Merge tag 'for-linus-20190715' of git://git.kernel.dk/linux-block

Pull more block updates from Jens Axboe:
 "A later pull request with some followup items. I had some vacation
  coming up to the merge window, so certain things items were delayed a
  bit. This pull request also contains fixes that came in within the
  last few days of the merge window, which I didn't want to push right
  before sending you a pull request.

  This contains:

   - NVMe pull request, mostly fixes, but also a few minor items on the
     feature side that were timing constrained (Christoph et al)

   - Report zones fixes (Damien)

   - Removal of dead code (Damien)

   - Turn on cgroup psi memstall (Josef)

   - block cgroup MAINTAINERS entry (Konstantin)

   - Flush init fix (Josef)

   - blk-throttle low iops timing fix (Konstantin)

   - nbd resize fixes (Mike)

   - nbd 0 blocksize crash fix (Xiubo)

   - block integrity error leak fix (Wenwen)

   - blk-cgroup writeback and priority inheritance fixes (Tejun)"

* tag 'for-linus-20190715' of git://git.kernel.dk/linux-block: (42 commits)
  MAINTAINERS: add entry for block io cgroup
  null_blk: fixup ->report_zones() for !CONFIG_BLK_DEV_ZONED
  block: Limit zone array allocation size
  sd_zbc: Fix report zones buffer allocation
  block: Kill gfp_t argument of blkdev_report_zones()
  block: Allow mapping of vmalloc-ed buffers
  block/bio-integrity: fix a memory leak bug
  nvme: fix NULL deref for fabrics options
  nbd: add netlink reconfigure resize support
  nbd: fix crash when the blksize is zero
  block: Disable write plugging for zoned block devices
  block: Fix elevator name declaration
  block: Remove unused definitions
  nvme: fix regression upon hot device removal and insertion
  blk-throttle: fix zero wait time for iops throttled group
  block: Fix potential overflow in blk_report_zones()
  blkcg: implement REQ_CGROUP_PUNT
  blkcg, writeback: Implement wbc_blkcg_css()
  blkcg, writeback: Add wbc->no_cgroup_owner
  blkcg, writeback: Rename wbc_account_io() to wbc_account_cgroup_owner()
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -2124,7 +2124,7 @@ following two functions.
 	a queue (device) has been associated with the bio and
 	before submission.
 
-  wbc_account_io(@wbc, @page, @bytes)
+  wbc_account_cgroup_owner(@wbc, @page, @bytes)
 	Should be called for each data segment being written out.
 	While this function doesn't care exactly when it's called
 	during the writeback session, it's the easiest and most

Documentation/block/biodoc.txt

@@ -843,11 +843,6 @@ elevator_latter_req_fn		These return the request before or after the
 
 elevator_completed_req_fn	called when a request is completed.
 
-elevator_may_queue_fn		returns true if the scheduler wants to allow the
-				current context to queue a new request even if
-				it is over the queue limit. This must be used
-				very carefully!!
-
 elevator_set_req_fn
 elevator_put_req_fn		Must be used to allocate and free any elevator
 				specific storage for a request.

MAINTAINERS

@@ -4183,6 +4183,19 @@ S:	Maintained
 F:	mm/memcontrol.c
 F:	mm/swap_cgroup.c
 
+CONTROL GROUP - BLOCK IO CONTROLLER (BLKIO)
+M:	Tejun Heo <[email protected]>
+M:	Jens Axboe <[email protected]>
+L:	[email protected]
+L:	[email protected]
+T:	git git://git.kernel.dk/linux-block
+F:	Documentation/cgroup-v1/blkio-controller.rst
+F:	block/blk-cgroup.c
+F:	include/linux/blk-cgroup.h
+F:	block/blk-throttle.c
+F:	block/blk-iolatency.c
+F:	block/bfq-cgroup.c
+
 CORETEMP HARDWARE MONITORING DRIVER
 M:	Fenghua Yu <[email protected]>
 L:	[email protected]

block/bio-integrity.c

@@ -276,8 +276,12 @@ bool bio_integrity_prep(struct bio *bio)
 		ret = bio_integrity_add_page(bio, virt_to_page(buf),
 					     bytes, offset);
 
-		if (ret == 0)
-			return false;
+		if (ret == 0) {
+			printk(KERN_ERR "could not attach integrity payload\n");
+			kfree(buf);
+			status = BLK_STS_RESOURCE;
+			goto err_end_io;
+		}
 
 		if (ret < bytes)
 			break;

block/bio.c

@@ -16,6 +16,7 @@
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
 #include <linux/blk-cgroup.h>
+#include <linux/highmem.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
@@ -1441,8 +1442,22 @@ void bio_unmap_user(struct bio *bio)
 	bio_put(bio);
 }
 
+static void bio_invalidate_vmalloc_pages(struct bio *bio)
+{
+#ifdef ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+	if (bio->bi_private && !op_is_write(bio_op(bio))) {
+		unsigned long i, len = 0;
+
+		for (i = 0; i < bio->bi_vcnt; i++)
+			len += bio->bi_io_vec[i].bv_len;
+		invalidate_kernel_vmap_range(bio->bi_private, len);
+	}
+#endif
+}
+
 static void bio_map_kern_endio(struct bio *bio)
 {
+	bio_invalidate_vmalloc_pages(bio);
 	bio_put(bio);
 }
 
@@ -1463,13 +1478,20 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	unsigned long start = kaddr >> PAGE_SHIFT;
 	const int nr_pages = end - start;
+	bool is_vmalloc = is_vmalloc_addr(data);
+	struct page *page;
 	int offset, i;
 	struct bio *bio;
 
 	bio = bio_kmalloc(gfp_mask, nr_pages);
 	if (!bio)
 		return ERR_PTR(-ENOMEM);
 
+	if (is_vmalloc) {
+		flush_kernel_vmap_range(data, len);
+		bio->bi_private = data;
+	}
+
 	offset = offset_in_page(kaddr);
 	for (i = 0; i < nr_pages; i++) {
 		unsigned int bytes = PAGE_SIZE - offset;
@@ -1480,7 +1502,11 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
 		if (bytes > len)
 			bytes = len;
 
-		if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
+		if (!is_vmalloc)
+			page = virt_to_page(data);
+		else
+			page = vmalloc_to_page(data);
+		if (bio_add_pc_page(q, bio, page, bytes,
 				    offset) < bytes) {
 			/* we don't support partial mappings */
 			bio_put(bio);

block/blk-cgroup.c

@@ -29,6 +29,7 @@
 #include <linux/ctype.h>
 #include <linux/blk-cgroup.h>
 #include <linux/tracehook.h>
+#include <linux/psi.h>
 #include "blk.h"
 
 #define MAX_KEY_LEN 100
@@ -47,12 +48,14 @@ struct blkcg blkcg_root;
 EXPORT_SYMBOL_GPL(blkcg_root);
 
 struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;
+EXPORT_SYMBOL_GPL(blkcg_root_css);
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
 static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 
 static bool blkcg_debug_stats = false;
+static struct workqueue_struct *blkcg_punt_bio_wq;
 
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
@@ -87,6 +90,8 @@ static void __blkg_release(struct rcu_head *rcu)
 {
 	struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);
 
+	WARN_ON(!bio_list_empty(&blkg->async_bios));
+
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
 	if (blkg->parent)
@@ -112,6 +117,23 @@ static void blkg_release(struct percpu_ref *ref)
 	call_rcu(&blkg->rcu_head, __blkg_release);
 }
 
+static void blkg_async_bio_workfn(struct work_struct *work)
+{
+	struct blkcg_gq *blkg = container_of(work, struct blkcg_gq,
+					     async_bio_work);
+	struct bio_list bios = BIO_EMPTY_LIST;
+	struct bio *bio;
+
+	/* as long as there are pending bios, @blkg can't go away */
+	spin_lock_bh(&blkg->async_bio_lock);
+	bio_list_merge(&bios, &blkg->async_bios);
+	bio_list_init(&blkg->async_bios);
+	spin_unlock_bh(&blkg->async_bio_lock);
+
+	while ((bio = bio_list_pop(&bios)))
+		submit_bio(bio);
+}
+
 /**
  * blkg_alloc - allocate a blkg
  * @blkcg: block cgroup the new blkg is associated with
@@ -140,6 +162,9 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 
 	blkg->q = q;
 	INIT_LIST_HEAD(&blkg->q_node);
+	spin_lock_init(&blkg->async_bio_lock);
+	bio_list_init(&blkg->async_bios);
+	INIT_WORK(&blkg->async_bio_work, blkg_async_bio_workfn);
 	blkg->blkcg = blkcg;
 
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
@@ -1526,6 +1551,25 @@ void blkcg_policy_unregister(struct blkcg_policy *pol)
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
 
+bool __blkcg_punt_bio_submit(struct bio *bio)
+{
+	struct blkcg_gq *blkg = bio->bi_blkg;
+
+	/* consume the flag first */
+	bio->bi_opf &= ~REQ_CGROUP_PUNT;
+
+	/* never bounce for the root cgroup */
+	if (!blkg->parent)
+		return false;
+
+	spin_lock_bh(&blkg->async_bio_lock);
+	bio_list_add(&blkg->async_bios, bio);
+	spin_unlock_bh(&blkg->async_bio_lock);
+
+	queue_work(blkcg_punt_bio_wq, &blkg->async_bio_work);
+	return true;
+}
+
 /*
  * Scale the accumulated delay based on how long it has been since we updated
  * the delay.  We only call this when we are adding delay, in case it's been a
@@ -1587,6 +1631,7 @@ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
  */
 static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
+	unsigned long pflags;
 	u64 now = ktime_to_ns(ktime_get());
 	u64 exp;
 	u64 delay_nsec = 0;
@@ -1613,11 +1658,8 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 	 */
 	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
 
-	/*
-	 * TODO: the use_memdelay flag is going to be for the upcoming psi stuff
-	 * that hasn't landed upstream yet.  Once that stuff is in place we need
-	 * to do a psi_memstall_enter/leave if memdelay is set.
-	 */
+	if (use_memdelay)
+		psi_memstall_enter(&pflags);
 
 	exp = ktime_add_ns(now, delay_nsec);
 	tok = io_schedule_prepare();
@@ -1627,6 +1669,9 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 			break;
 	} while (!fatal_signal_pending(current));
 	io_schedule_finish(tok);
+
+	if (use_memdelay)
+		psi_memstall_leave(&pflags);
 }
 
 /**
@@ -1726,5 +1771,16 @@ void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
 	atomic64_add(delta, &blkg->delay_nsec);
 }
 
+static int __init blkcg_init(void)
+{
+	blkcg_punt_bio_wq = alloc_workqueue("blkcg_punt_bio",
+					    WQ_MEM_RECLAIM | WQ_FREEZABLE |
+					    WQ_UNBOUND | WQ_SYSFS, 0);
+	if (!blkcg_punt_bio_wq)
+		return -ENOMEM;
+	return 0;
+}
+subsys_initcall(blkcg_init);
+
 module_param(blkcg_debug_stats, bool, 0644);
 MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");

block/blk-core.c

@@ -117,6 +117,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->internal_tag = -1;
 	rq->start_time_ns = ktime_get_ns();
 	rq->part = NULL;
+	refcount_set(&rq->ref, 1);
 }
 EXPORT_SYMBOL(blk_rq_init);
 
@@ -687,7 +688,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	struct request *rq;
 	struct list_head *plug_list;
 
-	plug = current->plug;
+	plug = blk_mq_plug(q, bio);
 	if (!plug)
 		return false;
 
@@ -1127,6 +1128,9 @@ EXPORT_SYMBOL_GPL(direct_make_request);
  */
 blk_qc_t submit_bio(struct bio *bio)
 {
+	if (blkcg_punt_bio_submit(bio))
+		return BLK_QC_T_NONE;
+
 	/*
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.

block/blk-mq.c

@@ -1973,7 +1973,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_mq_bio_to_request(rq, bio, nr_segs);
 
-	plug = current->plug;
+	plug = blk_mq_plug(q, bio);
 	if (unlikely(is_flush_fua)) {
 		/* bypass scheduler for flush rq */
 		blk_insert_flush(rq);

block/blk-mq.h

@@ -233,4 +233,36 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
 		qmap->mq_map[cpu] = 0;
 }
 
+/*
+ * blk_mq_plug() - Get caller context plug
+ * @q: request queue
+ * @bio : the bio being submitted by the caller context
+ *
+ * Plugging, by design, may delay the insertion of BIOs into the elevator in
+ * order to increase BIO merging opportunities. This however can cause BIO
+ * insertion order to change from the order in which submit_bio() is being
+ * executed in the case of multiple contexts concurrently issuing BIOs to a
+ * device, even if these context are synchronized to tightly control BIO issuing
+ * order. While this is not a problem with regular block devices, this ordering
+ * change can cause write BIO failures with zoned block devices as these
+ * require sequential write patterns to zones. Prevent this from happening by
+ * ignoring the plug state of a BIO issuing context if the target request queue
+ * is for a zoned block device and the BIO to plug is a write operation.
+ *
+ * Return current->plug if the bio can be plugged and NULL otherwise
+ */
+static inline struct blk_plug *blk_mq_plug(struct request_queue *q,
+					   struct bio *bio)
+{
+	/*
+	 * For regular block devices or read operations, use the context plug
+	 * which may be NULL if blk_start_plug() was not executed.
+	 */
+	if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio)))
+		return current->plug;
+
+	/* Zoned block device write operation case: do not plug the BIO */
+	return NULL;
+}
+
 #endif

block/blk-throttle.c

@@ -881,13 +881,10 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
 	u64 tmp;
 
-	jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
-
-	/* Slice has just started. Consider one slice interval */
-	if (!jiffy_elapsed)
-		jiffy_elapsed_rnd = tg->td->throtl_slice;
+	jiffy_elapsed = jiffies - tg->slice_start[rw];
 
-	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
+	/* Round up to the next throttle slice, wait time must be nonzero */
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice);
 
 	/*
 	 * jiffy_elapsed_rnd should not be a big value as minimum iops can be