Merge tag 'for-6.14/dm-changes' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mikulas Patocka:

 - fix a spelling error in dm-raid

 - change kzalloc to kcalloc

 - remove useless test in alloc_multiple_bios

 - disable REQ_NOWAIT for flushes

 - dm-transaction-manager: use red-black trees instead of linear lists

 - atomic writes support for dm-linear, dm-stripe and dm-mirror

 - dm-crypt: code cleanups and two bugfixes

* tag 'for-6.14/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm-crypt: track tag_offset in convert_context
  dm-crypt: don't initialize cc_sector again
  dm-crypt: don't update io->sector after kcryptd_crypt_write_io_submit()
  dm-crypt: use bi_sector in bio when initialize integrity seed
  dm-crypt: fully initialize clone->bi_iter in crypt_alloc_buffer()
  dm-crypt: set atomic as false when calling crypt_convert() in kworker
  dm-mirror: Support atomic writes
  dm-io: Warn on creating multiple atomic write bios for a region
  dm-stripe: Enable atomic writes
  dm-linear: Enable atomic writes
  dm: Ensure cloned bio is same length for atomic write
  dm-table: atomic writes support
  dm-transaction-manager: use red-black trees instead of linear lists
  dm: disable REQ_NOWAIT for flushes
  dm: remove useless test in alloc_multiple_bios
  dm: change kzalloc to kcalloc
  dm raid: fix spelling errors in raid_ctr()

drivers/md/dm-crypt.c

@@ -59,6 +59,7 @@ struct convert_context {
 	struct bio *bio_out;
 	struct bvec_iter iter_out;
 	atomic_t cc_pending;
+	unsigned int tag_offset;
 	u64 cc_sector;
 	union {
 		struct skcipher_request *req;
@@ -1187,7 +1188,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio)
 
 	tag_len = io->cc->tuple_size * (bio_sectors(bio) >> io->cc->sector_shift);
 
-	bip->bip_iter.bi_sector = io->cc->start + io->sector;
+	bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
 
 	ret = bio_integrity_add_page(bio, virt_to_page(io->integrity_metadata),
 				     tag_len, offset_in_page(io->integrity_metadata));
@@ -1256,6 +1257,7 @@ static void crypt_convert_init(struct crypt_config *cc,
 	if (bio_out)
 		ctx->iter_out = bio_out->bi_iter;
 	ctx->cc_sector = sector + cc->iv_offset;
+	ctx->tag_offset = 0;
 	init_completion(&ctx->restart);
 }
 
@@ -1588,7 +1590,6 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
 static blk_status_t crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx, bool atomic, bool reset_pending)
 {
-	unsigned int tag_offset = 0;
 	unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
 	int r;
 
@@ -1611,9 +1612,9 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		atomic_inc(&ctx->cc_pending);
 
 		if (crypt_integrity_aead(cc))
-			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, tag_offset);
+			r = crypt_convert_block_aead(cc, ctx, ctx->r.req_aead, ctx->tag_offset);
 		else
-			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, tag_offset);
+			r = crypt_convert_block_skcipher(cc, ctx, ctx->r.req, ctx->tag_offset);
 
 		switch (r) {
 		/*
@@ -1633,8 +1634,8 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 					 * exit and continue processing in a workqueue
 					 */
 					ctx->r.req = NULL;
+					ctx->tag_offset++;
 					ctx->cc_sector += sector_step;
-					tag_offset++;
 					return BLK_STS_DEV_RESOURCE;
 				}
 			} else {
@@ -1648,16 +1649,16 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		 */
 		case -EINPROGRESS:
 			ctx->r.req = NULL;
+			ctx->tag_offset++;
 			ctx->cc_sector += sector_step;
-			tag_offset++;
 			continue;
 		/*
 		 * The request was already processed (synchronously).
 		 */
 		case 0:
 			atomic_dec(&ctx->cc_pending);
 			ctx->cc_sector += sector_step;
-			tag_offset++;
+			ctx->tag_offset++;
 			if (!atomic)
 				cond_resched();
 			continue;
@@ -1719,6 +1720,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 	clone->bi_private = io;
 	clone->bi_end_io = crypt_endio;
 	clone->bi_ioprio = io->base_bio->bi_ioprio;
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 
 	remaining_size = size;
 
@@ -1909,7 +1911,6 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 			crypt_dec_pending(io);
 			return 1;
 		}
-		clone->bi_iter.bi_sector = cc->start + io->sector;
 		crypt_convert_init(cc, &io->ctx, clone, clone, io->sector);
 		io->saved_bi_iter = clone->bi_iter;
 		dm_submit_bio_remap(io->base_bio, clone);
@@ -1925,13 +1926,13 @@ static int kcryptd_io_read(struct dm_crypt_io *io, gfp_t gfp)
 	clone = bio_alloc_clone(cc->dev->bdev, io->base_bio, gfp, &cc->bs);
 	if (!clone)
 		return 1;
+
+	clone->bi_iter.bi_sector = cc->start + io->sector;
 	clone->bi_private = io;
 	clone->bi_end_io = crypt_endio;
 
 	crypt_inc_pending(io);
 
-	clone->bi_iter.bi_sector = cc->start + io->sector;
-
 	if (dm_crypt_integrity_io_alloc(io, clone)) {
 		crypt_dec_pending(io);
 		bio_put(clone);
@@ -2039,8 +2040,6 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 	/* crypt_convert should have filled the clone bio */
 	BUG_ON(io->ctx.iter_out.bi_size);
 
-	clone->bi_iter.bi_sector = cc->start + io->sector;
-
 	if ((likely(!async) && test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags)) ||
 	    test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)) {
 		dm_submit_bio_remap(io->base_bio, clone);
@@ -2092,13 +2091,12 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	struct crypt_config *cc = io->cc;
 	struct convert_context *ctx = &io->ctx;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	wait_for_completion(&ctx->restart);
 	reinit_completion(&ctx->restart);
 
-	r = crypt_convert(cc, &io->ctx, true, false);
+	r = crypt_convert(cc, &io->ctx, false, false);
 	if (r)
 		io->error = r;
 	crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
@@ -2109,10 +2107,8 @@ static void kcryptd_crypt_write_continue(struct work_struct *work)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 	crypt_dec_pending(io);
 }
@@ -2123,14 +2119,13 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	struct convert_context *ctx = &io->ctx;
 	struct bio *clone;
 	int crypt_finished;
-	sector_t sector = io->sector;
 	blk_status_t r;
 
 	/*
 	 * Prevent io from disappearing until this function completes.
 	 */
 	crypt_inc_pending(io);
-	crypt_convert_init(cc, ctx, NULL, io->base_bio, sector);
+	crypt_convert_init(cc, ctx, NULL, io->base_bio, io->sector);
 
 	clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
 	if (unlikely(!clone)) {
@@ -2147,8 +2142,6 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 		io->ctx.iter_in = clone->bi_iter;
 	}
 
-	sector += bio_sectors(clone);
-
 	crypt_inc_pending(io);
 	r = crypt_convert(cc, ctx,
 			  test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
@@ -2172,10 +2165,8 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	}
 
 	/* Encryption was already finished, submit io now */
-	if (crypt_finished) {
+	if (crypt_finished)
 		kcryptd_crypt_write_io_submit(io, 0);
-		io->sector = sector;
-	}
 
 dec:
 	crypt_dec_pending(io);
@@ -2203,7 +2194,7 @@ static void kcryptd_crypt_read_continue(struct work_struct *work)
 	wait_for_completion(&io->ctx.restart);
 	reinit_completion(&io->ctx.restart);
 
-	r = crypt_convert(cc, &io->ctx, true, false);
+	r = crypt_convert(cc, &io->ctx, false, false);
 	if (r)
 		io->error = r;
 
@@ -2221,7 +2212,6 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 	crypt_inc_pending(io);
 
 	if (io->ctx.aead_recheck) {
-		io->ctx.cc_sector = io->sector + cc->iv_offset;
 		r = crypt_convert(cc, &io->ctx,
 				  test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
 	} else {

drivers/md/dm-io.c

@@ -379,6 +379,7 @@ static void do_region(const blk_opf_t opf, unsigned int region,
 
 		atomic_inc(&io->count);
 		submit_bio(bio);
+		WARN_ON_ONCE(opf & REQ_ATOMIC && remaining);
 	} while (remaining);
 }
 

drivers/md/dm-linear.c

@@ -199,9 +199,10 @@ static size_t linear_dax_recovery_write(struct dm_target *ti, pgoff_t pgoff,
 
 static struct target_type linear_target = {
 	.name   = "linear",
-	.version = {1, 4, 0},
+	.version = {1, 5, 0},
 	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
-		    DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO,
+		    DM_TARGET_ZONED_HM | DM_TARGET_PASSES_CRYPTO |
+		    DM_TARGET_ATOMIC_WRITES,
 	.report_zones = linear_report_zones,
 	.module = THIS_MODULE,
 	.ctr    = linear_ctr,

drivers/md/dm-ps-io-affinity.c

@@ -116,7 +116,7 @@ static int ioa_create(struct path_selector *ps, unsigned int argc, char **argv)
 	if (!s)
 		return -ENOMEM;
 
-	s->path_map = kzalloc(nr_cpu_ids * sizeof(struct path_info *),
+	s->path_map = kcalloc(nr_cpu_ids, sizeof(struct path_info *),
 			      GFP_KERNEL);
 	if (!s->path_map)
 		goto free_selector;

drivers/md/dm-raid.c

@@ -3196,7 +3196,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		if (reshape_sectors || rs_is_raid1(rs)) {
 			/*
 			 * We can only prepare for a reshape here, because the
-			 * raid set needs to run to provide the repective reshape
+			 * raid set needs to run to provide the respective reshape
 			 * check functions via its MD personality instance.
 			 *
 			 * So do the reshape check after md_run() succeeded.

drivers/md/dm-raid1.c

@@ -656,7 +656,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	unsigned int i;
 	struct dm_io_region io[MAX_NR_MIRRORS], *dest = io;
 	struct mirror *m;
-	blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH);
+	blk_opf_t op_flags = bio->bi_opf & (REQ_FUA | REQ_PREFLUSH | REQ_ATOMIC);
 	struct dm_io_request io_req = {
 		.bi_opf = REQ_OP_WRITE | op_flags,
 		.mem.type = DM_IO_BIO,
@@ -1483,8 +1483,9 @@ static int mirror_iterate_devices(struct dm_target *ti,
 
 static struct target_type mirror_target = {
 	.name	 = "mirror",
-	.version = {1, 14, 0},
+	.version = {1, 15, 0},
 	.module	 = THIS_MODULE,
+	.features = DM_TARGET_ATOMIC_WRITES,
 	.ctr	 = mirror_ctr,
 	.dtr	 = mirror_dtr,
 	.map	 = mirror_map,

drivers/md/dm-stripe.c

@@ -465,8 +465,9 @@ static void stripe_io_hints(struct dm_target *ti,
 
 static struct target_type stripe_target = {
 	.name   = "striped",
-	.version = {1, 6, 0},
-	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT,
+	.version = {1, 7, 0},
+	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_NOWAIT |
+		    DM_TARGET_ATOMIC_WRITES,
 	.module = THIS_MODULE,
 	.ctr    = stripe_ctr,
 	.dtr    = stripe_dtr,

drivers/md/dm-table.c

@@ -1806,6 +1806,32 @@ static bool dm_table_supports_secure_erase(struct dm_table *t)
 	return true;
 }
 
+static int device_not_atomic_write_capable(struct dm_target *ti,
+			struct dm_dev *dev, sector_t start,
+			sector_t len, void *data)
+{
+	return !bdev_can_atomic_write(dev->bdev);
+}
+
+static bool dm_table_supports_atomic_writes(struct dm_table *t)
+{
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (!dm_target_supports_atomic_writes(ti->type))
+			return false;
+
+		if (!ti->type->iterate_devices)
+			return false;
+
+		if (ti->type->iterate_devices(ti,
+			device_not_atomic_write_capable, NULL)) {
+			return false;
+		}
+	}
+	return true;
+}
+
 int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			      struct queue_limits *limits)
 {
@@ -1854,6 +1880,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			return r;
 	}
 
+	if (dm_table_supports_atomic_writes(t))
+		limits->features |= BLK_FEAT_ATOMIC_WRITES;
+
 	r = queue_limits_set(q, limits);
 	if (r)
 		return r;