Merge tag 'block-6.9-20240412' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - MD pull request via Song:
       - UAF fix (Yu)

 - Avoid out-of-bounds shift in blk-iocost (Rik)

 - Fix for q->blkg_list corruption (Ming)

 - Relax virt boundary mask/size segment checking (Ming)

* tag 'block-6.9-20240412' of git://git.kernel.dk/linux:
  block: fix that blk_time_get_ns() doesn't update time after schedule
  block: allow device to have both virt_boundary_mask and max segment size
  block: fix q->blkg_list corruption during disk rebind
  blk-iocost: avoid out of bounds shift
  raid1: fix use-after-free for original bio in raid1_write_request()

6 files changed, 22 insertions, 17 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bdbb557feb5a0e..059467086b1312 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1409,6 +1409,12 @@ static int blkcg_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
+void blkg_init_queue(struct request_queue *q)
+{
+	INIT_LIST_HEAD(&q->blkg_list);
+	mutex_init(&q->blkcg_mutex);
+}
+
 int blkcg_init_disk(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
@@ -1416,9 +1422,6 @@ int blkcg_init_disk(struct gendisk *disk)
 	bool preloaded;
 	int ret;
 
-	INIT_LIST_HEAD(&q->blkg_list);
-	mutex_init(&q->blkcg_mutex);
-
 	new_blkg = blkg_alloc(&blkcg_root, disk, GFP_KERNEL);
 	if (!new_blkg)
 		return -ENOMEM;
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 78b74106bf10c5..90b3959d88cfa4 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -189,6 +189,7 @@ struct blkcg_policy {
 extern struct blkcg blkcg_root;
 extern bool blkcg_debug_stats;
 
+void blkg_init_queue(struct request_queue *q);
 int blkcg_init_disk(struct gendisk *disk);
 void blkcg_exit_disk(struct gendisk *disk);
 
@@ -482,6 +483,7 @@ struct blkcg {
 };
 
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline void blkg_init_queue(struct request_queue *q) { }
 static inline int blkcg_init_disk(struct gendisk *disk) { return 0; }
 static inline void blkcg_exit_disk(struct gendisk *disk) { }
 static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
diff --git a/block/blk-core.c b/block/blk-core.c
index a16b5abdbbf56f..b795ac177281ad 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -442,6 +442,8 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 	init_waitqueue_head(&q->mq_freeze_wq);
 	mutex_init(&q->mq_freeze_lock);
 
+	blkg_init_queue(q);
+
 	/*
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
 	 * See blk_register_queue() for details.
@@ -1195,6 +1197,7 @@ void __blk_flush_plug(struct blk_plug *plug, bool from_schedule)
 	if (unlikely(!rq_list_empty(plug->cached_rq)))
 		blk_mq_free_plug_rqs(plug);
 
+	plug->cur_ktime = 0;
 	current->flags &= ~PF_BLOCK_TS;
 }
 
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 9a85bfbbc45a01..baa20c85799d54 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1347,7 +1347,7 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
 {
 	struct ioc *ioc = iocg->ioc;
 	struct blkcg_gq *blkg = iocg_to_blkg(iocg);
-	u64 tdelta, delay, new_delay;
+	u64 tdelta, delay, new_delay, shift;
 	s64 vover, vover_pct;
 	u32 hwa;
 
@@ -1362,8 +1362,9 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now)
 
 	/* calculate the current delay in effect - 1/2 every second */
 	tdelta = now->now - iocg->delay_at;
-	if (iocg->delay)
-		delay = iocg->delay >> div64_u64(tdelta, USEC_PER_SEC);
+	shift = div64_u64(tdelta, USEC_PER_SEC);
+	if (iocg->delay && shift < BITS_PER_LONG)
+		delay = iocg->delay >> shift;
 	else
 		delay = 0;
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index cdbaef159c4bc3..d2731843f2fccb 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -182,17 +182,13 @@ static int blk_validate_limits(struct queue_limits *lim)
 		return -EINVAL;
 
 	/*
-	 * Devices that require a virtual boundary do not support scatter/gather
-	 * I/O natively, but instead require a descriptor list entry for each
-	 * page (which might not be identical to the Linux PAGE_SIZE).  Because
-	 * of that they are not limited by our notion of "segment size".
+	 * Stacking device may have both virtual boundary and max segment
+	 * size limit, so allow this setting now, and long-term the two
+	 * might need to move out of stacking limits since we have immutable
+	 * bvec and lower layer bio splitting is supposed to handle the two
+	 * correctly.
 	 */
-	if (lim->virt_boundary_mask) {
-		if (WARN_ON_ONCE(lim->max_segment_size &&
-				 lim->max_segment_size != UINT_MAX))
-			return -EINVAL;
-		lim->max_segment_size = UINT_MAX;
-	} else {
+	if (!lim->virt_boundary_mask) {
 		/*
 		 * The maximum segment size has an odd historic 64k default that
 		 * drivers probably should override.  Just like the I/O size we
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index be8ac24f50b6ad..7b8a71ca66dde0 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1558,7 +1558,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		for (j = 0; j < i; j++)
 			if (r1_bio->bios[j])
 				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
-		free_r1bio(r1_bio);
+		mempool_free(r1_bio, &conf->r1bio_pool);
 		allow_barrier(conf, bio->bi_iter.bi_sector);
 
 		if (bio->bi_opf & REQ_NOWAIT) {