Thread (1 message) 1 message, 1 author, 2017-06-12

[PATCH v4.1 4/8] mm, gup: Ensure real head page is ref-counted when using hugepages

From: Punit Agrawal <hidden>
Date: 2017-06-12 14:36:17
Also in: linux-arch, linux-mm, lkml

Possibly related (same subject, not in this thread)

Punit Agrawal [off-list ref] writes:
When speculatively taking references to a hugepage using
page_cache_add_speculative() in gup_huge_pmd(), it is assumed that the
page returned by pmd_page() is the head page. Although normally true,
this assumption doesn't hold when the hugepage comprises of successive
page table entries such as when using contiguous bit on arm64 at PTE or
PMD levels.

This can be addressed by ensuring that the page passed to
page_cache_add_speculative() is the real head or by de-referencing the
head page within the function.

We take the first approach to keep the usage pattern aligned with
page_cache_get_speculative() where users already pass the appropriate
page, i.e., the de-referenced head.

Apply the same logic to fix gup_huge_[pud|pgd]() as well.

Signed-off-by: Punit Agrawal <redacted>
Cc: Steve Capper <redacted>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Kirill A. Shutemov" <redacted>
Cc: Aneesh Kumar K.V <redacted>
---

Hi Andrew,

Please update the patch in your queue with this version.

It fixes the ltp failures reported by Yury[0]. The original patch led
to incorrect ref-count on certain pages due to taking a referencing on
the following page in some instances. Should be fixed with this
version.
Gentle ping!

Andrew, please update to this version of the patch - it fixes a breakage
on arm64.

Alternately, if you're OK with it, we could take the whole series via
the arm64 tree.
quoted hunk
Thanks,
Punit

[0] http://lists.infradead.org/pipermail/linux-arm-kernel/2017-June/510318.html

 mm/gup.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/mm/gup.c b/mm/gup.c
index e74e0b5a0c7c..6bd39264d0e7 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1354,8 +1354,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return __gup_device_huge_pmd(orig, addr, end, pages, nr);
 
 	refs = 0;
-	head = pmd_page(orig);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 	do {
 		pages[*nr] = page;
 		(*nr)++;
@@ -1363,6 +1362,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
+	head = compound_head(pmd_page(orig));
 	if (!page_cache_add_speculative(head, refs)) {
 		*nr -= refs;
 		return 0;
@@ -1392,8 +1392,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return __gup_device_huge_pud(orig, addr, end, pages, nr);
 
 	refs = 0;
-	head = pud_page(orig);
-	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 	do {
 		pages[*nr] = page;
 		(*nr)++;
@@ -1401,6 +1400,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
+	head = compound_head(pud_page(orig));
 	if (!page_cache_add_speculative(head, refs)) {
 		*nr -= refs;
 		return 0;
@@ -1429,8 +1429,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 
 	BUILD_BUG_ON(pgd_devmap(orig));
 	refs = 0;
-	head = pgd_page(orig);
-	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
 	do {
 		pages[*nr] = page;
 		(*nr)++;
@@ -1438,6 +1437,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
+	head = compound_head(pgd_page(orig));
 	if (!page_cache_add_speculative(head, refs)) {
 		*nr -= refs;
 		return 0;
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help