The patch titled
Subject: mm/khugepaged: fix GUP-fast interaction by sending IPI
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
mm-khugepaged-fix-gup-fast-interaction-by-sending-ipi.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Jann Horn <jannh(a)google.com>
Subject: mm/khugepaged: fix GUP-fast interaction by sending IPI
Date: Fri, 25 Nov 2022 22:37:13 +0100
Since commit 70cbc3cc78a99 ("mm: gup: fix the fast GUP race against THP
collapse"), the lockless_pages_from_mm() fastpath rechecks the pmd_t to
ensure that the page table was not removed by khugepaged in between.
However, lockless_pages_from_mm() still requires that the page table is
not concurrently freed. Fix it by sending IPIs (if the architecture uses
semi-RCU-style page table freeing) before freeing/reusing page tables.
Link: https://lkml.kernel.org/r/20221125213714.4115729-2-jannh@google.com
Fixes: ba76149f47d8 ("thp: khugepaged")
Signed-off-by: Jann Horn <jannh(a)google.com>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: John Hubbard <jhubbard(a)nvidia.com>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Yang Shi <shy828301(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/asm-generic/tlb.h | 4 ++++
mm/khugepaged.c | 2 ++
mm/mmu_gather.c | 4 +---
3 files changed, 7 insertions(+), 3 deletions(-)
--- a/include/asm-generic/tlb.h~mm-khugepaged-fix-gup-fast-interaction-by-sending-ipi
+++ a/include/asm-generic/tlb.h
@@ -222,12 +222,16 @@ extern void tlb_remove_table(struct mmu_
#define tlb_needs_table_invalidate() (true)
#endif
+void tlb_remove_table_sync_one(void);
+
#else
#ifdef tlb_needs_table_invalidate
#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
#endif
+static inline void tlb_remove_table_sync_one(void) { }
+
#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
--- a/mm/khugepaged.c~mm-khugepaged-fix-gup-fast-interaction-by-sending-ipi
+++ a/mm/khugepaged.c
@@ -1051,6 +1051,7 @@ static int collapse_huge_page(struct mm_
_pmd = pmdp_collapse_flush(vma, address, pmd);
spin_unlock(pmd_ptl);
mmu_notifier_invalidate_range_end(&range);
+ tlb_remove_table_sync_one();
spin_lock(pte_ptl);
result = __collapse_huge_page_isolate(vma, address, pte, cc,
@@ -1410,6 +1411,7 @@ static void collapse_and_free_pmd(struct
lockdep_assert_held_write(&vma->anon_vma->root->rwsem);
pmd = pmdp_collapse_flush(vma, addr, pmdp);
+ tlb_remove_table_sync_one();
mm_dec_nr_ptes(mm);
page_table_check_pte_clear_range(mm, addr, pmd);
pte_free(mm, pmd_pgtable(pmd));
--- a/mm/mmu_gather.c~mm-khugepaged-fix-gup-fast-interaction-by-sending-ipi
+++ a/mm/mmu_gather.c
@@ -153,7 +153,7 @@ static void tlb_remove_table_smp_sync(vo
/* Simply deliver the interrupt */
}
-static void tlb_remove_table_sync_one(void)
+void tlb_remove_table_sync_one(void)
{
/*
* This isn't an RCU grace period and hence the page-tables cannot be
@@ -177,8 +177,6 @@ static void tlb_remove_table_free(struct
#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */
-static void tlb_remove_table_sync_one(void) { }
-
static void tlb_remove_table_free(struct mmu_table_batch *batch)
{
__tlb_remove_table_free(batch);
_
Patches currently in -mm which might be from jannh(a)google.com are
mm-khugepaged-take-the-right-locks-for-page-table-retraction.patch
mm-khugepaged-fix-gup-fast-interaction-by-sending-ipi.patch
mm-khugepaged-invoke-mmu-notifiers-in-shmem-file-collapse-paths.patch
The patch titled
Subject: mm/khugepaged: take the right locks for page table retraction
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
mm-khugepaged-take-the-right-locks-for-page-table-retraction.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Jann Horn <jannh(a)google.com>
Subject: mm/khugepaged: take the right locks for page table retraction
Date: Fri, 25 Nov 2022 22:37:12 +0100
pagetable walks on address ranges mapped by VMAs can be done under the
mmap lock, the lock of an anon_vma attached to the VMA, or the lock of the
VMA's address_space. Only one of these needs to be held, and it does not
need to be held in exclusive mode.
Under those circumstances, the rules for concurrent access to page table
entries are:
- Terminal page table entries (entries that don't point to another page
table) can be arbitrarily changed under the page table lock, with the
exception that they always need to be consistent for
hardware page table walks and lockless_pages_from_mm().
This includes that they can be changed into non-terminal entries.
- Non-terminal page table entries (which point to another page table)
can not be modified; readers are allowed to READ_ONCE() an entry, verify
that it is non-terminal, and then assume that its value will stay as-is.
Retracting a page table involves modifying a non-terminal entry, so
page-table-level locks are insufficient to protect against concurrent page
table traversal; it requires taking all the higher-level locks under which
it is possible to start a page walk in the relevant range in exclusive
mode.
The collapse_huge_page() path for anonymous THP already follows this rule,
but the shmem/file THP path was getting it wrong, making it possible for
concurrent rmap-based operations to cause corruption.
Link: https://lkml.kernel.org/r/20221125213714.4115729-1-jannh@google.com
Fixes: 27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP")
Signed-off-by: Jann Horn <jannh(a)google.com>
Cc: David Hildenbrand <david(a)redhat.com>
Cc: John Hubbard <jhubbard(a)nvidia.com>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: Yang Shi <shy828301(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/khugepaged.c | 55 ++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 51 insertions(+), 4 deletions(-)
--- a/mm/khugepaged.c~mm-khugepaged-take-the-right-locks-for-page-table-retraction
+++ a/mm/khugepaged.c
@@ -1379,16 +1379,37 @@ static int set_huge_pmd(struct vm_area_s
return SCAN_SUCCEED;
}
+/*
+ * A note about locking:
+ * Trying to take the page table spinlocks would be useless here because those
+ * are only used to synchronize:
+ *
+ * - modifying terminal entries (ones that point to a data page, not to another
+ * page table)
+ * - installing *new* non-terminal entries
+ *
+ * Instead, we need roughly the same kind of protection as free_pgtables() or
+ * mm_take_all_locks() (but only for a single VMA):
+ * The mmap lock together with this VMA's rmap locks covers all paths towards
+ * the page table entries we're messing with here, except for hardware page
+ * table walks and lockless_pages_from_mm().
+ */
static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
- spinlock_t *ptl;
pmd_t pmd;
mmap_assert_write_locked(mm);
- ptl = pmd_lock(vma->vm_mm, pmdp);
+ if (vma->vm_file)
+ lockdep_assert_held_write(&vma->vm_file->f_mapping->i_mmap_rwsem);
+ /*
+ * All anon_vmas attached to the VMA have the same root and are
+ * therefore locked by the same lock.
+ */
+ if (vma->anon_vma)
+ lockdep_assert_held_write(&vma->anon_vma->root->rwsem);
+
pmd = pmdp_collapse_flush(vma, addr, pmdp);
- spin_unlock(ptl);
mm_dec_nr_ptes(mm);
page_table_check_pte_clear_range(mm, addr, pmd);
pte_free(mm, pmd_pgtable(pmd));
@@ -1439,6 +1460,14 @@ int collapse_pte_mapped_thp(struct mm_st
if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
return SCAN_VMA_CHECK;
+ /*
+ * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings
+ * that got written to. Without this, we'd have to also lock the
+ * anon_vma if one exists.
+ */
+ if (vma->anon_vma)
+ return SCAN_VMA_CHECK;
+
/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
if (userfaultfd_wp(vma))
return SCAN_PTE_UFFD_WP;
@@ -1472,6 +1501,20 @@ int collapse_pte_mapped_thp(struct mm_st
goto drop_hpage;
}
+ /*
+ * We need to lock the mapping so that from here on, only GUP-fast and
+ * hardware page walks can access the parts of the page tables that
+ * we're operating on.
+ * See collapse_and_free_pmd().
+ */
+ i_mmap_lock_write(vma->vm_file->f_mapping);
+
+ /*
+ * This spinlock should be unnecessary: Nobody else should be accessing
+ * the page tables under spinlock protection here, only
+ * lockless_pages_from_mm() and the hardware page walker can access page
+ * tables while all the high-level locks are held in write mode.
+ */
start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
result = SCAN_FAIL;
@@ -1526,6 +1569,8 @@ int collapse_pte_mapped_thp(struct mm_st
/* step 4: remove pte entries */
collapse_and_free_pmd(mm, vma, haddr, pmd);
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+
maybe_install_pmd:
/* step 5: install pmd entry */
result = install_pmd
@@ -1539,6 +1584,7 @@ drop_hpage:
abort:
pte_unmap_unlock(start_pte, ptl);
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
goto drop_hpage;
}
@@ -1595,7 +1641,8 @@ static int retract_page_tables(struct ad
* An alternative would be drop the check, but check that page
* table is clear before calling pmdp_collapse_flush() under
* ptl. It has higher chance to recover THP for the VMA, but
- * has higher cost too.
+ * has higher cost too. It would also probably require locking
+ * the anon_vma.
*/
if (vma->anon_vma) {
result = SCAN_PAGE_ANON;
_
Patches currently in -mm which might be from jannh(a)google.com are
mm-khugepaged-take-the-right-locks-for-page-table-retraction.patch
mm-khugepaged-fix-gup-fast-interaction-by-sending-ipi.patch
mm-khugepaged-invoke-mmu-notifiers-in-shmem-file-collapse-paths.patch