[PATCH 4.0 05/72] net/mlx4_en: Schedule napi when RX buffers allocation fails

[Greg Kroah-Hartman]

4.0-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ido Shamay <idos@xxxxxxxxxxxx>

[ Upstream commit 07841f9d94c11afe00c0498cf242edf4075729f4 ]

When system is out of memory, refilling of RX buffers fails while
the driver continue to pass the received packets to the kernel stack.
At some point, when all RX buffers deplete, driver may fall into a
sleep, and not recover when memory for new RX buffers is once again
availible. This is because hardware does not have valid descriptors,
so no interrupt will be generated for the driver to return to work
in napi context. Fix it by schedule the napi poll function from
stats_task delayed workqueue, as long as the allocations fail.

Signed-off-by: Ido Shamay <idos@xxxxxxxxxxxx>
Signed-off-by: Amir Vadai <amirv@xxxxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c |    1 
 drivers/net/ethernet/mellanox/mlx4/en_rx.c     |   26 +++++++++++++++++++++++--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |    1 
 3 files changed, 26 insertions(+), 2 deletions(-)

--- 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
 		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);
 	}
--- 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(struc
 	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 m
 	       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)
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -790,6 +790,7 @@ int mlx4_en_activate_tx_ring(struct mlx4
 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);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/