[PATCH AUTOSEL 6.14 222/642] drm/amdgpu: Fix missing drain retry fault the last entry

Sasha Levin sashal at kernel.org
Mon May 5 22:07:18 UTC 2025


From: Emily Deng <Emily.Deng at amd.com>

[ Upstream commit fe2fa3be3d59ba67d6de54a0064441ec233cb50c ]

While the entry get in svm_range_unmap_from_cpu is the last entry, and
the entry is page fault, it also need to be dropped. So for equal case,
it also need to be dropped.

v2:
Only modify the svm_range_restore_pages.

Signed-off-by: Emily Deng <Emily.Deng at amd.com>
Reviewed-by: Xiaogang Chen<xiaogang.chen at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Sasha Levin <sashal at kernel.org>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h | 3 +++
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c   | 2 +-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
index 7d4395a5d8ac9..b0a88f92cd821 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.h
@@ -78,6 +78,9 @@ struct amdgpu_ih_ring {
 #define amdgpu_ih_ts_after(t1, t2) \
 		(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) > 0LL)
 
+#define amdgpu_ih_ts_after_or_equal(t1, t2) \
+		(((int64_t)((t2) << 16) - (int64_t)((t1) << 16)) >= 0LL)
+
 /* provided by the ih block */
 struct amdgpu_ih_funcs {
 	/* ring read/write ptr handling, called from interrupt context */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index d1cf9dd352904..47189453b20c3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -3024,7 +3024,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid,
 
 	/* check if this page fault time stamp is before svms->checkpoint_ts */
 	if (svms->checkpoint_ts[gpuidx] != 0) {
-		if (amdgpu_ih_ts_after(ts,  svms->checkpoint_ts[gpuidx])) {
+		if (amdgpu_ih_ts_after_or_equal(ts,  svms->checkpoint_ts[gpuidx])) {
 			pr_debug("draining retry fault, drop fault 0x%llx\n", addr);
 			r = -EAGAIN;
 			goto out_unlock_svms;
-- 
2.39.5



More information about the amd-gfx mailing list