[3.13.y.z extended stable] Patch "mm/memory-failure.c: don't let collect_procs() skip over processes for MF_ACTION_REQUIRED" has been added to staging queue

[Kamal Mostafa]

This is a note to let you know that I have just added a patch titled

    mm/memory-failure.c: don't let collect_procs() skip over processes for MF_ACTION_REQUIRED

to the linux-3.13.y-queue branch of the 3.13.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.13.y-queue

This patch is scheduled to be released in version 3.13.11.5.

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.13.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Kamal

------

>From 7b5ee5df34302e0efa0e32c04fa1a96c65c41dd5 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck at intel.com>
Date: Wed, 4 Jun 2014 16:11:01 -0700
Subject: mm/memory-failure.c: don't let collect_procs() skip over processes
 for MF_ACTION_REQUIRED

commit 74614de17db6fb472370c426d4f934d8d616edf2 upstream.

When Linux sees an "action optional" machine check (where h/w has reported
an error that is not in the current execution path) we generally do not
want to signal a process, since most processes do not have a SIGBUS
handler - we'd just prematurely terminate the process for a problem that
they might never actually see.

task_early_kill() decides whether to consider a process - and it checks
whether this specific process has been marked for early signals with
"prctl", or if the system administrator has requested early signals for
all processes using /proc/sys/vm/memory_failure_early_kill.

But for MF_ACTION_REQUIRED case we must not defer.  The error is in the
execution path of the current thread so we must send the SIGBUS
immediatley.

Fix by passing a flag argument through collect_procs*() to
task_early_kill() so it knows whether we can defer or must take action.

Signed-off-by: Tony Luck <tony.luck at intel.com>
Signed-off-by: Naoya Horiguchi <n-horiguchi at ah.jp.nec.com>
Cc: Andi Kleen <andi at firstfloor.org>
Cc: Borislav Petkov <bp at suse.de>
Cc: Chen Gong <gong.chen at linux.jf.intel.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 mm/memory-failure.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2b5da71..e5f7031 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -384,10 +384,12 @@ static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 	}
 }

-static int task_early_kill(struct task_struct *tsk)
+static int task_early_kill(struct task_struct *tsk, int force_early)
 {
 	if (!tsk->mm)
 		return 0;
+	if (force_early)
+		return 1;
 	if (tsk->flags & PF_MCE_PROCESS)
 		return !!(tsk->flags & PF_MCE_EARLY);
 	return sysctl_memory_failure_early_kill;
@@ -397,7 +399,7 @@ static int task_early_kill(struct task_struct *tsk)
  * Collect processes when the error hit an anonymous page.
  */
 static void collect_procs_anon(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -413,7 +415,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;

-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;
 		anon_vma_interval_tree_foreach(vmac, &av->rb_root,
 					       pgoff, pgoff) {
@@ -432,7 +434,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
  * Collect processes when the error hit a file mapped page.
  */
 static void collect_procs_file(struct page *page, struct list_head *to_kill,
-			      struct to_kill **tkc)
+			      struct to_kill **tkc, int force_early)
 {
 	struct vm_area_struct *vma;
 	struct task_struct *tsk;
@@ -443,7 +445,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);

-		if (!task_early_kill(tsk))
+		if (!task_early_kill(tsk, force_early))
 			continue;

 		vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff,
@@ -469,7 +471,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
  * First preallocate one tokill structure outside the spin locks,
  * so that we can kill at least one process reasonably reliable.
  */
-static void collect_procs(struct page *page, struct list_head *tokill)
+static void collect_procs(struct page *page, struct list_head *tokill,
+				int force_early)
 {
 	struct to_kill *tk;

@@ -480,9 +483,9 @@ static void collect_procs(struct page *page, struct list_head *tokill)
 	if (!tk)
 		return;
 	if (PageAnon(page))
-		collect_procs_anon(page, tokill, &tk);
+		collect_procs_anon(page, tokill, &tk, force_early);
 	else
-		collect_procs_file(page, tokill, &tk);
+		collect_procs_file(page, tokill, &tk, force_early);
 	kfree(tk);
 }

@@ -967,7 +970,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(ppage, &tokill);
+		collect_procs(ppage, &tokill, flags & MF_ACTION_REQUIRED);

 	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
--
1.9.1