From e5fd91f1ef340da553f7a79da9540c3db711c937 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Andr=C3=A9=20Fabian=20Silva=20Delgado?= Date: Tue, 8 Sep 2015 01:01:14 -0300 Subject: Linux-libre 4.2-gnu --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 127 ++++++- drivers/net/ethernet/mellanox/mlx4/cq.c | 13 +- drivers/net/ethernet/mellanox/mlx4/en_cq.c | 56 ++- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 17 + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 30 +- drivers/net/ethernet/mellanox/mlx4/en_port.c | 29 +- drivers/net/ethernet/mellanox/mlx4/en_resources.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 14 +- drivers/net/ethernet/mellanox/mlx4/eq.c | 404 +++++++++++++-------- drivers/net/ethernet/mellanox/mlx4/main.c | 290 ++++++++++++--- drivers/net/ethernet/mellanox/mlx4/mlx4.h | 17 +- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 4 +- drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h | 10 +- drivers/net/ethernet/mellanox/mlx4/profile.c | 8 +- drivers/net/ethernet/mellanox/mlx4/qp.c | 9 +- .../net/ethernet/mellanox/mlx4/resource_tracker.c | 208 ++++++++++- 16 files changed, 959 insertions(+), 279 deletions(-) (limited to 'drivers/net/ethernet/mellanox/mlx4') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 529ef0594..0a3202047 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -49,6 +49,7 @@ #include "mlx4.h" #include "fw.h" #include "fw_qos.h" +#include "mlx4_stats.h" #define CMD_POLL_TOKEN 0xffff #define INBOX_MASK 0xffffffffffffff00ULL @@ -685,6 +686,7 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param, { struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd; struct mlx4_cmd_context *context; + long ret_wait; int err = 0; down(&cmd->event_sem); @@ -710,8 +712,20 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param, if (err) goto out_reset; - if (!wait_for_completion_timeout(&context->done, - msecs_to_jiffies(timeout))) { + if (op == MLX4_CMD_SENSE_PORT) { + ret_wait = + wait_for_completion_interruptible_timeout(&context->done, + msecs_to_jiffies(timeout)); + if (ret_wait < 0) { + context->fw_status = 0; + context->out_param = 0; + context->result = 0; + } + } else { + ret_wait = (long)wait_for_completion_timeout(&context->done, + msecs_to_jiffies(timeout)); + } + if (!ret_wait) { mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n", op); if (op == MLX4_CMD_NOP) { @@ -882,7 +896,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, { struct ib_smp *smp = inbox->buf; u32 index; - u8 port; + u8 port, slave_port; u8 opcode_modifier; u16 *table; int err; @@ -894,7 +908,8 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, __be32 slave_cap_mask; __be64 slave_node_guid; - port = vhcr->in_modifier; + slave_port = vhcr->in_modifier; + port = mlx4_slave_convert_port(dev, slave, slave_port); /* network-view bit is for driver use only, and should not be passed to FW */ opcode_modifier = vhcr->op_modifier & ~0x8; /* clear netw view bit */ @@ -930,8 +945,9 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, if (smp->attr_id == IB_SMP_ATTR_PORT_INFO) { /*get the slave specific caps:*/ /*do the command */ + smp->attr_mod = cpu_to_be32(port); err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, - vhcr->in_modifier, opcode_modifier, + port, opcode_modifier, vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); /* modify the response for slaves */ if (!err && slave != mlx4_master_func_num(dev)) { @@ -975,7 +991,7 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave, } if (smp->attr_id == IB_SMP_ATTR_NODE_INFO) { err = mlx4_cmd_box(dev, inbox->dma, outbox->dma, - vhcr->in_modifier, opcode_modifier, + port, opcode_modifier, vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE); if (!err) { slave_node_guid = mlx4_get_slave_node_guid(dev, slave); @@ -2915,7 +2931,7 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac) port = mlx4_slaves_closest_port(dev, slave, port); s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; s_info->mac = mac; - mlx4_info(dev, "default mac on vf %d port %d to %llX will take afect only after vf restart\n", + mlx4_info(dev, "default mac on vf %d port %d to %llX will take effect only after vf restart\n", vf, port, s_info->mac); return 0; } @@ -3164,6 +3180,92 @@ int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_stat } EXPORT_SYMBOL_GPL(mlx4_set_vf_link_state); +int mlx4_get_counter_stats(struct mlx4_dev *dev, int counter_index, + struct mlx4_counter *counter_stats, int reset) +{ + struct mlx4_cmd_mailbox *mailbox = NULL; + struct mlx4_counter *tmp_counter; + int err; + u32 if_stat_in_mod; + + if (!counter_stats) + return -EINVAL; + + if (counter_index == MLX4_SINK_COUNTER_INDEX(dev)) + return 0; + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) + return PTR_ERR(mailbox); + + memset(mailbox->buf, 0, sizeof(struct mlx4_counter)); + if_stat_in_mod = counter_index; + if (reset) + if_stat_in_mod |= MLX4_QUERY_IF_STAT_RESET; + err = mlx4_cmd_box(dev, 0, mailbox->dma, + if_stat_in_mod, 0, + MLX4_CMD_QUERY_IF_STAT, + MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + if (err) { + mlx4_dbg(dev, "%s: failed to read statistics for counter index %d\n", + __func__, counter_index); + goto if_stat_out; + } + tmp_counter = (struct mlx4_counter *)mailbox->buf; + counter_stats->counter_mode = tmp_counter->counter_mode; + if (counter_stats->counter_mode == 0) { + counter_stats->rx_frames = + cpu_to_be64(be64_to_cpu(counter_stats->rx_frames) + + be64_to_cpu(tmp_counter->rx_frames)); + counter_stats->tx_frames = + cpu_to_be64(be64_to_cpu(counter_stats->tx_frames) + + be64_to_cpu(tmp_counter->tx_frames)); + counter_stats->rx_bytes = + cpu_to_be64(be64_to_cpu(counter_stats->rx_bytes) + + be64_to_cpu(tmp_counter->rx_bytes)); + counter_stats->tx_bytes = + cpu_to_be64(be64_to_cpu(counter_stats->tx_bytes) + + be64_to_cpu(tmp_counter->tx_bytes)); + } + +if_stat_out: + mlx4_free_cmd_mailbox(dev, mailbox); + + return err; +} +EXPORT_SYMBOL_GPL(mlx4_get_counter_stats); + +int mlx4_get_vf_stats(struct mlx4_dev *dev, int port, int vf_idx, + struct ifla_vf_stats *vf_stats) +{ + struct mlx4_counter tmp_vf_stats; + int slave; + int err = 0; + + if (!vf_stats) + return -EINVAL; + + if (!mlx4_is_master(dev)) + return -EPROTONOSUPPORT; + + slave = mlx4_get_slave_indx(dev, vf_idx); + if (slave < 0) + return -EINVAL; + + port = mlx4_slaves_closest_port(dev, slave, port); + err = mlx4_calc_vf_counters(dev, slave, port, &tmp_vf_stats); + if (!err && tmp_vf_stats.counter_mode == 0) { + vf_stats->rx_packets = be64_to_cpu(tmp_vf_stats.rx_frames); + vf_stats->tx_packets = be64_to_cpu(tmp_vf_stats.tx_frames); + vf_stats->rx_bytes = be64_to_cpu(tmp_vf_stats.rx_bytes); + vf_stats->tx_bytes = be64_to_cpu(tmp_vf_stats.tx_bytes); + } + + return err; +} +EXPORT_SYMBOL_GPL(mlx4_get_vf_stats); + int mlx4_vf_smi_enabled(struct mlx4_dev *dev, int slave, int port) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -3197,6 +3299,12 @@ int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port, int enabled) { struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_active_ports actv_ports = mlx4_get_active_ports( + &priv->dev, slave); + int min_port = find_first_bit(actv_ports.ports, + priv->dev.caps.num_ports) + 1; + int max_port = min_port - 1 + + bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports); if (slave == mlx4_master_func_num(dev)) return 0; @@ -3206,6 +3314,11 @@ int mlx4_vf_set_enable_smi_admin(struct mlx4_dev *dev, int slave, int port, enabled < 0 || enabled > 1) return -EINVAL; + if (min_port == max_port && dev->caps.num_ports > 1) { + mlx4_info(dev, "SMI access disallowed for single ported VFs\n"); + return -EPROTONOSUPPORT; + } + priv->mfunc.master.vf_admin[slave].enable_smi[port] = enabled; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index e71f31387..3348e646d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -292,7 +292,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, u64 mtt_addr; int err; - if (vector > dev->caps.num_comp_vectors + dev->caps.comp_pool) + if (vector >= dev->caps.num_comp_vectors) return -EINVAL; cq->vector = vector; @@ -319,7 +319,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, cq_context->flags |= cpu_to_be32(1 << 19); cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index); - cq_context->comp_eqn = priv->eq_table.eq[vector].eqn; + cq_context->comp_eqn = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn; cq_context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT; mtt_addr = mlx4_mtt_addr(dev, mtt); @@ -339,11 +339,11 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, init_completion(&cq->free); cq->comp = mlx4_add_cq_to_tasklet; cq->tasklet_ctx.priv = - &priv->eq_table.eq[cq->vector].tasklet_ctx; + &priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].tasklet_ctx; INIT_LIST_HEAD(&cq->tasklet_ctx.list); - cq->irq = priv->eq_table.eq[cq->vector].irq; + cq->irq = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].irq; return 0; err_radix: @@ -368,7 +368,10 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq) if (err) mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn); - synchronize_irq(priv->eq_table.eq[cq->vector].irq); + synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq); + if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq != + priv->eq_table.eq[MLX4_EQ_ASYNC].irq) + synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq); spin_lock_irq(&cq_table->lock); radix_tree_delete(&cq_table->tree, cq->cqn); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 22da4d0d0..63769df87 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -66,6 +66,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv, cq->ring = ring; cq->is_tx = mode; + cq->vector = mdev->dev->caps.num_comp_vectors; /* Allocate HW buffers on provided NUMA node. * dev->numa_node is used in mtt range allocation flow. @@ -101,12 +102,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, int err = 0; char name[25]; int timestamp_en = 0; - struct cpu_rmap *rmap = -#ifdef CONFIG_RFS_ACCEL - priv->dev->rx_cpu_rmap; -#else - NULL; -#endif + bool assigned_eq = false; cq->dev = mdev->pndev[priv->port]; cq->mcq.set_ci_db = cq->wqres.db.db; @@ -116,23 +112,19 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, memset(cq->buf, 0, cq->buf_size); if (cq->is_tx == RX) { - if (mdev->dev->caps.comp_pool) { - if (!cq->vector) { - sprintf(name, "%s-%d", priv->dev->name, - cq->ring); - /* Set IRQ for specific name (per ring) */ - if (mlx4_assign_eq(mdev->dev, name, rmap, - &cq->vector)) { - cq->vector = (cq->ring + 1 + priv->port) - % mdev->dev->caps.num_comp_vectors; - mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n", - name); - } - + if (!mlx4_is_eq_vector_valid(mdev->dev, priv->port, + cq->vector)) { + cq->vector = cpumask_first(priv->rx_ring[cq->ring]->affinity_mask); + + err = mlx4_assign_eq(mdev->dev, priv->port, + &cq->vector); + if (err) { + mlx4_err(mdev, "Failed assigning an EQ to %s\n", + name); + goto free_eq; } - } else { - cq->vector = (cq->ring + 1 + priv->port) % - mdev->dev->caps.num_comp_vectors; + + assigned_eq = true; } cq->irq_desc = @@ -159,7 +151,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq, cq->vector, 0, timestamp_en); if (err) - return err; + goto free_eq; cq->mcq.comp = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq; cq->mcq.event = mlx4_en_cq_event; @@ -168,13 +160,6 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_tx_cq, NAPI_POLL_WEIGHT); } else { - struct mlx4_en_rx_ring *ring = priv->rx_ring[cq->ring]; - - err = irq_set_affinity_hint(cq->mcq.irq, - ring->affinity_mask); - if (err) - mlx4_warn(mdev, "Failed setting affinity hint\n"); - netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64); napi_hash_add(&cq->napi); } @@ -182,6 +167,12 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, napi_enable(&cq->napi); return 0; + +free_eq: + if (assigned_eq) + mlx4_release_eq(mdev->dev, cq->vector); + cq->vector = mdev->dev->caps.num_comp_vectors; + return err; } void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq) @@ -191,9 +182,9 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq **pcq) mlx4_en_unmap_buffer(&cq->wqres.buf); mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size); - if (priv->mdev->dev->caps.comp_pool && cq->vector) { + if (mlx4_is_eq_vector_valid(mdev->dev, priv->port, cq->vector) && + cq->is_tx == RX) mlx4_release_eq(priv->mdev->dev, cq->vector); - } cq->vector = 0; cq->buf_size = 0; cq->buf = NULL; @@ -207,7 +198,6 @@ void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) if (!cq->is_tx) { napi_hash_del(&cq->napi); synchronize_rcu(); - irq_set_affinity_hint(cq->mcq.irq, NULL); } netif_napi_del(&cq->napi); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a2ddf3d75..99ba1c50e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -119,6 +119,12 @@ static const char main_strings[][ETH_GSTRING_LEN] = { "queue_stopped", "wake_queue", "tx_timeout", "rx_alloc_failed", "rx_csum_good", "rx_csum_none", "rx_csum_complete", "tx_chksum_offload", + /* pf statistics */ + "pf_rx_packets", + "pf_rx_bytes", + "pf_tx_packets", + "pf_tx_bytes", + /* priority flow control statistics rx */ "rx_pause_prio_0", "rx_pause_duration_prio_0", "rx_pause_transition_prio_0", @@ -368,6 +374,11 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev, if (bitmap_iterator_test(&it)) data[index++] = ((unsigned long *)&priv->port_stats)[i]; + for (i = 0; i < NUM_PF_STATS; i++, bitmap_iterator_inc(&it)) + if (bitmap_iterator_test(&it)) + data[index++] = + ((unsigned long *)&priv->pf_stats)[i]; + for (i = 0; i < NUM_FLOW_PRIORITY_STATS_RX; i++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) @@ -448,6 +459,12 @@ static void mlx4_en_get_strings(struct net_device *dev, strcpy(data + (index++) * ETH_GSTRING_LEN, main_strings[strings]); + for (i = 0; i < NUM_PF_STATS; i++, strings++, + bitmap_iterator_inc(&it)) + if (bitmap_iterator_test(&it)) + strcpy(data + (index++) * ETH_GSTRING_LEN, + main_strings[strings]); + for (i = 0; i < NUM_FLOW_STATS; i++, strings++, bitmap_iterator_inc(&it)) if (bitmap_iterator_test(&it)) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a5a0b8420..e0de2fd1c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -1597,6 +1597,9 @@ int mlx4_en_start_port(struct net_device *dev) } mdev->mac_removed[priv->port] = 0; + priv->counter_index = + mlx4_get_default_counter_index(mdev->dev, priv->port); + err = mlx4_en_config_rss_steer(priv); if (err) { en_err(priv, "Failed configuring rss steering\n"); @@ -1755,6 +1758,7 @@ void mlx4_en_stop_port(struct net_device *dev, int detach) /* Set port as not active */ priv->port_up = false; + priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); /* Promsicuous mode */ if (mdev->dev->caps.steering_mode == @@ -1891,6 +1895,7 @@ static void mlx4_en_clear_stats(struct net_device *dev) sizeof(priv->rx_priority_flowstats)); memset(&priv->tx_priority_flowstats, 0, sizeof(priv->tx_priority_flowstats)); + memset(&priv->pf_stats, 0, sizeof(priv->pf_stats)); for (i = 0; i < priv->tx_ring_num; i++) { priv->tx_ring[i]->bytes = 0; @@ -1954,7 +1959,6 @@ void mlx4_en_free_resources(struct mlx4_en_priv *priv) int i; #ifdef CONFIG_RFS_ACCEL - free_irq_cpu_rmap(priv->dev->rx_cpu_rmap); priv->dev->rx_cpu_rmap = NULL; #endif @@ -2008,11 +2012,7 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) } #ifdef CONFIG_RFS_ACCEL - if (priv->mdev->dev->caps.comp_pool) { - priv->dev->rx_cpu_rmap = alloc_irq_cpu_rmap(priv->mdev->dev->caps.comp_pool); - if (!priv->dev->rx_cpu_rmap) - goto err; - } + priv->dev->rx_cpu_rmap = mlx4_get_cpu_rmap(priv->mdev->dev, priv->port); #endif return 0; @@ -2288,6 +2288,15 @@ static int mlx4_en_set_vf_link_state(struct net_device *dev, int vf, int link_st return mlx4_set_vf_link_state(mdev->dev, en_priv->port, vf, link_state); } +static int mlx4_en_get_vf_stats(struct net_device *dev, int vf, + struct ifla_vf_stats *vf_stats) +{ + struct mlx4_en_priv *en_priv = netdev_priv(dev); + struct mlx4_en_dev *mdev = en_priv->mdev; + + return mlx4_get_vf_stats(mdev->dev, en_priv->port, vf, vf_stats); +} + #define PORT_ID_BYTE_LEN 8 static int mlx4_en_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid) @@ -2485,6 +2494,7 @@ static const struct net_device_ops mlx4_netdev_ops_master = { .ndo_set_vf_rate = mlx4_en_set_vf_rate, .ndo_set_vf_spoofchk = mlx4_en_set_vf_spoofchk, .ndo_set_vf_link_state = mlx4_en_set_vf_link_state, + .ndo_get_vf_stats = mlx4_en_get_vf_stats, .ndo_get_vf_config = mlx4_en_get_vf_config, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = mlx4_en_netpoll, @@ -2682,7 +2692,7 @@ void mlx4_en_update_pfc_stats_bitmap(struct mlx4_dev *dev, u8 rx_ppp, u8 rx_pause, u8 tx_ppp, u8 tx_pause) { - int last_i = NUM_MAIN_STATS + NUM_PORT_STATS; + int last_i = NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PF_STATS; if (!mlx4_is_slave(dev) && (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN)) { @@ -2744,6 +2754,11 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev, bitmap_set(stats_bitmap->bitmap, last_i, NUM_PORT_STATS); last_i += NUM_PORT_STATS; + if (mlx4_is_master(dev)) + bitmap_set(stats_bitmap->bitmap, last_i, + NUM_PF_STATS); + last_i += NUM_PF_STATS; + mlx4_en_update_pfc_stats_bitmap(dev, stats_bitmap, rx_ppp, rx_pause, tx_ppp, tx_pause); @@ -2779,6 +2794,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv = netdev_priv(dev); memset(priv, 0, sizeof(struct mlx4_en_priv)); + priv->counter_index = MLX4_SINK_COUNTER_INDEX(mdev->dev); spin_lock_init(&priv->stats_lock); INIT_WORK(&priv->rx_mode_task, mlx4_en_do_set_rx_mode); INIT_WORK(&priv->watchdog_task, mlx4_en_restart); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index 0a56f010c..ee99e6718 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -149,6 +149,7 @@ static unsigned long en_stats_adder(__be64 *start, __be64 *next, int num) int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) { + struct mlx4_counter tmp_counter_stats; struct mlx4_en_stat_out_mbox *mlx4_en_stats; struct mlx4_en_stat_out_flow_control_mbox *flowstats; struct mlx4_en_priv *priv = netdev_priv(mdev->pndev[port]); @@ -156,7 +157,7 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) struct mlx4_cmd_mailbox *mailbox; u64 in_mod = reset << 8 | port; int err; - int i; + int i, counter_index; mailbox = mlx4_alloc_cmd_mailbox(mdev->dev); if (IS_ERR(mailbox)) @@ -202,6 +203,20 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) priv->port_stats.tso_packets += ring->tso_packets; priv->port_stats.xmit_more += ring->xmit_more; } + if (mlx4_is_master(mdev->dev)) { + stats->rx_packets = en_stats_adder(&mlx4_en_stats->RTOT_prio_0, + &mlx4_en_stats->RTOT_prio_1, + NUM_PRIORITIES); + stats->tx_packets = en_stats_adder(&mlx4_en_stats->TTOT_prio_0, + &mlx4_en_stats->TTOT_prio_1, + NUM_PRIORITIES); + stats->rx_bytes = en_stats_adder(&mlx4_en_stats->ROCT_prio_0, + &mlx4_en_stats->ROCT_prio_1, + NUM_PRIORITIES); + stats->tx_bytes = en_stats_adder(&mlx4_en_stats->TOCT_prio_0, + &mlx4_en_stats->TOCT_prio_1, + NUM_PRIORITIES); + } /* net device stats */ stats->rx_errors = be64_to_cpu(mlx4_en_stats->PCS) + @@ -296,6 +311,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) spin_unlock_bh(&priv->stats_lock); + memset(&tmp_counter_stats, 0, sizeof(tmp_counter_stats)); + counter_index = mlx4_get_default_counter_index(mdev->dev, port); + err = mlx4_get_counter_stats(mdev->dev, counter_index, + &tmp_counter_stats, reset); + /* 0xffs indicates invalid value */ memset(mailbox->buf, 0xff, sizeof(*flowstats) * MLX4_NUM_PRIORITIES); @@ -314,6 +334,13 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) spin_lock_bh(&priv->stats_lock); + if (tmp_counter_stats.counter_mode == 0) { + priv->pf_stats.rx_bytes = be64_to_cpu(tmp_counter_stats.rx_bytes); + priv->pf_stats.tx_bytes = be64_to_cpu(tmp_counter_stats.tx_bytes); + priv->pf_stats.rx_packets = be64_to_cpu(tmp_counter_stats.rx_frames); + priv->pf_stats.tx_packets = be64_to_cpu(tmp_counter_stats.tx_frames); + } + for (i = 0; i < MLX4_NUM_PRIORITIES; i++) { priv->rx_priority_flowstats[i].rx_pause = be64_to_cpu(flowstats[i].rx_pause); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 34f2fdf4f..e482fa1bb 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -66,7 +66,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, context->pri_path.sched_queue |= user_prio << 3; context->pri_path.feup = MLX4_FEUP_FORCE_ETH_UP; } - context->pri_path.counter_index = 0xff; + context->pri_path.counter_index = priv->counter_index; context->cqn_send = cpu_to_be32(cqn); context->cqn_recv = cpu_to_be32(cqn); context->db_rec_addr = cpu_to_be64(priv->res.db.dma << 2); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index eab4e080e..9c145dddd 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -246,7 +246,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring) { - BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size); return ring->prod == ring->cons; } @@ -337,15 +336,10 @@ void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev) struct mlx4_dev *dev = mdev->dev; mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { - if (!dev->caps.comp_pool) - num_of_eqs = max_t(int, MIN_RX_RINGS, - min_t(int, - dev->caps.num_comp_vectors, - DEF_RX_RINGS)); - else - num_of_eqs = min_t(int, MAX_MSIX_P_PORT, - dev->caps.comp_pool/ - dev->caps.num_ports) - 1; + num_of_eqs = max_t(int, MIN_RX_RINGS, + min_t(int, + mlx4_get_eqs_per_port(mdev->dev, i), + DEF_RX_RINGS)); num_rx_rings = mlx4_low_memory_profile() ? MIN_RX_RINGS : min_t(int, num_of_eqs, diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 2619c9fbf..8e81e53c3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -145,7 +145,7 @@ void mlx4_gen_slave_eqe(struct work_struct *work) struct mlx4_slave_event_eq *slave_eq = &mfunc->master.slave_eq; struct mlx4_eqe *eqe; u8 slave; - int i; + int i, phys_port, slave_port; for (eqe = next_slave_event_eqe(slave_eq); eqe; eqe = next_slave_event_eqe(slave_eq)) { @@ -154,9 +154,20 @@ void mlx4_gen_slave_eqe(struct work_struct *work) /* All active slaves need to receive the event */ if (slave == ALL_SLAVES) { for (i = 0; i <= dev->persist->num_vfs; i++) { + phys_port = 0; + if (eqe->type == MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT && + eqe->subtype == MLX4_DEV_PMC_SUBTYPE_PORT_INFO) { + phys_port = eqe->event.port_mgmt_change.port; + slave_port = mlx4_phys_to_slave_port(dev, i, phys_port); + if (slave_port < 0) /* VF doesn't have this port */ + continue; + eqe->event.port_mgmt_change.port = slave_port; + } if (mlx4_GEN_EQE(dev, i, eqe)) mlx4_warn(dev, "Failed to generate event for slave %d\n", i); + if (phys_port) + eqe->event.port_mgmt_change.port = phys_port; } } else { if (mlx4_GEN_EQE(dev, slave, eqe)) @@ -210,6 +221,22 @@ static void mlx4_slave_event(struct mlx4_dev *dev, int slave, slave_event(dev, slave, eqe); } +#if defined(CONFIG_SMP) +static void mlx4_set_eq_affinity_hint(struct mlx4_priv *priv, int vec) +{ + int hint_err; + struct mlx4_dev *dev = &priv->dev; + struct mlx4_eq *eq = &priv->eq_table.eq[vec]; + + if (!eq->affinity_mask || cpumask_empty(eq->affinity_mask)) + return; + + hint_err = irq_set_affinity_hint(eq->irq, eq->affinity_mask); + if (hint_err) + mlx4_warn(dev, "irq_set_affinity_hint failed, err %d\n", hint_err); +} +#endif + int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port) { struct mlx4_eqe eqe; @@ -224,7 +251,7 @@ int mlx4_gen_pkey_eqe(struct mlx4_dev *dev, int slave, u8 port) eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; eqe.subtype = MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE; - eqe.event.port_mgmt_change.port = port; + eqe.event.port_mgmt_change.port = mlx4_phys_to_slave_port(dev, slave, port); return mlx4_GEN_EQE(dev, slave, &eqe); } @@ -241,7 +268,7 @@ int mlx4_gen_guid_change_eqe(struct mlx4_dev *dev, int slave, u8 port) eqe.type = MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT; eqe.subtype = MLX4_DEV_PMC_SUBTYPE_GUID_INFO; - eqe.event.port_mgmt_change.port = port; + eqe.event.port_mgmt_change.port = mlx4_phys_to_slave_port(dev, slave, port); return mlx4_GEN_EQE(dev, slave, &eqe); } @@ -251,6 +278,7 @@ int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port, u8 port_subtype_change) { struct mlx4_eqe eqe; + u8 slave_port = mlx4_phys_to_slave_port(dev, slave, port); /*don't send if we don't have the that slave */ if (dev->persist->num_vfs < slave) @@ -259,7 +287,7 @@ int mlx4_gen_port_state_change_eqe(struct mlx4_dev *dev, int slave, u8 port, eqe.type = MLX4_EVENT_TYPE_PORT_CHANGE; eqe.subtype = port_subtype_change; - eqe.event.port_change.port = cpu_to_be32(port << 28); + eqe.event.port_change.port = cpu_to_be32(slave_port << 28); mlx4_dbg(dev, "%s: sending: %d to slave: %d on port: %d\n", __func__, port_subtype_change, slave, port); @@ -573,7 +601,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) continue; mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n", __func__, i, port); - s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state; + s_info = &priv->mfunc.master.vf_oper[i].vport[port].state; if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) { eqe->event.port_change.port = cpu_to_be32( @@ -589,6 +617,10 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) if (SLAVE_PORT_GEN_EVENT_DOWN == gen_event) { if (i == mlx4_master_func_num(dev)) continue; + eqe->event.port_change.port = + cpu_to_be32( + (be32_to_cpu(eqe->event.port_change.port) & 0xFFFFFFF) + | (mlx4_phys_to_slave_port(dev, i, port) << 28)); mlx4_slave_event(dev, i, eqe); } } @@ -608,7 +640,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) continue; if (i == mlx4_master_func_num(dev)) continue; - s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state; + s_info = &priv->mfunc.master.vf_oper[i].vport[port].state; if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) { eqe->event.port_change.port = cpu_to_be32( @@ -879,8 +911,8 @@ static int mlx4_num_eq_uar(struct mlx4_dev *dev) * we need to map, take the difference of highest index and * the lowest index we'll use and add 1. */ - return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs + - dev->caps.comp_pool)/4 - dev->caps.reserved_eqs/4 + 1; + return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs) / 4 - + dev->caps.reserved_eqs / 4 + 1; } static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq) @@ -1069,32 +1101,21 @@ static void mlx4_free_eq(struct mlx4_dev *dev, static void mlx4_free_irqs(struct mlx4_dev *dev) { struct mlx4_eq_table *eq_table = &mlx4_priv(dev)->eq_table; - struct mlx4_priv *priv = mlx4_priv(dev); - int i, vec; + int i; if (eq_table->have_irq) free_irq(dev->persist->pdev->irq, dev); for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) if (eq_table->eq[i].have_irq) { + free_cpumask_var(eq_table->eq[i].affinity_mask); +#if defined(CONFIG_SMP) + irq_set_affinity_hint(eq_table->eq[i].irq, NULL); +#endif free_irq(eq_table->eq[i].irq, eq_table->eq + i); eq_table->eq[i].have_irq = 0; } - for (i = 0; i < dev->caps.comp_pool; i++) { - /* - * Freeing the assigned irq's - * all bits should be 0, but we need to validate - */ - if (priv->msix_ctl.pool_bm & 1ULL << i) { - /* NO need protecting*/ - vec = dev->caps.num_comp_vectors + 1 + i; - free_irq(priv->eq_table.eq[vec].irq, - &priv->eq_table.eq[vec]); - } - } - - kfree(eq_table->irq_names); } @@ -1175,76 +1196,73 @@ int mlx4_init_eq_table(struct mlx4_dev *dev) } priv->eq_table.irq_names = - kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1 + - dev->caps.comp_pool), + kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1), GFP_KERNEL); if (!priv->eq_table.irq_names) { err = -ENOMEM; - goto err_out_bitmap; + goto err_out_clr_int; } - for (i = 0; i < dev->caps.num_comp_vectors; ++i) { - err = mlx4_create_eq(dev, dev->caps.num_cqs - - dev->caps.reserved_cqs + - MLX4_NUM_SPARE_EQE, - (dev->flags & MLX4_FLAG_MSI_X) ? i : 0, - &priv->eq_table.eq[i]); - if (err) { - --i; - goto err_out_unmap; - } - } - - err = mlx4_create_eq(dev, MLX4_NUM_ASYNC_EQE + MLX4_NUM_SPARE_EQE, - (dev->flags & MLX4_FLAG_MSI_X) ? dev->caps.num_comp_vectors : 0, - &priv->eq_table.eq[dev->caps.num_comp_vectors]); - if (err) - goto err_out_comp; - - /*if additional completion vectors poolsize is 0 this loop will not run*/ - for (i = dev->caps.num_comp_vectors + 1; - i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i) { + for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) { + if (i == MLX4_EQ_ASYNC) { + err = mlx4_create_eq(dev, + MLX4_NUM_ASYNC_EQE + MLX4_NUM_SPARE_EQE, + 0, &priv->eq_table.eq[MLX4_EQ_ASYNC]); + } else { + struct mlx4_eq *eq = &priv->eq_table.eq[i]; +#ifdef CONFIG_RFS_ACCEL + int port = find_first_bit(eq->actv_ports.ports, + dev->caps.num_ports) + 1; + + if (port <= dev->caps.num_ports) { + struct mlx4_port_info *info = + &mlx4_priv(dev)->port[port]; + + if (!info->rmap) { + info->rmap = alloc_irq_cpu_rmap( + mlx4_get_eqs_per_port(dev, port)); + if (!info->rmap) { + mlx4_warn(dev, "Failed to allocate cpu rmap\n"); + err = -ENOMEM; + goto err_out_unmap; + } + } - err = mlx4_create_eq(dev, dev->caps.num_cqs - - dev->caps.reserved_cqs + - MLX4_NUM_SPARE_EQE, - (dev->flags & MLX4_FLAG_MSI_X) ? i : 0, - &priv->eq_table.eq[i]); - if (err) { - --i; - goto err_out_unmap; + err = irq_cpu_rmap_add( + info->rmap, eq->irq); + if (err) + mlx4_warn(dev, "Failed adding irq rmap\n"); + } +#endif + err = mlx4_create_eq(dev, dev->caps.num_cqs - + dev->caps.reserved_cqs + + MLX4_NUM_SPARE_EQE, + (dev->flags & MLX4_FLAG_MSI_X) ? + i + 1 - !!(i > MLX4_EQ_ASYNC) : 0, + eq); } + if (err) + goto err_out_unmap; } - if (dev->flags & MLX4_FLAG_MSI_X) { const char *eq_name; - for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) { - if (i < dev->caps.num_comp_vectors) { - snprintf(priv->eq_table.irq_names + - i * MLX4_IRQNAME_SIZE, - MLX4_IRQNAME_SIZE, - "mlx4-comp-%d@pci:%s", i, - pci_name(dev->persist->pdev)); - } else { - snprintf(priv->eq_table.irq_names + - i * MLX4_IRQNAME_SIZE, - MLX4_IRQNAME_SIZE, - "mlx4-async@pci:%s", - pci_name(dev->persist->pdev)); - } + snprintf(priv->eq_table.irq_names + + MLX4_EQ_ASYNC * MLX4_IRQNAME_SIZE, + MLX4_IRQNAME_SIZE, + "mlx4-async@pci:%s", + pci_name(dev->persist->pdev)); + eq_name = priv->eq_table.irq_names + + MLX4_EQ_ASYNC * MLX4_IRQNAME_SIZE; - eq_name = priv->eq_table.irq_names + - i * MLX4_IRQNAME_SIZE; - err = request_irq(priv->eq_table.eq[i].irq, - mlx4_msi_x_interrupt, 0, eq_name, - priv->eq_table.eq + i); - if (err) - goto err_out_async; + err = request_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq, + mlx4_msi_x_interrupt, 0, eq_name, + priv->eq_table.eq + MLX4_EQ_ASYNC); + if (err) + goto err_out_unmap; - priv->eq_table.eq[i].have_irq = 1; - } + priv->eq_table.eq[MLX4_EQ_ASYNC].have_irq = 1; } else { snprintf(priv->eq_table.irq_names, MLX4_IRQNAME_SIZE, @@ -1253,36 +1271,38 @@ int mlx4_init_eq_table(struct mlx4_dev *dev) err = request_irq(dev->persist->pdev->irq, mlx4_interrupt, IRQF_SHARED, priv->eq_table.irq_names, dev); if (err) - goto err_out_async; + goto err_out_unmap; priv->eq_table.have_irq = 1; } err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn); if (err) mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n", - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn, err); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn, err); - for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) - eq_set_ci(&priv->eq_table.eq[i], 1); + /* arm ASYNC eq */ + eq_set_ci(&priv->eq_table.eq[MLX4_EQ_ASYNC], 1); return 0; -err_out_async: - mlx4_free_eq(dev, &priv->eq_table.eq[dev->caps.num_comp_vectors]); - -err_out_comp: - i = dev->caps.num_comp_vectors - 1; - err_out_unmap: - while (i >= 0) { - mlx4_free_eq(dev, &priv->eq_table.eq[i]); - --i; + while (i >= 0) + mlx4_free_eq(dev, &priv->eq_table.eq[i--]); +#ifdef CONFIG_RFS_ACCEL + for (i = 1; i <= dev->caps.num_ports; i++) { + if (mlx4_priv(dev)->port[i].rmap) { + free_irq_cpu_rmap(mlx4_priv(dev)->port[i].rmap); + mlx4_priv(dev)->port[i].rmap = NULL; + } } +#endif + mlx4_free_irqs(dev); + +err_out_clr_int: if (!mlx4_is_slave(dev)) mlx4_unmap_clr_int(dev); - mlx4_free_irqs(dev); err_out_bitmap: mlx4_unmap_uar(dev); @@ -1300,11 +1320,19 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev) int i; mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 1, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn); +#ifdef CONFIG_RFS_ACCEL + for (i = 1; i <= dev->caps.num_ports; i++) { + if (mlx4_priv(dev)->port[i].rmap) { + free_irq_cpu_rmap(mlx4_priv(dev)->port[i].rmap); + mlx4_priv(dev)->port[i].rmap = NULL; + } + } +#endif mlx4_free_irqs(dev); - for (i = 0; i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i) + for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) mlx4_free_eq(dev, &priv->eq_table.eq[i]); if (!mlx4_is_slave(dev)) @@ -1355,87 +1383,169 @@ int mlx4_test_interrupts(struct mlx4_dev *dev) /* Return to default */ mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + priv->eq_table.eq[MLX4_EQ_ASYNC].eqn); return err; } EXPORT_SYMBOL(mlx4_test_interrupts); -int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, - int *vector) +bool mlx4_is_eq_vector_valid(struct mlx4_dev *dev, u8 port, int vector) { + struct mlx4_priv *priv = mlx4_priv(dev); + + vector = MLX4_CQ_TO_EQ_VECTOR(vector); + if (vector < 0 || (vector >= dev->caps.num_comp_vectors + 1) || + (vector == MLX4_EQ_ASYNC)) + return false; + + return test_bit(port - 1, priv->eq_table.eq[vector].actv_ports.ports); +} +EXPORT_SYMBOL(mlx4_is_eq_vector_valid); +u32 mlx4_get_eqs_per_port(struct mlx4_dev *dev, u8 port) +{ struct mlx4_priv *priv = mlx4_priv(dev); - int vec = 0, err = 0, i; + unsigned int i; + unsigned int sum = 0; + + for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) + sum += !!test_bit(port - 1, + priv->eq_table.eq[i].actv_ports.ports); + + return sum; +} +EXPORT_SYMBOL(mlx4_get_eqs_per_port); + +int mlx4_is_eq_shared(struct mlx4_dev *dev, int vector) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + vector = MLX4_CQ_TO_EQ_VECTOR(vector); + if (vector <= 0 || (vector >= dev->caps.num_comp_vectors + 1)) + return -EINVAL; + + return !!(bitmap_weight(priv->eq_table.eq[vector].actv_ports.ports, + dev->caps.num_ports) > 1); +} +EXPORT_SYMBOL(mlx4_is_eq_shared); + +struct cpu_rmap *mlx4_get_cpu_rmap(struct mlx4_dev *dev, int port) +{ + return mlx4_priv(dev)->port[port].rmap; +} +EXPORT_SYMBOL(mlx4_get_cpu_rmap); + +int mlx4_assign_eq(struct mlx4_dev *dev, u8 port, int *vector) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + int err = 0, i = 0; + u32 min_ref_count_val = (u32)-1; + int requested_vector = MLX4_CQ_TO_EQ_VECTOR(*vector); + int *prequested_vector = NULL; + mutex_lock(&priv->msix_ctl.pool_lock); - for (i = 0; !vec && i < dev->caps.comp_pool; i++) { - if (~priv->msix_ctl.pool_bm & 1ULL << i) { - priv->msix_ctl.pool_bm |= 1ULL << i; - vec = dev->caps.num_comp_vectors + 1 + i; - snprintf(priv->eq_table.irq_names + - vec * MLX4_IRQNAME_SIZE, - MLX4_IRQNAME_SIZE, "%s", name); -#ifdef CONFIG_RFS_ACCEL - if (rmap) { - err = irq_cpu_rmap_add(rmap, - priv->eq_table.eq[vec].irq); - if (err) - mlx4_warn(dev, "Failed adding irq rmap\n"); + if (requested_vector < (dev->caps.num_comp_vectors + 1) && + (requested_vector >= 0) && + (requested_vector != MLX4_EQ_ASYNC)) { + if (test_bit(port - 1, + priv->eq_table.eq[requested_vector].actv_ports.ports)) { + prequested_vector = &requested_vector; + } else { + struct mlx4_eq *eq; + + for (i = 1; i < port; + requested_vector += mlx4_get_eqs_per_port(dev, i++)) + ; + + eq = &priv->eq_table.eq[requested_vector]; + if (requested_vector < dev->caps.num_comp_vectors + 1 && + test_bit(port - 1, eq->actv_ports.ports)) { + prequested_vector = &requested_vector; } -#endif - err = request_irq(priv->eq_table.eq[vec].irq, - mlx4_msi_x_interrupt, 0, - &priv->eq_table.irq_names[vec<<5], - priv->eq_table.eq + vec); - if (err) { - /*zero out bit by fliping it*/ - priv->msix_ctl.pool_bm ^= 1 << i; - vec = 0; - continue; - /*we dont want to break here*/ + } + } + + if (!prequested_vector) { + requested_vector = -1; + for (i = 0; min_ref_count_val && i < dev->caps.num_comp_vectors + 1; + i++) { + struct mlx4_eq *eq = &priv->eq_table.eq[i]; + + if (min_ref_count_val > eq->ref_count && + test_bit(port - 1, eq->actv_ports.ports)) { + min_ref_count_val = eq->ref_count; + requested_vector = i; } + } + + if (requested_vector < 0) { + err = -ENOSPC; + goto err_unlock; + } + + prequested_vector = &requested_vector; + } + + if (!test_bit(*prequested_vector, priv->msix_ctl.pool_bm) && + dev->flags & MLX4_FLAG_MSI_X) { + set_bit(*prequested_vector, priv->msix_ctl.pool_bm); + snprintf(priv->eq_table.irq_names + + *prequested_vector * MLX4_IRQNAME_SIZE, + MLX4_IRQNAME_SIZE, "mlx4-%d@%s", + *prequested_vector, dev_name(&dev->persist->pdev->dev)); - eq_set_ci(&priv->eq_table.eq[vec], 1); + err = request_irq(priv->eq_table.eq[*prequested_vector].irq, + mlx4_msi_x_interrupt, 0, + &priv->eq_table.irq_names[*prequested_vector << 5], + priv->eq_table.eq + *prequested_vector); + + if (err) { + clear_bit(*prequested_vector, priv->msix_ctl.pool_bm); + *prequested_vector = -1; + } else { +#if defined(CONFIG_SMP) + mlx4_set_eq_affinity_hint(priv, *prequested_vector); +#endif + eq_set_ci(&priv->eq_table.eq[*prequested_vector], 1); + priv->eq_table.eq[*prequested_vector].have_irq = 1; } } + + if (!err && *prequested_vector >= 0) + priv->eq_table.eq[*prequested_vector].ref_count++; + +err_unlock: mutex_unlock(&priv->msix_ctl.pool_lock); - if (vec) { - *vector = vec; - } else { + if (!err && *prequested_vector >= 0) + *vector = MLX4_EQ_TO_CQ_VECTOR(*prequested_vector); + else *vector = 0; - err = (i == dev->caps.comp_pool) ? -ENOSPC : err; - } + return err; } EXPORT_SYMBOL(mlx4_assign_eq); -int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec) +int mlx4_eq_get_irq(struct mlx4_dev *dev, int cq_vec) { struct mlx4_priv *priv = mlx4_priv(dev); - return priv->eq_table.eq[vec].irq; + return priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq_vec)].irq; } EXPORT_SYMBOL(mlx4_eq_get_irq); void mlx4_release_eq(struct mlx4_dev *dev, int vec) { struct mlx4_priv *priv = mlx4_priv(dev); - /*bm index*/ - int i = vec - dev->caps.num_comp_vectors - 1; - - if (likely(i >= 0)) { - /*sanity check , making sure were not trying to free irq's - Belonging to a legacy EQ*/ - mutex_lock(&priv->msix_ctl.pool_lock); - if (priv->msix_ctl.pool_bm & 1ULL << i) { - free_irq(priv->eq_table.eq[vec].irq, - &priv->eq_table.eq[vec]); - priv->msix_ctl.pool_bm &= ~(1ULL << i); - } - mutex_unlock(&priv->msix_ctl.pool_lock); - } + int eq_vec = MLX4_CQ_TO_EQ_VECTOR(vec); + mutex_lock(&priv->msix_ctl.pool_lock); + priv->eq_table.eq[eq_vec].ref_count--; + + /* once we allocated EQ, we don't release it because it might be binded + * to cpu_rmap. + */ + mutex_unlock(&priv->msix_ctl.pool_lock); } EXPORT_SYMBOL(mlx4_release_eq); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index ced5ecab5..29c2a017a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -479,7 +479,15 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) } } - dev->caps.max_counters = 1 << ilog2(dev_cap->max_counters); + if (mlx4_is_master(dev) && (dev->caps.num_ports == 2) && + (port_type_array[0] == MLX4_PORT_TYPE_IB) && + (port_type_array[1] == MLX4_PORT_TYPE_ETH)) { + mlx4_warn(dev, + "Granular QoS per VF not supported with IB/Eth configuration\n"); + dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_QOS_VPP; + } + + dev->caps.max_counters = dev_cap->max_counters; dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps; dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] = @@ -1674,6 +1682,25 @@ static int map_internal_clock(struct mlx4_dev *dev) return 0; } +int mlx4_get_internal_clock_params(struct mlx4_dev *dev, + struct mlx4_clock_params *params) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + if (mlx4_is_slave(dev)) + return -ENOTSUPP; + + if (!params) + return -EINVAL; + + params->bar = priv->fw.clock_bar; + params->offset = priv->fw.clock_offset; + params->size = MLX4_CLOCK_SIZE; + + return 0; +} +EXPORT_SYMBOL_GPL(mlx4_get_internal_clock_params); + static void unmap_internal_clock(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -2193,20 +2220,78 @@ err_free_icm: static int mlx4_init_counters_table(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); - int nent; + int nent_pow2; if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS)) return -ENOENT; - nent = dev->caps.max_counters; - return mlx4_bitmap_init(&priv->counters_bitmap, nent, nent - 1, 0, 0); + if (!dev->caps.max_counters) + return -ENOSPC; + + nent_pow2 = roundup_pow_of_two(dev->caps.max_counters); + /* reserve last counter index for sink counter */ + return mlx4_bitmap_init(&priv->counters_bitmap, nent_pow2, + nent_pow2 - 1, 0, + nent_pow2 - dev->caps.max_counters + 1); } static void mlx4_cleanup_counters_table(struct mlx4_dev *dev) { + if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS)) + return; + + if (!dev->caps.max_counters) + return; + mlx4_bitmap_cleanup(&mlx4_priv(dev)->counters_bitmap); } +static void mlx4_cleanup_default_counters(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + int port; + + for (port = 0; port < dev->caps.num_ports; port++) + if (priv->def_counter[port] != -1) + mlx4_counter_free(dev, priv->def_counter[port]); +} + +static int mlx4_allocate_default_counters(struct mlx4_dev *dev) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + int port, err = 0; + u32 idx; + + for (port = 0; port < dev->caps.num_ports; port++) + priv->def_counter[port] = -1; + + for (port = 0; port < dev->caps.num_ports; port++) { + err = mlx4_counter_alloc(dev, &idx); + + if (!err || err == -ENOSPC) { + priv->def_counter[port] = idx; + } else if (err == -ENOENT) { + err = 0; + continue; + } else if (mlx4_is_slave(dev) && err == -EINVAL) { + priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev); + mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n", + MLX4_SINK_COUNTER_INDEX(dev)); + err = 0; + } else { + mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n", + __func__, port + 1, err); + mlx4_cleanup_default_counters(dev); + return err; + } + + mlx4_dbg(dev, "%s: default counter index %d for port %d\n", + __func__, priv->def_counter[port], port + 1); + } + + return err; +} + int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -2215,8 +2300,10 @@ int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx) return -ENOENT; *idx = mlx4_bitmap_alloc(&priv->counters_bitmap); - if (*idx == -1) - return -ENOMEM; + if (*idx == -1) { + *idx = MLX4_SINK_COUNTER_INDEX(dev); + return -ENOSPC; + } return 0; } @@ -2239,8 +2326,35 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx) } EXPORT_SYMBOL_GPL(mlx4_counter_alloc); +static int __mlx4_clear_if_stat(struct mlx4_dev *dev, + u8 counter_index) +{ + struct mlx4_cmd_mailbox *if_stat_mailbox; + int err; + u32 if_stat_in_mod = (counter_index & 0xff) | MLX4_QUERY_IF_STAT_RESET; + + if_stat_mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(if_stat_mailbox)) + return PTR_ERR(if_stat_mailbox); + + err = mlx4_cmd_box(dev, 0, if_stat_mailbox->dma, if_stat_in_mod, 0, + MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C, + MLX4_CMD_NATIVE); + + mlx4_free_cmd_mailbox(dev, if_stat_mailbox); + return err; +} + void __mlx4_counter_free(struct mlx4_dev *dev, u32 idx) { + if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_COUNTERS)) + return; + + if (idx == MLX4_SINK_COUNTER_INDEX(dev)) + return; + + __mlx4_clear_if_stat(dev, idx); + mlx4_bitmap_free(&mlx4_priv(dev)->counters_bitmap, idx, MLX4_USE_RR); return; } @@ -2260,6 +2374,14 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx) } EXPORT_SYMBOL_GPL(mlx4_counter_free); +int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + return priv->def_counter[port - 1]; +} +EXPORT_SYMBOL_GPL(mlx4_get_default_counter_index); + void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -2364,11 +2486,11 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) if (err) { if (dev->flags & MLX4_FLAG_MSI_X) { mlx4_warn(dev, "NOP command failed to generate MSI-X interrupt IRQ %d)\n", - priv->eq_table.eq[dev->caps.num_comp_vectors].irq); + priv->eq_table.eq[MLX4_EQ_ASYNC].irq); mlx4_warn(dev, "Trying again without MSI-X\n"); } else { mlx4_err(dev, "NOP command failed to generate interrupt (IRQ %d), aborting\n", - priv->eq_table.eq[dev->caps.num_comp_vectors].irq); + priv->eq_table.eq[MLX4_EQ_ASYNC].irq); mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n"); } @@ -2395,10 +2517,18 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) goto err_srq_table_free; } - err = mlx4_init_counters_table(dev); - if (err && err != -ENOENT) { - mlx4_err(dev, "Failed to initialize counters table, aborting\n"); - goto err_qp_table_free; + if (!mlx4_is_slave(dev)) { + err = mlx4_init_counters_table(dev); + if (err && err != -ENOENT) { + mlx4_err(dev, "Failed to initialize counters table, aborting\n"); + goto err_qp_table_free; + } + } + + err = mlx4_allocate_default_counters(dev); + if (err) { + mlx4_err(dev, "Failed to allocate default counters, aborting\n"); + goto err_counters_table_free; } if (!mlx4_is_slave(dev)) { @@ -2432,15 +2562,19 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) if (err) { mlx4_err(dev, "Failed to set port %d, aborting\n", port); - goto err_counters_table_free; + goto err_default_countes_free; } } } return 0; +err_default_countes_free: + mlx4_cleanup_default_counters(dev); + err_counters_table_free: - mlx4_cleanup_counters_table(dev); + if (!mlx4_is_slave(dev)) + mlx4_cleanup_counters_table(dev); err_qp_table_free: mlx4_cleanup_qp_table(dev); @@ -2481,14 +2615,45 @@ err_uar_table_free: return err; } +static int mlx4_init_affinity_hint(struct mlx4_dev *dev, int port, int eqn) +{ + int requested_cpu = 0; + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_eq *eq; + int off = 0; + int i; + + if (eqn > dev->caps.num_comp_vectors) + return -EINVAL; + + for (i = 1; i < port; i++) + off += mlx4_get_eqs_per_port(dev, i); + + requested_cpu = eqn - off - !!(eqn > MLX4_EQ_ASYNC); + + /* Meaning EQs are shared, and this call comes from the second port */ + if (requested_cpu < 0) + return 0; + + eq = &priv->eq_table.eq[eqn]; + + if (!zalloc_cpumask_var(&eq->affinity_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_set_cpu(requested_cpu, eq->affinity_mask); + + return 0; +} + static void mlx4_enable_msi_x(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); struct msix_entry *entries; int i; + int port = 0; if (msi_x) { - int nreq = dev->caps.num_ports * num_online_cpus() + MSIX_LEGACY_SZ; + int nreq = dev->caps.num_ports * num_online_cpus() + 1; nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs, nreq); @@ -2503,20 +2668,55 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) nreq = pci_enable_msix_range(dev->persist->pdev, entries, 2, nreq); - if (nreq < 0) { + if (nreq < 0 || nreq < MLX4_EQ_ASYNC) { kfree(entries); goto no_msi; - } else if (nreq < MSIX_LEGACY_SZ + - dev->caps.num_ports * MIN_MSIX_P_PORT) { - /*Working in legacy mode , all EQ's shared*/ - dev->caps.comp_pool = 0; - dev->caps.num_comp_vectors = nreq - 1; - } else { - dev->caps.comp_pool = nreq - MSIX_LEGACY_SZ; - dev->caps.num_comp_vectors = MSIX_LEGACY_SZ - 1; } - for (i = 0; i < nreq; ++i) - priv->eq_table.eq[i].irq = entries[i].vector; + /* 1 is reserved for events (asyncrounous EQ) */ + dev->caps.num_comp_vectors = nreq - 1; + + priv->eq_table.eq[MLX4_EQ_ASYNC].irq = entries[0].vector; + bitmap_zero(priv->eq_table.eq[MLX4_EQ_ASYNC].actv_ports.ports, + dev->caps.num_ports); + + for (i = 0; i < dev->caps.num_comp_vectors + 1; i++) { + if (i == MLX4_EQ_ASYNC) + continue; + + priv->eq_table.eq[i].irq = + entries[i + 1 - !!(i > MLX4_EQ_ASYNC)].vector; + + if (MLX4_IS_LEGACY_EQ_MODE(dev->caps)) { + bitmap_fill(priv->eq_table.eq[i].actv_ports.ports, + dev->caps.num_ports); + /* We don't set affinity hint when there + * aren't enough EQs + */ + } else { + set_bit(port, + priv->eq_table.eq[i].actv_ports.ports); + if (mlx4_init_affinity_hint(dev, port + 1, i)) + mlx4_warn(dev, "Couldn't init hint cpumask for EQ %d\n", + i); + } + /* We divide the Eqs evenly between the two ports. + * (dev->caps.num_comp_vectors / dev->caps.num_ports) + * refers to the number of Eqs per port + * (i.e eqs_per_port). Theoretically, we would like to + * write something like (i + 1) % eqs_per_port == 0. + * However, since there's an asynchronous Eq, we have + * to skip over it by comparing this condition to + * !!((i + 1) > MLX4_EQ_ASYNC). + */ + if ((dev->caps.num_comp_vectors > dev->caps.num_ports) && + ((i + 1) % + (dev->caps.num_comp_vectors / dev->caps.num_ports)) == + !!((i + 1) > MLX4_EQ_ASYNC)) + /* If dev->caps.num_comp_vectors < dev->caps.num_ports, + * everything is shared anyway. + */ + port++; + } dev->flags |= MLX4_FLAG_MSI_X; @@ -2526,10 +2726,15 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) no_msi: dev->caps.num_comp_vectors = 1; - dev->caps.comp_pool = 0; - for (i = 0; i < 2; ++i) + BUG_ON(MLX4_EQ_ASYNC >= 2); + for (i = 0; i < 2; ++i) { priv->eq_table.eq[i].irq = dev->persist->pdev->irq; + if (i != MLX4_EQ_ASYNC) { + bitmap_fill(priv->eq_table.eq[i].actv_ports.ports, + dev->caps.num_ports); + } + } } static int mlx4_init_port_info(struct mlx4_dev *dev, int port) @@ -2594,6 +2799,10 @@ static void mlx4_cleanup_port_info(struct mlx4_port_info *info) device_remove_file(&info->dev->persist->pdev->dev, &info->port_attr); device_remove_file(&info->dev->persist->pdev->dev, &info->port_mtu_attr); +#ifdef CONFIG_RFS_ACCEL + free_irq_cpu_rmap(info->rmap); + info->rmap = NULL; +#endif } static int mlx4_init_steering(struct mlx4_dev *dev) @@ -2749,6 +2958,7 @@ disable_sriov: free_mem: dev->persist->num_vfs = 0; kfree(dev->dev_vfs); + dev->dev_vfs = NULL; return dev_flags & ~MLX4_FLAG_MASTER; } @@ -2900,6 +3110,7 @@ slave_start: existing_vfs, reset_flow); + mlx4_close_fw(dev); mlx4_cmd_cleanup(dev, MLX4_CMD_CLEANUP_ALL); dev->flags = dev_flags; if (!SRIOV_VALID_STATE(dev->flags)) { @@ -2988,18 +3199,6 @@ slave_start: /* In master functions, the communication channel must be initialized * after obtaining its address from fw */ if (mlx4_is_master(dev)) { - int ib_ports = 0; - - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) - ib_ports++; - - if (ib_ports && - (num_vfs_argc > 1 || probe_vfs_argc > 1)) { - mlx4_err(dev, - "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n"); - err = -EINVAL; - goto err_close; - } if (dev->caps.num_ports < 2 && num_vfs_argc > 1) { err = -EINVAL; @@ -3036,7 +3235,7 @@ slave_start: if (err) goto err_master_mfunc; - priv->msix_ctl.pool_bm = 0; + bitmap_zero(priv->msix_ctl.pool_bm, MAX_MSIX); mutex_init(&priv->msix_ctl.pool_lock); mlx4_enable_msi_x(dev); @@ -3058,7 +3257,6 @@ slave_start: !mlx4_is_mfunc(dev)) { dev->flags &= ~MLX4_FLAG_MSI_X; dev->caps.num_comp_vectors = 1; - dev->caps.comp_pool = 0; pci_disable_msix(pdev); err = mlx4_setup_hca(dev); } @@ -3109,7 +3307,9 @@ err_port: for (--port; port >= 1; --port) mlx4_cleanup_port_info(&priv->port[port]); - mlx4_cleanup_counters_table(dev); + mlx4_cleanup_default_counters(dev); + if (!mlx4_is_slave(dev)) + mlx4_cleanup_counters_table(dev); mlx4_cleanup_qp_table(dev); mlx4_cleanup_srq_table(dev); mlx4_cleanup_cq_table(dev); @@ -3407,7 +3607,9 @@ static void mlx4_unload_one(struct pci_dev *pdev) mlx4_free_resource_tracker(dev, RES_TR_FREE_SLAVES_ONLY); - mlx4_cleanup_counters_table(dev); + mlx4_cleanup_default_counters(dev); + if (!mlx4_is_slave(dev)) + mlx4_cleanup_counters_table(dev); mlx4_cleanup_qp_table(dev); mlx4_cleanup_srq_table(dev); mlx4_cleanup_cq_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 502d3dd2c..a092c5c34 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -65,6 +65,8 @@ #define INIT_HCA_TPT_MW_ENABLE (1 << 7) +#define MLX4_QUERY_IF_STAT_RESET BIT(31) + enum { MLX4_HCR_BASE = 0x80680, MLX4_HCR_SIZE = 0x0001c, @@ -287,6 +289,12 @@ struct mlx4_icm_table { #define MLX4_CQE_SIZE_MASK_STRIDE 0x3 #define MLX4_EQE_SIZE_MASK_STRIDE 0x30 +#define MLX4_EQ_ASYNC 0 +#define MLX4_EQ_TO_CQ_VECTOR(vector) ((vector) - \ + !!((int)(vector) >= MLX4_EQ_ASYNC)) +#define MLX4_CQ_TO_EQ_VECTOR(vector) ((vector) + \ + !!((int)(vector) >= MLX4_EQ_ASYNC)) + /* * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits. */ @@ -391,6 +399,9 @@ struct mlx4_eq { struct mlx4_buf_list *page_list; struct mlx4_mtt mtt; struct mlx4_eq_tasklet tasklet_ctx; + struct mlx4_active_ports actv_ports; + u32 ref_count; + cpumask_var_t affinity_mask; }; struct mlx4_slave_eqe { @@ -808,6 +819,7 @@ struct mlx4_port_info { struct mlx4_vlan_table vlan_table; struct mlx4_roce_gid_table gid_table; int base_qpn; + struct cpu_rmap *rmap; }; struct mlx4_sense { @@ -818,7 +830,7 @@ struct mlx4_sense { }; struct mlx4_msix_ctl { - u64 pool_bm; + DECLARE_BITMAP(pool_bm, MAX_MSIX); struct mutex pool_lock; }; @@ -864,6 +876,7 @@ struct mlx4_priv { struct mlx4_qp_table qp_table; struct mlx4_mcg_table mcg_table; struct mlx4_bitmap counters_bitmap; + int def_counter[MLX4_MAX_PORTS]; struct mlx4_catas_err catas_err; @@ -997,6 +1010,8 @@ int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int start_index, int npages, u64 *page_list); int __mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); void __mlx4_counter_free(struct mlx4_dev *dev, u32 idx); +int mlx4_calc_vf_counters(struct mlx4_dev *dev, int slave, int port, + struct mlx4_counter *data); int __mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn); void __mlx4_xrcd_free(struct mlx4_dev *dev, u32 xrcdn); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 909fcf803..666d1669e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -339,7 +339,7 @@ struct mlx4_en_cq { struct napi_struct napi; int size; int buf_size; - unsigned vector; + int vector; enum cq_type is_tx; u16 moder_time; u16 moder_cnt; @@ -567,6 +567,7 @@ struct mlx4_en_priv { #endif struct mlx4_en_perf_stats pstats; struct mlx4_en_pkt_stats pkstats; + struct mlx4_en_counter_stats pf_stats; struct mlx4_en_flow_stats_rx rx_priority_flowstats[MLX4_NUM_PRIORITIES]; struct mlx4_en_flow_stats_tx tx_priority_flowstats[MLX4_NUM_PRIORITIES]; struct mlx4_en_flow_stats_rx rx_flowstats; @@ -582,6 +583,7 @@ struct mlx4_en_priv { struct device *ddev; struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE]; struct hwtstamp_config hwtstamp_config; + u32 counter_index; #ifdef CONFIG_MLX4_EN_DCB struct ieee_ets ets; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h index 00555832a..7fd466c0b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_stats.h @@ -23,6 +23,14 @@ struct mlx4_en_pkt_stats { #define NUM_PKT_STATS 43 }; +struct mlx4_en_counter_stats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +#define NUM_PF_STATS 4 +}; + struct mlx4_en_port_stats { unsigned long tso_packets; unsigned long xmit_more; @@ -99,7 +107,7 @@ enum { }; #define NUM_ALL_STATS (NUM_MAIN_STATS + NUM_PORT_STATS + NUM_PKT_STATS + \ - NUM_FLOW_STATS + NUM_PERF_STATS) + NUM_FLOW_STATS + NUM_PERF_STATS + NUM_PF_STATS) #define MLX4_FIND_NETDEV_STAT(n) (offsetof(struct net_device_stats, n) / \ sizeof(((struct net_device_stats *)0)->n)) diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c index 2bf437aaf..bae8b22ed 100644 --- a/drivers/net/ethernet/mellanox/mlx4/profile.c +++ b/drivers/net/ethernet/mellanox/mlx4/profile.c @@ -82,7 +82,6 @@ u64 mlx4_make_profile(struct mlx4_dev *dev, u64 total_size = 0; struct mlx4_resource *profile; - struct mlx4_resource tmp; struct sysinfo si; int i, j; @@ -149,11 +148,8 @@ u64 mlx4_make_profile(struct mlx4_dev *dev, */ for (i = MLX4_RES_NUM; i > 0; --i) for (j = 1; j < i; ++j) { - if (profile[j].size > profile[j - 1].size) { - tmp = profile[j]; - profile[j] = profile[j - 1]; - profile[j - 1] = tmp; - } + if (profile[j].size > profile[j - 1].size) + swap(profile[j], profile[j - 1]); } for (i = 0; i < MLX4_RES_NUM; ++i) { diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index b75214a80..20268634a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -749,7 +749,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) { int sort[MLX4_NUM_QP_REGION]; - int i, j, tmp; + int i, j; int last_base = dev->caps.num_qps; for (i = 1; i < MLX4_NUM_QP_REGION; ++i) @@ -758,11 +758,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) for (i = MLX4_NUM_QP_REGION; i > MLX4_QP_REGION_BOTTOM; --i) { for (j = MLX4_QP_REGION_BOTTOM + 2; j < i; ++j) { if (dev->caps.reserved_qps_cnt[sort[j]] > - dev->caps.reserved_qps_cnt[sort[j - 1]]) { - tmp = sort[j]; - sort[j] = sort[j - 1]; - sort[j - 1] = tmp; - } + dev->caps.reserved_qps_cnt[sort[j - 1]]) + swap(sort[j], sort[j - 1]); } } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index bafe2180c..731423ca5 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -46,8 +46,11 @@ #include "mlx4.h" #include "fw.h" +#include "mlx4_stats.h" #define MLX4_MAC_VALID (1ull << 63) +#define MLX4_PF_COUNTERS_PER_PORT 2 +#define MLX4_VF_COUNTERS_PER_PORT 1 struct mac_res { struct list_head list; @@ -459,11 +462,21 @@ void mlx4_init_quotas(struct mlx4_dev *dev) dev->quotas.mpt = priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[pf]; } + +static int get_max_gauranteed_vfs_counter(struct mlx4_dev *dev) +{ + /* reduce the sink counter */ + return (dev->caps.max_counters - 1 - + (MLX4_PF_COUNTERS_PER_PORT * MLX4_MAX_PORTS)) + / MLX4_MAX_PORTS; +} + int mlx4_init_resource_tracker(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); int i, j; int t; + int max_vfs_guarantee_counter = get_max_gauranteed_vfs_counter(dev); priv->mfunc.master.res_tracker.slave_list = kzalloc(dev->num_slaves * sizeof(struct slave_list), @@ -499,6 +512,9 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev) res_alloc->allocated = kzalloc((dev->persist-> num_vfs + 1) * sizeof(int), GFP_KERNEL); + /* Reduce the sink counter */ + if (i == RES_COUNTER) + res_alloc->res_free = dev->caps.max_counters - 1; if (!res_alloc->quota || !res_alloc->guaranteed || !res_alloc->allocated) @@ -577,9 +593,17 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev) break; case RES_COUNTER: res_alloc->quota[t] = dev->caps.max_counters; - res_alloc->guaranteed[t] = 0; if (t == mlx4_master_func_num(dev)) - res_alloc->res_free = res_alloc->quota[t]; + res_alloc->guaranteed[t] = + MLX4_PF_COUNTERS_PER_PORT * + MLX4_MAX_PORTS; + else if (t <= max_vfs_guarantee_counter) + res_alloc->guaranteed[t] = + MLX4_VF_COUNTERS_PER_PORT * + MLX4_MAX_PORTS; + else + res_alloc->guaranteed[t] = 0; + res_alloc->res_free -= res_alloc->guaranteed[t]; break; default: break; @@ -700,6 +724,9 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox, } } +static int handle_counter(struct mlx4_dev *dev, struct mlx4_qp_context *qpc, + u8 slave, int port); + static int update_vport_qp_param(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox, u8 slave, u32 qpn) @@ -715,6 +742,10 @@ static int update_vport_qp_param(struct mlx4_dev *dev, vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; qp_type = (be32_to_cpu(qpc->flags) >> 16) & 0xff; + err = handle_counter(dev, qpc, slave, port); + if (err) + goto out; + if (MLX4_VGT != vp_oper->state.default_vlan) { /* the reserved QPs (special, proxy, tunnel) * do not operate over vlans @@ -859,6 +890,83 @@ static void put_res(struct mlx4_dev *dev, int slave, u64 res_id, spin_unlock_irq(mlx4_tlock(dev)); } +static int counter_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, + u64 in_param, u64 *out_param, int port); + +static int handle_existing_counter(struct mlx4_dev *dev, u8 slave, int port, + int counter_index) +{ + struct res_common *r; + struct res_counter *counter; + int ret = 0; + + if (counter_index == MLX4_SINK_COUNTER_INDEX(dev)) + return ret; + + spin_lock_irq(mlx4_tlock(dev)); + r = find_res(dev, counter_index, RES_COUNTER); + if (!r || r->owner != slave) + ret = -EINVAL; + counter = container_of(r, struct res_counter, com); + if (!counter->port) + counter->port = port; + + spin_unlock_irq(mlx4_tlock(dev)); + return ret; +} + +static int handle_unexisting_counter(struct mlx4_dev *dev, + struct mlx4_qp_context *qpc, u8 slave, + int port) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker; + struct res_common *tmp; + struct res_counter *counter; + u64 counter_idx = MLX4_SINK_COUNTER_INDEX(dev); + int err = 0; + + spin_lock_irq(mlx4_tlock(dev)); + list_for_each_entry(tmp, + &tracker->slave_list[slave].res_list[RES_COUNTER], + list) { + counter = container_of(tmp, struct res_counter, com); + if (port == counter->port) { + qpc->pri_path.counter_index = counter->com.res_id; + spin_unlock_irq(mlx4_tlock(dev)); + return 0; + } + } + spin_unlock_irq(mlx4_tlock(dev)); + + /* No existing counter, need to allocate a new counter */ + err = counter_alloc_res(dev, slave, RES_OP_RESERVE, 0, 0, &counter_idx, + port); + if (err == -ENOENT) { + err = 0; + } else if (err && err != -ENOSPC) { + mlx4_err(dev, "%s: failed to create new counter for slave %d err %d\n", + __func__, slave, err); + } else { + qpc->pri_path.counter_index = counter_idx; + mlx4_dbg(dev, "%s: alloc new counter for slave %d index %d\n", + __func__, slave, qpc->pri_path.counter_index); + err = 0; + } + + return err; +} + +static int handle_counter(struct mlx4_dev *dev, struct mlx4_qp_context *qpc, + u8 slave, int port) +{ + if (qpc->pri_path.counter_index != MLX4_SINK_COUNTER_INDEX(dev)) + return handle_existing_counter(dev, slave, port, + qpc->pri_path.counter_index); + + return handle_unexisting_counter(dev, qpc, slave, port); +} + static struct res_common *alloc_qp_tr(int id) { struct res_qp *ret; @@ -952,7 +1060,7 @@ static struct res_common *alloc_srq_tr(int id) return &ret->com; } -static struct res_common *alloc_counter_tr(int id) +static struct res_common *alloc_counter_tr(int id, int port) { struct res_counter *ret; @@ -962,6 +1070,7 @@ static struct res_common *alloc_counter_tr(int id) ret->com.res_id = id; ret->com.state = RES_COUNTER_ALLOCATED; + ret->port = port; return &ret->com; } @@ -1022,7 +1131,7 @@ static struct res_common *alloc_tr(u64 id, enum mlx4_resource type, int slave, pr_err("implementation missing\n"); return NULL; case RES_COUNTER: - ret = alloc_counter_tr(id); + ret = alloc_counter_tr(id, extra); break; case RES_XRCD: ret = alloc_xrcdn_tr(id); @@ -1039,6 +1148,53 @@ static struct res_common *alloc_tr(u64 id, enum mlx4_resource type, int slave, return ret; } +int mlx4_calc_vf_counters(struct mlx4_dev *dev, int slave, int port, + struct mlx4_counter *data) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker; + struct res_common *tmp; + struct res_counter *counter; + int *counters_arr; + int i = 0, err = 0; + + memset(data, 0, sizeof(*data)); + + counters_arr = kmalloc_array(dev->caps.max_counters, + sizeof(*counters_arr), GFP_KERNEL); + if (!counters_arr) + return -ENOMEM; + + spin_lock_irq(mlx4_tlock(dev)); + list_for_each_entry(tmp, + &tracker->slave_list[slave].res_list[RES_COUNTER], + list) { + counter = container_of(tmp, struct res_counter, com); + if (counter->port == port) { + counters_arr[i] = (int)tmp->res_id; + i++; + } + } + spin_unlock_irq(mlx4_tlock(dev)); + counters_arr[i] = -1; + + i = 0; + + while (counters_arr[i] != -1) { + err = mlx4_get_counter_stats(dev, counters_arr[i], data, + 0); + if (err) { + memset(data, 0, sizeof(*data)); + goto table_changed; + } + i++; + } + +table_changed: + kfree(counters_arr); + return 0; +} + static int add_res_range(struct mlx4_dev *dev, int slave, u64 base, int count, enum mlx4_resource type, int extra) { @@ -2001,7 +2157,7 @@ static int vlan_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, } static int counter_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, - u64 in_param, u64 *out_param) + u64 in_param, u64 *out_param, int port) { u32 index; int err; @@ -2019,7 +2175,7 @@ static int counter_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, return err; } - err = add_res_range(dev, slave, index, 1, RES_COUNTER, 0); + err = add_res_range(dev, slave, index, 1, RES_COUNTER, port); if (err) { __mlx4_counter_free(dev, index); mlx4_release_resource(dev, slave, RES_COUNTER, 1, 0); @@ -2101,7 +2257,7 @@ int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave, case RES_COUNTER: err = counter_alloc_res(dev, slave, vhcr->op_modifier, alop, - vhcr->in_param, &vhcr->out_param); + vhcr->in_param, &vhcr->out_param, 0); break; case RES_XRCD: @@ -2335,6 +2491,9 @@ static int counter_free_res(struct mlx4_dev *dev, int slave, int op, int cmd, return -EINVAL; index = get_param_l(&in_param); + if (index == MLX4_SINK_COUNTER_INDEX(dev)) + return 0; + err = rem_res_range(dev, slave, index, 1, RES_COUNTER, 0); if (err) return err; @@ -2703,6 +2862,10 @@ static void adjust_proxy_tun_qkey(struct mlx4_dev *dev, struct mlx4_vhcr *vhcr, context->qkey = cpu_to_be32(qkey); } +static int adjust_qp_sched_queue(struct mlx4_dev *dev, int slave, + struct mlx4_qp_context *qpc, + struct mlx4_cmd_mailbox *inbox); + int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -2725,6 +2888,10 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, struct res_srq *srq; int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff; + err = adjust_qp_sched_queue(dev, slave, qpc, inbox); + if (err) + return err; + err = qp_res_start_move_to(dev, slave, qpn, RES_QP_HW, &qp, 0); if (err) return err; @@ -3526,8 +3693,8 @@ static int adjust_qp_sched_queue(struct mlx4_dev *dev, int slave, pri_sched_queue = (qpc->pri_path.sched_queue & ~(1 << 6)) | ((port & 1) << 6); - if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH || - mlx4_is_eth(dev, port + 1)) { + if (optpar & (MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH | MLX4_QP_OPTPAR_SCHED_QUEUE) || + qpc->pri_path.sched_queue || mlx4_is_eth(dev, port + 1)) { qpc->pri_path.sched_queue = pri_sched_queue; } @@ -3965,6 +4132,22 @@ static int validate_eth_header_mac(int slave, struct _rule_hw *eth_header, return 0; } +static void handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl, + struct _rule_hw *eth_header) +{ + if (is_multicast_ether_addr(eth_header->eth.dst_mac) || + is_broadcast_ether_addr(eth_header->eth.dst_mac)) { + struct mlx4_net_trans_rule_hw_eth *eth = + (struct mlx4_net_trans_rule_hw_eth *)eth_header; + struct _rule_hw *next_rule = (struct _rule_hw *)(eth + 1); + bool last_rule = next_rule->size == 0 && next_rule->id == 0 && + next_rule->rsvd == 0; + + if (last_rule) + ctrl->prio = cpu_to_be16(MLX4_DOMAIN_NIC); + } +} + /* * In case of missing eth header, append eth header with a MAC address * assigned to the VF. @@ -4117,6 +4300,12 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, rule_header = (struct _rule_hw *)(ctrl + 1); header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id)); + if (header_id == MLX4_NET_TRANS_RULE_ID_ETH) + handle_eth_header_mcast_prio(ctrl, rule_header); + + if (slave == dev->caps.function) + goto execute; + switch (header_id) { case MLX4_NET_TRANS_RULE_ID_ETH: if (validate_eth_header_mac(slave, rule_header, rlist)) { @@ -4143,6 +4332,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave, goto err_put; } +execute: err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param, vhcr->in_modifier, 0, MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A, -- cgit v1.2.3