The patch titled
Subject: mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2
has been added to the -mm tree. Its filename is
mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2.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: Jérôme Glisse <jglisse@xxxxxxxxxx>
Subject: mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2
Changed since v1:
- typos (thanks to Andrea)
- Avoid unnecessary precaution in try_to_unmap() (Andrea)
- Be more conservative in try_to_unmap_one()
Link: http://lkml.kernel.org/r/20171017031003.7481-2-jglisse@xxxxxxxxxx
Signed-off-by: Jérôme Glisse <jglisse@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Nadav Amit <nadav.amit@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Joerg Roedel <jroedel@xxxxxxx>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
Cc: David Woodhouse <dwmw2@xxxxxxxxxxxxx>
Cc: Alistair Popple <alistair@xxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Stephen Rothwell <sfr@xxxxxxxxxxxxxxxx>
Cc: Andrew Donnellan <andrew.donnellan@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/vm/mmu_notifier.txt | 4 +-
mm/huge_memory.c | 2 -
mm/hugetlb.c | 4 +-
mm/ksm.c | 6 +--
mm/rmap.c | 44 +++++++++++++++++-----------
5 files changed, 36 insertions(+), 24 deletions(-)
diff -puN Documentation/vm/mmu_notifier.txt~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2 Documentation/vm/mmu_notifier.txt
--- a/Documentation/vm/mmu_notifier.txt~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2
+++ a/Documentation/vm/mmu_notifier.txt
@@ -14,7 +14,7 @@ those secondary TLB while holding page t
on zero page, __replace_page(), ...)
Case A is obvious you do not want to take the risk for the device to write to
-a page that might now be use by some completely different task.
+a page that might now be used by some completely different task.
Case B is more subtle. For correctness it requires the following sequence to
happen:
@@ -89,5 +89,5 @@ for the device.
When changing a pte to write protect or to point to a new write protected page
with same content (KSM) it is fine to delay the mmu_notifier_invalidate_range
call to mmu_notifier_invalidate_range_end() outside the page table lock. This
-is true ven if the thread doing the page table update is preempted right after
+is true even if the thread doing the page table update is preempted right after
releasing page table lock but before call mmu_notifier_invalidate_range_end().
diff -puN mm/huge_memory.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2 mm/huge_memory.c
--- a/mm/huge_memory.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2
+++ a/mm/huge_memory.c
@@ -1189,7 +1189,7 @@ static int do_huge_pmd_wp_page_fallback(
/*
* Leave pmd empty until pte is filled note we must notify here as
* concurrent CPU thread might write to new page before the call to
- * mmu_notifier_invalidate_range_end() happen which can lead to a
+ * mmu_notifier_invalidate_range_end() happens which can lead to a
* device seeing memory write in different order than CPU.
*
* See Documentation/vm/mmu_notifier.txt
diff -puN mm/hugetlb.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2 mm/hugetlb.c
--- a/mm/hugetlb.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2
+++ a/mm/hugetlb.c
@@ -3257,10 +3257,10 @@ int copy_hugetlb_page_range(struct mm_st
} else {
if (cow) {
/*
- * No need to notify as we downgrading page
+ * No need to notify as we are downgrading page
* table protection not changing it to point
* to a new page.
- *
+ *
* See Documentation/vm/mmu_notifier.txt
*/
huge_ptep_set_wrprotect(src, addr, src_pte);
diff -puN mm/ksm.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2 mm/ksm.c
--- a/mm/ksm.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2
+++ a/mm/ksm.c
@@ -1053,8 +1053,8 @@ static int write_protect_page(struct vm_
* this assure us that no O_DIRECT can happen after the check
* or in the middle of the check.
*
- * No need to notify as we downgrading page table to read only
- * not changing it to point to a new page.
+ * No need to notify as we are downgrading page table to read
+ * only not changing it to point to a new page.
*
* See Documentation/vm/mmu_notifier.txt
*/
@@ -1142,7 +1142,7 @@ static int replace_page(struct vm_area_s
flush_cache_page(vma, addr, pte_pfn(*ptep));
/*
- * No need to notify as we replacing a read only page with another
+ * No need to notify as we are replacing a read only page with another
* read only page with the same content.
*
* See Documentation/vm/mmu_notifier.txt
diff -puN mm/rmap.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2 mm/rmap.c
--- a/mm/rmap.c~mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2
+++ a/mm/rmap.c
@@ -1431,6 +1431,10 @@ static bool try_to_unmap_one(struct page
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte);
+ /*
+ * No need to invalidate here it will synchronize on
+ * against the special swap migration pte.
+ */
goto discard;
}
@@ -1488,6 +1492,9 @@ static bool try_to_unmap_one(struct page
* will take care of the rest.
*/
dec_mm_counter(mm, mm_counter(page));
+ /* We have to invalidate as we cleared the pte */
+ mmu_notifier_invalidate_range(mm, address,
+ address + PAGE_SIZE);
} else if (IS_ENABLED(CONFIG_MIGRATION) &&
(flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) {
swp_entry_t entry;
@@ -1503,6 +1510,10 @@ static bool try_to_unmap_one(struct page
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
+ /*
+ * No need to invalidate here it will synchronize on
+ * against the special swap migration pte.
+ */
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(subpage) };
pte_t swp_pte;
@@ -1514,6 +1525,8 @@ static bool try_to_unmap_one(struct page
WARN_ON_ONCE(1);
ret = false;
/* We have to invalidate as we cleared the pte */
+ mmu_notifier_invalidate_range(mm, address,
+ address + PAGE_SIZE);
page_vma_mapped_walk_done(&pvmw);
break;
}
@@ -1521,6 +1534,9 @@ static bool try_to_unmap_one(struct page
/* MADV_FREE page check */
if (!PageSwapBacked(page)) {
if (!PageDirty(page)) {
+ /* Invalidate as we cleared the pte */
+ mmu_notifier_invalidate_range(mm,
+ address, address + PAGE_SIZE);
dec_mm_counter(mm, MM_ANONPAGES);
goto discard;
}
@@ -1554,6 +1570,9 @@ static bool try_to_unmap_one(struct page
if (pte_soft_dirty(pteval))
swp_pte = pte_swp_mksoft_dirty(swp_pte);
set_pte_at(mm, address, pvmw.pte, swp_pte);
+ /* Invalidate as we cleared the pte */
+ mmu_notifier_invalidate_range(mm, address,
+ address + PAGE_SIZE);
} else {
/*
* We should not need to notify here as we reach this
@@ -1563,29 +1582,22 @@ static bool try_to_unmap_one(struct page
* - page is not anonymous
* - page is locked
*
- * So as it is a shared page and it is locked, it can
- * not be remove from the page cache and replace by
- * a new page before mmu_notifier_invalidate_range_end
- * so no concurrent thread might update its page table
- * to point at new page while a device still is using
- * this page.
- *
- * But we can not assume that new user of try_to_unmap
- * will have that in mind so just to be safe here call
- * mmu_notifier_invalidate_range()
+ * So as it is a locked file back page thus it can not
+ * be remove from the page cache and replace by a new
+ * page before mmu_notifier_invalidate_range_end so no
+ * concurrent thread might update its page table to
+ * point at new page while a device still is using this
+ * page.
*
* See Documentation/vm/mmu_notifier.txt
*/
dec_mm_counter(mm, mm_counter_file(page));
- mmu_notifier_invalidate_range(mm, address,
- address + PAGE_SIZE);
}
discard:
/*
- * No need to call mmu_notifier_invalidate_range() as we are
- * either replacing a present pte with non present one (either
- * a swap or special one). We handling the clearing pte case
- * above.
+ * No need to call mmu_notifier_invalidate_range() it has be
+ * done above for all cases requiring it to happen under page
+ * table lock before mmu_notifier_invalidate_range_end()
*
* See Documentation/vm/mmu_notifier.txt
*/
_
Patches currently in -mm which might be from jglisse@xxxxxxxxxx are
mm-mmu_notifier-avoid-double-notification-when-it-is-useless.patch
mm-mmu_notifier-avoid-double-notification-when-it-is-useless-v2.patch
mm-mmu_notifier-avoid-call-to-invalidate_range-in-range_end.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
