core: Fix user return notifier on fork()

fork() clones all thread_info flags, including
TIF_USER_RETURN_NOTIFY; if the new task is first scheduled on a cpu
which doesn't have user return notifiers set, this causes user
return notifiers to trigger without any way of clearing itself.

This is easy to trigger with a forky workload on the host in
parallel with kvm, resulting in a cpu in an endless loop on the
verge of returning to userspace.

Fix by dropping the TIF_USER_RETURN_NOTIFY immediately after fork.

Signed-off-by: Avi Kivity <avi@redhat.com>
LKML-Reference: <1259505288-16559-1-git-send-email-avi@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/user-return-notifier.h b/include/linux/user-return-notifier.h
index b6ac056291d71531427e724dd056d0ffcd0059a1..9c4a445bb43c69999eb29303e9d8a0c4c6412c89 100644 (file)
--- a/include/linux/user-return-notifier.h
+++ b/include/linux/user-return-notifier.h
@@ -26,6 +26,11 @@ static inline void propagate_user_return_notify(struct task_struct *prev,
 
 void fire_user_return_notifiers(void);
 
+static inline void clear_user_return_notifier(struct task_struct *p)
+{
+       clear_tsk_thread_flag(p, TIF_USER_RETURN_NOTIFY);
+}
+
 #else
 
 struct user_return_notifier {};
@@ -37,6 +42,8 @@ static inline void propagate_user_return_notify(struct task_struct *prev,
 
 static inline void fire_user_return_notifiers(void) {}
 
+static inline void clear_user_return_notifier(struct task_struct *p) {}
+
 #endif
 
 #endif

diff --git a/kernel/fork.c b/kernel/fork.c
index 266c6af6ef1b089a1c64ee96428bd153db39217c..1b7512d5a64a88fb76908251e38104f13008f72c 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -64,6 +64,7 @@
 #include <linux/magic.h>
 #include <linux/perf_event.h>
 #include <linux/posix-timers.h>
+#include <linux/user-return-notifier.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -249,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
                goto out;
 
        setup_thread_stack(tsk, orig);
+       clear_user_return_notifier(tsk);
        stackend = end_of_stack(tsk);
        *stackend = STACK_END_MAGIC;    /* for overflow detection */