diff options
author | 2020-06-05 15:45:03 -0700 | |
---|---|---|
committer | 2020-06-05 15:45:03 -0700 | |
commit | b25c6644bfd3affd7d0127ce95c5c96c155a7515 (patch) | |
tree | 9ef9c0fe74a08b7baf3a3c3753368b0f481b581f /drivers/md | |
parent | Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi (diff) | |
parent | dm crypt: avoid truncating the logical block size (diff) | |
download | linux-b25c6644bfd3affd7d0127ce95c5c96c155a7515.tar.gz linux-b25c6644bfd3affd7d0127ce95c5c96c155a7515.tar.bz2 linux-b25c6644bfd3affd7d0127ce95c5c96c155a7515.zip |
Merge tag 'for-5.8/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
Pull device mapper updates from Mike Snitzer:
- The largest change for this cycle is the DM zoned target's metadata
version 2 feature that adds support for pairing regular block devices
with a zoned device to ease the performance impact associated with
finite random zones of zoned device.
The changes came in three batches: the first prepared for and then
added the ability to pair a single regular block device, the second
was a batch of fixes to improve zoned's reclaim heuristic, and the
third removed the limitation of only adding a single additional
regular block device to allow many devices.
Testing has shown linear scaling as more devices are added.
- Add new emulated block size (ebs) target that emulates a smaller
logical_block_size than a block device supports
The primary use-case is to emulate "512e" devices that have 512 byte
logical_block_size and 4KB physical_block_size. This is useful to
some legacy applications that otherwise wouldn't be able to be used
on 4K devices because they depend on issuing IO in 512 byte
granularity.
- Add discard interfaces to DM bufio. First consumer of the interface
is the dm-ebs target that makes heavy use of dm-bufio.
- Fix DM crypt's block queue_limits stacking to not truncate
logic_block_size.
- Add Documentation for DM integrity's status line.
- Switch DMDEBUG from a compile time config option to instead use
dynamic debug via pr_debug.
- Fix DM multipath target's hueristic for how it manages
"queue_if_no_path" state internally.
DM multipath now avoids disabling "queue_if_no_path" unless it is
actually needed (e.g. in response to configure timeout or explicit
"fail_if_no_path" message).
This fixes reports of spurious -EIO being reported back to userspace
application during fault tolerance testing with an NVMe backend.
Added various dynamic DMDEBUG messages to assist with debugging
queue_if_no_path in the future.
- Add a new DM multipath "Historical Service Time" Path Selector.
- Fix DM multipath's dm_blk_ioctl() to switch paths on IO error.
- Improve DM writecache target performance by using explicit cache
flushing for target's single-threaded usecase and a small cleanup to
remove unnecessary test in persistent_memory_claim.
- Other small cleanups in DM core, dm-persistent-data, and DM
integrity.
* tag 'for-5.8/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (62 commits)
dm crypt: avoid truncating the logical block size
dm mpath: add DM device name to Failing/Reinstating path log messages
dm mpath: enhance queue_if_no_path debugging
dm mpath: restrict queue_if_no_path state machine
dm mpath: simplify __must_push_back
dm zoned: check superblock location
dm zoned: prefer full zones for reclaim
dm zoned: select reclaim zone based on device index
dm zoned: allocate zone by device index
dm zoned: support arbitrary number of devices
dm zoned: move random and sequential zones into struct dmz_dev
dm zoned: per-device reclaim
dm zoned: add metadata pointer to struct dmz_dev
dm zoned: add device pointer to struct dm_zone
dm zoned: allocate temporary superblock for tertiary devices
dm zoned: convert to xarray
dm zoned: add a 'reserved' zone flag
dm zoned: improve logging messages for reclaim
dm zoned: avoid unnecessary device recalulation for secondary superblock
dm zoned: add debugging message for reading superblocks
...
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/Kconfig | 20 | ||||
-rw-r--r-- | drivers/md/Makefile | 3 | ||||
-rw-r--r-- | drivers/md/dm-bufio.c | 109 | ||||
-rw-r--r-- | drivers/md/dm-crypt.c | 80 | ||||
-rw-r--r-- | drivers/md/dm-ebs-target.c | 471 | ||||
-rw-r--r-- | drivers/md/dm-historical-service-time.c | 561 | ||||
-rw-r--r-- | drivers/md/dm-integrity.c | 6 | ||||
-rw-r--r-- | drivers/md/dm-log-writes.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-mpath.c | 123 | ||||
-rw-r--r-- | drivers/md/dm-path-selector.h | 2 | ||||
-rw-r--r-- | drivers/md/dm-queue-length.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-raid.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-raid1.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-service-time.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-stats.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-stripe.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-switch.c | 2 | ||||
-rw-r--r-- | drivers/md/dm-writecache.c | 42 | ||||
-rw-r--r-- | drivers/md/dm-zoned-metadata.c | 1046 | ||||
-rw-r--r-- | drivers/md/dm-zoned-reclaim.c | 210 | ||||
-rw-r--r-- | drivers/md/dm-zoned-target.c | 463 | ||||
-rw-r--r-- | drivers/md/dm-zoned.h | 113 | ||||
-rw-r--r-- | drivers/md/dm.c | 11 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-internal.h | 4 | ||||
-rw-r--r-- | drivers/md/persistent-data/dm-btree-spine.c | 6 |
25 files changed, 2650 insertions, 636 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index d6d5ab23c088..6665b56865b7 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -269,6 +269,7 @@ config DM_UNSTRIPED config DM_CRYPT tristate "Crypt target support" depends on BLK_DEV_DM + depends on (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n) select CRYPTO select CRYPTO_CBC select CRYPTO_ESSIV @@ -336,6 +337,14 @@ config DM_WRITECACHE The writecache target doesn't cache reads because reads are supposed to be cached in standard RAM. +config DM_EBS + tristate "Emulated block size target (EXPERIMENTAL)" + depends on BLK_DEV_DM + select DM_BUFIO + help + dm-ebs emulates smaller logical block size on backing devices + with larger ones (e.g. 512 byte sectors on 4K native disks). + config DM_ERA tristate "Era target (EXPERIMENTAL)" depends on BLK_DEV_DM @@ -443,6 +452,17 @@ config DM_MULTIPATH_ST If unsure, say N. +config DM_MULTIPATH_HST + tristate "I/O Path Selector based on historical service time" + depends on DM_MULTIPATH + help + This path selector is a dynamic load balancer which selects + the path expected to complete the incoming I/O in the shortest + time by comparing estimated service time (based on historical + service time). + + If unsure, say N. + config DM_DELAY tristate "I/O delaying target" depends on BLK_DEV_DM diff --git a/drivers/md/Makefile b/drivers/md/Makefile index d91a7edcd2ab..31840f95cd40 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -17,6 +17,7 @@ dm-thin-pool-y += dm-thin.o dm-thin-metadata.o dm-cache-y += dm-cache-target.o dm-cache-metadata.o dm-cache-policy.o \ dm-cache-background-tracker.o dm-cache-smq-y += dm-cache-policy-smq.o +dm-ebs-y += dm-ebs-target.o dm-era-y += dm-era-target.o dm-clone-y += dm-clone-target.o dm-clone-metadata.o dm-verity-y += dm-verity-target.o @@ -54,6 +55,7 @@ obj-$(CONFIG_DM_FLAKEY) += dm-flakey.o obj-$(CONFIG_DM_MULTIPATH) += dm-multipath.o dm-round-robin.o obj-$(CONFIG_DM_MULTIPATH_QL) += dm-queue-length.o obj-$(CONFIG_DM_MULTIPATH_ST) += dm-service-time.o +obj-$(CONFIG_DM_MULTIPATH_HST) += dm-historical-service-time.o obj-$(CONFIG_DM_SWITCH) += dm-switch.o obj-$(CONFIG_DM_SNAPSHOT) += dm-snapshot.o obj-$(CONFIG_DM_PERSISTENT_DATA) += persistent-data/ @@ -65,6 +67,7 @@ obj-$(CONFIG_DM_THIN_PROVISIONING) += dm-thin-pool.o obj-$(CONFIG_DM_VERITY) += dm-verity.o obj-$(CONFIG_DM_CACHE) += dm-cache.o obj-$(CONFIG_DM_CACHE_SMQ) += dm-cache-smq.o +obj-$(CONFIG_DM_EBS) += dm-ebs.o obj-$(CONFIG_DM_ERA) += dm-era.o obj-$(CONFIG_DM_CLONE) += dm-clone.o obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index d1786cfd7f22..6d1565021d74 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -256,12 +256,35 @@ static struct dm_buffer *__find(struct dm_bufio_client *c, sector_t block) if (b->block == block) return b; - n = (b->block < block) ? n->rb_left : n->rb_right; + n = block < b->block ? n->rb_left : n->rb_right; } return NULL; } +static struct dm_buffer *__find_next(struct dm_bufio_client *c, sector_t block) +{ + struct rb_node *n = c->buffer_tree.rb_node; + struct dm_buffer *b; + struct dm_buffer *best = NULL; + + while (n) { + b = container_of(n, struct dm_buffer, node); + + if (b->block == block) + return b; + + if (block <= b->block) { + n = n->rb_left; + best = b; + } else { + n = n->rb_right; + } + } + + return best; +} + static void __insert(struct dm_bufio_client *c, struct dm_buffer *b) { struct rb_node **new = &c->buffer_tree.rb_node, *parent = NULL; @@ -276,8 +299,8 @@ static void __insert(struct dm_bufio_client *c, struct dm_buffer *b) } parent = *new; - new = (found->block < b->block) ? - &((*new)->rb_left) : &((*new)->rb_right); + new = b->block < found->block ? + &found->node.rb_left : &found->node.rb_right; } rb_link_node(&b->node, parent, new); @@ -631,6 +654,19 @@ dmio: submit_bio(bio); } +static inline sector_t block_to_sector(struct dm_bufio_client *c, sector_t block) +{ + sector_t sector; + + if (likely(c->sectors_per_block_bits >= 0)) + sector = block << c->sectors_per_block_bits; + else + sector = block * (c->block_size >> SECTOR_SHIFT); + sector += c->start; + + return sector; +} + static void submit_io(struct dm_buffer *b, int rw, void (*end_io)(struct dm_buffer *, blk_status_t)) { unsigned n_sectors; @@ -639,11 +675,7 @@ static void submit_io(struct dm_buffer *b, int rw, void (*end_io)(struct dm_buff b->end_io = end_io; - if (likely(b->c->sectors_per_block_bits >= 0)) - sector = b->block << b->c->sectors_per_block_bits; - else - sector = b->block * (b->c->block_size >> SECTOR_SHIFT); - sector += b->c->start; + sector = block_to_sector(b->c, b->block); if (rw != REQ_OP_WRITE) { n_sectors = b->c->block_size >> SECTOR_SHIFT; @@ -1326,6 +1358,30 @@ int dm_bufio_issue_flush(struct dm_bufio_client *c) EXPORT_SYMBOL_GPL(dm_bufio_issue_flush); /* + * Use dm-io to send a discard request to flush the device. + */ +int dm_bufio_issue_discard(struct dm_bufio_client *c, sector_t block, sector_t count) +{ + struct dm_io_request io_req = { + .bi_op = REQ_OP_DISCARD, + .bi_op_flags = REQ_SYNC, + .mem.type = DM_IO_KMEM, + .mem.ptr.addr = NULL, + .client = c->dm_io, + }; + struct dm_io_region io_reg = { + .bdev = c->bdev, + .sector = block_to_sector(c, block), + .count = block_to_sector(c, count), + }; + + BUG_ON(dm_bufio_in_request()); + + return dm_io(&io_req, 1, &io_reg, NULL); +} +EXPORT_SYMBOL_GPL(dm_bufio_issue_discard); + +/* * We first delete any other buffer that may be at that new location. * * Then, we write the buffer to the original location if it was dirty. @@ -1401,6 +1457,14 @@ retry: } EXPORT_SYMBOL_GPL(dm_bufio_release_move); +static void forget_buffer_locked(struct dm_buffer *b) +{ + if (likely(!b->hold_count) && likely(!b->state)) { + __unlink_buffer(b); + __free_buffer_wake(b); + } +} + /* * Free the given buffer. * @@ -1414,15 +1478,36 @@ void dm_bufio_forget(struct dm_bufio_client *c, sector_t block) dm_bufio_lock(c); b = __find(c, block); - if (b && likely(!b->hold_count) && likely(!b->state)) { - __unlink_buffer(b); - __free_buffer_wake(b); - } + if (b) + forget_buffer_locked(b); dm_bufio_unlock(c); } EXPORT_SYMBOL_GPL(dm_bufio_forget); +void dm_bufio_forget_buffers(struct dm_bufio_client *c, sector_t block, sector_t n_blocks) +{ + struct dm_buffer *b; + sector_t end_block = block + n_blocks; + + while (block < end_block) { + dm_bufio_lock(c); + + b = __find_next(c, block); + if (b) { + block = b->block + 1; + forget_buffer_locked(b); + } + + dm_bufio_unlock(c); + + if (!b) + break; + } + +} +EXPORT_SYMBOL_GPL(dm_bufio_forget_buffers); + void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n) { c->minimum_buffers = n; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 3df90daba89e..000ddfab5ba0 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -34,7 +34,9 @@ #include <crypto/aead.h> #include <crypto/authenc.h> #include <linux/rtnetlink.h> /* for struct rtattr and RTA macros only */ +#include <linux/key-type.h> #include <keys/user-type.h> +#include <keys/encrypted-type.h> #include <linux/device-mapper.h> @@ -212,7 +214,7 @@ struct crypt_config { struct mutex bio_alloc_lock; u8 *authenc_key; /* space for keys in authenc() format (if used) */ - u8 key[0]; + u8 key[]; }; #define MIN_IOS 64 @@ -2215,12 +2217,47 @@ static bool contains_whitespace(const char *str) return false; } +static int set_key_user(struct crypt_config *cc, struct key *key) +{ + const struct user_key_payload *ukp; + + ukp = user_key_payload_locked(key); + if (!ukp) + return -EKEYREVOKED; + + if (cc->key_size != ukp->datalen) + return -EINVAL; + + memcpy(cc->key, ukp->data, cc->key_size); + + return 0; +} + +#if defined(CONFIG_ENCRYPTED_KEYS) || defined(CONFIG_ENCRYPTED_KEYS_MODULE) +static int set_key_encrypted(struct crypt_config *cc, struct key *key) +{ + const struct encrypted_key_payload *ekp; + + ekp = key->payload.data[0]; + if (!ekp) + return -EKEYREVOKED; + + if (cc->key_size != ekp->decrypted_datalen) + return -EINVAL; + + memcpy(cc->key, ekp->decrypted_data, cc->key_size); + + return 0; +} +#endif /* CONFIG_ENCRYPTED_KEYS */ + static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string) { char *new_key_string, *key_desc; int ret; + struct key_type *type; struct key *key; - const struct user_key_payload *ukp; + int (*set_key)(struct crypt_config *cc, struct key *key); /* * Reject key_string with whitespace. dm core currently lacks code for @@ -2236,16 +2273,26 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string if (!key_desc || key_desc == key_string || !strlen(key_desc + 1)) return -EINVAL; - if (strncmp(key_string, "logon:", key_desc - key_string + 1) && - strncmp(key_string, "user:", key_desc - key_string + 1)) + if (!strncmp(key_string, "logon:", key_desc - key_string + 1)) { + type = &key_type_logon; + set_key = set_key_user; + } else if (!strncmp(key_string, "user:", key_desc - key_string + 1)) { + type = &key_type_user; + set_key = set_key_user; +#if defined(CONFIG_ENCRYPTED_KEYS) || defined(CONFIG_ENCRYPTED_KEYS_MODULE) + } else if (!strncmp(key_string, "encrypted:", key_desc - key_string + 1)) { + type = &key_type_encrypted; + set_key = set_key_encrypted; +#endif + } else { return -EINVAL; + } new_key_string = kstrdup(key_string, GFP_KERNEL); if (!new_key_string) return -ENOMEM; - key = request_key(key_string[0] == 'l' ? &key_type_logon : &key_type_user, - key_desc + 1, NULL); + key = request_key(type, key_desc + 1, NULL); if (IS_ERR(key)) { kzfree(new_key_string); return PTR_ERR(key); @@ -2253,23 +2300,14 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string down_read(&key->sem); - ukp = user_key_payload_locked(key); - if (!ukp) { - up_read(&key->sem); - key_put(key); - kzfree(new_key_string); - return -EKEYREVOKED; - } - - if (cc->key_size != ukp->datalen) { + ret = set_key(cc, key); + if (ret < 0) { up_read(&key->sem); key_put(key); kzfree(new_key_string); - return -EINVAL; + return ret; } - memcpy(cc->key, ukp->data, cc->key_size); - up_read(&key->sem); key_put(key); @@ -2323,7 +2361,7 @@ static int get_key_size(char **key_string) return (*key_string[0] == ':') ? -EINVAL : strlen(*key_string) >> 1; } -#endif +#endif /* CONFIG_KEYS */ static int crypt_set_key(struct crypt_config *cc, char *key) { @@ -3274,7 +3312,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) limits->max_segment_size = PAGE_SIZE; limits->logical_block_size = - max_t(unsigned short, limits->logical_block_size, cc->sector_size); + max_t(unsigned, limits->logical_block_size, cc->sector_size); limits->physical_block_size = max_t(unsigned, limits->physical_block_size, cc->sector_size); limits->io_min = max_t(unsigned, limits->io_min, cc->sector_size); @@ -3282,7 +3320,7 @@ static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type crypt_target = { .name = "crypt", - .version = {1, 20, 0}, + .version = {1, 21, 0}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c new file mode 100644 index 000000000000..44451276f128 --- /dev/null +++ b/drivers/md/dm-ebs-target.c @@ -0,0 +1,471 @@ +/* + * Copyright (C) 2020 Red Hat GmbH + * + * This file is released under the GPL. + * + * Device-mapper target to emulate smaller logical block + * size on backing devices exposing (natively) larger ones. + * + * E.g. 512 byte sector emulation on 4K native disks. + */ + +#include "dm.h" +#include <linux/module.h> +#include <linux/workqueue.h> +#include <linux/dm-bufio.h> + +#define DM_MSG_PREFIX "ebs" + +static void ebs_dtr(struct dm_target *ti); + +/* Emulated block size context. */ +struct ebs_c { + struct dm_dev *dev; /* Underlying device to emulate block size on. */ + struct dm_bufio_client *bufio; /* Use dm-bufio for read and read-modify-write processing. */ + struct workqueue_struct *wq; /* Workqueue for ^ processing of bios. */ + struct work_struct ws; /* Work item used for ^. */ + struct bio_list bios_in; /* Worker bios input list. */ + spinlock_t lock; /* Guard bios input list above. */ + sector_t start; /* <start> table line argument, see ebs_ctr below. */ + unsigned int e_bs; /* Emulated block size in sectors exposed to upper layer. */ + unsigned int u_bs; /* Underlying block size in sectors retrievd from/set on lower layer device. */ + unsigned char block_shift; /* bitshift sectors -> blocks used in dm-bufio API. */ + bool u_bs_set:1; /* Flag to indicate underlying block size is set on table line. */ +}; + +static inline sector_t __sector_to_block(struct ebs_c *ec, sector_t sector) +{ + return sector >> ec->block_shift; +} + +static inline sector_t __block_mod(sector_t sector, unsigned int bs) +{ + return sector & (bs - 1); +} + +/* Return number of blocks for a bio, accounting for misalignement of start and end sectors. */ +static inline unsigned int __nr_blocks(struct ebs_c *ec, struct bio *bio) +{ + sector_t end_sector = __block_mod(bio->bi_iter.bi_sector, ec->u_bs) + bio_sectors(bio); + + return __sector_to_block(ec, end_sector) + (__block_mod(end_sector, ec->u_bs) ? 1 : 0); +} + +static inline bool __ebs_check_bs(unsigned int bs) +{ + return bs && is_power_of_2(bs); +} + +/* + * READ/WRITE: + * + * copy blocks between bufio blocks and bio vector's (partial/overlapping) pages. + */ +static int __ebs_rw_bvec(struct ebs_c *ec, int rw, struct bio_vec *bv, struct bvec_iter *iter) +{ + int r = 0; + unsigned char *ba, *pa; + unsigned int cur_len; + unsigned int bv_len = bv->bv_len; + unsigned int buf_off = to_bytes(__block_mod(iter->bi_sector, ec->u_bs)); + sector_t block = __sector_to_block(ec, iter->bi_sector); + struct dm_buffer *b; + + if (unlikely(!bv->bv_page || !bv_len)) + return -EIO; + + pa = page_address(bv->bv_page) + bv->bv_offset; + + /* Handle overlapping page <-> blocks */ + while (bv_len) { + cur_len = min(dm_bufio_get_block_size(ec->bufio) - buf_off, bv_len); + + /* Avoid reading for writes in case bio vector's page overwrites block completely. */ + if (rw == READ || buf_off || bv_len < dm_bufio_get_block_size(ec->bufio)) + ba = dm_bufio_read(ec->bufio, block, &b); + else + ba = dm_bufio_new(ec->bufio, block, &b); + + if (unlikely(IS_ERR(ba))) { + /* + * Carry on with next buffer, if any, to issue all possible + * data but return error. + */ + r = PTR_ERR(ba); + } else { + /* Copy data to/from bio to buffer if read/new was successful above. */ + ba += buf_off; + if (rw == READ) { + memcpy(pa, ba, cur_len); + flush_dcache_page(bv->bv_page); + } else { + flush_dcache_page(bv->bv_page); + memcpy(ba, pa, cur_len); + dm_bufio_mark_partial_buffer_dirty(b, buf_off, buf_off + cur_len); + } + + dm_bufio_release(b); + } + + pa += cur_len; + bv_len -= cur_len; + buf_off = 0; + block++; + } + + return r; +} + +/* READ/WRITE: iterate bio vector's copying between (partial) pages and bufio blocks. */ +static int __ebs_rw_bio(struct ebs_c *ec, int rw, struct bio *bio) +{ + int r = 0, rr; + struct bio_vec bv; + struct bvec_iter iter; + + bio_for_each_bvec(bv, bio, iter) { + rr = __ebs_rw_bvec(ec, rw, &bv, &iter); + if (rr) + r = rr; + } + + return r; +} + +/* + * Discard bio's blocks, i.e. pass discards down. + * + * Avoid discarding partial blocks at beginning and end; + * return 0 in case no blocks can be discarded as a result. + */ +static int __ebs_discard_bio(struct ebs_c *ec, struct bio *bio) +{ + sector_t block, blocks, sector = bio->bi_iter.bi_sector; + + block = __sector_to_block(ec, sector); + blocks = __nr_blocks(ec, bio); + + /* + * Partial first underlying block (__nr_blocks() may have + * resulted in one block). + */ + if (__block_mod(sector, ec->u_bs)) { + block++; + blocks--; + } + + /* Partial last underlying block if any. */ + if (blocks && __block_mod(bio_end_sector(bio), ec->u_bs)) + blocks--; + + return blocks ? dm_bufio_issue_discard(ec->bufio, block, blocks) : 0; +} + +/* Release blocks them from the bufio cache. */ +static void __ebs_forget_bio(struct ebs_c *ec, struct bio *bio) +{ + sector_t blocks, sector = bio->bi_iter.bi_sector; + + blocks = __nr_blocks(ec, bio); + + dm_bufio_forget_buffers(ec->bufio, __sector_to_block(ec, sector), blocks); +} + +/* Worker funtion to process incoming bios. */ +static void __ebs_process_bios(struct work_struct *ws) +{ + int r; + bool write = false; + sector_t block1, block2; + struct ebs_c *ec = container_of(ws, struct ebs_c, ws); + struct bio *bio; + struct bio_list bios; + + bio_list_init(&bios); + + spin_lock_irq(&ec->lock); + bios = ec->bios_in; + bio_list_init(&ec->bios_in); + spin_unlock_irq(&ec->lock); + + /* Prefetch all read and any mis-aligned write buffers */ + bio_list_for_each(bio, &bios) { + block1 = __sector_to_block(ec, bio->bi_iter.bi_sector); + if (bio_op(bio) == REQ_OP_READ) + dm_bufio_prefetch(ec->bufio, block1, __nr_blocks(ec, bio)); + else if (bio_op(bio) == REQ_OP_WRITE && !(bio->bi_opf & REQ_PREFLUSH)) { + block2 = __sector_to_block(ec, bio_end_sector(bio)); + if (__block_mod(bio->bi_iter.bi_sector, ec->u_bs)) + dm_bufio_prefetch(ec->bufio, block1, 1); + if (__block_mod(bio_end_sector(bio), ec->u_bs) && block2 != block1) + dm_bufio_prefetch(ec->bufio, block2, 1); + } + } + + bio_list_for_each(bio, &bios) { + r = -EIO; + if (bio_op(bio) == REQ_OP_READ) + r = __ebs_rw_bio(ec, READ, bio); + else if (bio_op(bio) == REQ_OP_WRITE) { + write = true; + r = __ebs_rw_bio(ec, WRITE, bio); + } else if (bio_op(bio) == REQ_OP_DISCARD) { + __ebs_forget_bio(ec, bio); + r = __ebs_discard_bio(ec, bio); + } + + if (r < 0) + bio->bi_status = errno_to_blk_status(r); + } + + /* + * We write dirty buffers after processing I/O on them + * but before we endio thus addressing REQ_FUA/REQ_SYNC. + */ + r = write ? dm_bufio_write_dirty_buffers(ec->bufio) : 0; + + while ((bio = bio_list_pop(&bios))) { + /* Any other request is endioed. */ + if (unlikely(r && bio_op(bio) == REQ_OP_WRITE)) + bio_io_error(bio); + else + bio_endio(bio); + } +} + +/* + * Construct an emulated block size mapping: <dev_path> <offset> <ebs> [<ubs>] + * + * <dev_path>: path of the underlying device + * <offset>: offset in 512 bytes sectors into <dev_path> + * <ebs>: emulated block size in units of 512 bytes exposed to the upper layer + * [<ubs>]: underlying block size in units of 512 bytes imposed on the lower layer; + * optional, if not supplied, retrieve logical block size from underlying device + */ +static int ebs_ctr(struct dm_target *ti, unsigned int argc, char **argv) +{ + int r; + unsigned short tmp1; + unsigned long long tmp; + char dummy; + struct ebs_c *ec; + + if (argc < 3 || argc > 4) { + ti->error = "Invalid argument count"; + return -EINVAL; + } + + ec = ti->private = kzalloc(sizeof(*ec), GFP_KERNEL); + if (!ec) { + ti->error = "Cannot allocate ebs context"; + return -ENOMEM; + } + + r = -EINVAL; + if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1 || + tmp != (sector_t)tmp || + (sector_t)tmp >= ti->len) { + ti->error = "Invalid device offset sector"; + goto bad; + } + ec->start = tmp; + + if (sscanf(argv[2], "%hu%c", &tmp1, &dummy) != 1 || + !__ebs_check_bs(tmp1) || + to_bytes(tmp1) > PAGE_SIZE) { + ti->error = "Invalid emulated block size"; + goto bad; + } + ec->e_bs = tmp1; + + if (argc > 3) { + if (sscanf(argv[3], "%hu%c", &tmp1, &dummy) != 1 || !__ebs_check_bs(tmp1)) { + ti->error = "Invalid underlying block size"; + goto bad; + } + ec->u_bs = tmp1; + ec->u_bs_set = true; + } else + ec->u_bs_set = false; + + r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &ec->dev); + if (r) { + ti->error = "Device lookup failed"; + ec->dev = NULL; + goto bad; + } + + r = -EINVAL; + if (!ec->u_bs_set) { + ec->u_bs = to_sector(bdev_logical_block_size(ec->dev->bdev)); + if (!__ebs_check_bs(ec->u_bs)) { + ti->error = "Invalid retrieved underlying block size"; + goto bad; + } + } + + if (!ec->u_bs_set && ec->e_bs == ec->u_bs) + DMINFO("Emulation superfluous: emulated equal to underlying block size"); + + if (__block_mod(ec->start, ec->u_bs)) { + ti->error = "Device offset must be multiple of underlying block size"; + goto bad; + } + + ec->bufio = dm_bufio_client_create(ec->dev->bdev, to_bytes(ec->u_bs), 1, 0, NULL, NULL); + if (IS_ERR(ec->bufio)) { + ti->error = "Cannot create dm bufio client"; + r = PTR_ERR(ec->bufio); + ec->bufio = NULL; + goto bad; + } + + ec->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM); + if (!ec->wq) { + ti->error = "Cannot create dm-" DM_MSG_PREFIX " workqueue"; + r = -ENOMEM; + goto bad; + } + + ec->block_shift = __ffs(ec->u_bs); + INIT_WORK(&ec->ws, &__ebs_process_bios); + bio_list_init(&ec->bios_in); + spin_lock_init(&ec->lock); + + ti->num_flush_bios = 1; + ti->num_discard_bios = 1; + ti->num_secure_erase_bios = 0; + ti->num_write_same_bios = 0; + ti->num_write_zeroes_bios = 0; + return 0; +bad: + ebs_dtr(ti); + return r; +} + +static void ebs_dtr(struct dm_target *ti) +{ + struct ebs_c *ec = ti->private; + + if (ec->wq) + destroy_workqueue(ec->wq); + if (ec->bufio) + dm_bufio_client_destroy(ec->bufio); + if (ec->dev) + dm_put_device(ti, ec->dev); + kfree(ec); +} + +static int ebs_map(struct dm_target *ti, struct bio *bio) +{ + struct ebs_c *ec = ti->private; + + bio_set_dev(bio, ec->dev->bdev); + bio->bi_iter.bi_sector = ec->start + dm_target_offset(ti, bio->bi_iter.bi_sector); + + if (unlikely(bio->bi_opf & REQ_OP_FLUSH)) + return DM_MAPIO_REMAPPED; + /* + * Only queue for bufio processing in case of partial or overlapping buffers + * -or- + * emulation with ebs == ubs aiming for tests of dm-bufio overhead. + */ + if (likely(__block_mod(bio->bi_iter.bi_sector, ec->u_bs) || + __block_mod(bio_end_sector(bio), ec->u_bs) || + ec->e_bs == ec->u_bs)) { + spin_lock_irq(&ec->lock); + bio_list_add(&ec->bios_in, bio); + spin_unlock_irq(&ec->lock); + + queue_work(ec->wq, &ec->ws); + + return DM_MAPIO_SUBMITTED; + } + + /* Forget any buffer content relative to this direct backing device I/O. */ + __ebs_forget_bio(ec, bio); + + return DM_MAPIO_REMAPPED; +} + +static void ebs_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) +{ + struct ebs_c *ec = ti->private; + + switch (type) { + case STATUSTYPE_INFO: + *result = '\0'; + break; + case STATUSTYPE_TABLE: + snprintf(result, maxlen, ec->u_bs_set ? "%s %llu %u %u" : "%s %llu %u", + ec->dev->name, (unsigned long long) ec->start, ec->e_bs, ec->u_bs); + break; + } +} + +static int ebs_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) +{ + struct ebs_c *ec = ti->private; + struct dm_dev *dev = ec->dev; + + /* + * Only pass ioctls through if the device sizes match exactly. + */ + *bdev = dev->bdev; + return !!(ec->start || ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT); +} + +static void ebs_io_hints(struct dm_target *ti, struct queue_limits *limits) +{ + struct ebs_c *ec = ti->private; + + limits->logical_block_size = to_bytes(ec->e_bs); + limits->physical_block_size = to_bytes(ec->u_bs); + limits->alignment_offset = limits->physical_block_size; + blk_limits_io_min(limits, limits->logical_block_size); +} + +static int ebs_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct ebs_c *ec = ti->private; + + return fn(ti, ec->dev, ec->start, ti->len, data); +} + +static struct target_type ebs_target = { + .name = "ebs", + .version = {1, 0, 1}, + .features = DM_TARGET_PASSES_INTEGRITY, + .module = THIS_MODULE, + .ctr = ebs_ctr, + .dtr = ebs_dtr, + .map = ebs_map, + .status = ebs_status, + .io_hints = ebs_io_hints, + .prepare_ioctl = ebs_prepare_ioctl, + .iterate_devices = ebs_iterate_devices, +}; + +static int __init dm_ebs_init(void) +{ + int r = dm_register_target(&ebs_target); + + if (r < 0) + DMERR("register failed %d", r); + + return r; +} + +static void dm_ebs_exit(void) +{ + dm_unregister_target(&ebs_target); +} + +module_init(dm_ebs_init); +module_exit(dm_ebs_exit); + +MODULE_AUTHOR("Heinz Mauelshagen <dm-devel@redhat.com>"); +MODULE_DESCRIPTION(DM_NAME " emulated block size target"); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-historical-service-time.c b/drivers/md/dm-historical-service-time.c new file mode 100644 index 000000000000..186f91e2752c --- /dev/null +++ b/drivers/md/dm-historical-service-time.c @@ -0,0 +1,561 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Historical Service Time + * + * Keeps a time-weighted exponential moving average of the historical + * service time. Estimates future service time based on the historical + * service time and the number of outstanding requests. + * + * Marks paths stale if they have not finished within hst * + * num_paths. If a path is stale and unused, we will send a single + * request to probe in case the path has improved. This situation + * generally arises if the path is so much worse than others that it + * will never have the best estimated service time, or if the entire + * multipath device is unused. If a path is stale and in use, limit the + * number of requests it can receive with the assumption that the path + * has become degraded. + * + * To avoid repeatedly calculating exponents for time weighting, times + * are split into HST_WEIGHT_COUNT buckets each (1 >> HST_BUCKET_SHIFT) + * ns, and the weighting is pre-calculated. + * + */ + +#include "dm.h" +#include "dm-path-selector.h" + +#include <linux/blkdev.h> +#include <linux/slab.h> +#include <linux/module.h> + + +#define DM_MSG_PREFIX "multipath historical-service-time" +#define HST_MIN_IO 1 +#define HST_VERSION "0.1.1" + +#define HST_FIXED_SHIFT 10 /* 10 bits of decimal precision */ +#define HST_FIXED_MAX (ULLONG_MAX >> HST_FIXED_SHIFT) +#define HST_FIXED_1 (1 << HST_FIXED_SHIFT) +#define HST_FIXED_95 972 +#define HST_MAX_INFLIGHT HST_FIXED_1 +#define HST_BUCKET_SHIFT 24 /* Buckets are ~ 16ms */ +#define HST_WEIGHT_COUNT 64ULL + +struct selector { + struct list_head valid_paths; + struct list_head failed_paths; + int valid_count; + spinlock_t lock; + + unsigned int weights[HST_WEIGHT_COUNT]; + unsigned int threshold_multiplier; +}; + +struct path_info { + struct list_head list; + struct dm_path *path; + unsigned int repeat_count; + + spinlock_t lock; + + u64 historical_service_time; /* Fixed point */ + + u64 stale_after; + u64 last_finish; + + u64 outstanding; +}; + +/** + * fixed_power - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. + * + * (see: kernel/sched/loadavg.c) + */ +static u64 fixed_power(u64 x, unsigned int frac_bits, unsigned int n) +{ + unsigned long result = 1UL << frac_bits; + + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + } + + return result; +} + +/* + * Calculate the next value of an exponential moving average + * a_1 = a_0 * e + a * (1 - e) + * + * @last: [0, ULLONG_MAX >> HST_FIXED_SHIFT] + * @next: [0, ULLONG_MAX >> HST_FIXED_SHIFT] + * @weight: [0, HST_FIXED_1] + * + * Note: + * To account for multiple periods in the same calculation, + * a_n = a_0 * e^n + a * (1 - e^n), + * so call fixed_ema(last, next, pow(weight, N)) + */ +static u64 fixed_ema(u64 last, u64 next, u64 weight) +{ + last *= weight; + last += next * (HST_FIXED_1 - weight); + last += 1ULL << (HST_FIXED_SHIFT - 1); + return last >> HST_FIXED_SHIFT; +} + +static struct selector *alloc_selector(void) +{ + struct selector *s = kmalloc(sizeof(*s), GFP_KERNEL); + + if (s) { + INIT_LIST_HEAD(&s->valid_paths); + INIT_LIST_HEAD(&s->failed_paths); + spin_lock_init(&s->lock); + s->valid_count = 0; + } + + return s; +} + +/* + * Get the weight for a given time span. + */ +static u64 hst_weight(struct path_selector *ps, u64 delta) +{ + struct selector *s = ps->context; + int bucket = clamp(delta >> HST_BUCKET_SHIFT, 0ULL, + HST_WEIGHT_COUNT - 1); + + return s->weights[bucket]; +} + +/* + * Set up the weights array. + * + * weights[len-1] = 0 + * weights[n] = base ^ (n + 1) + */ +static void hst_set_weights(struct path_selector *ps, unsigned int base) +{ + struct selector *s = ps->context; + int i; + + if (base >= HST_FIXED_1) + return; + + for (i = 0; i < HST_WEIGHT_COUNT - 1; i++) + s->weights[i] = fixed_power(base, HST_FIXED_SHIFT, i + 1); + s->weights[HST_WEIGHT_COUNT - 1] = 0; +} + +static int hst_create(struct path_selector *ps, unsigned int argc, char **argv) +{ + struct selector *s; + unsigned int base_weight = HST_FIXED_95; + unsigned int threshold_multiplier = 0; + char dummy; + + /* + * Arguments: [<base_weight> [<threshold_multiplier>]] + * <base_weight>: Base weight for ema [0, 1024) 10-bit fixed point. A + * value of 0 will completely ignore any history. + * If not given, default (HST_FIXED_95) is used. + * <threshold_multiplier>: Minimum threshold multiplier for paths to + * be considered different. That is, a path is + * considered different iff (p1 > N * p2) where p1 + * is the path with higher service time. A threshold + * of 1 or 0 has no effect. Defaults to 0. + */ + if (argc > 2) + return -EINVAL; + + if (argc && (sscanf(argv[0], "%u%c", &base_weight, &dummy) != 1 || + base_weight >= HST_FIXED_1)) { + return -EINVAL; + } + + if (argc > 1 && (sscanf(argv[1], "%u%c", + &threshold_multiplier, &dummy) != 1)) { + return -EINVAL; + } + + s = alloc_selector(); + if (!s) + return -ENOMEM; + + ps->context = s; + + hst_set_weights(ps, base_weight); + s->threshold_multiplier = threshold_multiplier; + return 0; +} + +static void free_paths(struct list_head *paths) +{ + struct path_info *pi, *next; + + list_for_each_entry_safe(pi, next, paths, list) { + list_del(&pi->list); + kfree(pi); + } +} + +static void hst_destroy(struct path_selector *ps) +{ + struct selector *s = ps->context; + + free_paths(&s->valid_paths); + free_paths(&s->failed_paths); + kfree(s); + ps->context = NULL; +} + +static int hst_status(struct path_selector *ps, struct dm_path *path, + status_type_t type, char *result, unsigned int maxlen) +{ + unsigned int sz = 0; + struct path_info *pi; + + if (!path) { + struct selector *s = ps->context; + + DMEMIT("2 %u %u ", s->weights[0], s->threshold_multiplier); + } else { + pi = path->pscontext; + + switch (type) { + case STATUSTYPE_INFO: + DMEMIT("%llu %llu %llu ", pi->historical_service_time, + pi->outstanding, pi->stale_after); + break; + case STATUSTYPE_TABLE: + DMEMIT("0 "); + break; + } + } + + return sz; +} + +static int hst_add_path(struct path_selector *ps, struct dm_path *path, + int argc, char **argv, char **error) +{ + struct selector *s = ps->context; + struct path_info *pi; + unsigned int repeat_count = HST_MIN_IO; + char dummy; + unsigned long flags; + + /* + * Arguments: [<repeat_count>] + * <repeat_count>: The number of I/Os before switching path. + * If not given, default (HST_MIN_IO) is used. + */ + if (argc > 1) { + *error = "historical-service-time ps: incorrect number of arguments"; + return -EINVAL; + } + + if (argc && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) { + *error = "historical-service-time ps: invalid repeat count"; + return -EINVAL; + } + + /* allocate the path */ + pi = kmalloc(sizeof(*pi), GFP_KERNEL); + if (!pi) { + *error = "historical-service-time ps: Error allocating path context"; + return -ENOMEM; + } + + pi->path = path; + pi->repeat_count = repeat_count; + + pi->historical_service_time = HST_FIXED_1; + + spin_lock_init(&pi->lock); + pi->outstanding = 0; + + pi->stale_after = 0; + pi->last_finish = 0; + + path->pscontext = pi; + + spin_lock_irqsave(&s->lock, flags); + list_add_tail(&pi->list, &s->valid_paths); + s->valid_count++; + spin_unlock_irqrestore(&s->lock, flags); + + return 0; +} + +static void hst_fail_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + unsigned long flags; + + spin_lock_irqsave(&s->lock, flags); + list_move(&pi->list, &s->failed_paths); + s->valid_count--; + spin_unlock_irqrestore(&s->lock, flags); +} + +static int hst_reinstate_path(struct path_selector *ps, struct dm_path *path) +{ + struct selector *s = ps->context; + struct path_info *pi = path->pscontext; + unsigned long flags; + + spin_lock_irqsave(&s->lock, flags); + list_move_tail(&pi->list, &s->valid_paths); + s->valid_count++; + spin_unlock_irqrestore(&s->lock, flags); + + return 0; +} + +static void hst_fill_compare(struct path_info *pi, u64 *hst, + u64 *out, u64 *stale) +{ + unsigned long flags; + + spin_lock_irqsave(&pi->lock, flags); + *hst = pi->historical_service_time; + *out = pi->outstanding; + *stale = pi->stale_after; + spin_unlock_irqrestore(&pi->lock, flags); +} + +/* + * Compare the estimated service time of 2 paths, pi1 and pi2, + * for the incoming I/O. + * + * Returns: + * < 0 : pi1 is better + * 0 : no difference between pi1 and pi2 + * > 0 : pi2 is better + * + */ +static long long hst_compare(struct path_info *pi1, struct path_info *pi2, + u64 time_now, struct path_selector *ps) +{ + struct selector *s = ps->context; + u64 hst1, hst2; + long long out1, out2, stale1, stale2; + int pi2_better, over_threshold; + + hst_fill_compare(pi1, &hst1, &out1, &stale1); + hst_fill_compare(pi2, &hst2, &out2, &stale2); + + /* Check here if estimated latency for two paths are too similar. + * If this is the case, we skip extra calculation and just compare + * outstanding requests. In this case, any unloaded paths will + * be preferred. + */ + if (hst1 > hst2) + over_threshold = hst1 > (s->threshold_multiplier * hst2); + else + over_threshold = hst2 > (s->threshold_multiplier * hst1); + + if (!over_threshold) + return out1 - out2; + + /* + * If an unloaded path is stale, choose it. If both paths are unloaded, + * choose path that is the most stale. + * (If one path is loaded, choose the other) + */ + if ((!out1 && stale1 < time_now) || (!out2 && stale2 < time_now) || + (!out1 && !out2)) + return (!out2 * stale1) - (!out1 * stale2); + + /* Compare estimated service time. If outstanding is the same, we + * don't need to multiply + */ + if (out1 == out2) { + pi2_better = hst1 > hst2; + } else { + /* Potential overflow with out >= 1024 */ + if (unlikely(out1 >= HST_MAX_INFLIGHT || + out2 >= HST_MAX_INFLIGHT)) { + /* If over 1023 in-flights, we may overflow if hst + * is at max. (With this shift we still overflow at + * 1048576 in-flights, which is high enough). + */ + hst1 >>= HST_FIXED_SHIFT; + hst2 >>= HST_FIXED_SHIFT; + } + pi2_better = (1 + out1) * hst1 > (1 + out2) * hst2; + } + + /* In the case that the 'winner' is stale, limit to equal usage. */ + if (pi2_better) { + if (stale2 < time_now) + return out1 - out2; + return 1; + } + if (stale1 < time_now) + return out1 - out2; + return -1; +} + +static struct dm_path *hst_select_path(struct path_selector *ps, + size_t nr_bytes) +{ + struct selector *s = ps->context; + struct path_info *pi = NULL, *best = NULL; + u64 time_now = sched_clock(); + struct dm_path *ret = NULL; + unsigned long flags; + + spin_lock_irqsave(&s->lock, flags); + if (list_empty(&s->valid_paths)) + goto out; + + list_for_each_entry(pi, &s->valid_paths, list) { + if (!best || (hst_compare(pi, best, time_now, ps) < 0)) + best = pi; + } + + if (!best) + goto out; + + /* Move last used path to end (least preferred in case of ties) */ + list_move_tail(&best->list, &s->valid_paths); + + ret = best->path; + +out: + spin_unlock_irqrestore(&s->lock, flags); + return ret; +} + +static int hst_start_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes) +{ + struct path_info *pi = path->pscontext; + unsigned long flags; + + spin_lock_irqsave(&pi->lock, flags); + pi->outstanding++; + spin_unlock_irqrestore(&pi->lock, flags); + + return 0; +} + +static u64 path_service_time(struct path_info *pi, u64 start_time) +{ + u64 sched_now = ktime_get_ns(); + + /* if a previous disk request has finished after this IO was + * sent to the hardware, pretend the submission happened + * serially. + */ + 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)) + return 0; + + return sched_now - start_time; +} + +static int hst_end_io(struct path_selector *ps, struct dm_path *path, + size_t nr_bytes, u64 start_time) +{ + struct path_info *pi = path->pscontext; + struct selector *s = ps->context; + unsigned long flags; + u64 st; + + spin_lock_irqsave(&pi->lock, flags); + + st = path_service_time(pi, start_time); + pi->outstanding--; + pi->historical_service_time = + fixed_ema(pi->historical_service_time, + min(st * HST_FIXED_1, HST_FIXED_MAX), + hst_weight(ps, st)); + + /* + * On request end, mark path as fresh. If a path hasn't + * finished any requests within the fresh period, the estimated + * service time is considered too optimistic and we limit the + * maximum requests on that path. + */ + pi->stale_after = pi->last_finish + + (s->valid_count * (pi->historical_service_time >> HST_FIXED_SHIFT)); + + spin_unlock_irqrestore(&pi->lock, flags); + + return 0; +} + +static struct path_selector_type hst_ps = { + .name = "historical-service-time", + .module = THIS_MODULE, + .table_args = 1, + .info_args = 3, + .create = hst_create, + .destroy = hst_destroy, + .status = hst_status, + .add_path = hst_add_path, + .fail_path = hst_fail_path, + .reinstate_path = hst_reinstate_path, + .select_path = hst_select_path, + .start_io = hst_start_io, + .end_io = hst_end_io, +}; + +static int __init dm_hst_init(void) +{ + int r = dm_register_path_selector(&hst_ps); + + if (r < 0) + DMERR("register failed %d", r); + + DMINFO("version " HST_VERSION " loaded"); + + return r; +} + +static void __exit dm_hst_exit(void) +{ + int r = dm_unregister_path_selector(&hst_ps); + + if (r < 0) + DMERR("unregister failed %d", r); +} + +module_init(dm_hst_init); +module_exit(dm_hst_exit); + +MODULE_DESCRIPTION(DM_NAME " measured service time oriented path selector"); +MODULE_AUTHOR("Khazhismel Kumykov <khazhy@google.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 84cb04904fab..81dc5ff08909 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -92,7 +92,7 @@ struct journal_entry { } s; __u64 sector; } u; - commit_id_t last_bytes[0]; + commit_id_t last_bytes[]; /* __u8 tag[0]; */ }; @@ -1553,8 +1553,6 @@ static void integrity_metadata(struct work_struct *w) char checksums_onstack[max((size_t)HASH_MAX_DIGESTSIZE, MAX_TAG_SIZE)]; sector_t sector; unsigned sectors_to_process; - sector_t save_metadata_block; - unsigned save_metadata_offset; if (unlikely(ic->mode == 'R')) goto skip_io; @@ -1605,8 +1603,6 @@ static void integrity_metadata(struct work_struct *w) goto skip_io; } - save_metadata_block = dio->metadata_block; - save_metadata_offset = dio->metadata_offset; sector = dio->range.logical_sector; sectors_to_process = dio->range.n_sectors; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 8ea20b56b4d6..e3d35c6c9f71 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -127,7 +127,7 @@ struct pending_block { char *data; u32 datalen; struct list_head list; - struct bio_vec vecs[0]; + struct bio_vec vecs[]; }; struct per_bio_data { diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 3e500098132f..78cff42d987e 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -439,7 +439,7 @@ failed: } /* - * dm_report_EIO() is a macro instead of a function to make pr_debug() + * dm_report_EIO() is a macro instead of a function to make pr_debug_ratelimited() * report the function name and line number of the function from which * it has been invoked. */ @@ -447,43 +447,25 @@ failed: do { \ struct mapped_device *md = dm_table_get_md((m)->ti->table); \ \ - pr_debug("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d\n", \ - dm_device_name(md), \ - test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags), \ - test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags), \ - dm_noflush_suspending((m)->ti)); \ + DMDEBUG_LIMIT("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d", \ + dm_device_name(md), \ + test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags), \ + test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags), \ + dm_noflush_suspending((m)->ti)); \ } while (0) /* * Check whether bios must be queued in the device-mapper core rather * than here in the target. - * - * If MPATHF_QUEUE_IF_NO_PATH and MPATHF_SAVED_QUEUE_IF_NO_PATH hold - * the same value then we are not between multipath_presuspend() - * and multipath_resume() calls and we have no need to check - * for the DMF_NOFLUSH_SUSPENDING flag. */ -static bool __must_push_back(struct multipath *m, unsigned long flags) +static bool __must_push_back(struct multipath *m) { - return ((test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) != - test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &flags)) && - dm_noflush_suspending(m->ti)); + return dm_noflush_suspending(m->ti); } -/* - * Following functions use READ_ONCE to get atomic access to - * all m->flags to avoid taking spinlock - */ static bool must_push_back_rq(struct multipath *m) { - unsigned long flags = READ_ONCE(m->flags); - return test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) || __must_push_back(m, flags); -} - -static bool must_push_back_bio(struct multipath *m) -{ - unsigned long flags = READ_ONCE(m->flags); - return __must_push_back(m, flags); + return test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags) || __must_push_back(m); } /* @@ -567,7 +549,8 @@ static void multipath_release_clone(struct request *clone, if (pgpath && pgpath->pg->ps.type->end_io) pgpath->pg->ps.type->end_io(&pgpath->pg->ps, &pgpath->path, - mpio->nr_bytes); + mpio->nr_bytes, + clone->io_start_time_ns); } blk_put_request(clone); @@ -619,7 +602,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, return DM_MAPIO_SUBMITTED; if (!pgpath) { - if (must_push_back_bio(m)) + if (__must_push_back(m)) return DM_MAPIO_REQUEUE; dm_report_EIO(m); return DM_MAPIO_KILL; @@ -709,15 +692,38 @@ static void process_queued_bios(struct work_struct *work) * If we run out of usable paths, should we queue I/O or error it? */ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path, - bool save_old_value) + bool save_old_value, const char *caller) { unsigned long flags; + bool queue_if_no_path_bit, saved_queue_if_no_path_bit; + const char *dm_dev_name = dm_device_name(dm_table_get_md(m->ti->table)); + + DMDEBUG("%s: %s caller=%s queue_if_no_path=%d save_old_value=%d", + dm_dev_name, __func__, caller, queue_if_no_path, save_old_value); spin_lock_irqsave(&m->lock, flags); - assign_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags, - (save_old_value && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) || - (!save_old_value && queue_if_no_path)); + + queue_if_no_path_bit = test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags); + saved_queue_if_no_path_bit = test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags); + + if (save_old_value) { + if (unlikely(!queue_if_no_path_bit && saved_queue_if_no_path_bit)) { + DMERR("%s: QIFNP disabled but saved as enabled, saving again loses state, not saving!", + dm_dev_name); + } else + assign_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags, queue_if_no_path_bit); + } else if (!queue_if_no_path && saved_queue_if_no_path_bit) { + /* due to "fail_if_no_path" message, need to honor it. */ + clear_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags); + } assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags, queue_if_no_path); + + DMDEBUG("%s: after %s changes; QIFNP = %d; SQIFNP = %d; DNFS = %d", + dm_dev_name, __func__, + test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags), + test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags), + dm_noflush_suspending(m->ti)); + spin_unlock_irqrestore(&m->lock, flags); if (!queue_if_no_path) { @@ -738,7 +744,7 @@ static void queue_if_no_path_timeout_work(struct timer_list *t) 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); + queue_if_no_path(m, false, false, __func__); } /* @@ -1078,7 +1084,7 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) argc--; if (!strcasecmp(arg_name, "queue_if_no_path")) { - r = queue_if_no_path(m, true, false); + r = queue_if_no_path(m, true, false, __func__); continue; } @@ -1279,7 +1285,9 @@ static int fail_path(struct pgpath *pgpath) if (!pgpath->is_active) goto out; - DMWARN("Failing path %s.", pgpath->path.dev->name); + DMWARN("%s: Failing path %s.", + dm_device_name(dm_table_get_md(m->ti->table)), + pgpath->path.dev->name); pgpath->pg->ps.type->fail_path(&pgpath->pg->ps, &pgpath->path); pgpath->is_active = false; @@ -1318,7 +1326,9 @@ static int reinstate_path(struct pgpath *pgpath) if (pgpath->is_active) goto out; - DMWARN("Reinstating path %s.", pgpath->path.dev->name); + DMWARN("%s: Reinstating path %s.", + dm_device_name(dm_table_get_md(m->ti->table)), + pgpath->path.dev->name); r = pgpath->pg->ps.type->reinstate_path(&pgpath->pg->ps, &pgpath->path); if (r) @@ -1617,7 +1627,8 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone, struct path_selector *ps = &pgpath->pg->ps; if (ps->type->end_io) - ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes); + ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes, + clone->io_start_time_ns); } return r; @@ -1640,7 +1651,7 @@ static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, if (atomic_read(&m->nr_valid_paths) == 0 && !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) { - if (must_push_back_bio(m)) { + if (__must_push_back(m)) { r = DM_ENDIO_REQUEUE; } else { dm_report_EIO(m); @@ -1661,23 +1672,27 @@ done: struct path_selector *ps = &pgpath->pg->ps; if (ps->type->end_io) - ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes); + ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes, + dm_start_time_ns_from_clone(clone)); } return r; } /* - * Suspend can't complete until all the I/O is processed so if - * the last path fails we must error any remaining I/O. - * Note that if the freeze_bdev fails while suspending, the - * queue_if_no_path state is lost - userspace should reset it. + * Suspend with flush can't complete until all the I/O is processed + * so if the last path fails we must error any remaining I/O. + * - Note that if the freeze_bdev fails while suspending, the + * queue_if_no_path state is lost - userspace should reset it. + * Otherwise, during noflush suspend, queue_if_no_path will not change. */ static void multipath_presuspend(struct dm_target *ti) { struct multipath *m = ti->private; - queue_if_no_path(m, false, true); + /* FIXME: bio-based shouldn't need to always disable queue_if_no_path */ + if (m->queue_mode == DM_TYPE_BIO_BASED || !dm_noflush_suspending(m->ti)) + queue_if_no_path(m, false, true, __func__); } static void multipath_postsuspend(struct dm_target *ti) @@ -1698,8 +1713,16 @@ static void multipath_resume(struct dm_target *ti) unsigned long flags; spin_lock_irqsave(&m->lock, flags); - assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags, - test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)); + if (test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)) { + set_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags); + clear_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags); + } + + DMDEBUG("%s: %s finished; QIFNP = %d; SQIFNP = %d", + dm_device_name(dm_table_get_md(m->ti->table)), __func__, + test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags), + test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags)); + spin_unlock_irqrestore(&m->lock, flags); } @@ -1859,13 +1882,13 @@ 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); + r = queue_if_no_path(m, true, false, __func__); 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); + r = queue_if_no_path(m, false, false, __func__); disable_nopath_timeout(m); goto out; } @@ -1918,7 +1941,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti, int r; current_pgpath = READ_ONCE(m->current_pgpath); - if (!current_pgpath) + if (!current_pgpath || !test_bit(MPATHF_QUEUE_IO, &m->flags)) current_pgpath = choose_pgpath(m, 0); if (current_pgpath) { diff --git a/drivers/md/dm-path-selector.h b/drivers/md/dm-path-selector.h index b6eb5365b1a4..c47bc0e20275 100644 --- a/drivers/md/dm-path-selector.h +++ b/drivers/md/dm-path-selector.h @@ -74,7 +74,7 @@ struct path_selector_type { int (*start_io) (struct path_selector *ps, struct dm_path *path, size_t nr_bytes); int (*end_io) (struct path_selector *ps, struct dm_path *path, - size_t nr_bytes); + size_t nr_bytes, u64 start_time); }; /* Register a path selector */ diff --git a/drivers/md/dm-queue-length.c b/drivers/md/dm-queue-length.c index 969c4f1a3633..5fd018d18418 100644 --- a/drivers/md/dm-queue-length.c +++ b/drivers/md/dm-queue-length.c @@ -227,7 +227,7 @@ static int ql_start_io(struct path_selector *ps, struct dm_path *path, } static int ql_end_io(struct path_selector *ps, struct dm_path *path, - size_t nr_bytes) + size_t nr_bytes, u64 start_time) { struct path_info *pi = path->pscontext; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 9a18bef0a5ff..10e8b2fe787b 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -254,7 +254,7 @@ struct raid_set { int mode; } journal_dev; - struct raid_dev dev[0]; + struct raid_dev dev[]; }; static void rs_config_backup(struct raid_set *rs, struct rs_layout *l) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 089aed57e083..2f655d9f4200 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -83,7 +83,7 @@ struct mirror_set { struct work_struct trigger_event; unsigned nr_mirrors; - struct mirror mirror[0]; + struct mirror mirror[]; }; DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(raid1_resync_throttle, diff --git a/drivers/md/dm-service-time.c b/drivers/md/dm-service-time.c index f006a9005593..9cfda665e9eb 100644 --- a/drivers/md/dm-service-time.c +++ b/drivers/md/dm-service-time.c @@ -309,7 +309,7 @@ static int st_start_io(struct path_selector *ps, struct dm_path *path, } static int st_end_io(struct path_selector *ps, struct dm_path *path, - size_t nr_bytes) + size_t nr_bytes, u64 start_time) { struct path_info *pi = path->pscontext; diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 71417048256a..35d368c418d0 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -56,7 +56,7 @@ struct dm_stat { size_t percpu_alloc_size; size_t histogram_alloc_size; struct dm_stat_percpu *stat_percpu[NR_CPUS]; - struct dm_stat_shared stat_shared[0]; + struct dm_stat_shared stat_shared[]; }; #define STAT_PRECISE_TIMESTAMPS 1 diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index fa813c0f993d..151d022b032d 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -41,7 +41,7 @@ struct stripe_c { /* Work struct used for triggering events*/ struct work_struct trigger_event; - struct stripe stripe[0]; + struct stripe stripe[]; }; /* diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 8a0f057b8122..bff4c7fa1cd2 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -53,7 +53,7 @@ struct switch_ctx { /* * Array of dm devices to switch between. */ - struct switch_path path_list[0]; + struct switch_path path_list[]; }; static struct switch_ctx *alloc_switch_ctx(struct dm_target *ti, unsigned nr_paths, diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 613c171b1b6d..74f3c506f084 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -234,10 +234,6 @@ static int persistent_memory_claim(struct dm_writecache *wc) wc->memory_vmapped = false; - if (!wc->ssd_dev->dax_dev) { - r = -EOPNOTSUPP; - goto err1; - } s = wc->memory_map_size; p = s >> PAGE_SHIFT; if (!p) { @@ -1143,6 +1139,42 @@ static int writecache_message(struct dm_target *ti, unsigned argc, char **argv, return r; } +static void memcpy_flushcache_optimized(void *dest, void *source, size_t size) +{ + /* + * clflushopt performs better with block size 1024, 2048, 4096 + * non-temporal stores perform better with block size 512 + * + * block size 512 1024 2048 4096 + * movnti 496 MB/s 642 MB/s 725 MB/s 744 MB/s + * clflushopt 373 MB/s 688 MB/s 1.1 GB/s 1.2 GB/s + * + * We see that movnti performs better for 512-byte blocks, and + * clflushopt performs better for 1024-byte and larger blocks. So, we + * prefer clflushopt for sizes >= 768. + * + * NOTE: this happens to be the case now (with dm-writecache's single + * threaded model) but re-evaluate this once memcpy_flushcache() is + * enabled to use movdir64b which might invalidate this performance + * advantage seen with cache-allocating-writes plus flushing. + */ +#ifdef CONFIG_X86 + if (static_cpu_has(X86_FEATURE_CLFLUSHOPT) && + likely(boot_cpu_data.x86_clflush_size == 64) && + likely(size >= 768)) { + do { + memcpy((void *)dest, (void *)source, 64); + clflushopt((void *)dest); + dest += 64; + source += 64; + size -= 64; + } while (size >= 64); + return; + } +#endif + memcpy_flushcache(dest, source, size); +} + static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data) { void *buf; @@ -1168,7 +1200,7 @@ static void bio_copy_block(struct dm_writecache *wc, struct bio *bio, void *data } } else { flush_dcache_page(bio_page(bio)); - memcpy_flushcache(data, buf, size); + memcpy_flushcache_optimized(data, buf, size); } bvec_kunmap_irq(buf, &flags); diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index bf2245370305..130b5a6d9f12 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -16,7 +16,7 @@ /* * Metadata version. */ -#define DMZ_META_VER 1 +#define DMZ_META_VER 2 /* * On-disk super block magic. @@ -69,8 +69,17 @@ struct dmz_super { /* Checksum */ __le32 crc; /* 48 */ + /* DM-Zoned label */ + u8 dmz_label[32]; /* 80 */ + + /* DM-Zoned UUID */ + u8 dmz_uuid[16]; /* 96 */ + + /* Device UUID */ + u8 dev_uuid[16]; /* 112 */ + /* Padding to full 512B sector */ - u8 reserved[464]; /* 512 */ + u8 reserved[400]; /* 512 */ }; /* @@ -122,8 +131,10 @@ enum { */ struct dmz_sb { sector_t block; + struct dmz_dev *dev; struct dmz_mblock *mblk; struct dmz_super *sb; + struct dm_zone *zone; }; /* @@ -131,28 +142,41 @@ struct dmz_sb { */ struct dmz_metadata { struct dmz_dev *dev; + unsigned int nr_devs; + + char devname[BDEVNAME_SIZE]; + char label[BDEVNAME_SIZE]; + uuid_t uuid; sector_t zone_bitmap_size; unsigned int zone_nr_bitmap_blocks; unsigned int zone_bits_per_mblk; + sector_t zone_nr_blocks; + sector_t zone_nr_blocks_shift; + + sector_t zone_nr_sectors; + sector_t zone_nr_sectors_shift; + unsigned int nr_bitmap_blocks; unsigned int nr_map_blocks; + unsigned int nr_zones; unsigned int nr_useable_zones; unsigned int nr_meta_blocks; unsigned int nr_meta_zones; unsigned int nr_data_zones; + unsigned int nr_cache_zones; unsigned int nr_rnd_zones; unsigned int nr_reserved_seq; unsigned int nr_chunks; /* Zone information array */ - struct dm_zone *zones; + struct xarray zones; - struct dm_zone *sb_zone; struct dmz_sb sb[2]; unsigned int mblk_primary; + unsigned int sb_version; u64 sb_gen; unsigned int min_nr_mblks; unsigned int max_nr_mblks; @@ -168,15 +192,11 @@ struct dmz_metadata { /* Zone allocation management */ struct mutex map_lock; struct dmz_mblock **map_mblk; - unsigned int nr_rnd; - atomic_t unmap_nr_rnd; - struct list_head unmap_rnd_list; - struct list_head map_rnd_list; - unsigned int nr_seq; - atomic_t unmap_nr_seq; - struct list_head unmap_seq_list; - struct list_head map_seq_list; + unsigned int nr_cache; + atomic_t unmap_nr_cache; + struct list_head unmap_cache_list; + struct list_head map_cache_list; atomic_t nr_reserved_seq_zones; struct list_head reserved_seq_zones_list; @@ -184,22 +204,65 @@ struct dmz_metadata { wait_queue_head_t free_wq; }; +#define dmz_zmd_info(zmd, format, args...) \ + DMINFO("(%s): " format, (zmd)->label, ## args) + +#define dmz_zmd_err(zmd, format, args...) \ + DMERR("(%s): " format, (zmd)->label, ## args) + +#define dmz_zmd_warn(zmd, format, args...) \ + DMWARN("(%s): " format, (zmd)->label, ## args) + +#define dmz_zmd_debug(zmd, format, args...) \ + DMDEBUG("(%s): " format, (zmd)->label, ## args) /* * Various accessors */ -unsigned int dmz_id(struct dmz_metadata *zmd, struct dm_zone *zone) +static unsigned int dmz_dev_zone_id(struct dmz_metadata *zmd, struct dm_zone *zone) { - return ((unsigned int)(zone - zmd->zones)); + if (WARN_ON(!zone)) + return 0; + + return zone->id - zone->dev->zone_offset; } sector_t dmz_start_sect(struct dmz_metadata *zmd, struct dm_zone *zone) { - return (sector_t)dmz_id(zmd, zone) << zmd->dev->zone_nr_sectors_shift; + unsigned int zone_id = dmz_dev_zone_id(zmd, zone); + + return (sector_t)zone_id << zmd->zone_nr_sectors_shift; } sector_t dmz_start_block(struct dmz_metadata *zmd, struct dm_zone *zone) { - return (sector_t)dmz_id(zmd, zone) << zmd->dev->zone_nr_blocks_shift; + unsigned int zone_id = dmz_dev_zone_id(zmd, zone); + + return (sector_t)zone_id << zmd->zone_nr_blocks_shift; +} + +unsigned int dmz_zone_nr_blocks(struct dmz_metadata *zmd) +{ + return zmd->zone_nr_blocks; +} + +unsigned int dmz_zone_nr_blocks_shift(struct dmz_metadata *zmd) +{ + return zmd->zone_nr_blocks_shift; +} + +unsigned int dmz_zone_nr_sectors(struct dmz_metadata *zmd) +{ + return zmd->zone_nr_sectors; +} + +unsigned int dmz_zone_nr_sectors_shift(struct dmz_metadata *zmd) +{ + return zmd->zone_nr_sectors_shift; +} + +unsigned int dmz_nr_zones(struct dmz_metadata *zmd) +{ + return zmd->nr_zones; } unsigned int dmz_nr_chunks(struct dmz_metadata *zmd) @@ -207,14 +270,88 @@ unsigned int dmz_nr_chunks(struct dmz_metadata *zmd) return zmd->nr_chunks; } -unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd) +unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd, int idx) { - return zmd->nr_rnd; + return zmd->dev[idx].nr_rnd; } -unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd) +unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd, int idx) { - return atomic_read(&zmd->unmap_nr_rnd); + return atomic_read(&zmd->dev[idx].unmap_nr_rnd); +} + +unsigned int dmz_nr_cache_zones(struct dmz_metadata *zmd) +{ + return zmd->nr_cache; +} + +unsigned int dmz_nr_unmap_cache_zones(struct dmz_metadata *zmd) +{ + return atomic_read(&zmd->unmap_nr_cache); +} + +unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd, int idx) +{ + return zmd->dev[idx].nr_seq; +} + +unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd, int idx) +{ + return atomic_read(&zmd->dev[idx].unmap_nr_seq); +} + +static struct dm_zone *dmz_get(struct dmz_metadata *zmd, unsigned int zone_id) +{ + return xa_load(&zmd->zones, zone_id); +} + +static struct dm_zone *dmz_insert(struct dmz_metadata *zmd, + unsigned int zone_id, struct dmz_dev *dev) +{ + struct dm_zone *zone = kzalloc(sizeof(struct dm_zone), GFP_KERNEL); + + if (!zone) + return ERR_PTR(-ENOMEM); + + if (xa_insert(&zmd->zones, zone_id, zone, GFP_KERNEL)) { + kfree(zone); + return ERR_PTR(-EBUSY); + } + + INIT_LIST_HEAD(&zone->link); + atomic_set(&zone->refcount, 0); + zone->id = zone_id; + zone->chunk = DMZ_MAP_UNMAPPED; + zone->dev = dev; + + return zone; +} + +const char *dmz_metadata_label(struct dmz_metadata *zmd) +{ + return (const char *)zmd->label; +} + +bool dmz_check_dev(struct dmz_metadata *zmd) +{ + unsigned int i; + + for (i = 0; i < zmd->nr_devs; i++) { + if (!dmz_check_bdev(&zmd->dev[i])) + return false; + } + return true; +} + +bool dmz_dev_is_dying(struct dmz_metadata *zmd) +{ + unsigned int i; + + for (i = 0; i < zmd->nr_devs; i++) { + if (dmz_bdev_is_dying(&zmd->dev[i])) + return true; + } + return false; } /* @@ -402,9 +539,10 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, { struct dmz_mblock *mblk, *m; sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no; + struct dmz_dev *dev = zmd->sb[zmd->mblk_primary].dev; struct bio *bio; - if (dmz_bdev_is_dying(zmd->dev)) + if (dmz_bdev_is_dying(dev)) return ERR_PTR(-EIO); /* Get a new block and a BIO to read it */ @@ -440,7 +578,7 @@ static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, /* Submit read BIO */ bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_set_dev(bio, zmd->dev->bdev); + bio_set_dev(bio, dev->bdev); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; bio_set_op_attrs(bio, REQ_OP_READ, REQ_META | REQ_PRIO); @@ -537,6 +675,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, sector_t mblk_no) { struct dmz_mblock *mblk; + struct dmz_dev *dev = zmd->sb[zmd->mblk_primary].dev; /* Check rbtree */ spin_lock(&zmd->mblk_lock); @@ -555,7 +694,7 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { dmz_release_mblock(zmd, mblk); - dmz_check_bdev(zmd->dev); + dmz_check_bdev(dev); return ERR_PTR(-EIO); } @@ -579,10 +718,11 @@ static void dmz_dirty_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk) static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, unsigned int set) { + struct dmz_dev *dev = zmd->sb[set].dev; sector_t block = zmd->sb[set].block + mblk->no; struct bio *bio; - if (dmz_bdev_is_dying(zmd->dev)) + if (dmz_bdev_is_dying(dev)) return -EIO; bio = bio_alloc(GFP_NOIO, 1); @@ -594,7 +734,7 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, set_bit(DMZ_META_WRITING, &mblk->state); bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_set_dev(bio, zmd->dev->bdev); + bio_set_dev(bio, dev->bdev); bio->bi_private = mblk; bio->bi_end_io = dmz_mblock_bio_end_io; bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO); @@ -607,13 +747,16 @@ static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk, /* * Read/write a metadata block. */ -static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, - struct page *page) +static int dmz_rdwr_block(struct dmz_dev *dev, int op, + sector_t block, struct page *page) { struct bio *bio; int ret; - if (dmz_bdev_is_dying(zmd->dev)) + if (WARN_ON(!dev)) + return -EIO; + + if (dmz_bdev_is_dying(dev)) return -EIO; bio = bio_alloc(GFP_NOIO, 1); @@ -621,14 +764,14 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, return -ENOMEM; bio->bi_iter.bi_sector = dmz_blk2sect(block); - bio_set_dev(bio, zmd->dev->bdev); + bio_set_dev(bio, dev->bdev); bio_set_op_attrs(bio, op, REQ_SYNC | REQ_META | REQ_PRIO); bio_add_page(bio, page, DMZ_BLOCK_SIZE, 0); ret = submit_bio_wait(bio); bio_put(bio); if (ret) - dmz_check_bdev(zmd->dev); + dmz_check_bdev(dev); return ret; } @@ -637,18 +780,32 @@ static int dmz_rdwr_block(struct dmz_metadata *zmd, int op, sector_t block, */ static int dmz_write_sb(struct dmz_metadata *zmd, unsigned int set) { - sector_t block = zmd->sb[set].block; struct dmz_mblock *mblk = zmd->sb[set].mblk; struct dmz_super *sb = zmd->sb[set].sb; + struct dmz_dev *dev = zmd->sb[set].dev; + sector_t sb_block; u64 sb_gen = zmd->sb_gen + 1; int ret; sb->magic = cpu_to_le32(DMZ_MAGIC); - sb->version = cpu_to_le32(DMZ_META_VER); + + sb->version = cpu_to_le32(zmd->sb_version); + if (zmd->sb_version > 1) { + BUILD_BUG_ON(UUID_SIZE != 16); + export_uuid(sb->dmz_uuid, &zmd->uuid); + memcpy(sb->dmz_label, zmd->label, BDEVNAME_SIZE); + export_uuid(sb->dev_uuid, &dev->uuid); + } sb->gen = cpu_to_le64(sb_gen); - sb->sb_block = cpu_to_le64(block); + /* + * The metadata always references the absolute block address, + * ie relative to the entire block range, not the per-device + * block address. + */ + sb_block = zmd->sb[set].zone->id << zmd->zone_nr_blocks_shift; + sb->sb_block = cpu_to_le64(sb_block); sb->nr_meta_blocks = cpu_to_le32(zmd->nr_meta_blocks); sb->nr_reserved_seq = cpu_to_le32(zmd->nr_reserved_seq); sb->nr_chunks = cpu_to_le32(zmd->nr_chunks); @@ -659,9 +816,10 @@ static int dmz_write_sb(struct dmz_metadata *zmd, unsigned int set) sb->crc = 0; sb->crc = cpu_to_le32(crc32_le(sb_gen, (unsigned char *)sb, DMZ_BLOCK_SIZE)); - ret = dmz_rdwr_block(zmd, REQ_OP_WRITE, block, mblk->page); + ret = dmz_rdwr_block(dev, REQ_OP_WRITE, zmd->sb[set].block, + mblk->page); if (ret == 0) - ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO); + ret = blkdev_issue_flush(dev->bdev, GFP_NOIO); return ret; } @@ -674,6 +832,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, unsigned int set) { struct dmz_mblock *mblk; + struct dmz_dev *dev = zmd->sb[set].dev; struct blk_plug plug; int ret = 0, nr_mblks_submitted = 0; @@ -695,7 +854,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, TASK_UNINTERRUPTIBLE); if (test_bit(DMZ_META_ERROR, &mblk->state)) { clear_bit(DMZ_META_ERROR, &mblk->state); - dmz_check_bdev(zmd->dev); + dmz_check_bdev(dev); ret = -EIO; } nr_mblks_submitted--; @@ -703,7 +862,7 @@ static int dmz_write_dirty_mblocks(struct dmz_metadata *zmd, /* Flush drive cache (this will also sync data) */ if (ret == 0) - ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO); + ret = blkdev_issue_flush(dev->bdev, GFP_NOIO); return ret; } @@ -740,6 +899,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) { struct dmz_mblock *mblk; struct list_head write_list; + struct dmz_dev *dev; int ret; if (WARN_ON(!zmd)) @@ -753,6 +913,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) * from modifying metadata. */ down_write(&zmd->mblk_sem); + dev = zmd->sb[zmd->mblk_primary].dev; /* * This is called from the target flush work and reclaim work. @@ -760,7 +921,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) */ dmz_lock_flush(zmd); - if (dmz_bdev_is_dying(zmd->dev)) { + if (dmz_bdev_is_dying(dev)) { ret = -EIO; goto out; } @@ -772,7 +933,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) /* If there are no dirty metadata blocks, just flush the device cache */ if (list_empty(&write_list)) { - ret = blkdev_issue_flush(zmd->dev->bdev, GFP_NOIO); + ret = blkdev_issue_flush(dev->bdev, GFP_NOIO); goto err; } @@ -821,7 +982,7 @@ err: list_splice(&write_list, &zmd->mblk_dirty_list); spin_unlock(&zmd->mblk_lock); } - if (!dmz_check_bdev(zmd->dev)) + if (!dmz_check_bdev(dev)) ret = -EIO; goto out; } @@ -829,12 +990,31 @@ err: /* * Check super block. */ -static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_super *sb) +static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_sb *dsb, + bool tertiary) { + struct dmz_super *sb = dsb->sb; + struct dmz_dev *dev = dsb->dev; unsigned int nr_meta_zones, nr_data_zones; - struct dmz_dev *dev = zmd->dev; u32 crc, stored_crc; - u64 gen; + u64 gen, sb_block; + + if (le32_to_cpu(sb->magic) != DMZ_MAGIC) { + dmz_dev_err(dev, "Invalid meta magic (needed 0x%08x, got 0x%08x)", + DMZ_MAGIC, le32_to_cpu(sb->magic)); + return -ENXIO; + } + + zmd->sb_version = le32_to_cpu(sb->version); + if (zmd->sb_version > DMZ_META_VER) { + dmz_dev_err(dev, "Invalid meta version (needed %d, got %d)", + DMZ_META_VER, zmd->sb_version); + return -EINVAL; + } + if (zmd->sb_version < 2 && tertiary) { + dmz_dev_err(dev, "Tertiary superblocks are not supported"); + return -EINVAL; + } gen = le64_to_cpu(sb->gen); stored_crc = le32_to_cpu(sb->crc); @@ -846,20 +1026,57 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_super *sb) return -ENXIO; } - if (le32_to_cpu(sb->magic) != DMZ_MAGIC) { - dmz_dev_err(dev, "Invalid meta magic (needed 0x%08x, got 0x%08x)", - DMZ_MAGIC, le32_to_cpu(sb->magic)); - return -ENXIO; - } + sb_block = le64_to_cpu(sb->sb_block); + if (sb_block != (u64)dsb->zone->id << zmd->zone_nr_blocks_shift ) { + dmz_dev_err(dev, "Invalid superblock position " + "(is %llu expected %llu)", + sb_block, + (u64)dsb->zone->id << zmd->zone_nr_blocks_shift); + return -EINVAL; + } + if (zmd->sb_version > 1) { + uuid_t sb_uuid; + + import_uuid(&sb_uuid, sb->dmz_uuid); + if (uuid_is_null(&sb_uuid)) { + dmz_dev_err(dev, "NULL DM-Zoned uuid"); + return -ENXIO; + } else if (uuid_is_null(&zmd->uuid)) { + uuid_copy(&zmd->uuid, &sb_uuid); + } else if (!uuid_equal(&zmd->uuid, &sb_uuid)) { + dmz_dev_err(dev, "mismatching DM-Zoned uuid, " + "is %pUl expected %pUl", + &sb_uuid, &zmd->uuid); + return -ENXIO; + } + if (!strlen(zmd->label)) + memcpy(zmd->label, sb->dmz_label, BDEVNAME_SIZE); + else if (memcmp(zmd->label, sb->dmz_label, BDEVNAME_SIZE)) { + dmz_dev_err(dev, "mismatching DM-Zoned label, " + "is %s expected %s", + sb->dmz_label, zmd->label); + return -ENXIO; + } + import_uuid(&dev->uuid, sb->dev_uuid); + if (uuid_is_null(&dev->uuid)) { + dmz_dev_err(dev, "NULL device uuid"); + return -ENXIO; + } - if (le32_to_cpu(sb->version) != DMZ_META_VER) { - dmz_dev_err(dev, "Invalid meta version (needed %d, got %d)", - DMZ_META_VER, le32_to_cpu(sb->version)); - return -ENXIO; + if (tertiary) { + /* + * Generation number should be 0, but it doesn't + * really matter if it isn't. + */ + if (gen != 0) + dmz_dev_warn(dev, "Invalid generation %llu", + gen); + return 0; + } } - nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + dev->zone_nr_blocks - 1) - >> dev->zone_nr_blocks_shift; + nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + zmd->zone_nr_blocks - 1) + >> zmd->zone_nr_blocks_shift; if (!nr_meta_zones || nr_meta_zones >= zmd->nr_rnd_zones) { dmz_dev_err(dev, "Invalid number of metadata blocks"); @@ -895,10 +1112,13 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_super *sb) /* * Read the first or second super block from disk. */ -static int dmz_read_sb(struct dmz_metadata *zmd, unsigned int set) +static int dmz_read_sb(struct dmz_metadata *zmd, struct dmz_sb *sb, int set) { - return dmz_rdwr_block(zmd, REQ_OP_READ, zmd->sb[set].block, - zmd->sb[set].mblk->page); + dmz_zmd_debug(zmd, "read superblock set %d dev %s block %llu", + set, sb->dev->name, sb->block); + + return dmz_rdwr_block(sb->dev, REQ_OP_READ, + sb->block, sb->mblk->page); } /* @@ -908,8 +1128,9 @@ static int dmz_read_sb(struct dmz_metadata *zmd, unsigned int set) */ static int dmz_lookup_secondary_sb(struct dmz_metadata *zmd) { - unsigned int zone_nr_blocks = zmd->dev->zone_nr_blocks; + unsigned int zone_nr_blocks = zmd->zone_nr_blocks; struct dmz_mblock *mblk; + unsigned int zone_id = zmd->sb[0].zone->id; int i; /* Allocate a block */ @@ -922,24 +1143,29 @@ static int dmz_lookup_secondary_sb(struct dmz_metadata *zmd) /* Bad first super block: search for the second one */ zmd->sb[1].block = zmd->sb[0].block + zone_nr_blocks; - for (i = 0; i < zmd->nr_rnd_zones - 1; i++) { - if (dmz_read_sb(zmd, 1) != 0) + zmd->sb[1].zone = dmz_get(zmd, zone_id + 1); + zmd->sb[1].dev = zmd->sb[0].dev; + for (i = 1; i < zmd->nr_rnd_zones; i++) { + if (dmz_read_sb(zmd, &zmd->sb[1], 1) != 0) break; if (le32_to_cpu(zmd->sb[1].sb->magic) == DMZ_MAGIC) return 0; zmd->sb[1].block += zone_nr_blocks; + zmd->sb[1].zone = dmz_get(zmd, zone_id + i); } dmz_free_mblock(zmd, mblk); zmd->sb[1].mblk = NULL; + zmd->sb[1].zone = NULL; + zmd->sb[1].dev = NULL; return -EIO; } /* - * Read the first or second super block from disk. + * Read a super block from disk. */ -static int dmz_get_sb(struct dmz_metadata *zmd, unsigned int set) +static int dmz_get_sb(struct dmz_metadata *zmd, struct dmz_sb *sb, int set) { struct dmz_mblock *mblk; int ret; @@ -949,14 +1175,14 @@ static int dmz_get_sb(struct dmz_metadata *zmd, unsigned int set) if (!mblk) return -ENOMEM; - zmd->sb[set].mblk = mblk; - zmd->sb[set].sb = mblk->data; + sb->mblk = mblk; + sb->sb = mblk->data; /* Read super block */ - ret = dmz_read_sb(zmd, set); + ret = dmz_read_sb(zmd, sb, set); if (ret) { dmz_free_mblock(zmd, mblk); - zmd->sb[set].mblk = NULL; + sb->mblk = NULL; return ret; } @@ -972,14 +1198,13 @@ static int dmz_recover_mblocks(struct dmz_metadata *zmd, unsigned int dst_set) struct page *page; int i, ret; - dmz_dev_warn(zmd->dev, "Metadata set %u invalid: recovering", dst_set); + dmz_dev_warn(zmd->sb[dst_set].dev, + "Metadata set %u invalid: recovering", dst_set); if (dst_set == 0) - zmd->sb[0].block = dmz_start_block(zmd, zmd->sb_zone); - else { - zmd->sb[1].block = zmd->sb[0].block + - (zmd->nr_meta_zones << zmd->dev->zone_nr_blocks_shift); - } + zmd->sb[0].block = dmz_start_block(zmd, zmd->sb[0].zone); + else + zmd->sb[1].block = dmz_start_block(zmd, zmd->sb[1].zone); page = alloc_page(GFP_NOIO); if (!page) @@ -987,11 +1212,11 @@ static int dmz_recover_mblocks(struct dmz_metadata *zmd, unsigned int dst_set) /* Copy metadata blocks */ for (i = 1; i < zmd->nr_meta_blocks; i++) { - ret = dmz_rdwr_block(zmd, REQ_OP_READ, + ret = dmz_rdwr_block(zmd->sb[src_set].dev, REQ_OP_READ, zmd->sb[src_set].block + i, page); if (ret) goto out; - ret = dmz_rdwr_block(zmd, REQ_OP_WRITE, + ret = dmz_rdwr_block(zmd->sb[dst_set].dev, REQ_OP_WRITE, zmd->sb[dst_set].block + i, page); if (ret) goto out; @@ -1023,53 +1248,73 @@ static int dmz_load_sb(struct dmz_metadata *zmd) u64 sb_gen[2] = {0, 0}; int ret; + if (!zmd->sb[0].zone) { + dmz_zmd_err(zmd, "Primary super block zone not set"); + return -ENXIO; + } + /* Read and check the primary super block */ - zmd->sb[0].block = dmz_start_block(zmd, zmd->sb_zone); - ret = dmz_get_sb(zmd, 0); + zmd->sb[0].block = dmz_start_block(zmd, zmd->sb[0].zone); + zmd->sb[0].dev = zmd->sb[0].zone->dev; + ret = dmz_get_sb(zmd, &zmd->sb[0], 0); if (ret) { - dmz_dev_err(zmd->dev, "Read primary super block failed"); + dmz_dev_err(zmd->sb[0].dev, "Read primary super block failed"); return ret; } - ret = dmz_check_sb(zmd, zmd->sb[0].sb); + ret = dmz_check_sb(zmd, &zmd->sb[0], false); /* Read and check secondary super block */ if (ret == 0) { sb_good[0] = true; - zmd->sb[1].block = zmd->sb[0].block + - (zmd->nr_meta_zones << zmd->dev->zone_nr_blocks_shift); - ret = dmz_get_sb(zmd, 1); + if (!zmd->sb[1].zone) { + unsigned int zone_id = + zmd->sb[0].zone->id + zmd->nr_meta_zones; + + zmd->sb[1].zone = dmz_get(zmd, zone_id); + } + zmd->sb[1].block = dmz_start_block(zmd, zmd->sb[1].zone); + zmd->sb[1].dev = zmd->sb[0].dev; + ret = dmz_get_sb(zmd, &zmd->sb[1], 1); } else ret = dmz_lookup_secondary_sb(zmd); if (ret) { - dmz_dev_err(zmd->dev, "Read secondary super block failed"); + dmz_dev_err(zmd->sb[1].dev, "Read secondary super block failed"); return ret; } - ret = dmz_check_sb(zmd, zmd->sb[1].sb); + ret = dmz_check_sb(zmd, &zmd->sb[1], false); if (ret == 0) sb_good[1] = true; /* Use highest generation sb first */ if (!sb_good[0] && !sb_good[1]) { - dmz_dev_err(zmd->dev, "No valid super block found"); + dmz_zmd_err(zmd, "No valid super block found"); return -EIO; } if (sb_good[0]) sb_gen[0] = le64_to_cpu(zmd->sb[0].sb->gen); - else + else { ret = dmz_recover_mblocks(zmd, 0); + if (ret) { + dmz_dev_err(zmd->sb[0].dev, + "Recovery of superblock 0 failed"); + return -EIO; + } + } if (sb_good[1]) sb_gen[1] = le64_to_cpu(zmd->sb[1].sb->gen); - else + else { ret = dmz_recover_mblocks(zmd, 1); - if (ret) { - dmz_dev_err(zmd->dev, "Recovery failed"); - return -EIO; + if (ret) { + dmz_dev_err(zmd->sb[1].dev, + "Recovery of superblock 1 failed"); + return -EIO; + } } if (sb_gen[0] >= sb_gen[1]) { @@ -1080,32 +1325,70 @@ static int dmz_load_sb(struct dmz_metadata *zmd) zmd->mblk_primary = 1; } - dmz_dev_debug(zmd->dev, "Using super block %u (gen %llu)", + dmz_dev_debug(zmd->sb[zmd->mblk_primary].dev, + "Using super block %u (gen %llu)", zmd->mblk_primary, zmd->sb_gen); - return 0; + if (zmd->sb_version > 1) { + int i; + struct dmz_sb *sb; + + sb = kzalloc(sizeof(struct dmz_sb), GFP_KERNEL); + if (!sb) + return -ENOMEM; + for (i = 1; i < zmd->nr_devs; i++) { + sb->block = 0; + sb->zone = dmz_get(zmd, zmd->dev[i].zone_offset); + sb->dev = &zmd->dev[i]; + if (!dmz_is_meta(sb->zone)) { + dmz_dev_err(sb->dev, + "Tertiary super block zone %u not marked as metadata zone", + sb->zone->id); + ret = -EINVAL; + goto out_kfree; + } + ret = dmz_get_sb(zmd, sb, i + 1); + if (ret) { + dmz_dev_err(sb->dev, + "Read tertiary super block failed"); + dmz_free_mblock(zmd, sb->mblk); + goto out_kfree; + } + ret = dmz_check_sb(zmd, sb, true); + dmz_free_mblock(zmd, sb->mblk); + if (ret == -EINVAL) + goto out_kfree; + } + out_kfree: + kfree(sb); + } + return ret; } /* * Initialize a zone descriptor. */ -static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data) +static int dmz_init_zone(struct blk_zone *blkz, unsigned int num, void *data) { - struct dmz_metadata *zmd = data; - struct dm_zone *zone = &zmd->zones[idx]; - struct dmz_dev *dev = zmd->dev; + struct dmz_dev *dev = data; + struct dmz_metadata *zmd = dev->metadata; + int idx = num + dev->zone_offset; + struct dm_zone *zone; + + zone = dmz_insert(zmd, idx, dev); + if (IS_ERR(zone)) + return PTR_ERR(zone); - /* Ignore the eventual last runt (smaller) zone */ - if (blkz->len != dev->zone_nr_sectors) { - if (blkz->start + blkz->len == dev->capacity) + if (blkz->len != zmd->zone_nr_sectors) { + if (zmd->sb_version > 1) { + /* Ignore the eventual runt (smaller) zone */ + set_bit(DMZ_OFFLINE, &zone->flags); + return 0; + } else if (blkz->start + blkz->len == dev->capacity) return 0; return -ENXIO; } - INIT_LIST_HEAD(&zone->link); - atomic_set(&zone->refcount, 0); - zone->chunk = DMZ_MAP_UNMAPPED; - switch (blkz->type) { case BLK_ZONE_TYPE_CONVENTIONAL: set_bit(DMZ_RND, &zone->flags); @@ -1131,13 +1414,45 @@ static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data) zmd->nr_useable_zones++; if (dmz_is_rnd(zone)) { zmd->nr_rnd_zones++; - if (!zmd->sb_zone) { - /* Super block zone */ - zmd->sb_zone = zone; + if (zmd->nr_devs == 1 && !zmd->sb[0].zone) { + /* Primary super block zone */ + zmd->sb[0].zone = zone; } } + if (zmd->nr_devs > 1 && num == 0) { + /* + * Tertiary superblock zones are always at the + * start of the zoned devices, so mark them + * as metadata zone. + */ + set_bit(DMZ_META, &zone->flags); + } } + return 0; +} + +static int dmz_emulate_zones(struct dmz_metadata *zmd, struct dmz_dev *dev) +{ + int idx; + sector_t zone_offset = 0; + for(idx = 0; idx < dev->nr_zones; idx++) { + struct dm_zone *zone; + + zone = dmz_insert(zmd, idx, dev); + if (IS_ERR(zone)) + return PTR_ERR(zone); + set_bit(DMZ_CACHE, &zone->flags); + zone->wp_block = 0; + zmd->nr_cache_zones++; + zmd->nr_useable_zones++; + if (dev->capacity - zone_offset < zmd->zone_nr_sectors) { + /* Disable runt zone */ + set_bit(DMZ_OFFLINE, &zone->flags); + break; + } + zone_offset += zmd->zone_nr_sectors; + } return 0; } @@ -1146,8 +1461,15 @@ static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data) */ static void dmz_drop_zones(struct dmz_metadata *zmd) { - kfree(zmd->zones); - zmd->zones = NULL; + int idx; + + for(idx = 0; idx < zmd->nr_zones; idx++) { + struct dm_zone *zone = xa_load(&zmd->zones, idx); + + kfree(zone); + xa_erase(&zmd->zones, idx); + } + xa_destroy(&zmd->zones); } /* @@ -1156,32 +1478,87 @@ static void dmz_drop_zones(struct dmz_metadata *zmd) */ static int dmz_init_zones(struct dmz_metadata *zmd) { - struct dmz_dev *dev = zmd->dev; - int ret; + int i, ret; + struct dmz_dev *zoned_dev = &zmd->dev[0]; /* Init */ - zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3; + zmd->zone_nr_sectors = zmd->dev[0].zone_nr_sectors; + zmd->zone_nr_sectors_shift = ilog2(zmd->zone_nr_sectors); + zmd->zone_nr_blocks = dmz_sect2blk(zmd->zone_nr_sectors); + zmd->zone_nr_blocks_shift = ilog2(zmd->zone_nr_blocks); + zmd->zone_bitmap_size = zmd->zone_nr_blocks >> 3; 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, + zmd->zone_bits_per_mblk = min_t(sector_t, zmd->zone_nr_blocks, DMZ_BLOCK_SIZE_BITS); /* Allocate zone array */ - zmd->zones = kcalloc(dev->nr_zones, sizeof(struct dm_zone), GFP_KERNEL); - if (!zmd->zones) - return -ENOMEM; + zmd->nr_zones = 0; + for (i = 0; i < zmd->nr_devs; i++) { + struct dmz_dev *dev = &zmd->dev[i]; + + dev->metadata = zmd; + zmd->nr_zones += dev->nr_zones; + + atomic_set(&dev->unmap_nr_rnd, 0); + INIT_LIST_HEAD(&dev->unmap_rnd_list); + INIT_LIST_HEAD(&dev->map_rnd_list); + + atomic_set(&dev->unmap_nr_seq, 0); + INIT_LIST_HEAD(&dev->unmap_seq_list); + INIT_LIST_HEAD(&dev->map_seq_list); + } + + if (!zmd->nr_zones) { + DMERR("(%s): No zones found", zmd->devname); + return -ENXIO; + } + xa_init(&zmd->zones); + + DMDEBUG("(%s): Using %zu B for zone information", + zmd->devname, sizeof(struct dm_zone) * zmd->nr_zones); - dmz_dev_info(dev, "Using %zu B for zone information", - sizeof(struct dm_zone) * dev->nr_zones); + if (zmd->nr_devs > 1) { + ret = dmz_emulate_zones(zmd, &zmd->dev[0]); + if (ret < 0) { + DMDEBUG("(%s): Failed to emulate zones, error %d", + zmd->devname, ret); + dmz_drop_zones(zmd); + return ret; + } + + /* + * Primary superblock zone is always at zone 0 when multiple + * drives are present. + */ + zmd->sb[0].zone = dmz_get(zmd, 0); + + for (i = 1; i < zmd->nr_devs; i++) { + zoned_dev = &zmd->dev[i]; + + ret = blkdev_report_zones(zoned_dev->bdev, 0, + BLK_ALL_ZONES, + dmz_init_zone, zoned_dev); + if (ret < 0) { + DMDEBUG("(%s): Failed to report zones, error %d", + zmd->devname, ret); + dmz_drop_zones(zmd); + return ret; + } + } + return 0; + } /* * Get zone information and initialize zone descriptors. At the same * time, determine where the super block should be: first block of the * first randomly writable zone. */ - ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone, - zmd); + ret = blkdev_report_zones(zoned_dev->bdev, 0, BLK_ALL_ZONES, + dmz_init_zone, zoned_dev); if (ret < 0) { + DMDEBUG("(%s): Failed to report zones, error %d", + zmd->devname, ret); dmz_drop_zones(zmd); return ret; } @@ -1213,9 +1590,13 @@ static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx, */ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) { + struct dmz_dev *dev = zone->dev; unsigned int noio_flag; int ret; + if (dev->flags & DMZ_BDEV_REGULAR) + return 0; + /* * Get zone information from disk. Since blkdev_report_zones() uses * GFP_KERNEL by default for memory allocations, set the per-task @@ -1223,16 +1604,16 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) * GFP_NOIO was specified. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1, + ret = blkdev_report_zones(dev->bdev, dmz_start_sect(zmd, zone), 1, dmz_update_zone_cb, zone); memalloc_noio_restore(noio_flag); if (ret == 0) ret = -EIO; if (ret < 0) { - dmz_dev_err(zmd->dev, "Get zone %u report failed", - dmz_id(zmd, zone)); - dmz_check_bdev(zmd->dev); + dmz_dev_err(dev, "Get zone %u report failed", + zone->id); + dmz_check_bdev(dev); return ret; } @@ -1246,6 +1627,7 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone) static int dmz_handle_seq_write_err(struct dmz_metadata *zmd, struct dm_zone *zone) { + struct dmz_dev *dev = zone->dev; unsigned int wp = 0; int ret; @@ -1254,8 +1636,8 @@ static int dmz_handle_seq_write_err(struct dmz_metadata *zmd, if (ret) return ret; - dmz_dev_warn(zmd->dev, "Processing zone %u write error (zone wp %u/%u)", - dmz_id(zmd, zone), zone->wp_block, wp); + dmz_dev_warn(dev, "Processing zone %u write error (zone wp %u/%u)", + zone->id, zone->wp_block, wp); if (zone->wp_block < wp) { dmz_invalidate_blocks(zmd, zone, zone->wp_block, @@ -1265,11 +1647,6 @@ static int dmz_handle_seq_write_err(struct dmz_metadata *zmd, return 0; } -static struct dm_zone *dmz_get(struct dmz_metadata *zmd, unsigned int zone_id) -{ - return &zmd->zones[zone_id]; -} - /* * Reset a zone write pointer. */ @@ -1287,14 +1664,14 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone) return 0; if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) { - struct dmz_dev *dev = zmd->dev; + struct dmz_dev *dev = zone->dev; ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET, dmz_start_sect(zmd, zone), - dev->zone_nr_sectors, GFP_NOIO); + zmd->zone_nr_sectors, GFP_NOIO); if (ret) { dmz_dev_err(dev, "Reset zone %u failed %d", - dmz_id(zmd, zone), ret); + zone->id, ret); return ret; } } @@ -1313,7 +1690,6 @@ static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone); */ static int dmz_load_mapping(struct dmz_metadata *zmd) { - struct dmz_dev *dev = zmd->dev; struct dm_zone *dzone, *bzone; struct dmz_mblock *dmap_mblk = NULL; struct dmz_map *dmap; @@ -1345,36 +1721,48 @@ static int dmz_load_mapping(struct dmz_metadata *zmd) if (dzone_id == DMZ_MAP_UNMAPPED) goto next; - if (dzone_id >= dev->nr_zones) { - dmz_dev_err(dev, "Chunk %u mapping: invalid data zone ID %u", + if (dzone_id >= zmd->nr_zones) { + dmz_zmd_err(zmd, "Chunk %u mapping: invalid data zone ID %u", chunk, dzone_id); return -EIO; } dzone = dmz_get(zmd, dzone_id); + if (!dzone) { + dmz_zmd_err(zmd, "Chunk %u mapping: data zone %u not present", + chunk, dzone_id); + return -EIO; + } set_bit(DMZ_DATA, &dzone->flags); dzone->chunk = chunk; dmz_get_zone_weight(zmd, dzone); - if (dmz_is_rnd(dzone)) - list_add_tail(&dzone->link, &zmd->map_rnd_list); + if (dmz_is_cache(dzone)) + list_add_tail(&dzone->link, &zmd->map_cache_list); + else if (dmz_is_rnd(dzone)) + list_add_tail(&dzone->link, &dzone->dev->map_rnd_list); else - list_add_tail(&dzone->link, &zmd->map_seq_list); + list_add_tail(&dzone->link, &dzone->dev->map_seq_list); /* Check buffer zone */ bzone_id = le32_to_cpu(dmap[e].bzone_id); if (bzone_id == DMZ_MAP_UNMAPPED) goto next; - if (bzone_id >= dev->nr_zones) { - dmz_dev_err(dev, "Chunk %u mapping: invalid buffer zone ID %u", + if (bzone_id >= zmd->nr_zones) { + dmz_zmd_err(zmd, "Chunk %u mapping: invalid buffer zone ID %u", chunk, bzone_id); return -EIO; } bzone = dmz_get(zmd, bzone_id); - if (!dmz_is_rnd(bzone)) { - dmz_dev_err(dev, "Chunk %u mapping: invalid buffer zone %u", + if (!bzone) { + dmz_zmd_err(zmd, "Chunk %u mapping: buffer zone %u not present", + chunk, bzone_id); + return -EIO; + } + if (!dmz_is_rnd(bzone) && !dmz_is_cache(bzone)) { + dmz_zmd_err(zmd, "Chunk %u mapping: invalid buffer zone %u", chunk, bzone_id); return -EIO; } @@ -1385,7 +1773,10 @@ static int dmz_load_mapping(struct dmz_metadata *zmd) bzone->bzone = dzone; dzone->bzone = bzone; dmz_get_zone_weight(zmd, bzone); - list_add_tail(&bzone->link, &zmd->map_rnd_list); + if (dmz_is_cache(bzone)) + list_add_tail(&bzone->link, &zmd->map_cache_list); + else + list_add_tail(&bzone->link, &bzone->dev->map_rnd_list); next: chunk++; e++; @@ -1398,15 +1789,21 @@ next: * fully initialized. All remaining zones are unmapped data * zones. Finish initializing those here. */ - for (i = 0; i < dev->nr_zones; i++) { + for (i = 0; i < zmd->nr_zones; i++) { dzone = dmz_get(zmd, i); + if (!dzone) + continue; if (dmz_is_meta(dzone)) continue; + if (dmz_is_offline(dzone)) + continue; - if (dmz_is_rnd(dzone)) - zmd->nr_rnd++; + if (dmz_is_cache(dzone)) + zmd->nr_cache++; + else if (dmz_is_rnd(dzone)) + dzone->dev->nr_rnd++; else - zmd->nr_seq++; + dzone->dev->nr_seq++; if (dmz_is_data(dzone)) { /* Already initialized */ @@ -1416,16 +1813,22 @@ next: /* Unmapped data zone */ set_bit(DMZ_DATA, &dzone->flags); dzone->chunk = DMZ_MAP_UNMAPPED; - if (dmz_is_rnd(dzone)) { - list_add_tail(&dzone->link, &zmd->unmap_rnd_list); - atomic_inc(&zmd->unmap_nr_rnd); + if (dmz_is_cache(dzone)) { + list_add_tail(&dzone->link, &zmd->unmap_cache_list); + atomic_inc(&zmd->unmap_nr_cache); + } else if (dmz_is_rnd(dzone)) { + list_add_tail(&dzone->link, + &dzone->dev->unmap_rnd_list); + atomic_inc(&dzone->dev->unmap_nr_rnd); } else if (atomic_read(&zmd->nr_reserved_seq_zones) < zmd->nr_reserved_seq) { list_add_tail(&dzone->link, &zmd->reserved_seq_zones_list); + set_bit(DMZ_RESERVED, &dzone->flags); atomic_inc(&zmd->nr_reserved_seq_zones); - zmd->nr_seq--; + dzone->dev->nr_seq--; } else { - list_add_tail(&dzone->link, &zmd->unmap_seq_list); - atomic_inc(&zmd->unmap_nr_seq); + list_add_tail(&dzone->link, + &dzone->dev->unmap_seq_list); + atomic_inc(&dzone->dev->unmap_nr_seq); } } @@ -1459,10 +1862,13 @@ static void __dmz_lru_zone(struct dmz_metadata *zmd, struct dm_zone *zone) list_del_init(&zone->link); if (dmz_is_seq(zone)) { /* LRU rotate sequential zone */ - list_add_tail(&zone->link, &zmd->map_seq_list); + list_add_tail(&zone->link, &zone->dev->map_seq_list); + } else if (dmz_is_cache(zone)) { + /* LRU rotate cache zone */ + list_add_tail(&zone->link, &zmd->map_cache_list); } else { /* LRU rotate random zone */ - list_add_tail(&zone->link, &zmd->map_rnd_list); + list_add_tail(&zone->link, &zone->dev->map_rnd_list); } } @@ -1529,58 +1935,76 @@ static void dmz_wait_for_reclaim(struct dmz_metadata *zmd, struct dm_zone *zone) { dmz_unlock_map(zmd); dmz_unlock_metadata(zmd); + set_bit(DMZ_RECLAIM_TERMINATE, &zone->flags); wait_on_bit_timeout(&zone->flags, DMZ_RECLAIM, TASK_UNINTERRUPTIBLE, HZ); + clear_bit(DMZ_RECLAIM_TERMINATE, &zone->flags); dmz_lock_metadata(zmd); dmz_lock_map(zmd); } /* - * Select a random write zone for reclaim. + * Select a cache or random write zone for reclaim. */ -static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd) +static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd, + unsigned int idx, bool idle) { struct dm_zone *dzone = NULL; - struct dm_zone *zone; - - if (list_empty(&zmd->map_rnd_list)) - return ERR_PTR(-EBUSY); + struct dm_zone *zone, *last = NULL; + struct list_head *zone_list; + + /* If we have cache zones select from the cache zone list */ + if (zmd->nr_cache) { + zone_list = &zmd->map_cache_list; + /* Try to relaim random zones, too, when idle */ + if (idle && list_empty(zone_list)) + zone_list = &zmd->dev[idx].map_rnd_list; + } else + zone_list = &zmd->dev[idx].map_rnd_list; - list_for_each_entry(zone, &zmd->map_rnd_list, link) { - if (dmz_is_buf(zone)) + list_for_each_entry(zone, zone_list, link) { + if (dmz_is_buf(zone)) { dzone = zone->bzone; - else + if (dzone->dev->dev_idx != idx) + continue; + if (!last) { + last = dzone; + continue; + } + if (last->weight < dzone->weight) + continue; + dzone = last; + } else dzone = zone; if (dmz_lock_zone_reclaim(dzone)) return dzone; } - return ERR_PTR(-EBUSY); + return NULL; } /* * Select a buffered sequential zone for reclaim. */ -static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd) +static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd, + unsigned int idx) { struct dm_zone *zone; - if (list_empty(&zmd->map_seq_list)) - return ERR_PTR(-EBUSY); - - list_for_each_entry(zone, &zmd->map_seq_list, link) { + list_for_each_entry(zone, &zmd->dev[idx].map_seq_list, link) { if (!zone->bzone) continue; if (dmz_lock_zone_reclaim(zone)) return zone; } - return ERR_PTR(-EBUSY); + return NULL; } /* * Select a zone for reclaim. */ -struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd) +struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd, + unsigned int dev_idx, bool idle) { struct dm_zone *zone; @@ -1594,9 +2018,9 @@ struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd) */ dmz_lock_map(zmd); if (list_empty(&zmd->reserved_seq_zones_list)) - zone = dmz_get_seq_zone_for_reclaim(zmd); + zone = dmz_get_seq_zone_for_reclaim(zmd, dev_idx); else - zone = dmz_get_rnd_zone_for_reclaim(zmd); + zone = dmz_get_rnd_zone_for_reclaim(zmd, dev_idx, idle); dmz_unlock_map(zmd); return zone; @@ -1616,6 +2040,7 @@ struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd, unsigned int chu unsigned int dzone_id; struct dm_zone *dzone = NULL; int ret = 0; + int alloc_flags = zmd->nr_cache ? DMZ_ALLOC_CACHE : DMZ_ALLOC_RND; dmz_lock_map(zmd); again: @@ -1630,9 +2055,9 @@ again: goto out; /* Allocate a random zone */ - dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); + dzone = dmz_alloc_zone(zmd, 0, alloc_flags); if (!dzone) { - if (dmz_bdev_is_dying(zmd->dev)) { + if (dmz_dev_is_dying(zmd)) { dzone = ERR_PTR(-EIO); goto out; } @@ -1645,6 +2070,10 @@ again: } else { /* The chunk is already mapped: get the mapping zone */ dzone = dmz_get(zmd, dzone_id); + if (!dzone) { + dzone = ERR_PTR(-EIO); + goto out; + } if (dzone->chunk != chunk) { dzone = ERR_PTR(-EIO); goto out; @@ -1723,6 +2152,7 @@ struct dm_zone *dmz_get_chunk_buffer(struct dmz_metadata *zmd, struct dm_zone *dzone) { struct dm_zone *bzone; + int alloc_flags = zmd->nr_cache ? DMZ_ALLOC_CACHE : DMZ_ALLOC_RND; dmz_lock_map(zmd); again: @@ -1731,9 +2161,9 @@ again: goto out; /* Allocate a random zone */ - bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND); + bzone = dmz_alloc_zone(zmd, 0, alloc_flags); if (!bzone) { - if (dmz_bdev_is_dying(zmd->dev)) { + if (dmz_dev_is_dying(zmd)) { bzone = ERR_PTR(-EIO); goto out; } @@ -1742,14 +2172,16 @@ again: } /* Update the chunk mapping */ - dmz_set_chunk_mapping(zmd, dzone->chunk, dmz_id(zmd, dzone), - dmz_id(zmd, bzone)); + dmz_set_chunk_mapping(zmd, dzone->chunk, dzone->id, bzone->id); set_bit(DMZ_BUF, &bzone->flags); bzone->chunk = dzone->chunk; bzone->bzone = dzone; dzone->bzone = bzone; - list_add_tail(&bzone->link, &zmd->map_rnd_list); + if (dmz_is_cache(bzone)) + list_add_tail(&bzone->link, &zmd->map_cache_list); + else + list_add_tail(&bzone->link, &bzone->dev->map_rnd_list); out: dmz_unlock_map(zmd); @@ -1760,46 +2192,68 @@ out: * Get an unmapped (free) zone. * This must be called with the mapping lock held. */ -struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned long flags) +struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned int dev_idx, + unsigned long flags) { struct list_head *list; struct dm_zone *zone; + int i = 0; - if (flags & DMZ_ALLOC_RND) - list = &zmd->unmap_rnd_list; - else - list = &zmd->unmap_seq_list; again: + if (flags & DMZ_ALLOC_CACHE) + list = &zmd->unmap_cache_list; + else if (flags & DMZ_ALLOC_RND) + list = &zmd->dev[dev_idx].unmap_rnd_list; + else + list = &zmd->dev[dev_idx].unmap_seq_list; + if (list_empty(list)) { /* - * No free zone: if this is for reclaim, allow using the - * reserved sequential zones. + * No free zone: return NULL if this is for not reclaim. */ - if (!(flags & DMZ_ALLOC_RECLAIM) || - list_empty(&zmd->reserved_seq_zones_list)) + if (!(flags & DMZ_ALLOC_RECLAIM)) return NULL; + /* + * Try to allocate from other devices + */ + if (i < zmd->nr_devs) { + dev_idx = (dev_idx + 1) % zmd->nr_devs; + i++; + goto again; + } - zone = list_first_entry(&zmd->reserved_seq_zones_list, - struct dm_zone, link); - list_del_init(&zone->link); - atomic_dec(&zmd->nr_reserved_seq_zones); + /* + * Fallback to the reserved sequential zones + */ + zone = list_first_entry_or_null(&zmd->reserved_seq_zones_list, + struct dm_zone, link); + if (zone) { + list_del_init(&zone->link); + atomic_dec(&zmd->nr_reserved_seq_zones); + } return zone; } zone = list_first_entry(list, struct dm_zone, link); list_del_init(&zone->link); - if (dmz_is_rnd(zone)) - atomic_dec(&zmd->unmap_nr_rnd); + if (dmz_is_cache(zone)) + atomic_dec(&zmd->unmap_nr_cache); + else if (dmz_is_rnd(zone)) + atomic_dec(&zone->dev->unmap_nr_rnd); else - atomic_dec(&zmd->unmap_nr_seq); + atomic_dec(&zone->dev->unmap_nr_seq); if (dmz_is_offline(zone)) { - dmz_dev_warn(zmd->dev, "Zone %u is offline", dmz_id(zmd, zone)); + dmz_zmd_warn(zmd, "Zone %u is offline", zone->id); + zone = NULL; + goto again; + } + if (dmz_is_meta(zone)) { + dmz_zmd_warn(zmd, "Zone %u has metadata", zone->id); zone = NULL; goto again; } - return zone; } @@ -1814,16 +2268,18 @@ void dmz_free_zone(struct dmz_metadata *zmd, struct dm_zone *zone) dmz_reset_zone(zmd, zone); /* Return the zone to its type unmap list */ - if (dmz_is_rnd(zone)) { - list_add_tail(&zone->link, &zmd->unmap_rnd_list); - atomic_inc(&zmd->unmap_nr_rnd); - } else if (atomic_read(&zmd->nr_reserved_seq_zones) < - zmd->nr_reserved_seq) { + if (dmz_is_cache(zone)) { + list_add_tail(&zone->link, &zmd->unmap_cache_list); + atomic_inc(&zmd->unmap_nr_cache); + } else if (dmz_is_rnd(zone)) { + list_add_tail(&zone->link, &zone->dev->unmap_rnd_list); + atomic_inc(&zone->dev->unmap_nr_rnd); + } else if (dmz_is_reserved(zone)) { list_add_tail(&zone->link, &zmd->reserved_seq_zones_list); atomic_inc(&zmd->nr_reserved_seq_zones); } else { - list_add_tail(&zone->link, &zmd->unmap_seq_list); - atomic_inc(&zmd->unmap_nr_seq); + list_add_tail(&zone->link, &zone->dev->unmap_seq_list); + atomic_inc(&zone->dev->unmap_nr_seq); } wake_up_all(&zmd->free_wq); @@ -1837,13 +2293,15 @@ void dmz_map_zone(struct dmz_metadata *zmd, struct dm_zone *dzone, unsigned int chunk) { /* Set the chunk mapping */ - dmz_set_chunk_mapping(zmd, chunk, dmz_id(zmd, dzone), + dmz_set_chunk_mapping(zmd, chunk, dzone->id, DMZ_MAP_UNMAPPED); dzone->chunk = chunk; - if (dmz_is_rnd(dzone)) - list_add_tail(&dzone->link, &zmd->map_rnd_list); + if (dmz_is_cache(dzone)) + list_add_tail(&dzone->link, &zmd->map_cache_list); + else if (dmz_is_rnd(dzone)) + list_add_tail(&dzone->link, &dzone->dev->map_rnd_list); else - list_add_tail(&dzone->link, &zmd->map_seq_list); + list_add_tail(&dzone->link, &dzone->dev->map_seq_list); } /* @@ -1865,7 +2323,7 @@ void dmz_unmap_zone(struct dmz_metadata *zmd, struct dm_zone *zone) * Unmapping the chunk buffer zone: clear only * the chunk buffer mapping */ - dzone_id = dmz_id(zmd, zone->bzone); + dzone_id = zone->bzone->id; zone->bzone->bzone = NULL; zone->bzone = NULL; @@ -1927,7 +2385,7 @@ static struct dmz_mblock *dmz_get_bitmap(struct dmz_metadata *zmd, sector_t chunk_block) { sector_t bitmap_block = 1 + zmd->nr_map_blocks + - (sector_t)(dmz_id(zmd, zone) * zmd->zone_nr_bitmap_blocks) + + (sector_t)(zone->id * zmd->zone_nr_bitmap_blocks) + (chunk_block >> DMZ_BLOCK_SHIFT_BITS); return dmz_get_mblock(zmd, bitmap_block); @@ -1943,7 +2401,7 @@ int dmz_copy_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone, sector_t chunk_block = 0; /* Get the zones bitmap blocks */ - while (chunk_block < zmd->dev->zone_nr_blocks) { + while (chunk_block < zmd->zone_nr_blocks) { from_mblk = dmz_get_bitmap(zmd, from_zone, chunk_block); if (IS_ERR(from_mblk)) return PTR_ERR(from_mblk); @@ -1978,7 +2436,7 @@ int dmz_merge_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone, int ret; /* Get the zones bitmap blocks */ - while (chunk_block < zmd->dev->zone_nr_blocks) { + while (chunk_block < zmd->zone_nr_blocks) { /* Get a valid region from the source zone */ ret = dmz_first_valid_block(zmd, from_zone, &chunk_block); if (ret <= 0) @@ -2002,12 +2460,12 @@ int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone, sector_t chunk_block, unsigned int nr_blocks) { unsigned int count, bit, nr_bits; - unsigned int zone_nr_blocks = zmd->dev->zone_nr_blocks; + unsigned int zone_nr_blocks = zmd->zone_nr_blocks; struct dmz_mblock *mblk; unsigned int n = 0; - dmz_dev_debug(zmd->dev, "=> VALIDATE zone %u, block %llu, %u blocks", - dmz_id(zmd, zone), (unsigned long long)chunk_block, + dmz_zmd_debug(zmd, "=> VALIDATE zone %u, block %llu, %u blocks", + zone->id, (unsigned long long)chunk_block, nr_blocks); WARN_ON(chunk_block + nr_blocks > zone_nr_blocks); @@ -2036,8 +2494,8 @@ int dmz_validate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone, if (likely(zone->weight + n <= zone_nr_blocks)) zone->weight += n; else { - dmz_dev_warn(zmd->dev, "Zone %u: weight %u should be <= %u", - dmz_id(zmd, zone), zone->weight, + dmz_zmd_warn(zmd, "Zone %u: weight %u should be <= %u", + zone->id, zone->weight, zone_nr_blocks - n); zone->weight = zone_nr_blocks; } @@ -2086,10 +2544,10 @@ int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone, struct dmz_mblock *mblk; unsigned int n = 0; - dmz_dev_debug(zmd->dev, "=> INVALIDATE zone %u, block %llu, %u blocks", - dmz_id(zmd, zone), (u64)chunk_block, nr_blocks); + dmz_zmd_debug(zmd, "=> INVALIDATE zone %u, block %llu, %u blocks", + zone->id, (u64)chunk_block, nr_blocks); - WARN_ON(chunk_block + nr_blocks > zmd->dev->zone_nr_blocks); + WARN_ON(chunk_block + nr_blocks > zmd->zone_nr_blocks); while (nr_blocks) { /* Get bitmap block */ @@ -2116,8 +2574,8 @@ int dmz_invalidate_blocks(struct dmz_metadata *zmd, struct dm_zone *zone, if (zone->weight >= n) zone->weight -= n; else { - dmz_dev_warn(zmd->dev, "Zone %u: weight %u should be >= %u", - dmz_id(zmd, zone), zone->weight, n); + dmz_zmd_warn(zmd, "Zone %u: weight %u should be >= %u", + zone->id, zone->weight, n); zone->weight = 0; } @@ -2133,7 +2591,7 @@ static int dmz_test_block(struct dmz_metadata *zmd, struct dm_zone *zone, struct dmz_mblock *mblk; int ret; - WARN_ON(chunk_block >= zmd->dev->zone_nr_blocks); + WARN_ON(chunk_block >= zmd->zone_nr_blocks); /* Get bitmap block */ mblk = dmz_get_bitmap(zmd, zone, chunk_block); @@ -2163,7 +2621,7 @@ static int dmz_to_next_set_block(struct dmz_metadata *zmd, struct dm_zone *zone, unsigned long *bitmap; int n = 0; - WARN_ON(chunk_block + nr_blocks > zmd->dev->zone_nr_blocks); + WARN_ON(chunk_block + nr_blocks > zmd->zone_nr_blocks); while (nr_blocks) { /* Get bitmap block */ @@ -2207,7 +2665,7 @@ int dmz_block_valid(struct dmz_metadata *zmd, struct dm_zone *zone, /* The block is valid: get the number of valid blocks from block */ return dmz_to_next_set_block(zmd, zone, chunk_block, - zmd->dev->zone_nr_blocks - chunk_block, 0); + zmd->zone_nr_blocks - chunk_block, 0); } /* @@ -2223,7 +2681,7 @@ int dmz_first_valid_block(struct dmz_metadata *zmd, struct dm_zone *zone, int ret; ret = dmz_to_next_set_block(zmd, zone, start_block, - zmd->dev->zone_nr_blocks - start_block, 1); + zmd->zone_nr_blocks - start_block, 1); if (ret < 0) return ret; @@ -2231,7 +2689,7 @@ int dmz_first_valid_block(struct dmz_metadata *zmd, struct dm_zone *zone, *chunk_block = start_block; return dmz_to_next_set_block(zmd, zone, start_block, - zmd->dev->zone_nr_blocks - start_block, 0); + zmd->zone_nr_blocks - start_block, 0); } /* @@ -2270,7 +2728,7 @@ static void dmz_get_zone_weight(struct dmz_metadata *zmd, struct dm_zone *zone) struct dmz_mblock *mblk; sector_t chunk_block = 0; unsigned int bit, nr_bits; - unsigned int nr_blocks = zmd->dev->zone_nr_blocks; + unsigned int nr_blocks = zmd->zone_nr_blocks; void *bitmap; int n = 0; @@ -2326,7 +2784,7 @@ static void dmz_cleanup_metadata(struct dmz_metadata *zmd) while (!list_empty(&zmd->mblk_dirty_list)) { mblk = list_first_entry(&zmd->mblk_dirty_list, struct dmz_mblock, link); - dmz_dev_warn(zmd->dev, "mblock %llu still in dirty list (ref %u)", + dmz_zmd_warn(zmd, "mblock %llu still in dirty list (ref %u)", (u64)mblk->no, mblk->ref); list_del_init(&mblk->link); rb_erase(&mblk->node, &zmd->mblk_rbtree); @@ -2344,7 +2802,7 @@ static void dmz_cleanup_metadata(struct dmz_metadata *zmd) /* Sanity checks: the mblock rbtree should now be empty */ root = &zmd->mblk_rbtree; rbtree_postorder_for_each_entry_safe(mblk, next, root, node) { - dmz_dev_warn(zmd->dev, "mblock %llu ref %u still in rbtree", + dmz_zmd_warn(zmd, "mblock %llu ref %u still in rbtree", (u64)mblk->no, mblk->ref); mblk->ref = 0; dmz_free_mblock(zmd, mblk); @@ -2357,13 +2815,42 @@ static void dmz_cleanup_metadata(struct dmz_metadata *zmd) mutex_destroy(&zmd->map_lock); } +static void dmz_print_dev(struct dmz_metadata *zmd, int num) +{ + struct dmz_dev *dev = &zmd->dev[num]; + + if (bdev_zoned_model(dev->bdev) == BLK_ZONED_NONE) + dmz_dev_info(dev, "Regular block device"); + else + dmz_dev_info(dev, "Host-%s zoned block device", + bdev_zoned_model(dev->bdev) == BLK_ZONED_HA ? + "aware" : "managed"); + if (zmd->sb_version > 1) { + sector_t sector_offset = + dev->zone_offset << zmd->zone_nr_sectors_shift; + + dmz_dev_info(dev, " %llu 512-byte logical sectors (offset %llu)", + (u64)dev->capacity, (u64)sector_offset); + dmz_dev_info(dev, " %u zones of %llu 512-byte logical sectors (offset %llu)", + dev->nr_zones, (u64)zmd->zone_nr_sectors, + (u64)dev->zone_offset); + } else { + dmz_dev_info(dev, " %llu 512-byte logical sectors", + (u64)dev->capacity); + dmz_dev_info(dev, " %u zones of %llu 512-byte logical sectors", + dev->nr_zones, (u64)zmd->zone_nr_sectors); + } +} + /* * Initialize the zoned metadata. */ -int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **metadata) +int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev, + struct dmz_metadata **metadata, + const char *devname) { struct dmz_metadata *zmd; - unsigned int i, zid; + unsigned int i; struct dm_zone *zone; int ret; @@ -2371,7 +2858,9 @@ int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **metadata) if (!zmd) return -ENOMEM; + strcpy(zmd->devname, devname); zmd->dev = dev; + zmd->nr_devs = num_dev; zmd->mblk_rbtree = RB_ROOT; init_rwsem(&zmd->mblk_sem); mutex_init(&zmd->mblk_flush_lock); @@ -2380,13 +2869,10 @@ int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **metadata) INIT_LIST_HEAD(&zmd->mblk_dirty_list); mutex_init(&zmd->map_lock); - atomic_set(&zmd->unmap_nr_rnd, 0); - INIT_LIST_HEAD(&zmd->unmap_rnd_list); - INIT_LIST_HEAD(&zmd->map_rnd_list); - atomic_set(&zmd->unmap_nr_seq, 0); - INIT_LIST_HEAD(&zmd->unmap_seq_list); - INIT_LIST_HEAD(&zmd->map_seq_list); + atomic_set(&zmd->unmap_nr_cache, 0); + INIT_LIST_HEAD(&zmd->unmap_cache_list); + INIT_LIST_HEAD(&zmd->map_cache_list); atomic_set(&zmd->nr_reserved_seq_zones, 0); INIT_LIST_HEAD(&zmd->reserved_seq_zones_list); @@ -2404,14 +2890,22 @@ int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **metadata) goto err; /* Set metadata zones starting from sb_zone */ - zid = dmz_id(zmd, zmd->sb_zone); for (i = 0; i < zmd->nr_meta_zones << 1; i++) { - zone = dmz_get(zmd, zid + i); - if (!dmz_is_rnd(zone)) + zone = dmz_get(zmd, zmd->sb[0].zone->id + i); + if (!zone) { + dmz_zmd_err(zmd, + "metadata zone %u not present", i); + ret = -ENXIO; + goto err; + } + if (!dmz_is_rnd(zone) && !dmz_is_cache(zone)) { + dmz_zmd_err(zmd, + "metadata zone %d is not random", i); + ret = -ENXIO; goto err; + } set_bit(DMZ_META, &zone->flags); } - /* Load mapping table */ ret = dmz_load_mapping(zmd); if (ret) @@ -2432,34 +2926,38 @@ int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **metadata) /* Metadata cache shrinker */ ret = register_shrinker(&zmd->mblk_shrinker); if (ret) { - dmz_dev_err(dev, "Register metadata cache shrinker failed"); + dmz_zmd_err(zmd, "Register metadata cache shrinker failed"); goto err; } - dmz_dev_info(dev, "Host-%s zoned block device", - bdev_zoned_model(dev->bdev) == BLK_ZONED_HA ? - "aware" : "managed"); - dmz_dev_info(dev, " %llu 512-byte logical sectors", - (u64)dev->capacity); - dmz_dev_info(dev, " %u zones of %llu 512-byte logical sectors", - dev->nr_zones, (u64)dev->zone_nr_sectors); - dmz_dev_info(dev, " %u metadata zones", - zmd->nr_meta_zones * 2); - dmz_dev_info(dev, " %u data zones for %u chunks", - zmd->nr_data_zones, zmd->nr_chunks); - dmz_dev_info(dev, " %u random zones (%u unmapped)", - zmd->nr_rnd, atomic_read(&zmd->unmap_nr_rnd)); - dmz_dev_info(dev, " %u sequential zones (%u unmapped)", - zmd->nr_seq, atomic_read(&zmd->unmap_nr_seq)); - dmz_dev_info(dev, " %u reserved sequential data zones", - zmd->nr_reserved_seq); - - dmz_dev_debug(dev, "Format:"); - dmz_dev_debug(dev, "%u metadata blocks per set (%u max cache)", + dmz_zmd_info(zmd, "DM-Zoned metadata version %d", zmd->sb_version); + for (i = 0; i < zmd->nr_devs; i++) + dmz_print_dev(zmd, i); + + dmz_zmd_info(zmd, " %u zones of %llu 512-byte logical sectors", + zmd->nr_zones, (u64)zmd->zone_nr_sectors); + dmz_zmd_debug(zmd, " %u metadata zones", + zmd->nr_meta_zones * 2); + dmz_zmd_debug(zmd, " %u data zones for %u chunks", + zmd->nr_data_zones, zmd->nr_chunks); + dmz_zmd_debug(zmd, " %u cache zones (%u unmapped)", + zmd->nr_cache, atomic_read(&zmd->unmap_nr_cache)); + for (i = 0; i < zmd->nr_devs; i++) { + dmz_zmd_debug(zmd, " %u random zones (%u unmapped)", + dmz_nr_rnd_zones(zmd, i), + dmz_nr_unmap_rnd_zones(zmd, i)); + dmz_zmd_debug(zmd, " %u sequential zones (%u unmapped)", + dmz_nr_seq_zones(zmd, i), + dmz_nr_unmap_seq_zones(zmd, i)); + } + dmz_zmd_debug(zmd, " %u reserved sequential data zones", + zmd->nr_reserved_seq); + dmz_zmd_debug(zmd, "Format:"); + dmz_zmd_debug(zmd, "%u metadata blocks per set (%u max cache)", zmd->nr_meta_blocks, zmd->max_nr_mblks); - dmz_dev_debug(dev, " %u data zone mapping blocks", + dmz_zmd_debug(zmd, " %u data zone mapping blocks", zmd->nr_map_blocks); - dmz_dev_debug(dev, " %u bitmap blocks", + dmz_zmd_debug(zmd, " %u bitmap blocks", zmd->nr_bitmap_blocks); *metadata = zmd; @@ -2488,30 +2986,28 @@ void dmz_dtr_metadata(struct dmz_metadata *zmd) */ int dmz_resume_metadata(struct dmz_metadata *zmd) { - struct dmz_dev *dev = zmd->dev; struct dm_zone *zone; sector_t wp_block; unsigned int i; int ret; /* Check zones */ - for (i = 0; i < dev->nr_zones; i++) { + for (i = 0; i < zmd->nr_zones; i++) { zone = dmz_get(zmd, i); if (!zone) { - dmz_dev_err(dev, "Unable to get zone %u", i); + dmz_zmd_err(zmd, "Unable to get zone %u", i); return -EIO; } - wp_block = zone->wp_block; ret = dmz_update_zone(zmd, zone); if (ret) { - dmz_dev_err(dev, "Broken zone %u", i); + dmz_zmd_err(zmd, "Broken zone %u", i); return ret; } if (dmz_is_offline(zone)) { - dmz_dev_warn(dev, "Zone %u is offline", i); + dmz_zmd_warn(zmd, "Zone %u is offline", i); continue; } @@ -2519,11 +3015,11 @@ int dmz_resume_metadata(struct dmz_metadata *zmd) if (!dmz_is_seq(zone)) zone->wp_block = 0; else if (zone->wp_block != wp_block) { - dmz_dev_err(dev, "Zone %u: Invalid wp (%llu / %llu)", + dmz_zmd_err(zmd, "Zone %u: Invalid wp (%llu / %llu)", i, (u64)zone->wp_block, (u64)wp_block); zone->wp_block = wp_block; dmz_invalidate_blocks(zmd, zone, zone->wp_block, - dev->zone_nr_blocks - zone->wp_block); + zmd->zone_nr_blocks - zone->wp_block); } } diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index e7ace908a9b7..2261b4dd60b7 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -13,7 +13,6 @@ struct dmz_reclaim { struct dmz_metadata *metadata; - struct dmz_dev *dev; struct delayed_work work; struct workqueue_struct *wq; @@ -22,6 +21,8 @@ struct dmz_reclaim { struct dm_kcopyd_throttle kc_throttle; int kc_err; + int dev_idx; + unsigned long flags; /* Last target access time */ @@ -44,13 +45,13 @@ enum { * Percentage of unmapped (free) random zones below which reclaim starts * even if the target is busy. */ -#define DMZ_RECLAIM_LOW_UNMAP_RND 30 +#define DMZ_RECLAIM_LOW_UNMAP_ZONES 30 /* * Percentage of unmapped (free) random zones above which reclaim will * stop if the target is busy. */ -#define DMZ_RECLAIM_HIGH_UNMAP_RND 50 +#define DMZ_RECLAIM_HIGH_UNMAP_ZONES 50 /* * Align a sequential zone write pointer to chunk_block. @@ -59,6 +60,7 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, sector_t block) { struct dmz_metadata *zmd = zrc->metadata; + struct dmz_dev *dev = zone->dev; sector_t wp_block = zone->wp_block; unsigned int nr_blocks; int ret; @@ -74,15 +76,15 @@ static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone, * pointer and the requested position. */ nr_blocks = block - wp_block; - ret = blkdev_issue_zeroout(zrc->dev->bdev, + ret = blkdev_issue_zeroout(dev->bdev, dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block), dmz_blk2sect(nr_blocks), GFP_NOIO, 0); if (ret) { - dmz_dev_err(zrc->dev, + dmz_dev_err(dev, "Align zone %u wp %llu to %llu (wp+%u) blocks failed %d", - dmz_id(zmd, zone), (unsigned long long)wp_block, + zone->id, (unsigned long long)wp_block, (unsigned long long)block, nr_blocks, ret); - dmz_check_bdev(zrc->dev); + dmz_check_bdev(dev); return ret; } @@ -116,7 +118,6 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc, struct dm_zone *src_zone, struct dm_zone *dst_zone) { struct dmz_metadata *zmd = zrc->metadata; - struct dmz_dev *dev = zrc->dev; struct dm_io_region src, dst; sector_t block = 0, end_block; sector_t nr_blocks; @@ -128,7 +129,7 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc, if (dmz_is_seq(src_zone)) end_block = src_zone->wp_block; else - end_block = dev->zone_nr_blocks; + end_block = dmz_zone_nr_blocks(zmd); src_zone_block = dmz_start_block(zmd, src_zone); dst_zone_block = dmz_start_block(zmd, dst_zone); @@ -136,9 +137,14 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc, set_bit(DM_KCOPYD_WRITE_SEQ, &flags); while (block < end_block) { - if (dev->flags & DMZ_BDEV_DYING) + if (src_zone->dev->flags & DMZ_BDEV_DYING) + return -EIO; + if (dst_zone->dev->flags & DMZ_BDEV_DYING) return -EIO; + if (dmz_reclaim_should_terminate(src_zone)) + return -EINTR; + /* Get a valid region from the source zone */ ret = dmz_first_valid_block(zmd, src_zone, &block); if (ret <= 0) @@ -156,11 +162,11 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc, return ret; } - src.bdev = dev->bdev; + src.bdev = src_zone->dev->bdev; src.sector = dmz_blk2sect(src_zone_block + block); src.count = dmz_blk2sect(nr_blocks); - dst.bdev = dev->bdev; + dst.bdev = dst_zone->dev->bdev; dst.sector = dmz_blk2sect(dst_zone_block + block); dst.count = src.count; @@ -194,10 +200,10 @@ static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone) struct dmz_metadata *zmd = zrc->metadata; int ret; - dmz_dev_debug(zrc->dev, - "Chunk %u, move buf zone %u (weight %u) to data zone %u (weight %u)", - dzone->chunk, dmz_id(zmd, bzone), dmz_weight(bzone), - dmz_id(zmd, dzone), dmz_weight(dzone)); + DMDEBUG("(%s/%u): Chunk %u, move buf zone %u (weight %u) to data zone %u (weight %u)", + dmz_metadata_label(zmd), zrc->dev_idx, + dzone->chunk, bzone->id, dmz_weight(bzone), + dzone->id, dmz_weight(dzone)); /* Flush data zone into the buffer zone */ ret = dmz_reclaim_copy(zrc, bzone, dzone); @@ -210,7 +216,7 @@ static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone) ret = dmz_merge_valid_blocks(zmd, bzone, dzone, chunk_block); if (ret == 0) { /* Free the buffer zone */ - dmz_invalidate_blocks(zmd, bzone, 0, zrc->dev->zone_nr_blocks); + dmz_invalidate_blocks(zmd, bzone, 0, dmz_zone_nr_blocks(zmd)); dmz_lock_map(zmd); dmz_unmap_zone(zmd, bzone); dmz_unlock_zone_reclaim(dzone); @@ -233,10 +239,10 @@ static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone) struct dmz_metadata *zmd = zrc->metadata; int ret = 0; - dmz_dev_debug(zrc->dev, - "Chunk %u, move data zone %u (weight %u) to buf zone %u (weight %u)", - chunk, dmz_id(zmd, dzone), dmz_weight(dzone), - dmz_id(zmd, bzone), dmz_weight(bzone)); + DMDEBUG("(%s/%u): Chunk %u, move data zone %u (weight %u) to buf zone %u (weight %u)", + dmz_metadata_label(zmd), zrc->dev_idx, + chunk, dzone->id, dmz_weight(dzone), + bzone->id, dmz_weight(bzone)); /* Flush data zone into the buffer zone */ ret = dmz_reclaim_copy(zrc, dzone, bzone); @@ -252,7 +258,7 @@ static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone) * Free the data zone and remap the chunk to * the buffer zone. */ - dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks); + dmz_invalidate_blocks(zmd, dzone, 0, dmz_zone_nr_blocks(zmd)); dmz_lock_map(zmd); dmz_unmap_zone(zmd, bzone); dmz_unmap_zone(zmd, dzone); @@ -277,18 +283,26 @@ static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone) struct dm_zone *szone = NULL; struct dmz_metadata *zmd = zrc->metadata; int ret; + int alloc_flags = DMZ_ALLOC_SEQ; - /* Get a free sequential zone */ + /* Get a free random or sequential zone */ dmz_lock_map(zmd); - szone = dmz_alloc_zone(zmd, DMZ_ALLOC_RECLAIM); +again: + szone = dmz_alloc_zone(zmd, zrc->dev_idx, + alloc_flags | DMZ_ALLOC_RECLAIM); + if (!szone && alloc_flags == DMZ_ALLOC_SEQ && dmz_nr_cache_zones(zmd)) { + alloc_flags = DMZ_ALLOC_RND; + goto again; + } dmz_unlock_map(zmd); if (!szone) return -ENOSPC; - dmz_dev_debug(zrc->dev, - "Chunk %u, move rnd zone %u (weight %u) to seq zone %u", - chunk, dmz_id(zmd, dzone), dmz_weight(dzone), - dmz_id(zmd, szone)); + DMDEBUG("(%s/%u): Chunk %u, move %s zone %u (weight %u) to %s zone %u", + dmz_metadata_label(zmd), zrc->dev_idx, chunk, + dmz_is_cache(dzone) ? "cache" : "rnd", + dzone->id, dmz_weight(dzone), + dmz_is_rnd(szone) ? "rnd" : "seq", szone->id); /* Flush the random data zone into the sequential zone */ ret = dmz_reclaim_copy(zrc, dzone, szone); @@ -306,7 +320,7 @@ static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone) dmz_unlock_map(zmd); } else { /* Free the data zone and remap the chunk */ - dmz_invalidate_blocks(zmd, dzone, 0, zrc->dev->zone_nr_blocks); + dmz_invalidate_blocks(zmd, dzone, 0, dmz_zone_nr_blocks(zmd)); dmz_lock_map(zmd); dmz_unmap_zone(zmd, dzone); dmz_unlock_zone_reclaim(dzone); @@ -337,6 +351,14 @@ static void dmz_reclaim_empty(struct dmz_reclaim *zrc, struct dm_zone *dzone) } /* + * Test if the target device is idle. + */ +static inline int dmz_target_idle(struct dmz_reclaim *zrc) +{ + return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD); +} + +/* * Find a candidate zone for reclaim and process it. */ static int dmz_do_reclaim(struct dmz_reclaim *zrc) @@ -348,13 +370,16 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) int ret; /* Get a data zone */ - dzone = dmz_get_zone_for_reclaim(zmd); - if (IS_ERR(dzone)) - return PTR_ERR(dzone); + dzone = dmz_get_zone_for_reclaim(zmd, zrc->dev_idx, + dmz_target_idle(zrc)); + if (!dzone) { + DMDEBUG("(%s/%u): No zone found to reclaim", + dmz_metadata_label(zmd), zrc->dev_idx); + return -EBUSY; + } start = jiffies; - - if (dmz_is_rnd(dzone)) { + if (dmz_is_cache(dzone) || dmz_is_rnd(dzone)) { if (!dmz_weight(dzone)) { /* Empty zone */ dmz_reclaim_empty(zrc, dzone); @@ -395,54 +420,80 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc) } out: if (ret) { + if (ret == -EINTR) + DMDEBUG("(%s/%u): reclaim zone %u interrupted", + dmz_metadata_label(zmd), zrc->dev_idx, + rzone->id); + else + DMDEBUG("(%s/%u): Failed to reclaim zone %u, err %d", + dmz_metadata_label(zmd), zrc->dev_idx, + rzone->id, ret); dmz_unlock_zone_reclaim(dzone); return ret; } ret = dmz_flush_metadata(zrc->metadata); if (ret) { - dmz_dev_debug(zrc->dev, - "Metadata flush for zone %u failed, err %d\n", - dmz_id(zmd, rzone), ret); + DMDEBUG("(%s/%u): Metadata flush for zone %u failed, err %d", + dmz_metadata_label(zmd), zrc->dev_idx, rzone->id, ret); return ret; } - dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms", - dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start)); + DMDEBUG("(%s/%u): Reclaimed zone %u in %u ms", + dmz_metadata_label(zmd), zrc->dev_idx, + rzone->id, jiffies_to_msecs(jiffies - start)); return 0; } -/* - * Test if the target device is idle. - */ -static inline int dmz_target_idle(struct dmz_reclaim *zrc) +static unsigned int dmz_reclaim_percentage(struct dmz_reclaim *zrc) { - return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD); + struct dmz_metadata *zmd = zrc->metadata; + unsigned int nr_cache = dmz_nr_cache_zones(zmd); + unsigned int nr_unmap, nr_zones; + + if (nr_cache) { + nr_zones = nr_cache; + nr_unmap = dmz_nr_unmap_cache_zones(zmd); + } else { + nr_zones = dmz_nr_rnd_zones(zmd, zrc->dev_idx); + nr_unmap = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx); + } + return nr_unmap * 100 / nr_zones; } /* * Test if reclaim is necessary. */ -static bool dmz_should_reclaim(struct dmz_reclaim *zrc) +static bool dmz_should_reclaim(struct dmz_reclaim *zrc, unsigned int p_unmap) { - struct dmz_metadata *zmd = zrc->metadata; - unsigned int nr_rnd = dmz_nr_rnd_zones(zmd); - unsigned int nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd); - unsigned int p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd; + unsigned int nr_reclaim; + + nr_reclaim = dmz_nr_rnd_zones(zrc->metadata, zrc->dev_idx); + + if (dmz_nr_cache_zones(zrc->metadata)) { + /* + * The first device in a multi-device + * setup only contains cache zones, so + * never start reclaim there. + */ + if (zrc->dev_idx == 0) + return false; + nr_reclaim += dmz_nr_cache_zones(zrc->metadata); + } /* Reclaim when idle */ - if (dmz_target_idle(zrc) && nr_unmap_rnd < nr_rnd) + if (dmz_target_idle(zrc) && nr_reclaim) return true; - /* If there are still plenty of random zones, do not reclaim */ - if (p_unmap_rnd >= DMZ_RECLAIM_HIGH_UNMAP_RND) + /* If there are still plenty of cache zones, do not reclaim */ + if (p_unmap >= DMZ_RECLAIM_HIGH_UNMAP_ZONES) return false; /* - * If the percentage of unmapped random zones is low, + * If the percentage of unmapped cache zones is low, * reclaim even if the target is busy. */ - return p_unmap_rnd <= DMZ_RECLAIM_LOW_UNMAP_RND; + return p_unmap <= DMZ_RECLAIM_LOW_UNMAP_ZONES; } /* @@ -452,14 +503,14 @@ static void dmz_reclaim_work(struct work_struct *work) { struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work); struct dmz_metadata *zmd = zrc->metadata; - unsigned int nr_rnd, nr_unmap_rnd; - unsigned int p_unmap_rnd; + unsigned int p_unmap, nr_unmap_rnd = 0, nr_rnd = 0; int ret; - if (dmz_bdev_is_dying(zrc->dev)) + if (dmz_dev_is_dying(zmd)) return; - if (!dmz_should_reclaim(zrc)) { + p_unmap = dmz_reclaim_percentage(zrc); + if (!dmz_should_reclaim(zrc, p_unmap)) { mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD); return; } @@ -470,27 +521,29 @@ static void dmz_reclaim_work(struct work_struct *work) * and slower if there are still some free random zones to avoid * as much as possible to negatively impact the user workload. */ - nr_rnd = dmz_nr_rnd_zones(zmd); - nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd); - p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd; - if (dmz_target_idle(zrc) || p_unmap_rnd < DMZ_RECLAIM_LOW_UNMAP_RND / 2) { + if (dmz_target_idle(zrc) || p_unmap < DMZ_RECLAIM_LOW_UNMAP_ZONES / 2) { /* Idle or very low percentage: go fast */ zrc->kc_throttle.throttle = 100; } else { /* Busy but we still have some random zone: throttle */ - zrc->kc_throttle.throttle = min(75U, 100U - p_unmap_rnd / 2); + zrc->kc_throttle.throttle = min(75U, 100U - p_unmap / 2); } - dmz_dev_debug(zrc->dev, - "Reclaim (%u): %s, %u%% free rnd zones (%u/%u)", - zrc->kc_throttle.throttle, - (dmz_target_idle(zrc) ? "Idle" : "Busy"), - p_unmap_rnd, nr_unmap_rnd, nr_rnd); + nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx); + nr_rnd = dmz_nr_rnd_zones(zmd, zrc->dev_idx); + + DMDEBUG("(%s/%u): Reclaim (%u): %s, %u%% free zones (%u/%u cache %u/%u random)", + dmz_metadata_label(zmd), zrc->dev_idx, + zrc->kc_throttle.throttle, + (dmz_target_idle(zrc) ? "Idle" : "Busy"), + p_unmap, dmz_nr_unmap_cache_zones(zmd), + dmz_nr_cache_zones(zmd), + dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx), + dmz_nr_rnd_zones(zmd, zrc->dev_idx)); ret = dmz_do_reclaim(zrc); - if (ret) { - dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret); - if (!dmz_check_bdev(zrc->dev)) + if (ret && ret != -EINTR) { + if (!dmz_check_dev(zmd)) return; } @@ -500,8 +553,8 @@ static void dmz_reclaim_work(struct work_struct *work) /* * Initialize reclaim. */ -int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd, - struct dmz_reclaim **reclaim) +int dmz_ctr_reclaim(struct dmz_metadata *zmd, + struct dmz_reclaim **reclaim, int idx) { struct dmz_reclaim *zrc; int ret; @@ -510,9 +563,9 @@ int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd, if (!zrc) return -ENOMEM; - zrc->dev = dev; zrc->metadata = zmd; zrc->atime = jiffies; + zrc->dev_idx = idx; /* Reclaim kcopyd client */ zrc->kc = dm_kcopyd_client_create(&zrc->kc_throttle); @@ -524,8 +577,8 @@ int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd, /* Reclaim work */ INIT_DELAYED_WORK(&zrc->work, dmz_reclaim_work); - zrc->wq = alloc_ordered_workqueue("dmz_rwq_%s", WQ_MEM_RECLAIM, - dev->name); + zrc->wq = alloc_ordered_workqueue("dmz_rwq_%s_%d", WQ_MEM_RECLAIM, + dmz_metadata_label(zmd), idx); if (!zrc->wq) { ret = -ENOMEM; goto err; @@ -583,7 +636,8 @@ void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc) */ void dmz_schedule_reclaim(struct dmz_reclaim *zrc) { - if (dmz_should_reclaim(zrc)) + unsigned int p_unmap = dmz_reclaim_percentage(zrc); + + if (dmz_should_reclaim(zrc, p_unmap)) mod_delayed_work(zrc->wq, &zrc->work, 0); } - diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index f4f83d39b3dc..a907a9446c0b 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -17,7 +17,7 @@ * Zone BIO context. */ struct dmz_bioctx { - struct dmz_target *target; + struct dmz_dev *dev; struct dm_zone *zone; struct bio *bio; refcount_t ref; @@ -38,9 +38,10 @@ struct dm_chunk_work { * Target descriptor. */ struct dmz_target { - struct dm_dev *ddev; + struct dm_dev **ddev; + unsigned int nr_ddevs; - unsigned long flags; + unsigned int flags; /* Zoned block device information */ struct dmz_dev *dev; @@ -48,9 +49,6 @@ struct dmz_target { /* For metadata handling */ struct dmz_metadata *metadata; - /* For reclaim */ - struct dmz_reclaim *reclaim; - /* For chunk work */ struct radix_tree_root chunk_rxtree; struct workqueue_struct *chunk_wq; @@ -76,12 +74,13 @@ struct dmz_target { */ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) { - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_bioctx *bioctx = + dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) bio->bi_status = status; - if (bio->bi_status != BLK_STS_OK) - bioctx->target->dev->flags |= DMZ_CHECK_BDEV; + if (bioctx->dev && bio->bi_status != BLK_STS_OK) + bioctx->dev->flags |= DMZ_CHECK_BDEV; if (refcount_dec_and_test(&bioctx->ref)) { struct dm_zone *zone = bioctx->zone; @@ -118,14 +117,20 @@ static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone, struct bio *bio, sector_t chunk_block, unsigned int nr_blocks) { - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_bioctx *bioctx = + dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_dev *dev = zone->dev; struct bio *clone; + if (dev->flags & DMZ_BDEV_DYING) + return -EIO; + clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set); if (!clone) return -ENOMEM; - bio_set_dev(clone, dmz->dev->bdev); + bio_set_dev(clone, dev->bdev); + bioctx->dev = dev; clone->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT; @@ -165,7 +170,8 @@ static void dmz_handle_read_zero(struct dmz_target *dmz, struct bio *bio, static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, struct bio *bio) { - sector_t chunk_block = dmz_chunk_block(dmz->dev, dmz_bio_block(bio)); + struct dmz_metadata *zmd = dmz->metadata; + sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio)); unsigned int nr_blocks = dmz_bio_blocks(bio); sector_t end_block = chunk_block + nr_blocks; struct dm_zone *rzone, *bzone; @@ -177,19 +183,22 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, return 0; } - dmz_dev_debug(dmz->dev, "READ chunk %llu -> %s zone %u, block %llu, %u blocks", - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - (dmz_is_rnd(zone) ? "RND" : "SEQ"), - dmz_id(dmz->metadata, zone), - (unsigned long long)chunk_block, nr_blocks); + DMDEBUG("(%s): READ chunk %llu -> %s zone %u, block %llu, %u blocks", + dmz_metadata_label(zmd), + (unsigned long long)dmz_bio_chunk(zmd, bio), + (dmz_is_rnd(zone) ? "RND" : + (dmz_is_cache(zone) ? "CACHE" : "SEQ")), + zone->id, + (unsigned long long)chunk_block, nr_blocks); /* Check block validity to determine the read location */ bzone = zone->bzone; while (chunk_block < end_block) { nr_blocks = 0; - if (dmz_is_rnd(zone) || chunk_block < zone->wp_block) { + if (dmz_is_rnd(zone) || dmz_is_cache(zone) || + chunk_block < zone->wp_block) { /* Test block validity in the data zone */ - ret = dmz_block_valid(dmz->metadata, zone, chunk_block); + ret = dmz_block_valid(zmd, zone, chunk_block); if (ret < 0) return ret; if (ret > 0) { @@ -204,7 +213,7 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, * Check the buffer zone, if there is one. */ if (!nr_blocks && bzone) { - ret = dmz_block_valid(dmz->metadata, bzone, chunk_block); + ret = dmz_block_valid(zmd, bzone, chunk_block); if (ret < 0) return ret; if (ret > 0) { @@ -216,8 +225,10 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, if (nr_blocks) { /* Valid blocks found: read them */ - nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block); - ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks); + nr_blocks = min_t(unsigned int, nr_blocks, + end_block - chunk_block); + ret = dmz_submit_bio(dmz, rzone, bio, + chunk_block, nr_blocks); if (ret) return ret; chunk_block += nr_blocks; @@ -308,25 +319,30 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz, static int dmz_handle_write(struct dmz_target *dmz, struct dm_zone *zone, struct bio *bio) { - sector_t chunk_block = dmz_chunk_block(dmz->dev, dmz_bio_block(bio)); + struct dmz_metadata *zmd = dmz->metadata; + sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio)); unsigned int nr_blocks = dmz_bio_blocks(bio); if (!zone) return -ENOSPC; - dmz_dev_debug(dmz->dev, "WRITE chunk %llu -> %s zone %u, block %llu, %u blocks", - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - (dmz_is_rnd(zone) ? "RND" : "SEQ"), - dmz_id(dmz->metadata, zone), - (unsigned long long)chunk_block, nr_blocks); + DMDEBUG("(%s): WRITE chunk %llu -> %s zone %u, block %llu, %u blocks", + dmz_metadata_label(zmd), + (unsigned long long)dmz_bio_chunk(zmd, bio), + (dmz_is_rnd(zone) ? "RND" : + (dmz_is_cache(zone) ? "CACHE" : "SEQ")), + zone->id, + (unsigned long long)chunk_block, nr_blocks); - if (dmz_is_rnd(zone) || chunk_block == zone->wp_block) { + if (dmz_is_rnd(zone) || dmz_is_cache(zone) || + chunk_block == zone->wp_block) { /* * zone is a random zone or it is a sequential zone * and the BIO is aligned to the zone write pointer: * direct write the zone. */ - return dmz_handle_direct_write(dmz, zone, bio, chunk_block, nr_blocks); + return dmz_handle_direct_write(dmz, zone, bio, + chunk_block, nr_blocks); } /* @@ -345,7 +361,7 @@ static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone, struct dmz_metadata *zmd = dmz->metadata; sector_t block = dmz_bio_block(bio); unsigned int nr_blocks = dmz_bio_blocks(bio); - sector_t chunk_block = dmz_chunk_block(dmz->dev, block); + sector_t chunk_block = dmz_chunk_block(zmd, block); int ret = 0; /* For unmapped chunks, there is nothing to do */ @@ -355,16 +371,18 @@ static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone, if (dmz_is_readonly(zone)) return -EROFS; - dmz_dev_debug(dmz->dev, "DISCARD chunk %llu -> zone %u, block %llu, %u blocks", - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - dmz_id(zmd, zone), - (unsigned long long)chunk_block, nr_blocks); + DMDEBUG("(%s): DISCARD chunk %llu -> zone %u, block %llu, %u blocks", + dmz_metadata_label(dmz->metadata), + (unsigned long long)dmz_bio_chunk(zmd, bio), + zone->id, + (unsigned long long)chunk_block, nr_blocks); /* * Invalidate blocks in the data zone and its * buffer zone if one is mapped. */ - if (dmz_is_rnd(zone) || chunk_block < zone->wp_block) + if (dmz_is_rnd(zone) || dmz_is_cache(zone) || + chunk_block < zone->wp_block) ret = dmz_invalidate_blocks(zmd, zone, chunk_block, nr_blocks); if (ret == 0 && zone->bzone) ret = dmz_invalidate_blocks(zmd, zone->bzone, @@ -378,31 +396,28 @@ static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone, static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, struct bio *bio) { - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); + struct dmz_bioctx *bioctx = + dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); struct dmz_metadata *zmd = dmz->metadata; struct dm_zone *zone; - int ret; + int i, ret; /* * Write may trigger a zone allocation. So make sure the * allocation can succeed. */ if (bio_op(bio) == REQ_OP_WRITE) - dmz_schedule_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_schedule_reclaim(dmz->dev[i].reclaim); dmz_lock_metadata(zmd); - if (dmz->dev->flags & DMZ_BDEV_DYING) { - ret = -EIO; - goto out; - } - /* * Get the data zone mapping the chunk. There may be no * mapping for read and discard. If a mapping is obtained, + the zone returned will be set to active state. */ - zone = dmz_get_chunk_mapping(zmd, dmz_bio_chunk(dmz->dev, bio), + zone = dmz_get_chunk_mapping(zmd, dmz_bio_chunk(zmd, bio), bio_op(bio)); if (IS_ERR(zone)) { ret = PTR_ERR(zone); @@ -413,6 +428,7 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, if (zone) { dmz_activate_zone(zone); bioctx->zone = zone; + dmz_reclaim_bio_acc(zone->dev->reclaim); } switch (bio_op(bio)) { @@ -427,8 +443,8 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw, ret = dmz_handle_discard(dmz, zone, bio); break; default: - dmz_dev_err(dmz->dev, "Unsupported BIO operation 0x%x", - bio_op(bio)); + DMERR("(%s): Unsupported BIO operation 0x%x", + dmz_metadata_label(dmz->metadata), bio_op(bio)); ret = -EIO; } @@ -502,7 +518,8 @@ static void dmz_flush_work(struct work_struct *work) /* Flush dirty metadata blocks */ ret = dmz_flush_metadata(dmz->metadata); if (ret) - dmz_dev_debug(dmz->dev, "Metadata flush failed, rc=%d\n", ret); + DMDEBUG("(%s): Metadata flush failed, rc=%d", + dmz_metadata_label(dmz->metadata), ret); /* Process queued flush requests */ while (1) { @@ -525,7 +542,7 @@ static void dmz_flush_work(struct work_struct *work) */ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) { - unsigned int chunk = dmz_bio_chunk(dmz->dev, bio); + unsigned int chunk = dmz_bio_chunk(dmz->metadata, bio); struct dm_chunk_work *cw; int ret = 0; @@ -558,7 +575,6 @@ static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) bio_list_add(&cw->bio_list, bio); - dmz_reclaim_bio_acc(dmz->reclaim); if (queue_work(dmz->chunk_wq, &cw->work)) dmz_get_chunk_work(cw); out: @@ -618,23 +634,22 @@ bool dmz_check_bdev(struct dmz_dev *dmz_dev) static int dmz_map(struct dm_target *ti, struct bio *bio) { struct dmz_target *dmz = ti->private; - struct dmz_dev *dev = dmz->dev; + struct dmz_metadata *zmd = dmz->metadata; struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); sector_t sector = bio->bi_iter.bi_sector; unsigned int nr_sectors = bio_sectors(bio); sector_t chunk_sector; int ret; - if (dmz_bdev_is_dying(dmz->dev)) + if (dmz_dev_is_dying(zmd)) return DM_MAPIO_KILL; - dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks", - bio_op(bio), (unsigned long long)sector, nr_sectors, - (unsigned long long)dmz_bio_chunk(dmz->dev, bio), - (unsigned long long)dmz_chunk_block(dmz->dev, dmz_bio_block(bio)), - (unsigned int)dmz_bio_blocks(bio)); - - bio_set_dev(bio, dev->bdev); + DMDEBUG("(%s): BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks", + dmz_metadata_label(zmd), + bio_op(bio), (unsigned long long)sector, nr_sectors, + (unsigned long long)dmz_bio_chunk(zmd, bio), + (unsigned long long)dmz_chunk_block(zmd, dmz_bio_block(bio)), + (unsigned int)dmz_bio_blocks(bio)); if (!nr_sectors && bio_op(bio) != REQ_OP_WRITE) return DM_MAPIO_REMAPPED; @@ -644,7 +659,7 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_KILL; /* Initialize the BIO context */ - bioctx->target = dmz; + bioctx->dev = NULL; bioctx->zone = NULL; bioctx->bio = bio; refcount_set(&bioctx->ref, 1); @@ -659,17 +674,17 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) } /* Split zone BIOs to fit entirely into a zone */ - chunk_sector = sector & (dev->zone_nr_sectors - 1); - if (chunk_sector + nr_sectors > dev->zone_nr_sectors) - dm_accept_partial_bio(bio, dev->zone_nr_sectors - chunk_sector); + chunk_sector = sector & (dmz_zone_nr_sectors(zmd) - 1); + if (chunk_sector + nr_sectors > dmz_zone_nr_sectors(zmd)) + dm_accept_partial_bio(bio, dmz_zone_nr_sectors(zmd) - chunk_sector); /* Now ready to handle this BIO */ ret = dmz_queue_chunk_work(dmz, bio); if (ret) { - dmz_dev_debug(dmz->dev, - "BIO op %d, can't process chunk %llu, err %i\n", - bio_op(bio), (u64)dmz_bio_chunk(dmz->dev, bio), - ret); + DMDEBUG("(%s): BIO op %d, can't process chunk %llu, err %i", + dmz_metadata_label(zmd), + bio_op(bio), (u64)dmz_bio_chunk(zmd, bio), + ret); return DM_MAPIO_REQUEUE; } @@ -679,64 +694,65 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) /* * Get zoned device information. */ -static int dmz_get_zoned_device(struct dm_target *ti, char *path) +static int dmz_get_zoned_device(struct dm_target *ti, char *path, + int idx, int nr_devs) { struct dmz_target *dmz = ti->private; - struct request_queue *q; + struct dm_dev *ddev; struct dmz_dev *dev; - sector_t aligned_capacity; int ret; + struct block_device *bdev; /* Get the target device */ - ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &dmz->ddev); + ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &ddev); if (ret) { ti->error = "Get target device failed"; - dmz->ddev = NULL; return ret; } - dev = kzalloc(sizeof(struct dmz_dev), GFP_KERNEL); - if (!dev) { - ret = -ENOMEM; - goto err; + bdev = ddev->bdev; + if (bdev_zoned_model(bdev) == BLK_ZONED_NONE) { + if (nr_devs == 1) { + ti->error = "Invalid regular device"; + goto err; + } + if (idx != 0) { + ti->error = "First device must be a regular device"; + goto err; + } + if (dmz->ddev[0]) { + ti->error = "Too many regular devices"; + goto err; + } + dev = &dmz->dev[idx]; + dev->flags = DMZ_BDEV_REGULAR; + } else { + if (dmz->ddev[idx]) { + ti->error = "Too many zoned devices"; + goto err; + } + if (nr_devs > 1 && idx == 0) { + ti->error = "First device must be a regular device"; + goto err; + } + dev = &dmz->dev[idx]; } - - dev->bdev = dmz->ddev->bdev; + dev->bdev = bdev; + dev->dev_idx = idx; (void)bdevname(dev->bdev, dev->name); - if (bdev_zoned_model(dev->bdev) == BLK_ZONED_NONE) { - ti->error = "Not a zoned block device"; - ret = -EINVAL; + dev->capacity = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + if (ti->begin) { + ti->error = "Partial mapping is not supported"; goto err; } - q = bdev_get_queue(dev->bdev); - dev->capacity = i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; - aligned_capacity = dev->capacity & - ~((sector_t)blk_queue_zone_sectors(q) - 1); - if (ti->begin || - ((ti->len != dev->capacity) && (ti->len != aligned_capacity))) { - ti->error = "Partial mapping not supported"; - ret = -EINVAL; - goto err; - } - - dev->zone_nr_sectors = blk_queue_zone_sectors(q); - dev->zone_nr_sectors_shift = ilog2(dev->zone_nr_sectors); - - dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors); - dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks); - - dev->nr_zones = blkdev_nr_zones(dev->bdev->bd_disk); - - dmz->dev = dev; + dmz->ddev[idx] = ddev; return 0; err: - dm_put_device(ti, dmz->ddev); - kfree(dev); - - return ret; + dm_put_device(ti, ddev); + return -EINVAL; } /* @@ -745,10 +761,78 @@ err: static void dmz_put_zoned_device(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; - dm_put_device(ti, dmz->ddev); - kfree(dmz->dev); - dmz->dev = NULL; + for (i = 0; i < dmz->nr_ddevs; i++) { + if (dmz->ddev[i]) { + dm_put_device(ti, dmz->ddev[i]); + dmz->ddev[i] = NULL; + } + } +} + +static int dmz_fixup_devices(struct dm_target *ti) +{ + struct dmz_target *dmz = ti->private; + struct dmz_dev *reg_dev, *zoned_dev; + struct request_queue *q; + sector_t zone_nr_sectors = 0; + int i; + + /* + * When we have more than on devices, the first one must be a + * regular block device and the others zoned block devices. + */ + if (dmz->nr_ddevs > 1) { + reg_dev = &dmz->dev[0]; + if (!(reg_dev->flags & DMZ_BDEV_REGULAR)) { + ti->error = "Primary disk is not a regular device"; + return -EINVAL; + } + for (i = 1; i < dmz->nr_ddevs; i++) { + zoned_dev = &dmz->dev[i]; + if (zoned_dev->flags & DMZ_BDEV_REGULAR) { + ti->error = "Secondary disk is not a zoned device"; + return -EINVAL; + } + q = bdev_get_queue(zoned_dev->bdev); + if (zone_nr_sectors && + zone_nr_sectors != blk_queue_zone_sectors(q)) { + ti->error = "Zone nr sectors mismatch"; + return -EINVAL; + } + zone_nr_sectors = blk_queue_zone_sectors(q); + zoned_dev->zone_nr_sectors = zone_nr_sectors; + zoned_dev->nr_zones = + blkdev_nr_zones(zoned_dev->bdev->bd_disk); + } + } else { + reg_dev = NULL; + zoned_dev = &dmz->dev[0]; + if (zoned_dev->flags & DMZ_BDEV_REGULAR) { + ti->error = "Disk is not a zoned device"; + return -EINVAL; + } + q = bdev_get_queue(zoned_dev->bdev); + zoned_dev->zone_nr_sectors = blk_queue_zone_sectors(q); + zoned_dev->nr_zones = blkdev_nr_zones(zoned_dev->bdev->bd_disk); + } + + if (reg_dev) { + sector_t zone_offset; + + reg_dev->zone_nr_sectors = zone_nr_sectors; + reg_dev->nr_zones = + DIV_ROUND_UP_SECTOR_T(reg_dev->capacity, + reg_dev->zone_nr_sectors); + reg_dev->zone_offset = 0; + zone_offset = reg_dev->nr_zones; + for (i = 1; i < dmz->nr_ddevs; i++) { + dmz->dev[i].zone_offset = zone_offset; + zone_offset += dmz->dev[i].nr_zones; + } + } + return 0; } /* @@ -757,11 +841,10 @@ static void dmz_put_zoned_device(struct dm_target *ti) static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct dmz_target *dmz; - struct dmz_dev *dev; - int ret; + int ret, i; /* Check arguments */ - if (argc != 1) { + if (argc < 1) { ti->error = "Invalid argument count"; return -EINVAL; } @@ -772,25 +855,42 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->error = "Unable to allocate the zoned target descriptor"; return -ENOMEM; } + dmz->dev = kcalloc(argc, sizeof(struct dmz_dev), GFP_KERNEL); + if (!dmz->dev) { + ti->error = "Unable to allocate the zoned device descriptors"; + kfree(dmz); + return -ENOMEM; + } + dmz->ddev = kcalloc(argc, sizeof(struct dm_dev *), GFP_KERNEL); + if (!dmz->ddev) { + ti->error = "Unable to allocate the dm device descriptors"; + ret = -ENOMEM; + goto err; + } + dmz->nr_ddevs = argc; + ti->private = dmz; /* Get the target zoned block device */ - ret = dmz_get_zoned_device(ti, argv[0]); - if (ret) { - dmz->ddev = NULL; - goto err; + for (i = 0; i < argc; i++) { + ret = dmz_get_zoned_device(ti, argv[i], i, argc); + if (ret) + goto err_dev; } + ret = dmz_fixup_devices(ti); + if (ret) + goto err_dev; /* Initialize metadata */ - dev = dmz->dev; - ret = dmz_ctr_metadata(dev, &dmz->metadata); + ret = dmz_ctr_metadata(dmz->dev, argc, &dmz->metadata, + dm_table_device_name(ti->table)); if (ret) { ti->error = "Metadata initialization failed"; goto err_dev; } /* Set target (no write same support) */ - ti->max_io_len = dev->zone_nr_sectors << 9; + ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata) << 9; ti->num_flush_bios = 1; ti->num_discard_bios = 1; ti->num_write_zeroes_bios = 1; @@ -799,7 +899,8 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->discards_supported = true; /* The exposed capacity is the number of chunks that can be mapped */ - ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << dev->zone_nr_sectors_shift; + ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << + dmz_zone_nr_sectors_shift(dmz->metadata); /* Zone BIO */ ret = bioset_init(&dmz->bio_set, DMZ_MIN_BIOS, 0, 0); @@ -811,8 +912,9 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* Chunk BIO work */ mutex_init(&dmz->chunk_lock); INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO); - dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND, - 0, dev->name); + dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", + WQ_MEM_RECLAIM | WQ_UNBOUND, 0, + dmz_metadata_label(dmz->metadata)); if (!dmz->chunk_wq) { ti->error = "Create chunk workqueue failed"; ret = -ENOMEM; @@ -824,7 +926,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) bio_list_init(&dmz->flush_list); INIT_DELAYED_WORK(&dmz->flush_work, dmz_flush_work); dmz->flush_wq = alloc_ordered_workqueue("dmz_fwq_%s", WQ_MEM_RECLAIM, - dev->name); + dmz_metadata_label(dmz->metadata)); if (!dmz->flush_wq) { ti->error = "Create flush workqueue failed"; ret = -ENOMEM; @@ -833,15 +935,18 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) mod_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD); /* Initialize reclaim */ - ret = dmz_ctr_reclaim(dev, dmz->metadata, &dmz->reclaim); - if (ret) { - ti->error = "Zone reclaim initialization failed"; - goto err_fwq; + for (i = 0; i < dmz->nr_ddevs; i++) { + ret = dmz_ctr_reclaim(dmz->metadata, &dmz->dev[i].reclaim, i); + if (ret) { + ti->error = "Zone reclaim initialization failed"; + goto err_fwq; + } } - dmz_dev_info(dev, "Target device: %llu 512-byte logical sectors (%llu blocks)", - (unsigned long long)ti->len, - (unsigned long long)dmz_sect2blk(ti->len)); + DMINFO("(%s): Target device: %llu 512-byte logical sectors (%llu blocks)", + dmz_metadata_label(dmz->metadata), + (unsigned long long)ti->len, + (unsigned long long)dmz_sect2blk(ti->len)); return 0; err_fwq: @@ -856,6 +961,7 @@ err_meta: err_dev: dmz_put_zoned_device(ti); err: + kfree(dmz->dev); kfree(dmz); return ret; @@ -867,11 +973,13 @@ err: static void dmz_dtr(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; flush_workqueue(dmz->chunk_wq); destroy_workqueue(dmz->chunk_wq); - dmz_dtr_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_dtr_reclaim(dmz->dev[i].reclaim); cancel_delayed_work_sync(&dmz->flush_work); destroy_workqueue(dmz->flush_wq); @@ -886,6 +994,7 @@ static void dmz_dtr(struct dm_target *ti) mutex_destroy(&dmz->chunk_lock); + kfree(dmz->dev); kfree(dmz); } @@ -895,7 +1004,7 @@ static void dmz_dtr(struct dm_target *ti) static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct dmz_target *dmz = ti->private; - unsigned int chunk_sectors = dmz->dev->zone_nr_sectors; + unsigned int chunk_sectors = dmz_zone_nr_sectors(dmz->metadata); limits->logical_block_size = DMZ_BLOCK_SIZE; limits->physical_block_size = DMZ_BLOCK_SIZE; @@ -923,11 +1032,12 @@ static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits) static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) { struct dmz_target *dmz = ti->private; + struct dmz_dev *dev = &dmz->dev[0]; - if (!dmz_check_bdev(dmz->dev)) + if (!dmz_check_bdev(dev)) return -EIO; - *bdev = dmz->dev->bdev; + *bdev = dev->bdev; return 0; } @@ -938,9 +1048,11 @@ static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) static void dmz_suspend(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; flush_workqueue(dmz->chunk_wq); - dmz_suspend_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_suspend_reclaim(dmz->dev[i].reclaim); cancel_delayed_work_sync(&dmz->flush_work); } @@ -950,24 +1062,95 @@ static void dmz_suspend(struct dm_target *ti) static void dmz_resume(struct dm_target *ti) { struct dmz_target *dmz = ti->private; + int i; queue_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD); - dmz_resume_reclaim(dmz->reclaim); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_resume_reclaim(dmz->dev[i].reclaim); } static int dmz_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct dmz_target *dmz = ti->private; - struct dmz_dev *dev = dmz->dev; - sector_t capacity = dev->capacity & ~(dev->zone_nr_sectors - 1); + unsigned int zone_nr_sectors = dmz_zone_nr_sectors(dmz->metadata); + sector_t capacity; + int i, r; + + for (i = 0; i < dmz->nr_ddevs; i++) { + capacity = dmz->dev[i].capacity & ~(zone_nr_sectors - 1); + r = fn(ti, dmz->ddev[i], 0, capacity, data); + if (r) + break; + } + return r; +} + +static void dmz_status(struct dm_target *ti, status_type_t type, + unsigned int status_flags, char *result, + unsigned int maxlen) +{ + struct dmz_target *dmz = ti->private; + ssize_t sz = 0; + char buf[BDEVNAME_SIZE]; + struct dmz_dev *dev; + int i; + + switch (type) { + case STATUSTYPE_INFO: + DMEMIT("%u zones %u/%u cache", + dmz_nr_zones(dmz->metadata), + dmz_nr_unmap_cache_zones(dmz->metadata), + dmz_nr_cache_zones(dmz->metadata)); + for (i = 0; i < dmz->nr_ddevs; i++) { + /* + * For a multi-device setup the first device + * contains only cache zones. + */ + if ((i == 0) && + (dmz_nr_cache_zones(dmz->metadata) > 0)) + continue; + DMEMIT(" %u/%u random %u/%u sequential", + dmz_nr_unmap_rnd_zones(dmz->metadata, i), + dmz_nr_rnd_zones(dmz->metadata, i), + dmz_nr_unmap_seq_zones(dmz->metadata, i), + dmz_nr_seq_zones(dmz->metadata, i)); + } + break; + case STATUSTYPE_TABLE: + dev = &dmz->dev[0]; + format_dev_t(buf, dev->bdev->bd_dev); + DMEMIT("%s", buf); + for (i = 1; i < dmz->nr_ddevs; i++) { + dev = &dmz->dev[i]; + format_dev_t(buf, dev->bdev->bd_dev); + DMEMIT(" %s", buf); + } + break; + } + return; +} + +static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv, + char *result, unsigned int maxlen) +{ + struct dmz_target *dmz = ti->private; + int r = -EINVAL; + + if (!strcasecmp(argv[0], "reclaim")) { + int i; - return fn(ti, dmz->ddev, 0, capacity, data); + for (i = 0; i < dmz->nr_ddevs; i++) + dmz_schedule_reclaim(dmz->dev[i].reclaim); + r = 0; + } else + DMERR("unrecognized message %s", argv[0]); + return r; } static struct target_type dmz_type = { .name = "zoned", - .version = {1, 1, 0}, + .version = {2, 0, 0}, .features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM, .module = THIS_MODULE, .ctr = dmz_ctr, @@ -978,6 +1161,8 @@ static struct target_type dmz_type = { .postsuspend = dmz_suspend, .resume = dmz_resume, .iterate_devices = dmz_iterate_devices, + .status = dmz_status, + .message = dmz_message, }; static int __init dmz_init(void) diff --git a/drivers/md/dm-zoned.h b/drivers/md/dm-zoned.h index 5b5e493d479c..22f11440b423 100644 --- a/drivers/md/dm-zoned.h +++ b/drivers/md/dm-zoned.h @@ -45,34 +45,50 @@ #define dmz_bio_block(bio) dmz_sect2blk((bio)->bi_iter.bi_sector) #define dmz_bio_blocks(bio) dmz_sect2blk(bio_sectors(bio)) +struct dmz_metadata; +struct dmz_reclaim; + /* * Zoned block device information. */ struct dmz_dev { struct block_device *bdev; + struct dmz_metadata *metadata; + struct dmz_reclaim *reclaim; char name[BDEVNAME_SIZE]; + uuid_t uuid; sector_t capacity; + unsigned int dev_idx; + unsigned int nr_zones; + unsigned int zone_offset; unsigned int flags; sector_t zone_nr_sectors; - unsigned int zone_nr_sectors_shift; - sector_t zone_nr_blocks; - sector_t zone_nr_blocks_shift; + unsigned int nr_rnd; + atomic_t unmap_nr_rnd; + struct list_head unmap_rnd_list; + struct list_head map_rnd_list; + + unsigned int nr_seq; + atomic_t unmap_nr_seq; + struct list_head unmap_seq_list; + struct list_head map_seq_list; }; -#define dmz_bio_chunk(dev, bio) ((bio)->bi_iter.bi_sector >> \ - (dev)->zone_nr_sectors_shift) -#define dmz_chunk_block(dev, b) ((b) & ((dev)->zone_nr_blocks - 1)) +#define dmz_bio_chunk(zmd, bio) ((bio)->bi_iter.bi_sector >> \ + dmz_zone_nr_sectors_shift(zmd)) +#define dmz_chunk_block(zmd, b) ((b) & (dmz_zone_nr_blocks(zmd) - 1)) /* Device flags. */ #define DMZ_BDEV_DYING (1 << 0) #define DMZ_CHECK_BDEV (2 << 0) +#define DMZ_BDEV_REGULAR (4 << 0) /* * Zone descriptor. @@ -81,12 +97,18 @@ struct dm_zone { /* For listing the zone depending on its state */ struct list_head link; + /* Device containing this zone */ + struct dmz_dev *dev; + /* Zone type and state */ unsigned long flags; /* Zone activation reference count */ atomic_t refcount; + /* Zone id */ + unsigned int id; + /* Zone write pointer block (relative to the zone start block) */ unsigned int wp_block; @@ -109,6 +131,7 @@ struct dm_zone { */ enum { /* Zone write type */ + DMZ_CACHE, DMZ_RND, DMZ_SEQ, @@ -120,22 +143,28 @@ enum { DMZ_META, DMZ_DATA, DMZ_BUF, + DMZ_RESERVED, /* Zone internal state */ DMZ_RECLAIM, DMZ_SEQ_WRITE_ERR, + DMZ_RECLAIM_TERMINATE, }; /* * Zone data accessors. */ +#define dmz_is_cache(z) test_bit(DMZ_CACHE, &(z)->flags) #define dmz_is_rnd(z) test_bit(DMZ_RND, &(z)->flags) #define dmz_is_seq(z) test_bit(DMZ_SEQ, &(z)->flags) #define dmz_is_empty(z) ((z)->wp_block == 0) #define dmz_is_offline(z) test_bit(DMZ_OFFLINE, &(z)->flags) #define dmz_is_readonly(z) test_bit(DMZ_READ_ONLY, &(z)->flags) #define dmz_in_reclaim(z) test_bit(DMZ_RECLAIM, &(z)->flags) +#define dmz_is_reserved(z) test_bit(DMZ_RESERVED, &(z)->flags) #define dmz_seq_write_err(z) test_bit(DMZ_SEQ_WRITE_ERR, &(z)->flags) +#define dmz_reclaim_should_terminate(z) \ + test_bit(DMZ_RECLAIM_TERMINATE, &(z)->flags) #define dmz_is_meta(z) test_bit(DMZ_META, &(z)->flags) #define dmz_is_buf(z) test_bit(DMZ_BUF, &(z)->flags) @@ -158,13 +187,11 @@ enum { #define dmz_dev_debug(dev, format, args...) \ DMDEBUG("(%s): " format, (dev)->name, ## args) -struct dmz_metadata; -struct dmz_reclaim; - /* * Functions defined in dm-zoned-metadata.c */ -int dmz_ctr_metadata(struct dmz_dev *dev, struct dmz_metadata **zmd); +int dmz_ctr_metadata(struct dmz_dev *dev, int num_dev, + struct dmz_metadata **zmd, const char *devname); void dmz_dtr_metadata(struct dmz_metadata *zmd); int dmz_resume_metadata(struct dmz_metadata *zmd); @@ -175,23 +202,38 @@ void dmz_unlock_metadata(struct dmz_metadata *zmd); void dmz_lock_flush(struct dmz_metadata *zmd); void dmz_unlock_flush(struct dmz_metadata *zmd); int dmz_flush_metadata(struct dmz_metadata *zmd); +const char *dmz_metadata_label(struct dmz_metadata *zmd); -unsigned int dmz_id(struct dmz_metadata *zmd, struct dm_zone *zone); sector_t dmz_start_sect(struct dmz_metadata *zmd, struct dm_zone *zone); sector_t dmz_start_block(struct dmz_metadata *zmd, struct dm_zone *zone); unsigned int dmz_nr_chunks(struct dmz_metadata *zmd); +bool dmz_check_dev(struct dmz_metadata *zmd); +bool dmz_dev_is_dying(struct dmz_metadata *zmd); + #define DMZ_ALLOC_RND 0x01 -#define DMZ_ALLOC_RECLAIM 0x02 +#define DMZ_ALLOC_CACHE 0x02 +#define DMZ_ALLOC_SEQ 0x04 +#define DMZ_ALLOC_RECLAIM 0x10 -struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned long flags); +struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, + unsigned int dev_idx, unsigned long flags); void dmz_free_zone(struct dmz_metadata *zmd, struct dm_zone *zone); void dmz_map_zone(struct dmz_metadata *zmd, struct dm_zone *zone, unsigned int chunk); void dmz_unmap_zone(struct dmz_metadata *zmd, struct dm_zone *zone); -unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd); -unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd); +unsigned int dmz_nr_zones(struct dmz_metadata *zmd); +unsigned int dmz_nr_cache_zones(struct dmz_metadata *zmd); +unsigned int dmz_nr_unmap_cache_zones(struct dmz_metadata *zmd); +unsigned int dmz_nr_rnd_zones(struct dmz_metadata *zmd, int idx); +unsigned int dmz_nr_unmap_rnd_zones(struct dmz_metadata *zmd, int idx); +unsigned int dmz_nr_seq_zones(struct dmz_metadata *zmd, int idx); +unsigned int dmz_nr_unmap_seq_zones(struct dmz_metadata *zmd, int idx); +unsigned int dmz_zone_nr_blocks(struct dmz_metadata *zmd); +unsigned int dmz_zone_nr_blocks_shift(struct dmz_metadata *zmd); +unsigned int dmz_zone_nr_sectors(struct dmz_metadata *zmd); +unsigned int dmz_zone_nr_sectors_shift(struct dmz_metadata *zmd); /* * Activate a zone (increment its reference count). @@ -201,26 +243,10 @@ static inline void dmz_activate_zone(struct dm_zone *zone) atomic_inc(&zone->refcount); } -/* - * Deactivate a zone. This decrement the zone reference counter - * indicating that all BIOs to the zone have completed when the count is 0. - */ -static inline void dmz_deactivate_zone(struct dm_zone *zone) -{ - atomic_dec(&zone->refcount); -} - -/* - * Test if a zone is active, that is, has a refcount > 0. - */ -static inline bool dmz_is_active(struct dm_zone *zone) -{ - return atomic_read(&zone->refcount); -} - int dmz_lock_zone_reclaim(struct dm_zone *zone); void dmz_unlock_zone_reclaim(struct dm_zone *zone); -struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd); +struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd, + unsigned int dev_idx, bool idle); struct dm_zone *dmz_get_chunk_mapping(struct dmz_metadata *zmd, unsigned int chunk, int op); @@ -244,8 +270,7 @@ int dmz_merge_valid_blocks(struct dmz_metadata *zmd, struct dm_zone *from_zone, /* * Functions defined in dm-zoned-reclaim.c */ -int dmz_ctr_reclaim(struct dmz_dev *dev, struct dmz_metadata *zmd, - struct dmz_reclaim **zrc); +int dmz_ctr_reclaim(struct dmz_metadata *zmd, struct dmz_reclaim **zrc, int idx); void dmz_dtr_reclaim(struct dmz_reclaim *zrc); void dmz_suspend_reclaim(struct dmz_reclaim *zrc); void dmz_resume_reclaim(struct dmz_reclaim *zrc); @@ -258,4 +283,22 @@ void dmz_schedule_reclaim(struct dmz_reclaim *zrc); bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev); bool dmz_check_bdev(struct dmz_dev *dmz_dev); +/* + * Deactivate a zone. This decrement the zone reference counter + * indicating that all BIOs to the zone have completed when the count is 0. + */ +static inline void dmz_deactivate_zone(struct dm_zone *zone) +{ + dmz_reclaim_bio_acc(zone->dev->reclaim); + atomic_dec(&zone->refcount); +} + +/* + * Test if a zone is active, that is, has a refcount > 0. + */ +static inline bool dmz_is_active(struct dm_zone *zone) +{ + return atomic_read(&zone->refcount); +} + #endif /* DM_ZONED_H */ diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 3f39fa1ac756..109e81f33edb 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -676,6 +676,15 @@ static bool md_in_flight(struct mapped_device *md) return md_in_flight_bios(md); } +u64 dm_start_time_ns_from_clone(struct bio *bio) +{ + struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); + struct dm_io *io = tio->io; + + return jiffies_to_nsecs(io->start_time); +} +EXPORT_SYMBOL_GPL(dm_start_time_ns_from_clone); + static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; @@ -2610,7 +2619,7 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, if (noflush) set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags); else - pr_debug("%s: suspending with flush\n", dm_device_name(md)); + DMDEBUG("%s: suspending with flush", dm_device_name(md)); /* * This gets reverted if there's an error later and the targets diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index a240990a7f33..564896659dd4 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -38,7 +38,7 @@ struct node_header { struct btree_node { struct node_header header; - __le64 keys[0]; + __le64 keys[]; } __packed; @@ -68,7 +68,7 @@ struct ro_spine { }; void init_ro_spine(struct ro_spine *s, struct dm_btree_info *info); -int exit_ro_spine(struct ro_spine *s); +void exit_ro_spine(struct ro_spine *s); int ro_step(struct ro_spine *s, dm_block_t new_child); void ro_pop(struct ro_spine *s); struct btree_node *ro_node(struct ro_spine *s); diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index b27b8091a1ca..e03cb9e48773 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -132,15 +132,13 @@ void init_ro_spine(struct ro_spine *s, struct dm_btree_info *info) s->nodes[1] = NULL; } -int exit_ro_spine(struct ro_spine *s) +void exit_ro_spine(struct ro_spine *s) { - int r = 0, i; + int i; for (i = 0; i < s->count; i++) { unlock_block(s->info, s->nodes[i]); } - - return r; } int ro_step(struct ro_spine *s, dm_block_t new_child) |