From: Emily Deng <emily.d...@amd.com>
[ Upstream commit f844732e3ad9c4b78df7436232949b8d2096d1a6 ]
Issue:
In the scenario where svm_range_restore_pages is called, but
svm->checkpoint_ts has not been set and the retry fault has not been
drained, svm_range_unmap_from_cpu is triggered and calls svm_range_free.
Meanwhile, svm_range_restore_pages continues execution and reaches
svm_range_from_addr. This results in a "failed to find prange..." error,
causing the page recovery to fail.
How to fix:
Move the timestamp check code under the protection of svm->lock.
v2:
Make sure all right locks are released before go out.
v3:
Directly goto out_unlock_svms, and return -EAGAIN.
v4:
Refine code.
Signed-off-by: Emily Deng <emily.d...@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehl...@amd.com>
Signed-off-by: Alex Deucher <alexander.deuc...@amd.com>
Signed-off-by: Sasha Levin <sas...@kernel.org>
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 31 +++++++++++++++-------------
1 file changed, 17 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 1b04d54f9a69c..4eeea51c9a0eb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2992,19 +2992,6 @@ svm_range_restore_pages(struct amdgpu_device *adev,
unsigned int pasid,
goto out;
}
- /* 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])) {
- pr_debug("draining retry fault, drop fault 0x%llx\n",
addr);
- r = 0;
- goto out;
- } else
- /* ts is after svms->checkpoint_ts now, reset
svms->checkpoint_ts
- * to zero to avoid following ts wrap around give wrong
comparing
- */
- svms->checkpoint_ts[gpuidx] = 0;
- }
-
if (!p->xnack_enabled) {
pr_debug("XNACK not enabled for pasid 0x%x\n", pasid);
r = -EFAULT;
@@ -3024,6 +3011,21 @@ svm_range_restore_pages(struct amdgpu_device *adev,
unsigned int pasid,
mmap_read_lock(mm);
retry_write_locked:
mutex_lock(&svms->lock);
+
+ /* 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])) {
+ pr_debug("draining retry fault, drop fault 0x%llx\n",
addr);
+ r = -EAGAIN;
+ goto out_unlock_svms;
+ } else {
+ /* ts is after svms->checkpoint_ts now, reset
svms->checkpoint_ts
+ * to zero to avoid following ts wrap around give wrong
comparing
+ */
+ svms->checkpoint_ts[gpuidx] = 0;
+ }
+ }
+
prange = svm_range_from_addr(svms, addr, NULL);
if (!prange) {
pr_debug("failed to find prange svms 0x%p address [0x%llx]\n",
@@ -3149,7 +3151,8 @@ svm_range_restore_pages(struct amdgpu_device *adev,
unsigned int pasid,
mutex_unlock(&svms->lock);
mmap_read_unlock(mm);
- svm_range_count_fault(node, p, gpuidx);
+ if (r != -EAGAIN)
+ svm_range_count_fault(node, p, gpuidx);
mmput(mm);
out:
--
2.39.5
