[PATCH v10 8/8] drm/gpusvm: Use hmm_range_fault_unlocked_timeout() for range faults

[Stanislav Kinsburskii <skinsburskii@gmail.com>]

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.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Stanislav Kinsburskii <skinsburskii@gmail.com>
---
 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 958cb605aedd..b946f920b7a0 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;
 
@@ -1408,6 +1392,7 @@ 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;
@@ -1422,9 +1407,11 @@ int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
 	struct dma_iova_state *state = &svm_pages->state;
 
 retry:
-	if (time_after(jiffies, timeout))
+	if (time_after_eq(jiffies, timeout))
 		return -EBUSY;
 
+	remaining = timeout - jiffies;
+
 	hmm_range.notifier_seq = mmu_interval_read_begin(notifier);
 	if (drm_gpusvm_pages_valid_unlocked(gpusvm, svm_pages))
 		goto set_seqno;
@@ -1439,21 +1426,7 @@ 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;
@@ -1720,8 +1693,7 @@ 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));
@@ -1736,24 +1708,12 @@ int drm_gpusvm_range_evict(struct drm_gpusvm *gpusvm,
 		return -ENOMEM;
 
 	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);
 

-- 
2.43.0