[PATCH 2/2] Revert "drm/amdgpu: change aca bank error lock type to spinlock"

Yang Wang kevinyang.wang at amd.com
Tue Jun 18 07:48:35 UTC 2024


This reverts commit 354436e7905d166011f2aa26dccd9fa04b20940e.

Revert this patch to modify lock type back to 'mutex' to avoid kernel
calltrace issue.

[  602.668806] Workqueue: amdgpu-reset-dev amdgpu_ras_do_recovery [amdgpu]
[  602.668939] Call Trace:
[  602.668940]  <TASK>
[  602.668941]  dump_stack_lvl+0x4c/0x70
[  602.668945]  dump_stack+0x14/0x20
[  602.668946]  __schedule_bug+0x5a/0x70
[  602.668950]  __schedule+0x940/0xb30
[  602.668952]  ? srso_alias_return_thunk+0x5/0xfbef5
[  602.668955]  ? hrtimer_reprogram+0x77/0xb0
[  602.668957]  ? srso_alias_return_thunk+0x5/0xfbef5
[  602.668959]  ? hrtimer_start_range_ns+0x126/0x370
[  602.668961]  schedule+0x39/0xe0
[  602.668962]  schedule_hrtimeout_range_clock+0xb1/0x140
[  602.668964]  ? __pfx_hrtimer_wakeup+0x10/0x10
[  602.668966]  schedule_hrtimeout_range+0x17/0x20
[  602.668967]  usleep_range_state+0x69/0x90
[  602.668970]  psp_cmd_submit_buf+0x132/0x570 [amdgpu]
[  602.669066]  psp_ras_invoke+0x75/0x1a0 [amdgpu]
[  602.669156]  psp_ras_query_address+0x9c/0x120 [amdgpu]
[  602.669245]  umc_v12_0_update_ecc_status+0x16d/0x520 [amdgpu]
[  602.669337]  ? srso_alias_return_thunk+0x5/0xfbef5
[  602.669339]  ? stack_depot_save+0x12/0x20
[  602.669342]  ? srso_alias_return_thunk+0x5/0xfbef5
[  602.669343]  ? set_track_prepare+0x52/0x70
[  602.669346]  ? kmemleak_alloc+0x4f/0x90
[  602.669348]  ? __kmalloc_node+0x34b/0x450
[  602.669352]  amdgpu_umc_update_ecc_status+0x23/0x40 [amdgpu]
[  602.669438]  mca_umc_mca_get_err_count+0x85/0xc0 [amdgpu]
[  602.669554]  mca_smu_parse_mca_error_count+0x120/0x1d0 [amdgpu]
[  602.669655]  amdgpu_mca_dispatch_mca_set.part.0+0x141/0x250 [amdgpu]
[  602.669743]  ? kmemleak_free+0x36/0x60
[  602.669745]  ? kvfree+0x32/0x40
[  602.669747]  ? srso_alias_return_thunk+0x5/0xfbef5
[  602.669749]  ? kfree+0x15d/0x2a0
[  602.669752]  amdgpu_mca_smu_log_ras_error+0x1f6/0x210 [amdgpu]
[  602.669839]  amdgpu_ras_query_error_status_helper+0x2ad/0x390 [amdgpu]
[  602.669924]  ? srso_alias_return_thunk+0x5/0xfbef5
[  602.669925]  ? __call_rcu_common.constprop.0+0xa6/0x2b0
[  602.669929]  amdgpu_ras_query_error_status+0xf3/0x620 [amdgpu]
[  602.670014]  ? srso_alias_return_thunk+0x5/0xfbef5
[  602.670017]  amdgpu_ras_log_on_err_counter+0xe1/0x170 [amdgpu]
[  602.670103]  amdgpu_ras_do_recovery+0xd2/0x2c0 [amdgpu]
[  602.670187]  ? srso_alias_return_thunk+0x5/0

Signed-off-by: Yang Wang <kevinyang.wang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c | 19 ++++++++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h |  3 +--
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index 04515c1c7241..7945173321a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -222,9 +222,9 @@ static struct aca_bank_error *new_bank_error(struct aca_error *aerr, struct aca_
 	INIT_LIST_HEAD(&bank_error->node);
 	memcpy(&bank_error->info, info, sizeof(*info));
 
-	spin_lock(&aerr->lock);
+	mutex_lock(&aerr->lock);
 	list_add_tail(&bank_error->node, &aerr->list);
-	spin_unlock(&aerr->lock);
+	mutex_unlock(&aerr->lock);
 
 	return bank_error;
 }
@@ -235,7 +235,7 @@ static struct aca_bank_error *find_bank_error(struct aca_error *aerr, struct aca
 	struct aca_bank_info *tmp_info;
 	bool found = false;
 
-	spin_lock(&aerr->lock);
+	mutex_lock(&aerr->lock);
 	list_for_each_entry(bank_error, &aerr->list, node) {
 		tmp_info = &bank_error->info;
 		if (tmp_info->socket_id == info->socket_id &&
@@ -246,7 +246,7 @@ static struct aca_bank_error *find_bank_error(struct aca_error *aerr, struct aca
 	}
 
 out_unlock:
-	spin_unlock(&aerr->lock);
+	mutex_unlock(&aerr->lock);
 
 	return found ? bank_error : NULL;
 }
@@ -474,7 +474,7 @@ static int aca_log_aca_error(struct aca_handle *handle, enum aca_error_type type
 	struct aca_error *aerr = &error_cache->errors[type];
 	struct aca_bank_error *bank_error, *tmp;
 
-	spin_lock(&aerr->lock);
+	mutex_lock(&aerr->lock);
 
 	if (list_empty(&aerr->list))
 		goto out_unlock;
@@ -485,7 +485,7 @@ static int aca_log_aca_error(struct aca_handle *handle, enum aca_error_type type
 	}
 
 out_unlock:
-	spin_unlock(&aerr->lock);
+	mutex_unlock(&aerr->lock);
 
 	return 0;
 }
@@ -542,7 +542,7 @@ int amdgpu_aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *han
 
 static void aca_error_init(struct aca_error *aerr, enum aca_error_type type)
 {
-	spin_lock_init(&aerr->lock);
+	mutex_init(&aerr->lock);
 	INIT_LIST_HEAD(&aerr->list);
 	aerr->type = type;
 	aerr->nr_errors = 0;
@@ -561,10 +561,11 @@ static void aca_error_fini(struct aca_error *aerr)
 {
 	struct aca_bank_error *bank_error, *tmp;
 
-	spin_lock(&aerr->lock);
+	mutex_lock(&aerr->lock);
 	list_for_each_entry_safe(bank_error, tmp, &aerr->list, node)
 		aca_bank_error_remove(aerr, bank_error);
-	spin_unlock(&aerr->lock);
+
+	mutex_destroy(&aerr->lock);
 }
 
 static void aca_fini_error_cache(struct aca_handle *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h
index ba724c2a997d..5ef6b745f222 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.h
@@ -25,7 +25,6 @@
 #define __AMDGPU_ACA_H__
 
 #include <linux/list.h>
-#include <linux/spinlock.h>
 
 struct ras_err_data;
 struct ras_query_context;
@@ -134,7 +133,7 @@ struct aca_bank_error {
 
 struct aca_error {
 	struct list_head list;
-	spinlock_t lock;
+	struct mutex lock;
 	enum aca_error_type type;
 	int nr_errors;
 };
-- 
2.34.1



More information about the amd-gfx mailing list