On 2019-10-29 3:25 p.m., Jason Gunthorpe wrote:
> On Tue, Oct 29, 2019 at 07:22:37PM +0000, Yang, Philip wrote:
>> Hi Jason,
>>
>> I did quick test after merging amd-staging-drm-next with the
>> mmu_notifier branch, which includes this set changes. The test result
>> has different failures, app stuck intermittently, GUI no display etc. I
>> am understanding the changes and will try to figure out the cause.
>
> Thanks! I'm not surprised by this given how difficult this patch was
> to make. Let me know if I can assist in any way
>
> Please ensure to run with lockdep enabled.. Your symptops sounds sort
> of like deadlocking?
>
Hi Jason,
Attached patch fix several issues in amdgpu driver, maybe you can squash
this into patch 14. With this is done, patch 12, 13, 14 is Reviewed-by
and Tested-by Philip Yang <philip.yang@xxxxxxx>
Regards,
Philip
> Regards,
> Jason
>
From 5a0bd4d8cef8472fe2904550142d288feed8cd81 Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@xxxxxxx>
Date: Thu, 31 Oct 2019 09:10:30 -0400
Subject: [PATCH] drm/amdgpu: issues with new mmu_range_notifier api
put mmu_range_set_seq under the same lock which is used to call
mmu_range_read_retry.
fix amdgpu_ttm_tt_get_user_pages_done return value, because
mmu_range_read_retry means !hmm_range_valid
retry if hmm_range_fault return -EBUSY
fix false WARN for missing get_user_page_done, we should check all
pages not just the first page, don't understand why this issue is
triggered by this change.
Signed-off-by: Philip Yang <Philip.Yang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 32 +++++++--------------
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 37 +++++++++++++++++--------
2 files changed, 36 insertions(+), 33 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index cb718a064eb4..c8bbd06f1009 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -67,21 +67,15 @@ static bool amdgpu_mn_invalidate_gfx(struct mmu_range_notifier *mrn,
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
long r;
- /*
- * FIXME: Must hold some lock shared with
- * amdgpu_ttm_tt_get_user_pages_done()
- */
- mmu_range_set_seq(mrn, cur_seq);
+ mutex_lock(&adev->notifier_lock);
- /* FIXME: Is this necessary? */
- if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, range->start,
- range->end))
- return true;
+ mmu_range_set_seq(mrn, cur_seq);
- if (!mmu_notifier_range_blockable(range))
+ if (!mmu_notifier_range_blockable(range)) {
+ mutex_unlock(&adev->notifier_lock);
return false;
+ }
- mutex_lock(&adev->notifier_lock);
r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, true, false,
MAX_SCHEDULE_TIMEOUT);
mutex_unlock(&adev->notifier_lock);
@@ -110,21 +104,15 @@ static bool amdgpu_mn_invalidate_hsa(struct mmu_range_notifier *mrn,
struct amdgpu_bo *bo = container_of(mrn, struct amdgpu_bo, notifier);
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
- /*
- * FIXME: Must hold some lock shared with
- * amdgpu_ttm_tt_get_user_pages_done()
- */
- mmu_range_set_seq(mrn, cur_seq);
+ mutex_lock(&adev->notifier_lock);
- /* FIXME: Is this necessary? */
- if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, range->start,
- range->end))
- return true;
+ mmu_range_set_seq(mrn, cur_seq);
- if (!mmu_notifier_range_blockable(range))
+ if (!mmu_notifier_range_blockable(range)) {
+ mutex_unlock(&adev->notifier_lock);
return false;
+ }
- mutex_lock(&adev->notifier_lock);
amdgpu_amdkfd_evict_userptr(bo->kfd_bo, bo->notifier.mm);
mutex_unlock(&adev->notifier_lock);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index a38437fd290a..56fde43d5efa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -799,10 +799,11 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
{
struct ttm_tt *ttm = bo->tbo.ttm;
struct amdgpu_ttm_tt *gtt = (void *)ttm;
- struct mm_struct *mm;
- struct hmm_range *range;
unsigned long start = gtt->userptr;
struct vm_area_struct *vma;
+ struct hmm_range *range;
+ unsigned long timeout;
+ struct mm_struct *mm;
unsigned long i;
int r = 0;
@@ -841,8 +842,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
goto out_free_ranges;
}
- range->notifier_seq = mmu_range_read_begin(&bo->notifier);
-
down_read(&mm->mmap_sem);
vma = find_vma(mm, start);
if (unlikely(!vma || start < vma->vm_start)) {
@@ -854,12 +853,20 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
r = -EPERM;
goto out_unlock;
}
+ up_read(&mm->mmap_sem);
+ timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
+
+retry:
+ range->notifier_seq = mmu_range_read_begin(&bo->notifier);
+ down_read(&mm->mmap_sem);
r = hmm_range_fault(range, 0);
up_read(&mm->mmap_sem);
-
- if (unlikely(r < 0))
+ if (unlikely(r <= 0)) {
+ if ((r == 0 || r == -EBUSY) && !time_after(jiffies, timeout))
+ goto retry;
goto out_free_pfns;
+ }
for (i = 0; i < ttm->num_pages; i++) {
pages[i] = hmm_device_entry_to_page(range, range->pfns[i]);
@@ -916,7 +923,7 @@ bool amdgpu_ttm_tt_get_user_pages_done(struct ttm_tt *ttm)
gtt->range = NULL;
}
- return r;
+ return !r;
}
#endif
@@ -997,10 +1004,18 @@ static void amdgpu_ttm_tt_unpin_userptr(struct ttm_tt *ttm)
sg_free_table(ttm->sg);
#if IS_ENABLED(CONFIG_DRM_AMDGPU_USERPTR)
- if (gtt->range &&
- ttm->pages[0] == hmm_device_entry_to_page(gtt->range,
- gtt->range->pfns[0]))
- WARN_ONCE(1, "Missing get_user_page_done\n");
+ if (gtt->range) {
+ unsigned long i;
+
+ for (i = 0; i < ttm->num_pages; i++) {
+ if (ttm->pages[i] !=
+ hmm_device_entry_to_page(gtt->range,
+ gtt->range->pfns[i]))
+ break;
+ }
+
+ WARN((i == ttm->num_pages), "Missing get_user_page_done\n");
+ }
#endif
}
--
2.17.1
