drm/amdgpu: Fix the dead lock issue.
Subsystems (2)
PATCH 1/1 drm/amdgpu: Fix the dead lock issue.
It will ramdomly have the dead lock issue when test TDR:
1. amdgpu_device_handle_vram_lost gets the lock shadow_list_lock
2. amdgpu_bo_create locked the bo's resv lock
3. amdgpu_bo_create_shadow is waiting for the shadow_list_lock
4. amdgpu_device_recover_vram_from_shadow is waiting for the bo's resv lock.
v2:
Make a local copy of the list
--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +20 -1
@@ -3105,6 +3105,9 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)long r =1 ;int i =0 ;long tmo; +struct list_head local_shadow_list; + +INIT_LIST_HEAD (&local_shadow_list);if (amdgpu_sriov_runtime (adev)) tmo =msecs_to_jiffies (8000 );
@@ -3112,8 +3115,19 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) tmo =msecs_to_jiffies (100 );DRM_INFO ("recover vram bo from shadow start\n" ); + +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&adev->shadow_list, &local_shadow_list); +mutex_unlock (&adev->shadow_list_lock); + +mutex_lock (&adev->shadow_list_lock); -list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { +list_for_each_entry_safe (bo, tmp, &local_shadow_list, shadow_list) { +mutex_unlock (&adev->shadow_list_lock); + +if (!bo) +continue ; + next =NULL ;amdgpu_device_recover_vram_from_shadow (adev, ring, bo, &next);if (fence) {
@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)dma_fence_put (fence); fence = next; +mutex_lock (&adev->shadow_list_lock); }mutex_unlock (&adev->shadow_list_lock); +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&local_shadow_list, &adev->shadow_list); +mutex_unlock (&adev->shadow_list_lock); +if (fence) { r =dma_fence_wait_timeout (fence, false, tmo);if (r ==0 )
Signature · 6 lines
2.7.4 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 1536634293-26099-1-git-send-email-Emily.Deng-5C7GfCeVMHo@public.gmane.org
Quoted 33 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock
2.amdgpu_bo_createlocked the bo's resv lock
3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock
4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0@@ -3105,6 +3105,9 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)long r =1 ;int i =0 ;long tmo; +struct list_head local_shadow_list; + +INIT_LIST_HEAD (&local_shadow_list);if (amdgpu_sriov_runtime (adev)) tmo =msecs_to_jiffies (8000 );@@ -3112,8 +3115,19 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) tmo =msecs_to_jiffies (100 );DRM_INFO ("recover vram bo from shadow start\n" );
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) · line 3126
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +8
-1+ +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&adev->shadow_list, &local_shadow_list); +mutex_unlock (&adev->shadow_list_lock); + +mutex_lock (&adev->shadow_list_lock); -list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { +list_for_each_entry_safe (bo, tmp, &local_shadow_list, shadow_list) { +mutex_unlock (&adev->shadow_list_lock);
We may not to use shadow_list_lock when traverse the local shadow list.
Regards,
Jerry
Quoted 13 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5
-0+ +if (!bo) +continue ; + next =NULL ;amdgpu_device_recover_vram_from_shadow (adev, ring, bo, &next);if (fence) {@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)dma_fence_put (fence); fence = next; +mutex_lock (&adev->shadow_list_lock);
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) · line 3159
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0}mutex_unlock (&adev->shadow_list_lock); +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&local_shadow_list, &adev->shadow_list); +mutex_unlock (&adev->shadow_list_lock); +if (fence) { r =dma_fence_wait_timeout (fence, false, tmo);if (r ==0 )
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Quoted 30 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock
2.amdgpu_bo_createlocked the bo's resv lock
3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock
4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0@@ -3105,6 +3105,9 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)long r =1 ;int i =0 ;long tmo; +struct list_head local_shadow_list; + +INIT_LIST_HEAD (&local_shadow_list);if (amdgpu_sriov_runtime (adev)) tmo =msecs_to_jiffies (8000 );
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) · line 3124
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-0@@ -3112,8 +3115,19 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) tmo =msecs_to_jiffies (100 );DRM_INFO ("recover vram bo from shadow start\n" ); + +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&adev->shadow_list, &local_shadow_list); +mutex_unlock (&adev->shadow_list_lock); + +mutex_lock (&adev->shadow_list_lock);
local_shadow_list is a local variable, I think it doesn't need lock at all, no one change it. Otherwise looks good to me.
Thanks,
David Zhou
Quoted 15 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +7
-1-list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { +list_for_each_entry_safe (bo, tmp, &local_shadow_list, shadow_list) { +mutex_unlock (&adev->shadow_list_lock); + +if (!bo) +continue ; + next =NULL ;amdgpu_device_recover_vram_from_shadow (adev, ring, bo, &next);if (fence) {@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)dma_fence_put (fence); fence = next; +mutex_lock (&adev->shadow_list_lock);
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) · line 3159
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0}mutex_unlock (&adev->shadow_list_lock); +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&local_shadow_list, &adev->shadow_list); +mutex_unlock (&adev->shadow_list_lock); +if (fence) { r =dma_fence_wait_timeout (fence, false, tmo);if (r ==0 )
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): bf049e4b-321f-33b4-dad2-708269515e90-5C7GfCeVMHo@public.gmane.org
Quoted 45 lines
-----Original Message-----
From: Zhou, David(ChunMing)
Sent: Tuesday, September 11, 2018 11:03 AM
To: Deng, Emily <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 7 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock2.amdgpu_bo_createlocked the bo's resv lock 3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.Quoted 6 lines
v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21++++++++++++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 8 lines
1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -3105,6 +3105,9 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0long r =1 ;int i =0 ;long tmo; +struct list_head local_shadow_list; + +INIT_LIST_HEAD (&local_shadow_list);if (amdgpu_sriov_runtime (adev)) tmo =msecs_to_jiffies (8000 );@@ -3112,8 +3115,19 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0tmo =msecs_to_jiffies (100 );
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) · line 3124
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-0DRM_INFO ("recover vram bo from shadow start\n" ); + +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&adev->shadow_list, &local_shadow_list); +mutex_unlock (&adev->shadow_list_lock); + +mutex_lock (&adev->shadow_list_lock);
local_shadow_listis a local variable, I think it doesn't need lock at all, no one change it. Otherwise looks good to me.
The bo->shadow_list which now is in local_shadow_list maybe destroy in case that it already in amdgpu_bo_destroy, then it will change local_shadow_list, so need lock the shadow_list_lock.
Best wishes
Emily Deng
Quoted 22 lines
Thanks,
David Zhoudrivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-1-list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { +list_for_each_entry_safe (bo, tmp, &local_shadow_list, shadow_list) { +mutex_unlock (&adev->shadow_list_lock); + +if (!bo) +continue ; + next =NULL ; amdgpu_device_recover_vram_from_shadow(adev, ring, bo,&next);
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0if (fence) {@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)dma_fence_put (fence); fence = next; +mutex_lock (&adev->shadow_list_lock); }mutex_unlock (&adev->shadow_list_lock);
Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0+mutex_lock (&adev->shadow_list_lock); +list_splice_init (&local_shadow_list, &adev->shadow_list); +mutex_unlock (&adev->shadow_list_lock); +if (fence) { r =dma_fence_wait_timeout (fence, false, tmo);if (r == 0)
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BN7PR12MB2644CEE78E8E6D658D1A686E8F040-Zx/IyJUqfGKoYeSiBV3SvgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org
Quoted 55 lines · Emily
Quoted 45 lines
-----Original Message-----
From: Zhou, David(ChunMing)
Sent: Tuesday, September 11, 2018 11:03 AM
To: Deng, Emily <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 7 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock2.amdgpu_bo_createlocked the bo's resv lock 3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.Quoted 6 lines
v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21++++++++++++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 8 lines
1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -3105,6 +3105,9 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0long r =1 ;int i =0 ;long tmo; +struct list_head local_shadow_list; + +INIT_LIST_HEAD (&local_shadow_list);if (amdgpu_sriov_runtime (adev)) tmo =msecs_to_jiffies (8000 );@@ -3112,8 +3115,19 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0tmo =msecs_to_jiffies (100 );Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) · line 3124
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-0DRM_INFO ("recover vram bo from shadow start\n" ); + +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&adev->shadow_list, &local_shadow_list); +mutex_unlock (&adev->shadow_list_lock); + +mutex_lock (&adev->shadow_list_lock);
local_shadow_listis a local variable, I think it doesn't need lock at all, no one change it. Otherwise looks good to me.
Quoted 2 lines
The
bo->shadow_listwhich now is inlocal_shadow_listmaybe destroy in case that it already inamdgpu_bo_destroy, then it will changelocal_shadow_list, so need lock theshadow_list_lock.
Ah, sorry for noise, I forget you don't reference these BOs.
Thanks,
David Zhou
Quoted 24 lines
Best wishes
Emily DengQuoted 22 lines
Thanks,
David Zhoudrivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-1-list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { +list_for_each_entry_safe (bo, tmp, &local_shadow_list, shadow_list) { +mutex_unlock (&adev->shadow_list_lock); + +if (!bo) +continue ; + next =NULL ; amdgpu_device_recover_vram_from_shadow(adev, ring, bo,&next);
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0if (fence) {@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)dma_fence_put (fence); fence = next; +mutex_lock (&adev->shadow_list_lock); }mutex_unlock (&adev->shadow_list_lock);
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0+mutex_lock (&adev->shadow_list_lock); +list_splice_init (&local_shadow_list, &adev->shadow_list); +mutex_unlock (&adev->shadow_list_lock); +if (fence) { r =dma_fence_wait_timeout (fence, false, tmo);if (r == 0)
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): fcbc7544-d08d-4051-c554-f1f9cecb87e1-5C7GfCeVMHo@public.gmane.org
Quoted 66 lines
-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of zhoucm1
Sent: Tuesday, September 11, 2018 11:28 AM
To: Deng, Emily <[email protected]>; Zhou, David(ChunMing) <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 55 lines · Emily
Quoted 55 lines
-----Original Message-----
From: Zhou, David(ChunMing)
Sent: Tuesday, September 11, 2018 11:03 AM
To: Deng, Emily <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 7 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock2.amdgpu_bo_createlocked the bo's resv lock 3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.Quoted 6 lines
v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21++++++++++++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 8 lines
1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -3105,6 +3105,9 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0long r =1 ;int i =0 ;long tmo; +struct list_head local_shadow_list; + +INIT_LIST_HEAD (&local_shadow_list);if (amdgpu_sriov_runtime (adev)) tmo =msecs_to_jiffies (8000 );@@ -3112,8 +3115,19 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int · line 3124
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-0tmo =msecs_to_jiffies (100 );DRM_INFO ("recover vram bo from shadow start\n" ); + +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&adev->shadow_list, &local_shadow_list); +mutex_unlock (&adev->shadow_list_lock); + +mutex_lock (&adev->shadow_list_lock);
local_shadow_listis a local variable, I think it doesn't need lock at all, no one change it. Otherwise looks good to me.
Quoted 4 lines
Quoted 2 lines
The
bo->shadow_listwhich now is inlocal_shadow_listmaybe destroy in case that it already inamdgpu_bo_destroy, then it will change
local_shadow_list, so need lock theshadow_list_lock. Ah, sorry for noise, I forget you don't reference these BOs.
Yes, I don't reference these Bos, as I found even reference these Bos, it still couldn't avoid the case that another process is already in amdgpu_bo_destroy.
Quoted 27 lines
Thanks,
David ZhouQuoted 24 lines
Best wishes
Emily DengQuoted 22 lines
Thanks,
David Zhoudrivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int · line 3132
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-1-list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { +list_for_each_entry_safe (bo, tmp, &local_shadow_list, shadow_list) { +mutex_unlock (&adev->shadow_list_lock); + +if (!bo) +continue ; + next =NULL ; amdgpu_device_recover_vram_from_shadow(adev, ring, bo,&next);
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0if (fence) {@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)dma_fence_put (fence); fence = next; +mutex_lock (&adev->shadow_list_lock); }mutex_unlock (&adev->shadow_list_lock);
Quoted 12 lines
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0+mutex_lock (&adev->shadow_list_lock); +list_splice_init (&local_shadow_list, &adev->shadow_list); +mutex_unlock (&adev->shadow_list_lock); +if (fence) { r =dma_fence_wait_timeout (fence, false, tmo);if (r == 0)_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): BN7PR12MB2644E374B512DC7EF10CA6D08F040-Zx/IyJUqfGKoYeSiBV3SvgdYzm3356FpvxpqHgZTriW3zl9H0oFU5g@public.gmane.org
Quoted 66 lines · Emily
Quoted 66 lines
-----Original Message-----
From: amd-gfx <[email protected]> On Behalf Of zhoucm1
Sent: Tuesday, September 11, 2018 11:28 AM
To: Deng, Emily <[email protected]>; Zhou, David(ChunMing) <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 55 lines · Emily
Quoted 55 lines
-----Original Message-----
From: Zhou, David(ChunMing)
Sent: Tuesday, September 11, 2018 11:03 AM
To: Deng, Emily <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 7 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock2.amdgpu_bo_createlocked the bo's resv lock 3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.Quoted 6 lines
v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21++++++++++++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 8 lines
1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -3105,6 +3105,9 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0long r =1 ;int i =0 ;long tmo; +struct list_head local_shadow_list; + +INIT_LIST_HEAD (&local_shadow_list);if (amdgpu_sriov_runtime (adev)) tmo =msecs_to_jiffies (8000 );@@ -3112,8 +3115,19 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int · line 3124
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-0tmo =msecs_to_jiffies (100 );DRM_INFO ("recover vram bo from shadow start\n" ); + +mutex_lock (&adev->shadow_list_lock); +list_splice_init (&adev->shadow_list, &local_shadow_list); +mutex_unlock (&adev->shadow_list_lock); + +mutex_lock (&adev->shadow_list_lock);
local_shadow_listis a local variable, I think it doesn't need lock at all, no one change it. Otherwise looks good to me.
Quoted 6 lines
Quoted 4 lines
Quoted 2 lines
The
bo->shadow_listwhich now is inlocal_shadow_listmaybe destroy in case that it already inamdgpu_bo_destroy, then it will change
local_shadow_list, so need lock theshadow_list_lock. Ah, sorry for noise, I forget you don't reference these BOs.Yes, I don't reference these Bos, as I found even reference these Bos, it still couldn't avoid the case that another process is already in
amdgpu_bo_destroy.
??? that shouldn't happen, the reference is belonged to list. But back to here, we don't need reference them.
And since no shadow BO is added to local after splice, we'd better to use list_next_entry to iterate the local shadow list instead of list_for_each_entry_safe.
Thanks,
David Zhou
Quoted 26 lines
Quoted 26 lines
Thanks,
David ZhouQuoted 24 lines
Best wishes
Emily DengQuoted 22 lines
Thanks,
David Zhoudrivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int · line 3132
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-1-list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { +list_for_each_entry_safe (bo, tmp, &local_shadow_list, shadow_list) { +mutex_unlock (&adev->shadow_list_lock); + +if (!bo) +continue ; + next =NULL ; amdgpu_device_recover_vram_from_shadow(adev, ring, bo,&next);
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0if (fence) {@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)dma_fence_put (fence); fence = next; +mutex_lock (&adev->shadow_list_lock); }mutex_unlock (&adev->shadow_list_lock);
Quoted 11 lines
Quoted 11 lines
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0+mutex_lock (&adev->shadow_list_lock); +list_splice_init (&local_shadow_list, &adev->shadow_list); +mutex_unlock (&adev->shadow_list_lock); +if (fence) { r =dma_fence_wait_timeout (fence, false, tmo);if (r == 0)_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): be67e50d-f161-c7da-256e-149ed1b56f26-5C7GfCeVMHo@public.gmane.org
Quoted 73 lines · On 2018年09月11日 11:37, zhoucm1 wrote:
Quoted 70 lines · Emily
Quoted 70 lines
-----Original Message-----
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> On Behalf Of zhoucm1
Sent: Tuesday, September 11, 2018 11:28 AM
To: Deng, Emily <[email protected]>; Zhou, David(ChunMing) <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 55 lines · Emily
Quoted 45 lines
-----Original Message-----
From: Zhou, David(ChunMing)
Sent: Tuesday, September 11, 2018 11:03 AM
To: Deng, Emily <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 7 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock2.amdgpu_bo_createlocked the bo's resv lock 3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.Quoted 6 lines
v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c| 21++++++++++++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 8 lines
1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -3105,6 +3105,9 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0long r = 1; int i = 0; long tmo; + struct list_head local_shadow_list; + + INIT_LIST_HEAD(&local_shadow_list); if (amdgpu_sriov_runtime(adev)) tmo = msecs_to_jiffies(8000);@@ -3112,8 +3115,19 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0tmo = msecs_to_jiffies(100);Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int · line 3124
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-0DRM_INFO("recover vram bo from shadow start\n"); + + mutex_lock(&adev->shadow_list_lock); + list_splice_init(&adev->shadow_list, &local_shadow_list); + mutex_unlock(&adev->shadow_list_lock); + + mutex_lock(&adev->shadow_list_lock);
local_shadow_listis a local variable, I think it doesn't need lock at all, no one change it. Otherwise looks good to me.Quoted 2 lines
The
bo->shadow_listwhich now is inlocal_shadow_listmaybe destroy in case that it already inamdgpu_bo_destroy, then it will change
local_shadow_list, so need lock theshadow_list_lock. Ah, sorry for noise, I forget you don't reference these BOs.
Quoted 17 lines
Quoted 2 lines
Yes, I don't reference these Bos, as I found even reference these Bos, it still couldn't avoid the case that another process is already in
amdgpu_bo_destroy.??? that shouldn't happen, the reference is belonged to list. But back to here, we don't need reference them.
And since no shadow BO is added to local after splice, we'd better to uselist_next_entryto iterate the local shadow list instead oflist_for_each_entry_safe.Thanks,
David ZhouQuoted 10 lines
Quoted 10 lines
Thanks,
David ZhouQuoted 8 lines
Best wishes
Emily DengQuoted 6 lines
Thanks,
David ZhouQuoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-1- list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) { + list_for_each_entry_safe(bo, tmp, &local_shadow_list, shadow_list) {
because shadow list doesn't take bo reference, we should give a amdgpu_bo_ref(bo) with attached patch before unlock. You can have a try.
Thanks,
David Zhou
Quoted 30 lines
Quoted 18 lines
Quoted 18 lines
Quoted 18 lines
Quoted 18 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5
-0+mutex_unlock (&adev->shadow_list_lock); + + if (!bo) + continue; + next = NULL;amdgpu_device_recover_vram_from_shadow(adev, ring, bo,
&next);
Quoted 10 lines
if (fence) {
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) dma_fence_put(fence); fence = next; + mutex_lock(&adev->shadow_list_lock); } mutex_unlock(&adev->shadow_list_lock);Quoted 11 lines
Quoted 11 lines
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0+ mutex_lock(&adev->shadow_list_lock); + list_splice_init(&local_shadow_list, &adev->shadow_list); + mutex_unlock(&adev->shadow_list_lock); + if (fence) { r = dma_fence_wait_timeout(fence, false, tmo);if (r == 0)
_______________________________________________
amd-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Quoted 6 lines
_______________________________________________
amd-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfxFrom
7676fc70738699dddca5627e21be0d82e91aea05Mon Sep 17 00:00:00 2001
From: Chunming Zhou <[email protected]>
Date: Tue, 11 Sep 2018 13:37:31 +0800
Subject: [PATCH] drm/amdgpu: changing of shadow bo reference should take
shadow lock
because shadow list doesn't reference shadow bo.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +10 -4
@@ -101,11 +101,9 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)drm_prime_gem_destroy (&bo->gem_base, bo->tbo.sg);drm_gem_object_release (&bo->gem_base);amdgpu_bo_unref (&bo->parent); -if (!list_empty (&bo->shadow_list)) { -mutex_lock (&adev->shadow_list_lock); +if (!list_empty (&bo->shadow_list))list_del_init (&bo->shadow_list); -mutex_unlock (&adev->shadow_list_lock); - } +kfree (bo->metadata);kfree (bo); }
@@ -838,13 +836,21 @@ struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo)void amdgpu_bo_unref (struct amdgpu_bo **bo) {struct ttm_buffer_object *tbo; +bool locked = false;if ((*bo) ==NULL )return ; +if (bo->parent && bo->parent->shadow == bo && + !list_empty (&bo->parent->shadow_list)) { +mutex_lock (&adev->shadow_list_lock); + locked = true; + } tbo = &((*bo)->tbo);ttm_bo_put (tbo); *bo =NULL ; +if (locked) +mutex_unlock (&adev->shadow_list_lock); }/**
Signature · 1 line
2.17.1
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): 83f7a45f-1aee-a2a8-bc82-f3433157c6cb-5C7GfCeVMHo@public.gmane.org
That won't work correctly. The TTM BO is unreferenced in a couple of more places which we don't have control over.
To make it even worse we actually can't take the reservation lock during GPU reset because the reservation object might already be destroyed when we remove the BO from the list.
I will take a look at this myself today to find a solution which should work.
Regards,
Christian.
Am 11.09.2018 um 07:41 schrieb zhoucm1:
Quoted 135 lines · On 2018年09月11日 11:37, zhoucm1 wrote:
Quoted 73 lines · Emily
Quoted 70 lines
Quoted 70 lines
-----Original Message-----
From: amd-gfx <amd-gfx-bounces-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org> On Behalf Of zhoucm1
Sent: Tuesday, September 11, 2018 11:28 AM
To: Deng, Emily <[email protected]>; Zhou, David(ChunMing) <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 55 lines · Emily
Quoted 45 lines
-----Original Message-----
From: Zhou, David(ChunMing)
Sent: Tuesday, September 11, 2018 11:03 AM
To: Deng, Emily <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.Quoted 7 lines · Emily Deng
It will ramdomly have the dead lock issue when test TDR:
1.amdgpu_device_handle_vram_lostgets the lockshadow_list_lock2.amdgpu_bo_createlocked the bo's resv lock 3.amdgpu_bo_create_shadowis waiting for theshadow_list_lock4.amdgpu_device_recover_vram_from_shadowis waiting for the bo's resv lock.Quoted 6 lines
v2:
Make a local copy of the listSigned-off-by Emily Deng <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c| 21++++++++++++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 8 lines
1 file changed, 20 insertions(+), 1 deletion(-)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0@@ -3105,6 +3105,9 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int
Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +3
-0long r = 1; int i = 0; long tmo; + struct list_head local_shadow_list; + + INIT_LIST_HEAD(&local_shadow_list); if (amdgpu_sriov_runtime(adev)) tmo = msecs_to_jiffies(8000);@@ -3112,8 +3115,19 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0
-0tmo = msecs_to_jiffies(100);Quoted 10 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c static int · line 3124
Quoted 8 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +6
-0DRM_INFO("recover vram bo from shadow start\n"); + + mutex_lock(&adev->shadow_list_lock); + list_splice_init(&adev->shadow_list, &local_shadow_list); + mutex_unlock(&adev->shadow_list_lock); + + mutex_lock(&adev->shadow_list_lock);
local_shadow_listis a local variable, I think it doesn't need lock at all, no one change it. Otherwise looks good to me.Quoted 2 lines
The
bo->shadow_listwhich now is inlocal_shadow_listmaybe destroy in case that it already inamdgpu_bo_destroy, then it will change
local_shadow_list, so need lock theshadow_list_lock. Ah, sorry for noise, I forget you don't reference these BOs.Quoted 17 lines
Quoted 2 lines
Yes, I don't reference these Bos, as I found even reference these Bos, it still couldn't avoid the case that another process is already in
amdgpu_bo_destroy.??? that shouldn't happen, the reference is belonged to list. But back to here, we don't need reference them.
And since no shadow BO is added to local after splice, we'd better to uselist_next_entryto iterate the local shadow list instead oflist_for_each_entry_safe.Thanks,
David ZhouQuoted 10 lines
Quoted 10 lines
Thanks,
David ZhouQuoted 8 lines
Best wishes
Emily DengQuoted 6 lines
Thanks,
David ZhouQuoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-1-list_for_each_entry_safe (bo, tmp, &adev->shadow_list, shadow_list) { + list_for_each_entry_safe(bo, tmp, &local_shadow_list, shadow_list) {because shadow list doesn't take bo reference, we should give a
amdgpu_bo_ref(bo)with attached patch before unlock. You can have a try.Thanks,
David ZhouQuoted 30 lines
Quoted 18 lines
Quoted 18 lines
Quoted 18 lines
Quoted 18 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +5
-0+mutex_unlock (&adev->shadow_list_lock); + + if (!bo) + continue; + next = NULL;amdgpu_device_recover_vram_from_shadow(adev, ring, bo,
&next);
Quoted 10 lines
if (fence) {
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +1
-0@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev) dma_fence_put(fence); fence = next; + mutex_lock(&adev->shadow_list_lock); } mutex_unlock(&adev->shadow_list_lock);Quoted 11 lines
Quoted 11 lines
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +4
-0+ mutex_lock(&adev->shadow_list_lock); + list_splice_init(&local_shadow_list, &adev->shadow_list); + mutex_unlock(&adev->shadow_list_lock); + if (fence) { r = dma_fence_wait_timeout(fence, false, tmo);if (r == 0)
_______________________________________________
amd-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfxQuoted 4 lines
_______________________________________________
amd-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Quoted 4 lines
_______________________________________________
amd-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
A message that is not in the archive (sent off-list or not yet received): c67be83d-aecd-a291-a564-15f1fe501680-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org
From: Christian König <[email protected]>
Sent: Tuesday, September 11, 2018 2:40 PM
To: Zhou, David(ChunMing) <[email protected]>; Deng, Emily <[email protected]>; Zhou, David(ChunMing) <[email protected]>; [email protected]
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.
That won't work correctly. The TTM BO is unreferenced in a couple of more places which we don't have control over.
To make it even worse we actually can't take the reservation lock during GPU reset because the reservation object might already be destroyed when we remove the BO from the list.
I will take a look at this myself today to find a solution which should work. Ok, thanks very much.
Best wishes
Emily Deng
Regards,
Christian.
Am 11.09.2018 um 07:41 schrieb zhoucm1:
On 2018年09月11日 11:37, zhoucm1 wrote:
On 2018年09月11日 11:32, Deng, Emily wrote:
-----Original Message-----
From: amd-gfx <[email protected]><mailto:[email protected]> On Behalf Of zhoucm1
Sent: Tuesday, September 11, 2018 11:28 AM
To: Deng, Emily <[email protected]><mailto:[email protected]>; Zhou, David(ChunMing) <[email protected]><mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.
On 2018年09月11日 11:23, Deng, Emily wrote:
-----Original Message-----
From: Zhou, David(ChunMing)
Sent: Tuesday, September 11, 2018 11:03 AM
To: Deng, Emily <[email protected]><mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Fix the dead lock issue.
On 2018年09月11日 10:51, Emily Deng wrote:
It will ramdomly have the dead lock issue when test TDR:
1. amdgpu_device_handle_vram_lost gets the lock shadow_list_lock 2. amdgpu_bo_create locked the bo's resv lock 3. amdgpu_bo_create_shadow is waiting for the shadow_list_lock 4. amdgpu_device_recover_vram_from_shadow is waiting for the bo's resv lock.
v2:
Make a local copy of the list
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 21++++++++++++++++++++-
1 file changed, 20 insertions(+), 1 deletion(-)
(quoted diff) +0 -0
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2a21267..8c81404 100644
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +0 -0
@@ -3105,6 +3105,9 @@ static int
amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
long r = 1;
int i = 0;
long tmo;+ struct list_head local_shadow_list;
+
+ INIT_LIST_HEAD(&local_shadow_list);
if (amdgpu_sriov_runtime(adev))
tmo = msecs_to_jiffies(8000);@@ -3112,8 +3115,19 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
tmo = msecs_to_jiffies(100);
DRM_INFO("recover vram bo from shadow start\n");
+
+ mutex_lock(&adev->shadow_list_lock);
+ list_splice_init(&adev->shadow_list, &local_shadow_list);
+ mutex_unlock(&adev->shadow_list_lock);
+
+
mutex_lock(&adev->shadow_list_lock);local_shadow_list is a local variable, I think it doesn't need lock
at all, no one change it. Otherwise looks good to me.
The bo->shadow_list which now is in local_shadow_list maybe destroy in
case that it already in amdgpu_bo_destroy, then it will changelocal_shadow_list, so need lock the shadow_list_lock.
Ah, sorry for noise, I forget you don't reference these BOs.
Yes, I don't reference these Bos, as I found even reference these Bos, it still couldn't avoid the case that another process is already in amdgpu_bo_destroy.
??? that shouldn't happen, the reference is belonged to list. But back to here, we don't need reference them.
And since no shadow BO is added to local after splice, we'd better to use list_next_entry to iterate the local shadow list instead of list_for_each_entry_safe.
Thanks,
David Zhou
Thanks,
David Zhou
Best wishes
Emily Deng
Thanks,
David Zhou
- list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) {
+ list_for_each_entry_safe(bo, tmp, &local_shadow_list, shadow_list) {
because shadow list doesn't take bo reference, we should give a amdgpu_bo_ref(bo) with attached patch before unlock. You can have a try.
Thanks,
David Zhou
+ mutex_unlock(&adev->shadow_list_lock);
+
+ if (!bo)
+ continue;
+
next = NULL; amdgpu_device_recover_vram_from_shadow(adev, ring, bo,
&next);
if (fence) {@@ -3132,9 +3146,14 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
dma_fence_put(fence);
fence = next;
+ mutex_lock(&adev->shadow_list_lock);
}
mutex_unlock(&adev->shadow_list_lock);+ mutex_lock(&adev->shadow_list_lock);
+ list_splice_init(&local_shadow_list, &adev->shadow_list);
+ mutex_unlock(&adev->shadow_list_lock);
+
if (fence) {
r = dma_fence_wait_timeout(fence, false, tmo);
if (r == 0)_______________________________________________
amd-gfx mailing list [email protected]<mailto:[email protected]>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list [email protected]<mailto:[email protected]>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]<mailto:[email protected]>
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx