public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH] x86: add unlikely() to fatal signal check
@ 2011-05-26  8:12 KOSAKI Motohiro
  2011-05-26 12:01 ` [tip:x86/urgent] x86: Move do_page_fault()'s error path under unlikely() tip-bot for KOSAKI Motohiro
  0 siblings, 1 reply; 2+ messages in thread
From: KOSAKI Motohiro @ 2011-05-26  8:12 UTC (permalink / raw)
  To: mingo, linux-kernel, akpm, hpa, kamezawa.hiroyu, minchan.kim,
	tglx, willy
  Cc: kosaki.motohiro

Ingo suggested SIGKILL check should be moved into slowpath function.
It may reduce page fault fastpath impact. This patch do that.

Suggested-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
---
 arch/x86/mm/fault.c |   35 ++++++++++++++++++++---------------
 1 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f7a2a05..2dbf6bf 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -823,16 +823,30 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }

-static noinline void
+static noinline int
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	       unsigned long address, unsigned int fault)
 {
+	/*
+	 * Pagefault was interrupted by SIGKILL. We have no reason to
+	 * continue pagefault.
+	 */
+	if (fatal_signal_pending(current)) {
+		if (!(fault & VM_FAULT_RETRY))
+			up_read(&current->mm->mmap_sem);
+		if (!(error_code & PF_USER))
+			no_context(regs, error_code, address);
+		return 1;
+	}
+	if (!(fault & VM_FAULT_ERROR))
+		return 0;
+
 	if (fault & VM_FAULT_OOM) {
 		/* Kernel mode? Handle exceptions or die: */
 		if (!(error_code & PF_USER)) {
 			up_read(&current->mm->mmap_sem);
 			no_context(regs, error_code, address);
-			return;
+			return 1;
 		}

 		out_of_memory(regs, error_code, address);
@@ -843,6 +857,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 		else
 			BUG();
 	}
+	return 1;
 }

 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1133,19 +1148,9 @@ good_area:
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);

-	if (unlikely(fault & VM_FAULT_ERROR)) {
-		mm_fault_error(regs, error_code, address, fault);
-		return;
-	}
-
-	/*
-	 * Pagefault was interrupted by SIGKILL. We have no reason to
-	 * continue pagefault.
-	 */
-	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
-		if (!(error_code & PF_USER))
-			no_context(regs, error_code, address);
-		return;
+	if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+		if (mm_fault_error(regs, error_code, address, fault))
+			return;
 	}

 	/*
-- 
1.7.3.1



^ permalink raw reply related	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2011-05-26 12:02 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-05-26  8:12 [PATCH] x86: add unlikely() to fatal signal check KOSAKI Motohiro
2011-05-26 12:01 ` [tip:x86/urgent] x86: Move do_page_fault()'s error path under unlikely() tip-bot for KOSAKI Motohiro

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox