summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/mellanox/mlx4
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/mellanox/mlx4')
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/cmd.c74
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/cq.c13
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_cq.c56
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_ethtool.c29
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_netdev.c20
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_port.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_rx.c39
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/en_tx.c8
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/eq.c402
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/fw.c20
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/main.c155
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/mlx4.h13
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/mlx4_en.h3
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/resource_tracker.c57
14 files changed, 595 insertions, 296 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index f0fbb4ade85d..68ae765873a9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -714,8 +714,13 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
msecs_to_jiffies(timeout))) {
mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
op);
- err = -EIO;
- goto out_reset;
+ if (op == MLX4_CMD_NOP) {
+ err = -EBUSY;
+ goto out;
+ } else {
+ err = -EIO;
+ goto out_reset;
+ }
}
err = context->result;
@@ -877,7 +882,7 @@ 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;
@@ -889,7 +894,8 @@ 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 */
@@ -925,8 +931,9 @@ 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)) {
@@ -939,25 +946,38 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
return err;
}
if (smp->attr_id == IB_SMP_ATTR_GUID_INFO) {
- /* compute slave's gid block */
- smp->attr_mod = cpu_to_be32(slave / 8);
- /* execute cmd */
- err = mlx4_cmd_box(dev, inbox->dma, outbox->dma,
- vhcr->in_modifier, opcode_modifier,
- vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
- if (!err) {
- /* if needed, move slave gid to index 0 */
- if (slave % 8)
- memcpy(outsmp->data,
- outsmp->data + (slave % 8) * 8, 8);
- /* delete all other gids */
- memset(outsmp->data + 8, 0, 56);
+ __be64 guid = mlx4_get_admin_guid(dev, slave,
+ port);
+
+ /* set the PF admin guid to the FW/HW burned
+ * GUID, if it wasn't yet set
+ */
+ if (slave == 0 && guid == 0) {
+ smp->attr_mod = 0;
+ err = mlx4_cmd_box(dev,
+ inbox->dma,
+ outbox->dma,
+ vhcr->in_modifier,
+ opcode_modifier,
+ vhcr->op,
+ MLX4_CMD_TIME_CLASS_C,
+ MLX4_CMD_NATIVE);
+ if (err)
+ return err;
+ mlx4_set_admin_guid(dev,
+ *(__be64 *)outsmp->
+ data, slave, port);
+ } else {
+ memcpy(outsmp->data, &guid, 8);
}
- return err;
+
+ /* clean all other gids */
+ memset(outsmp->data + 8, 0, 56);
+ return 0;
}
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);
@@ -2350,6 +2370,7 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
oper_vport->qos_vport = MLX4_VPP_DEFAULT_VPORT;
vf_oper->vport[port].vlan_idx = NO_INDX;
vf_oper->vport[port].mac_idx = NO_INDX;
+ mlx4_set_random_admin_guid(dev, i, port);
}
spin_lock_init(&s_state->lock);
}
@@ -2896,7 +2917,7 @@ 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;
}
@@ -3178,6 +3199,12 @@ 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;
@@ -3187,6 +3214,11 @@ 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 e71f31387ac6..3348e646db70 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 22da4d0d0f05..63769df872a4 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 3f44e2bbb982..a2ddf3d75ff8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1102,20 +1102,21 @@ static int mlx4_en_check_rxfh_func(struct net_device *dev, u8 hfunc)
struct mlx4_en_priv *priv = netdev_priv(dev);
/* check if requested function is supported by the device */
- if ((hfunc == ETH_RSS_HASH_TOP &&
- !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP)) ||
- (hfunc == ETH_RSS_HASH_XOR &&
- !(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR)))
- return -EINVAL;
+ if (hfunc == ETH_RSS_HASH_TOP) {
+ if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_TOP))
+ return -EINVAL;
+ if (!(dev->features & NETIF_F_RXHASH))
+ en_warn(priv, "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n");
+ return 0;
+ } else if (hfunc == ETH_RSS_HASH_XOR) {
+ if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS_XOR))
+ return -EINVAL;
+ if (dev->features & NETIF_F_RXHASH)
+ en_warn(priv, "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n");
+ return 0;
+ }
- priv->rss_hash_fn = hfunc;
- if (hfunc == ETH_RSS_HASH_TOP && !(dev->features & NETIF_F_RXHASH))
- en_warn(priv,
- "Toeplitz hash function should be used in conjunction with RX hashing for optimal performance\n");
- if (hfunc == ETH_RSS_HASH_XOR && (dev->features & NETIF_F_RXHASH))
- en_warn(priv,
- "Enabling both XOR Hash function and RX Hashing can limit RPS functionality\n");
- return 0;
+ return -EINVAL;
}
static int mlx4_en_get_rxfh(struct net_device *dev, u32 *ring_index, u8 *key,
@@ -1189,6 +1190,8 @@ static int mlx4_en_set_rxfh(struct net_device *dev, const u32 *ring_index,
priv->prof->rss_rings = rss_rings;
if (key)
memcpy(priv->rss_key, key, MLX4_EN_RSS_KEY_SIZE);
+ if (hfunc != ETH_RSS_HASH_NO_CHANGE)
+ priv->rss_hash_fn = hfunc;
if (port_up) {
err = mlx4_en_start_port(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 0f1afc085d58..98efb5842fca 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1467,6 +1467,7 @@ static void mlx4_en_service_task(struct work_struct *work)
if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)
mlx4_en_ptp_overflow_check(mdev);
+ mlx4_en_recover_from_oom(priv);
queue_delayed_work(mdev->workqueue, &priv->service_task,
SERVICE_TASK_DELAY);
}
@@ -1500,17 +1501,13 @@ static int mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
{
struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
int numa_node = priv->mdev->dev->numa_node;
- int ret = 0;
if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL))
return -ENOMEM;
- ret = cpumask_set_cpu_local_first(ring_idx, numa_node,
- ring->affinity_mask);
- if (ret)
- free_cpumask_var(ring->affinity_mask);
-
- return ret;
+ cpumask_set_cpu(cpumask_local_spread(ring_idx, numa_node),
+ ring->affinity_mask);
+ return 0;
}
static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
@@ -1721,7 +1718,7 @@ mac_err:
cq_err:
while (rx_index--) {
mlx4_en_deactivate_cq(priv, priv->rx_cq[rx_index]);
- mlx4_en_free_affinity_hint(priv, i);
+ mlx4_en_free_affinity_hint(priv, rx_index);
}
for (i = 0; i < priv->rx_ring_num; i++)
mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
@@ -1957,7 +1954,6 @@ 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
@@ -2015,11 +2011,7 @@ 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;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 54f0e5ab2e55..0a56f010c846 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -139,7 +139,7 @@ static unsigned long en_stats_adder(__be64 *start, __be64 *next, int num)
int i;
int offset = next - start;
- for (i = 0; i <= num; i++) {
+ for (i = 0; i < num; i++) {
ret += be64_to_cpu(*curr);
curr += offset;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 4fdd3c37e47b..35f726c17e48 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -244,6 +244,12 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
return mlx4_en_alloc_frags(priv, rx_desc, frags, ring->page_alloc, gfp);
}
+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;
+}
+
static inline void mlx4_en_update_rx_prod_db(struct mlx4_en_rx_ring *ring)
{
*ring->wqres.db.db = cpu_to_be32(ring->prod & 0xffff);
@@ -315,8 +321,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
ring->cons, ring->prod);
/* Unmap and free Rx buffers */
- BUG_ON((u32) (ring->prod - ring->cons) > ring->actual_size);
- while (ring->cons != ring->prod) {
+ while (!mlx4_en_is_ring_empty(ring)) {
index = ring->cons & ring->size_mask;
en_dbg(DRV, priv, "Processing descriptor:%d\n", index);
mlx4_en_free_rx_desc(priv, ring, index);
@@ -332,15 +337,10 @@ 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,
@@ -491,6 +491,23 @@ err_allocator:
return err;
}
+/* We recover from out of memory by scheduling our napi poll
+ * function (mlx4_en_process_cq), which tries to allocate
+ * all missing RX buffers (call to mlx4_en_refill_rx_buffers).
+ */
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
+{
+ int ring;
+
+ if (!priv->port_up)
+ return;
+
+ for (ring = 0; ring < priv->rx_ring_num; ring++) {
+ if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+ napi_reschedule(&priv->rx_cq[ring]->napi);
+ }
+}
+
void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring **pring,
u32 size, u16 stride)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 1783705273d8..7bed3a88579f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -143,8 +143,10 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
ring->hwtstamp_tx_type = priv->hwtstamp_config.tx_type;
ring->queue_index = queue_index;
- if (queue_index < priv->num_tx_rings_p_up && cpu_online(queue_index))
- cpumask_set_cpu(queue_index, &ring->affinity_mask);
+ if (queue_index < priv->num_tx_rings_p_up)
+ cpumask_set_cpu(cpumask_local_spread(queue_index,
+ priv->mdev->dev->numa_node),
+ &ring->affinity_mask);
*pring = ring;
return 0;
@@ -213,7 +215,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context,
&ring->qp, &ring->qp_state);
- if (!user_prio && cpu_online(ring->queue_index))
+ if (!cpumask_empty(&ring->affinity_mask))
netif_set_xps_queue(priv->dev, &ring->affinity_mask,
ring->queue_index);
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 190fd624bdfe..aae13adfb492 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);
@@ -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);
}
}
@@ -702,6 +734,8 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
priv->mfunc.master.slave_state[flr_slave].is_slave_going_down = 1;
}
spin_unlock_irqrestore(&priv->mfunc.master.slave_state_lock, flags);
+ mlx4_dispatch_event(dev, MLX4_DEV_EVENT_SLAVE_SHUTDOWN,
+ flr_slave);
queue_work(priv->mfunc.master.comm_wq,
&priv->mfunc.master.slave_flr_event_work);
break;
@@ -877,8 +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)
@@ -1067,32 +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);
}
@@ -1173,76 +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,
@@ -1251,36 +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);
@@ -1298,11 +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))
@@ -1353,87 +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/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index b9881fc1252f..e30bf57ad7a1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -56,11 +56,13 @@ MODULE_PARM_DESC(enable_qos, "Enable Enhanced QoS support (default: on)");
#define MLX4_GET(dest, source, offset) \
do { \
void *__p = (char *) (source) + (offset); \
+ u64 val; \
switch (sizeof (dest)) { \
case 1: (dest) = *(u8 *) __p; break; \
case 2: (dest) = be16_to_cpup(__p); break; \
case 4: (dest) = be32_to_cpup(__p); break; \
- case 8: (dest) = be64_to_cpup(__p); break; \
+ case 8: val = get_unaligned((u64 *)__p); \
+ (dest) = be64_to_cpu(val); break; \
default: __buggy_use_of_MLX4_GET(); \
} \
} while (0)
@@ -781,10 +783,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
dev_cap->num_ports = field & 0xf;
MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_MSG_SZ_OFFSET);
+ dev_cap->max_msg_sz = 1 << (field & 0x1f);
MLX4_GET(field, outbox, QUERY_DEV_CAP_PORT_FLOWSTATS_COUNTERS_OFFSET);
if (field & 0x10)
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FLOWSTATS_EN;
- dev_cap->max_msg_sz = 1 << (field & 0x1f);
MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET);
if (field & 0x80)
dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN;
@@ -1605,9 +1607,17 @@ static void get_board_id(void *vsd, char *board_id)
* swaps each 4-byte word before passing it back to
* us. Therefore we need to swab it before printing.
*/
- for (i = 0; i < 4; ++i)
- ((u32 *) board_id)[i] =
- swab32(*(u32 *) (vsd + VSD_OFFSET_MLX_BOARD_ID + i * 4));
+ u32 *bid_u32 = (u32 *)board_id;
+
+ for (i = 0; i < 4; ++i) {
+ u32 *addr;
+ u32 val;
+
+ addr = (u32 *) (vsd + VSD_OFFSET_MLX_BOARD_ID + i * 4);
+ val = get_unaligned(addr);
+ val = swab32(val);
+ put_unaligned(val, &bid_u32[i]);
+ }
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index acceb75e8c44..7d57777e65c5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2260,6 +2260,37 @@ void mlx4_counter_free(struct mlx4_dev *dev, u32 idx)
}
EXPORT_SYMBOL_GPL(mlx4_counter_free);
+void mlx4_set_admin_guid(struct mlx4_dev *dev, __be64 guid, int entry, int port)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ priv->mfunc.master.vf_admin[entry].vport[port].guid = guid;
+}
+EXPORT_SYMBOL_GPL(mlx4_set_admin_guid);
+
+__be64 mlx4_get_admin_guid(struct mlx4_dev *dev, int entry, int port)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ return priv->mfunc.master.vf_admin[entry].vport[port].guid;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_admin_guid);
+
+void mlx4_set_random_admin_guid(struct mlx4_dev *dev, int entry, int port)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ __be64 guid;
+
+ /* hw GUID */
+ if (entry == 0)
+ return;
+
+ get_random_bytes((char *)&guid, sizeof(guid));
+ guid &= ~(cpu_to_be64(1ULL << 56));
+ guid |= cpu_to_be64(1ULL << 57);
+ priv->mfunc.master.vf_admin[entry].vport[port].guid = guid;
+}
+
static int mlx4_setup_hca(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
@@ -2333,11 +2364,11 @@ 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");
}
@@ -2450,14 +2481,45 @@ 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);
@@ -2472,20 +2534,55 @@ 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;
@@ -2495,10 +2592,15 @@ 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)
@@ -2563,6 +2665,10 @@ 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)
@@ -2718,6 +2824,7 @@ disable_sriov:
free_mem:
dev->persist->num_vfs = 0;
kfree(dev->dev_vfs);
+ dev->dev_vfs = NULL;
return dev_flags & ~MLX4_FLAG_MASTER;
}
@@ -2869,6 +2976,7 @@ 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)) {
@@ -2957,18 +3065,6 @@ 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;
@@ -3005,7 +3101,7 @@ 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);
@@ -3027,7 +3123,6 @@ 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);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index f30eeb730a86..f424900d23a6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -287,6 +287,12 @@ 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 +397,9 @@ 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 {
@@ -499,6 +508,7 @@ struct mlx4_vport_state {
bool spoofchk;
u32 link_state;
u8 qos_vport;
+ __be64 guid;
};
struct mlx4_vf_admin_state {
@@ -807,6 +817,7 @@ 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 {
@@ -817,7 +828,7 @@ struct mlx4_sense {
};
struct mlx4_msix_ctl {
- u64 pool_bm;
+ DECLARE_BITMAP(pool_bm, MAX_MSIX);
struct mutex pool_lock;
};
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 9de30216b146..edd8fd69ec9a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -338,7 +338,7 @@ 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;
@@ -774,6 +774,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv,
void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_tx_ring *ring);
void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev);
+void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv);
int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
struct mlx4_en_rx_ring **pring,
u32 size, u16 stride, int node);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index c7f28bf4b8e2..ab48386bfefc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2703,6 +2703,10 @@ 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 +2729,10 @@ 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;
@@ -2845,7 +2853,7 @@ int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
{
int err;
int eqn = vhcr->in_modifier;
- int res_id = (slave << 8) | eqn;
+ int res_id = (slave << 10) | eqn;
struct mlx4_eq_context *eqc = inbox->buf;
int mtt_base = eq_get_mtt_addr(eqc) / dev->caps.mtt_entry_sz;
int mtt_size = eq_get_mtt_size(eqc);
@@ -3051,7 +3059,7 @@ int mlx4_HW2SW_EQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_cmd_info *cmd)
{
int eqn = vhcr->in_modifier;
- int res_id = eqn | (slave << 8);
+ int res_id = eqn | (slave << 10);
struct res_eq *eq;
int err;
@@ -3108,7 +3116,7 @@ int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe)
return 0;
mutex_lock(&priv->mfunc.master.gen_eqe_mutex[slave]);
- res_id = (slave << 8) | event_eq->eqn;
+ res_id = (slave << 10) | event_eq->eqn;
err = get_res(dev, slave, res_id, RES_EQ, &req);
if (err)
goto unlock;
@@ -3131,7 +3139,7 @@ int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe)
memcpy(mailbox->buf, (u8 *) eqe, 28);
- in_modifier = (slave & 0xff) | ((event_eq->eqn & 0xff) << 16);
+ in_modifier = (slave & 0xff) | ((event_eq->eqn & 0x3ff) << 16);
err = mlx4_cmd(dev, mailbox->dma, in_modifier, 0,
MLX4_CMD_GEN_EQE, MLX4_CMD_TIME_CLASS_B,
@@ -3157,7 +3165,7 @@ int mlx4_QUERY_EQ_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_cmd_info *cmd)
{
int eqn = vhcr->in_modifier;
- int res_id = eqn | (slave << 8);
+ int res_id = eqn | (slave << 10);
struct res_eq *eq;
int err;
@@ -3187,7 +3195,7 @@ int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave,
int cqn = vhcr->in_modifier;
struct mlx4_cq_context *cqc = inbox->buf;
int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz;
- struct res_cq *cq;
+ struct res_cq *cq = NULL;
struct res_mtt *mtt;
err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_HW, &cq);
@@ -3223,7 +3231,7 @@ int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave,
{
int err;
int cqn = vhcr->in_modifier;
- struct res_cq *cq;
+ struct res_cq *cq = NULL;
err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_ALLOCATED, &cq);
if (err)
@@ -3362,7 +3370,7 @@ int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
int err;
int srqn = vhcr->in_modifier;
struct res_mtt *mtt;
- struct res_srq *srq;
+ struct res_srq *srq = NULL;
struct mlx4_srq_context *srqc = inbox->buf;
int mtt_base = srq_get_mtt_addr(srqc) / dev->caps.mtt_entry_sz;
@@ -3406,7 +3414,7 @@ int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
{
int err;
int srqn = vhcr->in_modifier;
- struct res_srq *srq;
+ struct res_srq *srq = NULL;
err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_ALLOCATED, &srq);
if (err)
@@ -3526,8 +3534,8 @@ 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 +3973,22 @@ 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 +4141,12 @@ 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 +4173,7 @@ 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,
@@ -4714,13 +4745,13 @@ static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
break;
case RES_EQ_HW:
- err = mlx4_cmd(dev, slave, eqn & 0xff,
+ err = mlx4_cmd(dev, slave, eqn & 0x3ff,
1, MLX4_CMD_HW2SW_EQ,
MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_NATIVE);
if (err)
mlx4_dbg(dev, "rem_slave_eqs: failed to move slave %d eqs %d to SW ownership\n",
- slave, eqn);
+ slave, eqn & 0x3ff);
atomic_dec(&eq->mtt->ref_count);
state = RES_EQ_RESERVED;
break;