = find_first_bit(&field_mask, f->field_bsize); MLX5_SET(set_action_in, action, offset, first - start); /* length is num of bits to be written, zero means length of 32 */ @@ -4402,8 +4409,8 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, goto err_free; /* actions validation depends on parsing the ct matches first */ - err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f, - &flow->esw_attr->ct_attr, extack); + err = mlx5_tc_ct_match_add(priv, &parse_attr->spec, f, + &flow->esw_attr->ct_attr, extack); if (err) goto err_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index de10b06bade5..d5868670f8a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -121,13 +121,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) struct mlx5e_xdpsq *xsksq = &c->xsksq; struct mlx5e_rq *xskrq = &c->xskrq; struct mlx5e_rq *rq = &c->rq; - bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); bool aff_change = false; bool busy_xsk = false; bool busy = false; int work_done = 0; + bool xsk_open; int i; + rcu_read_lock(); + + xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); + ch_stats->poll++; for (i = 0; i < c->num_tc; i++) @@ -167,8 +171,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) busy |= busy_xsk; if (busy) { - if (likely(mlx5e_channel_no_affinity_change(c))) - return budget; + if (likely(mlx5e_channel_no_affinity_change(c))) { + work_done = budget; + goto out; + } ch_stats->aff_change++; aff_change = true; if (budget && work_done == budget) @@ -176,7 +182,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) } if (unlikely(!napi_complete_done(napi, work_done))) - return work_done; + goto out; ch_stats->arm++; @@ -203,6 +209,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) ch_stats->force_irq++; } +out: + rcu_read_unlock(); + return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 31ef9f8420c8..22a19d391e17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -189,6 +189,29 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq) return count_eqe; } +static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags) + __acquires(&eq->lock) +{ + if (in_irq()) + spin_lock(&eq->lock); + else + spin_lock_irqsave(&eq->lock, *flags); +} + +static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags) + __releases(&eq->lock) +{ + if (in_irq()) + spin_unlock(&eq->lock); + else + spin_unlock_irqrestore(&eq->lock, *flags); +} + +enum async_eq_nb_action { + ASYNC_EQ_IRQ_HANDLER = 0, + ASYNC_EQ_RECOVER = 1, +}; + static int mlx5_eq_async_int(struct notifier_block *nb, unsigned long action, void *data) { @@ -198,11 +221,14 @@ static int mlx5_eq_async_int(struct notifier_block *nb, struct mlx5_eq_table *eqt; struct mlx5_core_dev *dev; struct mlx5_eqe *eqe; + unsigned long flags; int num_eqes = 0; dev = eq->dev; eqt = dev->priv.eq_table; + mlx5_eq_async_int_lock(eq_async, &flags); + eqe = next_eqe_sw(eq); if (!eqe) goto out; @@ -223,8 +249,19 @@ static int mlx5_eq_async_int(struct notifier_block *nb, out: eq_update_ci(eq, 1); + mlx5_eq_async_int_unlock(eq_async, &flags); - return 0; + return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0; +} + +void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev) +{ + struct mlx5_eq_async *eq = &dev->priv.eq_table->cmd_eq; + int eqes; + + eqes = mlx5_eq_async_int(&eq->irq_nb, ASYNC_EQ_RECOVER, NULL); + if (eqes) + mlx5_core_warn(dev, "Recovered %d EQEs on cmd_eq\n", eqes); } static void init_eq_buf(struct mlx5_eq *eq) @@ -569,6 +606,7 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq, int err; eq->irq_nb.notifier_call = mlx5_eq_async_int; + spin_lock_init(&eq->lock); err = create_async_eq(dev, &eq->core, param); if (err) { @@ -656,8 +694,10 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev) cleanup_async_eq(dev, &table->pages_eq, "pages"); cleanup_async_eq(dev, &table->async_eq, "async"); + mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_DESTROY_EQ); mlx5_cmd_use_polling(dev); cleanup_async_eq(dev, &table->cmd_eq, "cmd"); + mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); mlx5_eq_notifier_unregister(dev, &table->cq_err_nb); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d2516922d867..1bcf2609dca8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1219,35 +1219,37 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.send_to_vport_grp = g; - /* create peer esw miss group */ - memset(flow_group_in, 0, inlen); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { + /* create peer esw miss group */ + memset(flow_group_in, 0, inlen); - esw_set_flow_group_source_port(esw, flow_group_in); + esw_set_flow_group_source_port(esw, flow_group_in); - if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { - match_criteria = MLX5_ADDR_OF(create_flow_group_in, - flow_group_in, - match_criteria); + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { + match_criteria = MLX5_ADDR_OF(create_flow_group_in, + flow_group_in, + match_criteria); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - misc_parameters.source_eswitch_owner_vhca_id); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + misc_parameters.source_eswitch_owner_vhca_id); - MLX5_SET(create_flow_group_in, flow_group_in, - source_eswitch_owner_vhca_id_valid, 1); - } + MLX5_SET(create_flow_group_in, flow_group_in, + source_eswitch_owner_vhca_id_valid, 1); + } - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, - ix + esw->total_vports - 1); - ix += esw->total_vports; + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, + ix + esw->total_vports - 1); + ix += esw->total_vports; - g = mlx5_create_flow_group(fdb, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err); - goto peer_miss_err; + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err); + goto peer_miss_err; + } + esw->fdb_table.offloads.peer_miss_grp = g; } - esw->fdb_table.offloads.peer_miss_grp = g; /* create miss group */ memset(flow_group_in, 0, inlen); @@ -1281,7 +1283,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) miss_rule_err: mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); miss_err: - mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); peer_miss_err: mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); send_vport_err: @@ -1305,7 +1308,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi); mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni); mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); - mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); mlx5_esw_chains_destroy(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9ccec5f8b92a..75fa44eee434 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -654,7 +654,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft, fte->action = *flow_act; fte->flow_context = spec->flow_context; - tree_init_node(&fte->node, NULL, del_sw_fte); + tree_init_node(&fte->node, del_hw_fte, del_sw_fte); return fte; } @@ -1792,7 +1792,6 @@ skip_search: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); - tree_put_node(&fte->node, false); return rule; } rule = ERR_PTR(-ENOENT); @@ -1891,7 +1890,6 @@ search_again_locked: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); - tree_put_node(&fte->node, false); tree_put_node(&g->node, false); return rule; @@ -2001,7 +1999,9 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) up_write_ref_node(&fte->node, false); } else { del_hw_fte(&fte->node); - up_write(&fte->node.lock); + /* Avoid double call to del_hw_fte */ + fte->node.del_hw_func = NULL; + up_write_ref_node(&fte->node, false); tree_put_node(&fte->node, false); } kfree(handle); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 4aaca7400fb2..5c681e31983b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -37,6 +37,7 @@ struct mlx5_eq { struct mlx5_eq_async { struct mlx5_eq core; struct notifier_block irq_nb; + spinlock_t lock; /* To avoid irq EQ handle races with resiliency flows */ }; struct mlx5_eq_comp { @@ -81,6 +82,7 @@ void mlx5_cq_tasklet_cb(unsigned long data); struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix); u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq); +void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev); void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev); void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index f9b798af6335..c0e18f2ade99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -432,7 +432,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, u32 npages; u32 i = 0; - if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR) + if (!mlx5_cmd_is_down(dev)) return mlx5_cmd_exec(dev, in, in_size, out, out_size); /* No hard feelings, we want our pages back! */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 373981a659c7..6fd974920394 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -115,7 +115,7 @@ static int request_irqs(struct mlx5_core_dev *dev, int nvec) return 0; err_request_irq: - for (; i >= 0; i--) { + while (i--) { struct mlx5_irq *irq = mlx5_irq_get(dev, i); int irqn = pci_irq_vector(dev->pdev, i); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 4186e29119c2..f3c0e241e1b4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3690,13 +3690,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev) return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; } -static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) +static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) { - struct mlxsw_sp_port **p_mlxsw_sp_port = data; int ret = 0; if (mlxsw_sp_port_dev_check(lower_dev)) { - *p_mlxsw_sp_port = netdev_priv(lower_dev); + priv->data = (void *)netdev_priv(lower_dev); ret = 1; } @@ -3705,15 +3705,16 @@ static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev) { - struct mlxsw_sp_port *mlxsw_sp_port; + struct netdev_nested_priv priv = { + .data = NULL, + }; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - mlxsw_sp_port = NULL; - netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port); + netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &priv); - return mlxsw_sp_port; + return (struct mlxsw_sp_port *)priv.data; } struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) @@ -3726,16 +3727,17 @@ struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev) { - struct mlxsw_sp_port *mlxsw_sp_port; + struct netdev_nested_priv priv = { + .data = NULL, + }; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - mlxsw_sp_port = NULL; netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk, - &mlxsw_sp_port); + &priv); - return mlxsw_sp_port; + return (struct mlxsw_sp_port *)priv.data; } struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 5c020403342f..7cccc41dd69c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -292,13 +292,14 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp_acl_tcam *tcam, int err; group->tcam = tcam; - mutex_init(&group->lock); INIT_LIST_HEAD(&group->region_list); err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id); if (err) return err; + mutex_init(&group->lock); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 24f1fd1f8d56..460cb523312f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -7351,9 +7351,10 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, return err; } -static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data) +static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct mlxsw_sp_rif *rif = data; + struct mlxsw_sp_rif *rif = (struct mlxsw_sp_rif *)priv->data; if (!netif_is_macvlan(dev)) return 0; @@ -7364,12 +7365,16 @@ static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data) static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif) { + struct netdev_nested_priv priv = { + .data = (void *)rif, + }; + if (!netif_is_macvlan_port(rif->dev)) return 0; netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n"); return netdev_walk_all_upper_dev_rcu(rif->dev, - __mlxsw_sp_rif_macvlan_flush, rif); + __mlxsw_sp_rif_macvlan_flush, &priv); } static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 72912afa6f72..6501ce94ace5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -136,9 +136,9 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev, - void *data) + struct netdev_nested_priv *priv) { - struct mlxsw_sp *mlxsw_sp = data; + struct mlxsw_sp *mlxsw_sp = priv->data; mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); return 0; @@ -147,10 +147,14 @@ static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev, static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp, struct net_device *dev) { + struct netdev_nested_priv priv = { + .data = (void *)mlxsw_sp, + }; + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); netdev_walk_all_upper_dev_rcu(dev, mlxsw_sp_bridge_device_upper_rif_destroy, - mlxsw_sp); + &priv); } static int mlxsw_sp_bridge_device_vxlan_init(struct mlxsw_sp_bridge *bridge, |