Merge tag 'for-5.19/block-2022-05-22' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Here are the core block changes for 5.19. This contains:

   - blk-throttle accounting fix (Laibin)

   - Series removing redundant assignments (Michal)

   - Expose bio cache via the bio_set, so that DM can use it (Mike)

   - Finish off the bio allocation interface cleanups by dealing with
     the weirdest member of the family. bio_kmalloc combines a kmalloc
     for the bio and bio_vecs with a hidden bio_init call and magic
     cleanup semantics (Christoph)

   - Clean up the block layer API so that APIs consumed by file systems
     are (almost) only struct block_device based, so that file systems
     don't have to poke into block layer internals like the
     request_queue (Christoph)

   - Clean up the blk_execute_rq* API (Christoph)

   - Clean up various lose end in the blk-cgroup code to make it easier
     to follow in preparation of reworking the blkcg assignment for bios
     (Christoph)

   - Fix use-after-free issues in BFQ when processes with merged queues
     get moved to different cgroups (Jan)

   - BFQ fixes (Jan)

   - Various fixes and cleanups (Bart, Chengming, Fanjun, Julia, Ming,
     Wolfgang, me)"

* tag 'for-5.19/block-2022-05-22' of git://git.kernel.dk/linux-block: (83 commits)
  blk-mq: fix typo in comment
  bfq: Remove bfq_requeue_request_body()
  bfq: Remove superfluous conversion from RQ_BIC()
  bfq: Allow current waker to defend against a tentative one
  bfq: Relax waker detection for shared queues
  blk-cgroup: delete rcu_read_lock_held() WARN_ON_ONCE()
  blk-throttle: Set BIO_THROTTLED when bio has been throttled
  blk-cgroup: Remove unnecessary rcu_read_lock/unlock()
  blk-cgroup: always terminate io.stat lines
  block, bfq: make bfq_has_work() more accurate
  block, bfq: protect 'bfqd->queued' by 'bfqd->lock'
  block: cleanup the VM accounting in submit_bio
  block: Fix the bio.bi_opf comment
  block: reorder the REQ_ flags
  blk-iocost: combine local_stat and desc_stat to stat
  block: improve the error message from bio_check_eod
  block: allow passing a NULL bdev to bio_alloc_clone/bio_init_clone
  block: remove superfluous calls to blkcg_bio_issue_init
  kthread: unexport kthread_blkcg
  blk-cgroup: cleanup blkcg_maybe_throttle_current
  ...

4 files changed, 21 insertions, 35 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 7176af65b103..ff60bd7d74e0 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <linux/blkdev.h>
 #include <linux/wait.h>
 #include <linux/rbtree.h>
 #include <linux/kthread.h>
@@ -390,7 +391,6 @@ static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
-	struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css);
 	struct backing_dev_info *bdi = wb->bdi;
 
 	mutex_lock(&wb->bdi->cgwb_release_mutex);
@@ -401,7 +401,7 @@ static void cgwb_release_workfn(struct work_struct *work)
 	mutex_unlock(&wb->bdi->cgwb_release_mutex);
 
 	/* triggers blkg destruction if no online users left */
-	blkcg_unpin_online(blkcg);
+	blkcg_unpin_online(wb->blkcg_css);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 
@@ -446,7 +446,6 @@ static int cgwb_create(struct backing_dev_info *bdi,
 {
 	struct mem_cgroup *memcg;
 	struct cgroup_subsys_state *blkcg_css;
-	struct blkcg *blkcg;
 	struct list_head *memcg_cgwb_list, *blkcg_cgwb_list;
 	struct bdi_writeback *wb;
 	unsigned long flags;
@@ -454,9 +453,8 @@ static int cgwb_create(struct backing_dev_info *bdi,
 
 	memcg = mem_cgroup_from_css(memcg_css);
 	blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys);
-	blkcg = css_to_blkcg(blkcg_css);
 	memcg_cgwb_list = &memcg->cgwb_list;
-	blkcg_cgwb_list = &blkcg->cgwb_list;
+	blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css);
 
 	/* look up again under lock and discard on blkcg mismatch */
 	spin_lock_irqsave(&cgwb_lock, flags);
@@ -511,7 +509,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 			list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
 			list_add(&wb->memcg_node, memcg_cgwb_list);
 			list_add(&wb->blkcg_node, blkcg_cgwb_list);
-			blkcg_pin_online(blkcg);
+			blkcg_pin_online(blkcg_css);
 			css_get(memcg_css);
 			css_get(blkcg_css);
 		}
@@ -724,18 +722,19 @@ void wb_memcg_offline(struct mem_cgroup *memcg)
 
 /**
  * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined
- * @blkcg: blkcg being offlined
+ * @css: blkcg being offlined
  *
  * Also prevents creation of any new wb's associated with @blkcg.
  */
-void wb_blkcg_offline(struct blkcg *blkcg)
+void wb_blkcg_offline(struct cgroup_subsys_state *css)
 {
 	struct bdi_writeback *wb, *next;
+	struct list_head *list = blkcg_get_cgwb_list(css);
 
 	spin_lock_irq(&cgwb_lock);
-	list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node)
+	list_for_each_entry_safe(wb, next, list, blkcg_node)
 		cgwb_kill(wb);
-	blkcg->cgwb_list.next = NULL;	/* prevent new wb's */
+	list->next = NULL;	/* prevent new wb's */
 	spin_unlock_irq(&cgwb_lock);
 }
 
diff --git a/mm/page_io.c b/mm/page_io.c
index 89fbf3cae30f..3fbdab6a940e 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -360,7 +360,6 @@ int swap_readpage(struct page *page, bool synchronous)
 	 * attempt to access it in the page fault retry time check.
 	 */
 	if (synchronous) {
-		bio->bi_opf |= REQ_POLLED;
 		get_task_struct(current);
 		bio->bi_private = current;
 	}
@@ -372,8 +371,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		if (!READ_ONCE(bio->bi_private))
 			break;
 
-		if (!bio_poll(bio, NULL, 0))
-			blk_io_schedule();
+		blk_io_schedule();
 	}
 	__set_current_state(TASK_RUNNING);
 	bio_put(bio);
diff --git a/mm/readahead.c b/mm/readahead.c
index 4a60cdb64262..26bf74a6b2fe 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -113,6 +113,7 @@
  * ->readpage() which may be less efficient.
  */
 
+#include <linux/blkdev.h>
 #include <linux/kernel.h>
 #include <linux/dax.h>
 #include <linux/gfp.h>
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 63c61f8b2611..981a6e85c88e 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -6,6 +6,7 @@
  *  Swap reorganised 29.12.95, Stephen Tweedie
  */
 
+#include <linux/blkdev.h>
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task.h>
@@ -179,7 +180,7 @@ static int discard_swap(struct swap_info_struct *si)
 	nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
 	if (nr_blocks) {
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, 0);
+				nr_blocks, GFP_KERNEL);
 		if (err)
 			return err;
 		cond_resched();
@@ -190,7 +191,7 @@ static int discard_swap(struct swap_info_struct *si)
 		nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
 
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, 0);
+				nr_blocks, GFP_KERNEL);
 		if (err)
 			break;
 
@@ -254,7 +255,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 		start_block <<= PAGE_SHIFT - 9;
 		nr_blocks <<= PAGE_SHIFT - 9;
 		if (blkdev_issue_discard(si->bdev, start_block,
-					nr_blocks, GFP_NOIO, 0))
+					nr_blocks, GFP_NOIO))
 			break;
 
 		se = next_se(se);
@@ -2466,7 +2467,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	if (p->flags & SWP_CONTINUED)
 		free_swap_count_continuations(p);
 
-	if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev)))
+	if (!p->bdev || !bdev_nonrot(p->bdev))
 		atomic_dec(&nr_rotate_swap);
 
 	mutex_lock(&swapon_mutex);
@@ -2761,7 +2762,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 		 * write only restriction.  Hence zoned block devices are not
 		 * suitable for swapping.  Disallow them here.
 		 */
-		if (blk_queue_is_zoned(p->bdev->bd_disk->queue))
+		if (bdev_is_zoned(p->bdev))
 			return -EINVAL;
 		p->flags |= SWP_BLKDEV;
 	} else if (S_ISREG(inode->i_mode)) {
@@ -2957,20 +2958,6 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	return nr_extents;
 }
 
-/*
- * Helper to sys_swapon determining if a given swap
- * backing device queue supports DISCARD operations.
- */
-static bool swap_discardable(struct swap_info_struct *si)
-{
-	struct request_queue *q = bdev_get_queue(si->bdev);
-
-	if (!blk_queue_discard(q))
-		return false;
-
-	return true;
-}
-
 SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 {
 	struct swap_info_struct *p;
@@ -3065,13 +3052,13 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
-	if (p->bdev && blk_queue_stable_writes(p->bdev->bd_disk->queue))
+	if (p->bdev && bdev_stable_writes(p->bdev))
 		p->flags |= SWP_STABLE_WRITES;
 
 	if (p->bdev && p->bdev->bd_disk->fops->rw_page)
 		p->flags |= SWP_SYNCHRONOUS_IO;
 
-	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
+	if (p->bdev && bdev_nonrot(p->bdev)) {
 		int cpu;
 		unsigned long ci, nr_cluster;
 
@@ -3132,7 +3119,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 					 sizeof(long),
 					 GFP_KERNEL);
 
-	if (p->bdev && (swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
+	if ((swap_flags & SWAP_FLAG_DISCARD) &&
+	    p->bdev && bdev_max_discard_sectors(p->bdev)) {
 		/*
 		 * When discard is enabled for swap with no particular
 		 * policy flagged, we set all swap discard flags here in