When oom killer occured, almost processes are getting stuck following
two points.
1) __alloc_pages_nodemask
2) __lock_page_or_retry
1) is not much problematic because TIF_MEMDIE lead to make allocation
failure and get out from page allocator. 2) is more problematic. When
OOM situation, Zones typically don't have page cache at all and Memory
starvation might lead to reduce IO performance largely. When fork bomb
occur, TIF_MEMDIE task don't die quickly mean fork bomb may create
new process quickly rather than oom-killer kill it. Then, the system
may become livelock.
This patch makes pagefault interruptible by SIGKILL.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
---
arch/x86/mm/fault.c | 12 +++++++++++-
include/linux/mm.h | 1 +
mm/filemap.c | 31 ++++++++++++++++++++++++-------
3 files changed, 36 insertions(+), 8 deletions(-)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 20e3f87..57a9fce 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -964,7 +964,7 @@ 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;
@@ -1138,6 +1138,16 @@ 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 7606d7d..aba870b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -152,6 +152,7 @@ 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 dea8a38..8144f87 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;
}
}
--
1.7.1
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>