path: root/include
diff options
authorMichel Lespinasse <walken@google.com>2010-10-26 14:21:57 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-10-26 16:52:09 -0700
commitd065bd810b6deb67d4897a14bfe21f8eb526ba99 (patch)
treef58c59075732ec4ccba336278c9bdc7ff61bef94 /include
parentb522c94da5d9cbc73f708be5e530ebc3bbd4a031 (diff)
mm: retry page fault when blocking on disk transfer
This change reduces mmap_sem hold times that are caused by waiting for disk transfers when accessing file mapped VMAs. It introduces the VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants mmap_sem to be released if blocking on a pending disk transfer. In that case, filemap_fault() returns the VM_FAULT_RETRY status bit and do_page_fault() will then re-acquire mmap_sem and retry the page fault. It is expected that the retry will hit the same page which will now be cached, and thus it will complete with a low mmap_sem hold time. Tests: - microbenchmark: thread A mmaps a large file and does random read accesses to the mmaped area - achieves about 55 iterations/s. Thread B does mmap/munmap in a loop at a separate location - achieves 55 iterations/s before, 15000 iterations/s after. - We are seeing related effects in some applications in house, which show significant performance regressions when running without this change. [akpm@linux-foundation.org: fix warning & crash] Signed-off-by: Michel Lespinasse <walken@google.com> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Reviewed-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Ying Han <yinghan@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
2 files changed, 15 insertions, 0 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2862009f9573..3bf46655b50a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -144,6 +144,7 @@ extern pgprot_t protection_map[16];
#define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */
#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */
#define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */
+#define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */
* This interface is used by x86 PAT code to identify a pfn mapping that is
@@ -723,6 +724,7 @@ static inline int page_mapped(struct page *page)
#define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
+#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e12cdc6d79ee..2d1ffe3cf1ee 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -299,6 +299,8 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
extern void __lock_page(struct page *page);
extern int __lock_page_killable(struct page *page);
extern void __lock_page_nosync(struct page *page);
+extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+ unsigned int flags);
extern void unlock_page(struct page *page);
static inline void __set_page_locked(struct page *page)
@@ -351,6 +353,17 @@ static inline void lock_page_nosync(struct page *page)
+ * lock_page_or_retry - Lock the page, unless this would block and the
+ * caller indicated that it can handle a retry.
+ */
+static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
+ unsigned int flags)
+ might_sleep();
+ return trylock_page(page) || __lock_page_or_retry(page, mm, flags);
* This is exported only for wait_on_page_locked/wait_on_page_writeback.
* Never use this directly!

Privacy Policy