kernel.h: Add non_block_start/end()

In some special cases we must not block, but there's not a spinlock,
preempt-off, irqs-off or similar critical section already that arms the
might_sleep() debug checks. Add a non_block_start/end() pair to annotate
these.

This will be used in the oom paths of mmu-notifiers, where blocking is not
allowed to make sure there's forward progress. Quoting Michal:

"The notifier is called from quite a restricted context - oom_reaper -
which shouldn't depend on any locks or sleepable conditionals. The code
should be swift as well but we mostly do care about it to make a forward
progress. Checking for sleepable context is the best thing we could come
up with that would describe these demands at least partially."

Peter also asked whether we want to catch spinlocks on top, but Michal
said those are less of a problem because spinlocks can't have an indirect
dependency upon the page allocator and hence close the loop with the oom
reaper.

Suggested by Michal Hocko.

Link: https://lore.kernel.org/r/20190826201425.17547-4-daniel.vetter@ffwll.ch
Acked-by: Christian König <christian.koenig@amd.com> (v1)
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

3 files changed, 40 insertions, 6 deletions

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4fa360a13c1e..d83d403dac2e 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -217,7 +217,9 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
  * might_sleep - annotation for functions that can sleep
  *
  * this macro will print a stack trace if it is executed in an atomic
- * context (spinlock, irq-handler, ...).
+ * context (spinlock, irq-handler, ...). Additional sections where blocking is
+ * not allowed can be annotated with non_block_start() and non_block_end()
+ * pairs.
  *
  * This is a useful debugging help to be able to catch problems early and not
  * be bitten later when the calling function happens to sleep when it is not
@@ -233,6 +235,23 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 # define cant_sleep() \
 	do { __cant_sleep(__FILE__, __LINE__, 0); } while (0)
 # define sched_annotate_sleep()	(current->task_state_change = 0)
+/**
+ * non_block_start - annotate the start of section where sleeping is prohibited
+ *
+ * This is on behalf of the oom reaper, specifically when it is calling the mmu
+ * notifiers. The problem is that if the notifier were to block on, for example,
+ * mutex_lock() and if the process which holds that mutex were to perform a
+ * sleeping memory allocation, the oom reaper is now blocked on completion of
+ * that memory allocation. Other blocking calls like wait_event() pose similar
+ * issues.
+ */
+# define non_block_start() (current->non_block_count++)
+/**
+ * non_block_end - annotate the end of section where sleeping is prohibited
+ *
+ * Closes a section opened by non_block_start().
+ */
+# define non_block_end() WARN_ON(current->non_block_count-- == 0)
 #else
   static inline void ___might_sleep(const char *file, int line,
 				   int preempt_offset) { }
@@ -241,6 +260,8 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
 # define might_sleep() do { might_resched(); } while (0)
 # define cant_sleep() do { } while (0)
 # define sched_annotate_sleep() do { } while (0)
+# define non_block_start() do { } while (0)
+# define non_block_end() do { } while (0)
 #endif
 
 #define might_sleep_if(cond) do { if (cond) might_sleep(); } while (0)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9f51932bd543..c5630f3dca1f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -974,6 +974,10 @@ struct task_struct {
 	struct mutex_waiter		*blocked_on;
 #endif
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+	int				non_block_count;
+#endif
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	unsigned int			irq_events;
 	unsigned long			hardirq_enable_ip;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2b037f195473..57245770d6cc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3700,13 +3700,22 @@ static noinline void __schedule_bug(struct task_struct *prev)
 /*
  * Various schedule()-time debugging checks and statistics:
  */
-static inline void schedule_debug(struct task_struct *prev)
+static inline void schedule_debug(struct task_struct *prev, bool preempt)
 {
 #ifdef CONFIG_SCHED_STACK_END_CHECK
 	if (task_stack_end_corrupted(prev))
 		panic("corrupted stack end detected inside scheduler\n");
 #endif
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+	if (!preempt && prev->state && prev->non_block_count) {
+		printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
+			prev->comm, prev->pid, prev->non_block_count);
+		dump_stack();
+		add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+	}
+#endif
+
 	if (unlikely(in_atomic_preempt_off())) {
 		__schedule_bug(prev);
 		preempt_count_set(PREEMPT_DISABLED);
@@ -3813,7 +3822,7 @@ static void __sched notrace __schedule(bool preempt)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev);
+	schedule_debug(prev, preempt);
 
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
@@ -6570,7 +6579,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 	rcu_sleep_check();
 
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
-	     !is_idle_task(current)) ||
+	     !is_idle_task(current) && !current->non_block_count) ||
 	    system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
 	    oops_in_progress)
 		return;
@@ -6586,8 +6595,8 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 		"BUG: sleeping function called from invalid context at %s:%d\n",
 			file, line);
 	printk(KERN_ERR
-		"in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
-			in_atomic(), irqs_disabled(),
+		"in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
+			in_atomic(), irqs_disabled(), current->non_block_count,
 			current->pid, current->comm);
 
 	if (task_stack_end_corrupted(current))