The patch titled
Subject: mm: mprotect: use pmd_trans_unstable instead of taking the pmd_lock
has been added to the -mm tree. Its filename is
mm-mprotect-use-pmd_trans_unstable-instead-of-taking-the-pmd_lock.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-mprotect-use-pmd_trans_unstable-instead-of-taking-the-pmd_lock.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-mprotect-use-pmd_trans_unstable-instead-of-taking-the-pmd_lock.patch
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/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Subject: mm: mprotect: use pmd_trans_unstable instead of taking the pmd_lock
pmd_trans_unstable does an atomic read on the pmd so it doesn't
require the pmd_lock for the same check.
This also removes the special assumption that the mmap_sem is hold for
writing if prot_numa is not set. userfaultfd will hold the mmap_sem
only for reading in change_pte_range like prot_numa, but it will not
set prot_numa.
This is always a valid micro-optimization regardless of userfaultfd.
Link: http://lkml.kernel.org/r/20161216144821.5183-43-aarcange@xxxxxxxxxx
Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: "Dr. David Alan Gilbert" <dgilbert@xxxxxxxxxx>
Cc: Hillf Danton <hillf.zj@xxxxxxxxxxxxxxx>
Cc: Michael Rapoport <RAPOPORT@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/mprotect.c | 44 +++++++++++++++-----------------------------
1 file changed, 15 insertions(+), 29 deletions(-)
diff -puN mm/mprotect.c~mm-mprotect-use-pmd_trans_unstable-instead-of-taking-the-pmd_lock mm/mprotect.c
--- a/mm/mprotect.c~mm-mprotect-use-pmd_trans_unstable-instead-of-taking-the-pmd_lock
+++ a/mm/mprotect.c
@@ -33,34 +33,6 @@
#include "internal.h"
-/*
- * For a prot_numa update we only hold mmap_sem for read so there is a
- * potential race with faulting where a pmd was temporarily none. This
- * function checks for a transhuge pmd under the appropriate lock. It
- * returns a pte if it was successfully locked or NULL if it raced with
- * a transhuge insertion.
- */
-static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, int prot_numa, spinlock_t **ptl)
-{
- pte_t *pte;
- spinlock_t *pmdl;
-
- /* !prot_numa is protected by mmap_sem held for write */
- if (!prot_numa)
- return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
-
- pmdl = pmd_lock(vma->vm_mm, pmd);
- if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
- spin_unlock(pmdl);
- return NULL;
- }
-
- pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
- spin_unlock(pmdl);
- return pte;
-}
-
static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end, pgprot_t newprot,
int dirty_accountable, int prot_numa)
@@ -71,7 +43,21 @@ static unsigned long change_pte_range(st
unsigned long pages = 0;
int target_node = NUMA_NO_NODE;
- pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+ /*
+ * Can be called with only the mmap_sem for reading by
+ * prot_numa so we must check the pmd isn't constantly
+ * changing from under us from pmd_none to pmd_trans_huge
+ * and/or the other way around.
+ */
+ if (pmd_trans_unstable(pmd))
+ return 0;
+
+ /*
+ * The pmd points to a regular pte so the pmd can't change
+ * from under us even if the mmap_sem is only hold for
+ * reading.
+ */
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (!pte)
return 0;
_
Patches currently in -mm which might be from aarcange@xxxxxxxxxx are
userfaultfd-document-_ior-_iow.patch
userfaultfd-correct-comment-about-uffd_feature_pagefault_flag_wp.patch
userfaultfd-convert-bug-to-warn_on_once.patch
userfaultfd-use-vma_is_anonymous.patch
userfaultfd-non-cooperative-report-all-available-features-to-userland.patch
userfaultfd-non-cooperative-add-fork-event-build-warning-fix.patch
userfaultfd-non-cooperative-optimize-mremap_userfaultfd_complete.patch
userfaultfd-non-cooperative-avoid-madv_dontneed-race-condition.patch
userfaultfd-non-cooperative-wake-userfaults-after-uffdio_unregister.patch
userfaultfd-hugetlbfs-gup-support-vm_fault_retry.patch
userfaultfd-hugetlbfs-uffd_feature_missing_hugetlbfs.patch
userfaultfd-shmem-add-tlbflushh-header-for-microblaze.patch
userfaultfd-shmem-lock-the-page-before-adding-it-to-pagecache.patch
userfaultfd-shmem-avoid-leaking-blocks-and-used-blocks-in-uffdio_copy.patch
userfaultfd-hugetlbfs-uffd_feature_missing_shmem.patch
userfaultfd-selftest-test-uffdio_zeropage-on-all-memory-types.patch
mm-mprotect-use-pmd_trans_unstable-instead-of-taking-the-pmd_lock.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
