Merge tag 'for-5.18/dm-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - Fix memory corruption in DM integrity target when tag_size is less
   than digest size.

 - Fix DM multipath's historical-service-time path selector to not use
   sched_clock() and ktime_get_ns(); only use ktime_get_ns().

 - Fix dm_io->orig_bio NULL pointer dereference in dm_zone_map_bio() due
   to 5.18 changes that overlooked DM zone's use of ->orig_bio

 - Fix for regression that broke the use of dm_accept_partial_bio() for
   "abnormal" IO (e.g. WRITE ZEROES) that does not need duplicate bios

 - Fix DM's issuing of empty flush bio so that it's size is 0.

* tag 'for-5.18/dm-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: fix bio length of empty flush
  dm: allow dm_accept_partial_bio() for dm_io without duplicate bios
  dm zone: fix NULL pointer dereference in dm_zone_map_bio
  dm mpath: only use ktime_get_ns() in historical selector
  dm integrity: fix memory corruption when tag_size is less than digest size

4 files changed, 45 insertions, 40 deletions

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index ad2d5faa2ebb..36ae30b73a6e 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -4399,6 +4399,7 @@ try_smaller_buffer:
 	}
 
 	if (ic->internal_hash) {
+		size_t recalc_tags_size;
 		ic->recalc_wq = alloc_workqueue("dm-integrity-recalc", WQ_MEM_RECLAIM, 1);
 		if (!ic->recalc_wq ) {
 			ti->error = "Cannot allocate workqueue";
@@ -4412,8 +4413,10 @@ try_smaller_buffer:
 			r = -ENOMEM;
 			goto bad;
 		}
-		ic->recalc_tags = kvmalloc_array(RECALC_SECTORS >> ic->sb->log2_sectors_per_block,
-						 ic->tag_size, GFP_KERNEL);
+		recalc_tags_size = (RECALC_SECTORS >> ic->sb->log2_sectors_per_block) * ic->tag_size;
+		if (crypto_shash_digestsize(ic->internal_hash) > ic->tag_size)
+			recalc_tags_size += crypto_shash_digestsize(ic->internal_hash) - ic->tag_size;
+		ic->recalc_tags = kvmalloc(recalc_tags_size, GFP_KERNEL);
 		if (!ic->recalc_tags) {
 			ti->error = "Cannot allocate tags for recalculating";
 			r = -ENOMEM;
diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c
index 875bca30a0dd..82f2a06153dc 100644
--- a/drivers/md/dm-ps-historical-service-time.c
+++ b/drivers/md/dm-ps-historical-service-time.c
@@ -27,7 +27,6 @@
 #include <linux/blkdev.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/sched/clock.h>
 
 
 #define DM_MSG_PREFIX	"multipath historical-service-time"
@@ -433,7 +432,7 @@ static struct dm_path *hst_select_path(struct path_selector *ps,
 {
 	struct selector *s = ps->context;
 	struct path_info *pi = NULL, *best = NULL;
-	u64 time_now = sched_clock();
+	u64 time_now = ktime_get_ns();
 	struct dm_path *ret = NULL;
 	unsigned long flags;
 
@@ -474,7 +473,7 @@ static int hst_start_io(struct path_selector *ps, struct dm_path *path,
 
 static u64 path_service_time(struct path_info *pi, u64 start_time)
 {
-	u64 sched_now = ktime_get_ns();
+	u64 now = ktime_get_ns();
 
 	/* if a previous disk request has finished after this IO was
 	 * sent to the hardware, pretend the submission happened
@@ -483,11 +482,11 @@ static u64 path_service_time(struct path_info *pi, u64 start_time)
 	if (time_after64(pi->last_finish, start_time))
 		start_time = pi->last_finish;
 
-	pi->last_finish = sched_now;
-	if (time_before64(sched_now, start_time))
+	pi->last_finish = now;
+	if (time_before64(now, start_time))
 		return 0;
 
-	return sched_now - start_time;
+	return now - start_time;
 }
 
 static int hst_end_io(struct path_selector *ps, struct dm_path *path,
diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
index c1ca9be4b79e..57daa86c19cf 100644
--- a/drivers/md/dm-zone.c
+++ b/drivers/md/dm-zone.c
@@ -360,16 +360,20 @@ static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno,
 	return 0;
 }
 
+struct orig_bio_details {
+	unsigned int op;
+	unsigned int nr_sectors;
+};
+
 /*
  * First phase of BIO mapping for targets with zone append emulation:
  * check all BIO that change a zone writer pointer and change zone
  * append operations into regular write operations.
  */
 static bool dm_zone_map_bio_begin(struct mapped_device *md,
-				  struct bio *orig_bio, struct bio *clone)
+				  unsigned int zno, struct bio *clone)
 {
 	sector_t zsectors = blk_queue_zone_sectors(md->queue);
-	unsigned int zno = bio_zone_no(orig_bio);
 	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
 
 	/*
@@ -384,7 +388,7 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md,
 		WRITE_ONCE(md->zwp_offset[zno], zwp_offset);
 	}
 
-	switch (bio_op(orig_bio)) {
+	switch (bio_op(clone)) {
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_FINISH:
 		return true;
@@ -401,9 +405,8 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md,
 		 * target zone.
 		 */
 		clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE |
-			(orig_bio->bi_opf & (~REQ_OP_MASK));
-		clone->bi_iter.bi_sector =
-			orig_bio->bi_iter.bi_sector + zwp_offset;
+			(clone->bi_opf & (~REQ_OP_MASK));
+		clone->bi_iter.bi_sector += zwp_offset;
 		break;
 	default:
 		DMWARN_LIMIT("Invalid BIO operation");
@@ -423,11 +426,10 @@ static bool dm_zone_map_bio_begin(struct mapped_device *md,
  * data written to a zone. Note that at this point, the remapped clone BIO
  * may already have completed, so we do not touch it.
  */
-static blk_status_t dm_zone_map_bio_end(struct mapped_device *md,
-					struct bio *orig_bio,
+static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, unsigned int zno,
+					struct orig_bio_details *orig_bio_details,
 					unsigned int nr_sectors)
 {
-	unsigned int zno = bio_zone_no(orig_bio);
 	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);
 
 	/* The clone BIO may already have been completed and failed */
@@ -435,7 +437,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md,
 		return BLK_STS_IOERR;
 
 	/* Update the zone wp offset */
-	switch (bio_op(orig_bio)) {
+	switch (orig_bio_details->op) {
 	case REQ_OP_ZONE_RESET:
 		WRITE_ONCE(md->zwp_offset[zno], 0);
 		return BLK_STS_OK;
@@ -452,7 +454,7 @@ static blk_status_t dm_zone_map_bio_end(struct mapped_device *md,
 		 * Check that the target did not truncate the write operation
 		 * emulating a zone append.
 		 */
-		if (nr_sectors != bio_sectors(orig_bio)) {
+		if (nr_sectors != orig_bio_details->nr_sectors) {
 			DMWARN_LIMIT("Truncated write for zone append");
 			return BLK_STS_IOERR;
 		}
@@ -488,7 +490,7 @@ static inline void dm_zone_unlock(struct request_queue *q,
 	bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED);
 }
 
-static bool dm_need_zone_wp_tracking(struct bio *orig_bio)
+static bool dm_need_zone_wp_tracking(struct bio *bio)
 {
 	/*
 	 * Special processing is not needed for operations that do not need the
@@ -496,15 +498,15 @@ static bool dm_need_zone_wp_tracking(struct bio *orig_bio)
 	 * zones and all operations that do not modify directly a sequential
 	 * zone write pointer.
 	 */
-	if (op_is_flush(orig_bio->bi_opf) && !bio_sectors(orig_bio))
+	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
 		return false;
-	switch (bio_op(orig_bio)) {
+	switch (bio_op(bio)) {
 	case REQ_OP_WRITE_ZEROES:
 	case REQ_OP_WRITE:
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_FINISH:
 	case REQ_OP_ZONE_APPEND:
-		return bio_zone_is_seq(orig_bio);
+		return bio_zone_is_seq(bio);
 	default:
 		return false;
 	}
@@ -519,8 +521,8 @@ int dm_zone_map_bio(struct dm_target_io *tio)
 	struct dm_target *ti = tio->ti;
 	struct mapped_device *md = io->md;
 	struct request_queue *q = md->queue;
-	struct bio *orig_bio = io->orig_bio;
 	struct bio *clone = &tio->clone;
+	struct orig_bio_details orig_bio_details;
 	unsigned int zno;
 	blk_status_t sts;
 	int r;
@@ -529,18 +531,21 @@ int dm_zone_map_bio(struct dm_target_io *tio)
 	 * IOs that do not change a zone write pointer do not need
 	 * any additional special processing.
 	 */
-	if (!dm_need_zone_wp_tracking(orig_bio))
+	if (!dm_need_zone_wp_tracking(clone))
 		return ti->type->map(ti, clone);
 
 	/* Lock the target zone */
-	zno = bio_zone_no(orig_bio);
+	zno = bio_zone_no(clone);
 	dm_zone_lock(q, zno, clone);
 
+	orig_bio_details.nr_sectors = bio_sectors(clone);
+	orig_bio_details.op = bio_op(clone);
+
 	/*
 	 * Check that the bio and the target zone write pointer offset are
 	 * both valid, and if the bio is a zone append, remap it to a write.
 	 */
-	if (!dm_zone_map_bio_begin(md, orig_bio, clone)) {
+	if (!dm_zone_map_bio_begin(md, zno, clone)) {
 		dm_zone_unlock(q, zno, clone);
 		return DM_MAPIO_KILL;
 	}
@@ -560,7 +565,8 @@ int dm_zone_map_bio(struct dm_target_io *tio)
 		 * The target submitted the clone BIO. The target zone will
 		 * be unlocked on completion of the clone.
 		 */
-		sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr);
+		sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
+					  *tio->len_ptr);
 		break;
 	case DM_MAPIO_REMAPPED:
 		/*
@@ -568,7 +574,8 @@ int dm_zone_map_bio(struct dm_target_io *tio)
 		 * unlock the target zone here as the clone will not be
 		 * submitted.
 		 */
-		sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr);
+		sts = dm_zone_map_bio_end(md, zno, &orig_bio_details,
+					  *tio->len_ptr);
 		if (sts != BLK_STS_OK)
 			dm_zone_unlock(q, zno, clone);
 		break;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3c5fad7c4ee6..82957bd460e8 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1323,8 +1323,7 @@ static void __map_bio(struct bio *clone)
 }
 
 static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
-				struct dm_target *ti, unsigned num_bios,
-				unsigned *len)
+				struct dm_target *ti, unsigned num_bios)
 {
 	struct bio *bio;
 	int try;
@@ -1335,7 +1334,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 		if (try)
 			mutex_lock(&ci->io->md->table_devices_lock);
 		for (bio_nr = 0; bio_nr < num_bios; bio_nr++) {
-			bio = alloc_tio(ci, ti, bio_nr, len,
+			bio = alloc_tio(ci, ti, bio_nr, NULL,
 					try ? GFP_NOIO : GFP_NOWAIT);
 			if (!bio)
 				break;
@@ -1363,11 +1362,11 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
 		break;
 	case 1:
 		clone = alloc_tio(ci, ti, 0, len, GFP_NOIO);
-		dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
 		__map_bio(clone);
 		break;
 	default:
-		alloc_multiple_bios(&blist, ci, ti, num_bios, len);
+		/* dm_accept_partial_bio() is not supported with shared tio->len_ptr */
+		alloc_multiple_bios(&blist, ci, ti, num_bios);
 		while ((clone = bio_list_pop(&blist))) {
 			dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
 			__map_bio(clone);
@@ -1392,6 +1391,7 @@ static void __send_empty_flush(struct clone_info *ci)
 
 	ci->bio = &flush_bio;
 	ci->sector_count = 0;
+	ci->io->tio.clone.bi_iter.bi_size = 0;
 
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
 		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
@@ -1407,14 +1407,10 @@ static void __send_changing_extent_only(struct clone_info *ci, struct dm_target
 	len = min_t(sector_t, ci->sector_count,
 		    max_io_len_target_boundary(ti, dm_target_offset(ti, ci->sector)));
 
-	/*
-	 * dm_accept_partial_bio cannot be used with duplicate bios,
-	 * so update clone_info cursor before __send_duplicate_bios().
-	 */
+	__send_duplicate_bios(ci, ti, num_bios, &len);
+
 	ci->sector += len;
 	ci->sector_count -= len;
-
-	__send_duplicate_bios(ci, ti, num_bios, &len);
 }
 
 static bool is_abnormal_io(struct bio *bio)