[PATCH hmm 2/5] mm/hmm: make hmm_range_fault return 0 or -1

[Jason Gunthorpe]

From: Jason Gunthorpe <jgg@xxxxxxxxxxxx>

hmm_vma_walk->last is supposed to be updated after every write to the
pfns, so that it can be returned by hmm_range_fault(). However, this is
not done consistently. Fortunately nothing checks the return code of
hmm_range_fault() for anything other than error.

More importantly last must be set before returning -EBUSY as it is used to
prevent reading an output pfn as an input flags when the loop restarts.

For clarity and simplicity make hmm_range_fault() return 0 or -ERRNO. Only
set last when returning -EBUSY.

Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
---
 Documentation/vm/hmm.rst                |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c |  4 ++--
 drivers/gpu/drm/nouveau/nouveau_svm.c   |  6 +++---
 include/linux/hmm.h                     |  2 +-
 mm/hmm.c                                | 25 +++++++++----------------
 5 files changed, 16 insertions(+), 23 deletions(-)

diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
index 4e3e9362afeb10..9924f2caa0184c 100644
--- a/Documentation/vm/hmm.rst
+++ b/Documentation/vm/hmm.rst
@@ -161,7 +161,7 @@ device must complete the update before the driver callback returns.
 When the device driver wants to populate a range of virtual addresses, it can
 use::
 
-  long hmm_range_fault(struct hmm_range *range);
+  int hmm_range_fault(struct hmm_range *range);
 
 It will trigger a page fault on missing or read-only entries if write access is
 requested (see below). Page faults use the generic mm page fault code path just
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6309ff72bd7876..efc1329a019127 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -852,12 +852,12 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 	down_read(&mm->mmap_sem);
 	r = hmm_range_fault(range);
 	up_read(&mm->mmap_sem);
-	if (unlikely(r <= 0)) {
+	if (unlikely(r)) {
 		/*
 		 * FIXME: This timeout should encompass the retry from
 		 * mmu_interval_read_retry() as well.
 		 */
-		if ((r == 0 || r == -EBUSY) && !time_after(jiffies, timeout))
+		if ((r == -EBUSY) && !time_after(jiffies, timeout))
 			goto retry;
 		goto out_free_pfns;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index 645fedd77e21b4..c68e9317cf0740 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -536,7 +536,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 		.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT,
 	};
 	struct mm_struct *mm = notifier->notifier.mm;
-	long ret;
+	int ret;
 
 	while (true) {
 		if (time_after(jiffies, timeout))
@@ -548,8 +548,8 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 		down_read(&mm->mmap_sem);
 		ret = hmm_range_fault(&range);
 		up_read(&mm->mmap_sem);
-		if (ret <= 0) {
-			if (ret == 0 || ret == -EBUSY)
+		if (ret) {
+			if (ret == -EBUSY)
 				continue;
 			return ret;
 		}
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 7475051100c782..0df27dd03d53d7 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -120,7 +120,7 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang
 /*
  * Please see Documentation/vm/hmm.rst for how to use the range API.
  */
-long hmm_range_fault(struct hmm_range *range);
+int hmm_range_fault(struct hmm_range *range);
 
 /*
  * HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
diff --git a/mm/hmm.c b/mm/hmm.c
index 280585833adfc1..4c7c396655b528 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -174,7 +174,6 @@ static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
 	}
 	if (required_fault)
 		return hmm_vma_fault(addr, end, required_fault, walk);
-	hmm_vma_walk->last = addr;
 	return hmm_pfns_fill(addr, end, range, HMM_PFN_NONE);
 }
 
@@ -207,7 +206,6 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
 	pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
 		pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
-	hmm_vma_walk->last = end;
 	return 0;
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -386,13 +384,10 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 		r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, pfns);
 		if (r) {
 			/* hmm_vma_handle_pte() did pte_unmap() */
-			hmm_vma_walk->last = addr;
 			return r;
 		}
 	}
 	pte_unmap(ptep - 1);
-
-	hmm_vma_walk->last = addr;
 	return 0;
 }
 
@@ -455,7 +450,6 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
 		for (i = 0; i < npages; ++i, ++pfn)
 			pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
 				  cpu_flags;
-		hmm_vma_walk->last = end;
 		goto out_unlock;
 	}
 
@@ -500,7 +494,6 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 	for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
 		range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
 				 cpu_flags;
-	hmm_vma_walk->last = end;
 	spin_unlock(ptl);
 	return 0;
 }
@@ -537,7 +530,6 @@ static int hmm_vma_walk_test(unsigned long start, unsigned long end,
 		return -EFAULT;
 
 	hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
-	hmm_vma_walk->last = end;
 
 	/* Skip this vma and continue processing the next vma. */
 	return 1;
@@ -555,9 +547,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
  * hmm_range_fault - try to fault some address in a virtual address range
  * @range:	argument structure
  *
- * Return: the number of valid pages in range->pfns[] (from range start
- * address), which may be zero.  On error one of the following status codes
- * can be returned:
+ * Return: 0 or -ERRNO with one of the following status codes:
  *
  * -EINVAL:	Invalid arguments or mm or virtual address is in an invalid vma
  *		(e.g., device file vma).
@@ -572,7 +562,7 @@ static const struct mm_walk_ops hmm_walk_ops = {
  * This is similar to get_user_pages(), except that it can read the page tables
  * without mutating them (ie causing faults).
  */
-long hmm_range_fault(struct hmm_range *range)
+int hmm_range_fault(struct hmm_range *range)
 {
 	struct hmm_vma_walk hmm_vma_walk = {
 		.range = range,
@@ -590,10 +580,13 @@ long hmm_range_fault(struct hmm_range *range)
 			return -EBUSY;
 		ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
 				      &hmm_walk_ops, &hmm_vma_walk);
+		/*
+		 * When -EBUSY is returned the loop restarts with
+		 * hmm_vma_walk.last set to an address that has not been stored
+		 * in pfns. All entries < last in the pfn array are set to their
+		 * output, and all >= are still at their input values.
+		 */
 	} while (ret == -EBUSY);
-
-	if (ret)
-		return ret;
-	return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
+	return ret;
 }
 EXPORT_SYMBOL(hmm_range_fault);
-- 
2.26.0