This is a note to let you know that I've just added the patch titled
mm/memory-failure.c: don't let collect_procs() skip over processes for MF_ACTION_REQUIRED
to the 3.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
mm-memory-failure.c-don-t-let-collect_procs-skip-over-processes-for-mf_action_required.patch
and it can be found in the queue-3.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 74614de17db6fb472370c426d4f934d8d616edf2 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@xxxxxxxxx>
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
From: Tony Luck <tony.luck@xxxxxxxxx>
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@xxxxxxxxx>
Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Chen Gong <gong.chen@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
mm/memory-failure.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -380,10 +380,12 @@ static void kill_procs(struct list_head
}
}
-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;
@@ -393,7 +395,7 @@ static int task_early_kill(struct task_s
* 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;
@@ -409,7 +411,7 @@ static void collect_procs_anon(struct pa
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) {
@@ -428,7 +430,7 @@ static void collect_procs_anon(struct pa
* 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;
@@ -439,7 +441,7 @@ static void collect_procs_file(struct pa
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,
@@ -465,7 +467,8 @@ static void collect_procs_file(struct pa
* 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;
@@ -476,9 +479,9 @@ static void collect_procs(struct page *p
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);
}
@@ -963,7 +966,7 @@ static int hwpoison_user_mappings(struct
* 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)
Patches currently in stable-queue which might be from tony.luck@xxxxxxxxx are
queue-3.15/mm-memory-failure.c-failure-send-right-signal-code-to-correct-thread.patch
queue-3.15/mm-memory-failure.c-don-t-let-collect_procs-skip-over-processes-for-mf_action_required.patch
queue-3.15/hugetlb-restrict-hugepage_migration_support-to-x86_64.patch
queue-3.15/mm-memory-failure.c-support-use-of-a-dedicated-thread-to-handle-sigbus-bus_mceerr_ao.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html