blk-mq: Use proper cpumask iterator

queue_for_each_ctx() iterates over per_cpu variables under the assumption that
the possible cpu mask cannot have holes. That's wrong as all cpumasks can have
holes. In case there are holes the iteration ends up accessing uninitialized
memory and crashing as a result.

Replace the macro by a proper for_each_possible_cpu() loop and drop the unused
macro blk_ctx_sum() which references queue_for_each_ctx().

Reported-by: Xiong Zhou <jencce.kernel@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index 431fdda2..4ea4dd8 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -416,12 +416,14 @@
 static void blk_mq_sysfs_init(struct request_queue *q)
 {
 	struct blk_mq_ctx *ctx;
-	int i;
+	int cpu;
 
 	kobject_init(&q->mq_kobj, &blk_mq_ktype);
 
-	queue_for_each_ctx(q, ctx, i)
+	for_each_possible_cpu(cpu) {
+		ctx = per_cpu_ptr(q->queue_ctx, cpu);
 		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
+	}
 }
 
 int blk_mq_register_disk(struct gendisk *disk)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 050f7a1..1699baf 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1798,11 +1798,12 @@
 	/*
 	 * Map software to hardware queues
 	 */
-	queue_for_each_ctx(q, ctx, i) {
+	for_each_possible_cpu(i) {
 		/* If the cpu isn't online, the cpu is mapped to first hctx */
 		if (!cpumask_test_cpu(i, online_mask))
 			continue;
 
+		ctx = per_cpu_ptr(q->queue_ctx, i);
 		hctx = q->mq_ops->map_queue(q, i);
 
 		cpumask_set_cpu(i, hctx->cpumask);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 15a73d4..9ac9799 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -263,22 +263,8 @@
 	for ((i) = 0; (i) < (q)->nr_hw_queues &&			\
 	     ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++)
 
-#define queue_for_each_ctx(q, ctx, i)					\
-	for ((i) = 0; (i) < (q)->nr_queues &&				\
-	     ({ ctx = per_cpu_ptr((q)->queue_ctx, (i)); 1; }); (i)++)
-
 #define hctx_for_each_ctx(hctx, ctx, i)					\
 	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\
 	     ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++)
 
-#define blk_ctx_sum(q, sum)						\
-({									\
-	struct blk_mq_ctx *__x;						\
-	unsigned int __ret = 0, __i;					\
-									\
-	queue_for_each_ctx((q), __x, __i)				\
-		__ret += sum;						\
-	__ret;								\
-})
-
 #endif