summaryrefslogtreecommitdiff
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2016-05-12 15:42:25 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-05-12 15:52:50 -0700
commit6d0a07edd17cfc12fdc1f36de8072fa17cc3666f (patch)
treea80f20857e658de5aaa8ffa769f32d2f3bf7a9a5 /mm/huge_memory.c
parent7496fea9a6bf644afe360af795b121a77635b37d (diff)
downloadlinux-6d0a07edd17cfc12fdc1f36de8072fa17cc3666f.tar.gz
mm: thp: calculate the mapcount correctly for THP pages during WP faults
This will provide fully accuracy to the mapcount calculation in the write protect faults, so page pinning will not get broken by false positive copy-on-writes. total_mapcount() isn't the right calculation needed in reuse_swap_page(), so this introduces a page_trans_huge_mapcount() that is effectively the full accurate return value for page_mapcount() if dealing with Transparent Hugepages, however we only use the page_trans_huge_mapcount() during COW faults where it strictly needed, due to its higher runtime cost. This also provide at practical zero cost the total_mapcount information which is needed to know if we can still relocate the page anon_vma to the local vma. If page_trans_huge_mapcount() returns 1 we can reuse the page no matter if it's a pte or a pmd_trans_huge triggering the fault, but we can only relocate the page anon_vma to the local vma->anon_vma if we're sure it's only this "vma" mapping the whole THP physical range. Kirill A. Shutemov discovered the problem with moving the page anon_vma to the local vma->anon_vma in a previous version of this patch and another problem in the way page_move_anon_rmap() was called. Andrew Morton discovered that CONFIG_SWAP=n wouldn't build in a previous version, because reuse_swap_page must be a macro to call page_trans_huge_mapcount from swap.h, so this uses a macro again instead of an inline function. With this change at least it's a less dangerous usage than it was before, because "page" is used only once now, while with the previous code reuse_swap_page(page++) would have called page_mapcount on page+1 and it would have increased page twice instead of just once. Dean Luick noticed an uninitialized variable that could result in a rmap inefficiency for the non-THP case in a previous version. Mike Marciniszyn said: : Our RDMA tests are seeing an issue with memory locking that bisects to : commit 61f5d698cc97 ("mm: re-enable THP") : : The test program registers two rather large MRs (512M) and RDMA : writes data to a passive peer using the first and RDMA reads it back : into the second MR and compares that data. The sizes are chosen randomly : between 0 and 1024 bytes. : : The test will get through a few (<= 4 iterations) and then gets a : compare error. : : Tracing indicates the kernel logical addresses associated with the individual : pages at registration ARE correct , the data in the "RDMA read response only" : packets ARE correct. : : The "corruption" occurs when the packet crosse two pages that are not physically : contiguous. The second page reads back as zero in the program. : : It looks like the user VA at the point of the compare error no longer points to : the same physical address as was registered. : : This patch totally resolves the issue! Link: http://lkml.kernel.org/r/1462547040-1737-2-git-send-email-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Reviewed-by: "Kirill A. Shutemov" <kirill@shutemov.name> Reviewed-by: Dean Luick <dean.luick@intel.com> Tested-by: Alex Williamson <alex.williamson@redhat.com> Tested-by: Mike Marciniszyn <mike.marciniszyn@intel.com> Tested-by: Josh Collier <josh.d.collier@intel.com> Cc: Marc Haber <mh+linux-kernel@zugschlus.de> Cc: <stable@vger.kernel.org> [4.5] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c71
1 files changed, 62 insertions, 9 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f7daa7de8f48..b49ee126d4d1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1298,15 +1298,9 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
VM_BUG_ON_PAGE(!PageCompound(page) || !PageHead(page), page);
/*
* We can only reuse the page if nobody else maps the huge page or it's
- * part. We can do it by checking page_mapcount() on each sub-page, but
- * it's expensive.
- * The cheaper way is to check page_count() to be equal 1: every
- * mapcount takes page reference reference, so this way we can
- * guarantee, that the PMD is the only mapping.
- * This can give false negative if somebody pinned the page, but that's
- * fine.
+ * part.
*/
- if (page_mapcount(page) == 1 && page_count(page) == 1) {
+ if (page_trans_huge_mapcount(page, NULL) == 1) {
pmd_t entry;
entry = pmd_mkyoung(orig_pmd);
entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
@@ -2079,7 +2073,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
if (pte_write(pteval)) {
writable = true;
} else {
- if (PageSwapCache(page) && !reuse_swap_page(page)) {
+ if (PageSwapCache(page) &&
+ !reuse_swap_page(page, NULL)) {
unlock_page(page);
result = SCAN_SWAP_CACHE_PAGE;
goto out;
@@ -3223,6 +3218,64 @@ int total_mapcount(struct page *page)
}
/*
+ * This calculates accurately how many mappings a transparent hugepage
+ * has (unlike page_mapcount() which isn't fully accurate). This full
+ * accuracy is primarily needed to know if copy-on-write faults can
+ * reuse the page and change the mapping to read-write instead of
+ * copying them. At the same time this returns the total_mapcount too.
+ *
+ * The function returns the highest mapcount any one of the subpages
+ * has. If the return value is one, even if different processes are
+ * mapping different subpages of the transparent hugepage, they can
+ * all reuse it, because each process is reusing a different subpage.
+ *
+ * The total_mapcount is instead counting all virtual mappings of the
+ * subpages. If the total_mapcount is equal to "one", it tells the
+ * caller all mappings belong to the same "mm" and in turn the
+ * anon_vma of the transparent hugepage can become the vma->anon_vma
+ * local one as no other process may be mapping any of the subpages.
+ *
+ * It would be more accurate to replace page_mapcount() with
+ * page_trans_huge_mapcount(), however we only use
+ * page_trans_huge_mapcount() in the copy-on-write faults where we
+ * need full accuracy to avoid breaking page pinning, because
+ * page_trans_huge_mapcount() is slower than page_mapcount().
+ */
+int page_trans_huge_mapcount(struct page *page, int *total_mapcount)
+{
+ int i, ret, _total_mapcount, mapcount;
+
+ /* hugetlbfs shouldn't call it */
+ VM_BUG_ON_PAGE(PageHuge(page), page);
+
+ if (likely(!PageTransCompound(page))) {
+ mapcount = atomic_read(&page->_mapcount) + 1;
+ if (total_mapcount)
+ *total_mapcount = mapcount;
+ return mapcount;
+ }
+
+ page = compound_head(page);
+
+ _total_mapcount = ret = 0;
+ for (i = 0; i < HPAGE_PMD_NR; i++) {
+ mapcount = atomic_read(&page[i]._mapcount) + 1;
+ ret = max(ret, mapcount);
+ _total_mapcount += mapcount;
+ }
+ if (PageDoubleMap(page)) {
+ ret -= 1;
+ _total_mapcount -= HPAGE_PMD_NR;
+ }
+ mapcount = compound_mapcount(page);
+ ret += mapcount;
+ _total_mapcount += mapcount;
+ if (total_mapcount)
+ *total_mapcount = _total_mapcount;
+ return ret;
+}
+
+/*
* This function splits huge page into normal pages. @page can point to any
* subpage of huge page to split. Split doesn't change the position of @page.
*