x86,mm: make pagefault killable

When an oom killing occurs, almost all processes are getting stuck at the
following two points.

	1) __alloc_pages_nodemask
	2) __lock_page_or_retry

1) is not very problematic because TIF_MEMDIE leads to an allocation
failure and getting out from page allocator.

2) is more problematic.  In an OOM situation, zones typically don't have
page cache at all and memory starvation might lead to greatly reduced IO
performance.  When a fork bomb occurs, TIF_MEMDIE tasks don't die quickly,
meaning that a fork bomb may create new process quickly rather than the
oom-killer killing it.  Then, the system may become livelocked.

This patch makes the pagefault interruptible by SIGKILL.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 36 insertions, 8 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index bcb394dfbb3..f7a2a054a3c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -965,7 +965,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	struct mm_struct *mm;
 	int fault;
 	int write = error_code & PF_WRITE;
-	unsigned int flags = FAULT_FLAG_ALLOW_RETRY |
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
 					(write ? FAULT_FLAG_WRITE : 0);
 
 	tsk = current;
@@ -1139,6 +1139,16 @@ good_area:
 	}
 
 	/*
+	 * 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;
+	}
+
+	/*
 	 * 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.
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1746f67c33d..57d3d5fade1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -153,6 +153,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_MKWRITE	0x04	/* Fault was mkwrite of existing pte */
 #define FAULT_FLAG_ALLOW_RETRY	0x08	/* Retry fault if blocking */
 #define FAULT_FLAG_RETRY_NOWAIT	0x10	/* Don't drop mmap_sem and wait when retrying */
+#define FAULT_FLAG_KILLABLE	0x20	/* The fault task is in SIGKILL killable region */
 
 /*
  * This interface is used by x86 PAT code to identify a pfn mapping that is
diff --git a/mm/filemap.c b/mm/filemap.c
index dea8a38bb2b..8144f87dcbb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -654,15 +654,32 @@ EXPORT_SYMBOL_GPL(__lock_page_killable);
 int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 			 unsigned int flags)
 {
-	if (!(flags & FAULT_FLAG_ALLOW_RETRY)) {
-		__lock_page(page);
-		return 1;
-	} else {
-		if (!(flags & FAULT_FLAG_RETRY_NOWAIT)) {
-			up_read(&mm->mmap_sem);
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		/*
+		 * CAUTION! In this case, mmap_sem is not released
+		 * even though return 0.
+		 */
+		if (flags & FAULT_FLAG_RETRY_NOWAIT)
+			return 0;
+
+		up_read(&mm->mmap_sem);
+		if (flags & FAULT_FLAG_KILLABLE)
+			wait_on_page_locked_killable(page);
+		else
 			wait_on_page_locked(page);
-		}
 		return 0;
+	} else {
+		if (flags & FAULT_FLAG_KILLABLE) {
+			int ret;
+
+			ret = __lock_page_killable(page);
+			if (ret) {
+				up_read(&mm->mmap_sem);
+				return 0;
+			}
+		} else
+			__lock_page(page);
+		return 1;
 	}
 }