[PATCH 1/2] Revert "drm/amdgpu: change bank cache lock type to spinlock"

Yang Wang kevinyang.wang at amd.com
Tue Jun 18 07:48:34 UTC 2024


This reverts commit 379e6cd11499f35d67bbf8f0114b0a054b9f73d7

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+0x5/0xfbef5
[  602.670189]  ? __schedule+0x37d/0xb30
[  602.670191]  process_one_work+0x176/0x350
[  602.670194]  worker_thread+0x2f7/0x420
[  602.670197]  ?

Signed-off-by: Yang Wang <kevinyang.wang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c | 11 ++++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h |  2 +-
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
index c7e602d69f2c..9d3a3c778504 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.c
@@ -232,7 +232,7 @@ int amdgpu_mca_init(struct amdgpu_device *adev)
 
 	for (i = 0; i < ARRAY_SIZE(mca->mca_caches); i++) {
 		mca_cache = &mca->mca_caches[i];
-		spin_lock_init(&mca_cache->lock);
+		mutex_init(&mca_cache->lock);
 		amdgpu_mca_bank_set_init(&mca_cache->mca_set);
 	}
 
@@ -250,6 +250,7 @@ void amdgpu_mca_fini(struct amdgpu_device *adev)
 	for (i = 0; i < ARRAY_SIZE(mca->mca_caches); i++) {
 		mca_cache = &mca->mca_caches[i];
 		amdgpu_mca_bank_set_release(&mca_cache->mca_set);
+		mutex_destroy(&mca_cache->lock);
 	}
 }
 
@@ -454,9 +455,9 @@ static int amdgpu_mca_add_mca_set_to_cache(struct amdgpu_device *adev, enum amdg
 	struct mca_bank_cache *mca_cache = &adev->mca.mca_caches[type];
 	int ret;
 
-	spin_lock(&mca_cache->lock);
+	mutex_lock(&mca_cache->lock);
 	ret = amdgpu_mca_bank_set_merge(&mca_cache->mca_set, new);
-	spin_unlock(&mca_cache->lock);
+	mutex_unlock(&mca_cache->lock);
 
 	return ret;
 }
@@ -486,10 +487,10 @@ int amdgpu_mca_smu_log_ras_error(struct amdgpu_device *adev, enum amdgpu_ras_blo
 	}
 
 	/* dispatch mca set again if mca cache has valid data */
-	spin_lock(&mca_cache->lock);
+	mutex_lock(&mca_cache->lock);
 	if (mca_cache->mca_set.nr_entries)
 		ret = amdgpu_mca_dispatch_mca_set(adev, blk, type, &mca_cache->mca_set, err_data);
-	spin_unlock(&mca_cache->lock);
+	mutex_unlock(&mca_cache->lock);
 
 out_mca_release:
 	amdgpu_mca_bank_set_release(&mca_set);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index c3c184c88dad..e80323ff90c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -84,7 +84,7 @@ struct mca_bank_set {
 
 struct mca_bank_cache {
 	struct mca_bank_set mca_set;
-	spinlock_t lock;
+	struct mutex lock;
 };
 
 struct amdgpu_mca {
-- 
2.34.1



More information about the amd-gfx mailing list