From d065bd810b6deb67d4897a14bfe21f8eb526ba99 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Tue, 26 Oct 2010 14:21:57 -0700 Subject: 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 Acked-by: Rik van Riel Acked-by: Linus Torvalds Cc: Nick Piggin Reviewed-by: Wu Fengguang Cc: Ying Han Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Thomas Gleixner Acked-by: "H. Peter Anvin" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 38 ++++++++++++++++++++++++++------------ 1 file changed, 26 insertions(+), 12 deletions(-) (limited to 'arch') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 852b319edbdc..9b2345c9e0c3 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -956,8 +956,10 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) struct task_struct *tsk; unsigned long address; struct mm_struct *mm; - int write; int fault; + int write = error_code & PF_WRITE; + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | + (write ? FAULT_FLAG_WRITE : 0); tsk = current; mm = tsk->mm; @@ -1068,6 +1070,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) bad_area_nosemaphore(regs, error_code, address); return; } +retry: down_read(&mm->mmap_sem); } else { /* @@ -1111,8 +1114,6 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) * we can handle it.. */ good_area: - write = error_code & PF_WRITE; - if (unlikely(access_error(error_code, write, vma))) { bad_area_access_error(regs, error_code, address); return; @@ -1123,21 +1124,34 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault: */ - fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(mm, vma, address, flags); if (unlikely(fault & VM_FAULT_ERROR)) { mm_fault_error(regs, error_code, address, fault); return; } - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, - regs, address); + /* + * Major/minor page fault accounting is only done on the + * initial attempt. If we go through a retry, it is extremely + * likely that the page will be found in page cache at that point. + */ + if (flags & FAULT_FLAG_ALLOW_RETRY) { + if (fault & VM_FAULT_MAJOR) { + tsk->maj_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, + regs, address); + } else { + tsk->min_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, + regs, address); + } + if (fault & VM_FAULT_RETRY) { + /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk + * of starvation. */ + flags &= ~FAULT_FLAG_ALLOW_RETRY; + goto retry; + } } check_v8086_mode(regs, address, tsk); -- cgit v1.2.1