[PATCH 6.19 138/844] drm/amdkfd: Handle GPU reset and drain retry fault race

[Sasha Levin]

From: Philip Yang <Philip.Yang@xxxxxxx>

[ Upstream commit 5b57c3c3f22336e8fd5edb7f0fef3c7823f8eac1 ]

Only check and drain IH1 ring if CAM is not enabled.

If GPU is under reset, don't access IH to drain retry fault.

Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 79ea138897fcf..a10cf8650c92b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -33,6 +33,7 @@
 #include "amdgpu_hmm.h"
 #include "amdgpu.h"
 #include "amdgpu_xgmi.h"
+#include "amdgpu_reset.h"
 #include "kfd_priv.h"
 #include "kfd_svm.h"
 #include "kfd_migrate.h"
@@ -2349,6 +2350,9 @@ static void svm_range_drain_retry_fault(struct svm_range_list *svms)
 
 		pr_debug("drain retry fault gpu %d svms %p\n", i, svms);
 
+		if (!down_read_trylock(&pdd->dev->adev->reset_domain->sem))
+			continue;
+
 		amdgpu_ih_wait_on_checkpoint_process_ts(pdd->dev->adev,
 				pdd->dev->adev->irq.retry_cam_enabled ?
 				&pdd->dev->adev->irq.ih :
@@ -2358,6 +2362,7 @@ static void svm_range_drain_retry_fault(struct svm_range_list *svms)
 			amdgpu_ih_wait_on_checkpoint_process_ts(pdd->dev->adev,
 				&pdd->dev->adev->irq.ih_soft);
 
+		up_read(&pdd->dev->adev->reset_domain->sem);
 
 		pr_debug("drain retry fault gpu %d svms 0x%p done\n", i, svms);
 	}
@@ -2541,7 +2546,7 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,
 		adev = pdd->dev->adev;
 
 		/* Check and drain ih1 ring if cam not available */
-		if (adev->irq.ih1.ring_size) {
+		if (!adev->irq.retry_cam_enabled && adev->irq.ih1.ring_size) {
 			ih = &adev->irq.ih1;
 			checkpoint_wptr = amdgpu_ih_get_wptr(adev, ih);
 			if (ih->rptr != checkpoint_wptr) {
-- 
2.51.0