[patch 01/24] mm: page_vma_mapped_walk(): use page for pvmw->page

[patch 01/24] mm: page_vma_mapped_walk(): use page for pvmw->page

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): use page for pvmw->page

Patch series "mm: page_vma_mapped_walk() cleanup and THP fixes".

I've marked all of these for stable: many are merely cleanups,
but I think they are much better before the main fix than after.


This patch (of 11):

page_vma_mapped_walk() cleanup: sometimes the local copy of pvwm->page was
used, sometimes pvmw->page itself: use the local copy "page" throughout.

Link: https://lkml.kernel.org/r/589b358c-febc-c88e-d4c2-7834b37fa7bf@google.com
Link: https://lkml.kernel.org/r/88e67645-f467-c279-bf5e-af4b5c6b13eb@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Will Deacon <will@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |    9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-use-page-for-pvmw-page
+++ a/mm/page_vma_mapped.c
@@ -156,7 +156,7 @@ bool page_vma_mapped_walk(struct page_vm
 	if (pvmw->pte)
 		goto next_pte;
 
-	if (unlikely(PageHuge(pvmw->page))) {
+	if (unlikely(PageHuge(page))) {
 		/* when pud is not present, pte will be NULL */
 		pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page));
 		if (!pvmw->pte)
@@ -217,8 +217,7 @@ restart:
 		 * cannot return prematurely, while zap_huge_pmd() has
 		 * cleared *pmd but not decremented compound_mapcount().
 		 */
-		if ((pvmw->flags & PVMW_SYNC) &&
-		    PageTransCompound(pvmw->page)) {
+		if ((pvmw->flags & PVMW_SYNC) && PageTransCompound(page)) {
 			spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
 
 			spin_unlock(ptl);
@@ -234,9 +233,9 @@ restart:
 			return true;
 next_pte:
 		/* Seek to next pte only makes sense for THP */
-		if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
+		if (!PageTransHuge(page) || PageHuge(page))
 			return not_found(pvmw);
-		end = vma_address_end(pvmw->page, pvmw->vma);
+		end = vma_address_end(page, pvmw->vma);
 		do {
 			pvmw->address += PAGE_SIZE;
 			if (pvmw->address >= end)
_

[patch 02/24] mm: page_vma_mapped_walk(): settle PageHuge on entry

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): settle PageHuge on entry

page_vma_mapped_walk() cleanup: get the hugetlbfs PageHuge case out of the
way at the start, so no need to worry about it later.

Link: https://lkml.kernel.org/r/e31a483c-6d73-a6bb-26c5-43c3b880a2@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-settle-pagehuge-on-entry
+++ a/mm/page_vma_mapped.c
@@ -153,10 +153,11 @@ bool page_vma_mapped_walk(struct page_vm
 	if (pvmw->pmd && !pvmw->pte)
 		return not_found(pvmw);
 
-	if (pvmw->pte)
-		goto next_pte;
-
 	if (unlikely(PageHuge(page))) {
+		/* 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));
 		if (!pvmw->pte)
@@ -168,6 +169,9 @@ bool page_vma_mapped_walk(struct page_vm
 			return not_found(pvmw);
 		return true;
 	}
+
+	if (pvmw->pte)
+		goto next_pte;
 restart:
 	pgd = pgd_offset(mm, pvmw->address);
 	if (!pgd_present(*pgd))
@@ -233,7 +237,7 @@ restart:
 			return true;
 next_pte:
 		/* Seek to next pte only makes sense for THP */
-		if (!PageTransHuge(page) || PageHuge(page))
+		if (!PageTransHuge(page))
 			return not_found(pvmw);
 		end = vma_address_end(page, pvmw->vma);
 		do {
_

[patch 03/24] mm: page_vma_mapped_walk(): use pmde for *pvmw->pmd

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): use pmde for *pvmw->pmd

page_vma_mapped_walk() cleanup: re-evaluate pmde after taking lock, then
use it in subsequent tests, instead of repeatedly dereferencing pointer.

Link: https://lkml.kernel.org/r/53fbc9d-891e-46b2-cb4b-468c3b19238e@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |   11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-use-pmde-for-pvmw-pmd
+++ a/mm/page_vma_mapped.c
@@ -191,18 +191,19 @@ restart:
 	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))) {
+		pmde = *pvmw->pmd;
+		if (likely(pmd_trans_huge(pmde))) {
 			if (pvmw->flags & PVMW_MIGRATION)
 				return not_found(pvmw);
-			if (pmd_page(*pvmw->pmd) != page)
+			if (pmd_page(pmde) != page)
 				return not_found(pvmw);
 			return true;
-		} else if (!pmd_present(*pvmw->pmd)) {
+		} else if (!pmd_present(pmde)) {
 			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);
+				if (is_migration_entry(pmd_to_swp_entry(pmde))) {
+					swp_entry_t entry = pmd_to_swp_entry(pmde);
 
 					if (migration_entry_to_page(entry) != page)
 						return not_found(pvmw);
_

[patch 04/24] mm: page_vma_mapped_walk(): prettify PVMW_MIGRATION block

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): prettify PVMW_MIGRATION block

page_vma_mapped_walk() cleanup: rearrange the !pmd_present() block to
follow the same "return not_found, return not_found, return true" pattern
as the block above it (note: returning not_found there is never premature,
since existence or prior existence of huge pmd guarantees good alignment).

Link: https://lkml.kernel.org/r/378c8650-1488-2edf-9647-32a53cf2e21@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |   30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-prettify-pvmw_migration-block
+++ a/mm/page_vma_mapped.c
@@ -198,24 +198,22 @@ restart:
 			if (pmd_page(pmde) != page)
 				return not_found(pvmw);
 			return true;
-		} else if (!pmd_present(pmde)) {
-			if (thp_migration_supported()) {
-				if (!(pvmw->flags & PVMW_MIGRATION))
-					return not_found(pvmw);
-				if (is_migration_entry(pmd_to_swp_entry(pmde))) {
-					swp_entry_t entry = pmd_to_swp_entry(pmde);
+		}
+		if (!pmd_present(pmde)) {
+			swp_entry_t entry;
 
-					if (migration_entry_to_page(entry) != page)
-						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;
+			if (!thp_migration_supported() ||
+			    !(pvmw->flags & PVMW_MIGRATION))
+				return not_found(pvmw);
+			entry = pmd_to_swp_entry(pmde);
+			if (!is_migration_entry(entry) ||
+			    migration_entry_to_page(entry) != page)
+				return not_found(pvmw);
+			return true;
 		}
+		/* 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
_

[patch 05/24] mm: page_vma_mapped_walk(): crossing page table boundary

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): crossing page table boundary

page_vma_mapped_walk() cleanup: adjust the test for crossing page table
boundary - I believe pvmw->address is always page-aligned, but nothing
else here assumed that; and remember to reset pvmw->pte to NULL after
unmapping the page table, though I never saw any bug from that.

Link: https://lkml.kernel.org/r/799b3f9c-2a9e-dfef-5d89-26e9f76fd97@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-crossing-page-table-boundary
+++ a/mm/page_vma_mapped.c
@@ -244,16 +244,16 @@ next_pte:
 			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++;
 			}
+			pvmw->pte++;
 		} while (pte_none(*pvmw->pte));
 
 		if (!pvmw->ptl) {
_

[patch 06/24] mm: page_vma_mapped_walk(): add a level of indentation

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): add a level of indentation

page_vma_mapped_walk() cleanup: add a level of indentation to much of the
body, making no functional change in this commit, but reducing the later
diff when this is all converted to a loop.

[hughd@google.com: : page_vma_mapped_walk(): add a level of indentation fix]
  Link: https://lkml.kernel.org/r/7f817555-3ce1-c785-e438-87d8efdcaf26@google.com
Link: https://lkml.kernel.org/r/efde211-f3e2-fe54-977-ef481419e7f3@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |  105 +++++++++++++++++++++--------------------
 1 file changed, 55 insertions(+), 50 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-add-a-level-of-indentation
+++ a/mm/page_vma_mapped.c
@@ -173,62 +173,67 @@ bool page_vma_mapped_walk(struct page_vm
 	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);
-		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;
+	{
+		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;
 
-			if (!thp_migration_supported() ||
-			    !(pvmw->flags & PVMW_MIGRATION))
-				return not_found(pvmw);
-			entry = pmd_to_swp_entry(pmde);
-			if (!is_migration_entry(entry) ||
-			    migration_entry_to_page(entry) != page)
-				return not_found(pvmw);
-			return true;
-		}
-		/* THP pmd was split under us: handle on pte level */
-		spin_unlock(pvmw->ptl);
-		pvmw->ptl = NULL;
-	} else if (!pmd_present(pmde)) {
+		pvmw->pmd = pmd_offset(pud, pvmw->address);
 		/*
-		 * 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().
+		 * 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.
 		 */
-		if ((pvmw->flags & PVMW_SYNC) && PageTransCompound(page)) {
-			spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+		pmde = READ_ONCE(*pvmw->pmd);
+
+		if (pmd_trans_huge(pmde) || is_pmd_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;
 
-			spin_unlock(ptl);
+				if (!thp_migration_supported() ||
+				    !(pvmw->flags & PVMW_MIGRATION))
+					return not_found(pvmw);
+				entry = pmd_to_swp_entry(pmde);
+				if (!is_migration_entry(entry) ||
+				    migration_entry_to_page(entry) != page)
+					return not_found(pvmw);
+				return true;
+			}
+			/* 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) &&
+			    PageTransCompound(page)) {
+				spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+
+				spin_unlock(ptl);
+			}
+			return false;
 		}
-		return false;
+		if (!map_pte(pvmw))
+			goto next_pte;
 	}
-	if (!map_pte(pvmw))
-		goto next_pte;
 	while (1) {
 		unsigned long end;
 
_

[patch 07/24] mm: page_vma_mapped_walk(): use goto instead of while (1)

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): use goto instead of while (1)

page_vma_mapped_walk() cleanup: add a label this_pte, matching next_pte,
and use "goto this_pte", in place of the "while (1)" loop at the end.

Link: https://lkml.kernel.org/r/a52b234a-851-3616-2525-f42736e8934@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-use-goto-instead-of-while-1
+++ a/mm/page_vma_mapped.c
@@ -144,6 +144,7 @@ bool page_vma_mapped_walk(struct page_vm
 {
 	struct mm_struct *mm = pvmw->vma->vm_mm;
 	struct page *page = pvmw->page;
+	unsigned long end;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
@@ -233,10 +234,7 @@ restart:
 		}
 		if (!map_pte(pvmw))
 			goto next_pte;
-	}
-	while (1) {
-		unsigned long end;
-
+this_pte:
 		if (check_pte(pvmw))
 			return true;
 next_pte:
@@ -265,6 +263,7 @@ next_pte:
 			pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
 			spin_lock(pvmw->ptl);
 		}
+		goto this_pte;
 	}
 }
 
_

[patch 08/24] mm: page_vma_mapped_walk(): get vma_address_end() earlier

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm: page_vma_mapped_walk(): get vma_address_end() earlier

page_vma_mapped_walk() cleanup: get THP's vma_address_end() at the start,
rather than later at next_pte.  It's a little unnecessary overhead on the
first call, but makes for a simpler loop in the following commit.

Link: https://lkml.kernel.org/r/4542b34d-862f-7cb4-bb22-e0df6ce830a2@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/mm/page_vma_mapped.c~mm-page_vma_mapped_walk-get-vma_address_end-earlier
+++ a/mm/page_vma_mapped.c
@@ -171,6 +171,15 @@ bool page_vma_mapped_walk(struct page_vm
 		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;
 	if (pvmw->pte)
 		goto next_pte;
 restart:
@@ -238,10 +247,6 @@ this_pte:
 		if (check_pte(pvmw))
 			return true;
 next_pte:
-		/* Seek to next pte only makes sense for THP */
-		if (!PageTransHuge(page))
-			return not_found(pvmw);
-		end = vma_address_end(page, pvmw->vma);
 		do {
 			pvmw->address += PAGE_SIZE;
 			if (pvmw->address >= end)
_

[patch 09/24] mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes

Running certain tests with a DEBUG_VM kernel would crash within hours, on
the total_mapcount BUG() in split_huge_page_to_list(), while trying to
free up some memory by punching a hole in a shmem huge page: split's
try_to_unmap() was unable to find all the mappings of the page (which, on
a !DEBUG_VM kernel, would then keep the huge page pinned in memory).

Crash dumps showed two tail pages of a shmem huge page remained mapped by
pte: ptes in a non-huge-aligned vma of a gVisor process, at the end of a
long unmapped range; and no page table had yet been allocated for the head
of the huge page to be mapped into.

Although designed to handle these odd misaligned huge-page-mapped-by-pte
cases, page_vma_mapped_walk() falls short by returning false prematurely
when !pmd_present or !pud_present or !p4d_present or !pgd_present: there
are cases when a huge page may span the boundary, with ptes present in the
next.

Restructure page_vma_mapped_walk() as a loop to continue in these cases,
while keeping its layout much as before.  Add a step_forward() helper to
advance pvmw->address across those boundaries: originally I tried to use
mm's standard p?d_addr_end() macros, but hit the same crash 512 times less
often: because of the way redundant levels are folded together, but folded
differently in different configurations, it was just too difficult to use
them correctly; and step_forward() is simpler anyway.

Link: https://lkml.kernel.org/r/fedb8632-1798-de42-f39e-873551d5bc81@google.com
Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Wang Yugui <wangyugui@e16-tech.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |   34 +++++++++++++++++++++++++---------
 1 file changed, 25 insertions(+), 9 deletions(-)

--- a/mm/page_vma_mapped.c~mm-thp-fix-page_vma_mapped_walk-if-thp-mapped-by-ptes
+++ a/mm/page_vma_mapped.c
@@ -116,6 +116,13 @@ static bool check_pte(struct page_vma_ma
 	return pfn_is_match(pvmw->page, pfn);
 }
 
+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
  * @pvmw->address
@@ -183,16 +190,22 @@ bool page_vma_mapped_walk(struct page_vm
 	if (pvmw->pte)
 		goto next_pte;
 restart:
-	{
+	do {
 		pgd = pgd_offset(mm, pvmw->address);
-		if (!pgd_present(*pgd))
-			return false;
+		if (!pgd_present(*pgd)) {
+			step_forward(pvmw, PGDIR_SIZE);
+			continue;
+		}
 		p4d = p4d_offset(pgd, pvmw->address);
-		if (!p4d_present(*p4d))
-			return false;
+		if (!p4d_present(*p4d)) {
+			step_forward(pvmw, P4D_SIZE);
+			continue;
+		}
 		pud = pud_offset(p4d, pvmw->address);
-		if (!pud_present(*pud))
-			return false;
+		if (!pud_present(*pud)) {
+			step_forward(pvmw, PUD_SIZE);
+			continue;
+		}
 
 		pvmw->pmd = pmd_offset(pud, pvmw->address);
 		/*
@@ -239,7 +252,8 @@ restart:
 
 				spin_unlock(ptl);
 			}
-			return false;
+			step_forward(pvmw, PMD_SIZE);
+			continue;
 		}
 		if (!map_pte(pvmw))
 			goto next_pte;
@@ -269,7 +283,9 @@ next_pte:
 			spin_lock(pvmw->ptl);
 		}
 		goto this_pte;
-	}
+	} while (pvmw->address < end);
+
+	return false;
 }
 
 /**
_

[patch 10/24] mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk()

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk()

Aha!  Shouldn't that quick scan over pte_none()s make sure that it holds
ptlock in the PVMW_SYNC case?  That too might have been responsible for
BUGs or WARNs in split_huge_page_to_list() or its unmap_page(), though
I've never seen any.

Link: https://lkml.kernel.org/r/1bdf384c-8137-a149-2a1e-475a4791c3c@google.com
Link: https://lore.kernel.org/linux-mm/20210412180659.B9E3.409509F4@e16-tech.com/
Fixes: ace71a19cec5 ("mm: introduce page_vma_mapped_walk()")
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Wang Yugui <wangyugui@e16-tech.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_vma_mapped.c |    4 ++++
 1 file changed, 4 insertions(+)

--- a/mm/page_vma_mapped.c~mm-thp-another-pvmw_sync-fix-in-page_vma_mapped_walk
+++ a/mm/page_vma_mapped.c
@@ -276,6 +276,10 @@ next_pte:
 				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));
 
 		if (!pvmw->ptl) {
_

[patch 15/24] kthread_worker: split code for canceling the delayed work timer

[Andrew Morton]

From: Petr Mladek <pmladek@suse.com>
Subject: kthread_worker: split code for canceling the delayed work timer

Patch series "kthread_worker: Fix race between kthread_mod_delayed_work()
and kthread_cancel_delayed_work_sync()".

This patchset fixes the race between kthread_mod_delayed_work() and
kthread_cancel_delayed_work_sync() including proper return value handling.


This patch (of 2):

Simple code refactoring as a preparation step for fixing a race between
kthread_mod_delayed_work() and kthread_cancel_delayed_work_sync().

It does not modify the existing behavior.

Link: https://lkml.kernel.org/r/20210610133051.15337-2-pmladek@suse.com
Signed-off-by: Petr Mladek <pmladek@suse.com>
Cc: <jenhaochen@google.com>
Cc: Martin Liu <liumartin@google.com>
Cc: Minchan Kim <minchan@google.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 kernel/kthread.c |   46 ++++++++++++++++++++++++++++-----------------
 1 file changed, 29 insertions(+), 17 deletions(-)

--- a/kernel/kthread.c~kthread_worker-split-code-for-canceling-the-delayed-work-timer
+++ a/kernel/kthread.c
@@ -1093,6 +1093,33 @@ void kthread_flush_work(struct kthread_w
 EXPORT_SYMBOL_GPL(kthread_flush_work);
 
 /*
+ * Make sure that the timer is neither set nor running and could
+ * not manipulate the work list_head any longer.
+ *
+ * The function is called under worker->lock. The lock is temporary
+ * released but the timer can't be set again in the meantime.
+ */
+static void kthread_cancel_delayed_work_timer(struct kthread_work *work,
+					      unsigned long *flags)
+{
+	struct kthread_delayed_work *dwork =
+		container_of(work, struct kthread_delayed_work, work);
+	struct kthread_worker *worker = work->worker;
+
+	/*
+	 * del_timer_sync() must be called to make sure that the timer
+	 * callback is not running. The lock must be temporary released
+	 * to avoid a deadlock with the callback. In the meantime,
+	 * any queuing is blocked by setting the canceling counter.
+	 */
+	work->canceling++;
+	raw_spin_unlock_irqrestore(&worker->lock, *flags);
+	del_timer_sync(&dwork->timer);
+	raw_spin_lock_irqsave(&worker->lock, *flags);
+	work->canceling--;
+}
+
+/*
  * This function removes the work from the worker queue. Also it makes sure
  * that it won't get queued later via the delayed work's timer.
  *
@@ -1106,23 +1133,8 @@ static bool __kthread_cancel_work(struct
 				  unsigned long *flags)
 {
 	/* Try to cancel the timer if exists. */
-	if (is_dwork) {
-		struct kthread_delayed_work *dwork =
-			container_of(work, struct kthread_delayed_work, work);
-		struct kthread_worker *worker = work->worker;
-
-		/*
-		 * del_timer_sync() must be called to make sure that the timer
-		 * callback is not running. The lock must be temporary released
-		 * to avoid a deadlock with the callback. In the meantime,
-		 * any queuing is blocked by setting the canceling counter.
-		 */
-		work->canceling++;
-		raw_spin_unlock_irqrestore(&worker->lock, *flags);
-		del_timer_sync(&dwork->timer);
-		raw_spin_lock_irqsave(&worker->lock, *flags);
-		work->canceling--;
-	}
+	if (is_dwork)
+		kthread_cancel_delayed_work_timer(work, flags);
 
 	/*
 	 * Try to remove the work from a worker list. It might either
_

[patch 16/24] kthread: prevent deadlock when kthread_mod_delayed_work() races with kthread_cancel_delayed_work_sync()

[Andrew Morton]

From: Petr Mladek <pmladek@suse.com>
Subject: kthread: prevent deadlock when kthread_mod_delayed_work() races with kthread_cancel_delayed_work_sync()

The system might hang with the following backtrace:

	schedule+0x80/0x100
	schedule_timeout+0x48/0x138
	wait_for_common+0xa4/0x134
	wait_for_completion+0x1c/0x2c
	kthread_flush_work+0x114/0x1cc
	kthread_cancel_work_sync.llvm.16514401384283632983+0xe8/0x144
	kthread_cancel_delayed_work_sync+0x18/0x2c
	xxxx_pm_notify+0xb0/0xd8
	blocking_notifier_call_chain_robust+0x80/0x194
	pm_notifier_call_chain_robust+0x28/0x4c
	suspend_prepare+0x40/0x260
	enter_state+0x80/0x3f4
	pm_suspend+0x60/0xdc
	state_store+0x108/0x144
	kobj_attr_store+0x38/0x88
	sysfs_kf_write+0x64/0xc0
	kernfs_fop_write_iter+0x108/0x1d0
	vfs_write+0x2f4/0x368
	ksys_write+0x7c/0xec

It is caused by the following race between kthread_mod_delayed_work() and
kthread_cancel_delayed_work_sync():

CPU0				CPU1

Context: Thread A		Context: Thread B

kthread_mod_delayed_work()
  spin_lock()
  __kthread_cancel_work()
     spin_unlock()
     del_timer_sync()
				kthread_cancel_delayed_work_sync()
				  spin_lock()
				  __kthread_cancel_work()
				    spin_unlock()
				    del_timer_sync()
				    spin_lock()

				  work->canceling++
				  spin_unlock
     spin_lock()
   queue_delayed_work()
     // dwork is put into the worker->delayed_work_list

   spin_unlock()

				  kthread_flush_work()
     // flush_work is put at the tail of the dwork

				    wait_for_completion()

Context: IRQ

  kthread_delayed_work_timer_fn()
    spin_lock()
    list_del_init(&work->node);
    spin_unlock()

BANG: flush_work is not longer linked and will never get proceed.

The problem is that kthread_mod_delayed_work() checks work->canceling flag
before canceling the timer.

A simple solution is to (re)check work->canceling after
__kthread_cancel_work().  But then it is not clear what should be returned
when __kthread_cancel_work() removed the work from the queue (list) and it
can't queue it again with the new @delay.

The return value might be used for reference counting.  The caller has to
know whether a new work has been queued or an existing one was replaced.

The proper solution is that kthread_mod_delayed_work() will remove the
work from the queue (list) _only_ when work->canceling is not set.  The
flag must be checked after the timer is stopped and the remaining
operations can be done under worker->lock.

Note that kthread_mod_delayed_work() could remove the timer and then bail
out.  It is fine.  The other canceling caller needs to cancel the timer as
well.  The important thing is that the queue (list) manipulation is done
atomically under worker->lock.

Link: https://lkml.kernel.org/r/20210610133051.15337-3-pmladek@suse.com
Fixes: 9a6b06c8d9a220860468a ("kthread: allow to modify delayed kthread work")
Signed-off-by: Petr Mladek <pmladek@suse.com>
Reported-by: Martin Liu <liumartin@google.com>
Cc: <jenhaochen@google.com>
Cc: Minchan Kim <minchan@google.com>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 kernel/kthread.c |   35 ++++++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 11 deletions(-)

--- a/kernel/kthread.c~kthread-prevent-deadlock-when-kthread_mod_delayed_work-races-with-kthread_cancel_delayed_work_sync
+++ a/kernel/kthread.c
@@ -1120,8 +1120,11 @@ static void kthread_cancel_delayed_work_
 }
 
 /*
- * This function removes the work from the worker queue. Also it makes sure
- * that it won't get queued later via the delayed work's timer.
+ * This function removes the work from the worker queue.
+ *
+ * It is called under worker->lock. The caller must make sure that
+ * the timer used by delayed work is not running, e.g. by calling
+ * kthread_cancel_delayed_work_timer().
  *
  * The work might still be in use when this function finishes. See the
  * current_work proceed by the worker.
@@ -1129,13 +1132,8 @@ static void kthread_cancel_delayed_work_
  * Return: %true if @work was pending and successfully canceled,
  *	%false if @work was not pending
  */
-static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork,
-				  unsigned long *flags)
+static bool __kthread_cancel_work(struct kthread_work *work)
 {
-	/* Try to cancel the timer if exists. */
-	if (is_dwork)
-		kthread_cancel_delayed_work_timer(work, flags);
-
 	/*
 	 * Try to remove the work from a worker list. It might either
 	 * be from worker->work_list or from worker->delayed_work_list.
@@ -1188,11 +1186,23 @@ bool kthread_mod_delayed_work(struct kth
 	/* Work must not be used with >1 worker, see kthread_queue_work() */
 	WARN_ON_ONCE(work->worker != worker);
 
-	/* Do not fight with another command that is canceling this work. */
+	/*
+	 * Temporary cancel the work but do not fight with another command
+	 * that is canceling the work as well.
+	 *
+	 * It is a bit tricky because of possible races with another
+	 * mod_delayed_work() and cancel_delayed_work() callers.
+	 *
+	 * The timer must be canceled first because worker->lock is released
+	 * when doing so. But the work can be removed from the queue (list)
+	 * only when it can be queued again so that the return value can
+	 * be used for reference counting.
+	 */
+	kthread_cancel_delayed_work_timer(work, &flags);
 	if (work->canceling)
 		goto out;
+	ret = __kthread_cancel_work(work);
 
-	ret = __kthread_cancel_work(work, true, &flags);
 fast_queue:
 	__kthread_queue_delayed_work(worker, dwork, delay);
 out:
@@ -1214,7 +1224,10 @@ static bool __kthread_cancel_work_sync(s
 	/* Work must not be used with >1 worker, see kthread_queue_work(). */
 	WARN_ON_ONCE(work->worker != worker);
 
-	ret = __kthread_cancel_work(work, is_dwork, &flags);
+	if (is_dwork)
+		kthread_cancel_delayed_work_timer(work, &flags);
+
+	ret = __kthread_cancel_work(work);
 
 	if (worker->current_work != work)
 		goto out_fast;
_

[patch 17/24] mm, futex: fix shared futex pgoff on shmem huge page

[Andrew Morton]

From: Hugh Dickins <hughd@google.com>
Subject: mm, futex: fix shared futex pgoff on shmem huge page

If more than one futex is placed on a shmem huge page, it can happen that
waking the second wakes the first instead, and leaves the second waiting:
the key's shared.pgoff is wrong.

When 3.11 commit 13d60f4b6ab5 ("futex: Take hugepages into account when
generating futex_key"), the only shared huge pages came from hugetlbfs,
and the code added to deal with its exceptional page->index was put into
hugetlb source.  Then that was missed when 4.8 added shmem huge pages.

page_to_pgoff() is what others use for this nowadays: except that, as
currently written, it gives the right answer on hugetlbfs head, but
nonsense on hugetlbfs tails.  Fix that by calling hugetlbfs-specific
hugetlb_basepage_index() on PageHuge tails as well as on head.

Yes, it's unconventional to declare hugetlb_basepage_index() there in
pagemap.h, rather than in hugetlb.h; but I do not expect anything but
page_to_pgoff() ever to need it.

[akpm@linux-foundation.org: give hugetlb_basepage_index() prototype the correct scope]
Link: https://lkml.kernel.org/r/b17d946b-d09-326e-b42a-52884c36df32@google.com
Fixes: 800d8c63b2e9 ("shmem: add huge pages support")
Reported-by: Neel Natu <neelnatu@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Zhang Yi <wetpzy@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/hugetlb.h |   16 ----------------
 include/linux/pagemap.h |   13 +++++++------
 kernel/futex.c          |    3 +--
 mm/hugetlb.c            |    5 +----
 4 files changed, 9 insertions(+), 28 deletions(-)

--- a/include/linux/hugetlb.h~mm-futex-fix-shared-futex-pgoff-on-shmem-huge-page
+++ a/include/linux/hugetlb.h
@@ -741,17 +741,6 @@ static inline int hstate_index(struct hs
 	return h - hstates;
 }
 
-pgoff_t __basepage_index(struct page *page);
-
-/* Return page->index in PAGE_SIZE units */
-static inline pgoff_t basepage_index(struct page *page)
-{
-	if (!PageCompound(page))
-		return page->index;
-
-	return __basepage_index(page);
-}
-
 extern int dissolve_free_huge_page(struct page *page);
 extern int dissolve_free_huge_pages(unsigned long start_pfn,
 				    unsigned long end_pfn);
@@ -988,11 +977,6 @@ static inline int hstate_index(struct hs
 	return 0;
 }
 
-static inline pgoff_t basepage_index(struct page *page)
-{
-	return page->index;
-}
-
 static inline int dissolve_free_huge_page(struct page *page)
 {
 	return 0;
--- a/include/linux/pagemap.h~mm-futex-fix-shared-futex-pgoff-on-shmem-huge-page
+++ a/include/linux/pagemap.h
@@ -516,7 +516,7 @@ static inline struct page *read_mapping_
 }
 
 /*
- * Get index of the page with in radix-tree
+ * Get index of the page within radix-tree (but not for hugetlb pages).
  * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
  */
 static inline pgoff_t page_to_index(struct page *page)
@@ -535,15 +535,16 @@ static inline pgoff_t page_to_index(stru
 	return pgoff;
 }
 
+extern pgoff_t hugetlb_basepage_index(struct page *page);
+
 /*
- * Get the offset in PAGE_SIZE.
- * (TODO: hugepage should have ->index in PAGE_SIZE)
+ * Get the offset in PAGE_SIZE (even for hugetlb pages).
+ * (TODO: hugetlb pages should have ->index in PAGE_SIZE)
  */
 static inline pgoff_t page_to_pgoff(struct page *page)
 {
-	if (unlikely(PageHeadHuge(page)))
-		return page->index << compound_order(page);
-
+	if (unlikely(PageHuge(page)))
+		return hugetlb_basepage_index(page);
 	return page_to_index(page);
 }
 
--- a/kernel/futex.c~mm-futex-fix-shared-futex-pgoff-on-shmem-huge-page
+++ a/kernel/futex.c
@@ -35,7 +35,6 @@
 #include <linux/jhash.h>
 #include <linux/pagemap.h>
 #include <linux/syscalls.h>
-#include <linux/hugetlb.h>
 #include <linux/freezer.h>
 #include <linux/memblock.h>
 #include <linux/fault-inject.h>
@@ -650,7 +649,7 @@ again:
 
 		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
 		key->shared.i_seq = get_inode_sequence_number(inode);
-		key->shared.pgoff = basepage_index(tail);
+		key->shared.pgoff = page_to_pgoff(tail);
 		rcu_read_unlock();
 	}
 
--- a/mm/hugetlb.c~mm-futex-fix-shared-futex-pgoff-on-shmem-huge-page
+++ a/mm/hugetlb.c
@@ -1588,15 +1588,12 @@ struct address_space *hugetlb_page_mappi
 	return NULL;
 }
 
-pgoff_t __basepage_index(struct page *page)
+pgoff_t hugetlb_basepage_index(struct page *page)
 {
 	struct page *page_head = compound_head(page);
 	pgoff_t index = page_index(page_head);
 	unsigned long compound_idx;
 
-	if (!PageHuge(page_head))
-		return page_index(page);
-
 	if (compound_order(page_head) >= MAX_ORDER)
 		compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
 	else
_

[patch 18/24] mm/memory-failure: use a mutex to avoid memory_failure() races

[Andrew Morton]

From: Tony Luck <tony.luck@intel.com>
Subject: mm/memory-failure: use a mutex to avoid memory_failure() races

Patch series "mm,hwpoison: fix sending SIGBUS for Action Required MCE", v5.

I wrote this patchset to materialize what I think is the current allowable
solution mentioned by the previous discussion [1].  I simply borrowed
Tony's mutex patch and Aili's return code patch, then I queued another one
to find error virtual address in the best effort manner.  I know that this
is not a perfect solution, but should work for some typical case.

[1]: https://lore.kernel.org/linux-mm/20210331192540.2141052f@alex-virtual-machine/


This patch (of 2):

There can be races when multiple CPUs consume poison from the same page. 
The first into memory_failure() atomically sets the HWPoison page flag and
begins hunting for tasks that map this page.  Eventually it invalidates
those mappings and may send a SIGBUS to the affected tasks.

But while all that work is going on, other CPUs see a "success" return
code from memory_failure() and so they believe the error has been handled
and continue executing.

Fix by wrapping most of the internal parts of memory_failure() in a mutex.

[akpm@linux-foundation.org: make mf_mutex local to memory_failure()]
Link: https://lkml.kernel.org/r/20210521030156.2612074-1-nao.horiguchi@gmail.com
Link: https://lkml.kernel.org/r/20210521030156.2612074-2-nao.horiguchi@gmail.com
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Aili Yao <yaoaili@kingsoft.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jue Wang <juew@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/memory-failure.c |   36 +++++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 13 deletions(-)

--- a/mm/memory-failure.c~mm-memory-failure-use-a-mutex-to-avoid-memory_failure-races
+++ a/mm/memory-failure.c
@@ -1429,9 +1429,10 @@ int memory_failure(unsigned long pfn, in
 	struct page *hpage;
 	struct page *orig_head;
 	struct dev_pagemap *pgmap;
-	int res;
+	int res = 0;
 	unsigned long page_flags;
 	bool retry = true;
+	static DEFINE_MUTEX(mf_mutex);
 
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure on page %lx", pfn);
@@ -1449,13 +1450,18 @@ int memory_failure(unsigned long pfn, in
 		return -ENXIO;
 	}
 
+	mutex_lock(&mf_mutex);
+
 try_again:
-	if (PageHuge(p))
-		return memory_failure_hugetlb(pfn, flags);
+	if (PageHuge(p)) {
+		res = memory_failure_hugetlb(pfn, flags);
+		goto unlock_mutex;
+	}
+
 	if (TestSetPageHWPoison(p)) {
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
 			pfn);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	orig_head = hpage = compound_head(p);
@@ -1488,17 +1494,19 @@ try_again:
 				res = MF_FAILED;
 			}
 			action_result(pfn, MF_MSG_BUDDY, res);
-			return res == MF_RECOVERED ? 0 : -EBUSY;
+			res = res == MF_RECOVERED ? 0 : -EBUSY;
 		} else {
 			action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
-			return -EBUSY;
+			res = -EBUSY;
 		}
+		goto unlock_mutex;
 	}
 
 	if (PageTransHuge(hpage)) {
 		if (try_to_split_thp_page(p, "Memory Failure") < 0) {
 			action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
-			return -EBUSY;
+			res = -EBUSY;
+			goto unlock_mutex;
 		}
 		VM_BUG_ON_PAGE(!page_count(p), p);
 	}
@@ -1522,7 +1530,7 @@ try_again:
 	if (PageCompound(p) && compound_head(p) != orig_head) {
 		action_result(pfn, MF_MSG_DIFFERENT_COMPOUND, MF_IGNORED);
 		res = -EBUSY;
-		goto out;
+		goto unlock_page;
 	}
 
 	/*
@@ -1542,14 +1550,14 @@ try_again:
 		num_poisoned_pages_dec();
 		unlock_page(p);
 		put_page(p);
-		return 0;
+		goto unlock_mutex;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
 			num_poisoned_pages_dec();
 		unlock_page(p);
 		put_page(p);
-		return 0;
+		goto unlock_mutex;
 	}
 
 	/*
@@ -1573,7 +1581,7 @@ try_again:
 	if (!hwpoison_user_mappings(p, pfn, flags, &p)) {
 		action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
 		res = -EBUSY;
-		goto out;
+		goto unlock_page;
 	}
 
 	/*
@@ -1582,13 +1590,15 @@ try_again:
 	if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
 		action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED);
 		res = -EBUSY;
-		goto out;
+		goto unlock_page;
 	}
 
 identify_page_state:
 	res = identify_page_state(pfn, p, page_flags);
-out:
+unlock_page:
 	unlock_page(p);
+unlock_mutex:
+	mutex_unlock(&mf_mutex);
 	return res;
 }
 EXPORT_SYMBOL_GPL(memory_failure);
_

[patch 19/24] mm,hwpoison: return -EHWPOISON to denote that the page has already been poisoned

[Andrew Morton]

From: Aili Yao <yaoaili@kingsoft.com>
Subject: mm,hwpoison: return -EHWPOISON to denote that the page has already been poisoned

When memory_failure() is called with MF_ACTION_REQUIRED on the page that
has already been hwpoisoned, memory_failure() could fail to send SIGBUS to
the affected process, which results in infinite loop of MCEs.

Currently memory_failure() returns 0 if it's called for already hwpoisoned
page, then the caller, kill_me_maybe(), could return without sending
SIGBUS to current process.  An action required MCE is raised when the
current process accesses to the broken memory, so no SIGBUS means that the
current process continues to run and access to the error page again soon,
so running into MCE loop.

This issue can arise for example in the following scenarios:

- Two or more threads access to the poisoned page concurrently.  If
  local MCE is enabled, MCE handler independently handles the MCE events. 
  So there's a race among MCE events, and the second or latter threads
  fall into the situation in question.

- If there was a precedent memory error event and memory_failure() for
  the event failed to unmap the error page for some reason, the subsequent
  memory access to the error page triggers the MCE loop situation.

To fix the issue, make memory_failure() return an error code when the
error page has already been hwpoisoned.  This allows memory error handler
to control how it sends signals to userspace.  And make sure that any
process touching a hwpoisoned page should get a SIGBUS even in "already
hwpoisoned" path of memory_failure() as is done in page fault path.

Link: https://lkml.kernel.org/r/20210521030156.2612074-3-nao.horiguchi@gmail.com
Signed-off-by: Aili Yao <yaoaili@kingsoft.com>
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jue Wang <juew@google.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/memory-failure.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/mm/memory-failure.c~mmhwpoison-return-ehwpoison-to-denote-that-the-page-has-already-been-poisoned
+++ a/mm/memory-failure.c
@@ -1253,7 +1253,7 @@ static int memory_failure_hugetlb(unsign
 	if (TestSetPageHWPoison(head)) {
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
 		       pfn);
-		return 0;
+		return -EHWPOISON;
 	}
 
 	num_poisoned_pages_inc();
@@ -1461,6 +1461,7 @@ try_again:
 	if (TestSetPageHWPoison(p)) {
 		pr_err("Memory failure: %#lx: already hardware poisoned\n",
 			pfn);
+		res = -EHWPOISON;
 		goto unlock_mutex;
 	}
 
_

[patch 20/24] mm/hwpoison: do not lock page again when me_huge_page() successfully recovers

[Andrew Morton]

From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm/hwpoison: do not lock page again when me_huge_page() successfully recovers

Currently me_huge_page() temporary unlocks page to perform some actions
then locks it again later.  My testcase (which calls hard-offline on some
tail page in a hugetlb, then accesses the address of the hugetlb range)
showed that page allocation code detects this page lock on buddy page and
printed out "BUG: Bad page state" message.

check_new_page_bad() does not consider a page with __PG_HWPOISON as bad
page, so this flag works as kind of filter, but this filtering doesn't
work in this case because the "bad page" is not the actual hwpoisoned
page.  So stop locking page again.  Actions to be taken depend on the page
type of the error, so page unlocking should be done in ->action()
callbacks.  So let's make it assumed and change all existing callbacks
that way.

Link: https://lkml.kernel.org/r/20210609072029.74645-1-nao.horiguchi@gmail.com
Fixes: commit 78bb920344b8 ("mm: hwpoison: dissolve in-use hugepage in unrecoverable memory error")
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/memory-failure.c |   44 ++++++++++++++++++++++++++++--------------
 1 file changed, 30 insertions(+), 14 deletions(-)

--- a/mm/memory-failure.c~mm-hwpoison-do-not-lock-page-again-when-me_huge_page-successfully-recovers
+++ a/mm/memory-failure.c
@@ -658,6 +658,7 @@ static int truncate_error_page(struct pa
  */
 static int me_kernel(struct page *p, unsigned long pfn)
 {
+	unlock_page(p);
 	return MF_IGNORED;
 }
 
@@ -667,6 +668,7 @@ static int me_kernel(struct page *p, uns
 static int me_unknown(struct page *p, unsigned long pfn)
 {
 	pr_err("Memory failure: %#lx: Unknown page state\n", pfn);
+	unlock_page(p);
 	return MF_FAILED;
 }
 
@@ -675,6 +677,7 @@ static int me_unknown(struct page *p, un
  */
 static int me_pagecache_clean(struct page *p, unsigned long pfn)
 {
+	int ret;
 	struct address_space *mapping;
 
 	delete_from_lru_cache(p);
@@ -683,8 +686,10 @@ static int me_pagecache_clean(struct pag
 	 * For anonymous pages we're done the only reference left
 	 * should be the one m_f() holds.
 	 */
-	if (PageAnon(p))
-		return MF_RECOVERED;
+	if (PageAnon(p)) {
+		ret = MF_RECOVERED;
+		goto out;
+	}
 
 	/*
 	 * Now truncate the page in the page cache. This is really
@@ -698,7 +703,8 @@ static int me_pagecache_clean(struct pag
 		/*
 		 * Page has been teared down in the meanwhile
 		 */
-		return MF_FAILED;
+		ret = MF_FAILED;
+		goto out;
 	}
 
 	/*
@@ -706,7 +712,10 @@ static int me_pagecache_clean(struct pag
 	 *
 	 * Open: to take i_mutex or not for this? Right now we don't.
 	 */
-	return truncate_error_page(p, pfn, mapping);
+	ret = truncate_error_page(p, pfn, mapping);
+out:
+	unlock_page(p);
+	return ret;
 }
 
 /*
@@ -782,24 +791,26 @@ static int me_pagecache_dirty(struct pag
  */
 static int me_swapcache_dirty(struct page *p, unsigned long pfn)
 {
+	int ret;
+
 	ClearPageDirty(p);
 	/* Trigger EIO in shmem: */
 	ClearPageUptodate(p);
 
-	if (!delete_from_lru_cache(p))
-		return MF_DELAYED;
-	else
-		return MF_FAILED;
+	ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED;
+	unlock_page(p);
+	return ret;
 }
 
 static int me_swapcache_clean(struct page *p, unsigned long pfn)
 {
+	int ret;
+
 	delete_from_swap_cache(p);
 
-	if (!delete_from_lru_cache(p))
-		return MF_RECOVERED;
-	else
-		return MF_FAILED;
+	ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED;
+	unlock_page(p);
+	return ret;
 }
 
 /*
@@ -820,6 +831,7 @@ static int me_huge_page(struct page *p,
 	mapping = page_mapping(hpage);
 	if (mapping) {
 		res = truncate_error_page(hpage, pfn, mapping);
+		unlock_page(hpage);
 	} else {
 		res = MF_FAILED;
 		unlock_page(hpage);
@@ -834,7 +846,6 @@ static int me_huge_page(struct page *p,
 			page_ref_inc(p);
 			res = MF_RECOVERED;
 		}
-		lock_page(hpage);
 	}
 
 	return res;
@@ -866,6 +877,8 @@ static struct page_state {
 	unsigned long mask;
 	unsigned long res;
 	enum mf_action_page_type type;
+
+	/* Callback ->action() has to unlock the relevant page inside it. */
 	int (*action)(struct page *p, unsigned long pfn);
 } error_states[] = {
 	{ reserved,	reserved,	MF_MSG_KERNEL,	me_kernel },
@@ -929,6 +942,7 @@ static int page_action(struct page_state
 	int result;
 	int count;
 
+	/* page p should be unlocked after returning from ps->action().  */
 	result = ps->action(p, pfn);
 
 	count = page_count(p) - 1;
@@ -1313,7 +1327,7 @@ static int memory_failure_hugetlb(unsign
 		goto out;
 	}
 
-	res = identify_page_state(pfn, p, page_flags);
+	return identify_page_state(pfn, p, page_flags);
 out:
 	unlock_page(head);
 	return res;
@@ -1596,6 +1610,8 @@ try_again:
 
 identify_page_state:
 	res = identify_page_state(pfn, p, page_flags);
+	mutex_unlock(&mf_mutex);
+	return res;
 unlock_page:
 	unlock_page(p);
 unlock_mutex:
_