1 files changed, 198 insertions, 136 deletions

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 5e77b269c330..74d2de15fb5e 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -13,71 +13,82 @@ static inline bool not_found(struct page_vma_mapped_walk *pvmw)
 	return false;
 }
 
-static bool map_pte(struct page_vma_mapped_walk *pvmw)
+static bool map_pte(struct page_vma_mapped_walk *pvmw, spinlock_t **ptlp)
 {
-	pvmw->pte = pte_offset_map(pvmw->pmd, pvmw->address);
-	if (!(pvmw->flags & PVMW_SYNC)) {
-		if (pvmw->flags & PVMW_MIGRATION) {
-			if (!is_swap_pte(*pvmw->pte))
-				return false;
-		} else {
-			/*
-			 * We get here when we are trying to unmap a private
-			 * device page from the process address space. Such
-			 * page is not CPU accessible and thus is mapped as
-			 * a special swap entry, nonetheless it still does
-			 * count as a valid regular mapping for the page (and
-			 * is accounted as such in page maps count).
-			 *
-			 * So handle this special case as if it was a normal
-			 * page mapping ie lock CPU page table and returns
-			 * true.
-			 *
-			 * For more details on device private memory see HMM
-			 * (include/linux/hmm.h or mm/hmm.c).
-			 */
-			if (is_swap_pte(*pvmw->pte)) {
-				swp_entry_t entry;
+	pte_t ptent;
 
-				/* Handle un-addressable ZONE_DEVICE memory */
-				entry = pte_to_swp_entry(*pvmw->pte);
-				if (!is_device_private_entry(entry))
-					return false;
-			} else if (!pte_present(*pvmw->pte))
-				return false;
-		}
+	if (pvmw->flags & PVMW_SYNC) {
+		/* Use the stricter lookup */
+		pvmw->pte = pte_offset_map_lock(pvmw->vma->vm_mm, pvmw->pmd,
+						pvmw->address, &pvmw->ptl);
+		*ptlp = pvmw->ptl;
+		return !!pvmw->pte;
 	}
-	pvmw->ptl = pte_lockptr(pvmw->vma->vm_mm, pvmw->pmd);
-	spin_lock(pvmw->ptl);
-	return true;
-}
 
-static inline bool pfn_is_match(struct page *page, unsigned long pfn)
-{
-	unsigned long page_pfn = page_to_pfn(page);
+	/*
+	 * It is important to return the ptl corresponding to pte,
+	 * in case *pvmw->pmd changes underneath us; so we need to
+	 * return it even when choosing not to lock, in case caller
+	 * proceeds to loop over next ptes, and finds a match later.
+	 * Though, in most cases, page lock already protects this.
+	 */
+	pvmw->pte = pte_offset_map_nolock(pvmw->vma->vm_mm, pvmw->pmd,
+					  pvmw->address, ptlp);
+	if (!pvmw->pte)
+		return false;
 
-	/* normal page and hugetlbfs page */
-	if (!PageTransCompound(page) || PageHuge(page))
-		return page_pfn == pfn;
+	ptent = ptep_get(pvmw->pte);
 
-	/* THP can be referenced by any subpage */
-	return pfn >= page_pfn && pfn - page_pfn < thp_nr_pages(page);
+	if (pvmw->flags & PVMW_MIGRATION) {
+		if (!is_swap_pte(ptent))
+			return false;
+	} else if (is_swap_pte(ptent)) {
+		swp_entry_t entry;
+		/*
+		 * Handle un-addressable ZONE_DEVICE memory.
+		 *
+		 * We get here when we are trying to unmap a private
+		 * device page from the process address space. Such
+		 * page is not CPU accessible and thus is mapped as
+		 * a special swap entry, nonetheless it still does
+		 * count as a valid regular mapping for the page
+		 * (and is accounted as such in page maps count).
+		 *
+		 * So handle this special case as if it was a normal
+		 * page mapping ie lock CPU page table and return true.
+		 *
+		 * For more details on device private memory see HMM
+		 * (include/linux/hmm.h or mm/hmm.c).
+		 */
+		entry = pte_to_swp_entry(ptent);
+		if (!is_device_private_entry(entry) &&
+		    !is_device_exclusive_entry(entry))
+			return false;
+	} else if (!pte_present(ptent)) {
+		return false;
+	}
+	pvmw->ptl = *ptlp;
+	spin_lock(pvmw->ptl);
+	return true;
 }
 
 /**
- * check_pte - check if @pvmw->page is mapped at the @pvmw->pte
+ * check_pte - check if [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages) is
+ * mapped at the @pvmw->pte
+ * @pvmw: page_vma_mapped_walk struct, includes a pair pte and pfn range
+ * for checking
  *
- * page_vma_mapped_walk() found a place where @pvmw->page is *potentially*
+ * page_vma_mapped_walk() found a place where pfn range is *potentially*
  * mapped. check_pte() has to validate this.
  *
- * @pvmw->pte may point to empty PTE, swap PTE or PTE pointing to arbitrary
- * page.
+ * pvmw->pte may point to empty PTE, swap PTE or PTE pointing to
+ * arbitrary page.
  *
  * If PVMW_MIGRATION flag is set, returns true if @pvmw->pte contains migration
- * entry that points to @pvmw->page or any subpage in case of THP.
+ * entry that points to [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages)
  *
- * If PVMW_MIGRATION flag is not set, returns true if @pvmw->pte points to
- * @pvmw->page or any subpage in case of THP.
+ * If PVMW_MIGRATION flag is not set, returns true if pvmw->pte points to
+ * [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages)
  *
  * Otherwise, return false.
  *
@@ -85,38 +96,58 @@ static inline bool pfn_is_match(struct page *page, unsigned long pfn)
 static bool check_pte(struct page_vma_mapped_walk *pvmw)
 {
 	unsigned long pfn;
+	pte_t ptent = ptep_get(pvmw->pte);
 
 	if (pvmw->flags & PVMW_MIGRATION) {
 		swp_entry_t entry;
-		if (!is_swap_pte(*pvmw->pte))
+		if (!is_swap_pte(ptent))
 			return false;
-		entry = pte_to_swp_entry(*pvmw->pte);
+		entry = pte_to_swp_entry(ptent);
 
-		if (!is_migration_entry(entry))
+		if (!is_migration_entry(entry) &&
+		    !is_device_exclusive_entry(entry))
 			return false;
 
-		pfn = migration_entry_to_pfn(entry);
-	} else if (is_swap_pte(*pvmw->pte)) {
+		pfn = swp_offset_pfn(entry);
+	} else if (is_swap_pte(ptent)) {
 		swp_entry_t entry;
 
 		/* Handle un-addressable ZONE_DEVICE memory */
-		entry = pte_to_swp_entry(*pvmw->pte);
-		if (!is_device_private_entry(entry))
+		entry = pte_to_swp_entry(ptent);
+		if (!is_device_private_entry(entry) &&
+		    !is_device_exclusive_entry(entry))
 			return false;
 
-		pfn = device_private_entry_to_pfn(entry);
+		pfn = swp_offset_pfn(entry);
 	} else {
-		if (!pte_present(*pvmw->pte))
+		if (!pte_present(ptent))
 			return false;
 
-		pfn = pte_pfn(*pvmw->pte);
+		pfn = pte_pfn(ptent);
 	}
 
-	return pfn_is_match(pvmw->page, pfn);
+	return (pfn - pvmw->pfn) < pvmw->nr_pages;
+}
+
+/* Returns true if the two ranges overlap.  Careful to not overflow. */
+static bool check_pmd(unsigned long pfn, struct page_vma_mapped_walk *pvmw)
+{
+	if ((pfn + HPAGE_PMD_NR - 1) < pvmw->pfn)
+		return false;
+	if (pfn > pvmw->pfn + pvmw->nr_pages - 1)
+		return false;
+	return true;
+}
+
+static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size)
+{
+	pvmw->address = (pvmw->address + size) & ~(size - 1);
+	if (!pvmw->address)
+		pvmw->address = ULONG_MAX;
 }
 
 /**
- * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at
+ * page_vma_mapped_walk - check if @pvmw->pfn is mapped in @pvmw->vma at
  * @pvmw->address
  * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags
  * must be set. pmd, pte and ptl must be NULL.
@@ -133,7 +164,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
  * regardless of which page table level the page is mapped at. @pvmw->pmd is
  * NULL.
  *
- * Retruns false if there are no more page table entries for the page in
+ * Returns false if there are no more page table entries for the page in
  * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped.
  *
  * If you need to stop the walk before page_vma_mapped_walk() returned false,
@@ -141,8 +172,10 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
  */
 bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 {
-	struct mm_struct *mm = pvmw->vma->vm_mm;
-	struct page *page = pvmw->page;
+	struct vm_area_struct *vma = pvmw->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long end;
+	spinlock_t *ptl;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
@@ -152,101 +185,133 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	if (pvmw->pmd && !pvmw->pte)
 		return not_found(pvmw);
 
-	if (pvmw->pte)
-		goto next_pte;
-
-	if (unlikely(PageHuge(pvmw->page))) {
-		/* when pud is not present, pte will be NULL */
-		pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page));
+	if (unlikely(is_vm_hugetlb_page(vma))) {
+		struct hstate *hstate = hstate_vma(vma);
+		unsigned long size = huge_page_size(hstate);
+		/* The only possible mapping was handled on last iteration */
+		if (pvmw->pte)
+			return not_found(pvmw);
+		/*
+		 * All callers that get here will already hold the
+		 * i_mmap_rwsem.  Therefore, no additional locks need to be
+		 * taken before calling hugetlb_walk().
+		 */
+		pvmw->pte = hugetlb_walk(vma, pvmw->address, size);
 		if (!pvmw->pte)
 			return false;
 
-		pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte);
-		spin_lock(pvmw->ptl);
+		pvmw->ptl = huge_pte_lock(hstate, mm, pvmw->pte);
 		if (!check_pte(pvmw))
 			return not_found(pvmw);
 		return true;
 	}
+
+	end = vma_address_end(pvmw);
+	if (pvmw->pte)
+		goto next_pte;
 restart:
-	pgd = pgd_offset(mm, pvmw->address);
-	if (!pgd_present(*pgd))
-		return false;
-	p4d = p4d_offset(pgd, pvmw->address);
-	if (!p4d_present(*p4d))
-		return false;
-	pud = pud_offset(p4d, pvmw->address);
-	if (!pud_present(*pud))
-		return false;
-	pvmw->pmd = pmd_offset(pud, pvmw->address);
-	/*
-	 * Make sure the pmd value isn't cached in a register by the
-	 * compiler and used as a stale value after we've observed a
-	 * subsequent update.
-	 */
-	pmde = READ_ONCE(*pvmw->pmd);
-	if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
-		pvmw->ptl = pmd_lock(mm, pvmw->pmd);
-		if (likely(pmd_trans_huge(*pvmw->pmd))) {
-			if (pvmw->flags & PVMW_MIGRATION)
-				return not_found(pvmw);
-			if (pmd_page(*pvmw->pmd) != page)
-				return not_found(pvmw);
-			return true;
-		} else if (!pmd_present(*pvmw->pmd)) {
-			if (thp_migration_supported()) {
-				if (!(pvmw->flags & PVMW_MIGRATION))
-					return not_found(pvmw);
-				if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) {
-					swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd);
+	do {
+		pgd = pgd_offset(mm, pvmw->address);
+		if (!pgd_present(*pgd)) {
+			step_forward(pvmw, PGDIR_SIZE);
+			continue;
+		}
+		p4d = p4d_offset(pgd, pvmw->address);
+		if (!p4d_present(*p4d)) {
+			step_forward(pvmw, P4D_SIZE);
+			continue;
+		}
+		pud = pud_offset(p4d, pvmw->address);
+		if (!pud_present(*pud)) {
+			step_forward(pvmw, PUD_SIZE);
+			continue;
+		}
 
-					if (migration_entry_to_page(entry) != page)
-						return not_found(pvmw);
-					return true;
-				}
+		pvmw->pmd = pmd_offset(pud, pvmw->address);
+		/*
+		 * Make sure the pmd value isn't cached in a register by the
+		 * compiler and used as a stale value after we've observed a
+		 * subsequent update.
+		 */
+		pmde = pmdp_get_lockless(pvmw->pmd);
+
+		if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde) ||
+		    (pmd_present(pmde) && pmd_devmap(pmde))) {
+			pvmw->ptl = pmd_lock(mm, pvmw->pmd);
+			pmde = *pvmw->pmd;
+			if (!pmd_present(pmde)) {
+				swp_entry_t entry;
+
+				if (!thp_migration_supported() ||
+				    !(pvmw->flags & PVMW_MIGRATION))
+					return not_found(pvmw);
+				entry = pmd_to_swp_entry(pmde);
+				if (!is_migration_entry(entry) ||
+				    !check_pmd(swp_offset_pfn(entry), pvmw))
+					return not_found(pvmw);
+				return true;
+			}
+			if (likely(pmd_trans_huge(pmde) || pmd_devmap(pmde))) {
+				if (pvmw->flags & PVMW_MIGRATION)
+					return not_found(pvmw);
+				if (!check_pmd(pmd_pfn(pmde), pvmw))
+					return not_found(pvmw);
+				return true;
 			}
-			return not_found(pvmw);
-		} else {
 			/* THP pmd was split under us: handle on pte level */
 			spin_unlock(pvmw->ptl);
 			pvmw->ptl = NULL;
+		} else if (!pmd_present(pmde)) {
+			/*
+			 * If PVMW_SYNC, take and drop THP pmd lock so that we
+			 * cannot return prematurely, while zap_huge_pmd() has
+			 * cleared *pmd but not decremented compound_mapcount().
+			 */
+			if ((pvmw->flags & PVMW_SYNC) &&
+			    thp_vma_suitable_order(vma, pvmw->address,
+						   PMD_ORDER) &&
+			    (pvmw->nr_pages >= HPAGE_PMD_NR)) {
+				spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+
+				spin_unlock(ptl);
+			}
+			step_forward(pvmw, PMD_SIZE);
+			continue;
 		}
-	} else if (!pmd_present(pmde)) {
-		return false;
-	}
-	if (!map_pte(pvmw))
-		goto next_pte;
-	while (1) {
+		if (!map_pte(pvmw, &ptl)) {
+			if (!pvmw->pte)
+				goto restart;
+			goto next_pte;
+		}
+this_pte:
 		if (check_pte(pvmw))
 			return true;
 next_pte:
-		/* Seek to next pte only makes sense for THP */
-		if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
-			return not_found(pvmw);
 		do {
 			pvmw->address += PAGE_SIZE;
-			if (pvmw->address >= pvmw->vma->vm_end ||
-			    pvmw->address >=
-					__vma_address(pvmw->page, pvmw->vma) +
-					thp_size(pvmw->page))
+			if (pvmw->address >= end)
 				return not_found(pvmw);
 			/* Did we cross page table boundary? */
-			if (pvmw->address % PMD_SIZE == 0) {
-				pte_unmap(pvmw->pte);
+			if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) {
 				if (pvmw->ptl) {
 					spin_unlock(pvmw->ptl);
 					pvmw->ptl = NULL;
 				}
+				pte_unmap(pvmw->pte);
+				pvmw->pte = NULL;
 				goto restart;
-			} else {
-				pvmw->pte++;
 			}
-		} while (pte_none(*pvmw->pte));
+			pvmw->pte++;
+		} while (pte_none(ptep_get(pvmw->pte)));
 
 		if (!pvmw->ptl) {
-			pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
+			pvmw->ptl = ptl;
 			spin_lock(pvmw->ptl);
 		}
-	}
+		goto this_pte;
+	} while (pvmw->address < end);
+
+	return false;
 }
 
 /**
@@ -261,18 +326,15 @@ next_pte:
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 {
 	struct page_vma_mapped_walk pvmw = {
-		.page = page,
+		.pfn = page_to_pfn(page),
+		.nr_pages = 1,
 		.vma = vma,
 		.flags = PVMW_SYNC,
 	};
-	unsigned long start, end;
-
-	start = __vma_address(page, vma);
-	end = start + thp_size(page) - PAGE_SIZE;
 
-	if (unlikely(end < vma->vm_start || start >= vma->vm_end))
+	pvmw.address = vma_address(page, vma);
+	if (pvmw.address == -EFAULT)
 		return 0;
-	pvmw.address = max(start, vma->vm_start);
 	if (!page_vma_mapped_walk(&pvmw))
 		return 0;
 	page_vma_mapped_walk_done(&pvmw);