Merge tag 'for-5.19/dm-changes' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Enable DM core bioset's per-cpu bio cache if QUEUE_FLAG_POLL set.
   This change improves DM's hipri bio polling (REQ_POLLED) performance
   by 7 - 20% depending on the system.

 - Update DM core to use jump_labels to further reduce cost of unlikely
   branches for zoned block devices, dm-stats and swap_bios throttling.

 - Various DM core changes to reduce bio-based DM overhead and simplify
   IO accounting.

 - Fundamental DM core improvements to dm_io reference counting and the
   elimination of using bio_split()+bio_chain() -- instead DM's
   bio-based IO accounting is updated to account that a split occurred.

 - Improve DM core's abnormal bio processing to do less work.

 - Improve DM core's hipri polling support to use a single list rather
   than an hlist.

 - Update DM core to pass NULL bdev to bio_alloc_clone() so that
   initialization that isn't useful for DM can be elided.

 - Add cond_resched to DM stats' various loops that loop over all
   entries.

 - Fix incorrect error code return from DM integrity's constructor.

 - Make DM crypt's printing of the key constant-time.

 - Update bio-based DM multipath to provide high-resolution timer to the
   Historical Service Time (HST) path selector.

* tag 'for-5.19/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (26 commits)
  dm: pass NULL bdev to bio_alloc_clone
  dm cache metadata: remove unnecessary variable in __dump_mapping
  dm mpath: provide high-resolution timer to HST for bio-based
  dm crypt: make printing of the key constant-time
  dm integrity: fix error code in dm_integrity_ctr()
  dm stats: add cond_resched when looping over entries
  dm: improve abnormal bio processing
  dm: simplify bio-based IO accounting further
  dm: put all polled dm_io instances into a single list
  dm: improve dm_io reference counting
  dm: don't grab target io reference in dm_zone_map_bio
  dm: improve bio splitting and associated IO accounting
  dm: switch to bdev based IO accounting interfaces
  dm: pass dm_io instance to dm_io_acct directly
  dm: don't pass bio to __dm_start_io_acct and dm_end_io_acct
  dm: use bio_sectors in dm_aceept_partial_bio
  dm: simplify basic targets
  dm: conditionally enable branching for less used features
  dm: introduce dm_{get,put}_live_table_bio called from dm_submit_bio
  dm: move hot dm_io members to same cacheline as dm_target_io
  ...

drivers/md/dm-cache-metadata.c

@@ -1509,15 +1509,14 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
 
 static int __dump_mapping(void *context, uint64_t cblock, void *leaf)
 {
-	int r = 0;
 	__le64 value;
 	dm_oblock_t oblock;
 	unsigned flags;
 
 	memcpy(&value, leaf, sizeof(value));
 	unpack_value(value, &oblock, &flags);
 
-	return r;
+	return 0;
 }
 
 static int __dump_mappings(struct dm_cache_metadata *cmd)

drivers/md/dm-core.h

@@ -13,6 +13,7 @@
 #include <linux/ktime.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-crypto-profile.h>
+#include <linux/jump_label.h>
 
 #include <trace/events/block.h>
 
@@ -154,6 +155,10 @@ static inline struct dm_stats *dm_get_stats(struct mapped_device *md)
 	return &md->stats;
 }
 
+DECLARE_STATIC_KEY_FALSE(stats_enabled);
+DECLARE_STATIC_KEY_FALSE(swap_bios_enabled);
+DECLARE_STATIC_KEY_FALSE(zoned_enabled);
+
 static inline bool dm_emulate_zone_append(struct mapped_device *md)
 {
 	if (blk_queue_is_zoned(md->queue))
@@ -237,6 +242,12 @@ static inline void dm_tio_set_flag(struct dm_target_io *tio, unsigned int bit)
 	tio->flags |= (1U << bit);
 }
 
+static inline bool dm_tio_is_normal(struct dm_target_io *tio)
+{
+	return (dm_tio_flagged(tio, DM_TIO_INSIDE_DM_IO) &&
+		!dm_tio_flagged(tio, DM_TIO_IS_DUPLICATE_BIO));
+}
+
 /*
  * One of these is allocated per original bio.
  * It contains the first clone used for that original.
@@ -245,16 +256,20 @@ static inline void dm_tio_set_flag(struct dm_target_io *tio, unsigned int bit)
 struct dm_io {
 	unsigned short magic;
 	blk_short_t flags;
-	atomic_t io_count;
-	struct mapped_device *md;
-	struct bio *orig_bio;
-	blk_status_t status;
 	spinlock_t lock;
 	unsigned long start_time;
 	void *data;
-	struct hlist_node node;
-	struct task_struct *map_task;
+	struct dm_io *next;
 	struct dm_stats_aux stats_aux;
+	blk_status_t status;
+	atomic_t io_count;
+	struct mapped_device *md;
+
+	/* The three fields represent mapped part of original bio */
+	struct bio *orig_bio;
+	unsigned int sector_offset; /* offset to end of orig_bio */
+	unsigned int sectors;
+
 	/* last member of dm_target_io is 'struct bio' */
 	struct dm_target_io tio;
 };
@@ -263,8 +278,8 @@ struct dm_io {
  * dm_io flags
  */
 enum {
-	DM_IO_START_ACCT,
-	DM_IO_ACCOUNTED
+	DM_IO_ACCOUNTED,
+	DM_IO_WAS_SPLIT
 };
 
 static inline bool dm_io_flagged(struct dm_io *io, unsigned int bit)
@@ -277,13 +292,6 @@ static inline void dm_io_set_flag(struct dm_io *io, unsigned int bit)
 	io->flags |= (1U << bit);
 }
 
-static inline void dm_io_inc_pending(struct dm_io *io)
-{
-	atomic_inc(&io->io_count);
-}
-
-void dm_io_dec_pending(struct dm_io *io, blk_status_t error);
-
 static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
 {
 	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;

drivers/md/dm-crypt.c

@@ -3439,6 +3439,11 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_SUBMITTED;
 }
 
+static char hex2asc(unsigned char c)
+{
+	return c + '0' + ((unsigned)(9 - c) >> 4 & 0x27);
+}
+
 static void crypt_status(struct dm_target *ti, status_type_t type,
 			 unsigned status_flags, char *result, unsigned maxlen)
 {
@@ -3457,9 +3462,12 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 		if (cc->key_size > 0) {
 			if (cc->key_string)
 				DMEMIT(":%u:%s", cc->key_size, cc->key_string);
-			else
-				for (i = 0; i < cc->key_size; i++)
-					DMEMIT("%02x", cc->key[i]);
+			else {
+				for (i = 0; i < cc->key_size; i++) {
+					DMEMIT("%c%c", hex2asc(cc->key[i] >> 4),
+					       hex2asc(cc->key[i] & 0xf));
+				}
+			}
 		} else
 			DMEMIT("-");
 

drivers/md/dm-delay.c

@@ -296,8 +296,7 @@ static int delay_map(struct dm_target *ti, struct bio *bio)
 	}
 	delayed->class = c;
 	bio_set_dev(bio, c->dev->bdev);
-	if (bio_sectors(bio))
-		bio->bi_iter.bi_sector = c->start + dm_target_offset(ti, bio->bi_iter.bi_sector);
+	bio->bi_iter.bi_sector = c->start + dm_target_offset(ti, bio->bi_iter.bi_sector);
 
 	return delay_bio(dc, c, bio);
 }

drivers/md/dm-flakey.c

@@ -280,9 +280,7 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 	struct flakey_c *fc = ti->private;
 
 	bio_set_dev(bio, fc->dev->bdev);
-	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
-		bio->bi_iter.bi_sector =
-			flakey_map_sector(ti, bio->bi_iter.bi_sector);
+	bio->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector);
 }
 
 static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)

drivers/md/dm-integrity.c

@@ -4494,8 +4494,6 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 
 	if (should_write_sb) {
-		int r;
-
 		init_journal(ic, 0, ic->journal_sections, 0);
 		r = dm_integrity_failed(ic);
 		if (unlikely(r)) {

drivers/md/dm-linear.c

@@ -84,19 +84,12 @@ static sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector)
 	return lc->start + dm_target_offset(ti, bi_sector);
 }
 
-static void linear_map_bio(struct dm_target *ti, struct bio *bio)
+static int linear_map(struct dm_target *ti, struct bio *bio)
 {
 	struct linear_c *lc = ti->private;
 
 	bio_set_dev(bio, lc->dev->bdev);
-	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio)))
-		bio->bi_iter.bi_sector =
-			linear_map_sector(ti, bio->bi_iter.bi_sector);
-}
-
-static int linear_map(struct dm_target *ti, struct bio *bio)
-{
-	linear_map_bio(ti, bio);
+	bio->bi_iter.bi_sector = linear_map_sector(ti, bio->bi_iter.bi_sector);
 
 	return DM_MAPIO_REMAPPED;
 }

drivers/md/dm-mpath.c

@@ -105,6 +105,7 @@ struct multipath {
 struct dm_mpath_io {
 	struct pgpath *pgpath;
 	size_t nr_bytes;
+	u64 start_time_ns;
 };
 
 typedef int (*action_fn) (struct pgpath *pgpath);
@@ -295,6 +296,7 @@ static void multipath_init_per_bio_data(struct bio *bio, struct dm_mpath_io **mp
 
 	mpio->nr_bytes = bio->bi_iter.bi_size;
 	mpio->pgpath = NULL;
+	mpio->start_time_ns = 0;
 	*mpio_p = mpio;
 
 	dm_bio_record(bio_details, bio);
@@ -647,6 +649,9 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio,
 
 	mpio->pgpath = pgpath;
 
+	if (dm_ps_use_hr_timer(pgpath->pg->ps.type))
+		mpio->start_time_ns = ktime_get_ns();
+
 	bio->bi_status = 0;
 	bio_set_dev(bio, pgpath->path.dev->bdev);
 	bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
@@ -1713,7 +1718,8 @@ static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone,
 
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes,
-					 dm_start_time_ns_from_clone(clone));
+					 (mpio->start_time_ns ?:
+					  dm_start_time_ns_from_clone(clone)));
 	}
 
 	return r;

drivers/md/dm-path-selector.h

@@ -26,11 +26,26 @@ struct path_selector {
 	void *context;
 };
 
+/*
+ * If a path selector uses this flag, a high resolution timer is used
+ * (via ktime_get_ns) to account for IO start time in BIO-based mpath.
+ * This improves performance of some path selectors (i.e. HST), in
+ * exchange for slightly higher overhead when submitting the BIO.
+ * The extra cost is usually offset by improved path selection for
+ * some benchmarks.
+ *
+ * This has no effect for request-based mpath, since it already uses a
+ * higher precision timer by default.
+ */
+#define DM_PS_USE_HR_TIMER		0x00000001
+#define dm_ps_use_hr_timer(type)	((type)->features & DM_PS_USE_HR_TIMER)
+
 /* Information about a path selector type */
 struct path_selector_type {
 	char *name;
 	struct module *module;
 
+	unsigned int features;
 	unsigned int table_args;
 	unsigned int info_args;
 

drivers/md/dm-ps-historical-service-time.c

@@ -523,6 +523,7 @@ static int hst_end_io(struct path_selector *ps, struct dm_path *path,
 static struct path_selector_type hst_ps = {
 	.name		= "historical-service-time",
 	.module		= THIS_MODULE,
+	.features	= DM_PS_USE_HR_TIMER,
 	.table_args	= 1,
 	.info_args	= 3,
 	.create		= hst_create,

drivers/md/dm-stats.c

@@ -225,6 +225,7 @@ void dm_stats_cleanup(struct dm_stats *stats)
 				       atomic_read(&shared->in_flight[READ]),
 				       atomic_read(&shared->in_flight[WRITE]));
 			}
+			cond_resched();
 		}
 		dm_stat_free(&s->rcu_head);
 	}
@@ -330,6 +331,7 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 	for (ni = 0; ni < n_entries; ni++) {
 		atomic_set(&s->stat_shared[ni].in_flight[READ], 0);
 		atomic_set(&s->stat_shared[ni].in_flight[WRITE], 0);
+		cond_resched();
 	}
 
 	if (s->n_histogram_entries) {
@@ -342,6 +344,7 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 		for (ni = 0; ni < n_entries; ni++) {
 			s->stat_shared[ni].tmp.histogram = hi;
 			hi += s->n_histogram_entries + 1;
+			cond_resched();
 		}
 	}
 
@@ -362,6 +365,7 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 			for (ni = 0; ni < n_entries; ni++) {
 				p[ni].histogram = hi;
 				hi += s->n_histogram_entries + 1;
+				cond_resched();
 			}
 		}
 	}
@@ -396,6 +400,9 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end,
 
 	dm_stats_recalc_precise_timestamps(stats);
 
+	if (!static_key_enabled(&stats_enabled.key))
+		static_branch_enable(&stats_enabled);
+
 	mutex_unlock(&stats->mutex);
 
 	resume_callback(md);
@@ -497,6 +504,7 @@ static int dm_stats_list(struct dm_stats *stats, const char *program,
 			}
 			DMEMIT("\n");
 		}
+		cond_resched();
 	}
 	mutex_unlock(&stats->mutex);
 
@@ -774,6 +782,7 @@ static void __dm_stat_clear(struct dm_stat *s, size_t idx_start, size_t idx_end,
 				local_irq_enable();
 			}
 		}
+		cond_resched();
 	}
 }
 
@@ -889,6 +898,8 @@ static int dm_stats_print(struct dm_stats *stats, int id,
 
 		if (unlikely(sz + 1 >= maxlen))
 			goto buffer_overflow;
+
+		cond_resched();
 	}
 
 	if (clear)

drivers/md/dm-table.c

@@ -719,6 +719,9 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 		DMWARN("%s: %s: ignoring discards_supported because num_discard_bios is zero.",
 		       dm_device_name(t->md), type);
 
+	if (tgt->limit_swap_bios && !static_key_enabled(&swap_bios_enabled.key))
+		static_branch_enable(&swap_bios_enabled);
+
 	return 0;
 
  bad:
@@ -1002,28 +1005,33 @@ bool dm_table_request_based(struct dm_table *t)
 	return __table_type_request_based(dm_table_get_type(t));
 }
 
+static int dm_table_supports_poll(struct dm_table *t);
+
 static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md)
 {
 	enum dm_queue_mode type = dm_table_get_type(t);
 	unsigned per_io_data_size = 0;
 	unsigned min_pool_size = 0;
 	struct dm_target *ti;
 	unsigned i;
+	bool poll_supported = false;
 
 	if (unlikely(type == DM_TYPE_NONE)) {
 		DMWARN("no table type is set, can't allocate mempools");
 		return -EINVAL;
 	}
 
-	if (__table_type_bio_based(type))
+	if (__table_type_bio_based(type)) {
 		for (i = 0; i < t->num_targets; i++) {
 			ti = t->targets + i;
 			per_io_data_size = max(per_io_data_size, ti->per_io_data_size);
 			min_pool_size = max(min_pool_size, ti->num_flush_bios);
 		}
+		poll_supported = !!dm_table_supports_poll(t);
+	}
 
-	t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported,
-					   per_io_data_size, min_pool_size);
+	t->mempools = dm_alloc_md_mempools(md, type, per_io_data_size, min_pool_size,
+					   t->integrity_supported, poll_supported);
 	if (!t->mempools)
 		return -ENOMEM;
 
@@ -2035,6 +2043,8 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 		r = dm_set_zones_restrictions(t, q);
 		if (r)
 			return r;
+		if (!static_key_enabled(&zoned_enabled.key))
+			static_branch_enable(&zoned_enabled);
 	}
 
 	dm_update_crypto_profile(q, t);

drivers/md/dm-zone.c

@@ -550,13 +550,6 @@ int dm_zone_map_bio(struct dm_target_io *tio)
 		return DM_MAPIO_KILL;
 	}
 
-	/*
-	 * The target map function may issue and complete the IO quickly.
-	 * Take an extra reference on the IO to make sure it does disappear
-	 * until we run dm_zone_map_bio_end().
-	 */
-	dm_io_inc_pending(io);
-
 	/* Let the target do its work */
 	r = ti->type->map(ti, clone);
 	switch (r) {
@@ -587,9 +580,6 @@ int dm_zone_map_bio(struct dm_target_io *tio)
 		break;
 	}
 
-	/* Drop the extra reference on the IO */
-	dm_io_dec_pending(io, sts);
-
 	if (sts != BLK_STS_OK)
 		return DM_MAPIO_KILL;