[PATCH net] net/mlx5: fw_tracer, return NULL on create error

[PATCH net] net/mlx5: fw_tracer, return NULL on create error

[Tariq Toukan]

From: Michael Guralnik <michaelgur@nvidia.com>

Tracer creation can fail by returning either NULL or ERR_PTR.
The return value is stored without a check on the device, and users
treat ERR_PTR and NULL the same way.
This also causes a crash in the core dump logic, which is missing the
ERR_PTR check and ends up dereferencing it, as shown in the trace below.

Switch tracer creation to return NULL on failure only, so callers only
need a single NULL check.

  Internal error: Oops: 0000000096000006 [#1]  SMP
  Modules linked in: mlx5_ib ib_uverbs ib_core ipv6 mlx5_core
  CPU: 1 UID: 0 PID: 12 Comm: kworker/u16:0 Not tainted 6.19.7 #1 PREEMPT(none)
  Workqueue: mlx5_health0001:01:00.0 mlx5_fw_reporter_err_work [mlx5_core]
  pstate: a3400009 (NzCv daif +PAN -UAO +TCO +DIT -SSBS BTYPE=--)
  pc : mlx5_fw_tracer_trigger_core_dump_general+0x58/0xe0 [mlx5_core]
  lr : mlx5_fw_tracer_trigger_core_dump_general+0x40/0xe0 [mlx5_core]
  sp : ffff800081cf3c40
  x29: ffff800081cf3c90 x28: 0000000000000000 x27: 0000000000000000
  x26: ffff000080018828 x25: 0000000000000000 x24: ffff000080304a05
  x23: ffff800081cf3d80 x22: ffff0000847e01a0 x21: 0000000000000000
  x20: ffff0000847e01a0 x19: ffffffffffffffa1 x18: ffff80008310bbf0
  x17: ffff800080119650 x16: ffff80008010df54 x15: ffff80008010d4ac
  x14: ffff800079c202e4 x13: ffff80008002fe60 x12: ffff800080119650
  x11: ffff80008010df54 x10: ffff80008010d4ac x9 : ffff800079c203d8
  x8 : ffff800081cf3c88 x7 : 0000000000000000 x6 : 0000000000000000
  x5 : 0000000000000000 x4 : 0000000000000008 x3 : 0000000000000030
  x2 : 0000000000000008 x1 : 0000000000000000 x0 : 00000000c5c4000e
  Call trace:
   mlx5_fw_tracer_trigger_core_dump_general+0x58/0xe0 [mlx5_core] (P)
   mlx5_fw_reporter_dump+0x30/0x2e0 [mlx5_core]
   devlink_health_do_dump+0x9c/0x160
   devlink_health_report+0x1c0/0x288
   mlx5_fw_reporter_err_work+0xac/0xc0 [mlx5_core]
   process_one_work+0x15c/0x3d8
   worker_thread+0x18c/0x320
   kthread+0x148/0x228
   ret_from_fork+0x10/0x20
  Code: b9400000 5ac00800 7a401800 540003ca (3940a260)
  ---[ end trace 0000000000000000 ]---
  Kernel panic - not syncing: Oops: Fatal exception
  SMP: stopping secondary CPUs
  Kernel Offset: disabled
  CPU features: 0x000000,00078031,75fce5a1,35fffe67
  Memory Limit: none
  ---[ end Kernel panic - not syncing: Oops: Fatal exception ]---

Fixes: fd1483fe1f9f ("net/mlx5: Add support for FW reporter dump")
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index adcc73e2a5b3..1493d8106c1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -1025,13 +1025,11 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 
 	tracer = kvzalloc_obj(*tracer);
 	if (!tracer)
-		return ERR_PTR(-ENOMEM);
+		return NULL;
 
 	tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer");
-	if (!tracer->work_queue) {
-		err = -ENOMEM;
+	if (!tracer->work_queue)
 		goto free_tracer;
-	}
 
 	tracer->dev = dev;
 
@@ -1073,7 +1071,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 	destroy_workqueue(tracer->work_queue);
 free_tracer:
 	kvfree(tracer);
-	return ERR_PTR(err);
+	return NULL;
 }
 
 static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data);
@@ -1084,7 +1082,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 	struct mlx5_core_dev *dev;
 	int err;
 
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return 0;
 
 	if (!tracer->str_db.loaded)
@@ -1134,7 +1132,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 /* Stop tracer + Cleanup HW resources */
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 {
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return;
 
 	mutex_lock(&tracer->state_lock);
@@ -1163,7 +1161,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 /* Free software resources (Buffers, etc ..) */
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 {
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return;
 
 	mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n");
@@ -1215,7 +1213,7 @@ int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer)
 	struct mlx5_core_dev *dev;
 	int err;
 
-	if (IS_ERR_OR_NULL(tracer))
+	if (!tracer)
 		return 0;
 
 	dev = tracer->dev;

base-commit: 3bd438a58e910db5dc369aa25dfed1fc95f1b596
-- 
2.44.0