diff mbox series

[2/2] mm: Convert page_vma_mapped_walk to work on PFNs

Message ID 20220203171904.609984-2-willy@infradead.org (mailing list archive)
State New
Headers show
Series [1/2] mm: Add pvmw_set_page() | expand

Commit Message

Matthew Wilcox Feb. 3, 2022, 5:19 p.m. UTC 
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) <willy@infradead.org>
---
 include/linux/hugetlb.h |  5 ++++
 include/linux/rmap.h    | 13 +++++++---
 mm/internal.h           | 15 ++++++-----
 mm/migrate.c            |  2 +-
 mm/page_vma_mapped.c    | 57 ++++++++++++++++++-----------------------
 mm/rmap.c               |  8 +++---
 6 files changed, 52 insertions(+), 48 deletions(-)

Comments

kernel test robot Feb. 4, 2022, 1:30 a.m. UTC | #1 
Hi "Matthew,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on tip/perf/core v5.17-rc2 next-20220203]
[cannot apply to hnaz-mm/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Matthew-Wilcox-Oracle/mm-Add-pvmw_set_page/20220204-012111
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git c36c04c2e132fc39f6b658bf607aed4425427fd7
config: riscv-randconfig-r042-20220131 (https://download.01.org/0day-ci/archive/20220204/202202040625.ZAq9Op2f-lkp@intel.com/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project a73e4ce6a59b01f0e37037761c1e6889d539d233)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install riscv cross compiling tool for clang build
        # apt-get install binutils-riscv64-linux-gnu
        # https://github.com/0day-ci/linux/commit/4a5a2cece4c5d9ac56322c6828efbea7fcd2e480
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Matthew-Wilcox-Oracle/mm-Add-pvmw_set_page/20220204-012111
        git checkout 4a5a2cece4c5d9ac56322c6828efbea7fcd2e480
        # save the config file to linux build tree
        mkdir build_dir
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=riscv SHELL=/bin/bash

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

>> mm/page_vma_mapped.c:245:27: error: call to __compiletime_assert_255 declared with 'error' attribute: BUILD_BUG failed
                               (pvmw->nr_pages >= HPAGE_PMD_NR)) {
                                                  ^
   include/linux/huge_mm.h:105:26: note: expanded from macro 'HPAGE_PMD_NR'
   #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
                            ^
   include/linux/huge_mm.h:104:26: note: expanded from macro 'HPAGE_PMD_ORDER'
   #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
                            ^
   include/linux/huge_mm.h:331:28: note: expanded from macro 'HPAGE_PMD_SHIFT'
   #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
                              ^
   note: (skipping 3 expansions in backtrace; use -fmacro-backtrace-limit=0 to see all)
   include/linux/compiler_types.h:334:2: note: expanded from macro '_compiletime_assert'
           __compiletime_assert(condition, msg, prefix, suffix)
           ^
   include/linux/compiler_types.h:327:4: note: expanded from macro '__compiletime_assert'
                           prefix ## suffix();                             \
                           ^
   <scratch space>:161:1: note: expanded from here
   __compiletime_assert_255
   ^
   1 error generated.


vim +/error +245 mm/page_vma_mapped.c

   126	
   127	/**
   128	 * page_vma_mapped_walk - check if @pvmw->pfn is mapped in @pvmw->vma at
   129	 * @pvmw->address
   130	 * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags
   131	 * must be set. pmd, pte and ptl must be NULL.
   132	 *
   133	 * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point
   134	 * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is
   135	 * adjusted if needed (for PTE-mapped THPs).
   136	 *
   137	 * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page
   138	 * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in
   139	 * a loop to find all PTEs that map the THP.
   140	 *
   141	 * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry
   142	 * regardless of which page table level the page is mapped at. @pvmw->pmd is
   143	 * NULL.
   144	 *
   145	 * Returns false if there are no more page table entries for the page in
   146	 * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped.
   147	 *
   148	 * If you need to stop the walk before page_vma_mapped_walk() returned false,
   149	 * use page_vma_mapped_walk_done(). It will do the housekeeping.
   150	 */
   151	bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
   152	{
   153		struct vm_area_struct *vma = pvmw->vma;
   154		struct mm_struct *mm = vma->vm_mm;
   155		unsigned long end;
   156		pgd_t *pgd;
   157		p4d_t *p4d;
   158		pud_t *pud;
   159		pmd_t pmde;
   160	
   161		/* The only possible pmd mapping has been handled on last iteration */
   162		if (pvmw->pmd && !pvmw->pte)
   163			return not_found(pvmw);
   164	
   165		if (unlikely(is_vm_hugetlb_page(vma))) {
   166			unsigned long size = pvmw->nr_pages * PAGE_SIZE;
   167			/* The only possible mapping was handled on last iteration */
   168			if (pvmw->pte)
   169				return not_found(pvmw);
   170	
   171			/* when pud is not present, pte will be NULL */
   172			pvmw->pte = huge_pte_offset(mm, pvmw->address, size);
   173			if (!pvmw->pte)
   174				return false;
   175	
   176			pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm,
   177							pvmw->pte);
   178			spin_lock(pvmw->ptl);
   179			if (!check_pte(pvmw))
   180				return not_found(pvmw);
   181			return true;
   182		}
   183	
   184		end = vma_address_end(pvmw);
   185		if (pvmw->pte)
   186			goto next_pte;
   187	restart:
   188		do {
   189			pgd = pgd_offset(mm, pvmw->address);
   190			if (!pgd_present(*pgd)) {
   191				step_forward(pvmw, PGDIR_SIZE);
   192				continue;
   193			}
   194			p4d = p4d_offset(pgd, pvmw->address);
   195			if (!p4d_present(*p4d)) {
   196				step_forward(pvmw, P4D_SIZE);
   197				continue;
   198			}
   199			pud = pud_offset(p4d, pvmw->address);
   200			if (!pud_present(*pud)) {
   201				step_forward(pvmw, PUD_SIZE);
   202				continue;
   203			}
   204	
   205			pvmw->pmd = pmd_offset(pud, pvmw->address);
   206			/*
   207			 * Make sure the pmd value isn't cached in a register by the
   208			 * compiler and used as a stale value after we've observed a
   209			 * subsequent update.
   210			 */
   211			pmde = READ_ONCE(*pvmw->pmd);
   212	
   213			if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
   214				pvmw->ptl = pmd_lock(mm, pvmw->pmd);
   215				pmde = *pvmw->pmd;
   216				if (likely(pmd_trans_huge(pmde))) {
   217					if (pvmw->flags & PVMW_MIGRATION)
   218						return not_found(pvmw);
   219					if (!check_pmd(pmd_pfn(pmde), pvmw))
   220						return not_found(pvmw);
   221					return true;
   222				}
   223				if (!pmd_present(pmde)) {
   224					swp_entry_t entry;
   225	
   226					if (!thp_migration_supported() ||
   227					    !(pvmw->flags & PVMW_MIGRATION))
   228						return not_found(pvmw);
   229					entry = pmd_to_swp_entry(pmde);
   230					if (!is_migration_entry(entry) ||
   231					    !check_pmd(swp_offset(entry), pvmw))
   232						return not_found(pvmw);
   233					return true;
   234				}
   235				/* THP pmd was split under us: handle on pte level */
   236				spin_unlock(pvmw->ptl);
   237				pvmw->ptl = NULL;
   238			} else if (!pmd_present(pmde)) {
   239				/*
   240				 * If PVMW_SYNC, take and drop THP pmd lock so that we
   241				 * cannot return prematurely, while zap_huge_pmd() has
   242				 * cleared *pmd but not decremented compound_mapcount().
   243				 */
   244				if ((pvmw->flags & PVMW_SYNC) &&
 > 245				    (pvmw->nr_pages >= HPAGE_PMD_NR)) {
   246					spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
   247	
   248					spin_unlock(ptl);
   249				}
   250				step_forward(pvmw, PMD_SIZE);
   251				continue;
   252			}
   253			if (!map_pte(pvmw))
   254				goto next_pte;
   255	this_pte:
   256			if (check_pte(pvmw))
   257				return true;
   258	next_pte:
   259			do {
   260				pvmw->address += PAGE_SIZE;
   261				if (pvmw->address >= end)
   262					return not_found(pvmw);
   263				/* Did we cross page table boundary? */
   264				if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) {
   265					if (pvmw->ptl) {
   266						spin_unlock(pvmw->ptl);
   267						pvmw->ptl = NULL;
   268					}
   269					pte_unmap(pvmw->pte);
   270					pvmw->pte = NULL;
   271					goto restart;
   272				}
   273				pvmw->pte++;
   274				if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) {
   275					pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
   276					spin_lock(pvmw->ptl);
   277				}
   278			} while (pte_none(*pvmw->pte));
   279	
   280			if (!pvmw->ptl) {
   281				pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
   282				spin_lock(pvmw->ptl);
   283			}
   284			goto this_pte;
   285		} while (pvmw->address < end);
   286	
   287		return false;
   288	}
   289	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
kernel test robot Feb. 4, 2022, 1:30 a.m. UTC | #2 
Hi "Matthew,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on tip/perf/core v5.17-rc2 next-20220203]
[cannot apply to hnaz-mm/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Matthew-Wilcox-Oracle/mm-Add-pvmw_set_page/20220204-012111
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git c36c04c2e132fc39f6b658bf607aed4425427fd7
config: hexagon-randconfig-r045-20220130 (https://download.01.org/0day-ci/archive/20220204/202202040601.7rVVBoVe-lkp@intel.com/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project a73e4ce6a59b01f0e37037761c1e6889d539d233)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/0day-ci/linux/commit/4a5a2cece4c5d9ac56322c6828efbea7fcd2e480
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Matthew-Wilcox-Oracle/mm-Add-pvmw_set_page/20220204-012111
        git checkout 4a5a2cece4c5d9ac56322c6828efbea7fcd2e480
        # save the config file to linux build tree
        mkdir build_dir
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=hexagon SHELL=/bin/bash

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

>> mm/page_vma_mapped.c:219:20: error: implicit declaration of function 'pmd_pfn' [-Werror,-Wimplicit-function-declaration]
                                   if (!check_pmd(pmd_pfn(pmde), pvmw))
                                                  ^
   mm/page_vma_mapped.c:219:20: note: did you mean 'pmd_off'?
   include/linux/pgtable.h:149:22: note: 'pmd_off' declared here
   static inline pmd_t *pmd_off(struct mm_struct *mm, unsigned long va)
                        ^
   1 error generated.


vim +/pmd_pfn +219 mm/page_vma_mapped.c

   126	
   127	/**
   128	 * page_vma_mapped_walk - check if @pvmw->pfn is mapped in @pvmw->vma at
   129	 * @pvmw->address
   130	 * @pvmw: pointer to struct page_vma_mapped_walk. page, vma, address and flags
   131	 * must be set. pmd, pte and ptl must be NULL.
   132	 *
   133	 * Returns true if the page is mapped in the vma. @pvmw->pmd and @pvmw->pte point
   134	 * to relevant page table entries. @pvmw->ptl is locked. @pvmw->address is
   135	 * adjusted if needed (for PTE-mapped THPs).
   136	 *
   137	 * If @pvmw->pmd is set but @pvmw->pte is not, you have found PMD-mapped page
   138	 * (usually THP). For PTE-mapped THP, you should run page_vma_mapped_walk() in
   139	 * a loop to find all PTEs that map the THP.
   140	 *
   141	 * For HugeTLB pages, @pvmw->pte is set to the relevant page table entry
   142	 * regardless of which page table level the page is mapped at. @pvmw->pmd is
   143	 * NULL.
   144	 *
   145	 * Returns false if there are no more page table entries for the page in
   146	 * the vma. @pvmw->ptl is unlocked and @pvmw->pte is unmapped.
   147	 *
   148	 * If you need to stop the walk before page_vma_mapped_walk() returned false,
   149	 * use page_vma_mapped_walk_done(). It will do the housekeeping.
   150	 */
   151	bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
   152	{
   153		struct vm_area_struct *vma = pvmw->vma;
   154		struct mm_struct *mm = vma->vm_mm;
   155		unsigned long end;
   156		pgd_t *pgd;
   157		p4d_t *p4d;
   158		pud_t *pud;
   159		pmd_t pmde;
   160	
   161		/* The only possible pmd mapping has been handled on last iteration */
   162		if (pvmw->pmd && !pvmw->pte)
   163			return not_found(pvmw);
   164	
   165		if (unlikely(is_vm_hugetlb_page(vma))) {
   166			unsigned long size = pvmw->nr_pages * PAGE_SIZE;
   167			/* The only possible mapping was handled on last iteration */
   168			if (pvmw->pte)
   169				return not_found(pvmw);
   170	
   171			/* when pud is not present, pte will be NULL */
   172			pvmw->pte = huge_pte_offset(mm, pvmw->address, size);
   173			if (!pvmw->pte)
   174				return false;
   175	
   176			pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm,
   177							pvmw->pte);
   178			spin_lock(pvmw->ptl);
   179			if (!check_pte(pvmw))
   180				return not_found(pvmw);
   181			return true;
   182		}
   183	
   184		end = vma_address_end(pvmw);
   185		if (pvmw->pte)
   186			goto next_pte;
   187	restart:
   188		do {
   189			pgd = pgd_offset(mm, pvmw->address);
   190			if (!pgd_present(*pgd)) {
   191				step_forward(pvmw, PGDIR_SIZE);
   192				continue;
   193			}
   194			p4d = p4d_offset(pgd, pvmw->address);
   195			if (!p4d_present(*p4d)) {
   196				step_forward(pvmw, P4D_SIZE);
   197				continue;
   198			}
   199			pud = pud_offset(p4d, pvmw->address);
   200			if (!pud_present(*pud)) {
   201				step_forward(pvmw, PUD_SIZE);
   202				continue;
   203			}
   204	
   205			pvmw->pmd = pmd_offset(pud, pvmw->address);
   206			/*
   207			 * Make sure the pmd value isn't cached in a register by the
   208			 * compiler and used as a stale value after we've observed a
   209			 * subsequent update.
   210			 */
   211			pmde = READ_ONCE(*pvmw->pmd);
   212	
   213			if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
   214				pvmw->ptl = pmd_lock(mm, pvmw->pmd);
   215				pmde = *pvmw->pmd;
   216				if (likely(pmd_trans_huge(pmde))) {
   217					if (pvmw->flags & PVMW_MIGRATION)
   218						return not_found(pvmw);
 > 219					if (!check_pmd(pmd_pfn(pmde), pvmw))
   220						return not_found(pvmw);
   221					return true;
   222				}
   223				if (!pmd_present(pmde)) {
   224					swp_entry_t entry;
   225	
   226					if (!thp_migration_supported() ||
   227					    !(pvmw->flags & PVMW_MIGRATION))
   228						return not_found(pvmw);
   229					entry = pmd_to_swp_entry(pmde);
   230					if (!is_migration_entry(entry) ||
   231					    !check_pmd(swp_offset(entry), pvmw))
   232						return not_found(pvmw);
   233					return true;
   234				}
   235				/* THP pmd was split under us: handle on pte level */
   236				spin_unlock(pvmw->ptl);
   237				pvmw->ptl = NULL;
   238			} else if (!pmd_present(pmde)) {
   239				/*
   240				 * If PVMW_SYNC, take and drop THP pmd lock so that we
   241				 * cannot return prematurely, while zap_huge_pmd() has
   242				 * cleared *pmd but not decremented compound_mapcount().
   243				 */
   244				if ((pvmw->flags & PVMW_SYNC) &&
   245				    (pvmw->nr_pages >= HPAGE_PMD_NR)) {
   246					spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
   247	
   248					spin_unlock(ptl);
   249				}
   250				step_forward(pvmw, PMD_SIZE);
   251				continue;
   252			}
   253			if (!map_pte(pvmw))
   254				goto next_pte;
   255	this_pte:
   256			if (check_pte(pvmw))
   257				return true;
   258	next_pte:
   259			do {
   260				pvmw->address += PAGE_SIZE;
   261				if (pvmw->address >= end)
   262					return not_found(pvmw);
   263				/* Did we cross page table boundary? */
   264				if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) {
   265					if (pvmw->ptl) {
   266						spin_unlock(pvmw->ptl);
   267						pvmw->ptl = NULL;
   268					}
   269					pte_unmap(pvmw->pte);
   270					pvmw->pte = NULL;
   271					goto restart;
   272				}
   273				pvmw->pte++;
   274				if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) {
   275					pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
   276					spin_lock(pvmw->ptl);
   277				}
   278			} while (pte_none(*pvmw->pte));
   279	
   280			if (!pvmw->ptl) {
   281				pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
   282				spin_lock(pvmw->ptl);
   283			}
   284			goto this_pte;
   285		} while (pvmw->address < end);
   286	
   287		return false;
   288	}
   289	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff mbox series

Patch

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d1897a69c540..6ba2f8e74fbb 100644
--- a/include/linux/hugetlb.h
+++ b/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;
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 003bb5775bb1..6c0ebbd96e95 100644
--- a/include/linux/rmap.h
+++ b/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
@@ -200,11 +201,13 @@  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;
@@ -216,13 +219,15 @@  struct page_vma_mapped_walk {
 static inline void pvmw_set_page(struct page_vma_mapped_walk *pvmw,
 		struct page *page)
 {
-	pvmw->page = page;
+	pvmw->pfn = page_to_pfn(page);
+	pvmw->nr_pages = compound_nr(page);
+	pvmw->pgoff = page_to_pgoff(page);
 }
 
 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);
diff --git a/mm/internal.h b/mm/internal.h
index b7a2195c12b1..7f1db0f1a8bc 100644
--- a/mm/internal.h
+++ b/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;
@@ -459,18 +460,20 @@  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)
diff --git a/mm/migrate.c b/mm/migrate.c
index 07464fd45925..766dc67874a1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -191,7 +191,7 @@  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
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index f7b331081791..228d5103e6d1 100644
--- a/mm/page_vma_mapped.c
+++ b/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 +242,7 @@  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)) {
+			    (pvmw->nr_pages >= HPAGE_PMD_NR)) {
 				spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
 
 				spin_unlock(ptl);
@@ -307,7 +299,8 @@  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,
 	};
diff --git a/mm/rmap.c b/mm/rmap.c
index fa8478372e94..d62a6fcef318 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -946,7 +946,7 @@  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)) {
@@ -1453,8 +1453,7 @@  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)) {
@@ -1757,8 +1756,7 @@  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)) {