mm/hmm: remove HMM_FAULT_SNAPSHOT

Now that flags are handled on a fine-grained per-page basis this global flag is redundant and has a confusing overlap with the pfn_flags_mask and default_flags. Normalize the HMM_FAULT_SNAPSHOT behavior into one place. Callers needing the SNAPSHOT behavior should set a pfn_flags_mask and default_flags that always results in a cleared HMM_PFN_VALID. Then no pages will be faulted, and HMM_FAULT_SNAPSHOT is not a special flow that overrides the masking mechanism. As this is the last flag, also remove the flags argument. If future flags are needed they can be part of the struct hmm_range function arguments. Link: https://lore.kernel.org/r/[email protected] Reviewed-by: Christoph Hellwig <[email protected]> Signed-off-by: Jason Gunthorpe <[email protected]>
chewitt · Mar 27, 2020 · 6bfef2f · 6bfef2f
1 parent f970b97
commit 6bfef2f
Show file tree

Hide file tree

Showing 5 changed files with 17 additions and 21 deletions.
diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst
@@ -161,13 +161,11 @@ 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, unsigned int flags);
+  long hmm_range_fault(struct hmm_range *range);
 
-With the HMM_RANGE_SNAPSHOT flag, it will only fetch present CPU page table
-entries and will not trigger a page fault on missing or non-present entries.
-Without that flag, it does 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 like a CPU page fault.
+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
+like a CPU page fault.
 
 Both functions copy CPU page table entries into their pfns array argument. Each
 entry in that array corresponds to an address in the virtual range. HMM
@@ -197,7 +195,7 @@ The usage pattern is::
  again:
       range.notifier_seq = mmu_interval_read_begin(&interval_sub);
       down_read(&mm->mmap_sem);
-      ret = hmm_range_fault(&range, HMM_RANGE_SNAPSHOT);
+      ret = hmm_range_fault(&range);
       if (ret) {
           up_read(&mm->mmap_sem);
           if (ret == -EBUSY)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -856,7 +856,7 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 	range->notifier_seq = mmu_interval_read_begin(&bo->notifier);
 
 	down_read(&mm->mmap_sem);
-	r = hmm_range_fault(range, 0);
+	r = hmm_range_fault(range);
 	up_read(&mm->mmap_sem);
 	if (unlikely(r <= 0)) {
 		/*

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -540,7 +540,7 @@ static int nouveau_range_fault(struct nouveau_svmm *svmm,
 		range.default_flags = 0;
 		range.pfn_flags_mask = -1UL;
 		down_read(&mm->mmap_sem);
-		ret = hmm_range_fault(&range, 0);
+		ret = hmm_range_fault(&range);
 		up_read(&mm->mmap_sem);
 		if (ret <= 0) {
 			if (ret == 0 || ret == -EBUSY)

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
@@ -117,13 +117,10 @@ static inline struct page *hmm_device_entry_to_page(const struct hmm_range *rang
 	return pfn_to_page(entry >> range->pfn_shift);
 }
 
-/* Don't fault in missing PTEs, just snapshot the current state. */
-#define HMM_FAULT_SNAPSHOT		(1 << 1)
-
 /*
  * Please see Documentation/vm/hmm.rst for how to use the range API.
  */
-long hmm_range_fault(struct hmm_range *range, unsigned int flags);
+long 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
@@ -29,7 +29,6 @@
 struct hmm_vma_walk {
 	struct hmm_range	*range;
 	unsigned long		last;
-	unsigned int		flags;
 };
 
 enum {
@@ -112,9 +111,6 @@ static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
 {
 	struct hmm_range *range = hmm_vma_walk->range;
 
-	if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT)
-		return 0;
-
 	/*
 	 * So we not only consider the individual per page request we also
 	 * consider the default flags requested for the range. The API can
@@ -147,10 +143,17 @@ hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
 		     const uint64_t *pfns, unsigned long npages,
 		     uint64_t cpu_flags)
 {
+	struct hmm_range *range = hmm_vma_walk->range;
 	unsigned int required_fault = 0;
 	unsigned long i;
 
-	if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT)
+	/*
+	 * If the default flags do not request to fault pages, and the mask does
+	 * not allow for individual pages to be faulted, then
+	 * hmm_pte_need_fault() will always return 0.
+	 */
+	if (!((range->default_flags | range->pfn_flags_mask) &
+	      range->flags[HMM_PFN_VALID]))
 		return 0;
 
 	for (i = 0; i < npages; ++i) {
@@ -557,7 +560,6 @@ 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
- * @flags:	HMM_FAULT_* flags
  *
  * 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
@@ -579,12 +581,11 @@ static const struct mm_walk_ops hmm_walk_ops = {
  * On error, for one virtual address in the range, the function will mark the
  * corresponding HMM pfn entry with an error flag.
  */
-long hmm_range_fault(struct hmm_range *range, unsigned int flags)
+long hmm_range_fault(struct hmm_range *range)
 {
 	struct hmm_vma_walk hmm_vma_walk = {
 		.range = range,
 		.last = range->start,
-		.flags = flags,
 	};
 	struct mm_struct *mm = range->notifier->mm;
 	int ret;