sched: Prevent recursion in io_schedule()

io_schedule() calls blk_flush_plug() which, depending on the
contents of current->plug, can initiate arbitrary blk-io requests.

Note that this contrasts with blk_schedule_flush_plug() which requires
all non-trivial work to be handed off to a separate thread.

This makes it possible for io_schedule() to recurse, and initiating
block requests could possibly call mempool_alloc() which, in times of
memory pressure, uses io_schedule().

Apart from any stack usage issues, io_schedule() will not behave
correctly when called recursively as delayacct_blkio_start() does
not allow for repeated calls.

So:
 - use ->in_iowait to detect recursion.  Set it earlier, and restore
   it to the old value.
 - move the call to "raw_rq" after the call to blk_flush_plug().
   As this is some sort of per-cpu thing, we want some chance that
   we are on the right CPU
 - When io_schedule() is called recurively, use blk_schedule_flush_plug()
   which cannot further recurse.
 - as this makes io_schedule() a lot more complex and as io_schedule()
   must match io_schedule_timeout(), but all the changes in io_schedule_timeout()
   and make io_schedule a simple wrapper for that.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[ Moved the now rudimentary io_schedule() into sched.h. ]
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Tony Battersby <tonyb@cybernetics.com>
Link: http://lkml.kernel.org/r/20150213162600.059fffb2@notabene.brown
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 19 insertions, 22 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8db31ef98d2f..cb5cdc777c8a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -363,9 +363,6 @@ extern void show_regs(struct pt_regs *);
  */
 extern void show_stack(struct task_struct *task, unsigned long *sp);
 
-void io_schedule(void);
-long io_schedule_timeout(long timeout);
-
 extern void cpu_init (void);
 extern void trap_init(void);
 extern void update_process_times(int user);
@@ -422,6 +419,13 @@ extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
 
+extern long io_schedule_timeout(long timeout);
+
+static inline void io_schedule(void)
+{
+	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
+}
+
 struct nsproxy;
 struct user_namespace;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c314000f5e52..daaea922f482 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4358,36 +4358,29 @@ EXPORT_SYMBOL_GPL(yield_to);
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
  */
-void __sched io_schedule(void)
-{
-	struct rq *rq = raw_rq();
-
-	delayacct_blkio_start();
-	atomic_inc(&rq->nr_iowait);
-	blk_flush_plug(current);
-	current->in_iowait = 1;
-	schedule();
-	current->in_iowait = 0;
-	atomic_dec(&rq->nr_iowait);
-	delayacct_blkio_end();
-}
-EXPORT_SYMBOL(io_schedule);
-
 long __sched io_schedule_timeout(long timeout)
 {
-	struct rq *rq = raw_rq();
+	int old_iowait = current->in_iowait;
+	struct rq *rq;
 	long ret;
 
+	current->in_iowait = 1;
+	if (old_iowait)
+		blk_schedule_flush_plug(current);
+	else
+		blk_flush_plug(current);
+
 	delayacct_blkio_start();
+	rq = raw_rq();
 	atomic_inc(&rq->nr_iowait);
-	blk_flush_plug(current);
-	current->in_iowait = 1;
 	ret = schedule_timeout(timeout);
-	current->in_iowait = 0;
+	current->in_iowait = old_iowait;
 	atomic_dec(&rq->nr_iowait);
 	delayacct_blkio_end();
+
 	return ret;
 }
+EXPORT_SYMBOL(io_schedule_timeout);
 
 /**
  * sys_sched_get_priority_max - return maximum RT priority.