1 files changed, 168 insertions, 122 deletions

diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index f7b331081791..b38a1d00c971 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -3,7 +3,7 @@
 #include <linux/rmap.h>
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
-#include <linux/swapops.h>
+#include <linux/leafops.h>
 
 #include "internal.h"
 
@@ -13,110 +13,137 @@ 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, pmd_t *pmdvalp,
+		    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;
-
-				/* Handle un-addressable ZONE_DEVICE memory */
-				entry = pte_to_swp_entry(*pvmw->pte);
-				if (!is_device_private_entry(entry) &&
-				    !is_device_exclusive_entry(entry))
-					return false;
-			} else if (!pte_present(*pvmw->pte))
-				return false;
-		}
+	bool is_migration;
+	pte_t ptent;
+
+	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);
+	is_migration = pvmw->flags & PVMW_MIGRATION;
+again:
+	/*
+	 * 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_rw_nolock(pvmw->vma->vm_mm, pvmw->pmd,
+					     pvmw->address, pmdvalp, 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);
+
+	if (pte_none(ptent)) {
+		return false;
+	} else if (pte_present(ptent)) {
+		if (is_migration)
+			return false;
+	} else if (!is_migration) {
+		softleaf_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 = softleaf_from_pte(ptent);
+		if (!softleaf_is_device_private(entry) &&
+		    !softleaf_is_device_exclusive(entry))
+			return false;
+	}
+	spin_lock(*ptlp);
+	if (unlikely(!pmd_same(*pmdvalp, pmdp_get_lockless(pvmw->pmd)))) {
+		pte_unmap_unlock(pvmw->pte, *ptlp);
+		goto again;
+	}
+	pvmw->ptl = *ptlp;
 
-	/* THP can be referenced by any subpage */
-	return pfn >= page_pfn && pfn - page_pfn < thp_nr_pages(page);
+	return true;
 }
 
 /**
- * check_pte - check if @pvmw->page is mapped at the @pvmw->pte
- * @pvmw: page_vma_mapped_walk struct, includes a pair pte and page for checking
+ * 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
+ * @pte_nr: the number of small pages described by @pvmw->pte.
  *
- * 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.
  *
  * 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.
+ * [pvmw->pfn, @pvmw->pfn + @pvmw->nr_pages)
  *
  * Otherwise, return false.
  *
  */
-static bool check_pte(struct page_vma_mapped_walk *pvmw)
+static bool check_pte(struct page_vma_mapped_walk *pvmw, unsigned long pte_nr)
 {
 	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))
-			return false;
-		entry = pte_to_swp_entry(*pvmw->pte);
+		const softleaf_t entry = softleaf_from_pte(ptent);
 
-		if (!is_migration_entry(entry) &&
-		    !is_device_exclusive_entry(entry))
+		if (!softleaf_is_migration(entry))
 			return false;
 
-		pfn = swp_offset(entry);
-	} else if (is_swap_pte(*pvmw->pte)) {
-		swp_entry_t entry;
+		pfn = softleaf_to_pfn(entry);
+	} else if (pte_present(ptent)) {
+		pfn = pte_pfn(ptent);
+	} else {
+		const softleaf_t entry = softleaf_from_pte(ptent);
 
 		/* Handle un-addressable ZONE_DEVICE memory */
-		entry = pte_to_swp_entry(*pvmw->pte);
-		if (!is_device_private_entry(entry) &&
-		    !is_device_exclusive_entry(entry))
-			return false;
-
-		pfn = swp_offset(entry);
-	} else {
-		if (!pte_present(*pvmw->pte))
+		if (!softleaf_is_device_private(entry) &&
+		    !softleaf_is_device_exclusive(entry))
 			return false;
 
-		pfn = pte_pfn(*pvmw->pte);
+		pfn = softleaf_to_pfn(entry);
 	}
 
-	return pfn_is_match(pvmw->page, pfn);
+	if ((pfn + pte_nr - 1) < pvmw->pfn)
+		return false;
+	if (pfn > (pvmw->pfn + pvmw->nr_pages - 1))
+		return false;
+	return true;
+}
+
+/* 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)
@@ -127,7 +154,7 @@ static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size)
 }
 
 /**
- * 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.
@@ -152,9 +179,10 @@ static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size)
  */
 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;
@@ -164,32 +192,28 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 	if (pvmw->pmd && !pvmw->pte)
 		return not_found(pvmw);
 
-	if (unlikely(PageHuge(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);
-
-		/* when pud is not present, pte will be NULL */
-		pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page));
+		/*
+		 * 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);
-		if (!check_pte(pvmw))
+		pvmw->ptl = huge_pte_lock(hstate, mm, pvmw->pte);
+		if (!check_pte(pvmw, pages_per_huge_page(hstate)))
 			return not_found(pvmw);
 		return true;
 	}
 
-	/*
-	 * Seek to next pte only makes sense for THP.
-	 * But more important than that optimization, is to filter out
-	 * any PageKsm page: whose page->index misleads vma_address()
-	 * and vma_address_end() to disaster.
-	 */
-	end = PageTransCompound(page) ?
-		vma_address_end(page, pvmw->vma) :
-		pvmw->address + PAGE_SIZE;
+	end = vma_address_end(pvmw);
 	if (pvmw->pte)
 		goto next_pte;
 restart:
@@ -216,27 +240,28 @@ restart:
 		 * compiler and used as a stale value after we've observed a
 		 * subsequent update.
 		 */
-		pmde = READ_ONCE(*pvmw->pmd);
+		pmde = pmdp_get_lockless(pvmw->pmd);
 
-		if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
+		if (pmd_trans_huge(pmde) || pmd_is_migration_entry(pmde)) {
 			pvmw->ptl = pmd_lock(mm, pvmw->pmd);
 			pmde = *pvmw->pmd;
-			if (likely(pmd_trans_huge(pmde))) {
-				if (pvmw->flags & PVMW_MIGRATION)
-					return not_found(pvmw);
-				if (pmd_page(pmde) != page)
-					return not_found(pvmw);
-				return true;
-			}
 			if (!pmd_present(pmde)) {
-				swp_entry_t entry;
+				softleaf_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) ||
-				    pfn_swap_entry_to_page(entry) != page)
+				entry = softleaf_from_pmd(pmde);
+
+				if (!softleaf_is_migration(entry) ||
+				    !check_pmd(softleaf_to_pfn(entry), pvmw))
+					return not_found(pvmw);
+				return true;
+			}
+			if (likely(pmd_trans_huge(pmde))) {
+				if (pvmw->flags & PVMW_MIGRATION)
+					return not_found(pvmw);
+				if (!check_pmd(pmd_pfn(pmde), pvmw))
 					return not_found(pvmw);
 				return true;
 			}
@@ -249,8 +274,17 @@ restart:
 			 * cannot return prematurely, while zap_huge_pmd() has
 			 * cleared *pmd but not decremented compound_mapcount().
 			 */
+			const softleaf_t entry = softleaf_from_pmd(pmde);
+
+			if (softleaf_is_device_private(entry)) {
+				pvmw->ptl = pmd_lock(mm, pvmw->pmd);
+				return true;
+			}
+
 			if ((pvmw->flags & PVMW_SYNC) &&
-			    PageTransCompound(page)) {
+			    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);
@@ -258,10 +292,13 @@ restart:
 			step_forward(pvmw, PMD_SIZE);
 			continue;
 		}
-		if (!map_pte(pvmw))
+		if (!map_pte(pvmw, &pmde, &ptl)) {
+			if (!pvmw->pte)
+				goto restart;
 			goto next_pte;
+		}
 this_pte:
-		if (check_pte(pvmw))
+		if (check_pte(pvmw, 1))
 			return true;
 next_pte:
 		do {
@@ -276,18 +313,20 @@ next_pte:
 				}
 				pte_unmap(pvmw->pte);
 				pvmw->pte = NULL;
+				pvmw->flags |= PVMW_PGTABLE_CROSSED;
 				goto restart;
 			}
 			pvmw->pte++;
-			if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) {
-				pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
-				spin_lock(pvmw->ptl);
-			}
-		} while (pte_none(*pvmw->pte));
+		} while (pte_none(ptep_get(pvmw->pte)));
 
 		if (!pvmw->ptl) {
-			pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
-			spin_lock(pvmw->ptl);
+			spin_lock(ptl);
+			if (unlikely(!pmd_same(pmde, pmdp_get_lockless(pvmw->pmd)))) {
+				pte_unmap_unlock(pvmw->pte, ptl);
+				pvmw->pte = NULL;
+				goto restart;
+			}
+			pvmw->ptl = ptl;
 		}
 		goto this_pte;
 	} while (pvmw->address < end);
@@ -295,28 +334,35 @@ next_pte:
 	return false;
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
 /**
  * page_mapped_in_vma - check whether a page is really mapped in a VMA
  * @page: the page to test
  * @vma: the VMA to test
  *
- * Returns 1 if the page is mapped into the page tables of the VMA, 0
- * if the page is not mapped into the page tables of this VMA.  Only
- * valid for normal file or anonymous VMAs.
+ * Return: The address the page is mapped at if the page is in the range
+ * covered by the VMA and present in the page table.  If the page is
+ * outside the VMA or not present, returns -EFAULT.
+ * Only valid for normal file or anonymous VMAs.
  */
-int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+unsigned long page_mapped_in_vma(const struct page *page,
+		struct vm_area_struct *vma)
 {
+	const struct folio *folio = page_folio(page);
 	struct page_vma_mapped_walk pvmw = {
-		.page = page,
+		.pfn = page_to_pfn(page),
+		.nr_pages = 1,
 		.vma = vma,
 		.flags = PVMW_SYNC,
 	};
 
-	pvmw.address = vma_address(page, vma);
+	pvmw.address = vma_address(vma, page_pgoff(folio, page), 1);
 	if (pvmw.address == -EFAULT)
-		return 0;
+		goto out;
 	if (!page_vma_mapped_walk(&pvmw))
-		return 0;
+		return -EFAULT;
 	page_vma_mapped_walk_done(&pvmw);
-	return 1;
+out:
+	return pvmw.address;
 }
+#endif