The patch titled
Subject: mm/mremap: move TLB flush outside page table lock
has been added to the -mm tree. Its filename is
mm-mremap-move-tlb-flush-outside-page-table-lock.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-mremap-move-tlb-flush-outside-page-table-lock.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-mremap-move-tlb-flush-outside-page-table-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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Aneesh Kumar K.V" <aneesh.kumar@xxxxxxxxxxxxx>
Subject: mm/mremap: move TLB flush outside page table lock
Move TLB flush outside page table lock so that kernel does less with page
table lock held. Releasing the ptl with old TLB contents still valid will
behave such that such access happened before the level3 or level2 entry
update.
Link: https://lkml.kernel.org/r/20210422054323.150993-8-aneesh.kumar@xxxxxxxxxxxxx
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
Cc: Kalesh Singh <kaleshsingh@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/mremap.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
--- a/mm/mremap.c~mm-mremap-move-tlb-flush-outside-page-table-lock
+++ a/mm/mremap.c
@@ -258,7 +258,7 @@ static bool move_normal_pmd(struct vm_ar
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
*/
- old_ptl = pmd_lock(vma->vm_mm, old_pmd);
+ old_ptl = pmd_lock(mm, old_pmd);
new_ptl = pmd_lockptr(mm, new_pmd);
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
@@ -270,11 +270,11 @@ static bool move_normal_pmd(struct vm_ar
VM_BUG_ON(!pmd_none(*new_pmd));
pmd_populate(mm, new_pmd, (pgtable_t)pmd_page_vaddr(pmd));
- flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PMD_SIZE);
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
spin_unlock(old_ptl);
+ flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PMD_SIZE);
return true;
}
#else
@@ -305,7 +305,7 @@ static bool move_normal_pud(struct vm_ar
* We don't have to worry about the ordering of src and dst
* ptlocks because exclusive mmap_lock prevents deadlock.
*/
- old_ptl = pud_lock(vma->vm_mm, old_pud);
+ old_ptl = pud_lock(mm, old_pud);
new_ptl = pud_lockptr(mm, new_pud);
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
@@ -317,11 +317,11 @@ static bool move_normal_pud(struct vm_ar
VM_BUG_ON(!pud_none(*new_pud));
pud_populate(mm, new_pud, (pmd_t *)pud_page_vaddr(pud));
- flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PUD_SIZE);
if (new_ptl != old_ptl)
spin_unlock(new_ptl);
spin_unlock(old_ptl);
+ flush_pte_tlb_pwc_range(vma, old_addr, old_addr + PUD_SIZE);
return true;
}
#else
_
Patches currently in -mm which might be from aneesh.kumar@xxxxxxxxxxxxx are
selftest-mremap_test-update-the-test-to-handle-pagesize-other-than-4k.patch
selftest-mremap_test-avoid-crash-with-static-build.patch
mm-mremap-use-pmd-pud_poplulate-to-update-page-table-entries.patch
powerpc-mm-book3s64-fix-possible-build-error.patch
powerpc-mm-book3s64-update-tlb-flush-routines-to-take-a-page-walk-cache-flush-argument.patch
mm-mremap-use-range-flush-that-does-tlb-and-page-walk-cache-flush.patch
mm-mremap-move-tlb-flush-outside-page-table-lock.patch
mm-mremap-allow-arch-runtime-override.patch
powerpc-mm-enable-move-pmd-pud.patch
