net/mlx5e: Wrap the tx reporter dump callback to extract the sq

Function mlx5e_tx_reporter_dump_sq() casts its void * argument to struct
mlx5e_txqsq *, but in TX-timeout-recovery flow the argument is actually
of type struct mlx5e_tx_timeout_ctx *.

 mlx5_core 0000:08:00.1 enp8s0f1: TX timeout detected
 mlx5_core 0000:08:00.1 enp8s0f1: TX timeout on queue: 1, SQ: 0x11ec, CQ: 0x146d, SQ Cons: 0x0 SQ Prod: 0x1, usecs since last trans: 21565000
 BUG: stack guard page was hit at 0000000093f1a2de (stack is 00000000b66ea0dc..000000004d932dae)
 kernel stack overflow (page fault): 0000 [#1] SMP NOPTI
 CPU: 5 PID: 95 Comm: kworker/u20:1 Tainted: G W OE 5.13.0_mlnx #1
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 Workqueue: mlx5e mlx5e_tx_timeout_work [mlx5_core]
 RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
 [mlx5_core]
 Call Trace:
 mlx5e_tx_reporter_dump+0x43/0x1c0 [mlx5_core]
 devlink_health_do_dump.part.91+0x71/0xd0
 devlink_health_report+0x157/0x1b0
 mlx5e_reporter_tx_timeout+0xb9/0xf0 [mlx5_core]
 ? mlx5e_tx_reporter_err_cqe_recover+0x1d0/0x1d0
 [mlx5_core]
 ? mlx5e_health_queue_dump+0xd0/0xd0 [mlx5_core]
 ? update_load_avg+0x19b/0x550
 ? set_next_entity+0x72/0x80
 ? pick_next_task_fair+0x227/0x340
 ? finish_task_switch+0xa2/0x280
   mlx5e_tx_timeout_work+0x83/0xb0 [mlx5_core]
   process_one_work+0x1de/0x3a0
   worker_thread+0x2d/0x3c0
 ? process_one_work+0x3a0/0x3a0
   kthread+0x115/0x130
 ? kthread_park+0x90/0x90
   ret_from_fork+0x1f/0x30
 --[ end trace 51ccabea504edaff ]---
 RIP: 0010:mlx5e_tx_reporter_dump_sq+0xd3/0x180
 PKRU: 55555554
 Kernel panic - not syncing: Fatal exception
 Kernel Offset: disabled
 end Kernel panic - not syncing: Fatal exception

To fix this bug add a wrapper for mlx5e_tx_reporter_dump_sq() which
extracts the sq from struct mlx5e_tx_timeout_ctx and set it as the
TX-timeout-recovery flow dump callback.

Fixes: b6c6f90b8988 ("net/mlx5e: Support dump callback in TX reporter")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 4f4bc8726ec4fa2b20a32edb25780ad177f6860a..614cd9477600032ca386f72b1960d894c2fed373 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -466,6 +466,14 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms
        return mlx5e_health_fmsg_named_obj_nest_end(fmsg);
 }
 
+static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg,
+                                         void *ctx)
+{
+       struct mlx5e_tx_timeout_ctx *to_ctx = ctx;
+
+       return mlx5e_tx_reporter_dump_sq(priv, fmsg, to_ctx->sq);
+}
+
 static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv,
                                          struct devlink_fmsg *fmsg)
 {
@@ -561,7 +569,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq)
        to_ctx.sq = sq;
        err_ctx.ctx = &to_ctx;
        err_ctx.recover = mlx5e_tx_reporter_timeout_recover;
-       err_ctx.dump = mlx5e_tx_reporter_dump_sq;
+       err_ctx.dump = mlx5e_tx_reporter_timeout_dump;
        snprintf(err_str, sizeof(err_str),
                 "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u",
                 sq->ch_ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,