The patch titled
Subject: THP: fix comment about memory barrier
has been added to the -mm tree. Its filename is
thp-fix-comment-about-memory-barrier.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: Minchan Kim <minchan@xxxxxxxxxx>
Subject: THP: fix comment about memory barrier
Now, memory barrier in __do_huge_pmd_anonymous_page doesn't work. Because
lru_cache_add_lru uses pagevec so it could miss spinlock easily so above
rule was broken so user might see inconsistent data.
I was not first person who pointed out the problem. Mel and Peter pointed
out a few months ago and Peter pointed out further that even
spin_lock/unlock can't make sure it. http://marc.info/?t=134333512700004
In particular:
*A = a;
LOCK
UNLOCK
*B = b;
may occur as:
LOCK, STORE *B, STORE *A, UNLOCK
At last, Hugh pointed out that even we don't need memory barrier in there
because __SetPageUpdate already have done it from Nick's 0ed361dec ("mm:
fix PageUptodate data race") explicitly.
So this patch fixes comment on THP and adds same comment for
do_anonymous_page, too because everybody except Hugh was missing that. It
means we need a comment about that.
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
Acked-by: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/huge_memory.c | 11 +++++------
mm/memory.c | 5 +++++
2 files changed, 10 insertions(+), 6 deletions(-)
diff -puN mm/huge_memory.c~thp-fix-comment-about-memory-barrier mm/huge_memory.c
--- a/mm/huge_memory.c~thp-fix-comment-about-memory-barrier
+++ a/mm/huge_memory.c
@@ -713,6 +713,11 @@ static int __do_huge_pmd_anonymous_page(
return VM_FAULT_OOM;
clear_huge_page(page, haddr, HPAGE_PMD_NR);
+ /*
+ * The memory barrier inside __SetPageUptodate makes sure that
+ * clear_huge_page writes become visible before the set_pmd_at()
+ * write.
+ */
__SetPageUptodate(page);
spin_lock(&mm->page_table_lock);
@@ -724,12 +729,6 @@ static int __do_huge_pmd_anonymous_page(
} else {
pmd_t entry;
entry = mk_huge_pmd(page, vma);
- /*
- * The spinlocking to take the lru_lock inside
- * page_add_new_anon_rmap() acts as a full memory
- * barrier to be sure clear_huge_page writes become
- * visible after the set_pmd_at() write.
- */
page_add_new_anon_rmap(page, vma, haddr);
set_pmd_at(mm, haddr, pmd, entry);
pgtable_trans_huge_deposit(mm, pgtable);
diff -puN mm/memory.c~thp-fix-comment-about-memory-barrier mm/memory.c
--- a/mm/memory.c~thp-fix-comment-about-memory-barrier
+++ a/mm/memory.c
@@ -3196,6 +3196,11 @@ static int do_anonymous_page(struct mm_s
page = alloc_zeroed_user_highpage_movable(vma, address);
if (!page)
goto oom;
+ /*
+ * The memory barrier inside __SetPageUptodate makes sure that
+ * preceeding stores to the page contents become visible before
+ * the set_pte_at() write.
+ */
__SetPageUptodate(page);
if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
_
Patches currently in -mm which might be from minchan@xxxxxxxxxx are
linux-next.patch
mm-frontswap-lazy-initialization-to-allow-tmem-backends-to-build-run-as-modules.patch
frontswap-make-frontswap_init-use-a-pointer-for-the-ops.patch
mm-frontswap-cleanup-code.patch
frontswap-get-rid-of-swap_lock-dependency.patch
mm-cleancache-lazy-initialization-to-allow-tmem-backends-to-build-run-as-modules.patch
cleancache-make-cleancache_init-use-a-pointer-for-the-ops.patch
mm-cleancache-clean-up-cleancache_enabled.patch
xen-tmem-enable-xen-tmem-shim-to-be-built-loaded-as-a-module.patch
xen-tmem-enable-xen-tmem-shim-to-be-built-loaded-as-a-module-fix.patch
zcache-tmem-better-error-checking-on-frontswap_register_ops-return-value.patch
staging-zcache-enable-ramster-to-be-built-loaded-as-a-module.patch
staging-zcache-enable-zcache-to-be-built-loaded-as-a-module.patch
mm-introduce-free_highmem_page-helper-to-free-highmem-pages-into-buddy-system.patch
thp-fix-comment-about-memory-barrier.patch
mm-add-vm-event-counters-for-balloon-pages-compaction.patch
block-aio-batch-completion-for-bios-kiocbs.patch
debugging-keep-track-of-page-owners-fix-2.patch
debugging-keep-track-of-page-owners-fix-2-fix.patch
debugging-keep-track-of-page-owners-fix-2-fix-fix.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
