From 702dde19d4b0e7927e93c0186be998819e9703b9 Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Fri, 22 Oct 2021 12:24:36 -0400
Subject: [PATCH] drm/amdkfd: restore userptr ignore bad address error
The userptr can be unmapped by application and still registered to
driver, restore userptr work return user pages will get -EFAULT bad
address error. Pretend this error as succeed. GPU access this userptr
will have VM fault later, it is better than application soft hangs with
stalled user mode queues.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 27 ++++++++++++-------
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 +++
2 files changed, 20 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index cdf46bd0d8d5b..6f01c6145a87f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2041,19 +2041,26 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
/* Get updated user pages */
ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);
if (ret) {
- pr_debug("%s: Failed to get user pages: %d\n",
- __func__, ret);
+ pr_debug("Failed %d to get user pages\n", ret);
+
+ /* Return -EFAULT bad address error as success. It will
+ * fail later with a VM fault if the GPU tries to access
+ * it. Better than hanging indefinitely with stalled
+ * user mode queues.
+ *
+ * Return other error -EBUSY or -ENOMEM to retry restore
+ */
+ if (ret != -EFAULT)
+ return ret;
+ } else {
- /* Return error -EBUSY or -ENOMEM, retry restore */
- return ret;
+ /*
+ * FIXME: Cannot ignore the return code, must hold
+ * notifier_lock
+ */
+ amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
}
- /*
- * FIXME: Cannot ignore the return code, must hold
- * notifier_lock
- */
- amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
-
/* Mark the BO as valid unless it was invalidated
* again concurrently.
*/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index d784f8d3a8347..ae6694f2c73d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -693,6 +693,9 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
r = amdgpu_hmm_range_get_pages(&bo->notifier, mm, pages, start,
ttm->num_pages, >t->range, readonly,
false, NULL);
+ if (r)
+ pr_debug("failed %d to get user pages 0x%llx\n", r, start);
+
out_putmm:
mmput(mm);
--
GitLab