mm: Convert page_vma_mapped_walk to work on PFNs

page_mapped_in_vma() really just wants to walk one page, but as the
code stands, if passed the head page of a compound page, it will
walk every page in the compound page.  Extract pfn/nr_pages/pgoff
from the struct page early, so they can be overridden by
page_mapped_in_vma().

Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>

Author: Matthew Wilcox (Oracle)

include/linux/hugetlb.h

@@ -970,6 +970,11 @@ static inline struct hstate *page_hstate(struct page *page)
 	return NULL;
 }
 
+static inline struct hstate *size_to_hstate(unsigned long size)
+{
+	return NULL;
+}
+
 static inline unsigned long huge_page_size(struct hstate *h)
 {
 	return PAGE_SIZE;

include/linux/rmap.h

@@ -11,6 +11,7 @@
 #include <linux/rwsem.h>
 #include <linux/memcontrol.h>
 #include <linux/highmem.h>
+#include <linux/pagemap.h>
 
 /*
  * The anon_vma heads a list of private "related" vmas, to scan if
@@ -201,11 +202,13 @@ int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
 
 /* Avoid racy checks */
 #define PVMW_SYNC		(1 << 0)
-/* Look for migarion entries rather than present PTEs */
+/* Look for migration entries rather than present PTEs */
 #define PVMW_MIGRATION		(1 << 1)
 
 struct page_vma_mapped_walk {
-	struct page *page;
+	unsigned long pfn;
+	unsigned long nr_pages;
+	pgoff_t pgoff;
 	struct vm_area_struct *vma;
 	unsigned long address;
 	pmd_t *pmd;
@@ -216,15 +219,19 @@ struct page_vma_mapped_walk {
 
 #define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags)	\
 	struct page_vma_mapped_walk name = {				\
-		.page = _page,						\
+		.pfn = page_to_pfn(_page),				\
+		.nr_pages = compound_nr(page),				\
+		.pgoff = page_to_pgoff(page),				\
 		.vma = _vma,						\
 		.address = _address,					\
 		.flags = _flags,					\
 	}
 
 #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags)	\
 	struct page_vma_mapped_walk name = {				\
-		.page = &_folio->page,					\
+		.pfn = folio_pfn(_folio),				\
+		.nr_pages = folio_nr_pages(_folio),			\
+		.pgoff = folio_pgoff(_folio),				\
 		.vma = _vma,						\
 		.address = _address,					\
 		.flags = _flags,					\
@@ -233,7 +240,7 @@ struct page_vma_mapped_walk {
 static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw)
 {
 	/* HugeTLB pte is set to the relevant page table entry without pte_mapped. */
-	if (pvmw->pte && !PageHuge(pvmw->page))
+	if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma))
 		pte_unmap(pvmw->pte);
 	if (pvmw->ptl)
 		spin_unlock(pvmw->ptl);

mm/internal.h

@@ -10,6 +10,7 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
+#include <linux/rmap.h>
 #include <linux/tracepoint-defs.h>
 
 struct folio_batch;
@@ -475,18 +476,20 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 }
 
 /*
- * Then at what user virtual address will none of the page be found in vma?
+ * Then at what user virtual address will none of the range be found in vma?
  * Assumes that vma_address() already returned a good starting address.
- * If page is a compound head, the entire compound page is considered.
  */
-static inline unsigned long
-vma_address_end(struct page *page, struct vm_area_struct *vma)
+static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw)
 {
+	struct vm_area_struct *vma = pvmw->vma;
 	pgoff_t pgoff;
 	unsigned long address;
 
-	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
-	pgoff = page_to_pgoff(page) + compound_nr(page);
+	/* Common case, plus ->pgoff is invalid for KSM */
+	if (pvmw->nr_pages == 1)
+		return pvmw->address + PAGE_SIZE;
+
+	pgoff = pvmw->pgoff + pvmw->nr_pages;
 	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 	/* Check for address beyond vma (or wrapped through 0?) */
 	if (address < vma->vm_start || address > vma->vm_end)

mm/migrate.c

@@ -174,7 +174,8 @@ void putback_movable_pages(struct list_head *l)
 static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 				 unsigned long addr, void *old)
 {
-	DEFINE_PAGE_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION);
+	DEFINE_PAGE_VMA_WALK(pvmw, (struct page *)old, vma, addr,
+				PVMW_SYNC | PVMW_MIGRATION);
 	struct page *new;
 	pte_t pte;
 	swp_entry_t entry;
@@ -184,7 +185,7 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 		if (PageKsm(page))
 			new = page;
 		else
-			new = page - pvmw.page->index +
+			new = page - pvmw.pgoff +
 				linear_page_index(vma, pvmw.address);
 
 #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION

mm/page_vma_mapped.c

@@ -53,18 +53,6 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw)
 	return true;
 }
 
-static inline bool pfn_is_match(struct page *page, unsigned long pfn)
-{
-	unsigned long page_pfn = page_to_pfn(page);
-
-	/* normal page and hugetlbfs page */
-	if (!PageTransCompound(page) || PageHuge(page))
-		return page_pfn == pfn;
-
-	/* THP can be referenced by any subpage */
-	return pfn >= page_pfn && pfn - page_pfn < thp_nr_pages(page);
-}
-
 /**
  * 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
@@ -116,7 +104,17 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
 		pfn = pte_pfn(*pvmw->pte);
 	}
 
-	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)
@@ -127,7 +125,7 @@ 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.
@@ -152,8 +150,8 @@ 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;
 	pgd_t *pgd;
 	p4d_t *p4d;
@@ -164,32 +162,26 @@ 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))) {
+		unsigned long size = pvmw->nr_pages * PAGE_SIZE;
 		/* 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));
+		pvmw->pte = huge_pte_offset(mm, pvmw->address, size);
 		if (!pvmw->pte)
 			return false;
 
-		pvmw->ptl = huge_pte_lockptr(page_hstate(page), mm, pvmw->pte);
+		pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm,
+						pvmw->pte);
 		spin_lock(pvmw->ptl);
 		if (!check_pte(pvmw))
 			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:
@@ -224,7 +216,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 			if (likely(pmd_trans_huge(pmde))) {
 				if (pvmw->flags & PVMW_MIGRATION)
 					return not_found(pvmw);
-				if (pmd_page(pmde) != page)
+				if (!check_pmd(pmd_pfn(pmde), pvmw))
 					return not_found(pvmw);
 				return true;
 			}
@@ -236,7 +228,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 					return not_found(pvmw);
 				entry = pmd_to_swp_entry(pmde);
 				if (!is_migration_entry(entry) ||
-				    pfn_swap_entry_to_page(entry) != page)
+				    !check_pmd(swp_offset(entry), pvmw))
 					return not_found(pvmw);
 				return true;
 			}
@@ -250,7 +242,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 			 * cleared *pmd but not decremented compound_mapcount().
 			 */
 			if ((pvmw->flags & PVMW_SYNC) &&
-			    PageTransCompound(page)) {
+			    transparent_hugepage_active(vma) &&
+			    (pvmw->nr_pages >= HPAGE_PMD_NR)) {
 				spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
 
 				spin_unlock(ptl);
@@ -307,7 +300,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
 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,
 	};

mm/rmap.c

@@ -940,7 +940,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
 	 */
 	mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE,
 				0, vma, vma->vm_mm, address,
-				vma_address_end(page, vma));
+				vma_address_end(&pvmw));
 	mmu_notifier_invalidate_range_start(&range);
 
 	while (page_vma_mapped_walk(&pvmw)) {
@@ -1437,8 +1437,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	 * Note that the page can not be free in this function as call of
 	 * try_to_unmap() must hold a reference on the page.
 	 */
-	range.end = PageKsm(page) ?
-			address + PAGE_SIZE : vma_address_end(page, vma);
+	range.end = vma_address_end(&pvmw);
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
 				address, range.end);
 	if (PageHuge(page)) {
@@ -1732,8 +1731,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
 	 * Note that the page can not be free in this function as call of
 	 * try_to_unmap() must hold a reference on the page.
 	 */
-	range.end = PageKsm(page) ?
-			address + PAGE_SIZE : vma_address_end(page, vma);
+	range.end = vma_address_end(&pvmw);
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm,
 				address, range.end);
 	if (PageHuge(page)) {