Merge tag 'block-7.2-20260717' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block fixes from Jens Axboe:

 - Fixes for the dio bounce buffer helpers: correct the alignment of
   bounced dio read bios to avoid a double unpin, handle huge zero
   folios in bio_free_folios(), and don't warn on the larger-order folio
   attempts in the greedy allocation path.

 - Try a slab allocation in bio_alloc_bioset() before falling back to
   the mempool, restoring the previous behavior for non-sleeping
   allocations from a cache-enabled bioset.

 - Serialize elevator changes for the same queue using the writer lock.

 - Fix a race in blk_time_get_ns() where a task preempted between
   setting PF_BLOCK_TS and the cached-timestamp reload could return 0.

 - blk-cgroup fix for leaks and the online flag on a radix_tree_insert()
   failure in blkg_create().

 - Free the copied pages when blk_rq_map_kern() fails after
   blk_rq_append_bio() rejects the bio.

 - Remove manually added partitions on loop device detach, fixing dead
   partition devices left behind and a subsequent LOOP_CONFIGURE -EBUSY

 - Bound the AIX partition lvd scan to the sector that was actually
   read.

 - Show the block operation in error injection rules (Jackie)

* tag 'block-7.2-20260717' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  block: fix aligning of bounced dio read bios
  block: handle huge zero folios in bio_free_folios
  block: try slab allocation in bio_alloc_bioset() before mempool
  block: show operation in error injection rules
  block: serialize elevator changes for the same queue using a writer lock
  block: free copied pages when blk_rq_map_kern() fails
  block: do not warn when doing greedy allocation in folio_alloc_greedy()
  partitions: aix: bound the lvd scan to one sector
  blk-cgroup: fix leaks and online flag on radix_tree_insert failure
  loop: remove manually added partitions on detach
  block: fix race in blk_time_get_ns() returning 0

Author: torvalds

block/bio.c

@@ -555,6 +555,14 @@ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
 		bio = bio_alloc_percpu_cache(bs);
 	} else {
 		opf &= ~REQ_ALLOC_CACHE;
+	}
+
+	/*
+	 * For a bioset without a percpu cache, or when the percpu cache was
+	 * empty, try a slab allocation with optimistic GFP_ flags before
+	 * falling back to the mempool.
+	 */
+	if (!bio) {
 		p = kmem_cache_alloc(bs->bio_slab, gfp);
 		if (p)
 			bio = p + bs->front_pad;
@@ -1191,7 +1199,7 @@ void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter)
  * for the next iteration.
  */
 static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
-			    unsigned len_align_mask)
+				   struct bio_vec *bv, unsigned len_align_mask)
 {
 	size_t nbytes = bio->bi_iter.bi_size & len_align_mask;
 
@@ -1200,23 +1208,16 @@ static int bio_iov_iter_align_down(struct bio *bio, struct iov_iter *iter,
 
 	iov_iter_revert(iter, nbytes);
 	bio->bi_iter.bi_size -= nbytes;
-	do {
-		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
-		if (nbytes < bv->bv_len) {
-			bv->bv_len -= nbytes;
-			break;
-		}
-
+	while (nbytes >= bv->bv_len) {
 		if (bio_flagged(bio, BIO_PAGE_PINNED))
 			unpin_user_page(bv->bv_page);
 
-		bio->bi_vcnt--;
+		if (!--bio->bi_vcnt)
+			return -EFAULT;
 		nbytes -= bv->bv_len;
-	} while (nbytes);
-
-	if (!bio->bi_vcnt)
-		return -EFAULT;
+		bv--;
+	}
+	bv->bv_len -= nbytes;
 	return 0;
 }
 
@@ -1276,7 +1277,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
 
 	if (is_pci_p2pdma_page(bio->bi_io_vec->bv_page))
 		bio->bi_opf |= REQ_NOMERGE;
-	return bio_iov_iter_align_down(bio, iter, len_align_mask);
+	return bio_iov_iter_align_down(bio, iter,
+			&bio->bi_io_vec[bio->bi_vcnt - 1], len_align_mask);
 }
 
 static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size,
@@ -1285,7 +1287,8 @@ static struct folio *folio_alloc_greedy(gfp_t gfp, size_t *size,
 	struct folio *folio;
 
 	while (*size > minsize) {
-		folio = folio_alloc(gfp | __GFP_NORETRY, get_order(*size));
+		folio = folio_alloc(gfp | __GFP_NORETRY | __GFP_NOWARN,
+				    get_order(*size));
 		if (folio)
 			return folio;
 		*size = rounddown_pow_of_two(*size - 1);
@@ -1302,7 +1305,7 @@ static void bio_free_folios(struct bio *bio)
 	bio_for_each_bvec_all(bv, bio, i) {
 		struct folio *folio = bvec_folio(bv);
 
-		if (!is_zero_folio(folio))
+		if (!is_zero_folio(folio) && !is_huge_zero_folio(folio))
 			folio_put(folio);
 	}
 }
@@ -1360,29 +1363,27 @@ static int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
 
 	if (!bio->bi_iter.bi_size)
 		return -ENOMEM;
-	return bio_iov_iter_align_down(bio, iter, minsize - 1);
+	return bio_iov_iter_align_down(bio, iter,
+			&bio->bi_io_vec[bio->bi_vcnt - 1], minsize - 1);
 }
 
 static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter,
 		size_t maxlen, size_t minsize)
 {
 	size_t len = min3(iov_iter_count(iter), maxlen, SZ_1M);
 	struct folio *folio;
+	ssize_t ret;
 
 	folio = folio_alloc_greedy(GFP_KERNEL, &len, minsize);
 	if (!folio)
 		return -ENOMEM;
 
 	do {
-		ssize_t ret;
-
 		ret = iov_iter_extract_bvecs(iter, bio->bi_io_vec + 1, len,
 				&bio->bi_vcnt, bio->bi_max_vecs - 1, 0);
 		if (ret <= 0) {
-			if (!bio->bi_vcnt) {
-				folio_put(folio);
-				return ret;
-			}
+			if (!bio->bi_vcnt)
+				goto out_folio_put;
 			break;
 		}
 		len -= ret;
@@ -1398,7 +1399,20 @@ static int bio_iov_iter_bounce_read(struct bio *bio, struct iov_iter *iter,
 	bvec_set_folio(&bio->bi_io_vec[0], folio, bio->bi_iter.bi_size, 0);
 	if (iov_iter_extract_will_pin(iter))
 		bio_set_flag(bio, BIO_PAGE_PINNED);
-	return bio_iov_iter_align_down(bio, iter, minsize - 1);
+
+	/* The first vec stores the bounce buffer, so do not subtract 1 here. */
+	ret = bio_iov_iter_align_down(bio, iter,
+			&bio->bi_io_vec[bio->bi_vcnt], minsize - 1);
+	if (ret)
+		goto out_folio_put;
+
+	/* Update the bounc buffer bv_len to the aligned down size. */
+	bio->bi_io_vec[0].bv_len = bio->bi_iter.bi_size;
+	return 0;
+
+out_folio_put:
+	folio_put(folio);
+	return ret;
 }
 
 /**

block/blk-cgroup.c

@@ -434,15 +434,15 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, struct gendisk *disk,
 				blkg->pd[i]->online = true;
 			}
 		}
+		blkg->online = true;
 	}
-	blkg->online = true;
 	spin_unlock(&blkcg->lock);
 
 	if (!ret)
 		return blkg;
 
 	/* @blkg failed fully initialized, use the usual release path */
-	blkg_put(blkg);
+	percpu_ref_kill(&blkg->refcnt);
 	return ERR_PTR(ret);
 
 err_free_blkg:

block/blk-map.c

@@ -653,6 +653,7 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len,
 		gfp_t gfp_mask)
 {
 	unsigned long addr = (unsigned long) kbuf;
+	bool do_copy;
 	struct bio *bio;
 	int ret;
 
@@ -661,7 +662,8 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len,
 	if (!len || !kbuf)
 		return -EINVAL;
 
-	if (!blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf))
+	do_copy = !blk_rq_aligned(rq->q, addr, len) || object_is_on_stack(kbuf);
+	if (do_copy)
 		bio = bio_copy_kern(rq, kbuf, len, gfp_mask);
 	else
 		bio = bio_map_kern(rq, kbuf, len, gfp_mask);
@@ -670,8 +672,11 @@ int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len,
 		return PTR_ERR(bio);
 
 	ret = blk_rq_append_bio(rq, bio);
-	if (unlikely(ret))
+	if (unlikely(ret)) {
+		if (do_copy)
+			bio_free_pages(bio);
 		blk_mq_map_bio_put(bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(blk_rq_map_kern);

block/blk.h

@@ -717,6 +717,7 @@ static inline int req_ref_read(struct request *req)
 static inline u64 blk_time_get_ns(void)
 {
 	struct blk_plug *plug = current->plug;
+	u64 now;
 
 	if (!plug || !in_task())
 		return ktime_get_ns();
@@ -725,12 +726,18 @@ static inline u64 blk_time_get_ns(void)
 	 * 0 could very well be a valid time, but rather than flag "this is
 	 * a valid timestamp" separately, just accept that we'll do an extra
 	 * ktime_get_ns() if we just happen to get 0 as the current time.
+	 *
+	 * cur_ktime can be zeroed by pre-emption the moment PF_BLOCK_TS is set.
 	 */
-	if (!plug->cur_ktime) {
-		plug->cur_ktime = ktime_get_ns();
+	now = READ_ONCE(plug->cur_ktime);
+	if (!now) {
+		now = ktime_get_ns();
+		WRITE_ONCE(plug->cur_ktime, now);
+		/* Ensure PF_BLOCK_TS is set after cur_ktime. */
+		barrier();
 		current->flags |= PF_BLOCK_TS;
 	}
-	return plug->cur_ktime;
+	return now;
 }
 
 static inline ktime_t blk_time_get(void)

block/elevator.c

@@ -812,8 +812,13 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	 * reference during concurrent disk deletion:
 	 *   update_nr_hwq_lock -> kn->active (via del_gendisk -> kobject_del)
 	 *   kn->active -> update_nr_hwq_lock (via this sysfs write path)
+	 *
+	 * Use the writer lock instead of the reader lock of update_nr_hwq_lock
+	 * to serialize the two-stage elevator switch steps in
+	 * elevator_change(): the core switch step under the elevator lock and
+	 * the elevator_change_done() step outside the elevator lock.
 	 */
-	if (!down_read_trylock(&set->update_nr_hwq_lock)) {
+	if (!down_write_trylock(&set->update_nr_hwq_lock)) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -824,7 +829,7 @@ ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 	} else {
 		ret = -ENOENT;
 	}
-	up_read(&set->update_nr_hwq_lock);
+	up_write(&set->update_nr_hwq_lock);
 
 out:
 	if (ctx.type)

block/error-injection.c

@@ -276,9 +276,10 @@ static int blk_error_injection_show(struct seq_file *s, void *private)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(inj, &disk->error_injection_list, entry) {
-		seq_printf(s, "%llu:%llu status=%s,chance=%u",
-			inj->start, inj->end,
-			blk_status_to_tag(inj->status), inj->chance);
+		seq_printf(s, "%llu:%llu op=%s,status=%s,chance=%u",
+			   inj->start, inj->end,
+			   blk_op_str(inj->op),
+			   blk_status_to_tag(inj->status), inj->chance);
 		seq_putc(s, '\n');
 	}
 	rcu_read_unlock();

block/partitions/aix.c

@@ -208,7 +208,14 @@ int aix_partition(struct parsed_partitions *state)
 		if (n) {
 			int foundlvs = 0;
 
-			for (i = 0; foundlvs < numlvs && i < state->limit; i += 1) {
+			/*
+			 * The lvd array was read as a single sector; only the
+			 * struct lvd entries that fit in it are valid.  Bound the
+			 * scan so an on-disk numlvs larger than that cannot walk
+			 * the read buffer out of bounds.
+			 */
+			for (i = 0; foundlvs < numlvs && i < state->limit &&
+				    i < SECTOR_SIZE / (int)sizeof(struct lvd); i++) {
 				lvip[i].pps_per_lv = be16_to_cpu(p[i].num_lps);
 				if (lvip[i].pps_per_lv)
 					foundlvs += 1;

drivers/block/loop.c

@@ -1113,6 +1113,7 @@ static void __loop_clr_fd(struct loop_device *lo)
 	struct queue_limits lim;
 	struct file *filp;
 	gfp_t gfp = lo->old_gfp_mask;
+	int err;
 
 	spin_lock_irq(&lo->lo_lock);
 	filp = lo->lo_backing_file;
@@ -1146,26 +1147,21 @@ static void __loop_clr_fd(struct loop_device *lo)
 
 	disk_force_media_change(lo->lo_disk);
 
-	if (lo->lo_flags & LO_FLAGS_PARTSCAN) {
-		int err;
-
-		/*
-		 * open_mutex has been held already in release path, so don't
-		 * acquire it if this function is called in such case.
-		 *
-		 * If the reread partition isn't from release path, lo_refcnt
-		 * must be at least one and it can only become zero when the
-		 * current holder is released.
-		 */
-		err = bdev_disk_changed(lo->lo_disk, false);
-		if (err)
-			pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
-				__func__, lo->lo_number, err);
-		/* Device is gone, no point in returning error */
-	}
+	/*
+	 * Remove all partitions, including partitions added manually with
+	 * BLKPG, which may exist even if LO_FLAGS_PARTSCAN is not set.
+	 *
+	 * open_mutex has been held already in release path, so don't acquire
+	 * it here.
+	 */
+	err = bdev_disk_changed(lo->lo_disk, false);
+	if (err)
+		pr_warn("%s: partition scan of loop%d failed (rc=%d)\n",
+			__func__, lo->lo_number, err);
+	/* Device is gone, no point in returning error */
 
 	/*
-	 * lo->lo_state is set to Lo_unbound here after above partscan has
+	 * lo->lo_state is set to Lo_unbound here after removing partitions has
 	 * finished. There cannot be anybody else entering __loop_clr_fd() as
 	 * Lo_rundown state protects us from all the other places trying to
 	 * change the 'lo' device.