1 files changed, 150 insertions, 97 deletions

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 59445763e55a..02a2919f4e5a 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -28,7 +28,7 @@
 #include <linux/rbtree.h>
 #include <linux/ctype.h>
 #include <asm/page.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <crypto/hash.h>
 #include <crypto/md5.h>
 #include <crypto/skcipher.h>
@@ -47,6 +47,8 @@
 
 #define DM_MSG_PREFIX "crypt"
 
+static DEFINE_IDA(workqueue_ida);
+
 /*
  * context holding the current state of a multi-part conversion
  */
@@ -57,6 +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;
@@ -137,14 +140,15 @@ struct iv_elephant_private {
  * and encrypts / decrypts at the same time.
  */
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
-	     DM_CRYPT_SAME_CPU, DM_CRYPT_NO_OFFLOAD,
-	     DM_CRYPT_NO_READ_WORKQUEUE, DM_CRYPT_NO_WRITE_WORKQUEUE,
-	     DM_CRYPT_WRITE_INLINE };
+	     DM_CRYPT_SAME_CPU, DM_CRYPT_HIGH_PRIORITY,
+	     DM_CRYPT_NO_OFFLOAD, DM_CRYPT_NO_READ_WORKQUEUE,
+	     DM_CRYPT_NO_WRITE_WORKQUEUE, DM_CRYPT_WRITE_INLINE };
 
 enum cipher_flags {
 	CRYPT_MODE_INTEGRITY_AEAD,	/* Use authenticated mode for cipher */
 	CRYPT_IV_LARGE_SECTORS,		/* Calculate IV from sector_size, not 512B sectors */
 	CRYPT_ENCRYPT_PREPROCESS,	/* Must preprocess data for encryption (elephant) */
+	CRYPT_KEY_MAC_SIZE_SET,		/* The integrity_key_size option was used */
 };
 
 /*
@@ -184,6 +188,7 @@ struct crypt_config {
 		struct crypto_aead **tfms_aead;
 	} cipher_tfm;
 	unsigned int tfms_count;
+	int workqueue_id;
 	unsigned long cipher_flags;
 
 	/*
@@ -211,7 +216,8 @@ struct crypt_config {
 
 	unsigned int integrity_tag_size;
 	unsigned int integrity_iv_size;
-	unsigned int on_disk_tag_size;
+	unsigned int used_tag_size;
+	unsigned int tuple_size;
 
 	/*
 	 * pool for per bio private data, crypto requests,
@@ -238,6 +244,31 @@ static unsigned int dm_crypt_clients_n;
 static volatile unsigned long dm_crypt_pages_per_client;
 #define DM_CRYPT_MEMORY_PERCENT			2
 #define DM_CRYPT_MIN_PAGES_PER_CLIENT		(BIO_MAX_VECS * 16)
+#define DM_CRYPT_DEFAULT_MAX_READ_SIZE		131072
+#define DM_CRYPT_DEFAULT_MAX_WRITE_SIZE		131072
+
+static unsigned int max_read_size = 0;
+module_param(max_read_size, uint, 0644);
+MODULE_PARM_DESC(max_read_size, "Maximum size of a read request");
+static unsigned int max_write_size = 0;
+module_param(max_write_size, uint, 0644);
+MODULE_PARM_DESC(max_write_size, "Maximum size of a write request");
+static unsigned get_max_request_size(struct crypt_config *cc, bool wrt)
+{
+	unsigned val, sector_align;
+	val = !wrt ? READ_ONCE(max_read_size) : READ_ONCE(max_write_size);
+	if (likely(!val))
+		val = !wrt ? DM_CRYPT_DEFAULT_MAX_READ_SIZE : DM_CRYPT_DEFAULT_MAX_WRITE_SIZE;
+	if (wrt || cc->used_tag_size) {
+		if (unlikely(val > BIO_MAX_VECS << PAGE_SHIFT))
+			val = BIO_MAX_VECS << PAGE_SHIFT;
+	}
+	sector_align = max(bdev_logical_block_size(cc->dev->bdev), (unsigned)cc->sector_size);
+	val = round_down(val, sector_align);
+	if (unlikely(!val))
+		val = sector_align;
+	return val >> SECTOR_SHIFT;
+}
 
 static void crypt_endio(struct bio *clone);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
@@ -1148,16 +1179,16 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio)
 	unsigned int tag_len;
 	int ret;
 
-	if (!bio_sectors(bio) || !io->cc->on_disk_tag_size)
+	if (!bio_sectors(bio) || !io->cc->tuple_size)
 		return 0;
 
 	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
 	if (IS_ERR(bip))
 		return PTR_ERR(bip);
 
-	tag_len = io->cc->on_disk_tag_size * (bio_sectors(bio) >> io->cc->sector_shift);
+	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));
@@ -1173,24 +1204,24 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 	struct blk_integrity *bi = blk_get_integrity(cc->dev->bdev->bd_disk);
 	struct mapped_device *md = dm_table_get_md(ti->table);
 
-	/* From now we require underlying device with our integrity profile */
-	if (!bi || strcasecmp(bi->profile->name, "DM-DIF-EXT-TAG")) {
+	/* We require an underlying device with non-PI metadata */
+	if (!bi || bi->csum_type != BLK_INTEGRITY_CSUM_NONE) {
 		ti->error = "Integrity profile not supported.";
 		return -EINVAL;
 	}
 
-	if (bi->tag_size != cc->on_disk_tag_size ||
-	    bi->tuple_size != cc->on_disk_tag_size) {
+	if (bi->tuple_size < cc->used_tag_size) {
 		ti->error = "Integrity profile tag size mismatch.";
 		return -EINVAL;
 	}
+	cc->tuple_size = bi->tuple_size;
 	if (1 << bi->interval_exp != cc->sector_size) {
 		ti->error = "Integrity profile sector size mismatch.";
 		return -EINVAL;
 	}
 
 	if (crypt_integrity_aead(cc)) {
-		cc->integrity_tag_size = cc->on_disk_tag_size - cc->integrity_iv_size;
+		cc->integrity_tag_size = cc->used_tag_size - cc->integrity_iv_size;
 		DMDEBUG("%s: Integrity AEAD, tag size %u, IV size %u.", dm_device_name(md),
 		       cc->integrity_tag_size, cc->integrity_iv_size);
 
@@ -1202,7 +1233,7 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 		DMDEBUG("%s: Additional per-sector space %u bytes for IV.", dm_device_name(md),
 		       cc->integrity_iv_size);
 
-	if ((cc->integrity_tag_size + cc->integrity_iv_size) != bi->tag_size) {
+	if ((cc->integrity_tag_size + cc->integrity_iv_size) > cc->tuple_size) {
 		ti->error = "Not enough space for integrity tag in the profile.";
 		return -EINVAL;
 	}
@@ -1226,6 +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);
 }
 
@@ -1281,7 +1313,7 @@ static void *tag_from_dmreq(struct crypt_config *cc,
 	struct dm_crypt_io *io = container_of(ctx, struct dm_crypt_io, ctx);
 
 	return &io->integrity_metadata[*org_tag_of_dmreq(cc, dmreq) *
-		cc->on_disk_tag_size];
+		cc->tuple_size];
 }
 
 static void *iv_tag_from_dmreq(struct crypt_config *cc,
@@ -1362,9 +1394,9 @@ static int crypt_convert_block_aead(struct crypt_config *cc,
 		aead_request_set_crypt(req, dmreq->sg_in, dmreq->sg_out,
 				       cc->sector_size, iv);
 		r = crypto_aead_encrypt(req);
-		if (cc->integrity_tag_size + cc->integrity_iv_size != cc->on_disk_tag_size)
+		if (cc->integrity_tag_size + cc->integrity_iv_size != cc->tuple_size)
 			memset(tag + cc->integrity_tag_size + cc->integrity_iv_size, 0,
-			       cc->on_disk_tag_size - (cc->integrity_tag_size + cc->integrity_iv_size));
+			       cc->tuple_size - (cc->integrity_tag_size + cc->integrity_iv_size));
 	} else {
 		aead_request_set_crypt(req, dmreq->sg_in, dmreq->sg_out,
 				       cc->sector_size + cc->integrity_tag_size, iv);
@@ -1558,7 +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;
 
@@ -1581,9 +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) {
 		/*
@@ -1603,8 +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 {
@@ -1618,8 +1649,8 @@ 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).
@@ -1627,7 +1658,7 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
 		case 0:
 			atomic_dec(&ctx->cc_pending);
 			ctx->cc_sector += sector_step;
-			tag_offset++;
+			ctx->tag_offset++;
 			if (!atomic)
 				cond_resched();
 			continue;
@@ -1653,8 +1684,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
 
 /*
  * Generate a new unfragmented bio with the given size
- * This should never violate the device limitations (but only because
- * max_segment_size is being constrained to PAGE_SIZE).
+ * This should never violate the device limitations (but if it did then block
+ * core should split the bio as needed).
  *
  * This function may be called concurrently. If we allocate from the mempool
  * concurrently, there is a possibility of deadlock. For example, if we have
@@ -1688,6 +1719,8 @@ retry:
 				 GFP_NOIO, &cc->bs);
 	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;
 
@@ -1793,7 +1826,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 		return;
 
 	if (likely(!io->ctx.aead_recheck) && unlikely(io->ctx.aead_failed) &&
-	    cc->on_disk_tag_size && bio_data_dir(base_bio) == READ) {
+	    cc->used_tag_size && bio_data_dir(base_bio) == READ) {
 		io->ctx.aead_recheck = true;
 		io->ctx.aead_failed = false;
 		io->error = 0;
@@ -1878,7 +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);
@@ -1894,13 +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);
@@ -1964,7 +1996,6 @@ continue_locked:
 
 		schedule();
 
-		set_current_state(TASK_RUNNING);
 		spin_lock_irq(&cc->write_thread_lock);
 		goto continue_locked;
 
@@ -2009,8 +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);
@@ -2062,13 +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);
@@ -2079,10 +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);
 }
@@ -2093,14 +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)) {
@@ -2117,8 +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);
@@ -2142,10 +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);
@@ -2173,7 +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;
 
@@ -2191,7 +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 {
@@ -2296,7 +2316,11 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
 		 * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
 		 * it is being executed with irqs disabled.
 		 */
-		if (!(in_hardirq() || irqs_disabled())) {
+		if (in_hardirq() || irqs_disabled()) {
+			INIT_WORK(&io->work, kcryptd_crypt);
+			queue_work(system_bh_wq, &io->work);
+			return;
+		} else {
 			kcryptd_crypt(&io->work);
 			return;
 		}
@@ -2580,35 +2604,31 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	key = request_key(type, key_desc + 1, NULL);
 	if (IS_ERR(key)) {
-		kfree_sensitive(new_key_string);
-		return PTR_ERR(key);
+		ret = PTR_ERR(key);
+		goto free_new_key_string;
 	}
 
 	down_read(&key->sem);
-
 	ret = set_key(cc, key);
-	if (ret < 0) {
-		up_read(&key->sem);
-		key_put(key);
-		kfree_sensitive(new_key_string);
-		return ret;
-	}
-
 	up_read(&key->sem);
 	key_put(key);
+	if (ret < 0)
+		goto free_new_key_string;
 
 	/* clear the flag since following operations may invalidate previously valid key */
 	clear_bit(DM_CRYPT_KEY_VALID, &cc->flags);
 
 	ret = crypt_setkey(cc);
+	if (ret)
+		goto free_new_key_string;
 
-	if (!ret) {
-		set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
-		kfree_sensitive(cc->key_string);
-		cc->key_string = new_key_string;
-	} else
-		kfree_sensitive(new_key_string);
+	set_bit(DM_CRYPT_KEY_VALID, &cc->flags);
+	kfree_sensitive(cc->key_string);
+	cc->key_string = new_key_string;
+	return 0;
 
+free_new_key_string:
+	kfree_sensitive(new_key_string);
 	return ret;
 }
 
@@ -2767,6 +2787,9 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->crypt_queue)
 		destroy_workqueue(cc->crypt_queue);
 
+	if (cc->workqueue_id)
+		ida_free(&workqueue_ida, cc->workqueue_id);
+
 	crypt_free_tfms(cc);
 
 	bioset_exit(&cc->bs);
@@ -2901,7 +2924,8 @@ static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api)
 	if (IS_ERR(mac))
 		return PTR_ERR(mac);
 
-	cc->key_mac_size = crypto_ahash_digestsize(mac);
+	if (!test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags))
+		cc->key_mac_size = crypto_ahash_digestsize(mac);
 	crypto_free_ahash(mac);
 
 	cc->authenc_key = kmalloc(crypt_authenckey_size(cc), GFP_KERNEL);
@@ -3130,7 +3154,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 	struct crypt_config *cc = ti->private;
 	struct dm_arg_set as;
 	static const struct dm_arg _args[] = {
-		{0, 8, "Invalid number of feature args"},
+		{0, 9, "Invalid number of feature args"},
 	};
 	unsigned int opt_params, val;
 	const char *opt_string, *sval;
@@ -3157,6 +3181,8 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 
 		else if (!strcasecmp(opt_string, "same_cpu_crypt"))
 			set_bit(DM_CRYPT_SAME_CPU, &cc->flags);
+		else if (!strcasecmp(opt_string, "high_priority"))
+			set_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags);
 
 		else if (!strcasecmp(opt_string, "submit_from_crypt_cpus"))
 			set_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
@@ -3169,7 +3195,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 				ti->error = "Invalid integrity arguments";
 				return -EINVAL;
 			}
-			cc->on_disk_tag_size = val;
+			cc->used_tag_size = val;
 			sval = strchr(opt_string + strlen("integrity:"), ':') + 1;
 			if (!strcasecmp(sval, "aead")) {
 				set_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags);
@@ -3181,6 +3207,13 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar
 			cc->cipher_auth = kstrdup(sval, GFP_KERNEL);
 			if (!cc->cipher_auth)
 				return -ENOMEM;
+		} else if (sscanf(opt_string, "integrity_key_size:%u%c", &val, &dummy) == 1) {
+			if (!val) {
+				ti->error = "Invalid integrity_key_size argument";
+				return -EINVAL;
+			}
+			cc->key_mac_size = val;
+			set_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags);
 		} else if (sscanf(opt_string, "sector_size:%hu%c", &cc->sector_size, &dummy) == 1) {
 			if (cc->sector_size < (1 << SECTOR_SHIFT) ||
 			    cc->sector_size > 4096 ||
@@ -3226,8 +3259,9 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct crypt_config *cc;
 	const char *devname = dm_table_device_name(ti->table);
-	int key_size;
+	int key_size, wq_id;
 	unsigned int align_mask;
+	unsigned int common_wq_flags;
 	unsigned long long tmpll;
 	int ret;
 	size_t iv_size_padding, additional_req_size;
@@ -3380,12 +3414,12 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		if (ret)
 			goto bad;
 
-		cc->tag_pool_max_sectors = POOL_ENTRY_SIZE / cc->on_disk_tag_size;
+		cc->tag_pool_max_sectors = POOL_ENTRY_SIZE / cc->tuple_size;
 		if (!cc->tag_pool_max_sectors)
 			cc->tag_pool_max_sectors = 1;
 
 		ret = mempool_init_kmalloc_pool(&cc->tag_pool, MIN_IOS,
-			cc->tag_pool_max_sectors * cc->on_disk_tag_size);
+			cc->tag_pool_max_sectors * cc->tuple_size);
 		if (ret) {
 			ti->error = "Cannot allocate integrity tags mempool";
 			goto bad;
@@ -3394,20 +3428,38 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		cc->tag_pool_max_sectors <<= cc->sector_shift;
 	}
 
+	wq_id = ida_alloc_min(&workqueue_ida, 1, GFP_KERNEL);
+	if (wq_id < 0) {
+		ti->error = "Couldn't get workqueue id";
+		ret = wq_id;
+		goto bad;
+	}
+	cc->workqueue_id = wq_id;
+
 	ret = -ENOMEM;
-	cc->io_queue = alloc_workqueue("kcryptd_io/%s", WQ_MEM_RECLAIM, 1, devname);
+	common_wq_flags = WQ_MEM_RECLAIM | WQ_SYSFS;
+	if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags))
+		common_wq_flags |= WQ_HIGHPRI;
+
+	cc->io_queue = alloc_workqueue("kcryptd_io-%s-%d", common_wq_flags, 1, devname, wq_id);
 	if (!cc->io_queue) {
 		ti->error = "Couldn't create kcryptd io queue";
 		goto bad;
 	}
 
-	if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
-		cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM,
-						  1, devname);
-	else
-		cc->crypt_queue = alloc_workqueue("kcryptd/%s",
-						  WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND,
-						  num_online_cpus(), devname);
+	if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) {
+		cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d",
+						  common_wq_flags | WQ_CPU_INTENSIVE,
+						  1, devname, wq_id);
+	} else {
+		/*
+		 * While crypt_queue is certainly CPU intensive, the use of
+		 * WQ_CPU_INTENSIVE is meaningless with WQ_UNBOUND.
+		 */
+		cc->crypt_queue = alloc_workqueue("kcryptd-%s-%d",
+						  common_wq_flags | WQ_UNBOUND,
+						  num_online_cpus(), devname, wq_id);
+	}
 	if (!cc->crypt_queue) {
 		ti->error = "Couldn't create kcryptd queue";
 		goto bad;
@@ -3423,6 +3475,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ti->error = "Couldn't spawn write thread";
 		goto bad;
 	}
+	if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags))
+		set_user_nice(cc->write_thread, MIN_NICE);
 
 	ti->num_flush_bios = 1;
 	ti->limit_swap_bios = true;
@@ -3441,6 +3495,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 {
 	struct dm_crypt_io *io;
 	struct crypt_config *cc = ti->private;
+	unsigned max_sectors;
 
 	/*
 	 * If bio is REQ_PREFLUSH or REQ_OP_DISCARD, just bypass crypt queues.
@@ -3459,9 +3514,9 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	/*
 	 * Check if bio is too large, split as needed.
 	 */
-	if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_VECS << PAGE_SHIFT)) &&
-	    (bio_data_dir(bio) == WRITE || cc->on_disk_tag_size))
-		dm_accept_partial_bio(bio, ((BIO_MAX_VECS << PAGE_SHIFT) >> SECTOR_SHIFT));
+	max_sectors = get_max_request_size(cc, bio_data_dir(bio) == WRITE);
+	if (unlikely(bio_sectors(bio) > max_sectors))
+		dm_accept_partial_bio(bio, max_sectors);
 
 	/*
 	 * Ensure that bio is a multiple of internal sector encryption size
@@ -3476,8 +3531,8 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	io = dm_per_bio_data(bio, cc->per_bio_data_size);
 	crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
 
-	if (cc->on_disk_tag_size) {
-		unsigned int tag_len = cc->on_disk_tag_size * (bio_sectors(bio) >> cc->sector_shift);
+	if (cc->tuple_size) {
+		unsigned int tag_len = cc->tuple_size * (bio_sectors(bio) >> cc->sector_shift);
 
 		if (unlikely(tag_len > KMALLOC_MAX_SIZE))
 			io->integrity_metadata = NULL;
@@ -3543,31 +3598,36 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 
 		num_feature_args += !!ti->num_discard_bios;
 		num_feature_args += test_bit(DM_CRYPT_SAME_CPU, &cc->flags);
+		num_feature_args += test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags);
 		num_feature_args += test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags);
+		num_feature_args += !!cc->used_tag_size;
 		num_feature_args += cc->sector_size != (1 << SECTOR_SHIFT);
 		num_feature_args += test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags);
-		if (cc->on_disk_tag_size)
-			num_feature_args++;
+		num_feature_args += test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags);
 		if (num_feature_args) {
 			DMEMIT(" %d", num_feature_args);
 			if (ti->num_discard_bios)
 				DMEMIT(" allow_discards");
 			if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags))
 				DMEMIT(" same_cpu_crypt");
+			if (test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags))
+				DMEMIT(" high_priority");
 			if (test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags))
 				DMEMIT(" submit_from_crypt_cpus");
 			if (test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags))
 				DMEMIT(" no_read_workqueue");
 			if (test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))
 				DMEMIT(" no_write_workqueue");
-			if (cc->on_disk_tag_size)
-				DMEMIT(" integrity:%u:%s", cc->on_disk_tag_size, cc->cipher_auth);
+			if (cc->used_tag_size)
+				DMEMIT(" integrity:%u:%s", cc->used_tag_size, cc->cipher_auth);
 			if (cc->sector_size != (1 << SECTOR_SHIFT))
 				DMEMIT(" sector_size:%d", cc->sector_size);
 			if (test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags))
 				DMEMIT(" iv_large_sectors");
+			if (test_bit(CRYPT_KEY_MAC_SIZE_SET, &cc->cipher_flags))
+				DMEMIT(" integrity_key_size:%u", cc->key_mac_size);
 		}
 		break;
 
@@ -3575,6 +3635,7 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 		DMEMIT_TARGET_NAME_VERSION(ti->type);
 		DMEMIT(",allow_discards=%c", ti->num_discard_bios ? 'y' : 'n');
 		DMEMIT(",same_cpu_crypt=%c", test_bit(DM_CRYPT_SAME_CPU, &cc->flags) ? 'y' : 'n');
+		DMEMIT(",high_priority=%c", test_bit(DM_CRYPT_HIGH_PRIORITY, &cc->flags) ? 'y' : 'n');
 		DMEMIT(",submit_from_crypt_cpus=%c", test_bit(DM_CRYPT_NO_OFFLOAD, &cc->flags) ?
 		       'y' : 'n');
 		DMEMIT(",no_read_workqueue=%c", test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags) ?
@@ -3584,9 +3645,9 @@ static void crypt_status(struct dm_target *ti, status_type_t type,
 		DMEMIT(",iv_large_sectors=%c", test_bit(CRYPT_IV_LARGE_SECTORS, &cc->cipher_flags) ?
 		       'y' : 'n');
 
-		if (cc->on_disk_tag_size)
+		if (cc->used_tag_size)
 			DMEMIT(",integrity_tag_size=%u,cipher_auth=%s",
-			       cc->on_disk_tag_size, cc->cipher_auth);
+			       cc->used_tag_size, cc->cipher_auth);
 		if (cc->sector_size != (1 << SECTOR_SHIFT))
 			DMEMIT(",sector_size=%d", cc->sector_size);
 		if (cc->cipher_string)
@@ -3684,14 +3745,6 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct crypt_config *cc = ti->private;
 
-	/*
-	 * Unfortunate constraint that is required to avoid the potential
-	 * for exceeding underlying device's max_segments limits -- due to
-	 * crypt_alloc_buffer() possibly allocating pages for the encryption
-	 * bio that are not as physically contiguous as the original bio.
-	 */
-	limits->max_segment_size = PAGE_SIZE;
-
 	limits->logical_block_size =
 		max_t(unsigned int, limits->logical_block_size, cc->sector_size);
 	limits->physical_block_size =
@@ -3702,7 +3755,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 25, 0},
+	.version = {1, 28, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,