diff options
author | Philip Yang <Philip.Yang@amd.com> | 2024-04-30 13:51:51 -0400 |
---|---|---|
committer | Alex Deucher <alexander.deucher@amd.com> | 2024-05-13 15:44:02 -0400 |
commit | 9095e5544061b16d1b331aca3f32c76cbd656d72 (patch) | |
tree | 1fc184dd13bc267638a4954ef3292ba7c144d77d | |
parent | 10f624ef239bd136cdcc5bbc626157a57b938a31 (diff) |
drm/amdkfd: Remove arbitrary timeout for hmm_range_fault
On system with khugepaged enabled and user cases with THP buffer, the
hmm_range_fault may takes > 15 seconds to return -EBUSY, the arbitrary
timeout value is not accurate, cause memory allocation failure.
Remove the arbitrary timeout value, return EAGAIN to application if
hmm_range_fault return EBUSY, then userspace libdrm and Thunk will call
ioctl again.
Change EAGAIN to debug message as this is not error.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 5 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c | 12 | ||||
-rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 5 |
3 files changed, 8 insertions, 14 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 75d49390cae0..3314821e4cf3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1088,7 +1088,10 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr, ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, &range); if (ret) { - pr_err("%s: Failed to get user pages: %d\n", __func__, ret); + if (ret == -EAGAIN) + pr_debug("Failed to get user pages, try again\n"); + else + pr_err("%s: Failed to get user pages: %d\n", __func__, ret); goto unregister_out; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c index 431ec72655ec..e36fede7f74c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_hmm.c @@ -202,20 +202,12 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, pr_debug("hmm range: start = 0x%lx, end = 0x%lx", hmm_range->start, hmm_range->end); - /* Assuming 64MB takes maximum 1 second to fault page address */ - timeout = max((hmm_range->end - hmm_range->start) >> 26, 1UL); - timeout *= HMM_RANGE_DEFAULT_TIMEOUT; - timeout = jiffies + msecs_to_jiffies(timeout); + timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); retry: hmm_range->notifier_seq = mmu_interval_read_begin(notifier); r = hmm_range_fault(hmm_range); if (unlikely(r)) { - schedule(); - /* - * FIXME: This timeout should encompass the retry from - * mmu_interval_read_retry() as well. - */ if (r == -EBUSY && !time_after(jiffies, timeout)) goto retry; goto out_free_pfns; @@ -247,6 +239,8 @@ out_free_pfns: out_free_range: kfree(hmm_range); + if (r == -EBUSY) + r = -EAGAIN; return r; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 4885d1b2cc29..4e5851bdf832 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1690,11 +1690,8 @@ static int svm_range_validate_and_map(struct mm_struct *mm, readonly, owner, NULL, &hmm_range); WRITE_ONCE(p->svms.faulting_task, NULL); - if (r) { + if (r) pr_debug("failed %d to get svm range pages\n", r); - if (r == -EBUSY) - r = -EAGAIN; - } } else { r = -EFAULT; } |