Merge tag 'for-5.6/dm-changes' of...

Merge tag 'for-5.6/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Fix DM core's potential for q->make_request_fn NULL pointer in the
   unlikely case that a DM device is created without a DM table and then
   accessed due to upper-layer userspace code or user error.

 - Fix DM thin-provisioning's metadata_pre_commit_callback to not use
   memory after it is free'd. Also refactor code to disallow changing
   the thin-pool's data device once in use -- doing so guarantees smae
   lifetime of pool's data device relative to the pool metadata.

 - Fix DM space maps used by DM thinp and DM cache to avoid reuse of a
   already used block. This race was identified with extremely heavy
   snapshot use in the context of DM thin provisioning.

 - Fix DM raid's table status relative to an active rebuild.

 - Fix DM crypt to use GFP_NOIO rather than GFP_NOFS in call to
   skcipher_request_alloc(). Also fix benbi IV constructor crash if used
   in authenticated mode.

 - Add DM crypt support for Elephant diffuser to allow for Bitlocker
   compatibility.

 - Fix DM verity target to not prefetch hash blocks for data that has
   already been verified.

 - Fix DM writecache's incorrect flush sequence during commit when in
   SSD mode.

 - Improve DM writecache's sequential write performance on SSDs.

 - Add DM zoned target support for zone sizes smaller than 128MiB.

 - Add DM multipath 'queue_if_no_path_timeout_secs' module param to
   allow timeout if path isn't reinstated. This allows users a kernel
   safety-net against IO hanging indefinitely, due to no active paths,
   that has historically only been provided by multipathd userspace.

 - Various DM code cleanups to use true/false rather than 1/0, a
   variable rename in dm-dust, and fix for a math error in comment for
   DM thin metadata's ondisk format.

* tag 'for-5.6/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (21 commits)
  dm: fix potential for q->make_request_fn NULL pointer
  dm writecache: improve performance of large linear writes on SSDs
  dm mpath: Add timeout mechanism for queue_if_no_path
  dm thin: change data device's flush_bio to be member of struct pool
  dm thin: don't allow changing data device during thin-pool reload
  dm thin: fix use-after-free in metadata_pre_commit_callback
  dm thin metadata: use pool locking at end of dm_pool_metadata_close
  dm writecache: fix incorrect flush sequence when doing SSD mode commit
  dm crypt: fix benbi IV constructor crash if used in authenticated mode
  dm crypt: Implement Elephant diffuser for Bitlocker compatibility
  dm space map common: fix to ensure new block isn't already in use
  dm verity: don't prefetch hash blocks for already-verified data
  dm crypt: fix GFP flags passed to skcipher_request_alloc()
  dm thin metadata: Fix trivial math error in on-disk format documentation
  dm thin metadata: use true/false for bool variable
  dm snapshot: use true/false for bool variable
  dm bio prison v2: use true/false for bool variable
  dm mpath: use true/false for bool variable
  dm zoned: support zone sizes smaller than 128MiB
  dm raid: table line rebuild status fixes
  ...

Documentation/admin-guide/device-mapper/dm-raid.rst

@@ -419,3 +419,5 @@ Version History
 	rebuild errors.
  1.15.0 Fix size extensions not being synchronized in case of new MD bitmap
         pages allocated;  also fix those not occuring after previous reductions
+ 1.15.1 Fix argument count and arguments for rebuild/write_mostly/journal_(dev|mode)
+        on the status line.

drivers/md/dm-bio-prison-v2.c

@@ -324,7 +324,7 @@ static bool __unlock(struct dm_bio_prison_v2 *prison,
 	bio_list_init(&cell->bios);
 
 	if (cell->shared_count) {
-		cell->exclusive_lock = 0;
+		cell->exclusive_lock = false;
 		return false;
 	}
 

drivers/md/dm-crypt.c

 /*
  * Copyright (C) 2003 Jana Saout <jana@saout.de>
  * Copyright (C) 2004 Clemens Fruhwirth <clemens@endorphin.org>
- * Copyright (C) 2006-2017 Red Hat, Inc. All rights reserved.
- * Copyright (C) 2013-2017 Milan Broz <gmazyland@gmail.com>
+ * Copyright (C) 2006-2020 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2013-2020 Milan Broz <gmazyland@gmail.com>
  *
  * This file is released under the GPL.
  */
@@ -115,6 +115,11 @@ struct iv_tcw_private {
 	u8 *whitening;
 };
 
+#define ELEPHANT_MAX_KEY_SIZE 32
+struct iv_elephant_private {
+	struct crypto_skcipher *tfm;
+};
+
 /*
  * Crypt: maps a linear range of a block device
  * and encrypts / decrypts at the same time.
@@ -125,6 +130,7 @@ enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID,
 enum cipher_flags {
 	CRYPT_MODE_INTEGRITY_AEAD,	/* Use authenticated mode for cihper */
 	CRYPT_IV_LARGE_SECTORS,		/* Calculate IV from sector_size, not 512B sectors */
+	CRYPT_ENCRYPT_PREPROCESS,	/* Must preprocess data for encryption (elephant) */
 };
 
 /*
@@ -152,6 +158,7 @@ struct crypt_config {
 		struct iv_benbi_private benbi;
 		struct iv_lmk_private lmk;
 		struct iv_tcw_private tcw;
+		struct iv_elephant_private elephant;
 	} iv_gen_private;
 	u64 iv_offset;
 	unsigned int iv_size;
@@ -285,6 +292,11 @@ static struct crypto_aead *any_tfm_aead(struct crypt_config *cc)
  * eboiv: Encrypted byte-offset IV (used in Bitlocker in CBC mode)
  *        The IV is encrypted little-endian byte-offset (with the same key
  *        and cipher as the volume).
+ *
+ * elephant: The extended version of eboiv with additional Elephant diffuser
+ *           used with Bitlocker CBC mode.
+ *           This mode was used in older Windows systems
+ *           http://download.microsoft.com/download/0/2/3/0238acaf-d3bf-4a6d-b3d6-0a0be4bbb36e/bitlockercipher200608.pdf
  */
 
 static int crypt_iv_plain_gen(struct crypt_config *cc, u8 *iv,
@@ -331,8 +343,14 @@ static int crypt_iv_essiv_gen(struct crypt_config *cc, u8 *iv,
 static int crypt_iv_benbi_ctr(struct crypt_config *cc, struct dm_target *ti,
 			      const char *opts)
 {
-	unsigned bs = crypto_skcipher_blocksize(any_tfm(cc));
-	int log = ilog2(bs);
+	unsigned bs;
+	int log;
+
+	if (test_bit(CRYPT_MODE_INTEGRITY_AEAD, &cc->cipher_flags))
+		bs = crypto_aead_blocksize(any_tfm_aead(cc));
+	else
+		bs = crypto_skcipher_blocksize(any_tfm(cc));
+	log = ilog2(bs);
 
 	/* we need to calculate how far we must shift the sector count
 	 * to get the cipher block count, we use this shift in _gen */
@@ -717,7 +735,7 @@ static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv,
 	struct crypto_wait wait;
 	int err;
 
-	req = skcipher_request_alloc(any_tfm(cc), GFP_KERNEL | GFP_NOFS);
+	req = skcipher_request_alloc(any_tfm(cc), GFP_NOIO);
 	if (!req)
 		return -ENOMEM;
 
@@ -734,6 +752,290 @@ static int crypt_iv_eboiv_gen(struct crypt_config *cc, u8 *iv,
 	return err;
 }
 
+static void crypt_iv_elephant_dtr(struct crypt_config *cc)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+
+	crypto_free_skcipher(elephant->tfm);
+	elephant->tfm = NULL;
+}
+
+static int crypt_iv_elephant_ctr(struct crypt_config *cc, struct dm_target *ti,
+			    const char *opts)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	int r;
+
+	elephant->tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+	if (IS_ERR(elephant->tfm)) {
+		r = PTR_ERR(elephant->tfm);
+		elephant->tfm = NULL;
+		return r;
+	}
+
+	r = crypt_iv_eboiv_ctr(cc, ti, NULL);
+	if (r)
+		crypt_iv_elephant_dtr(cc);
+	return r;
+}
+
+static void diffuser_disk_to_cpu(u32 *d, size_t n)
+{
+#ifndef __LITTLE_ENDIAN
+	int i;
+
+	for (i = 0; i < n; i++)
+		d[i] = le32_to_cpu((__le32)d[i]);
+#endif
+}
+
+static void diffuser_cpu_to_disk(__le32 *d, size_t n)
+{
+#ifndef __LITTLE_ENDIAN
+	int i;
+
+	for (i = 0; i < n; i++)
+		d[i] = cpu_to_le32((u32)d[i]);
+#endif
+}
+
+static void diffuser_a_decrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 5; i++) {
+		i1 = 0;
+		i2 = n - 2;
+		i3 = n - 5;
+
+		while (i1 < (n - 1)) {
+			d[i1] += d[i2] ^ (d[i3] << 9 | d[i3] >> 23);
+			i1++; i2++; i3++;
+
+			if (i3 >= n)
+				i3 -= n;
+
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+
+			if (i2 >= n)
+				i2 -= n;
+
+			d[i1] += d[i2] ^ (d[i3] << 13 | d[i3] >> 19);
+			i1++; i2++; i3++;
+
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+		}
+	}
+}
+
+static void diffuser_a_encrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 5; i++) {
+		i1 = n - 1;
+		i2 = n - 2 - 1;
+		i3 = n - 5 - 1;
+
+		while (i1 > 0) {
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+
+			d[i1] -= d[i2] ^ (d[i3] << 13 | d[i3] >> 19);
+			i1--; i2--; i3--;
+
+			if (i2 < 0)
+				i2 += n;
+
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+
+			if (i3 < 0)
+				i3 += n;
+
+			d[i1] -= d[i2] ^ (d[i3] << 9 | d[i3] >> 23);
+			i1--; i2--; i3--;
+		}
+	}
+}
+
+static void diffuser_b_decrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 3; i++) {
+		i1 = 0;
+		i2 = 2;
+		i3 = 5;
+
+		while (i1 < (n - 1)) {
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+
+			d[i1] += d[i2] ^ (d[i3] << 10 | d[i3] >> 22);
+			i1++; i2++; i3++;
+
+			if (i2 >= n)
+				i2 -= n;
+
+			d[i1] += d[i2] ^ d[i3];
+			i1++; i2++; i3++;
+
+			if (i3 >= n)
+				i3 -= n;
+
+			d[i1] += d[i2] ^ (d[i3] << 25 | d[i3] >> 7);
+			i1++; i2++; i3++;
+		}
+	}
+}
+
+static void diffuser_b_encrypt(u32 *d, size_t n)
+{
+	int i, i1, i2, i3;
+
+	for (i = 0; i < 3; i++) {
+		i1 = n - 1;
+		i2 = 2 - 1;
+		i3 = 5 - 1;
+
+		while (i1 > 0) {
+			d[i1] -= d[i2] ^ (d[i3] << 25 | d[i3] >> 7);
+			i1--; i2--; i3--;
+
+			if (i3 < 0)
+				i3 += n;
+
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+
+			if (i2 < 0)
+				i2 += n;
+
+			d[i1] -= d[i2] ^ (d[i3] << 10 | d[i3] >> 22);
+			i1--; i2--; i3--;
+
+			d[i1] -= d[i2] ^ d[i3];
+			i1--; i2--; i3--;
+		}
+	}
+}
+
+static int crypt_iv_elephant(struct crypt_config *cc, struct dm_crypt_request *dmreq)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	u8 *es, *ks, *data, *data2, *data_offset;
+	struct skcipher_request *req;
+	struct scatterlist *sg, *sg2, src, dst;
+	struct crypto_wait wait;
+	int i, r;
+
+	req = skcipher_request_alloc(elephant->tfm, GFP_NOIO);
+	es = kzalloc(16, GFP_NOIO); /* Key for AES */
+	ks = kzalloc(32, GFP_NOIO); /* Elephant sector key */
+
+	if (!req || !es || !ks) {
+		r = -ENOMEM;
+		goto out;
+	}
+
+	*(__le64 *)es = cpu_to_le64(dmreq->iv_sector * cc->sector_size);
+
+	/* E(Ks, e(s)) */
+	sg_init_one(&src, es, 16);
+	sg_init_one(&dst, ks, 16);
+	skcipher_request_set_crypt(req, &src, &dst, 16, NULL);
+	skcipher_request_set_callback(req, 0, crypto_req_done, &wait);
+	r = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	if (r)
+		goto out;
+
+	/* E(Ks, e'(s)) */
+	es[15] = 0x80;
+	sg_init_one(&dst, &ks[16], 16);
+	r = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	if (r)
+		goto out;
+
+	sg = crypt_get_sg_data(cc, dmreq->sg_out);
+	data = kmap_atomic(sg_page(sg));
+	data_offset = data + sg->offset;
+
+	/* Cannot modify original bio, copy to sg_out and apply Elephant to it */
+	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
+		sg2 = crypt_get_sg_data(cc, dmreq->sg_in);
+		data2 = kmap_atomic(sg_page(sg2));
+		memcpy(data_offset, data2 + sg2->offset, cc->sector_size);
+		kunmap_atomic(data2);
+	}
+
+	if (bio_data_dir(dmreq->ctx->bio_in) != WRITE) {
+		diffuser_disk_to_cpu((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_b_decrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_a_decrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_cpu_to_disk((__le32*)data_offset, cc->sector_size / sizeof(u32));
+	}
+
+	for (i = 0; i < (cc->sector_size / 32); i++)
+		crypto_xor(data_offset + i * 32, ks, 32);
+
+	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
+		diffuser_disk_to_cpu((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_a_encrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_b_encrypt((u32*)data_offset, cc->sector_size / sizeof(u32));
+		diffuser_cpu_to_disk((__le32*)data_offset, cc->sector_size / sizeof(u32));
+	}
+
+	kunmap_atomic(data);
+out:
+	kzfree(ks);
+	kzfree(es);
+	skcipher_request_free(req);
+	return r;
+}
+
+static int crypt_iv_elephant_gen(struct crypt_config *cc, u8 *iv,
+			    struct dm_crypt_request *dmreq)
+{
+	int r;
+
+	if (bio_data_dir(dmreq->ctx->bio_in) == WRITE) {
+		r = crypt_iv_elephant(cc, dmreq);
+		if (r)
+			return r;
+	}
+
+	return crypt_iv_eboiv_gen(cc, iv, dmreq);
+}
+
+static int crypt_iv_elephant_post(struct crypt_config *cc, u8 *iv,
+				  struct dm_crypt_request *dmreq)
+{
+	if (bio_data_dir(dmreq->ctx->bio_in) != WRITE)
+		return crypt_iv_elephant(cc, dmreq);
+
+	return 0;
+}
+
+static int crypt_iv_elephant_init(struct crypt_config *cc)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	int key_offset = cc->key_size - cc->key_extra_size;
+
+	return crypto_skcipher_setkey(elephant->tfm, &cc->key[key_offset], cc->key_extra_size);
+}
+
+static int crypt_iv_elephant_wipe(struct crypt_config *cc)
+{
+	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
+	u8 key[ELEPHANT_MAX_KEY_SIZE];
+
+	memset(key, 0, cc->key_extra_size);
+	return crypto_skcipher_setkey(elephant->tfm, key, cc->key_extra_size);
+}
+
 static const struct crypt_iv_operations crypt_iv_plain_ops = {
 	.generator = crypt_iv_plain_gen
 };
@@ -787,6 +1089,15 @@ static struct crypt_iv_operations crypt_iv_eboiv_ops = {
 	.generator = crypt_iv_eboiv_gen
 };
 
+static struct crypt_iv_operations crypt_iv_elephant_ops = {
+	.ctr	   = crypt_iv_elephant_ctr,
+	.dtr	   = crypt_iv_elephant_dtr,
+	.init	   = crypt_iv_elephant_init,
+	.wipe	   = crypt_iv_elephant_wipe,
+	.generator = crypt_iv_elephant_gen,
+	.post	   = crypt_iv_elephant_post
+};
+
 /*
  * Integrity extensions
  */
@@ -1103,6 +1414,9 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc,
 			r = cc->iv_gen_ops->generator(cc, org_iv, dmreq);
 			if (r < 0)
 				return r;
+			/* Data can be already preprocessed in generator */
+			if (test_bit(CRYPT_ENCRYPT_PREPROCESS, &cc->cipher_flags))
+				sg_in = sg_out;
 			/* Store generated IV in integrity metadata */
 			if (cc->integrity_iv_size)
 				memcpy(tag_iv, org_iv, cc->integrity_iv_size);
@@ -2191,7 +2505,14 @@ static int crypt_ctr_ivmode(struct dm_target *ti, const char *ivmode)
 		cc->iv_gen_ops = &crypt_iv_null_ops;
 	else if (strcmp(ivmode, "eboiv") == 0)
 		cc->iv_gen_ops = &crypt_iv_eboiv_ops;
-	else if (strcmp(ivmode, "lmk") == 0) {
+	else if (strcmp(ivmode, "elephant") == 0) {
+		cc->iv_gen_ops = &crypt_iv_elephant_ops;
+		cc->key_parts = 2;
+		cc->key_extra_size = cc->key_size / 2;
+		if (cc->key_extra_size > ELEPHANT_MAX_KEY_SIZE)
+			return -EINVAL;
+		set_bit(CRYPT_ENCRYPT_PREPROCESS, &cc->cipher_flags);
+	} else if (strcmp(ivmode, "lmk") == 0) {
 		cc->iv_gen_ops = &crypt_iv_lmk_ops;
 		/*
 		 * Version 2 and 3 is recognised according
@@ -2959,7 +3280,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 19, 0},
+	.version = {1, 20, 0},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,

drivers/md/dm-dust.c

@@ -207,16 +207,16 @@ static int dust_map_write(struct dust_device *dd, sector_t thisblock,
 			  bool fail_read_on_bb)
 {
 	unsigned long flags;
-	int ret = DM_MAPIO_REMAPPED;
+	int r = DM_MAPIO_REMAPPED;
 
 	if (fail_read_on_bb) {
 		thisblock >>= dd->sect_per_block_shift;
 		spin_lock_irqsave(&dd->dust_lock, flags);
-		ret = __dust_map_write(dd, thisblock);
+		r = __dust_map_write(dd, thisblock);
 		spin_unlock_irqrestore(&dd->dust_lock, flags);
 	}
 
-	return ret;
+	return r;
 }
 
 static int dust_map(struct dm_target *ti, struct bio *bio)

drivers/md/dm-mpath.c

@@ -20,6 +20,7 @@
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/time.h>
+#include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <scsi/scsi_dh.h>
@@ -29,6 +30,9 @@
 #define DM_MSG_PREFIX "multipath"
 #define DM_PG_INIT_DELAY_MSECS 2000
 #define DM_PG_INIT_DELAY_DEFAULT ((unsigned) -1)
+#define QUEUE_IF_NO_PATH_TIMEOUT_DEFAULT 0
+
+static unsigned long queue_if_no_path_timeout_secs = QUEUE_IF_NO_PATH_TIMEOUT_DEFAULT;
 
 /* Path properties */
 struct pgpath {
@@ -91,6 +95,8 @@ struct multipath {
 
 	struct work_struct process_queued_bios;
 	struct bio_list queued_bios;
+
+	struct timer_list nopath_timer;	/* Timeout for queue_if_no_path */
 };
 
 /*
@@ -108,6 +114,7 @@ static void trigger_event(struct work_struct *work);
 static void activate_or_offline_path(struct pgpath *pgpath);
 static void activate_path_work(struct work_struct *work);
 static void process_queued_bios(struct work_struct *work);
+static void queue_if_no_path_timeout_work(struct timer_list *t);
 
 /*-----------------------------------------------
  * Multipath state flags.
@@ -195,6 +202,8 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 
 		m->ti = ti;
 		ti->private = m;
+
+		timer_setup(&m->nopath_timer, queue_if_no_path_timeout_work, 0);
 	}
 
 	return m;
@@ -717,6 +726,43 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
 	return 0;
 }
 
+/*
+ * If the queue_if_no_path timeout fires, turn off queue_if_no_path and
+ * process any queued I/O.
+ */
+static void queue_if_no_path_timeout_work(struct timer_list *t)
+{
+	struct multipath *m = from_timer(m, t, nopath_timer);
+	struct mapped_device *md = dm_table_get_md(m->ti->table);
+
+	DMWARN("queue_if_no_path timeout on %s, failing queued IO", dm_device_name(md));
+	queue_if_no_path(m, false, false);
+}
+
+/*
+ * Enable the queue_if_no_path timeout if necessary.
+ * Called with m->lock held.
+ */
+static void enable_nopath_timeout(struct multipath *m)
+{
+	unsigned long queue_if_no_path_timeout =
+		READ_ONCE(queue_if_no_path_timeout_secs) * HZ;
+
+	lockdep_assert_held(&m->lock);
+
+	if (queue_if_no_path_timeout > 0 &&
+	    atomic_read(&m->nr_valid_paths) == 0 &&
+	    test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+		mod_timer(&m->nopath_timer,
+			  jiffies + queue_if_no_path_timeout);
+	}
+}
+
+static void disable_nopath_timeout(struct multipath *m)
+{
+	del_timer_sync(&m->nopath_timer);
+}
+
 /*
  * An event is triggered whenever a path is taken out of use.
  * Includes path failure and PG bypass.
@@ -1090,6 +1136,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	struct dm_arg_set as;
 	unsigned pg_count = 0;
 	unsigned next_pg_num;
+	unsigned long flags;
 
 	as.argc = argc;
 	as.argv = argv;
@@ -1154,6 +1201,10 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
+	spin_lock_irqsave(&m->lock, flags);
+	enable_nopath_timeout(m);
+	spin_unlock_irqrestore(&m->lock, flags);
+
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
 	ti->num_write_same_bios = 1;
@@ -1208,6 +1259,7 @@ static void multipath_dtr(struct dm_target *ti)
 {
 	struct multipath *m = ti->private;
 
+	disable_nopath_timeout(m);
 	flush_multipath_work(m);
 	free_multipath(m);
 }
@@ -1241,6 +1293,8 @@ static int fail_path(struct pgpath *pgpath)
 
 	schedule_work(&m->trigger_event);
 
+	enable_nopath_timeout(m);
+
 out:
 	spin_unlock_irqrestore(&m->lock, flags);
 
@@ -1291,6 +1345,9 @@ static int reinstate_path(struct pgpath *pgpath)
 		process_queued_io_list(m);
 	}
 
+	if (pgpath->is_active)
+		disable_nopath_timeout(m);
+
 	return r;
 }
 
@@ -1444,7 +1501,7 @@ static void pg_init_done(void *data, int errors)
 		break;
 	case SCSI_DH_RETRY:
 		/* Wait before retrying. */
-		delay_retry = 1;
+		delay_retry = true;
 		/* fall through */
 	case SCSI_DH_IMM_RETRY:
 	case SCSI_DH_RES_TEMP_UNAVAIL:
@@ -1789,6 +1846,7 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv,
 	struct dm_dev *dev;
 	struct multipath *m = ti->private;
 	action_fn action;
+	unsigned long flags;
 
 	mutex_lock(&m->work_mutex);
 
@@ -1800,9 +1858,13 @@ static int multipath_message(struct dm_target *ti, unsigned argc, char **argv,
 	if (argc == 1) {
 		if (!strcasecmp(argv[0], "queue_if_no_path")) {
 			r = queue_if_no_path(m, true, false);
+			spin_lock_irqsave(&m->lock, flags);
+			enable_nopath_timeout(m);
+			spin_unlock_irqrestore(&m->lock, flags);
 			goto out;
 		} else if (!strcasecmp(argv[0], "fail_if_no_path")) {
 			r = queue_if_no_path(m, false, false);
+			disable_nopath_timeout(m);
 			goto out;
 		}
 	}
@@ -2065,6 +2127,10 @@ static void __exit dm_multipath_exit(void)
 module_init(dm_multipath_init);
 module_exit(dm_multipath_exit);
 
+module_param_named(queue_if_no_path_timeout_secs,
+		   queue_if_no_path_timeout_secs, ulong, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(queue_if_no_path_timeout_secs, "No available paths queue IO timeout in seconds");
+
 MODULE_DESCRIPTION(DM_NAME " multipath target");
 MODULE_AUTHOR("Sistina Software <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");

drivers/md/dm-raid.c

@@ -129,7 +129,9 @@ struct raid_dev {
 				  CTR_FLAG_RAID10_COPIES | \
 				  CTR_FLAG_RAID10_FORMAT | \
 				  CTR_FLAG_DELTA_DISKS | \
-				  CTR_FLAG_DATA_OFFSET)
+				  CTR_FLAG_DATA_OFFSET | \
+				  CTR_FLAG_JOURNAL_DEV | \
+				  CTR_FLAG_JOURNAL_MODE)
 
 /* Valid options definitions per raid level... */
 
@@ -3001,7 +3003,6 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		{ 1, 254, "Cannot understand number of raid devices parameters" }
 	};
 
-	/* Must have <raid_type> */
 	arg = dm_shift_arg(&as);
 	if (!arg) {
 		ti->error = "No arguments";
@@ -3508,8 +3509,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	unsigned long recovery;
 	unsigned int raid_param_cnt = 1; /* at least 1 for chunksize */
 	unsigned int sz = 0;
-	unsigned int rebuild_disks;
-	unsigned int write_mostly_params = 0;
+	unsigned int rebuild_writemostly_count = 0;
 	sector_t progress, resync_max_sectors, resync_mismatches;
 	enum sync_state state;
 	struct raid_type *rt;
@@ -3593,18 +3593,20 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	case STATUSTYPE_TABLE:
 		/* Report the table line string you would use to construct this raid set */
 
-		/* Calculate raid parameter count */
-		for (i = 0; i < rs->raid_disks; i++)
-			if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
-				write_mostly_params += 2;
-		rebuild_disks = memweight(rs->rebuild_disks, DISKS_ARRAY_ELEMS * sizeof(*rs->rebuild_disks));
-		raid_param_cnt += rebuild_disks * 2 +
-				  write_mostly_params +
+		/*
+		 * Count any rebuild or writemostly argument pairs and subtract the
+		 * hweight count being added below of any rebuild and writemostly ctr flags.
+		 */
+		for (i = 0; i < rs->raid_disks; i++) {
+			rebuild_writemostly_count += (test_bit(i, (void *) rs->rebuild_disks) ? 2 : 0) +
+						     (test_bit(WriteMostly, &rs->dev[i].rdev.flags) ? 2 : 0);
+		}
+		rebuild_writemostly_count -= (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags) ? 2 : 0) +
+					     (test_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags) ? 2 : 0);
+		/* Calculate raid parameter count based on ^ rebuild/writemostly argument counts and ctr flags set. */
+		raid_param_cnt += rebuild_writemostly_count +
 				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_NO_ARGS) +
-				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_ONE_ARG) * 2 +
-				  (test_bit(__CTR_FLAG_JOURNAL_DEV, &rs->ctr_flags) ? 2 : 0) +
-				  (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags) ? 2 : 0);
-
+				  hweight32(rs->ctr_flags & CTR_FLAG_OPTIONS_ONE_ARG) * 2;
 		/* Emit table line */
 		/* This has to be in the documented order for userspace! */
 		DMEMIT("%s %u %u", rs->raid_type->name, raid_param_cnt, mddev->new_chunk_sectors);
@@ -3612,11 +3614,10 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_SYNC));
 		if (test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags))
 			DMEMIT(" %s", dm_raid_arg_name_by_flag(CTR_FLAG_NOSYNC));
-		if (rebuild_disks)
+		if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags))
 			for (i = 0; i < rs->raid_disks; i++)
-				if (test_bit(rs->dev[i].rdev.raid_disk, (void *) rs->rebuild_disks))
-					DMEMIT(" %s %u", dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD),
-							 rs->dev[i].rdev.raid_disk);
+				if (test_bit(i, (void *) rs->rebuild_disks))
+					DMEMIT(" %s %u", dm_raid_arg_name_by_flag(CTR_FLAG_REBUILD), i);
 		if (test_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags))
 			DMEMIT(" %s %lu", dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP),
 					  mddev->bitmap_info.daemon_sleep);
@@ -3626,7 +3627,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		if (test_bit(__CTR_FLAG_MAX_RECOVERY_RATE, &rs->ctr_flags))
 			DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE),
 					 mddev->sync_speed_max);
-		if (write_mostly_params)
+		if (test_bit(__CTR_FLAG_WRITE_MOSTLY, &rs->ctr_flags))
 			for (i = 0; i < rs->raid_disks; i++)
 				if (test_bit(WriteMostly, &rs->dev[i].rdev.flags))
 					DMEMIT(" %s %d", dm_raid_arg_name_by_flag(CTR_FLAG_WRITE_MOSTLY),
@@ -4029,7 +4030,7 @@ static void raid_resume(struct dm_target *ti)
 
 static struct target_type raid_target = {
 	.name = "raid",
-	.version = {1, 15, 0},
+	.version = {1, 15, 1},
 	.module = THIS_MODULE,
 	.ctr = raid_ctr,
 	.dtr = raid_dtr,

drivers/md/dm-snap.c

@@ -1061,7 +1061,7 @@ static void snapshot_merge_next_chunks(struct dm_snapshot *s)
 			DMERR("Read error in exception store: "
 			      "shutting down merge");
 			down_write(&s->lock);
-			s->merge_failed = 1;
+			s->merge_failed = true;
 			up_write(&s->lock);
 		}
 		goto shut;
@@ -1149,7 +1149,7 @@ static void merge_callback(int read_err, unsigned long write_err, void *context)
 
 shut:
 	down_write(&s->lock);
-	s->merge_failed = 1;
+	s->merge_failed = true;
 	b = __release_queued_bios_after_merge(s);
 	up_write(&s->lock);
 	error_bios(b);
@@ -1314,7 +1314,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	INIT_LIST_HEAD(&s->list);
 	spin_lock_init(&s->pe_lock);
 	s->state_bits = 0;
-	s->merge_failed = 0;
+	s->merge_failed = false;
 	s->first_merging_chunk = 0;
 	s->num_merging_chunks = 0;
 	bio_list_init(&s->bios_queued_during_merge);

drivers/md/dm-thin-metadata.c

@@ -28,7 +28,7 @@
  *
  * - A hierarchical btree, with 2 levels which effectively maps (thin
  *   dev id, virtual block) -> block_time.  Block time is a 64-bit
- *   field holding the time in the low 24 bits, and block in the top 48
+ *   field holding the time in the low 24 bits, and block in the top 40
  *   bits.
  *
  * BTrees consist solely of btree_nodes, that fill a block.  Some are
@@ -387,16 +387,15 @@ static int subtree_equal(void *context, const void *value1_le, const void *value
  * Variant that is used for in-core only changes or code that
  * shouldn't put the pool in service on its own (e.g. commit).
  */
-static inline void __pmd_write_lock(struct dm_pool_metadata *pmd)
+static inline void pmd_write_lock_in_core(struct dm_pool_metadata *pmd)
 	__acquires(pmd->root_lock)
 {
 	down_write(&pmd->root_lock);
 }
-#define pmd_write_lock_in_core(pmd) __pmd_write_lock((pmd))
 
 static inline void pmd_write_lock(struct dm_pool_metadata *pmd)
 {
-	__pmd_write_lock(pmd);
+	pmd_write_lock_in_core(pmd);
 	if (unlikely(!pmd->in_service))
 		pmd->in_service = true;
 }
@@ -811,7 +810,7 @@ static int __write_changed_details(struct dm_pool_metadata *pmd)
 			return r;
 
 		if (td->open_count)
-			td->changed = 0;
+			td->changed = false;
 		else {
 			list_del(&td->list);
 			kfree(td);
@@ -831,6 +830,7 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	 * We need to know if the thin_disk_superblock exceeds a 512-byte sector.
 	 */
 	BUILD_BUG_ON(sizeof(struct thin_disk_superblock) > 512);
+	BUG_ON(!rwsem_is_locked(&pmd->root_lock));
 
 	if (unlikely(!pmd->in_service))
 		return 0;
@@ -953,6 +953,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 		return -EBUSY;
 	}
 
+	pmd_write_lock_in_core(pmd);
 	if (!dm_bm_is_read_only(pmd->bm) && !pmd->fail_io) {
 		r = __commit_transaction(pmd);
 		if (r < 0)
@@ -961,6 +962,7 @@ int dm_pool_metadata_close(struct dm_pool_metadata *pmd)
 	}
 	if (!pmd->fail_io)
 		__destroy_persistent_data_objects(pmd);
+	pmd_write_unlock(pmd);
 
 	kfree(pmd);
 	return 0;
@@ -1106,7 +1108,7 @@ static int __set_snapshot_details(struct dm_pool_metadata *pmd,
 	if (r)
 		return r;
 
-	td->changed = 1;
+	td->changed = true;
 	td->snapshotted_time = time;
 
 	snap->mapped_blocks = td->mapped_blocks;
@@ -1618,7 +1620,7 @@ static int __insert(struct dm_thin_device *td, dm_block_t block,
 	if (r)
 		return r;
 
-	td->changed = 1;
+	td->changed = true;
 	if (inserted)
 		td->mapped_blocks++;
 
@@ -1649,7 +1651,7 @@ static int __remove(struct dm_thin_device *td, dm_block_t block)
 		return r;
 
 	td->mapped_blocks--;
-	td->changed = 1;
+	td->changed = true;
 
 	return 0;
 }
@@ -1703,7 +1705,7 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_
 	}
 
 	td->mapped_blocks -= total_count;
-	td->changed = 1;
+	td->changed = true;
 
 	/*
 	 * Reinsert the mapping tree.
@@ -1841,7 +1843,7 @@ int dm_pool_commit_metadata(struct dm_pool_metadata *pmd)
 	 * Care is taken to not have commit be what
 	 * triggers putting the thin-pool in-service.
 	 */
-	__pmd_write_lock(pmd);
+	pmd_write_lock_in_core(pmd);
 	if (pmd->fail_io)
 		goto out;
 

drivers/md/dm-thin.c

@@ -231,6 +231,7 @@ struct pool {
 	struct dm_target *ti;	/* Only set if a pool target is bound */
 
 	struct mapped_device *pool_md;
+	struct block_device *data_dev;
 	struct block_device *md_dev;
 	struct dm_pool_metadata *pmd;
 
@@ -281,6 +282,8 @@ struct pool {
 	struct dm_bio_prison_cell **cell_sort_array;
 
 	mempool_t mapping_pool;
+
+	struct bio flush_bio;
 };
 
 static void metadata_operation_failed(struct pool *pool, const char *op, int r);
@@ -328,7 +331,6 @@ struct pool_c {
 	dm_block_t low_water_blocks;
 	struct pool_features requested_pf; /* Features requested during table load */
 	struct pool_features adjusted_pf;  /* Features used after adjusting for constituent devices */
-	struct bio flush_bio;
 };
 
 /*
@@ -2924,6 +2926,7 @@ static void __pool_destroy(struct pool *pool)
 	if (pool->next_mapping)
 		mempool_free(pool->next_mapping, &pool->mapping_pool);
 	mempool_exit(&pool->mapping_pool);
+	bio_uninit(&pool->flush_bio);
 	dm_deferred_set_destroy(pool->shared_read_ds);
 	dm_deferred_set_destroy(pool->all_io_ds);
 	kfree(pool);
@@ -2933,6 +2936,7 @@ static struct kmem_cache *_new_mapping_cache;
 
 static struct pool *pool_create(struct mapped_device *pool_md,
 				struct block_device *metadata_dev,
+				struct block_device *data_dev,
 				unsigned long block_size,
 				int read_only, char **error)
 {
@@ -3003,6 +3007,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	pool->low_water_triggered = false;
 	pool->suspended = true;
 	pool->out_of_data_space = false;
+	bio_init(&pool->flush_bio, NULL, 0);
 
 	pool->shared_read_ds = dm_deferred_set_create();
 	if (!pool->shared_read_ds) {
@@ -3040,6 +3045,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 	pool->last_commit_jiffies = jiffies;
 	pool->pool_md = pool_md;
 	pool->md_dev = metadata_dev;
+	pool->data_dev = data_dev;
 	__pool_table_insert(pool);
 
 	return pool;
@@ -3081,6 +3087,7 @@ static void __pool_dec(struct pool *pool)
 
 static struct pool *__pool_find(struct mapped_device *pool_md,
 				struct block_device *metadata_dev,
+				struct block_device *data_dev,
 				unsigned long block_size, int read_only,
 				char **error, int *created)
 {
@@ -3091,19 +3098,23 @@ static struct pool *__pool_find(struct mapped_device *pool_md,
 			*error = "metadata device already in use by a pool";
 			return ERR_PTR(-EBUSY);
 		}
+		if (pool->data_dev != data_dev) {
+			*error = "data device already in use by a pool";
+			return ERR_PTR(-EBUSY);
+		}
 		__pool_inc(pool);
 
 	} else {
 		pool = __pool_table_lookup(pool_md);
 		if (pool) {
-			if (pool->md_dev != metadata_dev) {
+			if (pool->md_dev != metadata_dev || pool->data_dev != data_dev) {
 				*error = "different pool cannot replace a pool";
 				return ERR_PTR(-EINVAL);
 			}
 			__pool_inc(pool);
 
 		} else {
-			pool = pool_create(pool_md, metadata_dev, block_size, read_only, error);
+			pool = pool_create(pool_md, metadata_dev, data_dev, block_size, read_only, error);
 			*created = 1;
 		}
 	}
@@ -3124,7 +3135,6 @@ static void pool_dtr(struct dm_target *ti)
 	__pool_dec(pt->pool);
 	dm_put_device(ti, pt->metadata_dev);
 	dm_put_device(ti, pt->data_dev);
-	bio_uninit(&pt->flush_bio);
 	kfree(pt);
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
@@ -3203,11 +3213,11 @@ static void metadata_low_callback(void *context)
  */
 static int metadata_pre_commit_callback(void *context)
 {
-	struct pool_c *pt = context;
-	struct bio *flush_bio = &pt->flush_bio;
+	struct pool *pool = context;
+	struct bio *flush_bio = &pool->flush_bio;
 
 	bio_reset(flush_bio);
-	bio_set_dev(flush_bio, pt->data_dev->bdev);
+	bio_set_dev(flush_bio, pool->data_dev);
 	flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 
 	return submit_bio_wait(flush_bio);
@@ -3356,7 +3366,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto out;
 	}
 
-	pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev,
+	pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev, data_dev->bdev,
 			   block_size, pf.mode == PM_READ_ONLY, &ti->error, &pool_created);
 	if (IS_ERR(pool)) {
 		r = PTR_ERR(pool);
@@ -3381,7 +3391,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	pt->data_dev = data_dev;
 	pt->low_water_blocks = low_water_blocks;
 	pt->adjusted_pf = pt->requested_pf = pf;
-	bio_init(&pt->flush_bio, NULL, 0);
 	ti->num_flush_bios = 1;
 
 	/*
@@ -3408,9 +3417,8 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (r)
 		goto out_flags_changed;
 
-	dm_pool_register_pre_commit_callback(pt->pool->pmd,
-					     metadata_pre_commit_callback,
-					     pt);
+	dm_pool_register_pre_commit_callback(pool->pmd,
+					     metadata_pre_commit_callback, pool);
 
 	pt->callbacks.congested_fn = pool_is_congested;
 	dm_table_add_target_callbacks(ti->table, &pt->callbacks);
@@ -4099,7 +4107,7 @@ static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 21, 0},
+	.version = {1, 22, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -4476,7 +4484,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 21, 0},
+	.version = {1, 22, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,

drivers/md/dm-verity-target.c

@@ -611,8 +611,22 @@ static void verity_prefetch_io(struct work_struct *work)
 
 static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io)
 {
+	sector_t block = io->block;
+	unsigned int n_blocks = io->n_blocks;
 	struct dm_verity_prefetch_work *pw;
 
+	if (v->validated_blocks) {
+		while (n_blocks && test_bit(block, v->validated_blocks)) {
+			block++;
+			n_blocks--;
+		}
+		while (n_blocks && test_bit(block + n_blocks - 1,
+					    v->validated_blocks))
+			n_blocks--;
+		if (!n_blocks)
+			return;
+	}
+
 	pw = kmalloc(sizeof(struct dm_verity_prefetch_work),
 		GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
@@ -621,8 +635,8 @@ static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io)
 
 	INIT_WORK(&pw->work, verity_prefetch_io);
 	pw->v = v;
-	pw->block = io->block;
-	pw->n_blocks = io->n_blocks;
+	pw->block = block;
+	pw->n_blocks = n_blocks;
 	queue_work(v->verify_wq, &pw->work);
 }
 

drivers/md/dm-writecache.c

@@ -442,7 +442,13 @@ static void writecache_notify_io(unsigned long error, void *context)
 		complete(&endio->c);
 }
 
-static void ssd_commit_flushed(struct dm_writecache *wc)
+static void writecache_wait_for_ios(struct dm_writecache *wc, int direction)
+{
+	wait_event(wc->bio_in_progress_wait[direction],
+		   !atomic_read(&wc->bio_in_progress[direction]));
+}
+
+static void ssd_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	struct dm_io_region region;
 	struct dm_io_request req;
@@ -488,17 +494,20 @@ static void ssd_commit_flushed(struct dm_writecache *wc)
 	writecache_notify_io(0, &endio);
 	wait_for_completion_io(&endio.c);
 
+	if (wait_for_ios)
+		writecache_wait_for_ios(wc, WRITE);
+
 	writecache_disk_flush(wc, wc->ssd_dev);
 
 	memset(wc->dirty_bitmap, 0, wc->dirty_bitmap_size);
 }
 
-static void writecache_commit_flushed(struct dm_writecache *wc)
+static void writecache_commit_flushed(struct dm_writecache *wc, bool wait_for_ios)
 {
 	if (WC_MODE_PMEM(wc))
 		wmb();
 	else
-		ssd_commit_flushed(wc);
+		ssd_commit_flushed(wc, wait_for_ios);
 }
 
 static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
@@ -522,12 +531,6 @@ static void writecache_disk_flush(struct dm_writecache *wc, struct dm_dev *dev)
 		writecache_error(wc, r, "error flushing metadata: %d", r);
 }
 
-static void writecache_wait_for_ios(struct dm_writecache *wc, int direction)
-{
-	wait_event(wc->bio_in_progress_wait[direction],
-		   !atomic_read(&wc->bio_in_progress[direction]));
-}
-
 #define WFE_RETURN_FOLLOWING	1
 #define WFE_LOWEST_SEQ		2
 
@@ -622,7 +625,7 @@ static void writecache_add_to_freelist(struct dm_writecache *wc, struct wc_entry
 	wc->freelist_size++;
 }
 
-static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
+static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc, sector_t expected_sector)
 {
 	struct wc_entry *e;
 
@@ -631,6 +634,8 @@ static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
 		if (unlikely(!wc->current_free))
 			return NULL;
 		e = wc->current_free;
+		if (expected_sector != (sector_t)-1 && unlikely(cache_sector(wc, e) != expected_sector))
+			return NULL;
 		next = rb_next(&e->rb_node);
 		rb_erase(&e->rb_node, &wc->freetree);
 		if (unlikely(!next))
@@ -640,6 +645,8 @@ static struct wc_entry *writecache_pop_from_freelist(struct dm_writecache *wc)
 		if (unlikely(list_empty(&wc->freelist)))
 			return NULL;
 		e = container_of(wc->freelist.next, struct wc_entry, lru);
+		if (expected_sector != (sector_t)-1 && unlikely(cache_sector(wc, e) != expected_sector))
+			return NULL;
 		list_del(&e->lru);
 	}
 	wc->freelist_size--;
@@ -724,15 +731,12 @@ static void writecache_flush(struct dm_writecache *wc)
 		e = e2;
 		cond_resched();
 	}
-	writecache_commit_flushed(wc);
-
-	if (!WC_MODE_PMEM(wc))
-		writecache_wait_for_ios(wc, WRITE);
+	writecache_commit_flushed(wc, true);
 
 	wc->seq_count++;
 	pmem_assign(sb(wc)->seq_count, cpu_to_le64(wc->seq_count));
 	writecache_flush_region(wc, &sb(wc)->seq_count, sizeof sb(wc)->seq_count);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 
 	wc->overwrote_committed = false;
 
@@ -756,7 +760,7 @@ static void writecache_flush(struct dm_writecache *wc)
 	}
 
 	if (need_flush_after_free)
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 }
 
 static void writecache_flush_work(struct work_struct *work)
@@ -809,7 +813,7 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_
 	}
 
 	if (discarded_something)
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 }
 
 static bool writecache_wait_for_writeback(struct dm_writecache *wc)
@@ -958,7 +962,7 @@ static void writecache_resume(struct dm_target *ti)
 
 	if (need_flush) {
 		writecache_flush_all_metadata(wc);
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 	}
 
 	wc_unlock(wc);
@@ -1193,7 +1197,7 @@ static int writecache_map(struct dm_target *ti, struct bio *bio)
 					goto bio_copy;
 				}
 			}
-			e = writecache_pop_from_freelist(wc);
+			e = writecache_pop_from_freelist(wc, (sector_t)-1);
 			if (unlikely(!e)) {
 				writecache_wait_on_freelist(wc);
 				continue;
@@ -1205,9 +1209,26 @@ static int writecache_map(struct dm_target *ti, struct bio *bio)
 			if (WC_MODE_PMEM(wc)) {
 				bio_copy_block(wc, bio, memory_data(wc, e));
 			} else {
-				dm_accept_partial_bio(bio, wc->block_size >> SECTOR_SHIFT);
+				unsigned bio_size = wc->block_size;
+				sector_t start_cache_sec = cache_sector(wc, e);
+				sector_t current_cache_sec = start_cache_sec + (bio_size >> SECTOR_SHIFT);
+
+				while (bio_size < bio->bi_iter.bi_size) {
+					struct wc_entry *f = writecache_pop_from_freelist(wc, current_cache_sec);
+					if (!f)
+						break;
+					write_original_sector_seq_count(wc, f, bio->bi_iter.bi_sector +
+									(bio_size >> SECTOR_SHIFT), wc->seq_count);
+					writecache_insert_entry(wc, f);
+					wc->uncommitted_blocks++;
+					bio_size += wc->block_size;
+					current_cache_sec += wc->block_size >> SECTOR_SHIFT;
+				}
+
 				bio_set_dev(bio, wc->ssd_dev->bdev);
-				bio->bi_iter.bi_sector = cache_sector(wc, e);
+				bio->bi_iter.bi_sector = start_cache_sec;
+				dm_accept_partial_bio(bio, bio_size >> SECTOR_SHIFT);
+
 				if (unlikely(wc->uncommitted_blocks >= wc->autocommit_blocks)) {
 					wc->uncommitted_blocks = 0;
 					queue_work(wc->writeback_wq, &wc->flush_work);
@@ -1342,7 +1363,7 @@ static void __writecache_endio_pmem(struct dm_writecache *wc, struct list_head *
 			wc->writeback_size--;
 			n_walked++;
 			if (unlikely(n_walked >= ENDIO_LATENCY)) {
-				writecache_commit_flushed(wc);
+				writecache_commit_flushed(wc, false);
 				wc_unlock(wc);
 				wc_lock(wc);
 				n_walked = 0;
@@ -1423,7 +1444,7 @@ static int writecache_endio_thread(void *data)
 			writecache_wait_for_ios(wc, READ);
 		}
 
-		writecache_commit_flushed(wc);
+		writecache_commit_flushed(wc, false);
 
 		wc_unlock(wc);
 	}
@@ -1766,10 +1787,10 @@ static int init_memory(struct dm_writecache *wc)
 		write_original_sector_seq_count(wc, &wc->entries[b], -1, -1);
 
 	writecache_flush_all_metadata(wc);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 	pmem_assign(sb(wc)->magic, cpu_to_le32(MEMORY_SUPERBLOCK_MAGIC));
 	writecache_flush_region(wc, &sb(wc)->magic, sizeof sb(wc)->magic);
-	writecache_commit_flushed(wc);
+	writecache_commit_flushed(wc, false);
 
 	return 0;
 }

drivers/md/dm-zoned-metadata.c

@@ -134,6 +134,7 @@ struct dmz_metadata {
 
 	sector_t		zone_bitmap_size;
 	unsigned int		zone_nr_bitmap_blocks;
+	unsigned int		zone_bits_per_mblk;
 
 	unsigned int		nr_bitmap_blocks;
 	unsigned int		nr_map_blocks;
@@ -1161,7 +1162,10 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
 
 	/* Init */
 	zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
-	zmd->zone_nr_bitmap_blocks = zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT;
+	zmd->zone_nr_bitmap_blocks =
+		max_t(sector_t, 1, zmd->zone_bitmap_size >> DMZ_BLOCK_SHIFT);
+	zmd->zone_bits_per_mblk = min_t(sector_t, dev->zone_nr_blocks,
+					DMZ_BLOCK_SIZE_BITS);
 
 	/* Allocate zone array */
 	zmd->zones = kcalloc(dev->nr_zones, sizeof(struct dm_zone), GFP_KERNEL);
@@ -1956,7 +1960,7 @@ int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone,
 		dmz_release_mblock(zmd, to_mblk);
 		dmz_release_mblock(zmd, from_mblk);
 
-		chunk_block += DMZ_BLOCK_SIZE_BITS;
+		chunk_block += zmd->zone_bits_per_mblk;
 	}
 
 	to_zone->weight = from_zone->weight;
@@ -2017,7 +2021,7 @@ int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Set bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_set_bits((unsigned long *)mblk->data, bit, nr_bits);
 		if (count) {
@@ -2096,7 +2100,7 @@ int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone,
 
 		/* Clear bits */
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 
 		count = dmz_clear_bits((unsigned long *)mblk->data,
 				       bit, nr_bits);
@@ -2156,6 +2160,7 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 {
 	struct dmz_mblock *mblk;
 	unsigned int bit, set_bit, nr_bits;
+	unsigned int zone_bits = zmd->zone_bits_per_mblk;
 	unsigned long *bitmap;
 	int n = 0;
 
@@ -2170,15 +2175,15 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone,
 		/* Get offset */
 		bitmap = (unsigned long *) mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zone_bits - bit);
 		if (set)
-			set_bit = find_next_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_bit(bitmap, zone_bits, bit);
 		else
-			set_bit = find_next_zero_bit(bitmap, DMZ_BLOCK_SIZE_BITS, bit);
+			set_bit = find_next_zero_bit(bitmap, zone_bits, bit);
 		dmz_release_mblock(zmd, mblk);
 
 		n += set_bit - bit;
-		if (set_bit < DMZ_BLOCK_SIZE_BITS)
+		if (set_bit < zone_bits)
 			break;
 
 		nr_blocks -= nr_bits;
@@ -2281,7 +2286,7 @@ static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone)
 		/* Count bits in this block */
 		bitmap = mblk->data;
 		bit = chunk_block & DMZ_BLOCK_MASK_BITS;
-		nr_bits = min(nr_blocks, DMZ_BLOCK_SIZE_BITS - bit);
+		nr_bits = min(nr_blocks, zmd->zone_bits_per_mblk - bit);
 		n += dmz_count_bits(bitmap, bit, nr_bits);
 
 		dmz_release_mblock(zmd, mblk);

drivers/md/dm.c

@@ -1859,6 +1859,7 @@ static void dm_init_normal_md_queue(struct mapped_device *md)
 	/*
 	 * Initialize aspects of queue that aren't relevant for blk-mq
 	 */
+	md->queue->backing_dev_info->congested_data = md;
 	md->queue->backing_dev_info->congested_fn = dm_any_congested;
 }
 
@@ -1949,7 +1950,12 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->queue)
 		goto bad;
 	md->queue->queuedata = md;
-	md->queue->backing_dev_info->congested_data = md;
+	/*
+	 * default to bio-based required ->make_request_fn until DM
+	 * table is loaded and md->type established. If request-based
+	 * table is loaded: blk-mq will override accordingly.
+	 */
+	blk_queue_make_request(md->queue, dm_make_request);
 
 	md->disk = alloc_disk_node(1, md->numa_node_id);
 	if (!md->disk)
@@ -2264,7 +2270,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 	case DM_TYPE_DAX_BIO_BASED:
 	case DM_TYPE_NVME_BIO_BASED:
 		dm_init_normal_md_queue(md);
-		blk_queue_make_request(md->queue, dm_make_request);
 		break;
 	case DM_TYPE_NONE:
 		WARN_ON_ONCE(true);

drivers/md/persistent-data/dm-space-map-common.c

@@ -380,6 +380,33 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 	return -ENOSPC;
 }
 
+int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
+	                         dm_block_t begin, dm_block_t end, dm_block_t *b)
+{
+	int r;
+	uint32_t count;
+
+	do {
+		r = sm_ll_find_free_block(new_ll, begin, new_ll->nr_blocks, b);
+		if (r)
+			break;
+
+		/* double check this block wasn't used in the old transaction */
+		if (*b >= old_ll->nr_blocks)
+			count = 0;
+		else {
+			r = sm_ll_lookup(old_ll, *b, &count);
+			if (r)
+				break;
+
+			if (count)
+				begin = *b + 1;
+		}
+	} while (count);
+
+	return r;
+}
+
 static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b,
 			int (*mutator)(void *context, uint32_t old, uint32_t *new),
 			void *context, enum allocation_event *ev)

drivers/md/persistent-data/dm-space-map-common.h

@@ -109,6 +109,8 @@ int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result);
 int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result);
 int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin,
 			  dm_block_t end, dm_block_t *result);
+int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll,
+	                         dm_block_t begin, dm_block_t end, dm_block_t *result);
 int sm_ll_insert(struct ll_disk *ll, dm_block_t b, uint32_t ref_count, enum allocation_event *ev);
 int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);
 int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev);

drivers/md/persistent-data/dm-space-map-disk.c

@@ -167,8 +167,10 @@ static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b)
 	enum allocation_event ev;
 	struct sm_disk *smd = container_of(sm, struct sm_disk, sm);
 
-	/* FIXME: we should loop round a couple of times */
-	r = sm_ll_find_free_block(&smd->old_ll, smd->begin, smd->old_ll.nr_blocks, b);
+	/*
+	 * Any block we allocate has to be free in both the old and current ll.
+	 */
+	r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, smd->begin, smd->ll.nr_blocks, b);
 	if (r)
 		return r;
 

drivers/md/persistent-data/dm-space-map-metadata.c

@@ -448,7 +448,10 @@ static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b)
 	enum allocation_event ev;
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
-	r = sm_ll_find_free_block(&smm->old_ll, smm->begin, smm->old_ll.nr_blocks, b);
+	/*
+	 * Any block we allocate has to be free in both the old and current ll.
+	 */
+	r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, smm->begin, smm->ll.nr_blocks, b);
 	if (r)
 		return r;