5 files changed, 46 insertions, 10 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 0f1afc0..32f5ec7 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);
 	}
@@ -1721,7 +1722,7 @@ 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]);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 4fdd3c3..2a77a6b 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);
@@ -491,6 +496,23 @@ 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 1783705..f7bf312 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_local_first(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/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index a407981..e30bf57 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)
@@ -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/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 9de3021..d021f07 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -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);