linux-kernel - [PATCH 12/31] huge tmpfs: extend get_user_pages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.LSU.2.11.1604051429160.5965@eggly.anvils>
Date:	Tue, 5 Apr 2016 14:33:14 -0700 (PDT)
From:	Hugh Dickins <hughd@...gle.com>
To:	Andrew Morton <akpm@...ux-foundation.org>
cc:	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Andres Lagar-Cavilla <andreslc@...gle.com>,
	Yang Shi <yang.shi@...aro.org>, Ning Qu <quning@...il.com>,
	Ralf Baechle <ralf@...ux-mips.org>,
	Martin Schwidefsky <schwidefsky@...ibm.com>,
	David Miller <davem@...emloft.net>,
	Ingo Molnar <mingo@...nel.org>, linux-kernel@...r.kernel.org,
	linux-arch@...r.kernel.org, linux-mm@...ck.org
Subject: [PATCH 12/31] huge tmpfs: extend get_user_pages_fast to shmem pmd

The arch-specific get_user_pages_fast() has a gup_huge_pmd() designed to
optimize the refcounting on anonymous THP and hugetlbfs pages, with one
atomic addition to compound head's common refcount.  That optimization
must be avoided on huge tmpfs team pages, which use normal separate page
refcounting.  We could combine the PageTeam and PageCompound cases into
a single simple loop, but would lose the compound optimization that way.

One cannot go through these functions without wondering why some arches
(x86, mips) like to SetPageReferenced, while the rest do not: an x86
optimization that missed being propagated to the other architectures?
No, see commit 8ee53820edfd ("thp: mmu_notifier_test_young"): it's a
KVM GRU EPT thing, maybe not useful beyond x86.  I've just followed
the established practice in each architecture.

Signed-off-by: Hugh Dickins <hughd@...gle.com>
---
Cc'ed to arch maintainers as an FYI: this patch is not expected to
go into the tree in the next few weeks, and depends upon a PageTeam
definition not yet available outside this huge tmpfs patchset.
Please refer to linux-mm or linux-kernel for more context.

 arch/mips/mm/gup.c  |   15 ++++++++++++++-
 arch/s390/mm/gup.c  |   19 ++++++++++++++++++-
 arch/sparc/mm/gup.c |   19 ++++++++++++++++++-
 arch/x86/mm/gup.c   |   15 ++++++++++++++-
 mm/gup.c            |   19 ++++++++++++++++++-
 5 files changed, 82 insertions(+), 5 deletions(-)

--- a/arch/mips/mm/gup.c
+++ b/arch/mips/mm/gup.c
@@ -81,9 +81,22 @@ static int gup_huge_pmd(pmd_t pmd, unsig
 	VM_BUG_ON(pte_special(pte));
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-	refs = 0;
 	head = pte_page(pte);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+
+	if (PageTeam(head)) {
+		/* Handle a huge tmpfs team with normal refcounting. */
+		do {
+			get_page(page);
+			SetPageReferenced(page);
+			pages[*nr] = page;
+			(*nr)++;
+			page++;
+		} while (addr += PAGE_SIZE, addr != end);
+		return 1;
+	}
+
+	refs = 0;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
--- a/arch/s390/mm/gup.c
+++ b/arch/s390/mm/gup.c
@@ -66,9 +66,26 @@ static inline int gup_huge_pmd(pmd_t *pm
 		return 0;
 	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
 
-	refs = 0;
 	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+
+	if (PageTeam(head)) {
+		/* Handle a huge tmpfs team with normal refcounting. */
+		do {
+			if (!page_cache_get_speculative(page))
+				return 0;
+			if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
+				put_page(page);
+				return 0;
+			}
+			pages[*nr] = page;
+			(*nr)++;
+			page++;
+		} while (addr += PAGE_SIZE, addr != end);
+		return 1;
+	}
+
+	refs = 0;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
--- a/arch/sparc/mm/gup.c
+++ b/arch/sparc/mm/gup.c
@@ -77,9 +77,26 @@ static int gup_huge_pmd(pmd_t *pmdp, pmd
 	if (write && !pmd_write(pmd))
 		return 0;
 
-	refs = 0;
 	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+
+	if (PageTeam(head)) {
+		/* Handle a huge tmpfs team with normal refcounting. */
+		do {
+			if (!page_cache_get_speculative(page))
+				return 0;
+			if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
+				put_page(page);
+				return 0;
+			}
+			pages[*nr] = page;
+			(*nr)++;
+			page++;
+		} while (addr += PAGE_SIZE, addr != end);
+		return 1;
+	}
+
+	refs = 0;
 	do {
 		VM_BUG_ON(compound_head(page) != head);
 		pages[*nr] = page;
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -196,9 +196,22 @@ static noinline int gup_huge_pmd(pmd_t p
 	/* hugepages are never "special" */
 	VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL);
 
-	refs = 0;
 	head = pmd_page(pmd);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+
+	if (PageTeam(head)) {
+		/* Handle a huge tmpfs team with normal refcounting. */
+		do {
+			get_page(page);
+			SetPageReferenced(page);
+			pages[*nr] = page;
+			(*nr)++;
+			page++;
+		} while (addr += PAGE_SIZE, addr != end);
+		return 1;
+	}
+
+	refs = 0;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1247,9 +1247,26 @@ static int gup_huge_pmd(pmd_t orig, pmd_
 	if (write && !pmd_write(orig))
 		return 0;
 
-	refs = 0;
 	head = pmd_page(orig);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+
+	if (PageTeam(head)) {
+		/* Handle a huge tmpfs team with normal refcounting. */
+		do {
+			if (!page_cache_get_speculative(page))
+				return 0;
+			if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
+				put_page(page);
+				return 0;
+			}
+			pages[*nr] = page;
+			(*nr)++;
+			page++;
+		} while (addr += PAGE_SIZE, addr != end);
+		return 1;
+	}
+
+	refs = 0;
 	do {
 		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;