From aa8543e66268c38cd8a1974275dd8d8914fa7e38 Mon Sep 17 00:00:00 2001 From: Stanislav Kinsburskii Date: Thu, 23 Jul 2026 10:36:40 -0700 Subject: [PATCH] drm/gpusvm: use hmm_range_fault_unlocked_timeout() for range faults Several GPU SVM paths take mmap_read_lock() only to call hmm_range_fault() and open-code mmu interval sequence setup before each HMM walk. They also retry -EBUSY until HMM_RANGE_DEFAULT_TIMEOUT expires. Use hmm_range_fault_unlocked_timeout() for those faults. The HMM helper now owns mmap_lock acquisition and refreshes range->notifier_seq for its internal retries, while GPU SVM keeps its existing driver-lock validation with mmu_interval_read_retry() after a successful fault. drm_gpusvm_scan_mm() and drm_gpusvm_range_evict() pass HMM_RANGE_DEFAULT_TIMEOUT as the helper retry budget for each HMM fault attempt. drm_gpusvm_get_pages() keeps its existing absolute outer deadline because it can be reached from GPU page-fault workers, where fatal signals from the faulting process cannot stop an endless invalidation retry loop. It passes the remaining time from that deadline to HMM for each fault attempt. Leave drm_gpusvm_check_pages() on hmm_range_fault() because that path is called with the mmap lock already held by its caller. Link: https://lore.kernel.org/20260723-hmm-v10-v11-8-c55b003a4b61@gmail.com Signed-off-by: Stanislav Kinsburskii Reviewed-by: Jason Gunthorpe Cc: Danilo Krummrich Cc: Dave Airlie Cc: David Hildenbrand Cc: Dexuan Cui Cc: Haiyang Zhang Cc: Jonathan Corbet Cc: K. Y. Srinivasan Cc: Leon Romanovsky Cc: Liam R. Howlett Cc: Lizhi Hou Cc: Long Li Cc: Lorenzo Stoakes Cc: Lyude Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Michal Hocko Cc: Mike Rapoport Cc: Oded Gabbay Cc: Shuah Khan Cc: Suren Baghdasaryan Cc: Thomas Zimemrmann Cc: Vlastimil Babka Cc: Wei Liu Signed-off-by: Andrew Morton --- drivers/gpu/drm/drm_gpusvm.c | 60 ++++++------------------------------ 1 file changed, 10 insertions(+), 50 deletions(-) diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index 18ddef94da47..e5e105466f53 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -773,8 +773,7 @@ enum drm_gpusvm_scan_result drm_gpusvm_scan_mm(struct drm_gpusvm_range *range, .end = end, .dev_private_owner = dev_private_owner, }; - unsigned long timeout = - jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + unsigned long timeout = msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); enum drm_gpusvm_scan_result state = DRM_GPUSVM_SCAN_UNPOPULATED, new_state; unsigned long *pfns; unsigned long npages = npages_in_range(start, end); @@ -788,22 +787,7 @@ enum drm_gpusvm_scan_result drm_gpusvm_scan_mm(struct drm_gpusvm_range *range, hmm_range.hmm_pfns = pfns; retry: - hmm_range.notifier_seq = mmu_interval_read_begin(notifier); - mmap_read_lock(range->gpusvm->mm); - - while (true) { - err = hmm_range_fault(&hmm_range); - if (err == -EBUSY) { - if (time_after(jiffies, timeout)) - break; - - hmm_range.notifier_seq = - mmu_interval_read_begin(notifier); - continue; - } - break; - } - mmap_read_unlock(range->gpusvm->mm); + err = hmm_range_fault_unlocked_timeout(&hmm_range, timeout); if (err) goto err_free; @@ -1423,6 +1407,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, void *zdd; unsigned long timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + unsigned long remaining; unsigned long i, j; unsigned long npages = npages_in_range(pages_start, pages_end); unsigned long num_dma_mapped; @@ -1437,7 +1422,9 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, struct dma_iova_state *state = &svm_pages->state; retry: - if (time_after(jiffies, timeout)) + remaining = timeout - jiffies; + + if (time_after_eq(jiffies, timeout)) return -EBUSY; hmm_range.notifier_seq = mmu_interval_read_begin(notifier); @@ -1454,21 +1441,7 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm, } hmm_range.hmm_pfns = pfns; - while (true) { - mmap_read_lock(mm); - err = hmm_range_fault(&hmm_range); - mmap_read_unlock(mm); - - if (err == -EBUSY) { - if (time_after(jiffies, timeout)) - break; - - hmm_range.notifier_seq = - mmu_interval_read_begin(notifier); - continue; - } - break; - } + err = hmm_range_fault_unlocked_timeout(&hmm_range, remaining); mmput(mm); if (err) goto err_free; @@ -1741,8 +1714,7 @@ int drm_gpusvm_range_evict(struct drm_gpusvm *gpusvm, .end = drm_gpusvm_range_end(range), .dev_private_owner = NULL, }; - unsigned long timeout = - jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); + unsigned long timeout = msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); unsigned long *pfns; unsigned long npages = npages_in_range(drm_gpusvm_range_start(range), drm_gpusvm_range_end(range)); @@ -1759,24 +1731,12 @@ int drm_gpusvm_range_evict(struct drm_gpusvm *gpusvm, } hmm_range.hmm_pfns = pfns; - while (!time_after(jiffies, timeout)) { - hmm_range.notifier_seq = mmu_interval_read_begin(notifier); - if (time_after(jiffies, timeout)) { - err = -ETIME; - break; - } - - mmap_read_lock(mm); - err = hmm_range_fault(&hmm_range); - mmap_read_unlock(mm); - if (err != -EBUSY) - break; - } + err = hmm_range_fault_unlocked_timeout(&hmm_range, timeout); kvfree(pfns); mmput(mm); - return err; + return err == -EBUSY ? -ETIME : err; } EXPORT_SYMBOL_GPL(drm_gpusvm_range_evict);