--- /dev/null
+From c325b717eba6c144449b9d2c7bd5e96af5196f89 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 18 Dec 2020 14:01:31 -0800
+Subject: mm: add VM_WARN_ON_ONCE_PAGE() macro
+
+From: Alex Shi <alex.shi@linux.alibaba.com>
+
+[ Upstream commit a4055888629bc0467d12d912cd7c90acdf3d9b12 part ]
+
+Add VM_WARN_ON_ONCE_PAGE() macro.
+
+Link: https://lkml.kernel.org/r/1604283436-18880-3-git-send-email-alex.shi@linux.alibaba.com
+Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
+Acked-by: Michal Hocko <mhocko@suse.com>
+Acked-by: Hugh Dickins <hughd@google.com>
+Acked-by: Johannes Weiner <hannes@cmpxchg.org>
+Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+
+Note on stable backport: original commit was titled
+mm/memcg: warning on !memcg after readahead page charged
+which included uses of this macro in mm/memcontrol.c: here omitted.
+
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/linux/mmdebug.h | 13 +++++++++++++
+ 1 file changed, 13 insertions(+)
+
+diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
+index 2ad72d2c8cc5..5d0767cb424a 100644
+--- a/include/linux/mmdebug.h
++++ b/include/linux/mmdebug.h
+@@ -37,6 +37,18 @@ void dump_mm(const struct mm_struct *mm);
+ BUG(); \
+ } \
+ } while (0)
++#define VM_WARN_ON_ONCE_PAGE(cond, page) ({ \
++ static bool __section(".data.once") __warned; \
++ int __ret_warn_once = !!(cond); \
++ \
++ if (unlikely(__ret_warn_once && !__warned)) { \
++ dump_page(page, "VM_WARN_ON_ONCE_PAGE(" __stringify(cond)")");\
++ __warned = true; \
++ WARN_ON(1); \
++ } \
++ unlikely(__ret_warn_once); \
++})
++
+ #define VM_WARN_ON(cond) (void)WARN_ON(cond)
+ #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
+ #define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
+@@ -48,6 +60,7 @@ void dump_mm(const struct mm_struct *mm);
+ #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
+ #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
+ #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
++#define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond)
+ #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
+ #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
+ #endif
+--
+2.30.2
+
--- /dev/null
+From a5b64f8a0d902dc24075ae4e5edf673d2595e70c Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:52 -0700
+Subject: mm, futex: fix shared futex pgoff on shmem huge page
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit fe19bd3dae3d15d2fbfdb3de8839a6ea0fe94264 ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+
+Note on stable backport: leave redundant #include <linux/hugetlb.h>
+in kernel/futex.c, to avoid conflict over the header files included.
+
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/linux/hugetlb.h | 16 ----------------
+ include/linux/pagemap.h | 13 +++++++------
+ kernel/futex.c | 2 +-
+ mm/hugetlb.c | 5 +----
+ 4 files changed, 9 insertions(+), 27 deletions(-)
+
+diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
+index c129c1c14c5f..2df83a659818 100644
+--- a/include/linux/hugetlb.h
++++ b/include/linux/hugetlb.h
+@@ -477,17 +477,6 @@ static inline int hstate_index(struct hstate *h)
+ 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);
+@@ -582,11 +571,6 @@ static inline int hstate_index(struct hstate *h)
+ 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;
+diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
+index b1bd2186e6d2..33b63b2a163f 100644
+--- a/include/linux/pagemap.h
++++ b/include/linux/pagemap.h
+@@ -403,7 +403,7 @@ static inline struct page *read_mapping_page(struct address_space *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)
+@@ -422,15 +422,16 @@ static inline pgoff_t page_to_index(struct page *page)
+ 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);
+ }
+
+diff --git a/kernel/futex.c b/kernel/futex.c
+index 526ebcff5a0a..3c67da9b8408 100644
+--- a/kernel/futex.c
++++ b/kernel/futex.c
+@@ -719,7 +719,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw)
+
+ 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();
+ }
+
+diff --git a/mm/hugetlb.c b/mm/hugetlb.c
+index c69f12e4c149..ebcf26bc4cd4 100644
+--- a/mm/hugetlb.c
++++ b/mm/hugetlb.c
+@@ -1391,15 +1391,12 @@ int PageHeadHuge(struct page *page_head)
+ return get_compound_page_dtor(page_head) == free_huge_page;
+ }
+
+-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
+--
+2.30.2
+
--- /dev/null
+From 2e47b7cde41a8142f1f8b1182ac6e6388a90c32f Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:17 -0700
+Subject: mm: page_vma_mapped_walk(): add a level of indentation
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit b3807a91aca7d21c05d5790612e49969117a72b9 ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 105 ++++++++++++++++++++++---------------------
+ 1 file changed, 55 insertions(+), 50 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 1fccadd0eb6d..819945678264 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -169,62 +169,67 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ if (pvmw->pte)
+ goto next_pte;
+ restart:
+- pgd = pgd_offset(mm, pvmw->address);
+- if (!pgd_present(*pgd))
+- return false;
+- p4d = p4d_offset(pgd, pvmw->address);
+- if (!p4d_present(*p4d))
+- return false;
+- pud = pud_offset(p4d, pvmw->address);
+- if (!pud_present(*pud))
+- return false;
+- pvmw->pmd = pmd_offset(pud, pvmw->address);
+- /*
+- * Make sure the pmd value isn't cached in a register by the
+- * compiler and used as a stale value after we've observed a
+- * subsequent update.
+- */
+- pmde = READ_ONCE(*pvmw->pmd);
+- if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
+- pvmw->ptl = pmd_lock(mm, pvmw->pmd);
+- 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);
+
+- spin_unlock(ptl);
++ 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;
++
++ 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;
+
+--
+2.30.2
+
--- /dev/null
+From e63e589c194d8a5d9c0f48549ef4b40b95de5a03 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:14 -0700
+Subject: mm: page_vma_mapped_walk(): crossing page table boundary
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 448282487483d6fa5b2eeeafaa0acc681e544a9c ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index e32ed7912923..1fccadd0eb6d 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -240,16 +240,16 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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) {
+--
+2.30.2
+
--- /dev/null
+From c2f681dce8094b9faad9421bc29f4ffcb65e0360 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:23 -0700
+Subject: mm: page_vma_mapped_walk(): get vma_address_end() earlier
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit a765c417d876cc635f628365ec9aa6f09470069a ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 13 +++++++++----
+ 1 file changed, 9 insertions(+), 4 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 470f19c917ad..7239c38e99e2 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -167,6 +167,15 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *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;
+ if (pvmw->pte)
+ goto next_pte;
+ restart:
+@@ -234,10 +243,6 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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)
+--
+2.30.2
+
--- /dev/null
+From 2a7923a03791090dd697c03ee964458868936006 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:10 -0700
+Subject: mm: page_vma_mapped_walk(): prettify PVMW_MIGRATION block
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit e2e1d4076c77b3671cf8ce702535ae7dee3acf89 ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 30 ++++++++++++++----------------
+ 1 file changed, 14 insertions(+), 16 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 7e1db77b096a..e32ed7912923 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -194,24 +194,22 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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
+--
+2.30.2
+
--- /dev/null
+From 397604ef80482f0acae791596b46bf92ddda8dab Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:04 -0700
+Subject: mm: page_vma_mapped_walk(): settle PageHuge on entry
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 6d0fd5987657cb0c9756ce684e3a74c0f6351728 ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 12 ++++++++----
+ 1 file changed, 8 insertions(+), 4 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index d146f6d31a62..036ce20bb154 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -148,10 +148,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ if (pvmw->pmd && !pvmw->pte)
+ return not_found(pvmw);
+
+- if (pvmw->pte)
+- goto next_pte;
+-
+ if (unlikely(PageHuge(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 << compound_order(page));
+@@ -164,6 +165,9 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ return not_found(pvmw);
+ return true;
+ }
++
++ if (pvmw->pte)
++ goto next_pte;
+ restart:
+ pgd = pgd_offset(mm, pvmw->address);
+ if (!pgd_present(*pgd))
+@@ -229,7 +233,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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 {
+--
+2.30.2
+
--- /dev/null
+From 36861efd0164a2e41fc5c78ade2c309b2af28313 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:20 -0700
+Subject: mm: page_vma_mapped_walk(): use goto instead of while (1)
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 474466301dfd8b39a10c01db740645f3f7ae9a28 ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 7 +++----
+ 1 file changed, 3 insertions(+), 4 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 819945678264..470f19c917ad 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -139,6 +139,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ {
+ 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;
+@@ -229,10 +230,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ }
+ if (!map_pte(pvmw))
+ goto next_pte;
+- }
+- while (1) {
+- unsigned long end;
+-
++this_pte:
+ if (check_pte(pvmw))
+ return true;
+ next_pte:
+@@ -261,6 +259,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ pvmw->ptl = pte_lockptr(mm, pvmw->pmd);
+ spin_lock(pvmw->ptl);
+ }
++ goto this_pte;
+ }
+ }
+
+--
+2.30.2
+
--- /dev/null
+From 2afb51ee438175621161b4f372a171d0e82ab5fd Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:01 -0700
+Subject: mm: page_vma_mapped_walk(): use page for pvmw->page
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit f003c03bd29e6f46fef1b9a8e8d636ac732286d5 ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 9 ++++-----
+ 1 file changed, 4 insertions(+), 5 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index bb7488e86bea..d146f6d31a62 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -151,7 +151,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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 << compound_order(page));
+@@ -213,8 +213,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ * 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);
+@@ -230,9 +229,9 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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)
+--
+2.30.2
+
--- /dev/null
+From 5ae36a372ac02ec0f01f83a6bbe20256c9212d65 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:07 -0700
+Subject: mm: page_vma_mapped_walk(): use pmde for *pvmw->pmd
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 3306d3119ceacc43ea8b141a73e21fea68eec30c ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 11 ++++++-----
+ 1 file changed, 6 insertions(+), 5 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 036ce20bb154..7e1db77b096a 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -187,18 +187,19 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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);
+--
+2.30.2
+
--- /dev/null
+From e456fb814484049547135fd75cc54c109ceef7a9 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 25 Feb 2021 17:17:56 -0800
+Subject: mm/rmap: remove unneeded semicolon in page_not_mapped()
+
+From: Miaohe Lin <linmiaohe@huawei.com>
+
+[ Upstream commit e0af87ff7afcde2660be44302836d2d5618185af ]
+
+Remove extra semicolon without any functional change intended.
+
+Link: https://lkml.kernel.org/r/20210127093425.39640-1-linmiaohe@huawei.com
+Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/rmap.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 1bd94ea62f7f..69ce68616cbf 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -1729,7 +1729,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
+ static int page_not_mapped(struct page *page)
+ {
+ return !page_mapped(page);
+-};
++}
+
+ /**
+ * try_to_munlock - try to munlock a page
+--
+2.30.2
+
--- /dev/null
+From 68ebd86ec074de495e92928aa027e095260de6e1 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 25 Feb 2021 17:18:03 -0800
+Subject: mm/rmap: use page_not_mapped in try_to_unmap()
+
+From: Miaohe Lin <linmiaohe@huawei.com>
+
+[ Upstream commit b7e188ec98b1644ff70a6d3624ea16aadc39f5e0 ]
+
+page_mapcount_is_zero() calculates accurately how many mappings a hugepage
+has in order to check against 0 only. This is a waste of cpu time. We
+can do this via page_not_mapped() to save some possible atomic_read
+cycles. Remove the function page_mapcount_is_zero() as it's not used
+anymore and move page_not_mapped() above try_to_unmap() to avoid
+identifier undeclared compilation error.
+
+Link: https://lkml.kernel.org/r/20210130084904.35307-1-linmiaohe@huawei.com
+Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/rmap.c | 11 +++--------
+ 1 file changed, 3 insertions(+), 8 deletions(-)
+
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 69ce68616cbf..70872d5b203c 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -1682,9 +1682,9 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg)
+ return is_vma_temporary_stack(vma);
+ }
+
+-static int page_mapcount_is_zero(struct page *page)
++static int page_not_mapped(struct page *page)
+ {
+- return !total_mapcount(page);
++ return !page_mapped(page);
+ }
+
+ /**
+@@ -1702,7 +1702,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
+ struct rmap_walk_control rwc = {
+ .rmap_one = try_to_unmap_one,
+ .arg = (void *)flags,
+- .done = page_mapcount_is_zero,
++ .done = page_not_mapped,
+ .anon_lock = page_lock_anon_vma_read,
+ };
+
+@@ -1726,11 +1726,6 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
+ return !page_mapcount(page) ? true : false;
+ }
+
+-static int page_not_mapped(struct page *page)
+-{
+- return !page_mapped(page);
+-}
+-
+ /**
+ * try_to_munlock - try to munlock a page
+ * @page: the page to be munlocked
+--
+2.30.2
+
--- /dev/null
+From e7cde9583c41df7304513a4761748383ee6e7a49 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:30 -0700
+Subject: mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk()
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit a7a69d8ba88d8dcee7ef00e91d413a4bd003a814 ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index b7a8009c1549..edca78609318 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -272,6 +272,10 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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) {
+--
+2.30.2
+
--- /dev/null
+From 5666449928de45522010acb795a9dacf599e8a6d Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 15 Jun 2021 18:23:45 -0700
+Subject: mm/thp: fix __split_huge_pmd_locked() on shmem migration entry
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 99fa8a48203d62b3743d866fc48ef6abaee682be ]
+
+Patch series "mm/thp: fix THP splitting unmap BUGs and related", v10.
+
+Here is v2 batch of long-standing THP bug fixes that I had not got
+around to sending before, but prompted now by Wang Yugui's report
+https://lore.kernel.org/linux-mm/20210412180659.B9E3.409509F4@e16-tech.com/
+
+Wang Yugui has tested a rollup of these fixes applied to 5.10.39, and
+they have done no harm, but have *not* fixed that issue: something more
+is needed and I have no idea of what.
+
+This patch (of 7):
+
+Stressing huge tmpfs page migration racing hole punch often crashed on
+the VM_BUG_ON(!pmd_present) in pmdp_huge_clear_flush(), with DEBUG_VM=y
+kernel; or shortly afterwards, on a bad dereference in
+__split_huge_pmd_locked() when DEBUG_VM=n. They forgot to allow for pmd
+migration entries in the non-anonymous case.
+
+Full disclosure: those particular experiments were on a kernel with more
+relaxed mmap_lock and i_mmap_rwsem locking, and were not repeated on the
+vanilla kernel: it is conceivable that stricter locking happens to avoid
+those cases, or makes them less likely; but __split_huge_pmd_locked()
+already allowed for pmd migration entries when handling anonymous THPs,
+so this commit brings the shmem and file THP handling into line.
+
+And while there: use old_pmd rather than _pmd, as in the following
+blocks; and make it clearer to the eye that the !vma_is_anonymous()
+block is self-contained, making an early return after accounting for
+unmapping.
+
+Link: https://lkml.kernel.org/r/af88612-1473-2eaa-903-8d1a448b26@google.com
+Link: https://lkml.kernel.org/r/dd221a99-efb3-cd1d-6256-7e646af29314@google.com
+Fixes: e71769ae5260 ("mm: enable thp migration for shmem thp")
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Cc: Yang Shi <shy828301@gmail.com>
+Cc: Wang Yugui <wangyugui@e16-tech.com>
+Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
+Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
+Cc: Alistair Popple <apopple@nvidia.com>
+Cc: Ralph Campbell <rcampbell@nvidia.com>
+Cc: Zi Yan <ziy@nvidia.com>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: Jue Wang <juew@google.com>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: Jan Kara <jack@suse.cz>
+Cc: Shakeel Butt <shakeelb@google.com>
+Cc: Oscar Salvador <osalvador@suse.de>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+
+Note on stable backport: this commit made intervening cleanups in
+pmdp_huge_clear_flush() redundant: here it's rediffed to skip them.
+
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/huge_memory.c | 27 ++++++++++++++++++---------
+ mm/pgtable-generic.c | 4 ++--
+ 2 files changed, 20 insertions(+), 11 deletions(-)
+
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 7c374c0fcf0c..ce6ca09840bd 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -2125,7 +2125,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
+ count_vm_event(THP_SPLIT_PMD);
+
+ if (!vma_is_anonymous(vma)) {
+- _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
++ old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+ /*
+ * We are going to unmap this huge page. So
+ * just go ahead and zap it
+@@ -2134,16 +2134,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
+ zap_deposited_table(mm, pmd);
+ if (vma_is_dax(vma))
+ return;
+- page = pmd_page(_pmd);
+- if (!PageDirty(page) && pmd_dirty(_pmd))
+- set_page_dirty(page);
+- if (!PageReferenced(page) && pmd_young(_pmd))
+- SetPageReferenced(page);
+- page_remove_rmap(page, true);
+- put_page(page);
++ if (unlikely(is_pmd_migration_entry(old_pmd))) {
++ swp_entry_t entry;
++
++ entry = pmd_to_swp_entry(old_pmd);
++ page = migration_entry_to_page(entry);
++ } else {
++ page = pmd_page(old_pmd);
++ if (!PageDirty(page) && pmd_dirty(old_pmd))
++ set_page_dirty(page);
++ if (!PageReferenced(page) && pmd_young(old_pmd))
++ SetPageReferenced(page);
++ page_remove_rmap(page, true);
++ put_page(page);
++ }
+ add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
+ return;
+- } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
++ }
++
++ if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
+ /*
+ * FIXME: Do we want to invalidate secondary mmu by calling
+ * mmu_notifier_invalidate_range() see comments below inside
+diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
+index cf2af04b34b9..36770fcdc358 100644
+--- a/mm/pgtable-generic.c
++++ b/mm/pgtable-generic.c
+@@ -125,8 +125,8 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
+ {
+ pmd_t pmd;
+ VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+- VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
+- !pmd_devmap(*pmdp)) || !pmd_present(*pmdp));
++ VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
++ !pmd_devmap(*pmdp));
+ pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
+ flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+ return pmd;
+--
+2.30.2
+
--- /dev/null
+From b307df8546b8d14b061f9ebac1b9f07f1c216128 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 15 Jun 2021 18:24:00 -0700
+Subject: mm/thp: fix page_address_in_vma() on file THP tails
+
+From: Jue Wang <juew@google.com>
+
+[ Upstream commit 31657170deaf1d8d2f6a1955fbc6fa9d228be036 ]
+
+Anon THP tails were already supported, but memory-failure may need to
+use page_address_in_vma() on file THP tails, which its page->mapping
+check did not permit: fix it.
+
+hughd adds: no current usage is known to hit the issue, but this does
+fix a subtle trap in a general helper: best fixed in stable sooner than
+later.
+
+Link: https://lkml.kernel.org/r/a0d9b53-bf5d-8bab-ac5-759dc61819c1@google.com
+Fixes: 800d8c63b2e9 ("shmem: add huge pages support")
+Signed-off-by: Jue Wang <juew@google.com>
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
+Reviewed-by: Yang Shi <shy828301@gmail.com>
+Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Cc: Alistair Popple <apopple@nvidia.com>
+Cc: Jan Kara <jack@suse.cz>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
+Cc: Oscar Salvador <osalvador@suse.de>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: Ralph Campbell <rcampbell@nvidia.com>
+Cc: Shakeel Butt <shakeelb@google.com>
+Cc: Wang Yugui <wangyugui@e16-tech.com>
+Cc: Zi Yan <ziy@nvidia.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/rmap.c | 8 ++++----
+ 1 file changed, 4 insertions(+), 4 deletions(-)
+
+diff --git a/mm/rmap.c b/mm/rmap.c
+index ff56c460af53..699f445e3e78 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -695,11 +695,11 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
+ if (!vma->anon_vma || !page__anon_vma ||
+ vma->anon_vma->root != page__anon_vma->root)
+ return -EFAULT;
+- } else if (page->mapping) {
+- if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping)
+- return -EFAULT;
+- } else
++ } else if (!vma->vm_file) {
++ return -EFAULT;
++ } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) {
+ return -EFAULT;
++ }
+
+ return vma_address(page, vma);
+ }
+--
+2.30.2
+
--- /dev/null
+From 2f8bbf0efd9612ee2d54f32d56fad78665c326c4 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 24 Jun 2021 18:39:26 -0700
+Subject: mm/thp: fix page_vma_mapped_walk() if THP mapped by ptes
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit a9a7504d9beaf395481faa91e70e2fd08f7a3dde ]
+
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/page_vma_mapped.c | 34 +++++++++++++++++++++++++---------
+ 1 file changed, 25 insertions(+), 9 deletions(-)
+
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 7239c38e99e2..b7a8009c1549 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -111,6 +111,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw)
+ return pfn_in_hpage(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
+@@ -179,16 +186,22 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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);
+ /*
+@@ -235,7 +248,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+
+ spin_unlock(ptl);
+ }
+- return false;
++ step_forward(pvmw, PMD_SIZE);
++ continue;
+ }
+ if (!map_pte(pvmw))
+ goto next_pte;
+@@ -265,7 +279,9 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ spin_lock(pvmw->ptl);
+ }
+ goto this_pte;
+- }
++ } while (pvmw->address < end);
++
++ return false;
+ }
+
+ /**
+--
+2.30.2
+
--- /dev/null
+From 26074089939cce82dadfad5af596fda00efd06be Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 15 Jun 2021 18:23:56 -0700
+Subject: mm/thp: fix vma_address() if virtual address below file offset
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 494334e43c16d63b878536a26505397fce6ff3a2 ]
+
+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).
+
+When that BUG() was changed to a WARN(), it would later crash on the
+VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma) in
+mm/internal.h:vma_address(), used by rmap_walk_file() for
+try_to_unmap().
+
+vma_address() is usually correct, but there's a wraparound case when the
+vm_start address is unusually low, but vm_pgoff not so low:
+vma_address() chooses max(start, vma->vm_start), but that decides on the
+wrong address, because start has become almost ULONG_MAX.
+
+Rewrite vma_address() to be more careful about vm_pgoff; move the
+VM_BUG_ON_VMA() out of it, returning -EFAULT for errors, so that it can
+be safely used from page_mapped_in_vma() and page_address_in_vma() too.
+
+Add vma_address_end() to apply similar care to end address calculation,
+in page_vma_mapped_walk() and page_mkclean_one() and try_to_unmap_one();
+though it raises a question of whether callers would do better to supply
+pvmw->end to page_vma_mapped_walk() - I chose not, for a smaller patch.
+
+An irritation is that their apparent generality breaks down on KSM
+pages, which cannot be located by the page->index that page_to_pgoff()
+uses: as commit 4b0ece6fa016 ("mm: migrate: fix remove_migration_pte()
+for ksm pages") once discovered. I dithered over the best thing to do
+about that, and have ended up with a VM_BUG_ON_PAGE(PageKsm) in both
+vma_address() and vma_address_end(); though the only place in danger of
+using it on them was try_to_unmap_one().
+
+Sidenote: vma_address() and vma_address_end() now use compound_nr() on a
+head page, instead of thp_size(): to make the right calculation on a
+hugetlbfs page, whether or not THPs are configured. try_to_unmap() is
+used on hugetlbfs pages, but perhaps the wrong calculation never
+mattered.
+
+Link: https://lkml.kernel.org/r/caf1c1a3-7cfb-7f8f-1beb-ba816e932825@google.com
+Fixes: a8fa41ad2f6f ("mm, rmap: check all VMAs that PTE-mapped THP can be part of")
+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: Jan Kara <jack@suse.cz>
+Cc: Jue Wang <juew@google.com>
+Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
+Cc: Oscar Salvador <osalvador@suse.de>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: Ralph Campbell <rcampbell@nvidia.com>
+Cc: Shakeel Butt <shakeelb@google.com>
+Cc: Wang Yugui <wangyugui@e16-tech.com>
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+
+Note on stable backport: fixed up conflicts on intervening thp_size(),
+and mmu_notifier_range initializations; substitute for compound_nr().
+
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/internal.h | 53 ++++++++++++++++++++++++++++++++------------
+ mm/page_vma_mapped.c | 16 +++++--------
+ mm/rmap.c | 14 ++++++------
+ 3 files changed, 52 insertions(+), 31 deletions(-)
+
+diff --git a/mm/internal.h b/mm/internal.h
+index 397183c8fe47..3a2e973138d3 100644
+--- a/mm/internal.h
++++ b/mm/internal.h
+@@ -331,27 +331,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
+ extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
+
+ /*
+- * At what user virtual address is page expected in @vma?
++ * At what user virtual address is page expected in vma?
++ * Returns -EFAULT if all of the page is outside the range of vma.
++ * If page is a compound head, the entire compound page is considered.
+ */
+ static inline unsigned long
+-__vma_address(struct page *page, struct vm_area_struct *vma)
++vma_address(struct page *page, struct vm_area_struct *vma)
+ {
+- pgoff_t pgoff = page_to_pgoff(page);
+- return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
++ pgoff_t pgoff;
++ unsigned long address;
++
++ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
++ pgoff = page_to_pgoff(page);
++ if (pgoff >= vma->vm_pgoff) {
++ 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)
++ address = -EFAULT;
++ } else if (PageHead(page) &&
++ pgoff + (1UL << compound_order(page)) - 1 >= vma->vm_pgoff) {
++ /* Test above avoids possibility of wrap to 0 on 32-bit */
++ address = vma->vm_start;
++ } else {
++ address = -EFAULT;
++ }
++ return address;
+ }
+
++/*
++ * Then at what user virtual address will none of the page 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(struct page *page, struct vm_area_struct *vma)
++vma_address_end(struct page *page, struct vm_area_struct *vma)
+ {
+- unsigned long start, end;
+-
+- start = __vma_address(page, vma);
+- end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);
+-
+- /* page should be within @vma mapping range */
+- VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);
+-
+- return max(start, vma->vm_start);
++ pgoff_t pgoff;
++ unsigned long address;
++
++ VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
++ pgoff = page_to_pgoff(page) + (1UL << compound_order(page));
++ 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)
++ address = vma->vm_end;
++ return address;
+ }
+
+ #else /* !CONFIG_MMU */
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 08e283ad4660..bb7488e86bea 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -224,18 +224,18 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ if (!map_pte(pvmw))
+ goto next_pte;
+ while (1) {
++ unsigned long end;
++
+ if (check_pte(pvmw))
+ return true;
+ next_pte:
+ /* Seek to next pte only makes sense for THP */
+ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
+ return not_found(pvmw);
++ end = vma_address_end(pvmw->page, pvmw->vma);
+ do {
+ pvmw->address += PAGE_SIZE;
+- if (pvmw->address >= pvmw->vma->vm_end ||
+- pvmw->address >=
+- __vma_address(pvmw->page, pvmw->vma) +
+- hpage_nr_pages(pvmw->page) * PAGE_SIZE)
++ if (pvmw->address >= end)
+ return not_found(pvmw);
+ /* Did we cross page table boundary? */
+ if (pvmw->address % PMD_SIZE == 0) {
+@@ -273,14 +273,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+ .vma = vma,
+ .flags = PVMW_SYNC,
+ };
+- unsigned long start, end;
+-
+- start = __vma_address(page, vma);
+- end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);
+
+- if (unlikely(end < vma->vm_start || start >= vma->vm_end))
++ pvmw.address = vma_address(page, vma);
++ if (pvmw.address == -EFAULT)
+ return 0;
+- pvmw.address = max(start, vma->vm_start);
+ if (!page_vma_mapped_walk(&pvmw))
+ return 0;
+ page_vma_mapped_walk_done(&pvmw);
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 5df055654e63..ff56c460af53 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -686,7 +686,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags)
+ */
+ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
+ {
+- unsigned long address;
+ if (PageAnon(page)) {
+ struct anon_vma *page__anon_vma = page_anon_vma(page);
+ /*
+@@ -701,10 +700,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
+ return -EFAULT;
+ } else
+ return -EFAULT;
+- address = __vma_address(page, vma);
+- if (unlikely(address < vma->vm_start || address >= vma->vm_end))
+- return -EFAULT;
+- return address;
++
++ return vma_address(page, vma);
+ }
+
+ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
+@@ -896,7 +893,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
+ * We have to assume the worse case ie pmd for invalidation. Note that
+ * the page can not be free from this function.
+ */
+- end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page)));
++ end = vma_address_end(page, vma);
+ mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
+
+ while (page_vma_mapped_walk(&pvmw)) {
+@@ -1378,7 +1375,8 @@ 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.
+ */
+- end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page)));
++ end = PageKsm(page) ?
++ address + PAGE_SIZE : vma_address_end(page, vma);
+ if (PageHuge(page)) {
+ /*
+ * If sharing is possible, start and end will be adjusted
+@@ -1835,6 +1833,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc,
+ struct vm_area_struct *vma = avc->vma;
+ unsigned long address = vma_address(page, vma);
+
++ VM_BUG_ON_VMA(address == -EFAULT, vma);
+ cond_resched();
+
+ if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
+@@ -1889,6 +1888,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc,
+ pgoff_start, pgoff_end) {
+ unsigned long address = vma_address(page, vma);
+
++ VM_BUG_ON_VMA(address == -EFAULT, vma);
+ cond_resched();
+
+ if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg))
+--
+2.30.2
+
--- /dev/null
+From f26cbd96d3174c14752a230c738e876f153856f2 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 15 Jun 2021 18:23:49 -0700
+Subject: mm/thp: make is_huge_zero_pmd() safe and quicker
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 3b77e8c8cde581dadab9a0f1543a347e24315f11 ]
+
+Most callers of is_huge_zero_pmd() supply a pmd already verified
+present; but a few (notably zap_huge_pmd()) do not - it might be a pmd
+migration entry, in which the pfn is encoded differently from a present
+pmd: which might pass the is_huge_zero_pmd() test (though not on x86,
+since L1TF forced us to protect against that); or perhaps even crash in
+pmd_page() applied to a swap-like entry.
+
+Make it safe by adding pmd_present() check into is_huge_zero_pmd()
+itself; and make it quicker by saving huge_zero_pfn, so that
+is_huge_zero_pmd() will not need to do that pmd_page() lookup each time.
+
+__split_huge_pmd_locked() checked pmd_trans_huge() before: that worked,
+but is unnecessary now that is_huge_zero_pmd() checks present.
+
+Link: https://lkml.kernel.org/r/21ea9ca-a1f5-8b90-5e88-95fb1c49bbfa@google.com
+Fixes: e71769ae5260 ("mm: enable thp migration for shmem thp")
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Reviewed-by: Yang Shi <shy828301@gmail.com>
+Cc: Alistair Popple <apopple@nvidia.com>
+Cc: Jan Kara <jack@suse.cz>
+Cc: Jue Wang <juew@google.com>
+Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
+Cc: Oscar Salvador <osalvador@suse.de>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: Ralph Campbell <rcampbell@nvidia.com>
+Cc: Shakeel Butt <shakeelb@google.com>
+Cc: Wang Yugui <wangyugui@e16-tech.com>
+Cc: Zi Yan <ziy@nvidia.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/linux/huge_mm.h | 8 +++++++-
+ mm/huge_memory.c | 5 ++++-
+ 2 files changed, 11 insertions(+), 2 deletions(-)
+
+diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
+index e375f2249f52..becf9b1eae5a 100644
+--- a/include/linux/huge_mm.h
++++ b/include/linux/huge_mm.h
+@@ -224,6 +224,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
+ extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
+
+ extern struct page *huge_zero_page;
++extern unsigned long huge_zero_pfn;
+
+ static inline bool is_huge_zero_page(struct page *page)
+ {
+@@ -232,7 +233,7 @@ static inline bool is_huge_zero_page(struct page *page)
+
+ static inline bool is_huge_zero_pmd(pmd_t pmd)
+ {
+- return is_huge_zero_page(pmd_page(pmd));
++ return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd);
+ }
+
+ static inline bool is_huge_zero_pud(pud_t pud)
+@@ -342,6 +343,11 @@ static inline bool is_huge_zero_page(struct page *page)
+ return false;
+ }
+
++static inline bool is_huge_zero_pmd(pmd_t pmd)
++{
++ return false;
++}
++
+ static inline bool is_huge_zero_pud(pud_t pud)
+ {
+ return false;
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index ce6ca09840bd..82ed62775c00 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -62,6 +62,7 @@ static struct shrinker deferred_split_shrinker;
+
+ static atomic_t huge_zero_refcount;
+ struct page *huge_zero_page __read_mostly;
++unsigned long huge_zero_pfn __read_mostly = ~0UL;
+
+ bool transparent_hugepage_enabled(struct vm_area_struct *vma)
+ {
+@@ -93,6 +94,7 @@ static struct page *get_huge_zero_page(void)
+ __free_pages(zero_page, compound_order(zero_page));
+ goto retry;
+ }
++ WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
+
+ /* We take additional reference here. It will be put back by shrinker */
+ atomic_set(&huge_zero_refcount, 2);
+@@ -142,6 +144,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
+ if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
+ struct page *zero_page = xchg(&huge_zero_page, NULL);
+ BUG_ON(zero_page == NULL);
++ WRITE_ONCE(huge_zero_pfn, ~0UL);
+ __free_pages(zero_page, compound_order(zero_page));
+ return HPAGE_PMD_NR;
+ }
+@@ -2152,7 +2155,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
+ return;
+ }
+
+- if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
++ if (is_huge_zero_pmd(*pmd)) {
+ /*
+ * FIXME: Do we want to invalidate secondary mmu by calling
+ * mmu_notifier_invalidate_range() see comments below inside
+--
+2.30.2
+
--- /dev/null
+From 33053f106aaa9783cdad460f450f979b955faf6d Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 15 Jun 2021 18:24:07 -0700
+Subject: mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split
+
+From: Yang Shi <shy828301@gmail.com>
+
+[ Upstream commit 504e070dc08f757bccaed6d05c0f53ecbfac8a23 ]
+
+When debugging the bug reported by Wang Yugui [1], try_to_unmap() may
+fail, but the first VM_BUG_ON_PAGE() just checks page_mapcount() however
+it may miss the failure when head page is unmapped but other subpage is
+mapped. Then the second DEBUG_VM BUG() that check total mapcount would
+catch it. This may incur some confusion.
+
+As this is not a fatal issue, so consolidate the two DEBUG_VM checks
+into one VM_WARN_ON_ONCE_PAGE().
+
+[1] https://lore.kernel.org/linux-mm/20210412180659.B9E3.409509F4@e16-tech.com/
+
+Link: https://lkml.kernel.org/r/d0f0db68-98b8-ebfb-16dc-f29df24cf012@google.com
+Signed-off-by: Yang Shi <shy828301@gmail.com>
+Reviewed-by: Zi Yan <ziy@nvidia.com>
+Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Cc: Alistair Popple <apopple@nvidia.com>
+Cc: Jan Kara <jack@suse.cz>
+Cc: Jue Wang <juew@google.com>
+Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
+Cc: Oscar Salvador <osalvador@suse.de>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: Ralph Campbell <rcampbell@nvidia.com>
+Cc: Shakeel Butt <shakeelb@google.com>
+Cc: Wang Yugui <wangyugui@e16-tech.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+
+Note on stable backport: fixed up variables and split_queue_lock in
+split_huge_page_to_list(), and conflict on ttu_flags in unmap_page().
+
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ mm/huge_memory.c | 24 +++++++-----------------
+ 1 file changed, 7 insertions(+), 17 deletions(-)
+
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 78c1ad5f8109..4400957d8e4e 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -2431,15 +2431,15 @@ static void unmap_page(struct page *page)
+ {
+ enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
+ TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC;
+- bool unmap_success;
+
+ VM_BUG_ON_PAGE(!PageHead(page), page);
+
+ if (PageAnon(page))
+ ttu_flags |= TTU_SPLIT_FREEZE;
+
+- unmap_success = try_to_unmap(page, ttu_flags);
+- VM_BUG_ON_PAGE(!unmap_success, page);
++ try_to_unmap(page, ttu_flags);
++
++ VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
+ }
+
+ static void remap_page(struct page *page)
+@@ -2698,7 +2698,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
+ struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
+ struct anon_vma *anon_vma = NULL;
+ struct address_space *mapping = NULL;
+- int count, mapcount, extra_pins, ret;
++ int extra_pins, ret;
+ bool mlocked;
+ unsigned long flags;
+ pgoff_t end;
+@@ -2760,7 +2760,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
+
+ mlocked = PageMlocked(page);
+ unmap_page(head);
+- VM_BUG_ON_PAGE(compound_mapcount(head), head);
+
+ /* Make sure the page is not on per-CPU pagevec as it takes pin */
+ if (mlocked)
+@@ -2786,9 +2785,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
+
+ /* Prevent deferred_split_scan() touching ->_refcount */
+ spin_lock(&pgdata->split_queue_lock);
+- count = page_count(head);
+- mapcount = total_mapcount(head);
+- if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
++ if (page_ref_freeze(head, 1 + extra_pins)) {
+ if (!list_empty(page_deferred_list(head))) {
+ pgdata->split_queue_len--;
+ list_del(page_deferred_list(head));
+@@ -2804,16 +2801,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
+ } else
+ ret = 0;
+ } else {
+- if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
+- pr_alert("total_mapcount: %u, page_count(): %u\n",
+- mapcount, count);
+- if (PageTail(page))
+- dump_page(head, NULL);
+- dump_page(page, "total_mapcount(head) > 0");
+- BUG();
+- }
+ spin_unlock(&pgdata->split_queue_lock);
+-fail: if (mapping)
++fail:
++ if (mapping)
+ xa_unlock(&mapping->i_pages);
+ spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags);
+ remap_page(head);
+--
+2.30.2
+
--- /dev/null
+From db4c876505c08b94916c5292805f0851402638c7 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 15 Jun 2021 18:23:53 -0700
+Subject: mm/thp: try_to_unmap() use TTU_SYNC for safe splitting
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 732ed55823fc3ad998d43b86bf771887bcc5ec67 ]
+
+Stressing huge tmpfs often crashed on unmap_page()'s VM_BUG_ON_PAGE
+(!unmap_success): with dump_page() showing mapcount:1, but then its raw
+struct page output showing _mapcount ffffffff i.e. mapcount 0.
+
+And even if that particular VM_BUG_ON_PAGE(!unmap_success) is removed,
+it is immediately followed by a VM_BUG_ON_PAGE(compound_mapcount(head)),
+and further down an IS_ENABLED(CONFIG_DEBUG_VM) total_mapcount BUG():
+all indicative of some mapcount difficulty in development here perhaps.
+But the !CONFIG_DEBUG_VM path handles the failures correctly and
+silently.
+
+I believe the problem is that once a racing unmap has cleared pte or
+pmd, try_to_unmap_one() may skip taking the page table lock, and emerge
+from try_to_unmap() before the racing task has reached decrementing
+mapcount.
+
+Instead of abandoning the unsafe VM_BUG_ON_PAGE(), and the ones that
+follow, use PVMW_SYNC in try_to_unmap_one() in this case: adding
+TTU_SYNC to the options, and passing that from unmap_page().
+
+When CONFIG_DEBUG_VM, or for non-debug too? Consensus is to do the same
+for both: the slight overhead added should rarely matter, except perhaps
+if splitting sparsely-populated multiply-mapped shmem. Once confident
+that bugs are fixed, TTU_SYNC here can be removed, and the race
+tolerated.
+
+Link: https://lkml.kernel.org/r/c1e95853-8bcd-d8fd-55fa-e7f2488e78f@google.com
+Fixes: fec89c109f3a ("thp: rewrite freeze_page()/unfreeze_page() with generic rmap walkers")
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Cc: Alistair Popple <apopple@nvidia.com>
+Cc: Jan Kara <jack@suse.cz>
+Cc: Jue Wang <juew@google.com>
+Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
+Cc: Oscar Salvador <osalvador@suse.de>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: Ralph Campbell <rcampbell@nvidia.com>
+Cc: Shakeel Butt <shakeelb@google.com>
+Cc: Wang Yugui <wangyugui@e16-tech.com>
+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>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+
+Note on stable backport: upstream TTU_SYNC 0x10 takes the value which
+5.11 commit 013339df116c ("mm/rmap: always do TTU_IGNORE_ACCESS") freed.
+It is very tempting to backport that commit (as 5.10 already did) and
+make no change here; but on reflection, good as that commit is, I'm
+reluctant to include any possible side-effect of it in this series.
+
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/linux/rmap.h | 3 ++-
+ mm/huge_memory.c | 2 +-
+ mm/page_vma_mapped.c | 11 +++++++++++
+ mm/rmap.c | 17 ++++++++++++++++-
+ 4 files changed, 30 insertions(+), 3 deletions(-)
+
+diff --git a/include/linux/rmap.h b/include/linux/rmap.h
+index d7d6d4eb1794..91ccae946716 100644
+--- a/include/linux/rmap.h
++++ b/include/linux/rmap.h
+@@ -98,7 +98,8 @@ enum ttu_flags {
+ * do a final flush if necessary */
+ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock:
+ * caller holds it */
+- TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */
++ TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */
++ TTU_SYNC = 0x200, /* avoid racy checks with PVMW_SYNC */
+ };
+
+ #ifdef CONFIG_MMU
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 82ed62775c00..78c1ad5f8109 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -2430,7 +2430,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
+ static void unmap_page(struct page *page)
+ {
+ enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS |
+- TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
++ TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC;
+ bool unmap_success;
+
+ VM_BUG_ON_PAGE(!PageHead(page), page);
+diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
+index 11df03e71288..08e283ad4660 100644
+--- a/mm/page_vma_mapped.c
++++ b/mm/page_vma_mapped.c
+@@ -208,6 +208,17 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw)
+ 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(pvmw->page)) {
++ spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
++
++ spin_unlock(ptl);
++ }
+ return false;
+ }
+ if (!map_pte(pvmw))
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 70872d5b203c..5df055654e63 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -1348,6 +1348,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
+ unsigned long start = address, end;
+ enum ttu_flags flags = (enum ttu_flags)arg;
+
++ /*
++ * When racing against e.g. zap_pte_range() on another cpu,
++ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
++ * try_to_unmap() may return false when it is about to become true,
++ * if page table locking is skipped: use TTU_SYNC to wait for that.
++ */
++ if (flags & TTU_SYNC)
++ pvmw.flags = PVMW_SYNC;
++
+ /* munlock has nothing to gain from examining un-locked vmas */
+ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
+ return true;
+@@ -1723,7 +1732,13 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags)
+ else
+ rmap_walk(page, &rwc);
+
+- return !page_mapcount(page) ? true : false;
++ /*
++ * When racing against e.g. zap_pte_range() on another cpu,
++ * in between its ptep_get_and_clear_full() and page_remove_rmap(),
++ * try_to_unmap() may return false when it is about to become true,
++ * if page table locking is skipped: use TTU_SYNC to wait for that.
++ */
++ return !page_mapcount(page);
+ }
+
+ /**
+--
+2.30.2
+
--- /dev/null
+From 221080c4e3e372574021ee5d730df09e9418508c Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 15 Jun 2021 18:24:03 -0700
+Subject: mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page()
+
+From: Hugh Dickins <hughd@google.com>
+
+[ Upstream commit 22061a1ffabdb9c3385de159c5db7aac3a4df1cc ]
+
+There is a race between THP unmapping and truncation, when truncate sees
+pmd_none() and skips the entry, after munmap's zap_huge_pmd() cleared
+it, but before its page_remove_rmap() gets to decrement
+compound_mapcount: generating false "BUG: Bad page cache" reports that
+the page is still mapped when deleted. This commit fixes that, but not
+in the way I hoped.
+
+The first attempt used try_to_unmap(page, TTU_SYNC|TTU_IGNORE_MLOCK)
+instead of unmap_mapping_range() in truncate_cleanup_page(): it has
+often been an annoyance that we usually call unmap_mapping_range() with
+no pages locked, but there apply it to a single locked page.
+try_to_unmap() looks more suitable for a single locked page.
+
+However, try_to_unmap_one() contains a VM_BUG_ON_PAGE(!pvmw.pte,page):
+it is used to insert THP migration entries, but not used to unmap THPs.
+Copy zap_huge_pmd() and add THP handling now? Perhaps, but their TLB
+needs are different, I'm too ignorant of the DAX cases, and couldn't
+decide how far to go for anon+swap. Set that aside.
+
+The second attempt took a different tack: make no change in truncate.c,
+but modify zap_huge_pmd() to insert an invalidated huge pmd instead of
+clearing it initially, then pmd_clear() between page_remove_rmap() and
+unlocking at the end. Nice. But powerpc blows that approach out of the
+water, with its serialize_against_pte_lookup(), and interesting pgtable
+usage. It would need serious help to get working on powerpc (with a
+minor optimization issue on s390 too). Set that aside.
+
+Just add an "if (page_mapped(page)) synchronize_rcu();" or other such
+delay, after unmapping in truncate_cleanup_page()? Perhaps, but though
+that's likely to reduce or eliminate the number of incidents, it would
+give less assurance of whether we had identified the problem correctly.
+
+This successful iteration introduces "unmap_mapping_page(page)" instead
+of try_to_unmap(), and goes the usual unmap_mapping_range_tree() route,
+with an addition to details. Then zap_pmd_range() watches for this
+case, and does spin_unlock(pmd_lock) if so - just like
+page_vma_mapped_walk() now does in the PVMW_SYNC case. Not pretty, but
+safe.
+
+Note that unmap_mapping_page() is doing a VM_BUG_ON(!PageLocked) to
+assert its interface; but currently that's only used to make sure that
+page->mapping is stable, and zap_pmd_range() doesn't care if the page is
+locked or not. Along these lines, in invalidate_inode_pages2_range()
+move the initial unmap_mapping_range() out from under page lock, before
+then calling unmap_mapping_page() under page lock if still mapped.
+
+Link: https://lkml.kernel.org/r/a2a4a148-cdd8-942c-4ef8-51b77f643dbe@google.com
+Fixes: fc127da085c2 ("truncate: handle file thp")
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+Reviewed-by: Yang Shi <shy828301@gmail.com>
+Cc: Alistair Popple <apopple@nvidia.com>
+Cc: Jan Kara <jack@suse.cz>
+Cc: Jue Wang <juew@google.com>
+Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
+Cc: Miaohe Lin <linmiaohe@huawei.com>
+Cc: Minchan Kim <minchan@kernel.org>
+Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
+Cc: Oscar Salvador <osalvador@suse.de>
+Cc: Peter Xu <peterx@redhat.com>
+Cc: Ralph Campbell <rcampbell@nvidia.com>
+Cc: Shakeel Butt <shakeelb@google.com>
+Cc: Wang Yugui <wangyugui@e16-tech.com>
+Cc: Zi Yan <ziy@nvidia.com>
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
+Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
+
+Note on stable backport: fixed up call to truncate_cleanup_page()
+in truncate_inode_pages_range(). Use hpage_nr_pages() in
+unmap_mapping_page().
+
+Signed-off-by: Hugh Dickins <hughd@google.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ include/linux/mm.h | 3 +++
+ mm/memory.c | 41 +++++++++++++++++++++++++++++++++++++++++
+ mm/truncate.c | 43 +++++++++++++++++++------------------------
+ 3 files changed, 63 insertions(+), 24 deletions(-)
+
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index f6ecf41aea83..c736c677b876 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -1338,6 +1338,7 @@ struct zap_details {
+ struct address_space *check_mapping; /* Check page->mapping if set */
+ pgoff_t first_index; /* Lowest page->index to unmap */
+ pgoff_t last_index; /* Highest page->index to unmap */
++ struct page *single_page; /* Locked page to be unmapped */
+ };
+
+ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
+@@ -1428,6 +1429,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
+ extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+ unsigned long address, unsigned int fault_flags,
+ bool *unlocked);
++void unmap_mapping_page(struct page *page);
+ void unmap_mapping_pages(struct address_space *mapping,
+ pgoff_t start, pgoff_t nr, bool even_cows);
+ void unmap_mapping_range(struct address_space *mapping,
+@@ -1448,6 +1450,7 @@ static inline int fixup_user_fault(struct task_struct *tsk,
+ BUG();
+ return -EFAULT;
+ }
++static inline void unmap_mapping_page(struct page *page) { }
+ static inline void unmap_mapping_pages(struct address_space *mapping,
+ pgoff_t start, pgoff_t nr, bool even_cows) { }
+ static inline void unmap_mapping_range(struct address_space *mapping,
+diff --git a/mm/memory.c b/mm/memory.c
+index c2011c51f15d..49b546cdce0d 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -1439,7 +1439,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
+ else if (zap_huge_pmd(tlb, vma, pmd, addr))
+ goto next;
+ /* fall through */
++ } else if (details && details->single_page &&
++ PageTransCompound(details->single_page) &&
++ next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
++ spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
++ /*
++ * Take and drop THP pmd lock so that we cannot return
++ * prematurely, while zap_huge_pmd() has cleared *pmd,
++ * but not yet decremented compound_mapcount().
++ */
++ spin_unlock(ptl);
+ }
++
+ /*
+ * Here there can be other concurrent MADV_DONTNEED or
+ * trans huge page faults running, and if the pmd is
+@@ -2924,6 +2935,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root,
+ }
+ }
+
++/**
++ * unmap_mapping_page() - Unmap single page from processes.
++ * @page: The locked page to be unmapped.
++ *
++ * Unmap this page from any userspace process which still has it mmaped.
++ * Typically, for efficiency, the range of nearby pages has already been
++ * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once
++ * truncation or invalidation holds the lock on a page, it may find that
++ * the page has been remapped again: and then uses unmap_mapping_page()
++ * to unmap it finally.
++ */
++void unmap_mapping_page(struct page *page)
++{
++ struct address_space *mapping = page->mapping;
++ struct zap_details details = { };
++
++ VM_BUG_ON(!PageLocked(page));
++ VM_BUG_ON(PageTail(page));
++
++ details.check_mapping = mapping;
++ details.first_index = page->index;
++ details.last_index = page->index + hpage_nr_pages(page) - 1;
++ details.single_page = page;
++
++ i_mmap_lock_write(mapping);
++ if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
++ unmap_mapping_range_tree(&mapping->i_mmap, &details);
++ i_mmap_unlock_write(mapping);
++}
++
+ /**
+ * unmap_mapping_pages() - Unmap pages from processes.
+ * @mapping: The address space containing pages to be unmapped.
+diff --git a/mm/truncate.c b/mm/truncate.c
+index 71b65aab8077..43c73db17a0a 100644
+--- a/mm/truncate.c
++++ b/mm/truncate.c
+@@ -175,13 +175,10 @@ void do_invalidatepage(struct page *page, unsigned int offset,
+ * its lock, b) when a concurrent invalidate_mapping_pages got there first and
+ * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
+ */
+-static void
+-truncate_cleanup_page(struct address_space *mapping, struct page *page)
++static void truncate_cleanup_page(struct page *page)
+ {
+- if (page_mapped(page)) {
+- pgoff_t nr = PageTransHuge(page) ? HPAGE_PMD_NR : 1;
+- unmap_mapping_pages(mapping, page->index, nr, false);
+- }
++ if (page_mapped(page))
++ unmap_mapping_page(page);
+
+ if (page_has_private(page))
+ do_invalidatepage(page, 0, PAGE_SIZE);
+@@ -226,7 +223,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page)
+ if (page->mapping != mapping)
+ return -EIO;
+
+- truncate_cleanup_page(mapping, page);
++ truncate_cleanup_page(page);
+ delete_from_page_cache(page);
+ return 0;
+ }
+@@ -364,7 +361,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
+ pagevec_add(&locked_pvec, page);
+ }
+ for (i = 0; i < pagevec_count(&locked_pvec); i++)
+- truncate_cleanup_page(mapping, locked_pvec.pages[i]);
++ truncate_cleanup_page(locked_pvec.pages[i]);
+ delete_from_page_cache_batch(mapping, &locked_pvec);
+ for (i = 0; i < pagevec_count(&locked_pvec); i++)
+ unlock_page(locked_pvec.pages[i]);
+@@ -703,6 +700,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
+ continue;
+ }
+
++ if (!did_range_unmap && page_mapped(page)) {
++ /*
++ * If page is mapped, before taking its lock,
++ * zap the rest of the file in one hit.
++ */
++ unmap_mapping_pages(mapping, index,
++ (1 + end - index), false);
++ did_range_unmap = 1;
++ }
++
+ lock_page(page);
+ WARN_ON(page_to_index(page) != index);
+ if (page->mapping != mapping) {
+@@ -710,23 +717,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
+ continue;
+ }
+ wait_on_page_writeback(page);
+- if (page_mapped(page)) {
+- if (!did_range_unmap) {
+- /*
+- * Zap the rest of the file in one hit.
+- */
+- unmap_mapping_pages(mapping, index,
+- (1 + end - index), false);
+- did_range_unmap = 1;
+- } else {
+- /*
+- * Just zap this page
+- */
+- unmap_mapping_pages(mapping, index,
+- 1, false);
+- }
+- }
++
++ if (page_mapped(page))
++ unmap_mapping_page(page);
+ BUG_ON(page_mapped(page));
++
+ ret2 = do_launder_page(mapping, page);
+ if (ret2 == 0) {
+ if (!invalidate_complete_page2(mapping, page))
+--
+2.30.2
+
--- /dev/null
+mm-add-vm_warn_on_once_page-macro.patch
+mm-rmap-remove-unneeded-semicolon-in-page_not_mapped.patch
+mm-rmap-use-page_not_mapped-in-try_to_unmap.patch
+mm-thp-fix-__split_huge_pmd_locked-on-shmem-migratio.patch
+mm-thp-make-is_huge_zero_pmd-safe-and-quicker.patch
+mm-thp-try_to_unmap-use-ttu_sync-for-safe-splitting.patch
+mm-thp-fix-vma_address-if-virtual-address-below-file.patch
+mm-thp-fix-page_address_in_vma-on-file-thp-tails.patch
+mm-thp-unmap_mapping_page-to-fix-thp-truncate_cleanu.patch
+mm-thp-replace-debug_vm-bug-with-vm_warn-when-unmap-.patch
+mm-page_vma_mapped_walk-use-page-for-pvmw-page.patch
+mm-page_vma_mapped_walk-settle-pagehuge-on-entry.patch
+mm-page_vma_mapped_walk-use-pmde-for-pvmw-pmd.patch
+mm-page_vma_mapped_walk-prettify-pvmw_migration-bloc.patch
+mm-page_vma_mapped_walk-crossing-page-table-boundary.patch
+mm-page_vma_mapped_walk-add-a-level-of-indentation.patch
+mm-page_vma_mapped_walk-use-goto-instead-of-while-1.patch
+mm-page_vma_mapped_walk-get-vma_address_end-earlier.patch
+mm-thp-fix-page_vma_mapped_walk-if-thp-mapped-by-pte.patch
+mm-thp-another-pvmw_sync-fix-in-page_vma_mapped_walk.patch
+mm-futex-fix-shared-futex-pgoff-on-shmem-huge-page.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
