diff options
48 files changed, 8791 insertions, 601 deletions
diff --git a/Documentation/device-mapper/cache-policies.txt b/Documentation/device-mapper/cache-policies.txt new file mode 100644 index 00000000000..d7c440b444c --- /dev/null +++ b/Documentation/device-mapper/cache-policies.txt @@ -0,0 +1,77 @@ +Guidance for writing policies +============================= + +Try to keep transactionality out of it. The core is careful to +avoid asking about anything that is migrating. This is a pain, but +makes it easier to write the policies. + +Mappings are loaded into the policy at construction time. + +Every bio that is mapped by the target is referred to the policy. +The policy can return a simple HIT or MISS or issue a migration. + +Currently there's no way for the policy to issue background work, +e.g. to start writing back dirty blocks that are going to be evicte +soon. + +Because we map bios, rather than requests it's easy for the policy +to get fooled by many small bios. For this reason the core target +issues periodic ticks to the policy. It's suggested that the policy +doesn't update states (eg, hit counts) for a block more than once +for each tick. The core ticks by watching bios complete, and so +trying to see when the io scheduler has let the ios run. + + +Overview of supplied cache replacement policies +=============================================== + +multiqueue +---------- + +This policy is the default. + +The multiqueue policy has two sets of 16 queues: one set for entries +waiting for the cache and another one for those in the cache. +Cache entries in the queues are aged based on logical time. Entry into +the cache is based on variable thresholds and queue selection is based +on hit count on entry. The policy aims to take different cache miss +costs into account and to adjust to varying load patterns automatically. + +Message and constructor argument pairs are: + 'sequential_threshold <#nr_sequential_ios>' and + 'random_threshold <#nr_random_ios>'. + +The sequential threshold indicates the number of contiguous I/Os +required before a stream is treated as sequential. The random threshold +is the number of intervening non-contiguous I/Os that must be seen +before the stream is treated as random again. + +The sequential and random thresholds default to 512 and 4 respectively. + +Large, sequential ios are probably better left on the origin device +since spindles tend to have good bandwidth. The io_tracker counts +contiguous I/Os to try to spot when the io is in one of these sequential +modes. + +cleaner +------- + +The cleaner writes back all dirty blocks in a cache to decommission it. + +Examples +======== + +The syntax for a table is: + cache <metadata dev> <cache dev> <origin dev> <block size> + <#feature_args> [<feature arg>]* + <policy> <#policy_args> [<policy arg>]* + +The syntax to send a message using the dmsetup command is: + dmsetup message <mapped device> 0 sequential_threshold 1024 + dmsetup message <mapped device> 0 random_threshold 8 + +Using dmsetup: + dmsetup create blah --table "0 268435456 cache /dev/sdb /dev/sdc \ + /dev/sdd 512 0 mq 4 sequential_threshold 1024 random_threshold 8" + creates a 128GB large mapped device named 'blah' with the + sequential threshold set to 1024 and the random_threshold set to 8. diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt new file mode 100644 index 00000000000..f50470abe24 --- /dev/null +++ b/Documentation/device-mapper/cache.txt @@ -0,0 +1,243 @@ +Introduction +============ + +dm-cache is a device mapper target written by Joe Thornber, Heinz +Mauelshagen, and Mike Snitzer. + +It aims to improve performance of a block device (eg, a spindle) by +dynamically migrating some of its data to a faster, smaller device +(eg, an SSD). + +This device-mapper solution allows us to insert this caching at +different levels of the dm stack, for instance above the data device for +a thin-provisioning pool. Caching solutions that are integrated more +closely with the virtual memory system should give better performance. + +The target reuses the metadata library used in the thin-provisioning +library. + +The decision as to what data to migrate and when is left to a plug-in +policy module. Several of these have been written as we experiment, +and we hope other people will contribute others for specific io +scenarios (eg. a vm image server). + +Glossary +======== + + Migration - Movement of the primary copy of a logical block from one + device to the other. + Promotion - Migration from slow device to fast device. + Demotion - Migration from fast device to slow device. + +The origin device always contains a copy of the logical block, which +may be out of date or kept in sync with the copy on the cache device +(depending on policy). + +Design +====== + +Sub-devices +----------- + +The target is constructed by passing three devices to it (along with +other parameters detailed later): + +1. An origin device - the big, slow one. + +2. A cache device - the small, fast one. + +3. A small metadata device - records which blocks are in the cache, + which are dirty, and extra hints for use by the policy object. + This information could be put on the cache device, but having it + separate allows the volume manager to configure it differently, + e.g. as a mirror for extra robustness. + +Fixed block size +---------------- + +The origin is divided up into blocks of a fixed size. This block size +is configurable when you first create the cache. Typically we've been +using block sizes of 256k - 1024k. + +Having a fixed block size simplifies the target a lot. But it is +something of a compromise. For instance, a small part of a block may be +getting hit a lot, yet the whole block will be promoted to the cache. +So large block sizes are bad because they waste cache space. And small +block sizes are bad because they increase the amount of metadata (both +in core and on disk). + +Writeback/writethrough +---------------------- + +The cache has two modes, writeback and writethrough. + +If writeback, the default, is selected then a write to a block that is +cached will go only to the cache and the block will be marked dirty in +the metadata. + +If writethrough is selected then a write to a cached block will not +complete until it has hit both the origin and cache devices. Clean +blocks should remain clean. + +A simple cleaner policy is provided, which will clean (write back) all +dirty blocks in a cache. Useful for decommissioning a cache. + +Migration throttling +-------------------- + +Migrating data between the origin and cache device uses bandwidth. +The user can set a throttle to prevent more than a certain amount of +migration occuring at any one time. Currently we're not taking any +account of normal io traffic going to the devices. More work needs +doing here to avoid migrating during those peak io moments. + +For the time being, a message "migration_threshold <#sectors>" +can be used to set the maximum number of sectors being migrated, +the default being 204800 sectors (or 100MB). + +Updating on-disk metadata +------------------------- + +On-disk metadata is committed every time a REQ_SYNC or REQ_FUA bio is +written. If no such requests are made then commits will occur every +second. This means the cache behaves like a physical disk that has a +write cache (the same is true of the thin-provisioning target). If +power is lost you may lose some recent writes. The metadata should +always be consistent in spite of any crash. + +The 'dirty' state for a cache block changes far too frequently for us +to keep updating it on the fly. So we treat it as a hint. In normal +operation it will be written when the dm device is suspended. If the +system crashes all cache blocks will be assumed dirty when restarted. + +Per-block policy hints +---------------------- + +Policy plug-ins can store a chunk of data per cache block. It's up to +the policy how big this chunk is, but it should be kept small. Like the +dirty flags this data is lost if there's a crash so a safe fallback +value should always be possible. + +For instance, the 'mq' policy, which is currently the default policy, +uses this facility to store the hit count of the cache blocks. If +there's a crash this information will be lost, which means the cache +may be less efficient until those hit counts are regenerated. + +Policy hints affect performance, not correctness. + +Policy messaging +---------------- + +Policies will have different tunables, specific to each one, so we +need a generic way of getting and setting these. Device-mapper +messages are used. Refer to cache-policies.txt. + +Discard bitset resolution +------------------------- + +We can avoid copying data during migration if we know the block has +been discarded. A prime example of this is when mkfs discards the +whole block device. We store a bitset tracking the discard state of +blocks. However, we allow this bitset to have a different block size +from the cache blocks. This is because we need to track the discard +state for all of the origin device (compare with the dirty bitset +which is just for the smaller cache device). + +Target interface +================ + +Constructor +----------- + + cache <metadata dev> <cache dev> <origin dev> <block size> + <#feature args> [<feature arg>]* + <policy> <#policy args> [policy args]* + + metadata dev : fast device holding the persistent metadata + cache dev : fast device holding cached data blocks + origin dev : slow device holding original data blocks + block size : cache unit size in sectors + + #feature args : number of feature arguments passed + feature args : writethrough. (The default is writeback.) + + policy : the replacement policy to use + #policy args : an even number of arguments corresponding to + key/value pairs passed to the policy + policy args : key/value pairs passed to the policy + E.g. 'sequential_threshold 1024' + See cache-policies.txt for details. + +Optional feature arguments are: + writethrough : write through caching that prohibits cache block + content from being different from origin block content. + Without this argument, the default behaviour is to write + back cache block contents later for performance reasons, + so they may differ from the corresponding origin blocks. + +A policy called 'default' is always registered. This is an alias for +the policy we currently think is giving best all round performance. + +As the default policy could vary between kernels, if you are relying on +the characteristics of a specific policy, always request it by name. + +Status +------ + +<#used metadata blocks>/<#total metadata blocks> <#read hits> <#read misses> +<#write hits> <#write misses> <#demotions> <#promotions> <#blocks in cache> +<#dirty> <#features> <features>* <#core args> <core args>* <#policy args> +<policy args>* + +#used metadata blocks : Number of metadata blocks used +#total metadata blocks : Total number of metadata blocks +#read hits : Number of times a READ bio has been mapped + to the cache +#read misses : Number of times a READ bio has been mapped + to the origin +#write hits : Number of times a WRITE bio has been mapped + to the cache +#write misses : Number of times a WRITE bio has been + mapped to the origin +#demotions : Number of times a block has been removed + from the cache +#promotions : Number of times a block has been moved to + the cache +#blocks in cache : Number of blocks resident in the cache +#dirty : Number of blocks in the cache that differ + from the origin +#feature args : Number of feature args to follow +feature args : 'writethrough' (optional) +#core args : Number of core arguments (must be even) +core args : Key/value pairs for tuning the core + e.g. migration_threshold +#policy args : Number of policy arguments to follow (must be even) +policy args : Key/value pairs + e.g. 'sequential_threshold 1024 + +Messages +-------- + +Policies will have different tunables, specific to each one, so we +need a generic way of getting and setting these. Device-mapper +messages are used. (A sysfs interface would also be possible.) + +The message format is: + + <key> <value> + +E.g. + dmsetup message my_cache 0 sequential_threshold 1024 + +Examples +======== + +The test suite can be found here: + +https://github.com/jthornber/thinp-test-suite + +dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \ + /dev/mapper/ssd /dev/mapper/origin 512 1 writeback default 0' +dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \ + /dev/mapper/ssd /dev/mapper/origin 1024 1 writeback \ + mq 4 sequential_threshold 1024 random_threshold 8' diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 91a02eeeb31..e30b490055a 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -210,7 +210,7 @@ config DM_DEBUG config DM_BUFIO tristate - depends on BLK_DEV_DM && EXPERIMENTAL + depends on BLK_DEV_DM ---help--- This interface allows you to do buffered I/O on a device and acts as a cache, holding recently-read blocks in memory and performing @@ -218,7 +218,7 @@ config DM_BUFIO config DM_BIO_PRISON tristate - depends on BLK_DEV_DM && EXPERIMENTAL + depends on BLK_DEV_DM ---help--- Some bio locking schemes used by other device-mapper targets including thin provisioning. @@ -251,8 +251,8 @@ config DM_SNAPSHOT Allow volume managers to take writable snapshots of a device. config DM_THIN_PROVISIONING - tristate "Thin provisioning target (EXPERIMENTAL)" - depends on BLK_DEV_DM && EXPERIMENTAL + tristate "Thin provisioning target" + depends on BLK_DEV_DM select DM_PERSISTENT_DATA select DM_BIO_PRISON ---help--- @@ -268,6 +268,37 @@ config DM_DEBUG_BLOCK_STACK_TRACING If unsure, say N. +config DM_CACHE + tristate "Cache target (EXPERIMENTAL)" + depends on BLK_DEV_DM + default n + select DM_PERSISTENT_DATA + select DM_BIO_PRISON + ---help--- + dm-cache attempts to improve performance of a block device by + moving frequently used data to a smaller, higher performance + device. Different 'policy' plugins can be used to change the + algorithms used to select which blocks are promoted, demoted, + cleaned etc. It supports writeback and writethrough modes. + +config DM_CACHE_MQ + tristate "MQ Cache Policy (EXPERIMENTAL)" + depends on DM_CACHE + default y + ---help--- + A cache policy that uses a multiqueue ordered by recent hit + count to select which blocks should be promoted and demoted. + This is meant to be a general purpose policy. It prioritises + reads over writes. + +config DM_CACHE_CLEANER + tristate "Cleaner Cache Policy (EXPERIMENTAL)" + depends on DM_CACHE + default y + ---help--- + A simple cache policy that writes back all data to the + origin. Used when decommissioning a dm-cache. + config DM_MIRROR tristate "Mirror target" depends on BLK_DEV_DM @@ -302,8 +333,8 @@ config DM_RAID in one of the available parity distribution methods. config DM_LOG_USERSPACE - tristate "Mirror userspace logging (EXPERIMENTAL)" - depends on DM_MIRROR && EXPERIMENTAL && NET + tristate "Mirror userspace logging" + depends on DM_MIRROR && NET select CONNECTOR ---help--- The userspace logging module provides a mechanism for @@ -350,8 +381,8 @@ config DM_MULTIPATH_ST If unsure, say N. config DM_DELAY - tristate "I/O delaying target (EXPERIMENTAL)" - depends on BLK_DEV_DM && EXPERIMENTAL + tristate "I/O delaying target" + depends on BLK_DEV_DM ---help--- A target that delays reads and/or writes and can send them to different devices. Useful for testing. @@ -365,14 +396,14 @@ config DM_UEVENT Generate udev events for DM events. config DM_FLAKEY - tristate "Flakey target (EXPERIMENTAL)" - depends on BLK_DEV_DM && EXPERIMENTAL + tristate "Flakey target" + depends on BLK_DEV_DM ---help--- A target that intermittently fails I/O for debugging purposes. config DM_VERITY - tristate "Verity target support (EXPERIMENTAL)" - depends on BLK_DEV_DM && EXPERIMENTAL + tristate "Verity target support" + depends on BLK_DEV_DM select CRYPTO select CRYPTO_HASH select DM_BUFIO diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 94dce8b4932..7ceeaefc0e9 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -11,6 +11,9 @@ dm-mirror-y += dm-raid1.o dm-log-userspace-y \ += dm-log-userspace-base.o dm-log-userspace-transfer.o 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-mq-y += dm-cache-policy-mq.o +dm-cache-cleaner-y += dm-cache-policy-cleaner.o md-mod-y += md.o bitmap.o raid456-y += raid5.o @@ -44,6 +47,9 @@ obj-$(CONFIG_DM_ZERO) += dm-zero.o obj-$(CONFIG_DM_RAID) += dm-raid.o 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_MQ) += dm-cache-mq.o +obj-$(CONFIG_DM_CACHE_CLEANER) += dm-cache-cleaner.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o diff --git a/drivers/md/dm-bio-prison.c b/drivers/md/dm-bio-prison.c index d9d3f1c7b66..85f0b707425 100644 --- a/drivers/md/dm-bio-prison.c +++ b/drivers/md/dm-bio-prison.c @@ -14,14 +14,6 @@ /*----------------------------------------------------------------*/ -struct dm_bio_prison_cell { - struct hlist_node list; - struct dm_bio_prison *prison; - struct dm_cell_key key; - struct bio *holder; - struct bio_list bios; -}; - struct dm_bio_prison { spinlock_t lock; mempool_t *cell_pool; @@ -87,6 +79,19 @@ void dm_bio_prison_destroy(struct dm_bio_prison *prison) } EXPORT_SYMBOL_GPL(dm_bio_prison_destroy); +struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison, gfp_t gfp) +{ + return mempool_alloc(prison->cell_pool, gfp); +} +EXPORT_SYMBOL_GPL(dm_bio_prison_alloc_cell); + +void dm_bio_prison_free_cell(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell) +{ + mempool_free(cell, prison->cell_pool); +} +EXPORT_SYMBOL_GPL(dm_bio_prison_free_cell); + static uint32_t hash_key(struct dm_bio_prison *prison, struct dm_cell_key *key) { const unsigned long BIG_PRIME = 4294967291UL; @@ -114,91 +119,95 @@ static struct dm_bio_prison_cell *__search_bucket(struct hlist_head *bucket, return NULL; } -/* - * This may block if a new cell needs allocating. You must ensure that - * cells will be unlocked even if the calling thread is blocked. - * - * Returns 1 if the cell was already held, 0 if @inmate is the new holder. - */ -int dm_bio_detain(struct dm_bio_prison *prison, struct dm_cell_key *key, - struct bio *inmate, struct dm_bio_prison_cell **ref) +static void __setup_new_cell(struct dm_bio_prison *prison, + struct dm_cell_key *key, + struct bio *holder, + uint32_t hash, + struct dm_bio_prison_cell *cell) { - int r = 1; - unsigned long flags; - uint32_t hash = hash_key(prison, key); - struct dm_bio_prison_cell *cell, *cell2; - - BUG_ON(hash > prison->nr_buckets); - - spin_lock_irqsave(&prison->lock, flags); - - cell = __search_bucket(prison->cells + hash, key); - if (cell) { - bio_list_add(&cell->bios, inmate); - goto out; - } + memcpy(&cell->key, key, sizeof(cell->key)); + cell->holder = holder; + bio_list_init(&cell->bios); + hlist_add_head(&cell->list, prison->cells + hash); +} - /* - * Allocate a new cell - */ - spin_unlock_irqrestore(&prison->lock, flags); - cell2 = mempool_alloc(prison->cell_pool, GFP_NOIO); - spin_lock_irqsave(&prison->lock, flags); +static int __bio_detain(struct dm_bio_prison *prison, + struct dm_cell_key *key, + struct bio *inmate, + struct dm_bio_prison_cell *cell_prealloc, + struct dm_bio_prison_cell **cell_result) +{ + uint32_t hash = hash_key(prison, key); + struct dm_bio_prison_cell *cell; - /* - * We've been unlocked, so we have to double check that - * nobody else has inserted this cell in the meantime. - */ cell = __search_bucket(prison->cells + hash, key); if (cell) { - mempool_free(cell2, prison->cell_pool); - bio_list_add(&cell->bios, inmate); - goto out; + if (inmate) + bio_list_add(&cell->bios, inmate); + *cell_result = cell; + return 1; } - /* - * Use new cell. - */ - cell = cell2; - - cell->prison = prison; - memcpy(&cell->key, key, sizeof(cell->key)); - cell->holder = inmate; - bio_list_init(&cell->bios); - hlist_add_head(&cell->list, prison->cells + hash); + __setup_new_cell(prison, key, inmate, hash, cell_prealloc); + *cell_result = cell_prealloc; + return 0; +} - r = 0; +static int bio_detain(struct dm_bio_prison *prison, + struct dm_cell_key *key, + struct bio *inmate, + struct dm_bio_prison_cell *cell_prealloc, + struct dm_bio_prison_cell **cell_result) +{ + int r; + unsigned long flags; -out: + spin_lock_irqsave(&prison->lock, flags); + r = __bio_detain(prison, key, inmate, cell_prealloc, cell_result); spin_unlock_irqrestore(&prison->lock, flags); - *ref = cell; - return r; } + +int dm_bio_detain(struct dm_bio_prison *prison, + struct dm_cell_key *key, + struct bio *inmate, + struct dm_bio_prison_cell *cell_prealloc, + struct dm_bio_prison_cell **cell_result) +{ + return bio_detain(prison, key, inmate, cell_prealloc, cell_result); +} EXPORT_SYMBOL_GPL(dm_bio_detain); +int dm_get_cell(struct dm_bio_prison *prison, + struct dm_cell_key *key, + struct dm_bio_prison_cell *cell_prealloc, + struct dm_bio_prison_cell **cell_result) +{ + return bio_detain(prison, key, NULL, cell_prealloc, cell_result); +} +EXPORT_SYMBOL_GPL(dm_get_cell); + /* * @inmates must have been initialised prior to this call */ -static void __cell_release(struct dm_bio_prison_cell *cell, struct bio_list *inmates) +static void __cell_release(struct dm_bio_prison_cell *cell, + struct bio_list *inmates) { - struct dm_bio_prison *prison = cell->prison; - hlist_del(&cell->list); if (inmates) { - bio_list_add(inmates, cell->holder); + if (cell->holder) + bio_list_add(inmates, cell->holder); bio_list_merge(inmates, &cell->bios); } - - mempool_free(cell, prison->cell_pool); } -void dm_cell_release(struct dm_bio_prison_cell *cell, struct bio_list *bios) +void dm_cell_release(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell, + struct bio_list *bios) { unsigned long flags; - struct dm_bio_prison *prison = cell->prison; spin_lock_irqsave(&prison->lock, flags); __cell_release(cell, bios); @@ -209,20 +218,18 @@ EXPORT_SYMBOL_GPL(dm_cell_release); /* * Sometimes we don't want the holder, just the additional bios. */ -static void __cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list *inmates) +static void __cell_release_no_holder(struct dm_bio_prison_cell *cell, + struct bio_list *inmates) { - struct dm_bio_prison *prison = cell->prison; - hlist_del(&cell->list); bio_list_merge(inmates, &cell->bios); - - mempool_free(cell, prison->cell_pool); } -void dm_cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list *inmates) +void dm_cell_release_no_holder(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell, + struct bio_list *inmates) { unsigned long flags; - struct dm_bio_prison *prison = cell->prison; spin_lock_irqsave(&prison->lock, flags); __cell_release_no_holder(cell, inmates); @@ -230,9 +237,9 @@ void dm_cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list } EXPORT_SYMBOL_GPL(dm_cell_release_no_holder); -void dm_cell_error(struct dm_bio_prison_cell *cell) +void dm_cell_error(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell) { - struct dm_bio_prison *prison = cell->prison; struct bio_list bios; struct bio *bio; unsigned long flags; diff --git a/drivers/md/dm-bio-prison.h b/drivers/md/dm-bio-prison.h index 53d1a7a84e2..3f833190ead 100644 --- a/drivers/md/dm-bio-prison.h +++ b/drivers/md/dm-bio-prison.h @@ -22,7 +22,6 @@ * subsequently unlocked the bios become available. */ struct dm_bio_prison; -struct dm_bio_prison_cell; /* FIXME: this needs to be more abstract */ struct dm_cell_key { @@ -31,21 +30,62 @@ struct dm_cell_key { dm_block_t block; }; +/* + * Treat this as opaque, only in header so callers can manage allocation + * themselves. + */ +struct dm_bio_prison_cell { + struct hlist_node list; + struct dm_cell_key key; + struct bio *holder; + struct bio_list bios; +}; + struct dm_bio_prison *dm_bio_prison_create(unsigned nr_cells); void dm_bio_prison_destroy(struct dm_bio_prison *prison); /* - * This may block if a new cell needs allocating. You must ensure that - * cells will be unlocked even if the calling thread is blocked. + * These two functions just wrap a mempool. This is a transitory step: + * Eventually all bio prison clients should manage their own cell memory. * - * Returns 1 if the cell was already held, 0 if @inmate is the new holder. + * Like mempool_alloc(), dm_bio_prison_alloc_cell() can only fail if called + * in interrupt context or passed GFP_NOWAIT. */ -int dm_bio_detain(struct dm_bio_prison *prison, struct dm_cell_key *key, - struct bio *inmate, struct dm_bio_prison_cell **ref); +struct dm_bio_prison_cell *dm_bio_prison_alloc_cell(struct dm_bio_prison *prison, + gfp_t gfp); +void dm_bio_prison_free_cell(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell); -void dm_cell_release(struct dm_bio_prison_cell *cell, struct bio_list *bios); -void dm_cell_release_no_holder(struct dm_bio_prison_cell *cell, struct bio_list *inmates); -void dm_cell_error(struct dm_bio_prison_cell *cell); +/* + * Creates, or retrieves a cell for the given key. + * + * Returns 1 if pre-existing cell returned, zero if new cell created using + * @cell_prealloc. + */ +int dm_get_cell(struct dm_bio_prison *prison, + struct dm_cell_key *key, + struct dm_bio_prison_cell *cell_prealloc, + struct dm_bio_prison_cell **cell_result); + +/* + * An atomic op that combines retrieving a cell, and adding a bio to it. + * + * Returns 1 if the cell was already held, 0 if @inmate is the new holder. + */ +int dm_bio_detain(struct dm_bio_prison *prison, + struct dm_cell_key *key, + struct bio *inmate, + struct dm_bio_prison_cell *cell_prealloc, + struct dm_bio_prison_cell **cell_result); + +void dm_cell_release(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell, + struct bio_list *bios); +void dm_cell_release_no_holder(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell, + struct bio_list *inmates); +void dm_cell_error(struct dm_bio_prison *prison, + struct dm_bio_prison_cell *cell); /*----------------------------------------------------------------*/ diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 93205e32a00..3c955e10a61 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1192,7 +1192,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers); int dm_bufio_issue_flush(struct dm_bufio_client *c) { struct dm_io_request io_req = { - .bi_rw = REQ_FLUSH, + .bi_rw = WRITE_FLUSH, .mem.type = DM_IO_KMEM, .mem.ptr.addr = NULL, .client = c->dm_io, diff --git a/drivers/md/dm-cache-block-types.h b/drivers/md/dm-cache-block-types.h new file mode 100644 index 00000000000..bed4ad4e1b7 --- /dev/null +++ b/drivers/md/dm-cache-block-types.h @@ -0,0 +1,54 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef DM_CACHE_BLOCK_TYPES_H +#define DM_CACHE_BLOCK_TYPES_H + +#include "persistent-data/dm-block-manager.h" + +/*----------------------------------------------------------------*/ + +/* + * It's helpful to get sparse to differentiate between indexes into the + * origin device, indexes into the cache device, and indexes into the + * discard bitset. + */ + +typedef dm_block_t __bitwise__ dm_oblock_t; +typedef uint32_t __bitwise__ dm_cblock_t; +typedef dm_block_t __bitwise__ dm_dblock_t; + +static inline dm_oblock_t to_oblock(dm_block_t b) +{ + return (__force dm_oblock_t) b; +} + +static inline dm_block_t from_oblock(dm_oblock_t b) +{ + return (__force dm_block_t) b; +} + +static inline dm_cblock_t to_cblock(uint32_t b) +{ + return (__force dm_cblock_t) b; +} + +static inline uint32_t from_cblock(dm_cblock_t b) +{ + return (__force uint32_t) b; +} + +static inline dm_dblock_t to_dblock(dm_block_t b) +{ + return (__force dm_dblock_t) b; +} + +static inline dm_block_t from_dblock(dm_dblock_t b) +{ + return (__force dm_block_t) b; +} + +#endif /* DM_CACHE_BLOCK_TYPES_H */ diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c new file mode 100644 index 00000000000..fbd3625f274 --- /dev/null +++ b/drivers/md/dm-cache-metadata.c @@ -0,0 +1,1146 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-cache-metadata.h" + +#include "persistent-data/dm-array.h" +#include "persistent-data/dm-bitset.h" +#include "persistent-data/dm-space-map.h" +#include "persistent-data/dm-space-map-disk.h" +#include "persistent-data/dm-transaction-manager.h" + +#include <linux/device-mapper.h> + +/*----------------------------------------------------------------*/ + +#define DM_MSG_PREFIX "cache metadata" + +#define CACHE_SUPERBLOCK_MAGIC 06142003 +#define CACHE_SUPERBLOCK_LOCATION 0 +#define CACHE_VERSION 1 +#define CACHE_METADATA_CACHE_SIZE 64 + +/* + * 3 for btree insert + + * 2 for btree lookup used within space map + */ +#define CACHE_MAX_CONCURRENT_LOCKS 5 +#define SPACE_MAP_ROOT_SIZE 128 + +enum superblock_flag_bits { + /* for spotting crashes that would invalidate the dirty bitset */ + CLEAN_SHUTDOWN, +}; + +/* + * Each mapping from cache block -> origin block carries a set of flags. + */ +enum mapping_bits { + /* + * A valid mapping. Because we're using an array we clear this + * flag for an non existant mapping. + */ + M_VALID = 1, + + /* + * The data on the cache is different from that on the origin. + */ + M_DIRTY = 2 +}; + +struct cache_disk_superblock { + __le32 csum; + __le32 flags; + __le64 blocknr; + + __u8 uuid[16]; + __le64 magic; + __le32 version; + + __u8 policy_name[CACHE_POLICY_NAME_SIZE]; + __le32 policy_hint_size; + + __u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE]; + __le64 mapping_root; + __le64 hint_root; + + __le64 discard_root; + __le64 discard_block_size; + __le64 discard_nr_blocks; + + __le32 data_block_size; + __le32 metadata_block_size; + __le32 cache_blocks; + + __le32 compat_flags; + __le32 compat_ro_flags; + __le32 incompat_flags; + + __le32 read_hits; + __le32 read_misses; + __le32 write_hits; + __le32 write_misses; +} __packed; + +struct dm_cache_metadata { + struct block_device *bdev; + struct dm_block_manager *bm; + struct dm_space_map *metadata_sm; + struct dm_transaction_manager *tm; + + struct dm_array_info info; + struct dm_array_info hint_info; + struct dm_disk_bitset discard_info; + + struct rw_semaphore root_lock; + dm_block_t root; + dm_block_t hint_root; + dm_block_t discard_root; + + sector_t discard_block_size; + dm_dblock_t discard_nr_blocks; + + sector_t data_block_size; + dm_cblock_t cache_blocks; + bool changed:1; + bool clean_when_opened:1; + + char policy_name[CACHE_POLICY_NAME_SIZE]; + size_t policy_hint_size; + struct dm_cache_statistics stats; +}; + +/*------------------------------------------------------------------- + * superblock validator + *-----------------------------------------------------------------*/ + +#define SUPERBLOCK_CSUM_XOR 9031977 + +static void sb_prepare_for_write(struct dm_block_validator *v, + struct dm_block *b, + size_t sb_block_size) +{ + struct cache_disk_superblock *disk_super = dm_block_data(b); + + disk_super->blocknr = cpu_to_le64(dm_block_location(b)); + disk_super->csum = cpu_to_le32(dm_bm_checksum(&disk_super->flags, + sb_block_size - sizeof(__le32), + SUPERBLOCK_CSUM_XOR)); +} + +static int sb_check(struct dm_block_validator *v, + struct dm_block *b, + size_t sb_block_size) +{ + struct cache_disk_superblock *disk_super = dm_block_data(b); + __le32 csum_le; + + if (dm_block_location(b) != le64_to_cpu(disk_super->blocknr)) { + DMERR("sb_check failed: blocknr %llu: wanted %llu", + le64_to_cpu(disk_super->blocknr), + (unsigned long long)dm_block_location(b)); + return -ENOTBLK; + } + + if (le64_to_cpu(disk_super->magic) != CACHE_SUPERBLOCK_MAGIC) { + DMERR("sb_check failed: magic %llu: wanted %llu", + le64_to_cpu(disk_super->magic), + (unsigned long long)CACHE_SUPERBLOCK_MAGIC); + return -EILSEQ; + } + + csum_le = cpu_to_le32(dm_bm_checksum(&disk_super->flags, + sb_block_size - sizeof(__le32), + SUPERBLOCK_CSUM_XOR)); + if (csum_le != disk_super->csum) { + DMERR("sb_check failed: csum %u: wanted %u", + le32_to_cpu(csum_le), le32_to_cpu(disk_super->csum)); + return -EILSEQ; + } + + return 0; +} + +static struct dm_block_validator sb_validator = { + .name = "superblock", + .prepare_for_write = sb_prepare_for_write, + .check = sb_check +}; + +/*----------------------------------------------------------------*/ + +static int superblock_read_lock(struct dm_cache_metadata *cmd, + struct dm_block **sblock) +{ + return dm_bm_read_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION, + &sb_validator, sblock); +} + +static int superblock_lock_zero(struct dm_cache_metadata *cmd, + struct dm_block **sblock) +{ + return dm_bm_write_lock_zero(cmd->bm, CACHE_SUPERBLOCK_LOCATION, + &sb_validator, sblock); +} + +static int superblock_lock(struct dm_cache_metadata *cmd, + struct dm_block **sblock) +{ + return dm_bm_write_lock(cmd->bm, CACHE_SUPERBLOCK_LOCATION, + &sb_validator, sblock); +} + +/*----------------------------------------------------------------*/ + +static int __superblock_all_zeroes(struct dm_block_manager *bm, int *result) +{ + int r; + unsigned i; + struct dm_block *b; + __le64 *data_le, zero = cpu_to_le64(0); + unsigned sb_block_size = dm_bm_block_size(bm) / sizeof(__le64); + + /* + * We can't use a validator here - it may be all zeroes. + */ + r = dm_bm_read_lock(bm, CACHE_SUPERBLOCK_LOCATION, NULL, &b); + if (r) + return r; + + data_le = dm_block_data(b); + *result = 1; + for (i = 0; i < sb_block_size; i++) { + if (data_le[i] != zero) { + *result = 0; + break; + } + } + + return dm_bm_unlock(b); +} + +static void __setup_mapping_info(struct dm_cache_metadata *cmd) +{ + struct dm_btree_value_type vt; + + vt.context = NULL; + vt.size = sizeof(__le64); + vt.inc = NULL; + vt.dec = NULL; + vt.equal = NULL; + dm_array_info_init(&cmd->info, cmd->tm, &vt); + + if (cmd->policy_hint_size) { + vt.size = sizeof(__le32); + dm_array_info_init(&cmd->hint_info, cmd->tm, &vt); + } +} + +static int __write_initial_superblock(struct dm_cache_metadata *cmd) +{ + int r; + struct dm_block *sblock; + size_t metadata_len; + struct cache_disk_superblock *disk_super; + sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT; + + /* FIXME: see if we can lose the max sectors limit */ + if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS) + bdev_size = DM_CACHE_METADATA_MAX_SECTORS; + + r = dm_sm_root_size(cmd->metadata_sm, &metadata_len); + if (r < 0) + return r; + + r = dm_tm_pre_commit(cmd->tm); + if (r < 0) + return r; + + r = superblock_lock_zero(cmd, &sblock); + if (r) + return r; + + disk_super = dm_block_data(sblock); + disk_super->flags = 0; + memset(disk_super->uuid, 0, sizeof(disk_super->uuid)); + disk_super->magic = cpu_to_le64(CACHE_SUPERBLOCK_MAGIC); + disk_super->version = cpu_to_le32(CACHE_VERSION); + memset(disk_super->policy_name, 0, CACHE_POLICY_NAME_SIZE); + disk_super->policy_hint_size = 0; + + r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root, + metadata_len); + if (r < 0) + goto bad_locked; + + disk_super->mapping_root = cpu_to_le64(cmd->root); + disk_super->hint_root = cpu_to_le64(cmd->hint_root); + disk_super->discard_root = cpu_to_le64(cmd->discard_root); + disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size); + disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks)); + disk_super->metadata_block_size = cpu_to_le32(DM_CACHE_METADATA_BLOCK_SIZE >> SECTOR_SHIFT); + disk_super->data_block_size = cpu_to_le32(cmd->data_block_size); + disk_super->cache_blocks = cpu_to_le32(0); + memset(disk_super->policy_name, 0, sizeof(disk_super->policy_name)); + + disk_super->read_hits = cpu_to_le32(0); + disk_super->read_misses = cpu_to_le32(0); + disk_super->write_hits = cpu_to_le32(0); + disk_super->write_misses = cpu_to_le32(0); + + return dm_tm_commit(cmd->tm, sblock); + +bad_locked: + dm_bm_unlock(sblock); + return r; +} + +static int __format_metadata(struct dm_cache_metadata *cmd) +{ + int r; + + r = dm_tm_create_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION, + &cmd->tm, &cmd->metadata_sm); + if (r < 0) { + DMERR("tm_create_with_sm failed"); + return r; + } + + __setup_mapping_info(cmd); + + r = dm_array_empty(&cmd->info, &cmd->root); + if (r < 0) + goto bad; + + dm_disk_bitset_init(cmd->tm, &cmd->discard_info); + + r = dm_bitset_empty(&cmd->discard_info, &cmd->discard_root); + if (r < 0) + goto bad; + + cmd->discard_block_size = 0; + cmd->discard_nr_blocks = 0; + + r = __write_initial_superblock(cmd); + if (r) + goto bad; + + cmd->clean_when_opened = true; + return 0; + +bad: + dm_tm_destroy(cmd->tm); + dm_sm_destroy(cmd->metadata_sm); + + return r; +} + +static int __check_incompat_features(struct cache_disk_superblock *disk_super, + struct dm_cache_metadata *cmd) +{ + uint32_t features; + + features = le32_to_cpu(disk_super->incompat_flags) & ~DM_CACHE_FEATURE_INCOMPAT_SUPP; + if (features) { + DMERR("could not access metadata due to unsupported optional features (%lx).", + (unsigned long)features); + return -EINVAL; + } + + /* + * Check for read-only metadata to skip the following RDWR checks. + */ + if (get_disk_ro(cmd->bdev->bd_disk)) + return 0; + + features = le32_to_cpu(disk_super->compat_ro_flags) & ~DM_CACHE_FEATURE_COMPAT_RO_SUPP; + if (features) { + DMERR("could not access metadata RDWR due to unsupported optional features (%lx).", + (unsigned long)features); + return -EINVAL; + } + + return 0; +} + +static int __open_metadata(struct dm_cache_metadata *cmd) +{ + int r; + struct dm_block *sblock; + struct cache_disk_superblock *disk_super; + unsigned long sb_flags; + + r = superblock_read_lock(cmd, &sblock); + if (r < 0) { + DMERR("couldn't read lock superblock"); + return r; + } + + disk_super = dm_block_data(sblock); + + r = __check_incompat_features(disk_super, cmd); + if (r < 0) + goto bad; + + r = dm_tm_open_with_sm(cmd->bm, CACHE_SUPERBLOCK_LOCATION, + disk_super->metadata_space_map_root, + sizeof(disk_super->metadata_space_map_root), + &cmd->tm, &cmd->metadata_sm); + if (r < 0) { + DMERR("tm_open_with_sm failed"); + goto bad; + } + + __setup_mapping_info(cmd); + dm_disk_bitset_init(cmd->tm, &cmd->discard_info); + sb_flags = le32_to_cpu(disk_super->flags); + cmd->clean_when_opened = test_bit(CLEAN_SHUTDOWN, &sb_flags); + return dm_bm_unlock(sblock); + +bad: + dm_bm_unlock(sblock); + return r; +} + +static int __open_or_format_metadata(struct dm_cache_metadata *cmd, + bool format_device) +{ + int r, unformatted; + + r = __superblock_all_zeroes(cmd->bm, &unformatted); + if (r) + return r; + + if (unformatted) + return format_device ? __format_metadata(cmd) : -EPERM; + + return __open_metadata(cmd); +} + +static int __create_persistent_data_objects(struct dm_cache_metadata *cmd, + bool may_format_device) +{ + int r; + cmd->bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE, + CACHE_METADATA_CACHE_SIZE, + CACHE_MAX_CONCURRENT_LOCKS); + if (IS_ERR(cmd->bm)) { + DMERR("could not create block manager"); + return PTR_ERR(cmd->bm); + } + + r = __open_or_format_metadata(cmd, may_format_device); + if (r) + dm_block_manager_destroy(cmd->bm); + + return r; +} + +static void __destroy_persistent_data_objects(struct dm_cache_metadata *cmd) +{ + dm_sm_destroy(cmd->metadata_sm); + dm_tm_destroy(cmd->tm); + dm_block_manager_destroy(cmd->bm); +} + +typedef unsigned long (*flags_mutator)(unsigned long); + +static void update_flags(struct cache_disk_superblock *disk_super, + flags_mutator mutator) +{ + uint32_t sb_flags = mutator(le32_to_cpu(disk_super->flags)); + disk_super->flags = cpu_to_le32(sb_flags); +} + +static unsigned long set_clean_shutdown(unsigned long flags) +{ + set_bit(CLEAN_SHUTDOWN, &flags); + return flags; +} + +static unsigned long clear_clean_shutdown(unsigned long flags) +{ + clear_bit(CLEAN_SHUTDOWN, &flags); + return flags; +} + +static void read_superblock_fields(struct dm_cache_metadata *cmd, + struct cache_disk_superblock *disk_super) +{ + cmd->root = le64_to_cpu(disk_super->mapping_root); + cmd->hint_root = le64_to_cpu(disk_super->hint_root); + cmd->discard_root = le64_to_cpu(disk_super->discard_root); + cmd->discard_block_size = le64_to_cpu(disk_super->discard_block_size); + cmd->discard_nr_blocks = to_dblock(le64_to_cpu(disk_super->discard_nr_blocks)); + cmd->data_block_size = le32_to_cpu(disk_super->data_block_size); + cmd->cache_blocks = to_cblock(le32_to_cpu(disk_super->cache_blocks)); + strncpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name)); + cmd->policy_hint_size = le32_to_cpu(disk_super->policy_hint_size); + + cmd->stats.read_hits = le32_to_cpu(disk_super->read_hits); + cmd->stats.read_misses = le32_to_cpu(disk_super->read_misses); + cmd->stats.write_hits = le32_to_cpu(disk_super->write_hits); + cmd->stats.write_misses = le32_to_cpu(disk_super->write_misses); + + cmd->changed = false; +} + +/* + * The mutator updates the superblock flags. + */ +static int __begin_transaction_flags(struct dm_cache_metadata *cmd, + flags_mutator mutator) +{ + int r; + struct cache_disk_superblock *disk_super; + struct dm_block *sblock; + + r = superblock_lock(cmd, &sblock); + if (r) + return r; + + disk_super = dm_block_data(sblock); + update_flags(disk_super, mutator); + read_superblock_fields(cmd, disk_super); + + return dm_bm_flush_and_unlock(cmd->bm, sblock); +} + +static int __begin_transaction(struct dm_cache_metadata *cmd) +{ + int r; + struct cache_disk_superblock *disk_super; + struct dm_block *sblock; + + /* + * We re-read the superblock every time. Shouldn't need to do this + * really. + */ + r = superblock_read_lock(cmd, &sblock); + if (r) + return r; + + disk_super = dm_block_data(sblock); + read_superblock_fields(cmd, disk_super); + dm_bm_unlock(sblock); + + return 0; +} + +static int __commit_transaction(struct dm_cache_metadata *cmd, + flags_mutator mutator) +{ + int r; + size_t metadata_len; + struct cache_disk_superblock *disk_super; + struct dm_block *sblock; + + /* + * We need to know if the cache_disk_superblock exceeds a 512-byte sector. + */ + BUILD_BUG_ON(sizeof(struct cache_disk_superblock) > 512); + + r = dm_bitset_flush(&cmd->discard_info, cmd->discard_root, + &cmd->discard_root); + if (r) + return r; + + r = dm_tm_pre_commit(cmd->tm); + if (r < 0) + return r; + + r = dm_sm_root_size(cmd->metadata_sm, &metadata_len); + if (r < 0) + return r; + + r = superblock_lock(cmd, &sblock); + if (r) + return r; + + disk_super = dm_block_data(sblock); + + if (mutator) + update_flags(disk_super, mutator); + + disk_super->mapping_root = cpu_to_le64(cmd->root); + disk_super->hint_root = cpu_to_le64(cmd->hint_root); + disk_super->discard_root = cpu_to_le64(cmd->discard_root); + disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size); + disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks)); + disk_super->cache_blocks = cpu_to_le32(from_cblock(cmd->cache_blocks)); + strncpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name)); + + disk_super->read_hits = cpu_to_le32(cmd->stats.read_hits); + disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses); + disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits); + disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses); + + r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root, + metadata_len); + if (r < 0) { + dm_bm_unlock(sblock); + return r; + } + + return dm_tm_commit(cmd->tm, sblock); +} + +/*----------------------------------------------------------------*/ + +/* + * The mappings are held in a dm-array that has 64-bit values stored in + * little-endian format. The index is the cblock, the high 48bits of the + * value are the oblock and the low 16 bit the flags. + */ +#define FLAGS_MASK ((1 << 16) - 1) + +static __le64 pack_value(dm_oblock_t block, unsigned flags) +{ + uint64_t value = from_oblock(block); + value <<= 16; + value = value | (flags & FLAGS_MASK); + return cpu_to_le64(value); +} + +static void unpack_value(__le64 value_le, dm_oblock_t *block, unsigned *flags) +{ + uint64_t value = le64_to_cpu(value_le); + uint64_t b = value >> 16; + *block = to_oblock(b); + *flags = value & FLAGS_MASK; +} + +/*----------------------------------------------------------------*/ + +struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size) +{ + int r; + struct dm_cache_metadata *cmd; + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (!cmd) { + DMERR("could not allocate metadata struct"); + return NULL; + } + + init_rwsem(&cmd->root_lock); + cmd->bdev = bdev; + cmd->data_block_size = data_block_size; + cmd->cache_blocks = 0; + cmd->policy_hint_size = policy_hint_size; + cmd->changed = true; + + r = __create_persistent_data_objects(cmd, may_format_device); + if (r) { + kfree(cmd); + return ERR_PTR(r); + } + + r = __begin_transaction_flags(cmd, clear_clean_shutdown); + if (r < 0) { + dm_cache_metadata_close(cmd); + return ERR_PTR(r); + } + + return cmd; +} + +void dm_cache_metadata_close(struct dm_cache_metadata *cmd) +{ + __destroy_persistent_data_objects(cmd); + kfree(cmd); +} + +int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size) +{ + int r; + __le64 null_mapping = pack_value(0, 0); + + down_write(&cmd->root_lock); + __dm_bless_for_disk(&null_mapping); + r = dm_array_resize(&cmd->info, cmd->root, from_cblock(cmd->cache_blocks), + from_cblock(new_cache_size), + &null_mapping, &cmd->root); + if (!r) + cmd->cache_blocks = new_cache_size; + cmd->changed = true; + up_write(&cmd->root_lock); + + return r; +} + +int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd, + sector_t discard_block_size, + dm_dblock_t new_nr_entries) +{ + int r; + + down_write(&cmd->root_lock); + r = dm_bitset_resize(&cmd->discard_info, + cmd->discard_root, + from_dblock(cmd->discard_nr_blocks), + from_dblock(new_nr_entries), + false, &cmd->discard_root); + if (!r) { + cmd->discard_block_size = discard_block_size; + cmd->discard_nr_blocks = new_nr_entries; + } + + cmd->changed = true; + up_write(&cmd->root_lock); + + return r; +} + +static int __set_discard(struct dm_cache_metadata *cmd, dm_dblock_t b) +{ + return dm_bitset_set_bit(&cmd->discard_info, cmd->discard_root, + from_dblock(b), &cmd->discard_root); +} + +static int __clear_discard(struct dm_cache_metadata *cmd, dm_dblock_t b) +{ + return dm_bitset_clear_bit(&cmd->discard_info, cmd->discard_root, + from_dblock(b), &cmd->discard_root); +} + +static int __is_discarded(struct dm_cache_metadata *cmd, dm_dblock_t b, + bool *is_discarded) +{ + return dm_bitset_test_bit(&cmd->discard_info, cmd->discard_root, + from_dblock(b), &cmd->discard_root, + is_discarded); +} + +static int __discard(struct dm_cache_metadata *cmd, + dm_dblock_t dblock, bool discard) +{ + int r; + + r = (discard ? __set_discard : __clear_discard)(cmd, dblock); + if (r) + return r; + + cmd->changed = true; + return 0; +} + +int dm_cache_set_discard(struct dm_cache_metadata *cmd, + dm_dblock_t dblock, bool discard) +{ + int r; + + down_write(&cmd->root_lock); + r = __discard(cmd, dblock, discard); + up_write(&cmd->root_lock); + + return r; +} + +static int __load_discards(struct dm_cache_metadata *cmd, + load_discard_fn fn, void *context) +{ + int r = 0; + dm_block_t b; + bool discard; + + for (b = 0; b < from_dblock(cmd->discard_nr_blocks); b++) { + dm_dblock_t dblock = to_dblock(b); + + if (cmd->clean_when_opened) { + r = __is_discarded(cmd, dblock, &discard); + if (r) + return r; + } else + discard = false; + + r = fn(context, cmd->discard_block_size, dblock, discard); + if (r) + break; + } + + return r; +} + +int dm_cache_load_discards(struct dm_cache_metadata *cmd, + load_discard_fn fn, void *context) +{ + int r; + + down_read(&cmd->root_lock); + r = __load_discards(cmd, fn, context); + up_read(&cmd->root_lock); + + return r; +} + +dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd) +{ + dm_cblock_t r; + + down_read(&cmd->root_lock); + r = cmd->cache_blocks; + up_read(&cmd->root_lock); + + return r; +} + +static int __remove(struct dm_cache_metadata *cmd, dm_cblock_t cblock) +{ + int r; + __le64 value = pack_value(0, 0); + + __dm_bless_for_disk(&value); + r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock), + &value, &cmd->root); + if (r) + return r; + + cmd->changed = true; + return 0; +} + +int dm_cache_remove_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock) +{ + int r; + + down_write(&cmd->root_lock); + r = __remove(cmd, cblock); + up_write(&cmd->root_lock); + + return r; +} + +static int __insert(struct dm_cache_metadata *cmd, + dm_cblock_t cblock, dm_oblock_t oblock) +{ + int r; + __le64 value = pack_value(oblock, M_VALID); + __dm_bless_for_disk(&value); + + r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock), + &value, &cmd->root); + if (r) + return r; + + cmd->changed = true; + return 0; +} + +int dm_cache_insert_mapping(struct dm_cache_metadata *cmd, + dm_cblock_t cblock, dm_oblock_t oblock) +{ + int r; + + down_write(&cmd->root_lock); + r = __insert(cmd, cblock, oblock); + up_write(&cmd->root_lock); + + return r; +} + +struct thunk { + load_mapping_fn fn; + void *context; + + struct dm_cache_metadata *cmd; + bool respect_dirty_flags; + bool hints_valid; +}; + +static bool hints_array_initialized(struct dm_cache_metadata *cmd) +{ + return cmd->hint_root && cmd->policy_hint_size; +} + +static bool hints_array_available(struct dm_cache_metadata *cmd, + const char *policy_name) +{ + bool policy_names_match = !strncmp(cmd->policy_name, policy_name, + sizeof(cmd->policy_name)); + + return cmd->clean_when_opened && policy_names_match && + hints_array_initialized(cmd); +} + +static int __load_mapping(void *context, uint64_t cblock, void *leaf) +{ + int r = 0; + bool dirty; + __le64 value; + __le32 hint_value = 0; + dm_oblock_t oblock; + unsigned flags; + struct thunk *thunk = context; + struct dm_cache_metadata *cmd = thunk->cmd; + + memcpy(&value, leaf, sizeof(value)); + unpack_value(value, &oblock, &flags); + + if (flags & M_VALID) { + if (thunk->hints_valid) { + r = dm_array_get_value(&cmd->hint_info, cmd->hint_root, + cblock, &hint_value); + if (r && r != -ENODATA) + return r; + } + + dirty = thunk->respect_dirty_flags ? (flags & M_DIRTY) : true; + r = thunk->fn(thunk->context, oblock, to_cblock(cblock), + dirty, le32_to_cpu(hint_value), thunk->hints_valid); + } + + return r; +} + +static int __load_mappings(struct dm_cache_metadata *cmd, const char *policy_name, + load_mapping_fn fn, void *context) +{ + struct thunk thunk; + + thunk.fn = fn; + thunk.context = context; + + thunk.cmd = cmd; + thunk.respect_dirty_flags = cmd->clean_when_opened; + thunk.hints_valid = hints_array_available(cmd, policy_name); + + return dm_array_walk(&cmd->info, cmd->root, __load_mapping, &thunk); +} + +int dm_cache_load_mappings(struct dm_cache_metadata *cmd, const char *policy_name, + load_mapping_fn fn, void *context) +{ + int r; + + down_read(&cmd->root_lock); + r = __load_mappings(cmd, policy_name, fn, context); + up_read(&cmd->root_lock); + + return r; +} + +static int __dump_mapping(void *context, uint64_t cblock, void *leaf) +{ + int r = 0; + __le64 value; + dm_oblock_t oblock; + unsigned flags; + + memcpy(&value, leaf, sizeof(value)); + unpack_value(value, &oblock, &flags); + + return r; +} + +static int __dump_mappings(struct dm_cache_metadata *cmd) +{ + return dm_array_walk(&cmd->info, cmd->root, __dump_mapping, NULL); +} + +void dm_cache_dump(struct dm_cache_metadata *cmd) +{ + down_read(&cmd->root_lock); + __dump_mappings(cmd); + up_read(&cmd->root_lock); +} + +int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd) +{ + int r; + + down_read(&cmd->root_lock); + r = cmd->changed; + up_read(&cmd->root_lock); + + return r; +} + +static int __dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty) +{ + int r; + unsigned flags; + dm_oblock_t oblock; + __le64 value; + + r = dm_array_get_value(&cmd->info, cmd->root, from_cblock(cblock), &value); + if (r) + return r; + + unpack_value(value, &oblock, &flags); + + if (((flags & M_DIRTY) && dirty) || (!(flags & M_DIRTY) && !dirty)) + /* nothing to be done */ + return 0; + + value = pack_value(oblock, flags | (dirty ? M_DIRTY : 0)); + __dm_bless_for_disk(&value); + + r = dm_array_set_value(&cmd->info, cmd->root, from_cblock(cblock), + &value, &cmd->root); + if (r) + return r; + + cmd->changed = true; + return 0; + +} + +int dm_cache_set_dirty(struct dm_cache_metadata *cmd, + dm_cblock_t cblock, bool dirty) +{ + int r; + + down_write(&cmd->root_lock); + r = __dirty(cmd, cblock, dirty); + up_write(&cmd->root_lock); + + return r; +} + +void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd, + struct dm_cache_statistics *stats) +{ + down_read(&cmd->root_lock); + memcpy(stats, &cmd->stats, sizeof(*stats)); + up_read(&cmd->root_lock); +} + +void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd, + struct dm_cache_statistics *stats) +{ + down_write(&cmd->root_lock); + memcpy(&cmd->stats, stats, sizeof(*stats)); + up_write(&cmd->root_lock); +} + +int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown) +{ + int r; + flags_mutator mutator = (clean_shutdown ? set_clean_shutdown : + clear_clean_shutdown); + + down_write(&cmd->root_lock); + r = __commit_transaction(cmd, mutator); + if (r) + goto out; + + r = __begin_transaction(cmd); + +out: + up_write(&cmd->root_lock); + return r; +} + +int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd, + dm_block_t *result) +{ + int r = -EINVAL; + + down_read(&cmd->root_lock); + r = dm_sm_get_nr_free(cmd->metadata_sm, result); + up_read(&cmd->root_lock); + + return r; +} + +int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd, + dm_block_t *result) +{ + int r = -EINVAL; + + down_read(&cmd->root_lock); + r = dm_sm_get_nr_blocks(cmd->metadata_sm, result); + up_read(&cmd->root_lock); + + return r; +} + +/*----------------------------------------------------------------*/ + +static int begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy) +{ + int r; + __le32 value; + size_t hint_size; + const char *policy_name = dm_cache_policy_get_name(policy); + + if (!policy_name[0] || + (strlen(policy_name) > sizeof(cmd->policy_name) - 1)) + return -EINVAL; + + if (strcmp(cmd->policy_name, policy_name)) { + strncpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name)); + + hint_size = dm_cache_policy_get_hint_size(policy); + if (!hint_size) + return 0; /* short-circuit hints initialization */ + cmd->policy_hint_size = hint_size; + + if (cmd->hint_root) { + r = dm_array_del(&cmd->hint_info, cmd->hint_root); + if (r) + return r; + } + + r = dm_array_empty(&cmd->hint_info, &cmd->hint_root); + if (r) + return r; + + value = cpu_to_le32(0); + __dm_bless_for_disk(&value); + r = dm_array_resize(&cmd->hint_info, cmd->hint_root, 0, + from_cblock(cmd->cache_blocks), + &value, &cmd->hint_root); + if (r) + return r; + } + + return 0; +} + +int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy) +{ + int r; + + down_write(&cmd->root_lock); + r = begin_hints(cmd, policy); + up_write(&cmd->root_lock); + + return r; +} + +static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock, + uint32_t hint) +{ + int r; + __le32 value = cpu_to_le32(hint); + __dm_bless_for_disk(&value); + + r = dm_array_set_value(&cmd->hint_info, cmd->hint_root, + from_cblock(cblock), &value, &cmd->hint_root); + cmd->changed = true; + + return r; +} + +int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock, + uint32_t hint) +{ + int r; + + if (!hints_array_initialized(cmd)) + return 0; + + down_write(&cmd->root_lock); + r = save_hint(cmd, cblock, hint); + up_write(&cmd->root_lock); + + return r; +} diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h new file mode 100644 index 00000000000..135864ea0ee --- /dev/null +++ b/drivers/md/dm-cache-metadata.h @@ -0,0 +1,142 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef DM_CACHE_METADATA_H +#define DM_CACHE_METADATA_H + +#include "dm-cache-block-types.h" +#include "dm-cache-policy-internal.h" + +/*----------------------------------------------------------------*/ + +#define DM_CACHE_METADATA_BLOCK_SIZE 4096 + +/* FIXME: remove this restriction */ +/* + * The metadata device is currently limited in size. + * + * We have one block of index, which can hold 255 index entries. Each + * index entry contains allocation info about 16k metadata blocks. + */ +#define DM_CACHE_METADATA_MAX_SECTORS (255 * (1 << 14) * (DM_CACHE_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT))) + +/* + * A metadata device larger than 16GB triggers a warning. + */ +#define DM_CACHE_METADATA_MAX_SECTORS_WARNING (16 * (1024 * 1024 * 1024 >> SECTOR_SHIFT)) + +/*----------------------------------------------------------------*/ + +/* + * Ext[234]-style compat feature flags. + * + * A new feature which old metadata will still be compatible with should + * define a DM_CACHE_FEATURE_COMPAT_* flag (rarely useful). + * + * A new feature that is not compatible with old code should define a + * DM_CACHE_FEATURE_INCOMPAT_* flag and guard the relevant code with + * that flag. + * + * A new feature that is not compatible with old code accessing the + * metadata RDWR should define a DM_CACHE_FEATURE_RO_COMPAT_* flag and + * guard the relevant code with that flag. + * + * As these various flags are defined they should be added to the + * following masks. + */ +#define DM_CACHE_FEATURE_COMPAT_SUPP 0UL +#define DM_CACHE_FEATURE_COMPAT_RO_SUPP 0UL +#define DM_CACHE_FEATURE_INCOMPAT_SUPP 0UL + +/* + * Reopens or creates a new, empty metadata volume. + * Returns an ERR_PTR on failure. + */ +struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev, + sector_t data_block_size, + bool may_format_device, + size_t policy_hint_size); + +void dm_cache_metadata_close(struct dm_cache_metadata *cmd); + +/* + * The metadata needs to know how many cache blocks there are. We don't + * care about the origin, assuming the core target is giving us valid + * origin blocks to map to. + */ +int dm_cache_resize(struct dm_cache_metadata *cmd, dm_cblock_t new_cache_size); +dm_cblock_t dm_cache_size(struct dm_cache_metadata *cmd); + +int dm_cache_discard_bitset_resize(struct dm_cache_metadata *cmd, + sector_t discard_block_size, + dm_dblock_t new_nr_entries); + +typedef int (*load_discard_fn)(void *context, sector_t discard_block_size, + dm_dblock_t dblock, bool discarded); +int dm_cache_load_discards(struct dm_cache_metadata *cmd, + load_discard_fn fn, void *context); + +int dm_cache_set_discard(struct dm_cache_metadata *cmd, dm_dblock_t dblock, bool discard); + +int dm_cache_remove_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock); +int dm_cache_insert_mapping(struct dm_cache_metadata *cmd, dm_cblock_t cblock, dm_oblock_t oblock); +int dm_cache_changed_this_transaction(struct dm_cache_metadata *cmd); + +typedef int (*load_mapping_fn)(void *context, dm_oblock_t oblock, + dm_cblock_t cblock, bool dirty, + uint32_t hint, bool hint_valid); +int dm_cache_load_mappings(struct dm_cache_metadata *cmd, + const char *policy_name, + load_mapping_fn fn, + void *context); + +int dm_cache_set_dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty); + +struct dm_cache_statistics { + uint32_t read_hits; + uint32_t read_misses; + uint32_t write_hits; + uint32_t write_misses; +}; + +void dm_cache_metadata_get_stats(struct dm_cache_metadata *cmd, + struct dm_cache_statistics *stats); +void dm_cache_metadata_set_stats(struct dm_cache_metadata *cmd, + struct dm_cache_statistics *stats); + +int dm_cache_commit(struct dm_cache_metadata *cmd, bool clean_shutdown); + +int dm_cache_get_free_metadata_block_count(struct dm_cache_metadata *cmd, + dm_block_t *result); + +int dm_cache_get_metadata_dev_size(struct dm_cache_metadata *cmd, + dm_block_t *result); + +void dm_cache_dump(struct dm_cache_metadata *cmd); + +/* + * The policy is invited to save a 32bit hint value for every cblock (eg, + * for a hit count). These are stored against the policy name. If + * policies are changed, then hints will be lost. If the machine crashes, + * hints will be lost. + * + * The hints are indexed by the cblock, but many policies will not + * neccessarily have a fast way of accessing efficiently via cblock. So + * rather than querying the policy for each cblock, we let it walk its data + * structures and fill in the hints in whatever order it wishes. + */ + +int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p); + +/* + * requests hints for every cblock and stores in the metadata device. + */ +int dm_cache_save_hint(struct dm_cache_metadata *cmd, + dm_cblock_t cblock, uint32_t hint); + +/*----------------------------------------------------------------*/ + +#endif /* DM_CACHE_METADATA_H */ diff --git a/drivers/md/dm-cache-policy-cleaner.c b/drivers/md/dm-cache-policy-cleaner.c new file mode 100644 index 00000000000..cc05d70b3cb --- /dev/null +++ b/drivers/md/dm-cache-policy-cleaner.c @@ -0,0 +1,464 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * writeback cache policy supporting flushing out dirty cache blocks. + * + * This file is released under the GPL. + */ + +#include "dm-cache-policy.h" +#include "dm.h" + +#include <linux/hash.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +/*----------------------------------------------------------------*/ + +#define DM_MSG_PREFIX "cache cleaner" +#define CLEANER_VERSION "1.0.0" + +/* Cache entry struct. */ +struct wb_cache_entry { + struct list_head list; + struct hlist_node hlist; + + dm_oblock_t oblock; + dm_cblock_t cblock; + bool dirty:1; + bool pending:1; +}; + +struct hash { + struct hlist_head *table; + dm_block_t hash_bits; + unsigned nr_buckets; +}; + +struct policy { + struct dm_cache_policy policy; + spinlock_t lock; + + struct list_head free; + struct list_head clean; + struct list_head clean_pending; + struct list_head dirty; + + /* + * We know exactly how many cblocks will be needed, + * so we can allocate them up front. + */ + dm_cblock_t cache_size, nr_cblocks_allocated; + struct wb_cache_entry *cblocks; + struct hash chash; +}; + +/*----------------------------------------------------------------------------*/ + +/* + * Low-level functions. + */ +static unsigned next_power(unsigned n, unsigned min) +{ + return roundup_pow_of_two(max(n, min)); +} + +static struct policy *to_policy(struct dm_cache_policy *p) +{ + return container_of(p, struct policy, policy); +} + +static struct list_head *list_pop(struct list_head *q) +{ + struct list_head *r = q->next; + + list_del(r); + + return r; +} + +/*----------------------------------------------------------------------------*/ + +/* Allocate/free various resources. */ +static int alloc_hash(struct hash *hash, unsigned elts) +{ + hash->nr_buckets = next_power(elts >> 4, 16); + hash->hash_bits = ffs(hash->nr_buckets) - 1; + hash->table = vzalloc(sizeof(*hash->table) * hash->nr_buckets); + + return hash->table ? 0 : -ENOMEM; +} + +static void free_hash(struct hash *hash) +{ + vfree(hash->table); +} + +static int alloc_cache_blocks_with_hash(struct policy *p, dm_cblock_t cache_size) +{ + int r = -ENOMEM; + + p->cblocks = vzalloc(sizeof(*p->cblocks) * from_cblock(cache_size)); + if (p->cblocks) { + unsigned u = from_cblock(cache_size); + + while (u--) + list_add(&p->cblocks[u].list, &p->free); + + p->nr_cblocks_allocated = 0; + + /* Cache entries hash. */ + r = alloc_hash(&p->chash, from_cblock(cache_size)); + if (r) + vfree(p->cblocks); + } + + return r; +} + +static void free_cache_blocks_and_hash(struct policy *p) +{ + free_hash(&p->chash); + vfree(p->cblocks); +} + +static struct wb_cache_entry *alloc_cache_entry(struct policy *p) +{ + struct wb_cache_entry *e; + + BUG_ON(from_cblock(p->nr_cblocks_allocated) >= from_cblock(p->cache_size)); + + e = list_entry(list_pop(&p->free), struct wb_cache_entry, list); + p->nr_cblocks_allocated = to_cblock(from_cblock(p->nr_cblocks_allocated) + 1); + + return e; +} + +/*----------------------------------------------------------------------------*/ + +/* Hash functions (lookup, insert, remove). */ +static struct wb_cache_entry *lookup_cache_entry(struct policy *p, dm_oblock_t oblock) +{ + struct hash *hash = &p->chash; + unsigned h = hash_64(from_oblock(oblock), hash->hash_bits); + struct wb_cache_entry *cur; + struct hlist_head *bucket = &hash->table[h]; + + hlist_for_each_entry(cur, bucket, hlist) { + if (cur->oblock == oblock) { + /* Move upfront bucket for faster access. */ + hlist_del(&cur->hlist); + hlist_add_head(&cur->hlist, bucket); + return cur; + } + } + + return NULL; +} + +static void insert_cache_hash_entry(struct policy *p, struct wb_cache_entry *e) +{ + unsigned h = hash_64(from_oblock(e->oblock), p->chash.hash_bits); + + hlist_add_head(&e->hlist, &p->chash.table[h]); +} + +static void remove_cache_hash_entry(struct wb_cache_entry *e) +{ + hlist_del(&e->hlist); +} + +/* Public interface (see dm-cache-policy.h */ +static int wb_map(struct dm_cache_policy *pe, dm_oblock_t oblock, + bool can_block, bool can_migrate, bool discarded_oblock, + struct bio *bio, struct policy_result *result) +{ + struct policy *p = to_policy(pe); + struct wb_cache_entry *e; + unsigned long flags; + + result->op = POLICY_MISS; + + if (can_block) + spin_lock_irqsave(&p->lock, flags); + + else if (!spin_trylock_irqsave(&p->lock, flags)) + return -EWOULDBLOCK; + + e = lookup_cache_entry(p, oblock); + if (e) { + result->op = POLICY_HIT; + result->cblock = e->cblock; + + } + + spin_unlock_irqrestore(&p->lock, flags); + + return 0; +} + +static int wb_lookup(struct dm_cache_policy *pe, dm_oblock_t oblock, dm_cblock_t *cblock) +{ + int r; + struct policy *p = to_policy(pe); + struct wb_cache_entry *e; + unsigned long flags; + + if (!spin_trylock_irqsave(&p->lock, flags)) + return -EWOULDBLOCK; + + e = lookup_cache_entry(p, oblock); + if (e) { + *cblock = e->cblock; + r = 0; + + } else + r = -ENOENT; + + spin_unlock_irqrestore(&p->lock, flags); + + return r; +} + +static void __set_clear_dirty(struct dm_cache_policy *pe, dm_oblock_t oblock, bool set) +{ + struct policy *p = to_policy(pe); + struct wb_cache_entry *e; + + e = lookup_cache_entry(p, oblock); + BUG_ON(!e); + + if (set) { + if (!e->dirty) { + e->dirty = true; + list_move(&e->list, &p->dirty); + } + + } else { + if (e->dirty) { + e->pending = false; + e->dirty = false; + list_move(&e->list, &p->clean); + } + } +} + +static void wb_set_dirty(struct dm_cache_policy *pe, dm_oblock_t oblock) +{ + struct policy *p = to_policy(pe); + unsigned long flags; + + spin_lock_irqsave(&p->lock, flags); + __set_clear_dirty(pe, oblock, true); + spin_unlock_irqrestore(&p->lock, flags); +} + +static void wb_clear_dirty(struct dm_cache_policy *pe, dm_oblock_t oblock) +{ + struct policy *p = to_policy(pe); + unsigned long flags; + + spin_lock_irqsave(&p->lock, flags); + __set_clear_dirty(pe, oblock, false); + spin_unlock_irqrestore(&p->lock, flags); +} + +static void add_cache_entry(struct policy *p, struct wb_cache_entry *e) +{ + insert_cache_hash_entry(p, e); + if (e->dirty) + list_add(&e->list, &p->dirty); + else + list_add(&e->list, &p->clean); +} + +static int wb_load_mapping(struct dm_cache_policy *pe, + dm_oblock_t oblock, dm_cblock_t cblock, + uint32_t hint, bool hint_valid) +{ + int r; + struct policy *p = to_policy(pe); + struct wb_cache_entry *e = alloc_cache_entry(p); + + if (e) { + e->cblock = cblock; + e->oblock = oblock; + e->dirty = false; /* blocks default to clean */ + add_cache_entry(p, e); + r = 0; + + } else + r = -ENOMEM; + + return r; +} + +static void wb_destroy(struct dm_cache_policy *pe) +{ + struct policy *p = to_policy(pe); + + free_cache_blocks_and_hash(p); + kfree(p); +} + +static struct wb_cache_entry *__wb_force_remove_mapping(struct policy *p, dm_oblock_t oblock) +{ + struct wb_cache_entry *r = lookup_cache_entry(p, oblock); + + BUG_ON(!r); + + remove_cache_hash_entry(r); + list_del(&r->list); + + return r; +} + +static void wb_remove_mapping(struct dm_cache_policy *pe, dm_oblock_t oblock) +{ + struct policy *p = to_policy(pe); + struct wb_cache_entry *e; + unsigned long flags; + + spin_lock_irqsave(&p->lock, flags); + e = __wb_force_remove_mapping(p, oblock); + list_add_tail(&e->list, &p->free); + BUG_ON(!from_cblock(p->nr_cblocks_allocated)); + p->nr_cblocks_allocated = to_cblock(from_cblock(p->nr_cblocks_allocated) - 1); + spin_unlock_irqrestore(&p->lock, flags); +} + +static void wb_force_mapping(struct dm_cache_policy *pe, + dm_oblock_t current_oblock, dm_oblock_t oblock) +{ + struct policy *p = to_policy(pe); + struct wb_cache_entry *e; + unsigned long flags; + + spin_lock_irqsave(&p->lock, flags); + e = __wb_force_remove_mapping(p, current_oblock); + e->oblock = oblock; + add_cache_entry(p, e); + spin_unlock_irqrestore(&p->lock, flags); +} + +static struct wb_cache_entry *get_next_dirty_entry(struct policy *p) +{ + struct list_head *l; + struct wb_cache_entry *r; + + if (list_empty(&p->dirty)) + return NULL; + + l = list_pop(&p->dirty); + r = container_of(l, struct wb_cache_entry, list); + list_add(l, &p->clean_pending); + + return r; +} + +static int wb_writeback_work(struct dm_cache_policy *pe, + dm_oblock_t *oblock, + dm_cblock_t *cblock) +{ + int r = -ENOENT; + struct policy *p = to_policy(pe); + struct wb_cache_entry *e; + unsigned long flags; + + spin_lock_irqsave(&p->lock, flags); + + e = get_next_dirty_entry(p); + if (e) { + *oblock = e->oblock; + *cblock = e->cblock; + r = 0; + } + + spin_unlock_irqrestore(&p->lock, flags); + + return r; +} + +static dm_cblock_t wb_residency(struct dm_cache_policy *pe) +{ + return to_policy(pe)->nr_cblocks_allocated; +} + +/* Init the policy plugin interface function pointers. */ +static void init_policy_functions(struct policy *p) +{ + p->policy.destroy = wb_destroy; + p->policy.map = wb_map; + p->policy.lookup = wb_lookup; + p->policy.set_dirty = wb_set_dirty; + p->policy.clear_dirty = wb_clear_dirty; + p->policy.load_mapping = wb_load_mapping; + p->policy.walk_mappings = NULL; + p->policy.remove_mapping = wb_remove_mapping; + p->policy.writeback_work = wb_writeback_work; + p->policy.force_mapping = wb_force_mapping; + p->policy.residency = wb_residency; + p->policy.tick = NULL; +} + +static struct dm_cache_policy *wb_create(dm_cblock_t cache_size, + sector_t origin_size, + sector_t cache_block_size) +{ + int r; + struct policy *p = kzalloc(sizeof(*p), GFP_KERNEL); + + if (!p) + return NULL; + + init_policy_functions(p); + INIT_LIST_HEAD(&p->free); + INIT_LIST_HEAD(&p->clean); + INIT_LIST_HEAD(&p->clean_pending); + INIT_LIST_HEAD(&p->dirty); + + p->cache_size = cache_size; + spin_lock_init(&p->lock); + + /* Allocate cache entry structs and add them to free list. */ + r = alloc_cache_blocks_with_hash(p, cache_size); + if (!r) + return &p->policy; + + kfree(p); + + return NULL; +} +/*----------------------------------------------------------------------------*/ + +static struct dm_cache_policy_type wb_policy_type = { + .name = "cleaner", + .hint_size = 0, + .owner = THIS_MODULE, + .create = wb_create +}; + +static int __init wb_init(void) +{ + int r = dm_cache_policy_register(&wb_policy_type); + + if (r < 0) + DMERR("register failed %d", r); + else + DMINFO("version " CLEANER_VERSION " loaded"); + + return r; +} + +static void __exit wb_exit(void) +{ + dm_cache_policy_unregister(&wb_policy_type); +} + +module_init(wb_init); +module_exit(wb_exit); + +MODULE_AUTHOR("Heinz Mauelshagen <dm-devel@redhat.com>"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("cleaner cache policy"); diff --git a/drivers/md/dm-cache-policy-internal.h b/drivers/md/dm-cache-policy-internal.h new file mode 100644 index 00000000000..52a75beeced --- /dev/null +++ b/drivers/md/dm-cache-policy-internal.h @@ -0,0 +1,124 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * This file is released under the GPL. + */ + +#ifndef DM_CACHE_POLICY_INTERNAL_H +#define DM_CACHE_POLICY_INTERNAL_H + +#include "dm-cache-policy.h" + +/*----------------------------------------------------------------*/ + +/* + * Little inline functions that simplify calling the policy methods. + */ +static inline int policy_map(struct dm_cache_policy *p, dm_oblock_t oblock, + bool can_block, bool can_migrate, bool discarded_oblock, + struct bio *bio, struct policy_result *result) +{ + return p->map(p, oblock, can_block, can_migrate, discarded_oblock, bio, result); +} + +static inline int policy_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock) +{ + BUG_ON(!p->lookup); + return p->lookup(p, oblock, cblock); +} + +static inline void policy_set_dirty(struct dm_cache_policy *p, dm_oblock_t oblock) +{ + if (p->set_dirty) + p->set_dirty(p, oblock); +} + +static inline void policy_clear_dirty(struct dm_cache_policy *p, dm_oblock_t oblock) +{ + if (p->clear_dirty) + p->clear_dirty(p, oblock); +} + +static inline int policy_load_mapping(struct dm_cache_policy *p, + dm_oblock_t oblock, dm_cblock_t cblock, + uint32_t hint, bool hint_valid) +{ + return p->load_mapping(p, oblock, cblock, hint, hint_valid); +} + +static inline int policy_walk_mappings(struct dm_cache_policy *p, + policy_walk_fn fn, void *context) +{ + return p->walk_mappings ? p->walk_mappings(p, fn, context) : 0; +} + +static inline int policy_writeback_work(struct dm_cache_policy *p, + dm_oblock_t *oblock, + dm_cblock_t *cblock) +{ + return p->writeback_work ? p->writeback_work(p, oblock, cblock) : -ENOENT; +} + +static inline void policy_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock) +{ + return p->remove_mapping(p, oblock); +} + +static inline void policy_force_mapping(struct dm_cache_policy *p, + dm_oblock_t current_oblock, dm_oblock_t new_oblock) +{ + return p->force_mapping(p, current_oblock, new_oblock); +} + +static inline dm_cblock_t policy_residency(struct dm_cache_policy *p) +{ + return p->residency(p); +} + +static inline void policy_tick(struct dm_cache_policy *p) +{ + if (p->tick) + return p->tick(p); +} + +static inline int policy_emit_config_values(struct dm_cache_policy *p, char *result, unsigned maxlen) +{ + ssize_t sz = 0; + if (p->emit_config_values) + return p->emit_config_values(p, result, maxlen); + + DMEMIT("0"); + return 0; +} + +static inline int policy_set_config_value(struct dm_cache_policy *p, + const char *key, const char *value) +{ + return p->set_config_value ? p->set_config_value(p, key, value) : -EINVAL; +} + +/*----------------------------------------------------------------*/ + +/* + * Creates a new cache policy given a policy name, a cache size, an origin size and the block size. + */ +struct dm_cache_policy *dm_cache_policy_create(const char *name, dm_cblock_t cache_size, + sector_t origin_size, sector_t block_size); + +/* + * Destroys the policy. This drops references to the policy module as well + * as calling it's destroy method. So always use this rather than calling + * the policy->destroy method directly. + */ +void dm_cache_policy_destroy(struct dm_cache_policy *p); + +/* + * In case we've forgotten. + */ +const char *dm_cache_policy_get_name(struct dm_cache_policy *p); + +size_t dm_cache_policy_get_hint_size(struct dm_cache_policy *p); + +/*----------------------------------------------------------------*/ + +#endif /* DM_CACHE_POLICY_INTERNAL_H */ diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c new file mode 100644 index 00000000000..96415325507 --- /dev/null +++ b/drivers/md/dm-cache-policy-mq.c @@ -0,0 +1,1195 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * This file is released under the GPL. + */ + +#include "dm-cache-policy.h" +#include "dm.h" + +#include <linux/hash.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#define DM_MSG_PREFIX "cache-policy-mq" +#define MQ_VERSION "1.0.0" + +static struct kmem_cache *mq_entry_cache; + +/*----------------------------------------------------------------*/ + +static unsigned next_power(unsigned n, unsigned min) +{ + return roundup_pow_of_two(max(n, min)); +} + +/*----------------------------------------------------------------*/ + +static unsigned long *alloc_bitset(unsigned nr_entries) +{ + size_t s = sizeof(unsigned long) * dm_div_up(nr_entries, BITS_PER_LONG); + return vzalloc(s); +} + +static void free_bitset(unsigned long *bits) +{ + vfree(bits); +} + +/*----------------------------------------------------------------*/ + +/* + * Large, sequential ios are probably better left on the origin device since + * spindles tend to have good bandwidth. + * + * The io_tracker tries to spot when the io is in one of these sequential + * modes. + * + * Two thresholds to switch between random and sequential io mode are defaulting + * as follows and can be adjusted via the constructor and message interfaces. + */ +#define RANDOM_THRESHOLD_DEFAULT 4 +#define SEQUENTIAL_THRESHOLD_DEFAULT 512 + +enum io_pattern { + PATTERN_SEQUENTIAL, + PATTERN_RANDOM +}; + +struct io_tracker { + enum io_pattern pattern; + + unsigned nr_seq_samples; + unsigned nr_rand_samples; + unsigned thresholds[2]; + + dm_oblock_t last_end_oblock; +}; + +static void iot_init(struct io_tracker *t, + int sequential_threshold, int random_threshold) +{ + t->pattern = PATTERN_RANDOM; + t->nr_seq_samples = 0; + t->nr_rand_samples = 0; + t->last_end_oblock = 0; + t->thresholds[PATTERN_RANDOM] = random_threshold; + t->thresholds[PATTERN_SEQUENTIAL] = sequential_threshold; +} + +static enum io_pattern iot_pattern(struct io_tracker *t) +{ + return t->pattern; +} + +static void iot_update_stats(struct io_tracker *t, struct bio *bio) +{ + if (bio->bi_sector == from_oblock(t->last_end_oblock) + 1) + t->nr_seq_samples++; + else { + /* + * Just one non-sequential IO is enough to reset the + * counters. + */ + if (t->nr_seq_samples) { + t->nr_seq_samples = 0; + t->nr_rand_samples = 0; + } + + t->nr_rand_samples++; + } + + t->last_end_oblock = to_oblock(bio->bi_sector + bio_sectors(bio) - 1); +} + +static void iot_check_for_pattern_switch(struct io_tracker *t) +{ + switch (t->pattern) { + case PATTERN_SEQUENTIAL: + if (t->nr_rand_samples >= t->thresholds[PATTERN_RANDOM]) { + t->pattern = PATTERN_RANDOM; + t->nr_seq_samples = t->nr_rand_samples = 0; + } + break; + + case PATTERN_RANDOM: + if (t->nr_seq_samples >= t->thresholds[PATTERN_SEQUENTIAL]) { + t->pattern = PATTERN_SEQUENTIAL; + t->nr_seq_samples = t->nr_rand_samples = 0; + } + break; + } +} + +static void iot_examine_bio(struct io_tracker *t, struct bio *bio) +{ + iot_update_stats(t, bio); + iot_check_for_pattern_switch(t); +} + +/*----------------------------------------------------------------*/ + + +/* + * This queue is divided up into different levels. Allowing us to push + * entries to the back of any of the levels. Think of it as a partially + * sorted queue. + */ +#define NR_QUEUE_LEVELS 16u + +struct queue { + struct list_head qs[NR_QUEUE_LEVELS]; +}; + +static void queue_init(struct queue *q) +{ + unsigned i; + + for (i = 0; i < NR_QUEUE_LEVELS; i++) + INIT_LIST_HEAD(q->qs + i); +} + +/* + * Insert an entry to the back of the given level. + */ +static void queue_push(struct queue *q, unsigned level, struct list_head *elt) +{ + list_add_tail(elt, q->qs + level); +} + +static void queue_remove(struct list_head *elt) +{ + list_del(elt); +} + +/* + * Shifts all regions down one level. This has no effect on the order of + * the queue. + */ +static void queue_shift_down(struct queue *q) +{ + unsigned level; + + for (level = 1; level < NR_QUEUE_LEVELS; level++) + list_splice_init(q->qs + level, q->qs + level - 1); +} + +/* + * Gives us the oldest entry of the lowest popoulated level. If the first + * level is emptied then we shift down one level. + */ +static struct list_head *queue_pop(struct queue *q) +{ + unsigned level; + struct list_head *r; + + for (level = 0; level < NR_QUEUE_LEVELS; level++) + if (!list_empty(q->qs + level)) { + r = q->qs[level].next; + list_del(r); + + /* have we just emptied the bottom level? */ + if (level == 0 && list_empty(q->qs)) + queue_shift_down(q); + + return r; + } + + return NULL; +} + +static struct list_head *list_pop(struct list_head *lh) +{ + struct list_head *r = lh->next; + + BUG_ON(!r); + list_del_init(r); + + return r; +} + +/*----------------------------------------------------------------*/ + +/* + * Describes a cache entry. Used in both the cache and the pre_cache. + */ +struct entry { + struct hlist_node hlist; + struct list_head list; + dm_oblock_t oblock; + dm_cblock_t cblock; /* valid iff in_cache */ + + /* + * FIXME: pack these better + */ + bool in_cache:1; + unsigned hit_count; + unsigned generation; + unsigned tick; +}; + +struct mq_policy { + struct dm_cache_policy policy; + + /* protects everything */ + struct mutex lock; + dm_cblock_t cache_size; + struct io_tracker tracker; + + /* + * We maintain two queues of entries. The cache proper contains + * the currently active mappings. Whereas the pre_cache tracks + * blocks that are being hit frequently and potential candidates + * for promotion to the cache. + */ + struct queue pre_cache; + struct queue cache; + + /* + * Keeps track of time, incremented by the core. We use this to + * avoid attributing multiple hits within the same tick. + * + * Access to tick_protected should be done with the spin lock held. + * It's copied to tick at the start of the map function (within the + * mutex). + */ + spinlock_t tick_lock; + unsigned tick_protected; + unsigned tick; + + /* + * A count of the number of times the map function has been called + * and found an entry in the pre_cache or cache. Currently used to + * calculate the generation. + */ + unsigned hit_count; + + /* + * A generation is a longish period that is used to trigger some + * book keeping effects. eg, decrementing hit counts on entries. + * This is needed to allow the cache to evolve as io patterns + * change. + */ + unsigned generation; + unsigned generation_period; /* in lookups (will probably change) */ + + /* + * Entries in the pre_cache whose hit count passes the promotion + * threshold move to the cache proper. Working out the correct + * value for the promotion_threshold is crucial to this policy. + */ + unsigned promote_threshold; + + /* + * We need cache_size entries for the cache, and choose to have + * cache_size entries for the pre_cache too. One motivation for + * using the same size is to make the hit counts directly + * comparable between pre_cache and cache. + */ + unsigned nr_entries; + unsigned nr_entries_allocated; + struct list_head free; + + /* + * Cache blocks may be unallocated. We store this info in a + * bitset. + */ + unsigned long *allocation_bitset; + unsigned nr_cblocks_allocated; + unsigned find_free_nr_words; + unsigned find_free_last_word; + + /* + * The hash table allows us to quickly find an entry by origin + * block. Both pre_cache and cache entries are in here. + */ + unsigned nr_buckets; + dm_block_t hash_bits; + struct hlist_head *table; +}; + +/*----------------------------------------------------------------*/ +/* Free/alloc mq cache entry structures. */ +static void takeout_queue(struct list_head *lh, struct queue *q) +{ + unsigned level; + + for (level = 0; level < NR_QUEUE_LEVELS; level++) + list_splice(q->qs + level, lh); +} + +static void free_entries(struct mq_policy *mq) +{ + struct entry *e, *tmp; + + takeout_queue(&mq->free, &mq->pre_cache); + takeout_queue(&mq->free, &mq->cache); + + list_for_each_entry_safe(e, tmp, &mq->free, list) + kmem_cache_free(mq_entry_cache, e); +} + +static int alloc_entries(struct mq_policy *mq, unsigned elts) +{ + unsigned u = mq->nr_entries; + + INIT_LIST_HEAD(&mq->free); + mq->nr_entries_allocated = 0; + + while (u--) { + struct entry *e = kmem_cache_zalloc(mq_entry_cache, GFP_KERNEL); + + if (!e) { + free_entries(mq); + return -ENOMEM; + } + + + list_add(&e->list, &mq->free); + } + + return 0; +} + +/*----------------------------------------------------------------*/ + +/* + * Simple hash table implementation. Should replace with the standard hash + * table that's making its way upstream. + */ +static void hash_insert(struct mq_policy *mq, struct entry *e) +{ + unsigned h = hash_64(from_oblock(e->oblock), mq->hash_bits); + + hlist_add_head(&e->hlist, mq->table + h); +} + +static struct entry *hash_lookup(struct mq_policy *mq, dm_oblock_t oblock) +{ + unsigned h = hash_64(from_oblock(oblock), mq->hash_bits); + struct hlist_head *bucket = mq->table + h; + struct entry *e; + + hlist_for_each_entry(e, bucket, hlist) + if (e->oblock == oblock) { + hlist_del(&e->hlist); + hlist_add_head(&e->hlist, bucket); + return e; + } + + return NULL; +} + +static void hash_remove(struct entry *e) +{ + hlist_del(&e->hlist); +} + +/*----------------------------------------------------------------*/ + +/* + * Allocates a new entry structure. The memory is allocated in one lump, + * so we just handing it out here. Returns NULL if all entries have + * already been allocated. Cannot fail otherwise. + */ +static struct entry *alloc_entry(struct mq_policy *mq) +{ + struct entry *e; + + if (mq->nr_entries_allocated >= mq->nr_entries) { + BUG_ON(!list_empty(&mq->free)); + return NULL; + } + + e = list_entry(list_pop(&mq->free), struct entry, list); + INIT_LIST_HEAD(&e->list); + INIT_HLIST_NODE(&e->hlist); + + mq->nr_entries_allocated++; + return e; +} + +/*----------------------------------------------------------------*/ + +/* + * Mark cache blocks allocated or not in the bitset. + */ +static void alloc_cblock(struct mq_policy *mq, dm_cblock_t cblock) +{ + BUG_ON(from_cblock(cblock) > from_cblock(mq->cache_size)); + BUG_ON(test_bit(from_cblock(cblock), mq->allocation_bitset)); + + set_bit(from_cblock(cblock), mq->allocation_bitset); + mq->nr_cblocks_allocated++; +} + +static void free_cblock(struct mq_policy *mq, dm_cblock_t cblock) +{ + BUG_ON(from_cblock(cblock) > from_cblock(mq->cache_size)); + BUG_ON(!test_bit(from_cblock(cblock), mq->allocation_bitset)); + + clear_bit(from_cblock(cblock), mq->allocation_bitset); + mq->nr_cblocks_allocated--; +} + +static bool any_free_cblocks(struct mq_policy *mq) +{ + return mq->nr_cblocks_allocated < from_cblock(mq->cache_size); +} + +/* + * Fills result out with a cache block that isn't in use, or return + * -ENOSPC. This does _not_ mark the cblock as allocated, the caller is + * reponsible for that. + */ +static int __find_free_cblock(struct mq_policy *mq, unsigned begin, unsigned end, + dm_cblock_t *result, unsigned *last_word) +{ + int r = -ENOSPC; + unsigned w; + + for (w = begin; w < end; w++) { + /* + * ffz is undefined if no zero exists + */ + if (mq->allocation_bitset[w] != ~0UL) { + *last_word = w; + *result = to_cblock((w * BITS_PER_LONG) + ffz(mq->allocation_bitset[w])); + if (from_cblock(*result) < from_cblock(mq->cache_size)) + r = 0; + + break; + } + } + + return r; +} + +static int find_free_cblock(struct mq_policy *mq, dm_cblock_t *result) +{ + int r; + + if (!any_free_cblocks(mq)) + return -ENOSPC; + + r = __find_free_cblock(mq, mq->find_free_last_word, mq->find_free_nr_words, result, &mq->find_free_last_word); + if (r == -ENOSPC && mq->find_free_last_word) + r = __find_free_cblock(mq, 0, mq->find_free_last_word, result, &mq->find_free_last_word); + + return r; +} + +/*----------------------------------------------------------------*/ + +/* + * Now we get to the meat of the policy. This section deals with deciding + * when to to add entries to the pre_cache and cache, and move between + * them. + */ + +/* + * The queue level is based on the log2 of the hit count. + */ +static unsigned queue_level(struct entry *e) +{ + return min((unsigned) ilog2(e->hit_count), NR_QUEUE_LEVELS - 1u); +} + +/* + * Inserts the entry into the pre_cache or the cache. Ensures the cache + * block is marked as allocated if necc. Inserts into the hash table. Sets the + * tick which records when the entry was last moved about. + */ +static void push(struct mq_policy *mq, struct entry *e) +{ + e->tick = mq->tick; + hash_insert(mq, e); + + if (e->in_cache) { + alloc_cblock(mq, e->cblock); + queue_push(&mq->cache, queue_level(e), &e->list); + } else + queue_push(&mq->pre_cache, queue_level(e), &e->list); +} + +/* + * Removes an entry from pre_cache or cache. Removes from the hash table. + * Frees off the cache block if necc. + */ +static void del(struct mq_policy *mq, struct entry *e) +{ + queue_remove(&e->list); + hash_remove(e); + if (e->in_cache) + free_cblock(mq, e->cblock); +} + +/* + * Like del, except it removes the first entry in the queue (ie. the least + * recently used). + */ +static struct entry *pop(struct mq_policy *mq, struct queue *q) +{ + struct entry *e = container_of(queue_pop(q), struct entry, list); + + if (e) { + hash_remove(e); + + if (e->in_cache) + free_cblock(mq, e->cblock); + } + + return e; +} + +/* + * Has this entry already been updated? + */ +static bool updated_this_tick(struct mq_policy *mq, struct entry *e) +{ + return mq->tick == e->tick; +} + +/* + * The promotion threshold is adjusted every generation. As are the counts + * of the entries. + * + * At the moment the threshold is taken by averaging the hit counts of some + * of the entries in the cache (the first 20 entries of the first level). + * + * We can be much cleverer than this though. For example, each promotion + * could bump up the threshold helping to prevent churn. Much more to do + * here. + */ + +#define MAX_TO_AVERAGE 20 + +static void check_generation(struct mq_policy *mq) +{ + unsigned total = 0, nr = 0, count = 0, level; + struct list_head *head; + struct entry *e; + + if ((mq->hit_count >= mq->generation_period) && + (mq->nr_cblocks_allocated == from_cblock(mq->cache_size))) { + + mq->hit_count = 0; + mq->generation++; + + for (level = 0; level < NR_QUEUE_LEVELS && count < MAX_TO_AVERAGE; level++) { + head = mq->cache.qs + level; + list_for_each_entry(e, head, list) { + nr++; + total += e->hit_count; + + if (++count >= MAX_TO_AVERAGE) + break; + } + } + + mq->promote_threshold = nr ? total / nr : 1; + if (mq->promote_threshold * nr < total) + mq->promote_threshold++; + } +} + +/* + * Whenever we use an entry we bump up it's hit counter, and push it to the + * back to it's current level. + */ +static void requeue_and_update_tick(struct mq_policy *mq, struct entry *e) +{ + if (updated_this_tick(mq, e)) + return; + + e->hit_count++; + mq->hit_count++; + check_generation(mq); + + /* generation adjustment, to stop the counts increasing forever. */ + /* FIXME: divide? */ + /* e->hit_count -= min(e->hit_count - 1, mq->generation - e->generation); */ + e->generation = mq->generation; + + del(mq, e); + push(mq, e); +} + +/* + * Demote the least recently used entry from the cache to the pre_cache. + * Returns the new cache entry to use, and the old origin block it was + * mapped to. + * + * We drop the hit count on the demoted entry back to 1 to stop it bouncing + * straight back into the cache if it's subsequently hit. There are + * various options here, and more experimentation would be good: + * + * - just forget about the demoted entry completely (ie. don't insert it + into the pre_cache). + * - divide the hit count rather that setting to some hard coded value. + * - set the hit count to a hard coded value other than 1, eg, is it better + * if it goes in at level 2? + */ +static dm_cblock_t demote_cblock(struct mq_policy *mq, dm_oblock_t *oblock) +{ + dm_cblock_t result; + struct entry *demoted = pop(mq, &mq->cache); + + BUG_ON(!demoted); + result = demoted->cblock; + *oblock = demoted->oblock; + demoted->in_cache = false; + demoted->hit_count = 1; + push(mq, demoted); + + return result; +} + +/* + * We modify the basic promotion_threshold depending on the specific io. + * + * If the origin block has been discarded then there's no cost to copy it + * to the cache. + * + * We bias towards reads, since they can be demoted at no cost if they + * haven't been dirtied. + */ +#define DISCARDED_PROMOTE_THRESHOLD 1 +#define READ_PROMOTE_THRESHOLD 4 +#define WRITE_PROMOTE_THRESHOLD 8 + +static unsigned adjusted_promote_threshold(struct mq_policy *mq, + bool discarded_oblock, int data_dir) +{ + if (discarded_oblock && any_free_cblocks(mq) && data_dir == WRITE) + /* + * We don't need to do any copying at all, so give this a + * very low threshold. In practice this only triggers + * during initial population after a format. + */ + return DISCARDED_PROMOTE_THRESHOLD; + + return data_dir == READ ? + (mq->promote_threshold + READ_PROMOTE_THRESHOLD) : + (mq->promote_threshold + WRITE_PROMOTE_THRESHOLD); +} + +static bool should_promote(struct mq_policy *mq, struct entry *e, + bool discarded_oblock, int data_dir) +{ + return e->hit_count >= + adjusted_promote_threshold(mq, discarded_oblock, data_dir); +} + +static int cache_entry_found(struct mq_policy *mq, + struct entry *e, + struct policy_result *result) +{ + requeue_and_update_tick(mq, e); + + if (e->in_cache) { + result->op = POLICY_HIT; + result->cblock = e->cblock; + } + + return 0; +} + +/* + * Moves and entry from the pre_cache to the cache. The main work is + * finding which cache block to use. + */ +static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e, + struct policy_result *result) +{ + dm_cblock_t cblock; + + if (find_free_cblock(mq, &cblock) == -ENOSPC) { + result->op = POLICY_REPLACE; + cblock = demote_cblock(mq, &result->old_oblock); + } else + result->op = POLICY_NEW; + + result->cblock = e->cblock = cblock; + + del(mq, e); + e->in_cache = true; + push(mq, e); + + return 0; +} + +static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e, + bool can_migrate, bool discarded_oblock, + int data_dir, struct policy_result *result) +{ + int r = 0; + bool updated = updated_this_tick(mq, e); + + requeue_and_update_tick(mq, e); + + if ((!discarded_oblock && updated) || + !should_promote(mq, e, discarded_oblock, data_dir)) + result->op = POLICY_MISS; + else if (!can_migrate) + r = -EWOULDBLOCK; + else + r = pre_cache_to_cache(mq, e, result); + + return r; +} + +static void insert_in_pre_cache(struct mq_policy *mq, + dm_oblock_t oblock) +{ + struct entry *e = alloc_entry(mq); + + if (!e) + /* + * There's no spare entry structure, so we grab the least + * used one from the pre_cache. + */ + e = pop(mq, &mq->pre_cache); + + if (unlikely(!e)) { + DMWARN("couldn't pop from pre cache"); + return; + } + + e->in_cache = false; + e->oblock = oblock; + e->hit_count = 1; + e->generation = mq->generation; + push(mq, e); +} + +static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock, + struct policy_result *result) +{ + struct entry *e; + dm_cblock_t cblock; + + if (find_free_cblock(mq, &cblock) == -ENOSPC) { + result->op = POLICY_MISS; + insert_in_pre_cache(mq, oblock); + return; + } + + e = alloc_entry(mq); + if (unlikely(!e)) { + result->op = POLICY_MISS; + return; + } + + e->oblock = oblock; + e->cblock = cblock; + e->in_cache = true; + e->hit_count = 1; + e->generation = mq->generation; + push(mq, e); + + result->op = POLICY_NEW; + result->cblock = e->cblock; +} + +static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock, + bool can_migrate, bool discarded_oblock, + int data_dir, struct policy_result *result) +{ + if (adjusted_promote_threshold(mq, discarded_oblock, data_dir) == 1) { + if (can_migrate) + insert_in_cache(mq, oblock, result); + else + return -EWOULDBLOCK; + } else { + insert_in_pre_cache(mq, oblock); + result->op = POLICY_MISS; + } + + return 0; +} + +/* + * Looks the oblock up in the hash table, then decides whether to put in + * pre_cache, or cache etc. + */ +static int map(struct mq_policy *mq, dm_oblock_t oblock, + bool can_migrate, bool discarded_oblock, + int data_dir, struct policy_result *result) +{ + int r = 0; + struct entry *e = hash_lookup(mq, oblock); + + if (e && e->in_cache) + r = cache_entry_found(mq, e, result); + else if (iot_pattern(&mq->tracker) == PATTERN_SEQUENTIAL) + result->op = POLICY_MISS; + else if (e) + r = pre_cache_entry_found(mq, e, can_migrate, discarded_oblock, + data_dir, result); + else + r = no_entry_found(mq, oblock, can_migrate, discarded_oblock, + data_dir, result); + + if (r == -EWOULDBLOCK) + result->op = POLICY_MISS; + + return r; +} + +/*----------------------------------------------------------------*/ + +/* + * Public interface, via the policy struct. See dm-cache-policy.h for a + * description of these. + */ + +static struct mq_policy *to_mq_policy(struct dm_cache_policy *p) +{ + return container_of(p, struct mq_policy, policy); +} + +static void mq_destroy(struct dm_cache_policy *p) +{ + struct mq_policy *mq = to_mq_policy(p); + + free_bitset(mq->allocation_bitset); + kfree(mq->table); + free_entries(mq); + kfree(mq); +} + +static void copy_tick(struct mq_policy *mq) +{ + unsigned long flags; + + spin_lock_irqsave(&mq->tick_lock, flags); + mq->tick = mq->tick_protected; + spin_unlock_irqrestore(&mq->tick_lock, flags); +} + +static int mq_map(struct dm_cache_policy *p, dm_oblock_t oblock, + bool can_block, bool can_migrate, bool discarded_oblock, + struct bio *bio, struct policy_result *result) +{ + int r; + struct mq_policy *mq = to_mq_policy(p); + + result->op = POLICY_MISS; + + if (can_block) + mutex_lock(&mq->lock); + else if (!mutex_trylock(&mq->lock)) + return -EWOULDBLOCK; + + copy_tick(mq); + + iot_examine_bio(&mq->tracker, bio); + r = map(mq, oblock, can_migrate, discarded_oblock, + bio_data_dir(bio), result); + + mutex_unlock(&mq->lock); + + return r; +} + +static int mq_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock) +{ + int r; + struct mq_policy *mq = to_mq_policy(p); + struct entry *e; + + if (!mutex_trylock(&mq->lock)) + return -EWOULDBLOCK; + + e = hash_lookup(mq, oblock); + if (e && e->in_cache) { + *cblock = e->cblock; + r = 0; + } else + r = -ENOENT; + + mutex_unlock(&mq->lock); + + return r; +} + +static int mq_load_mapping(struct dm_cache_policy *p, + dm_oblock_t oblock, dm_cblock_t cblock, + uint32_t hint, bool hint_valid) +{ + struct mq_policy *mq = to_mq_policy(p); + struct entry *e; + + e = alloc_entry(mq); + if (!e) + return -ENOMEM; + + e->cblock = cblock; + e->oblock = oblock; + e->in_cache = true; + e->hit_count = hint_valid ? hint : 1; + e->generation = mq->generation; + push(mq, e); + + return 0; +} + +static int mq_walk_mappings(struct dm_cache_policy *p, policy_walk_fn fn, + void *context) +{ + struct mq_policy *mq = to_mq_policy(p); + int r = 0; + struct entry *e; + unsigned level; + + mutex_lock(&mq->lock); + + for (level = 0; level < NR_QUEUE_LEVELS; level++) + list_for_each_entry(e, &mq->cache.qs[level], list) { + r = fn(context, e->cblock, e->oblock, e->hit_count); + if (r) + goto out; + } + +out: + mutex_unlock(&mq->lock); + + return r; +} + +static void remove_mapping(struct mq_policy *mq, dm_oblock_t oblock) +{ + struct entry *e = hash_lookup(mq, oblock); + + BUG_ON(!e || !e->in_cache); + + del(mq, e); + e->in_cache = false; + push(mq, e); +} + +static void mq_remove_mapping(struct dm_cache_policy *p, dm_oblock_t oblock) +{ + struct mq_policy *mq = to_mq_policy(p); + + mutex_lock(&mq->lock); + remove_mapping(mq, oblock); + mutex_unlock(&mq->lock); +} + +static void force_mapping(struct mq_policy *mq, + dm_oblock_t current_oblock, dm_oblock_t new_oblock) +{ + struct entry *e = hash_lookup(mq, current_oblock); + + BUG_ON(!e || !e->in_cache); + + del(mq, e); + e->oblock = new_oblock; + push(mq, e); +} + +static void mq_force_mapping(struct dm_cache_policy *p, + dm_oblock_t current_oblock, dm_oblock_t new_oblock) +{ + struct mq_policy *mq = to_mq_policy(p); + + mutex_lock(&mq->lock); + force_mapping(mq, current_oblock, new_oblock); + mutex_unlock(&mq->lock); +} + +static dm_cblock_t mq_residency(struct dm_cache_policy *p) +{ + struct mq_policy *mq = to_mq_policy(p); + + /* FIXME: lock mutex, not sure we can block here */ + return to_cblock(mq->nr_cblocks_allocated); +} + +static void mq_tick(struct dm_cache_policy *p) +{ + struct mq_policy *mq = to_mq_policy(p); + unsigned long flags; + + spin_lock_irqsave(&mq->tick_lock, flags); + mq->tick_protected++; + spin_unlock_irqrestore(&mq->tick_lock, flags); +} + +static int mq_set_config_value(struct dm_cache_policy *p, + const char *key, const char *value) +{ + struct mq_policy *mq = to_mq_policy(p); + enum io_pattern pattern; + unsigned long tmp; + + if (!strcasecmp(key, "random_threshold")) + pattern = PATTERN_RANDOM; + else if (!strcasecmp(key, "sequential_threshold")) + pattern = PATTERN_SEQUENTIAL; + else + return -EINVAL; + + if (kstrtoul(value, 10, &tmp)) + return -EINVAL; + + mq->tracker.thresholds[pattern] = tmp; + + return 0; +} + +static int mq_emit_config_values(struct dm_cache_policy *p, char *result, unsigned maxlen) +{ + ssize_t sz = 0; + struct mq_policy *mq = to_mq_policy(p); + + DMEMIT("4 random_threshold %u sequential_threshold %u", + mq->tracker.thresholds[PATTERN_RANDOM], + mq->tracker.thresholds[PATTERN_SEQUENTIAL]); + + return 0; +} + +/* Init the policy plugin interface function pointers. */ +static void init_policy_functions(struct mq_policy *mq) +{ + mq->policy.destroy = mq_destroy; + mq->policy.map = mq_map; + mq->policy.lookup = mq_lookup; + mq->policy.load_mapping = mq_load_mapping; + mq->policy.walk_mappings = mq_walk_mappings; + mq->policy.remove_mapping = mq_remove_mapping; + mq->policy.writeback_work = NULL; + mq->policy.force_mapping = mq_force_mapping; + mq->policy.residency = mq_residency; + mq->policy.tick = mq_tick; + mq->policy.emit_config_values = mq_emit_config_values; + mq->policy.set_config_value = mq_set_config_value; +} + +static struct dm_cache_policy *mq_create(dm_cblock_t cache_size, + sector_t origin_size, + sector_t cache_block_size) +{ + int r; + struct mq_policy *mq = kzalloc(sizeof(*mq), GFP_KERNEL); + + if (!mq) + return NULL; + + init_policy_functions(mq); + iot_init(&mq->tracker, SEQUENTIAL_THRESHOLD_DEFAULT, RANDOM_THRESHOLD_DEFAULT); + + mq->cache_size = cache_size; + mq->tick_protected = 0; + mq->tick = 0; + mq->hit_count = 0; + mq->generation = 0; + mq->promote_threshold = 0; + mutex_init(&mq->lock); + spin_lock_init(&mq->tick_lock); + mq->find_free_nr_words = dm_div_up(from_cblock(mq->cache_size), BITS_PER_LONG); + mq->find_free_last_word = 0; + + queue_init(&mq->pre_cache); + queue_init(&mq->cache); + mq->generation_period = max((unsigned) from_cblock(cache_size), 1024U); + + mq->nr_entries = 2 * from_cblock(cache_size); + r = alloc_entries(mq, mq->nr_entries); + if (r) + goto bad_cache_alloc; + + mq->nr_entries_allocated = 0; + mq->nr_cblocks_allocated = 0; + + mq->nr_buckets = next_power(from_cblock(cache_size) / 2, 16); + mq->hash_bits = ffs(mq->nr_buckets) - 1; + mq->table = kzalloc(sizeof(*mq->table) * mq->nr_buckets, GFP_KERNEL); + if (!mq->table) + goto bad_alloc_table; + + mq->allocation_bitset = alloc_bitset(from_cblock(cache_size)); + if (!mq->allocation_bitset) + goto bad_alloc_bitset; + + return &mq->policy; + +bad_alloc_bitset: + kfree(mq->table); +bad_alloc_table: + free_entries(mq); +bad_cache_alloc: + kfree(mq); + + return NULL; +} + +/*----------------------------------------------------------------*/ + +static struct dm_cache_policy_type mq_policy_type = { + .name = "mq", + .hint_size = 4, + .owner = THIS_MODULE, + .create = mq_create +}; + +static struct dm_cache_policy_type default_policy_type = { + .name = "default", + .hint_size = 4, + .owner = THIS_MODULE, + .create = mq_create +}; + +static int __init mq_init(void) +{ + int r; + + mq_entry_cache = kmem_cache_create("dm_mq_policy_cache_entry", + sizeof(struct entry), + __alignof__(struct entry), + 0, NULL); + if (!mq_entry_cache) + goto bad; + + r = dm_cache_policy_register(&mq_policy_type); + if (r) { + DMERR("register failed %d", r); + goto bad_register_mq; + } + + r = dm_cache_policy_register(&default_policy_type); + if (!r) { + DMINFO("version " MQ_VERSION " loaded"); + return 0; + } + + DMERR("register failed (as default) %d", r); + + dm_cache_policy_unregister(&mq_policy_type); +bad_register_mq: + kmem_cache_destroy(mq_entry_cache); +bad: + return -ENOMEM; +} + +static void __exit mq_exit(void) +{ + dm_cache_policy_unregister(&mq_policy_type); + dm_cache_policy_unregister(&default_policy_type); + + kmem_cache_destroy(mq_entry_cache); +} + +module_init(mq_init); +module_exit(mq_exit); + +MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("mq cache policy"); + +MODULE_ALIAS("dm-cache-default"); diff --git a/drivers/md/dm-cache-policy.c b/drivers/md/dm-cache-policy.c new file mode 100644 index 00000000000..2cbf5fdaac5 --- /dev/null +++ b/drivers/md/dm-cache-policy.c @@ -0,0 +1,161 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * This file is released under the GPL. + */ + +#include "dm-cache-policy-internal.h" +#include "dm.h" + +#include <linux/module.h> +#include <linux/slab.h> + +/*----------------------------------------------------------------*/ + +#define DM_MSG_PREFIX "cache-policy" + +static DEFINE_SPINLOCK(register_lock); +static LIST_HEAD(register_list); + +static struct dm_cache_policy_type *__find_policy(const char *name) +{ + struct dm_cache_policy_type *t; + + list_for_each_entry(t, ®ister_list, list) + if (!strcmp(t->name, name)) + return t; + + return NULL; +} + +static struct dm_cache_policy_type *__get_policy_once(const char *name) +{ + struct dm_cache_policy_type *t = __find_policy(name); + + if (t && !try_module_get(t->owner)) { + DMWARN("couldn't get module %s", name); + t = ERR_PTR(-EINVAL); + } + + return t; +} + +static struct dm_cache_policy_type *get_policy_once(const char *name) +{ + struct dm_cache_policy_type *t; + + spin_lock(®ister_lock); + t = __get_policy_once(name); + spin_unlock(®ister_lock); + + return t; +} + +static struct dm_cache_policy_type *get_policy(const char *name) +{ + struct dm_cache_policy_type *t; + + t = get_policy_once(name); + if (IS_ERR(t)) + return NULL; + + if (t) + return t; + + request_module("dm-cache-%s", name); + + t = get_policy_once(name); + if (IS_ERR(t)) + return NULL; + + return t; +} + +static void put_policy(struct dm_cache_policy_type *t) +{ + module_put(t->owner); +} + +int dm_cache_policy_register(struct dm_cache_policy_type *type) +{ + int r; + + /* One size fits all for now */ + if (type->hint_size != 0 && type->hint_size != 4) { + DMWARN("hint size must be 0 or 4 but %llu supplied.", (unsigned long long) type->hint_size); + return -EINVAL; + } + + spin_lock(®ister_lock); + if (__find_policy(type->name)) { + DMWARN("attempt to register policy under duplicate name %s", type->name); + r = -EINVAL; + } else { + list_add(&type->list, ®ister_list); + r = 0; + } + spin_unlock(®ister_lock); + + return r; +} +EXPORT_SYMBOL_GPL(dm_cache_policy_register); + +void dm_cache_policy_unregister(struct dm_cache_policy_type *type) +{ + spin_lock(®ister_lock); + list_del_init(&type->list); + spin_unlock(®ister_lock); +} +EXPORT_SYMBOL_GPL(dm_cache_policy_unregister); + +struct dm_cache_policy *dm_cache_policy_create(const char *name, + dm_cblock_t cache_size, + sector_t origin_size, + sector_t cache_block_size) +{ + struct dm_cache_policy *p = NULL; + struct dm_cache_policy_type *type; + + type = get_policy(name); + if (!type) { + DMWARN("unknown policy type"); + return NULL; + } + + p = type->create(cache_size, origin_size, cache_block_size); + if (!p) { + put_policy(type); + return NULL; + } + p->private = type; + + return p; +} +EXPORT_SYMBOL_GPL(dm_cache_policy_create); + +void dm_cache_policy_destroy(struct dm_cache_policy *p) +{ + struct dm_cache_policy_type *t = p->private; + + p->destroy(p); + put_policy(t); +} +EXPORT_SYMBOL_GPL(dm_cache_policy_destroy); + +const char *dm_cache_policy_get_name(struct dm_cache_policy *p) +{ + struct dm_cache_policy_type *t = p->private; + + return t->name; +} +EXPORT_SYMBOL_GPL(dm_cache_policy_get_name); + +size_t dm_cache_policy_get_hint_size(struct dm_cache_policy *p) +{ + struct dm_cache_policy_type *t = p->private; + + return t->hint_size; +} +EXPORT_SYMBOL_GPL(dm_cache_policy_get_hint_size); + +/*----------------------------------------------------------------*/ diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h new file mode 100644 index 00000000000..f0f51b26054 --- /dev/null +++ b/drivers/md/dm-cache-policy.h @@ -0,0 +1,228 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * This file is released under the GPL. + */ + +#ifndef DM_CACHE_POLICY_H +#define DM_CACHE_POLICY_H + +#include "dm-cache-block-types.h" + +#include <linux/device-mapper.h> + +/*----------------------------------------------------------------*/ + +/* FIXME: make it clear which methods are optional. Get debug policy to + * double check this at start. + */ + +/* + * The cache policy makes the important decisions about which blocks get to + * live on the faster cache device. + * + * When the core target has to remap a bio it calls the 'map' method of the + * policy. This returns an instruction telling the core target what to do. + * + * POLICY_HIT: + * That block is in the cache. Remap to the cache and carry on. + * + * POLICY_MISS: + * This block is on the origin device. Remap and carry on. + * + * POLICY_NEW: + * This block is currently on the origin device, but the policy wants to + * move it. The core should: + * + * - hold any further io to this origin block + * - copy the origin to the given cache block + * - release all the held blocks + * - remap the original block to the cache + * + * POLICY_REPLACE: + * This block is currently on the origin device. The policy wants to + * move it to the cache, with the added complication that the destination + * cache block needs a writeback first. The core should: + * + * - hold any further io to this origin block + * - hold any further io to the origin block that's being written back + * - writeback + * - copy new block to cache + * - release held blocks + * - remap bio to cache and reissue. + * + * Should the core run into trouble while processing a POLICY_NEW or + * POLICY_REPLACE instruction it will roll back the policies mapping using + * remove_mapping() or force_mapping(). These methods must not fail. This + * approach avoids having transactional semantics in the policy (ie, the + * core informing the policy when a migration is complete), and hence makes + * it easier to write new policies. + * + * In general policy methods should never block, except in the case of the + * map function when can_migrate is set. So be careful to implement using + * bounded, preallocated memory. + */ +enum policy_operation { + POLICY_HIT, + POLICY_MISS, + POLICY_NEW, + POLICY_REPLACE +}; + +/* + * This is the instruction passed back to the core target. + */ +struct policy_result { + enum policy_operation op; + dm_oblock_t old_oblock; /* POLICY_REPLACE */ + dm_cblock_t cblock; /* POLICY_HIT, POLICY_NEW, POLICY_REPLACE */ +}; + +typedef int (*policy_walk_fn)(void *context, dm_cblock_t cblock, + dm_oblock_t oblock, uint32_t hint); + +/* + * The cache policy object. Just a bunch of methods. It is envisaged that + * this structure will be embedded in a bigger, policy specific structure + * (ie. use container_of()). + */ +struct dm_cache_policy { + + /* + * FIXME: make it clear which methods are optional, and which may + * block. + */ + + /* + * Destroys this object. + */ + void (*destroy)(struct dm_cache_policy *p); + + /* + * See large comment above. + * + * oblock - the origin block we're interested in. + * + * can_block - indicates whether the current thread is allowed to + * block. -EWOULDBLOCK returned if it can't and would. + * + * can_migrate - gives permission for POLICY_NEW or POLICY_REPLACE + * instructions. If denied and the policy would have + * returned one of these instructions it should + * return -EWOULDBLOCK. + * + * discarded_oblock - indicates whether the whole origin block is + * in a discarded state (FIXME: better to tell the + * policy about this sooner, so it can recycle that + * cache block if it wants.) + * bio - the bio that triggered this call. + * result - gets filled in with the instruction. + * + * May only return 0, or -EWOULDBLOCK (if !can_migrate) + */ + int (*map)(struct dm_cache_policy *p, dm_oblock_t oblock, + bool can_block, bool can_migrate, bool discarded_oblock, + struct bio *bio, struct policy_result *result); + + /* + * Sometimes we want to see if a block is in the cache, without + * triggering any update of stats. (ie. it's not a real hit). + * + * Must not block. + * + * Returns 1 iff in cache, 0 iff not, < 0 on error (-EWOULDBLOCK + * would be typical). + */ + int (*lookup)(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock); + + /* + * oblock must be a mapped block. Must not block. + */ + void (*set_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock); + void (*clear_dirty)(struct dm_cache_policy *p, dm_oblock_t oblock); + + /* + * Called when a cache target is first created. Used to load a + * mapping from the metadata device into the policy. + */ + int (*load_mapping)(struct dm_cache_policy *p, dm_oblock_t oblock, + dm_cblock_t cblock, uint32_t hint, bool hint_valid); + + int (*walk_mappings)(struct dm_cache_policy *p, policy_walk_fn fn, + void *context); + + /* + * Override functions used on the error paths of the core target. + * They must succeed. + */ + void (*remove_mapping)(struct dm_cache_policy *p, dm_oblock_t oblock); + void (*force_mapping)(struct dm_cache_policy *p, dm_oblock_t current_oblock, + dm_oblock_t new_oblock); + + int (*writeback_work)(struct dm_cache_policy *p, dm_oblock_t *oblock, dm_cblock_t *cblock); + + + /* + * How full is the cache? + */ + dm_cblock_t (*residency)(struct dm_cache_policy *p); + + /* + * Because of where we sit in the block layer, we can be asked to + * map a lot of little bios that are all in the same block (no + * queue merging has occurred). To stop the policy being fooled by + * these the core target sends regular tick() calls to the policy. + * The policy should only count an entry as hit once per tick. + */ + void (*tick)(struct dm_cache_policy *p); + + /* + * Configuration. + */ + int (*emit_config_values)(struct dm_cache_policy *p, + char *result, unsigned maxlen); + int (*set_config_value)(struct dm_cache_policy *p, + const char *key, const char *value); + + /* + * Book keeping ptr for the policy register, not for general use. + */ + void *private; +}; + +/*----------------------------------------------------------------*/ + +/* + * We maintain a little register of the different policy types. + */ +#define CACHE_POLICY_NAME_SIZE 16 + +struct dm_cache_policy_type { + /* For use by the register code only. */ + struct list_head list; + + /* + * Policy writers should fill in these fields. The name field is + * what gets passed on the target line to select your policy. + */ + char name[CACHE_POLICY_NAME_SIZE]; + + /* + * Policies may store a hint for each each cache block. + * Currently the size of this hint must be 0 or 4 bytes but we + * expect to relax this in future. + */ + size_t hint_size; + + struct module *owner; + struct dm_cache_policy *(*create)(dm_cblock_t cache_size, + sector_t origin_size, + sector_t block_size); +}; + +int dm_cache_policy_register(struct dm_cache_policy_type *type); +void dm_cache_policy_unregister(struct dm_cache_policy_type *type); + +/*----------------------------------------------------------------*/ + +#endif /* DM_CACHE_POLICY_H */ diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c new file mode 100644 index 00000000000..0f4e84b15c3 --- /dev/null +++ b/drivers/md/dm-cache-target.c @@ -0,0 +1,2584 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * This file is released under the GPL. + */ + +#include "dm.h" +#include "dm-bio-prison.h" +#include "dm-cache-metadata.h" + +#include <linux/dm-io.h> +#include <linux/dm-kcopyd.h> +#include <linux/init.h> +#include <linux/mempool.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#define DM_MSG_PREFIX "cache" + +DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(cache_copy_throttle, + "A percentage of time allocated for copying to and/or from cache"); + +/*----------------------------------------------------------------*/ + +/* + * Glossary: + * + * oblock: index of an origin block + * cblock: index of a cache block + * promotion: movement of a block from origin to cache + * demotion: movement of a block from cache to origin + * migration: movement of a block between the origin and cache device, + * either direction + */ + +/*----------------------------------------------------------------*/ + +static size_t bitset_size_in_bytes(unsigned nr_entries) +{ + return sizeof(unsigned long) * dm_div_up(nr_entries, BITS_PER_LONG); +} + +static unsigned long *alloc_bitset(unsigned nr_entries) +{ + size_t s = bitset_size_in_bytes(nr_entries); + return vzalloc(s); +} + +static void clear_bitset(void *bitset, unsigned nr_entries) +{ + size_t s = bitset_size_in_bytes(nr_entries); + memset(bitset, 0, s); +} + +static void free_bitset(unsigned long *bits) +{ + vfree(bits); +} + +/*----------------------------------------------------------------*/ + +#define PRISON_CELLS 1024 +#define MIGRATION_POOL_SIZE 128 +#define COMMIT_PERIOD HZ +#define MIGRATION_COUNT_WINDOW 10 + +/* + * The block size of the device holding cache data must be >= 32KB + */ +#define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (32 * 1024 >> SECTOR_SHIFT) + +/* + * FIXME: the cache is read/write for the time being. + */ +enum cache_mode { + CM_WRITE, /* metadata may be changed */ + CM_READ_ONLY, /* metadata may not be changed */ +}; + +struct cache_features { + enum cache_mode mode; + bool write_through:1; +}; + +struct cache_stats { + atomic_t read_hit; + atomic_t read_miss; + atomic_t write_hit; + atomic_t write_miss; + atomic_t demotion; + atomic_t promotion; + atomic_t copies_avoided; + atomic_t cache_cell_clash; + atomic_t commit_count; + atomic_t discard_count; +}; + +struct cache { + struct dm_target *ti; + struct dm_target_callbacks callbacks; + + /* + * Metadata is written to this device. + */ + struct dm_dev *metadata_dev; + + /* + * The slower of the two data devices. Typically a spindle. + */ + struct dm_dev *origin_dev; + + /* + * The faster of the two data devices. Typically an SSD. + */ + struct dm_dev *cache_dev; + + /* + * Cache features such as write-through. + */ + struct cache_features features; + + /* + * Size of the origin device in _complete_ blocks and native sectors. + */ + dm_oblock_t origin_blocks; + sector_t origin_sectors; + + /* + * Size of the cache device in blocks. + */ + dm_cblock_t cache_size; + + /* + * Fields for converting from sectors to blocks. + */ + uint32_t sectors_per_block; + int sectors_per_block_shift; + + struct dm_cache_metadata *cmd; + + spinlock_t lock; + struct bio_list deferred_bios; + struct bio_list deferred_flush_bios; + struct list_head quiesced_migrations; + struct list_head completed_migrations; + struct list_head need_commit_migrations; + sector_t migration_threshold; + atomic_t nr_migrations; + wait_queue_head_t migration_wait; + + /* + * cache_size entries, dirty if set + */ + dm_cblock_t nr_dirty; + unsigned long *dirty_bitset; + + /* + * origin_blocks entries, discarded if set. + */ + sector_t discard_block_size; /* a power of 2 times sectors per block */ + dm_dblock_t discard_nr_blocks; + unsigned long *discard_bitset; + + struct dm_kcopyd_client *copier; + struct workqueue_struct *wq; + struct work_struct worker; + + struct delayed_work waker; + unsigned long last_commit_jiffies; + + struct dm_bio_prison *prison; + struct dm_deferred_set *all_io_ds; + + mempool_t *migration_pool; + struct dm_cache_migration *next_migration; + + struct dm_cache_policy *policy; + unsigned policy_nr_args; + + bool need_tick_bio:1; + bool sized:1; + bool quiescing:1; + bool commit_requested:1; + bool loaded_mappings:1; + bool loaded_discards:1; + + struct cache_stats stats; + + /* + * Rather than reconstructing the table line for the status we just + * save it and regurgitate. + */ + unsigned nr_ctr_args; + const char **ctr_args; +}; + +struct per_bio_data { + bool tick:1; + unsigned req_nr:2; + struct dm_deferred_entry *all_io_entry; +}; + +struct dm_cache_migration { + struct list_head list; + struct cache *cache; + + unsigned long start_jiffies; + dm_oblock_t old_oblock; + dm_oblock_t new_oblock; + dm_cblock_t cblock; + + bool err:1; + bool writeback:1; + bool demote:1; + bool promote:1; + + struct dm_bio_prison_cell *old_ocell; + struct dm_bio_prison_cell *new_ocell; +}; + +/* + * Processing a bio in the worker thread may require these memory + * allocations. We prealloc to avoid deadlocks (the same worker thread + * frees them back to the mempool). + */ +struct prealloc { + struct dm_cache_migration *mg; + struct dm_bio_prison_cell *cell1; + struct dm_bio_prison_cell *cell2; +}; + +static void wake_worker(struct cache *cache) +{ + queue_work(cache->wq, &cache->worker); +} + +/*----------------------------------------------------------------*/ + +static struct dm_bio_prison_cell *alloc_prison_cell(struct cache *cache) +{ + /* FIXME: change to use a local slab. */ + return dm_bio_prison_alloc_cell(cache->prison, GFP_NOWAIT); +} + +static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell *cell) +{ + dm_bio_prison_free_cell(cache->prison, cell); +} + +static int prealloc_data_structs(struct cache *cache, struct prealloc *p) +{ + if (!p->mg) { + p->mg = mempool_alloc(cache->migration_pool, GFP_NOWAIT); + if (!p->mg) + return -ENOMEM; + } + + if (!p->cell1) { + p->cell1 = alloc_prison_cell(cache); + if (!p->cell1) + return -ENOMEM; + } + + if (!p->cell2) { + p->cell2 = alloc_prison_cell(cache); + if (!p->cell2) + return -ENOMEM; + } + + return 0; +} + +static void prealloc_free_structs(struct cache *cache, struct prealloc *p) +{ + if (p->cell2) + free_prison_cell(cache, p->cell2); + + if (p->cell1) + free_prison_cell(cache, p->cell1); + + if (p->mg) + mempool_free(p->mg, cache->migration_pool); +} + +static struct dm_cache_migration *prealloc_get_migration(struct prealloc *p) +{ + struct dm_cache_migration *mg = p->mg; + + BUG_ON(!mg); + p->mg = NULL; + + return mg; +} + +/* + * You must have a cell within the prealloc struct to return. If not this + * function will BUG() rather than returning NULL. + */ +static struct dm_bio_prison_cell *prealloc_get_cell(struct prealloc *p) +{ + struct dm_bio_prison_cell *r = NULL; + + if (p->cell1) { + r = p->cell1; + p->cell1 = NULL; + + } else if (p->cell2) { + r = p->cell2; + p->cell2 = NULL; + } else + BUG(); + + return r; +} + +/* + * You can't have more than two cells in a prealloc struct. BUG() will be + * called if you try and overfill. + */ +static void prealloc_put_cell(struct prealloc *p, struct dm_bio_prison_cell *cell) +{ + if (!p->cell2) + p->cell2 = cell; + + else if (!p->cell1) + p->cell1 = cell; + + else + BUG(); +} + +/*----------------------------------------------------------------*/ + +static void build_key(dm_oblock_t oblock, struct dm_cell_key *key) +{ + key->virtual = 0; + key->dev = 0; + key->block = from_oblock(oblock); +} + +/* + * The caller hands in a preallocated cell, and a free function for it. + * The cell will be freed if there's an error, or if it wasn't used because + * a cell with that key already exists. + */ +typedef void (*cell_free_fn)(void *context, struct dm_bio_prison_cell *cell); + +static int bio_detain(struct cache *cache, dm_oblock_t oblock, + struct bio *bio, struct dm_bio_prison_cell *cell_prealloc, + cell_free_fn free_fn, void *free_context, + struct dm_bio_prison_cell **cell_result) +{ + int r; + struct dm_cell_key key; + + build_key(oblock, &key); + r = dm_bio_detain(cache->prison, &key, bio, cell_prealloc, cell_result); + if (r) + free_fn(free_context, cell_prealloc); + + return r; +} + +static int get_cell(struct cache *cache, + dm_oblock_t oblock, + struct prealloc *structs, + struct dm_bio_prison_cell **cell_result) +{ + int r; + struct dm_cell_key key; + struct dm_bio_prison_cell *cell_prealloc; + + cell_prealloc = prealloc_get_cell(structs); + + build_key(oblock, &key); + r = dm_get_cell(cache->prison, &key, cell_prealloc, cell_result); + if (r) + prealloc_put_cell(structs, cell_prealloc); + + return r; +} + + /*----------------------------------------------------------------*/ + +static bool is_dirty(struct cache *cache, dm_cblock_t b) +{ + return test_bit(from_cblock(b), cache->dirty_bitset); +} + +static void set_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock) +{ + if (!test_and_set_bit(from_cblock(cblock), cache->dirty_bitset)) { + cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) + 1); + policy_set_dirty(cache->policy, oblock); + } +} + +static void clear_dirty(struct cache *cache, dm_oblock_t oblock, dm_cblock_t cblock) +{ + if (test_and_clear_bit(from_cblock(cblock), cache->dirty_bitset)) { + policy_clear_dirty(cache->policy, oblock); + cache->nr_dirty = to_cblock(from_cblock(cache->nr_dirty) - 1); + if (!from_cblock(cache->nr_dirty)) + dm_table_event(cache->ti->table); + } +} + +/*----------------------------------------------------------------*/ +static bool block_size_is_power_of_two(struct cache *cache) +{ + return cache->sectors_per_block_shift >= 0; +} + +static dm_dblock_t oblock_to_dblock(struct cache *cache, dm_oblock_t oblock) +{ + sector_t discard_blocks = cache->discard_block_size; + dm_block_t b = from_oblock(oblock); + + if (!block_size_is_power_of_two(cache)) + (void) sector_div(discard_blocks, cache->sectors_per_block); + else + discard_blocks >>= cache->sectors_per_block_shift; + + (void) sector_div(b, discard_blocks); + + return to_dblock(b); +} + +static void set_discard(struct cache *cache, dm_dblock_t b) +{ + unsigned long flags; + + atomic_inc(&cache->stats.discard_count); + + spin_lock_irqsave(&cache->lock, flags); + set_bit(from_dblock(b), cache->discard_bitset); + spin_unlock_irqrestore(&cache->lock, flags); +} + +static void clear_discard(struct cache *cache, dm_dblock_t b) +{ + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + clear_bit(from_dblock(b), cache->discard_bitset); + spin_unlock_irqrestore(&cache->lock, flags); +} + +static bool is_discarded(struct cache *cache, dm_dblock_t b) +{ + int r; + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + r = test_bit(from_dblock(b), cache->discard_bitset); + spin_unlock_irqrestore(&cache->lock, flags); + + return r; +} + +static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b) +{ + int r; + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + r = test_bit(from_dblock(oblock_to_dblock(cache, b)), + cache->discard_bitset); + spin_unlock_irqrestore(&cache->lock, flags); + + return r; +} + +/*----------------------------------------------------------------*/ + +static void load_stats(struct cache *cache) +{ + struct dm_cache_statistics stats; + + dm_cache_metadata_get_stats(cache->cmd, &stats); + atomic_set(&cache->stats.read_hit, stats.read_hits); + atomic_set(&cache->stats.read_miss, stats.read_misses); + atomic_set(&cache->stats.write_hit, stats.write_hits); + atomic_set(&cache->stats.write_miss, stats.write_misses); +} + +static void save_stats(struct cache *cache) +{ + struct dm_cache_statistics stats; + + stats.read_hits = atomic_read(&cache->stats.read_hit); + stats.read_misses = atomic_read(&cache->stats.read_miss); + stats.write_hits = atomic_read(&cache->stats.write_hit); + stats.write_misses = atomic_read(&cache->stats.write_miss); + + dm_cache_metadata_set_stats(cache->cmd, &stats); +} + +/*---------------------------------------------------------------- + * Per bio data + *--------------------------------------------------------------*/ +static struct per_bio_data *get_per_bio_data(struct bio *bio) +{ + struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); + BUG_ON(!pb); + return pb; +} + +static struct per_bio_data *init_per_bio_data(struct bio *bio) +{ + struct per_bio_data *pb = get_per_bio_data(bio); + + pb->tick = false; + pb->req_nr = dm_bio_get_target_bio_nr(bio); + pb->all_io_entry = NULL; + + return pb; +} + +/*---------------------------------------------------------------- + * Remapping + *--------------------------------------------------------------*/ +static void remap_to_origin(struct cache *cache, struct bio *bio) +{ + bio->bi_bdev = cache->origin_dev->bdev; +} + +static void remap_to_cache(struct cache *cache, struct bio *bio, + dm_cblock_t cblock) +{ + sector_t bi_sector = bio->bi_sector; + + bio->bi_bdev = cache->cache_dev->bdev; + if (!block_size_is_power_of_two(cache)) + bio->bi_sector = (from_cblock(cblock) * cache->sectors_per_block) + + sector_div(bi_sector, cache->sectors_per_block); + else + bio->bi_sector = (from_cblock(cblock) << cache->sectors_per_block_shift) | + (bi_sector & (cache->sectors_per_block - 1)); +} + +static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) +{ + unsigned long flags; + struct per_bio_data *pb = get_per_bio_data(bio); + + spin_lock_irqsave(&cache->lock, flags); + if (cache->need_tick_bio && + !(bio->bi_rw & (REQ_FUA | REQ_FLUSH | REQ_DISCARD))) { + pb->tick = true; + cache->need_tick_bio = false; + } + spin_unlock_irqrestore(&cache->lock, flags); +} + +static void remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, + dm_oblock_t oblock) +{ + check_if_tick_bio_needed(cache, bio); + remap_to_origin(cache, bio); + if (bio_data_dir(bio) == WRITE) + clear_discard(cache, oblock_to_dblock(cache, oblock)); +} + +static void remap_to_cache_dirty(struct cache *cache, struct bio *bio, + dm_oblock_t oblock, dm_cblock_t cblock) +{ + remap_to_cache(cache, bio, cblock); + if (bio_data_dir(bio) == WRITE) { + set_dirty(cache, oblock, cblock); + clear_discard(cache, oblock_to_dblock(cache, oblock)); + } +} + +static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio) +{ + sector_t block_nr = bio->bi_sector; + + if (!block_size_is_power_of_two(cache)) + (void) sector_div(block_nr, cache->sectors_per_block); + else + block_nr >>= cache->sectors_per_block_shift; + + return to_oblock(block_nr); +} + +static int bio_triggers_commit(struct cache *cache, struct bio *bio) +{ + return bio->bi_rw & (REQ_FLUSH | REQ_FUA); +} + +static void issue(struct cache *cache, struct bio *bio) +{ + unsigned long flags; + + if (!bio_triggers_commit(cache, bio)) { + generic_make_request(bio); + return; + } + + /* + * Batch together any bios that trigger commits and then issue a + * single commit for them in do_worker(). + */ + spin_lock_irqsave(&cache->lock, flags); + cache->commit_requested = true; + bio_list_add(&cache->deferred_flush_bios, bio); + spin_unlock_irqrestore(&cache->lock, flags); +} + +/*---------------------------------------------------------------- + * Migration processing + * + * Migration covers moving data from the origin device to the cache, or + * vice versa. + *--------------------------------------------------------------*/ +static void free_migration(struct dm_cache_migration *mg) +{ + mempool_free(mg, mg->cache->migration_pool); +} + +static void inc_nr_migrations(struct cache *cache) +{ + atomic_inc(&cache->nr_migrations); +} + +static void dec_nr_migrations(struct cache *cache) +{ + atomic_dec(&cache->nr_migrations); + + /* + * Wake the worker in case we're suspending the target. + */ + wake_up(&cache->migration_wait); +} + +static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, + bool holder) +{ + (holder ? dm_cell_release : dm_cell_release_no_holder) + (cache->prison, cell, &cache->deferred_bios); + free_prison_cell(cache, cell); +} + +static void cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell, + bool holder) +{ + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + __cell_defer(cache, cell, holder); + spin_unlock_irqrestore(&cache->lock, flags); + + wake_worker(cache); +} + +static void cleanup_migration(struct dm_cache_migration *mg) +{ + dec_nr_migrations(mg->cache); + free_migration(mg); +} + +static void migration_failure(struct dm_cache_migration *mg) +{ + struct cache *cache = mg->cache; + + if (mg->writeback) { + DMWARN_LIMIT("writeback failed; couldn't copy block"); + set_dirty(cache, mg->old_oblock, mg->cblock); + cell_defer(cache, mg->old_ocell, false); + + } else if (mg->demote) { + DMWARN_LIMIT("demotion failed; couldn't copy block"); + policy_force_mapping(cache->policy, mg->new_oblock, mg->old_oblock); + + cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1); + if (mg->promote) + cell_defer(cache, mg->new_ocell, 1); + } else { + DMWARN_LIMIT("promotion failed; couldn't copy block"); + policy_remove_mapping(cache->policy, mg->new_oblock); + cell_defer(cache, mg->new_ocell, 1); + } + + cleanup_migration(mg); +} + +static void migration_success_pre_commit(struct dm_cache_migration *mg) +{ + unsigned long flags; + struct cache *cache = mg->cache; + + if (mg->writeback) { + cell_defer(cache, mg->old_ocell, false); + clear_dirty(cache, mg->old_oblock, mg->cblock); + cleanup_migration(mg); + return; + + } else if (mg->demote) { + if (dm_cache_remove_mapping(cache->cmd, mg->cblock)) { + DMWARN_LIMIT("demotion failed; couldn't update on disk metadata"); + policy_force_mapping(cache->policy, mg->new_oblock, + mg->old_oblock); + if (mg->promote) + cell_defer(cache, mg->new_ocell, true); + cleanup_migration(mg); + return; + } + } else { + if (dm_cache_insert_mapping(cache->cmd, mg->cblock, mg->new_oblock)) { + DMWARN_LIMIT("promotion failed; couldn't update on disk metadata"); + policy_remove_mapping(cache->policy, mg->new_oblock); + cleanup_migration(mg); + return; + } + } + + spin_lock_irqsave(&cache->lock, flags); + list_add_tail(&mg->list, &cache->need_commit_migrations); + cache->commit_requested = true; + spin_unlock_irqrestore(&cache->lock, flags); +} + +static void migration_success_post_commit(struct dm_cache_migration *mg) +{ + unsigned long flags; + struct cache *cache = mg->cache; + + if (mg->writeback) { + DMWARN("writeback unexpectedly triggered commit"); + return; + + } else if (mg->demote) { + cell_defer(cache, mg->old_ocell, mg->promote ? 0 : 1); + + if (mg->promote) { + mg->demote = false; + + spin_lock_irqsave(&cache->lock, flags); + list_add_tail(&mg->list, &cache->quiesced_migrations); + spin_unlock_irqrestore(&cache->lock, flags); + + } else + cleanup_migration(mg); + + } else { + cell_defer(cache, mg->new_ocell, true); + clear_dirty(cache, mg->new_oblock, mg->cblock); + cleanup_migration(mg); + } +} + +static void copy_complete(int read_err, unsigned long write_err, void *context) +{ + unsigned long flags; + struct dm_cache_migration *mg = (struct dm_cache_migration *) context; + struct cache *cache = mg->cache; + + if (read_err || write_err) + mg->err = true; + + spin_lock_irqsave(&cache->lock, flags); + list_add_tail(&mg->list, &cache->completed_migrations); + spin_unlock_irqrestore(&cache->lock, flags); + + wake_worker(cache); +} + +static void issue_copy_real(struct dm_cache_migration *mg) +{ + int r; + struct dm_io_region o_region, c_region; + struct cache *cache = mg->cache; + + o_region.bdev = cache->origin_dev->bdev; + o_region.count = cache->sectors_per_block; + + c_region.bdev = cache->cache_dev->bdev; + c_region.sector = from_cblock(mg->cblock) * cache->sectors_per_block; + c_region.count = cache->sectors_per_block; + + if (mg->writeback || mg->demote) { + /* demote */ + o_region.sector = from_oblock(mg->old_oblock) * cache->sectors_per_block; + r = dm_kcopyd_copy(cache->copier, &c_region, 1, &o_region, 0, copy_complete, mg); + } else { + /* promote */ + o_region.sector = from_oblock(mg->new_oblock) * cache->sectors_per_block; + r = dm_kcopyd_copy(cache->copier, &o_region, 1, &c_region, 0, copy_complete, mg); + } + + if (r < 0) + migration_failure(mg); +} + +static void avoid_copy(struct dm_cache_migration *mg) +{ + atomic_inc(&mg->cache->stats.copies_avoided); + migration_success_pre_commit(mg); +} + +static void issue_copy(struct dm_cache_migration *mg) +{ + bool avoid; + struct cache *cache = mg->cache; + + if (mg->writeback || mg->demote) + avoid = !is_dirty(cache, mg->cblock) || + is_discarded_oblock(cache, mg->old_oblock); + else + avoid = is_discarded_oblock(cache, mg->new_oblock); + + avoid ? avoid_copy(mg) : issue_copy_real(mg); +} + +static void complete_migration(struct dm_cache_migration *mg) +{ + if (mg->err) + migration_failure(mg); + else + migration_success_pre_commit(mg); +} + +static void process_migrations(struct cache *cache, struct list_head *head, + void (*fn)(struct dm_cache_migration *)) +{ + unsigned long flags; + struct list_head list; + struct dm_cache_migration *mg, *tmp; + + INIT_LIST_HEAD(&list); + spin_lock_irqsave(&cache->lock, flags); + list_splice_init(head, &list); + spin_unlock_irqrestore(&cache->lock, flags); + + list_for_each_entry_safe(mg, tmp, &list, list) + fn(mg); +} + +static void __queue_quiesced_migration(struct dm_cache_migration *mg) +{ + list_add_tail(&mg->list, &mg->cache->quiesced_migrations); +} + +static void queue_quiesced_migration(struct dm_cache_migration *mg) +{ + unsigned long flags; + struct cache *cache = mg->cache; + + spin_lock_irqsave(&cache->lock, flags); + __queue_quiesced_migration(mg); + spin_unlock_irqrestore(&cache->lock, flags); + + wake_worker(cache); +} + +static void queue_quiesced_migrations(struct cache *cache, struct list_head *work) +{ + unsigned long flags; + struct dm_cache_migration *mg, *tmp; + + spin_lock_irqsave(&cache->lock, flags); + list_for_each_entry_safe(mg, tmp, work, list) + __queue_quiesced_migration(mg); + spin_unlock_irqrestore(&cache->lock, flags); + + wake_worker(cache); +} + +static void check_for_quiesced_migrations(struct cache *cache, + struct per_bio_data *pb) +{ + struct list_head work; + + if (!pb->all_io_entry) + return; + + INIT_LIST_HEAD(&work); + if (pb->all_io_entry) + dm_deferred_entry_dec(pb->all_io_entry, &work); + + if (!list_empty(&work)) + queue_quiesced_migrations(cache, &work); +} + +static void quiesce_migration(struct dm_cache_migration *mg) +{ + if (!dm_deferred_set_add_work(mg->cache->all_io_ds, &mg->list)) + queue_quiesced_migration(mg); +} + +static void promote(struct cache *cache, struct prealloc *structs, + dm_oblock_t oblock, dm_cblock_t cblock, + struct dm_bio_prison_cell *cell) +{ + struct dm_cache_migration *mg = prealloc_get_migration(structs); + + mg->err = false; + mg->writeback = false; + mg->demote = false; + mg->promote = true; + mg->cache = cache; + mg->new_oblock = oblock; + mg->cblock = cblock; + mg->old_ocell = NULL; + mg->new_ocell = cell; + mg->start_jiffies = jiffies; + + inc_nr_migrations(cache); + quiesce_migration(mg); +} + +static void writeback(struct cache *cache, struct prealloc *structs, + dm_oblock_t oblock, dm_cblock_t cblock, + struct dm_bio_prison_cell *cell) +{ + struct dm_cache_migration *mg = prealloc_get_migration(structs); + + mg->err = false; + mg->writeback = true; + mg->demote = false; + mg->promote = false; + mg->cache = cache; + mg->old_oblock = oblock; + mg->cblock = cblock; + mg->old_ocell = cell; + mg->new_ocell = NULL; + mg->start_jiffies = jiffies; + + inc_nr_migrations(cache); + quiesce_migration(mg); +} + +static void demote_then_promote(struct cache *cache, struct prealloc *structs, + dm_oblock_t old_oblock, dm_oblock_t new_oblock, + dm_cblock_t cblock, + struct dm_bio_prison_cell *old_ocell, + struct dm_bio_prison_cell *new_ocell) +{ + struct dm_cache_migration *mg = prealloc_get_migration(structs); + + mg->err = false; + mg->writeback = false; + mg->demote = true; + mg->promote = true; + mg->cache = cache; + mg->old_oblock = old_oblock; + mg->new_oblock = new_oblock; + mg->cblock = cblock; + mg->old_ocell = old_ocell; + mg->new_ocell = new_ocell; + mg->start_jiffies = jiffies; + + inc_nr_migrations(cache); + quiesce_migration(mg); +} + +/*---------------------------------------------------------------- + * bio processing + *--------------------------------------------------------------*/ +static void defer_bio(struct cache *cache, struct bio *bio) +{ + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + bio_list_add(&cache->deferred_bios, bio); + spin_unlock_irqrestore(&cache->lock, flags); + + wake_worker(cache); +} + +static void process_flush_bio(struct cache *cache, struct bio *bio) +{ + struct per_bio_data *pb = get_per_bio_data(bio); + + BUG_ON(bio->bi_size); + if (!pb->req_nr) + remap_to_origin(cache, bio); + else + remap_to_cache(cache, bio, 0); + + issue(cache, bio); +} + +/* + * People generally discard large parts of a device, eg, the whole device + * when formatting. Splitting these large discards up into cache block + * sized ios and then quiescing (always neccessary for discard) takes too + * long. + * + * We keep it simple, and allow any size of discard to come in, and just + * mark off blocks on the discard bitset. No passdown occurs! + * + * To implement passdown we need to change the bio_prison such that a cell + * can have a key that spans many blocks. + */ +static void process_discard_bio(struct cache *cache, struct bio *bio) +{ + dm_block_t start_block = dm_sector_div_up(bio->bi_sector, + cache->discard_block_size); + dm_block_t end_block = bio->bi_sector + bio_sectors(bio); + dm_block_t b; + + (void) sector_div(end_block, cache->discard_block_size); + + for (b = start_block; b < end_block; b++) + set_discard(cache, to_dblock(b)); + + bio_endio(bio, 0); +} + +static bool spare_migration_bandwidth(struct cache *cache) +{ + sector_t current_volume = (atomic_read(&cache->nr_migrations) + 1) * + cache->sectors_per_block; + return current_volume < cache->migration_threshold; +} + +static bool is_writethrough_io(struct cache *cache, struct bio *bio, + dm_cblock_t cblock) +{ + return bio_data_dir(bio) == WRITE && + cache->features.write_through && !is_dirty(cache, cblock); +} + +static void inc_hit_counter(struct cache *cache, struct bio *bio) +{ + atomic_inc(bio_data_dir(bio) == READ ? + &cache->stats.read_hit : &cache->stats.write_hit); +} + +static void inc_miss_counter(struct cache *cache, struct bio *bio) +{ + atomic_inc(bio_data_dir(bio) == READ ? + &cache->stats.read_miss : &cache->stats.write_miss); +} + +static void process_bio(struct cache *cache, struct prealloc *structs, + struct bio *bio) +{ + int r; + bool release_cell = true; + dm_oblock_t block = get_bio_block(cache, bio); + struct dm_bio_prison_cell *cell_prealloc, *old_ocell, *new_ocell; + struct policy_result lookup_result; + struct per_bio_data *pb = get_per_bio_data(bio); + bool discarded_block = is_discarded_oblock(cache, block); + bool can_migrate = discarded_block || spare_migration_bandwidth(cache); + + /* + * Check to see if that block is currently migrating. + */ + cell_prealloc = prealloc_get_cell(structs); + r = bio_detain(cache, block, bio, cell_prealloc, + (cell_free_fn) prealloc_put_cell, + structs, &new_ocell); + if (r > 0) + return; + + r = policy_map(cache->policy, block, true, can_migrate, discarded_block, + bio, &lookup_result); + + if (r == -EWOULDBLOCK) + /* migration has been denied */ + lookup_result.op = POLICY_MISS; + + switch (lookup_result.op) { + case POLICY_HIT: + inc_hit_counter(cache, bio); + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + + if (is_writethrough_io(cache, bio, lookup_result.cblock)) { + /* + * No need to mark anything dirty in write through mode. + */ + pb->req_nr == 0 ? + remap_to_cache(cache, bio, lookup_result.cblock) : + remap_to_origin_clear_discard(cache, bio, block); + } else + remap_to_cache_dirty(cache, bio, block, lookup_result.cblock); + + issue(cache, bio); + break; + + case POLICY_MISS: + inc_miss_counter(cache, bio); + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + + if (pb->req_nr != 0) { + /* + * This is a duplicate writethrough io that is no + * longer needed because the block has been demoted. + */ + bio_endio(bio, 0); + } else { + remap_to_origin_clear_discard(cache, bio, block); + issue(cache, bio); + } + break; + + case POLICY_NEW: + atomic_inc(&cache->stats.promotion); + promote(cache, structs, block, lookup_result.cblock, new_ocell); + release_cell = false; + break; + + case POLICY_REPLACE: + cell_prealloc = prealloc_get_cell(structs); + r = bio_detain(cache, lookup_result.old_oblock, bio, cell_prealloc, + (cell_free_fn) prealloc_put_cell, + structs, &old_ocell); + if (r > 0) { + /* + * We have to be careful to avoid lock inversion of + * the cells. So we back off, and wait for the + * old_ocell to become free. + */ + policy_force_mapping(cache->policy, block, + lookup_result.old_oblock); + atomic_inc(&cache->stats.cache_cell_clash); + break; + } + atomic_inc(&cache->stats.demotion); + atomic_inc(&cache->stats.promotion); + + demote_then_promote(cache, structs, lookup_result.old_oblock, + block, lookup_result.cblock, + old_ocell, new_ocell); + release_cell = false; + break; + + default: + DMERR_LIMIT("%s: erroring bio, unknown policy op: %u", __func__, + (unsigned) lookup_result.op); + bio_io_error(bio); + } + + if (release_cell) + cell_defer(cache, new_ocell, false); +} + +static int need_commit_due_to_time(struct cache *cache) +{ + return jiffies < cache->last_commit_jiffies || + jiffies > cache->last_commit_jiffies + COMMIT_PERIOD; +} + +static int commit_if_needed(struct cache *cache) +{ + if (dm_cache_changed_this_transaction(cache->cmd) && + (cache->commit_requested || need_commit_due_to_time(cache))) { + atomic_inc(&cache->stats.commit_count); + cache->last_commit_jiffies = jiffies; + cache->commit_requested = false; + return dm_cache_commit(cache->cmd, false); + } + + return 0; +} + +static void process_deferred_bios(struct cache *cache) +{ + unsigned long flags; + struct bio_list bios; + struct bio *bio; + struct prealloc structs; + + memset(&structs, 0, sizeof(structs)); + bio_list_init(&bios); + + spin_lock_irqsave(&cache->lock, flags); + bio_list_merge(&bios, &cache->deferred_bios); + bio_list_init(&cache->deferred_bios); + spin_unlock_irqrestore(&cache->lock, flags); + + while (!bio_list_empty(&bios)) { + /* + * If we've got no free migration structs, and processing + * this bio might require one, we pause until there are some + * prepared mappings to process. + */ + if (prealloc_data_structs(cache, &structs)) { + spin_lock_irqsave(&cache->lock, flags); + bio_list_merge(&cache->deferred_bios, &bios); + spin_unlock_irqrestore(&cache->lock, flags); + break; + } + + bio = bio_list_pop(&bios); + + if (bio->bi_rw & REQ_FLUSH) + process_flush_bio(cache, bio); + else if (bio->bi_rw & REQ_DISCARD) + process_discard_bio(cache, bio); + else + process_bio(cache, &structs, bio); + } + + prealloc_free_structs(cache, &structs); +} + +static void process_deferred_flush_bios(struct cache *cache, bool submit_bios) +{ + unsigned long flags; + struct bio_list bios; + struct bio *bio; + + bio_list_init(&bios); + + spin_lock_irqsave(&cache->lock, flags); + bio_list_merge(&bios, &cache->deferred_flush_bios); + bio_list_init(&cache->deferred_flush_bios); + spin_unlock_irqrestore(&cache->lock, flags); + + while ((bio = bio_list_pop(&bios))) + submit_bios ? generic_make_request(bio) : bio_io_error(bio); +} + +static void writeback_some_dirty_blocks(struct cache *cache) +{ + int r = 0; + dm_oblock_t oblock; + dm_cblock_t cblock; + struct prealloc structs; + struct dm_bio_prison_cell *old_ocell; + + memset(&structs, 0, sizeof(structs)); + + while (spare_migration_bandwidth(cache)) { + if (prealloc_data_structs(cache, &structs)) + break; + + r = policy_writeback_work(cache->policy, &oblock, &cblock); + if (r) + break; + + r = get_cell(cache, oblock, &structs, &old_ocell); + if (r) { + policy_set_dirty(cache->policy, oblock); + break; + } + + writeback(cache, &structs, oblock, cblock, old_ocell); + } + + prealloc_free_structs(cache, &structs); +} + +/*---------------------------------------------------------------- + * Main worker loop + *--------------------------------------------------------------*/ +static void start_quiescing(struct cache *cache) +{ + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + cache->quiescing = 1; + spin_unlock_irqrestore(&cache->lock, flags); +} + +static void stop_quiescing(struct cache *cache) +{ + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + cache->quiescing = 0; + spin_unlock_irqrestore(&cache->lock, flags); +} + +static bool is_quiescing(struct cache *cache) +{ + int r; + unsigned long flags; + + spin_lock_irqsave(&cache->lock, flags); + r = cache->quiescing; + spin_unlock_irqrestore(&cache->lock, flags); + + return r; +} + +static void wait_for_migrations(struct cache *cache) +{ + wait_event(cache->migration_wait, !atomic_read(&cache->nr_migrations)); +} + +static void stop_worker(struct cache *cache) +{ + cancel_delayed_work(&cache->waker); + flush_workqueue(cache->wq); +} + +static void requeue_deferred_io(struct cache *cache) +{ + struct bio *bio; + struct bio_list bios; + + bio_list_init(&bios); + bio_list_merge(&bios, &cache->deferred_bios); + bio_list_init(&cache->deferred_bios); + + while ((bio = bio_list_pop(&bios))) + bio_endio(bio, DM_ENDIO_REQUEUE); +} + +static int more_work(struct cache *cache) +{ + if (is_quiescing(cache)) + return !list_empty(&cache->quiesced_migrations) || + !list_empty(&cache->completed_migrations) || + !list_empty(&cache->need_commit_migrations); + else + return !bio_list_empty(&cache->deferred_bios) || + !bio_list_empty(&cache->deferred_flush_bios) || + !list_empty(&cache->quiesced_migrations) || + !list_empty(&cache->completed_migrations) || + !list_empty(&cache->need_commit_migrations); +} + +static void do_worker(struct work_struct *ws) +{ + struct cache *cache = container_of(ws, struct cache, worker); + + do { + if (!is_quiescing(cache)) + process_deferred_bios(cache); + + process_migrations(cache, &cache->quiesced_migrations, issue_copy); + process_migrations(cache, &cache->completed_migrations, complete_migration); + + writeback_some_dirty_blocks(cache); + + if (commit_if_needed(cache)) { + process_deferred_flush_bios(cache, false); + + /* + * FIXME: rollback metadata or just go into a + * failure mode and error everything + */ + } else { + process_deferred_flush_bios(cache, true); + process_migrations(cache, &cache->need_commit_migrations, + migration_success_post_commit); + } + } while (more_work(cache)); +} + +/* + * We want to commit periodically so that not too much + * unwritten metadata builds up. + */ +static void do_waker(struct work_struct *ws) +{ + struct cache *cache = container_of(to_delayed_work(ws), struct cache, waker); + wake_worker(cache); + queue_delayed_work(cache->wq, &cache->waker, COMMIT_PERIOD); +} + +/*----------------------------------------------------------------*/ + +static int is_congested(struct dm_dev *dev, int bdi_bits) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + return bdi_congested(&q->backing_dev_info, bdi_bits); +} + +static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits) +{ + struct cache *cache = container_of(cb, struct cache, callbacks); + + return is_congested(cache->origin_dev, bdi_bits) || + is_congested(cache->cache_dev, bdi_bits); +} + +/*---------------------------------------------------------------- + * Target methods + *--------------------------------------------------------------*/ + +/* + * This function gets called on the error paths of the constructor, so we + * have to cope with a partially initialised struct. + */ +static void destroy(struct cache *cache) +{ + unsigned i; + + if (cache->next_migration) + mempool_free(cache->next_migration, cache->migration_pool); + + if (cache->migration_pool) + mempool_destroy(cache->migration_pool); + + if (cache->all_io_ds) + dm_deferred_set_destroy(cache->all_io_ds); + + if (cache->prison) + dm_bio_prison_destroy(cache->prison); + + if (cache->wq) + destroy_workqueue(cache->wq); + + if (cache->dirty_bitset) + free_bitset(cache->dirty_bitset); + + if (cache->discard_bitset) + free_bitset(cache->discard_bitset); + + if (cache->copier) + dm_kcopyd_client_destroy(cache->copier); + + if (cache->cmd) + dm_cache_metadata_close(cache->cmd); + + if (cache->metadata_dev) + dm_put_device(cache->ti, cache->metadata_dev); + + if (cache->origin_dev) + dm_put_device(cache->ti, cache->origin_dev); + + if (cache->cache_dev) + dm_put_device(cache->ti, cache->cache_dev); + + if (cache->policy) + dm_cache_policy_destroy(cache->policy); + + for (i = 0; i < cache->nr_ctr_args ; i++) + kfree(cache->ctr_args[i]); + kfree(cache->ctr_args); + + kfree(cache); +} + +static void cache_dtr(struct dm_target *ti) +{ + struct cache *cache = ti->private; + + destroy(cache); +} + +static sector_t get_dev_size(struct dm_dev *dev) +{ + return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; +} + +/*----------------------------------------------------------------*/ + +/* + * Construct a cache device mapping. + * + * cache <metadata dev> <cache dev> <origin dev> <block size> + * <#feature args> [<feature arg>]* + * <policy> <#policy args> [<policy arg>]* + * + * metadata dev : fast device holding the persistent metadata + * cache dev : fast device holding cached data blocks + * origin dev : slow device holding original data blocks + * block size : cache unit size in sectors + * + * #feature args : number of feature arguments passed + * feature args : writethrough. (The default is writeback.) + * + * policy : the replacement policy to use + * #policy args : an even number of policy arguments corresponding + * to key/value pairs passed to the policy + * policy args : key/value pairs passed to the policy + * E.g. 'sequential_threshold 1024' + * See cache-policies.txt for details. + * + * Optional feature arguments are: + * writethrough : write through caching that prohibits cache block + * content from being different from origin block content. + * Without this argument, the default behaviour is to write + * back cache block contents later for performance reasons, + * so they may differ from the corresponding origin blocks. + */ +struct cache_args { + struct dm_target *ti; + + struct dm_dev *metadata_dev; + + struct dm_dev *cache_dev; + sector_t cache_sectors; + + struct dm_dev *origin_dev; + sector_t origin_sectors; + + uint32_t block_size; + + const char *policy_name; + int policy_argc; + const char **policy_argv; + + struct cache_features features; +}; + +static void destroy_cache_args(struct cache_args *ca) +{ + if (ca->metadata_dev) + dm_put_device(ca->ti, ca->metadata_dev); + + if (ca->cache_dev) + dm_put_device(ca->ti, ca->cache_dev); + + if (ca->origin_dev) + dm_put_device(ca->ti, ca->origin_dev); + + kfree(ca); +} + +static bool at_least_one_arg(struct dm_arg_set *as, char **error) +{ + if (!as->argc) { + *error = "Insufficient args"; + return false; + } + + return true; +} + +static int parse_metadata_dev(struct cache_args *ca, struct dm_arg_set *as, + char **error) +{ + int r; + sector_t metadata_dev_size; + char b[BDEVNAME_SIZE]; + + if (!at_least_one_arg(as, error)) + return -EINVAL; + + r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, + &ca->metadata_dev); + if (r) { + *error = "Error opening metadata device"; + return r; + } + + metadata_dev_size = get_dev_size(ca->metadata_dev); + if (metadata_dev_size > DM_CACHE_METADATA_MAX_SECTORS_WARNING) + DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.", + bdevname(ca->metadata_dev->bdev, b), THIN_METADATA_MAX_SECTORS); + + return 0; +} + +static int parse_cache_dev(struct cache_args *ca, struct dm_arg_set *as, + char **error) +{ + int r; + + if (!at_least_one_arg(as, error)) + return -EINVAL; + + r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, + &ca->cache_dev); + if (r) { + *error = "Error opening cache device"; + return r; + } + ca->cache_sectors = get_dev_size(ca->cache_dev); + + return 0; +} + +static int parse_origin_dev(struct cache_args *ca, struct dm_arg_set *as, + char **error) +{ + int r; + + if (!at_least_one_arg(as, error)) + return -EINVAL; + + r = dm_get_device(ca->ti, dm_shift_arg(as), FMODE_READ | FMODE_WRITE, + &ca->origin_dev); + if (r) { + *error = "Error opening origin device"; + return r; + } + + ca->origin_sectors = get_dev_size(ca->origin_dev); + if (ca->ti->len > ca->origin_sectors) { + *error = "Device size larger than cached device"; + return -EINVAL; + } + + return 0; +} + +static int parse_block_size(struct cache_args *ca, struct dm_arg_set *as, + char **error) +{ + unsigned long tmp; + + if (!at_least_one_arg(as, error)) + return -EINVAL; + + if (kstrtoul(dm_shift_arg(as), 10, &tmp) || !tmp || + tmp < DATA_DEV_BLOCK_SIZE_MIN_SECTORS || + tmp & (DATA_DEV_BLOCK_SIZE_MIN_SECTORS - 1)) { + *error = "Invalid data block size"; + return -EINVAL; + } + + if (tmp > ca->cache_sectors) { + *error = "Data block size is larger than the cache device"; + return -EINVAL; + } + + ca->block_size = tmp; + + return 0; +} + +static void init_features(struct cache_features *cf) +{ + cf->mode = CM_WRITE; + cf->write_through = false; +} + +static int parse_features(struct cache_args *ca, struct dm_arg_set *as, + char **error) +{ + static struct dm_arg _args[] = { + {0, 1, "Invalid number of cache feature arguments"}, + }; + + int r; + unsigned argc; + const char *arg; + struct cache_features *cf = &ca->features; + + init_features(cf); + + r = dm_read_arg_group(_args, as, &argc, error); + if (r) + return -EINVAL; + + while (argc--) { + arg = dm_shift_arg(as); + + if (!strcasecmp(arg, "writeback")) + cf->write_through = false; + + else if (!strcasecmp(arg, "writethrough")) + cf->write_through = true; + + else { + *error = "Unrecognised cache feature requested"; + return -EINVAL; + } + } + + return 0; +} + +static int parse_policy(struct cache_args *ca, struct dm_arg_set *as, + char **error) +{ + static struct dm_arg _args[] = { + {0, 1024, "Invalid number of policy arguments"}, + }; + + int r; + + if (!at_least_one_arg(as, error)) + return -EINVAL; + + ca->policy_name = dm_shift_arg(as); + + r = dm_read_arg_group(_args, as, &ca->policy_argc, error); + if (r) + return -EINVAL; + + ca->policy_argv = (const char **)as->argv; + dm_consume_args(as, ca->policy_argc); + + return 0; +} + +static int parse_cache_args(struct cache_args *ca, int argc, char **argv, + char **error) +{ + int r; + struct dm_arg_set as; + + as.argc = argc; + as.argv = argv; + + r = parse_metadata_dev(ca, &as, error); + if (r) + return r; + + r = parse_cache_dev(ca, &as, error); + if (r) + return r; + + r = parse_origin_dev(ca, &as, error); + if (r) + return r; + + r = parse_block_size(ca, &as, error); + if (r) + return r; + + r = parse_features(ca, &as, error); + if (r) + return r; + + r = parse_policy(ca, &as, error); + if (r) + return r; + + return 0; +} + +/*----------------------------------------------------------------*/ + +static struct kmem_cache *migration_cache; + +static int set_config_values(struct dm_cache_policy *p, int argc, const char **argv) +{ + int r = 0; + + if (argc & 1) { + DMWARN("Odd number of policy arguments given but they should be <key> <value> pairs."); + return -EINVAL; + } + + while (argc) { + r = policy_set_config_value(p, argv[0], argv[1]); + if (r) { + DMWARN("policy_set_config_value failed: key = '%s', value = '%s'", + argv[0], argv[1]); + return r; + } + + argc -= 2; + argv += 2; + } + + return r; +} + +static int create_cache_policy(struct cache *cache, struct cache_args *ca, + char **error) +{ + int r; + + cache->policy = dm_cache_policy_create(ca->policy_name, + cache->cache_size, + cache->origin_sectors, + cache->sectors_per_block); + if (!cache->policy) { + *error = "Error creating cache's policy"; + return -ENOMEM; + } + + r = set_config_values(cache->policy, ca->policy_argc, ca->policy_argv); + if (r) + dm_cache_policy_destroy(cache->policy); + + return r; +} + +/* + * We want the discard block size to be a power of two, at least the size + * of the cache block size, and have no more than 2^14 discard blocks + * across the origin. + */ +#define MAX_DISCARD_BLOCKS (1 << 14) + +static bool too_many_discard_blocks(sector_t discard_block_size, + sector_t origin_size) +{ + (void) sector_div(origin_size, discard_block_size); + + return origin_size > MAX_DISCARD_BLOCKS; +} + +static sector_t calculate_discard_block_size(sector_t cache_block_size, + sector_t origin_size) +{ + sector_t discard_block_size; + + discard_block_size = roundup_pow_of_two(cache_block_size); + + if (origin_size) + while (too_many_discard_blocks(discard_block_size, origin_size)) + discard_block_size *= 2; + + return discard_block_size; +} + +#define DEFAULT_MIGRATION_THRESHOLD (2048 * 100) + +static unsigned cache_num_write_bios(struct dm_target *ti, struct bio *bio); + +static int cache_create(struct cache_args *ca, struct cache **result) +{ + int r = 0; + char **error = &ca->ti->error; + struct cache *cache; + struct dm_target *ti = ca->ti; + dm_block_t origin_blocks; + struct dm_cache_metadata *cmd; + bool may_format = ca->features.mode == CM_WRITE; + + cache = kzalloc(sizeof(*cache), GFP_KERNEL); + if (!cache) + return -ENOMEM; + + cache->ti = ca->ti; + ti->private = cache; + ti->per_bio_data_size = sizeof(struct per_bio_data); + ti->num_flush_bios = 2; + ti->flush_supported = true; + + ti->num_discard_bios = 1; + ti->discards_supported = true; + ti->discard_zeroes_data_unsupported = true; + + memcpy(&cache->features, &ca->features, sizeof(cache->features)); + + if (cache->features.write_through) + ti->num_write_bios = cache_num_write_bios; + + cache->callbacks.congested_fn = cache_is_congested; + dm_table_add_target_callbacks(ti->table, &cache->callbacks); + + cache->metadata_dev = ca->metadata_dev; + cache->origin_dev = ca->origin_dev; + cache->cache_dev = ca->cache_dev; + + ca->metadata_dev = ca->origin_dev = ca->cache_dev = NULL; + + /* FIXME: factor out this whole section */ + origin_blocks = cache->origin_sectors = ca->origin_sectors; + (void) sector_div(origin_blocks, ca->block_size); + cache->origin_blocks = to_oblock(origin_blocks); + + cache->sectors_per_block = ca->block_size; + if (dm_set_target_max_io_len(ti, cache->sectors_per_block)) { + r = -EINVAL; + goto bad; + } + + if (ca->block_size & (ca->block_size - 1)) { + dm_block_t cache_size = ca->cache_sectors; + + cache->sectors_per_block_shift = -1; + (void) sector_div(cache_size, ca->block_size); + cache->cache_size = to_cblock(cache_size); + } else { + cache->sectors_per_block_shift = __ffs(ca->block_size); + cache->cache_size = to_cblock(ca->cache_sectors >> cache->sectors_per_block_shift); + } + + r = create_cache_policy(cache, ca, error); + if (r) + goto bad; + cache->policy_nr_args = ca->policy_argc; + + cmd = dm_cache_metadata_open(cache->metadata_dev->bdev, + ca->block_size, may_format, + dm_cache_policy_get_hint_size(cache->policy)); + if (IS_ERR(cmd)) { + *error = "Error creating metadata object"; + r = PTR_ERR(cmd); + goto bad; + } + cache->cmd = cmd; + + spin_lock_init(&cache->lock); + bio_list_init(&cache->deferred_bios); + bio_list_init(&cache->deferred_flush_bios); + INIT_LIST_HEAD(&cache->quiesced_migrations); + INIT_LIST_HEAD(&cache->completed_migrations); + INIT_LIST_HEAD(&cache->need_commit_migrations); + cache->migration_threshold = DEFAULT_MIGRATION_THRESHOLD; + atomic_set(&cache->nr_migrations, 0); + init_waitqueue_head(&cache->migration_wait); + + cache->nr_dirty = 0; + cache->dirty_bitset = alloc_bitset(from_cblock(cache->cache_size)); + if (!cache->dirty_bitset) { + *error = "could not allocate dirty bitset"; + goto bad; + } + clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size)); + + cache->discard_block_size = + calculate_discard_block_size(cache->sectors_per_block, + cache->origin_sectors); + cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks); + cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks)); + if (!cache->discard_bitset) { + *error = "could not allocate discard bitset"; + goto bad; + } + clear_bitset(cache->discard_bitset, from_dblock(cache->discard_nr_blocks)); + + cache->copier = dm_kcopyd_client_create(&dm_kcopyd_throttle); + if (IS_ERR(cache->copier)) { + *error = "could not create kcopyd client"; + r = PTR_ERR(cache->copier); + goto bad; + } + + cache->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM); + if (!cache->wq) { + *error = "could not create workqueue for metadata object"; + goto bad; + } + INIT_WORK(&cache->worker, do_worker); + INIT_DELAYED_WORK(&cache->waker, do_waker); + cache->last_commit_jiffies = jiffies; + + cache->prison = dm_bio_prison_create(PRISON_CELLS); + if (!cache->prison) { + *error = "could not create bio prison"; + goto bad; + } + + cache->all_io_ds = dm_deferred_set_create(); + if (!cache->all_io_ds) { + *error = "could not create all_io deferred set"; + goto bad; + } + + cache->migration_pool = mempool_create_slab_pool(MIGRATION_POOL_SIZE, + migration_cache); + if (!cache->migration_pool) { + *error = "Error creating cache's migration mempool"; + goto bad; + } + + cache->next_migration = NULL; + + cache->need_tick_bio = true; + cache->sized = false; + cache->quiescing = false; + cache->commit_requested = false; + cache->loaded_mappings = false; + cache->loaded_discards = false; + + load_stats(cache); + + atomic_set(&cache->stats.demotion, 0); + atomic_set(&cache->stats.promotion, 0); + atomic_set(&cache->stats.copies_avoided, 0); + atomic_set(&cache->stats.cache_cell_clash, 0); + atomic_set(&cache->stats.commit_count, 0); + atomic_set(&cache->stats.discard_count, 0); + + *result = cache; + return 0; + +bad: + destroy(cache); + return r; +} + +static int copy_ctr_args(struct cache *cache, int argc, const char **argv) +{ + unsigned i; + const char **copy; + + copy = kcalloc(argc, sizeof(*copy), GFP_KERNEL); + if (!copy) + return -ENOMEM; + for (i = 0; i < argc; i++) { + copy[i] = kstrdup(argv[i], GFP_KERNEL); + if (!copy[i]) { + while (i--) + kfree(copy[i]); + kfree(copy); + return -ENOMEM; + } + } + + cache->nr_ctr_args = argc; + cache->ctr_args = copy; + + return 0; +} + +static int cache_ctr(struct dm_target *ti, unsigned argc, char **argv) +{ + int r = -EINVAL; + struct cache_args *ca; + struct cache *cache = NULL; + + ca = kzalloc(sizeof(*ca), GFP_KERNEL); + if (!ca) { + ti->error = "Error allocating memory for cache"; + return -ENOMEM; + } + ca->ti = ti; + + r = parse_cache_args(ca, argc, argv, &ti->error); + if (r) + goto out; + + r = cache_create(ca, &cache); + + r = copy_ctr_args(cache, argc - 3, (const char **)argv + 3); + if (r) { + destroy(cache); + goto out; + } + + ti->private = cache; + +out: + destroy_cache_args(ca); + return r; +} + +static unsigned cache_num_write_bios(struct dm_target *ti, struct bio *bio) +{ + int r; + struct cache *cache = ti->private; + dm_oblock_t block = get_bio_block(cache, bio); + dm_cblock_t cblock; + + r = policy_lookup(cache->policy, block, &cblock); + if (r < 0) + return 2; /* assume the worst */ + + return (!r && !is_dirty(cache, cblock)) ? 2 : 1; +} + +static int cache_map(struct dm_target *ti, struct bio *bio) +{ + struct cache *cache = ti->private; + + int r; + dm_oblock_t block = get_bio_block(cache, bio); + bool can_migrate = false; + bool discarded_block; + struct dm_bio_prison_cell *cell; + struct policy_result lookup_result; + struct per_bio_data *pb; + + if (from_oblock(block) > from_oblock(cache->origin_blocks)) { + /* + * This can only occur if the io goes to a partial block at + * the end of the origin device. We don't cache these. + * Just remap to the origin and carry on. + */ + remap_to_origin_clear_discard(cache, bio, block); + return DM_MAPIO_REMAPPED; + } + + pb = init_per_bio_data(bio); + + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA | REQ_DISCARD)) { + defer_bio(cache, bio); + return DM_MAPIO_SUBMITTED; + } + + /* + * Check to see if that block is currently migrating. + */ + cell = alloc_prison_cell(cache); + if (!cell) { + defer_bio(cache, bio); + return DM_MAPIO_SUBMITTED; + } + + r = bio_detain(cache, block, bio, cell, + (cell_free_fn) free_prison_cell, + cache, &cell); + if (r) { + if (r < 0) + defer_bio(cache, bio); + + return DM_MAPIO_SUBMITTED; + } + + discarded_block = is_discarded_oblock(cache, block); + + r = policy_map(cache->policy, block, false, can_migrate, discarded_block, + bio, &lookup_result); + if (r == -EWOULDBLOCK) { + cell_defer(cache, cell, true); + return DM_MAPIO_SUBMITTED; + + } else if (r) { + DMERR_LIMIT("Unexpected return from cache replacement policy: %d", r); + bio_io_error(bio); + return DM_MAPIO_SUBMITTED; + } + + switch (lookup_result.op) { + case POLICY_HIT: + inc_hit_counter(cache, bio); + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + + if (is_writethrough_io(cache, bio, lookup_result.cblock)) { + /* + * No need to mark anything dirty in write through mode. + */ + pb->req_nr == 0 ? + remap_to_cache(cache, bio, lookup_result.cblock) : + remap_to_origin_clear_discard(cache, bio, block); + cell_defer(cache, cell, false); + } else { + remap_to_cache_dirty(cache, bio, block, lookup_result.cblock); + cell_defer(cache, cell, false); + } + break; + + case POLICY_MISS: + inc_miss_counter(cache, bio); + pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds); + + if (pb->req_nr != 0) { + /* + * This is a duplicate writethrough io that is no + * longer needed because the block has been demoted. + */ + bio_endio(bio, 0); + cell_defer(cache, cell, false); + return DM_MAPIO_SUBMITTED; + } else { + remap_to_origin_clear_discard(cache, bio, block); + cell_defer(cache, cell, false); + } + break; + + default: + DMERR_LIMIT("%s: erroring bio: unknown policy op: %u", __func__, + (unsigned) lookup_result.op); + bio_io_error(bio); + return DM_MAPIO_SUBMITTED; + } + + return DM_MAPIO_REMAPPED; +} + +static int cache_end_io(struct dm_target *ti, struct bio *bio, int error) +{ + struct cache *cache = ti->private; + unsigned long flags; + struct per_bio_data *pb = get_per_bio_data(bio); + + if (pb->tick) { + policy_tick(cache->policy); + + spin_lock_irqsave(&cache->lock, flags); + cache->need_tick_bio = true; + spin_unlock_irqrestore(&cache->lock, flags); + } + + check_for_quiesced_migrations(cache, pb); + + return 0; +} + +static int write_dirty_bitset(struct cache *cache) +{ + unsigned i, r; + + for (i = 0; i < from_cblock(cache->cache_size); i++) { + r = dm_cache_set_dirty(cache->cmd, to_cblock(i), + is_dirty(cache, to_cblock(i))); + if (r) + return r; + } + + return 0; +} + +static int write_discard_bitset(struct cache *cache) +{ + unsigned i, r; + + r = dm_cache_discard_bitset_resize(cache->cmd, cache->discard_block_size, + cache->discard_nr_blocks); + if (r) { + DMERR("could not resize on-disk discard bitset"); + return r; + } + + for (i = 0; i < from_dblock(cache->discard_nr_blocks); i++) { + r = dm_cache_set_discard(cache->cmd, to_dblock(i), + is_discarded(cache, to_dblock(i))); + if (r) + return r; + } + + return 0; +} + +static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock, + uint32_t hint) +{ + struct cache *cache = context; + return dm_cache_save_hint(cache->cmd, cblock, hint); +} + +static int write_hints(struct cache *cache) +{ + int r; + + r = dm_cache_begin_hints(cache->cmd, cache->policy); + if (r) { + DMERR("dm_cache_begin_hints failed"); + return r; + } + + r = policy_walk_mappings(cache->policy, save_hint, cache); + if (r) + DMERR("policy_walk_mappings failed"); + + return r; +} + +/* + * returns true on success + */ +static bool sync_metadata(struct cache *cache) +{ + int r1, r2, r3, r4; + + r1 = write_dirty_bitset(cache); + if (r1) + DMERR("could not write dirty bitset"); + + r2 = write_discard_bitset(cache); + if (r2) + DMERR("could not write discard bitset"); + + save_stats(cache); + + r3 = write_hints(cache); + if (r3) + DMERR("could not write hints"); + + /* + * If writing the above metadata failed, we still commit, but don't + * set the clean shutdown flag. This will effectively force every + * dirty bit to be set on reload. + */ + r4 = dm_cache_commit(cache->cmd, !r1 && !r2 && !r3); + if (r4) + DMERR("could not write cache metadata. Data loss may occur."); + + return !r1 && !r2 && !r3 && !r4; +} + +static void cache_postsuspend(struct dm_target *ti) +{ + struct cache *cache = ti->private; + + start_quiescing(cache); + wait_for_migrations(cache); + stop_worker(cache); + requeue_deferred_io(cache); + stop_quiescing(cache); + + (void) sync_metadata(cache); +} + +static int load_mapping(void *context, dm_oblock_t oblock, dm_cblock_t cblock, + bool dirty, uint32_t hint, bool hint_valid) +{ + int r; + struct cache *cache = context; + + r = policy_load_mapping(cache->policy, oblock, cblock, hint, hint_valid); + if (r) + return r; + + if (dirty) + set_dirty(cache, oblock, cblock); + else + clear_dirty(cache, oblock, cblock); + + return 0; +} + +static int load_discard(void *context, sector_t discard_block_size, + dm_dblock_t dblock, bool discard) +{ + struct cache *cache = context; + + /* FIXME: handle mis-matched block size */ + + if (discard) + set_discard(cache, dblock); + else + clear_discard(cache, dblock); + + return 0; +} + +static int cache_preresume(struct dm_target *ti) +{ + int r = 0; + struct cache *cache = ti->private; + sector_t actual_cache_size = get_dev_size(cache->cache_dev); + (void) sector_div(actual_cache_size, cache->sectors_per_block); + + /* + * Check to see if the cache has resized. + */ + if (from_cblock(cache->cache_size) != actual_cache_size || !cache->sized) { + cache->cache_size = to_cblock(actual_cache_size); + + r = dm_cache_resize(cache->cmd, cache->cache_size); + if (r) { + DMERR("could not resize cache metadata"); + return r; + } + + cache->sized = true; + } + + if (!cache->loaded_mappings) { + r = dm_cache_load_mappings(cache->cmd, + dm_cache_policy_get_name(cache->policy), + load_mapping, cache); + if (r) { + DMERR("could not load cache mappings"); + return r; + } + + cache->loaded_mappings = true; + } + + if (!cache->loaded_discards) { + r = dm_cache_load_discards(cache->cmd, load_discard, cache); + if (r) { + DMERR("could not load origin discards"); + return r; + } + + cache->loaded_discards = true; + } + + return r; +} + +static void cache_resume(struct dm_target *ti) +{ + struct cache *cache = ti->private; + + cache->need_tick_bio = true; + do_waker(&cache->waker.work); +} + +/* + * Status format: + * + * <#used metadata blocks>/<#total metadata blocks> + * <#read hits> <#read misses> <#write hits> <#write misses> + * <#demotions> <#promotions> <#blocks in cache> <#dirty> + * <#features> <features>* + * <#core args> <core args> + * <#policy args> <policy args>* + */ +static void cache_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) +{ + int r = 0; + unsigned i; + ssize_t sz = 0; + dm_block_t nr_free_blocks_metadata = 0; + dm_block_t nr_blocks_metadata = 0; + char buf[BDEVNAME_SIZE]; + struct cache *cache = ti->private; + dm_cblock_t residency; + + switch (type) { + case STATUSTYPE_INFO: + /* Commit to ensure statistics aren't out-of-date */ + if (!(status_flags & DM_STATUS_NOFLUSH_FLAG) && !dm_suspended(ti)) { + r = dm_cache_commit(cache->cmd, false); + if (r) + DMERR("could not commit metadata for accurate status"); + } + + r = dm_cache_get_free_metadata_block_count(cache->cmd, + &nr_free_blocks_metadata); + if (r) { + DMERR("could not get metadata free block count"); + goto err; + } + + r = dm_cache_get_metadata_dev_size(cache->cmd, &nr_blocks_metadata); + if (r) { + DMERR("could not get metadata device size"); + goto err; + } + + residency = policy_residency(cache->policy); + + DMEMIT("%llu/%llu %u %u %u %u %u %u %llu %u ", + (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata), + (unsigned long long)nr_blocks_metadata, + (unsigned) atomic_read(&cache->stats.read_hit), + (unsigned) atomic_read(&cache->stats.read_miss), + (unsigned) atomic_read(&cache->stats.write_hit), + (unsigned) atomic_read(&cache->stats.write_miss), + (unsigned) atomic_read(&cache->stats.demotion), + (unsigned) atomic_read(&cache->stats.promotion), + (unsigned long long) from_cblock(residency), + cache->nr_dirty); + + if (cache->features.write_through) + DMEMIT("1 writethrough "); + else + DMEMIT("0 "); + + DMEMIT("2 migration_threshold %llu ", (unsigned long long) cache->migration_threshold); + if (sz < maxlen) { + r = policy_emit_config_values(cache->policy, result + sz, maxlen - sz); + if (r) + DMERR("policy_emit_config_values returned %d", r); + } + + break; + + case STATUSTYPE_TABLE: + format_dev_t(buf, cache->metadata_dev->bdev->bd_dev); + DMEMIT("%s ", buf); + format_dev_t(buf, cache->cache_dev->bdev->bd_dev); + DMEMIT("%s ", buf); + format_dev_t(buf, cache->origin_dev->bdev->bd_dev); + DMEMIT("%s", buf); + + for (i = 0; i < cache->nr_ctr_args - 1; i++) + DMEMIT(" %s", cache->ctr_args[i]); + if (cache->nr_ctr_args) + DMEMIT(" %s", cache->ctr_args[cache->nr_ctr_args - 1]); + } + + return; + +err: + DMEMIT("Error"); +} + +#define NOT_CORE_OPTION 1 + +static int process_config_option(struct cache *cache, char **argv) +{ + unsigned long tmp; + + if (!strcasecmp(argv[0], "migration_threshold")) { + if (kstrtoul(argv[1], 10, &tmp)) + return -EINVAL; + + cache->migration_threshold = tmp; + return 0; + } + + return NOT_CORE_OPTION; +} + +/* + * Supports <key> <value>. + * + * The key migration_threshold is supported by the cache target core. + */ +static int cache_message(struct dm_target *ti, unsigned argc, char **argv) +{ + int r; + struct cache *cache = ti->private; + + if (argc != 2) + return -EINVAL; + + r = process_config_option(cache, argv); + if (r == NOT_CORE_OPTION) + return policy_set_config_value(cache->policy, argv[0], argv[1]); + + return r; +} + +static int cache_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + int r = 0; + struct cache *cache = ti->private; + + r = fn(ti, cache->cache_dev, 0, get_dev_size(cache->cache_dev), data); + if (!r) + r = fn(ti, cache->origin_dev, 0, ti->len, data); + + return r; +} + +/* + * We assume I/O is going to the origin (which is the volume + * more likely to have restrictions e.g. by being striped). + * (Looking up the exact location of the data would be expensive + * and could always be out of date by the time the bio is submitted.) + */ +static int cache_bvec_merge(struct dm_target *ti, + struct bvec_merge_data *bvm, + struct bio_vec *biovec, int max_size) +{ + struct cache *cache = ti->private; + struct request_queue *q = bdev_get_queue(cache->origin_dev->bdev); + + if (!q->merge_bvec_fn) + return max_size; + + bvm->bi_bdev = cache->origin_dev->bdev; + return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); +} + +static void set_discard_limits(struct cache *cache, struct queue_limits *limits) +{ + /* + * FIXME: these limits may be incompatible with the cache device + */ + limits->max_discard_sectors = cache->discard_block_size * 1024; + limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT; +} + +static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits) +{ + struct cache *cache = ti->private; + + blk_limits_io_min(limits, 0); + blk_limits_io_opt(limits, cache->sectors_per_block << SECTOR_SHIFT); + set_discard_limits(cache, limits); +} + +/*----------------------------------------------------------------*/ + +static struct target_type cache_target = { + .name = "cache", + .version = {1, 0, 0}, + .module = THIS_MODULE, + .ctr = cache_ctr, + .dtr = cache_dtr, + .map = cache_map, + .end_io = cache_end_io, + .postsuspend = cache_postsuspend, + .preresume = cache_preresume, + .resume = cache_resume, + .status = cache_status, + .message = cache_message, + .iterate_devices = cache_iterate_devices, + .merge = cache_bvec_merge, + .io_hints = cache_io_hints, +}; + +static int __init dm_cache_init(void) +{ + int r; + + r = dm_register_target(&cache_target); + if (r) { + DMERR("cache target registration failed: %d", r); + return r; + } + + migration_cache = KMEM_CACHE(dm_cache_migration, 0); + if (!migration_cache) { + dm_unregister_target(&cache_target); + return -ENOMEM; + } + + return 0; +} + +static void __exit dm_cache_exit(void) +{ + dm_unregister_target(&cache_target); + kmem_cache_destroy(migration_cache); +} + +module_init(dm_cache_init); +module_exit(dm_cache_exit); + +MODULE_DESCRIPTION(DM_NAME " cache target"); +MODULE_AUTHOR("Joe Thornber <ejt@redhat.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f7369f9d859..13c15480d94 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1234,20 +1234,6 @@ static int crypt_decode_key(u8 *key, char *hex, unsigned int size) return 0; } -/* - * Encode key into its hex representation - */ -static void crypt_encode_key(char *hex, u8 *key, unsigned int size) -{ - unsigned int i; - - for (i = 0; i < size; i++) { - sprintf(hex, "%02x", *key); - hex += 2; - key++; - } -} - static void crypt_free_tfms(struct crypt_config *cc) { unsigned i; @@ -1651,7 +1637,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (opt_params == 1 && opt_string && !strcasecmp(opt_string, "allow_discards")) - ti->num_discard_requests = 1; + ti->num_discard_bios = 1; else if (opt_params) { ret = -EINVAL; ti->error = "Invalid feature arguments"; @@ -1679,7 +1665,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - ti->num_flush_requests = 1; + ti->num_flush_bios = 1; ti->discard_zeroes_data_unsupported = true; return 0; @@ -1717,11 +1703,11 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } -static int crypt_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void crypt_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { struct crypt_config *cc = ti->private; - unsigned int sz = 0; + unsigned i, sz = 0; switch (type) { case STATUSTYPE_INFO: @@ -1731,27 +1717,20 @@ static int crypt_status(struct dm_target *ti, status_type_t type, case STATUSTYPE_TABLE: DMEMIT("%s ", cc->cipher_string); - if (cc->key_size > 0) { - if ((maxlen - sz) < ((cc->key_size << 1) + 1)) - return -ENOMEM; - - crypt_encode_key(result + sz, cc->key, cc->key_size); - sz += cc->key_size << 1; - } else { - if (sz >= maxlen) - return -ENOMEM; - result[sz++] = '-'; - } + if (cc->key_size > 0) + for (i = 0; i < cc->key_size; i++) + DMEMIT("%02x", cc->key[i]); + else + DMEMIT("-"); DMEMIT(" %llu %s %llu", (unsigned long long)cc->iv_offset, cc->dev->name, (unsigned long long)cc->start); - if (ti->num_discard_requests) + if (ti->num_discard_bios) DMEMIT(" 1 allow_discards"); break; } - return 0; } static void crypt_postsuspend(struct dm_target *ti) @@ -1845,7 +1824,7 @@ static int crypt_iterate_devices(struct dm_target *ti, static struct target_type crypt_target = { .name = "crypt", - .version = {1, 12, 0}, + .version = {1, 12, 1}, .module = THIS_MODULE, .ctr = crypt_ctr, .dtr = crypt_dtr, diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index cc1bd048acb..496d5f3646a 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -198,8 +198,8 @@ out: mutex_init(&dc->timer_lock); atomic_set(&dc->may_delay, 1); - ti->num_flush_requests = 1; - ti->num_discard_requests = 1; + ti->num_flush_bios = 1; + ti->num_discard_bios = 1; ti->private = dc; return 0; @@ -293,8 +293,8 @@ static int delay_map(struct dm_target *ti, struct bio *bio) return delay_bio(dc, dc->read_delay, bio); } -static int delay_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void delay_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { struct delay_c *dc = ti->private; int sz = 0; @@ -314,8 +314,6 @@ static int delay_status(struct dm_target *ti, status_type_t type, dc->write_delay); break; } - - return 0; } static int delay_iterate_devices(struct dm_target *ti, @@ -337,7 +335,7 @@ out: static struct target_type delay_target = { .name = "delay", - .version = {1, 2, 0}, + .version = {1, 2, 1}, .module = THIS_MODULE, .ctr = delay_ctr, .dtr = delay_dtr, diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 9721f2ffb1a..7fcf21cb4ff 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -216,8 +216,8 @@ static int flakey_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - ti->num_flush_requests = 1; - ti->num_discard_requests = 1; + ti->num_flush_bios = 1; + ti->num_discard_bios = 1; ti->per_bio_data_size = sizeof(struct per_bio_data); ti->private = fc; return 0; @@ -337,8 +337,8 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) return error; } -static int flakey_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void flakey_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { unsigned sz = 0; struct flakey_c *fc = ti->private; @@ -368,7 +368,6 @@ static int flakey_status(struct dm_target *ti, status_type_t type, break; } - return 0; } static int flakey_ioctl(struct dm_target *ti, unsigned int cmd, unsigned long arg) @@ -411,7 +410,7 @@ static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_ static struct target_type flakey_target = { .name = "flakey", - .version = {1, 3, 0}, + .version = {1, 3, 1}, .module = THIS_MODULE, .ctr = flakey_ctr, .dtr = flakey_dtr, diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 0666b5d14b8..aa04f022464 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1067,6 +1067,7 @@ static void retrieve_status(struct dm_table *table, num_targets = dm_table_get_num_targets(table); for (i = 0; i < num_targets; i++) { struct dm_target *ti = dm_table_get_target(table, i); + size_t l; remaining = len - (outptr - outbuf); if (remaining <= sizeof(struct dm_target_spec)) { @@ -1093,14 +1094,17 @@ static void retrieve_status(struct dm_table *table, if (ti->type->status) { if (param->flags & DM_NOFLUSH_FLAG) status_flags |= DM_STATUS_NOFLUSH_FLAG; - if (ti->type->status(ti, type, status_flags, outptr, remaining)) { - param->flags |= DM_BUFFER_FULL_FLAG; - break; - } + ti->type->status(ti, type, status_flags, outptr, remaining); } else outptr[0] = '\0'; - outptr += strlen(outptr) + 1; + l = strlen(outptr) + 1; + if (l == remaining) { + param->flags |= DM_BUFFER_FULL_FLAG; + break; + } + + outptr += l; used = param->data_start + (outptr - outbuf); outptr = align_ptr(outptr); @@ -1410,6 +1414,22 @@ static int table_status(struct dm_ioctl *param, size_t param_size) return 0; } +static bool buffer_test_overflow(char *result, unsigned maxlen) +{ + return !maxlen || strlen(result) + 1 >= maxlen; +} + +/* + * Process device-mapper dependent messages. + * Returns a number <= 1 if message was processed by device mapper. + * Returns 2 if message should be delivered to the target. + */ +static int message_for_md(struct mapped_device *md, unsigned argc, char **argv, + char *result, unsigned maxlen) +{ + return 2; +} + /* * Pass a message to the target that's at the supplied device offset. */ @@ -1421,6 +1441,8 @@ static int target_message(struct dm_ioctl *param, size_t param_size) struct dm_table *table; struct dm_target *ti; struct dm_target_msg *tmsg = (void *) param + param->data_start; + size_t maxlen; + char *result = get_result_buffer(param, param_size, &maxlen); md = find_device(param); if (!md) @@ -1444,6 +1466,10 @@ static int target_message(struct dm_ioctl *param, size_t param_size) goto out_argv; } + r = message_for_md(md, argc, argv, result, maxlen); + if (r <= 1) + goto out_argv; + table = dm_get_live_table(md); if (!table) goto out_argv; @@ -1469,44 +1495,68 @@ static int target_message(struct dm_ioctl *param, size_t param_size) out_argv: kfree(argv); out: - param->data_size = 0; + if (r >= 0) + __dev_status(md, param); + + if (r == 1) { + param->flags |= DM_DATA_OUT_FLAG; + if (buffer_test_overflow(result, maxlen)) + param->flags |= DM_BUFFER_FULL_FLAG; + else + param->data_size = param->data_start + strlen(result) + 1; + r = 0; + } + dm_put(md); return r; } +/* + * The ioctl parameter block consists of two parts, a dm_ioctl struct + * followed by a data buffer. This flag is set if the second part, + * which has a variable size, is not used by the function processing + * the ioctl. + */ +#define IOCTL_FLAGS_NO_PARAMS 1 + /*----------------------------------------------------------------- * Implementation of open/close/ioctl on the special char * device. *---------------------------------------------------------------*/ -static ioctl_fn lookup_ioctl(unsigned int cmd) +static ioctl_fn lookup_ioctl(unsigned int cmd, int *ioctl_flags) { static struct { int cmd; + int flags; ioctl_fn fn; } _ioctls[] = { - {DM_VERSION_CMD, NULL}, /* version is dealt with elsewhere */ - {DM_REMOVE_ALL_CMD, remove_all}, - {DM_LIST_DEVICES_CMD, list_devices}, - - {DM_DEV_CREATE_CMD, dev_create}, - {DM_DEV_REMOVE_CMD, dev_remove}, - {DM_DEV_RENAME_CMD, dev_rename}, - {DM_DEV_SUSPEND_CMD, dev_suspend}, - {DM_DEV_STATUS_CMD, dev_status}, - {DM_DEV_WAIT_CMD, dev_wait}, - - {DM_TABLE_LOAD_CMD, table_load}, - {DM_TABLE_CLEAR_CMD, table_clear}, - {DM_TABLE_DEPS_CMD, table_deps}, - {DM_TABLE_STATUS_CMD, table_status}, - - {DM_LIST_VERSIONS_CMD, list_versions}, - - {DM_TARGET_MSG_CMD, target_message}, - {DM_DEV_SET_GEOMETRY_CMD, dev_set_geometry} + {DM_VERSION_CMD, 0, NULL}, /* version is dealt with elsewhere */ + {DM_REMOVE_ALL_CMD, IOCTL_FLAGS_NO_PARAMS, remove_all}, + {DM_LIST_DEVICES_CMD, 0, list_devices}, + + {DM_DEV_CREATE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_create}, + {DM_DEV_REMOVE_CMD, IOCTL_FLAGS_NO_PARAMS, dev_remove}, + {DM_DEV_RENAME_CMD, 0, dev_rename}, + {DM_DEV_SUSPEND_CMD, IOCTL_FLAGS_NO_PARAMS, dev_suspend}, + {DM_DEV_STATUS_CMD, IOCTL_FLAGS_NO_PARAMS, dev_status}, + {DM_DEV_WAIT_CMD, 0, dev_wait}, + + {DM_TABLE_LOAD_CMD, 0, table_load}, + {DM_TABLE_CLEAR_CMD, IOCTL_FLAGS_NO_PARAMS, table_clear}, + {DM_TABLE_DEPS_CMD, 0, table_deps}, + {DM_TABLE_STATUS_CMD, 0, table_status}, + + {DM_LIST_VERSIONS_CMD, 0, list_versions}, + + {DM_TARGET_MSG_CMD, 0, target_message}, + {DM_DEV_SET_GEOMETRY_CMD, 0, dev_set_geometry} }; - return (cmd >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[cmd].fn; + if (unlikely(cmd >= ARRAY_SIZE(_ioctls))) + return NULL; + + *ioctl_flags = _ioctls[cmd].flags; + return _ioctls[cmd].fn; } /* @@ -1543,7 +1593,8 @@ static int check_version(unsigned int cmd, struct dm_ioctl __user *user) return r; } -#define DM_PARAMS_VMALLOC 0x0001 /* Params alloced with vmalloc not kmalloc */ +#define DM_PARAMS_KMALLOC 0x0001 /* Params alloced with kmalloc */ +#define DM_PARAMS_VMALLOC 0x0002 /* Params alloced with vmalloc */ #define DM_WIPE_BUFFER 0x0010 /* Wipe input buffer before returning from ioctl */ static void free_params(struct dm_ioctl *param, size_t param_size, int param_flags) @@ -1551,66 +1602,80 @@ static void free_params(struct dm_ioctl *param, size_t param_size, int param_fla if (param_flags & DM_WIPE_BUFFER) memset(param, 0, param_size); + if (param_flags & DM_PARAMS_KMALLOC) + kfree(param); if (param_flags & DM_PARAMS_VMALLOC) vfree(param); - else - kfree(param); } -static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl **param, int *param_flags) +static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kernel, + int ioctl_flags, + struct dm_ioctl **param, int *param_flags) { - struct dm_ioctl tmp, *dmi; + struct dm_ioctl *dmi; int secure_data; + const size_t minimum_data_size = sizeof(*param_kernel) - sizeof(param_kernel->data); - if (copy_from_user(&tmp, user, sizeof(tmp) - sizeof(tmp.data))) + if (copy_from_user(param_kernel, user, minimum_data_size)) return -EFAULT; - if (tmp.data_size < (sizeof(tmp) - sizeof(tmp.data))) + if (param_kernel->data_size < minimum_data_size) return -EINVAL; - secure_data = tmp.flags & DM_SECURE_DATA_FLAG; + secure_data = param_kernel->flags & DM_SECURE_DATA_FLAG; *param_flags = secure_data ? DM_WIPE_BUFFER : 0; + if (ioctl_flags & IOCTL_FLAGS_NO_PARAMS) { + dmi = param_kernel; + dmi->data_size = minimum_data_size; + goto data_copied; + } + /* * Try to avoid low memory issues when a device is suspended. * Use kmalloc() rather than vmalloc() when we can. */ dmi = NULL; - if (tmp.data_size <= KMALLOC_MAX_SIZE) - dmi = kmalloc(tmp.data_size, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (param_kernel->data_size <= KMALLOC_MAX_SIZE) { + dmi = kmalloc(param_kernel->data_size, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (dmi) + *param_flags |= DM_PARAMS_KMALLOC; + } if (!dmi) { - dmi = __vmalloc(tmp.data_size, GFP_NOIO | __GFP_REPEAT | __GFP_HIGH, PAGE_KERNEL); - *param_flags |= DM_PARAMS_VMALLOC; + dmi = __vmalloc(param_kernel->data_size, GFP_NOIO | __GFP_REPEAT | __GFP_HIGH, PAGE_KERNEL); + if (dmi) + *param_flags |= DM_PARAMS_VMALLOC; } if (!dmi) { - if (secure_data && clear_user(user, tmp.data_size)) + if (secure_data && clear_user(user, param_kernel->data_size)) return -EFAULT; return -ENOMEM; } - if (copy_from_user(dmi, user, tmp.data_size)) + if (copy_from_user(dmi, user, param_kernel->data_size)) goto bad; +data_copied: /* * Abort if something changed the ioctl data while it was being copied. */ - if (dmi->data_size != tmp.data_size) { + if (dmi->data_size != param_kernel->data_size) { DMERR("rejecting ioctl: data size modified while processing parameters"); goto bad; } /* Wipe the user buffer so we do not return it to userspace */ - if (secure_data && clear_user(user, tmp.data_size)) + if (secure_data && clear_user(user, param_kernel->data_size)) goto bad; *param = dmi; return 0; bad: - free_params(dmi, tmp.data_size, *param_flags); + free_params(dmi, param_kernel->data_size, *param_flags); return -EFAULT; } @@ -1621,6 +1686,7 @@ static int validate_params(uint cmd, struct dm_ioctl *param) param->flags &= ~DM_BUFFER_FULL_FLAG; param->flags &= ~DM_UEVENT_GENERATED_FLAG; param->flags &= ~DM_SECURE_DATA_FLAG; + param->flags &= ~DM_DATA_OUT_FLAG; /* Ignores parameters */ if (cmd == DM_REMOVE_ALL_CMD || @@ -1648,11 +1714,13 @@ static int validate_params(uint cmd, struct dm_ioctl *param) static int ctl_ioctl(uint command, struct dm_ioctl __user *user) { int r = 0; + int ioctl_flags; int param_flags; unsigned int cmd; struct dm_ioctl *uninitialized_var(param); ioctl_fn fn = NULL; size_t input_param_size; + struct dm_ioctl param_kernel; /* only root can play with this */ if (!capable(CAP_SYS_ADMIN)) @@ -1677,7 +1745,7 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user) if (cmd == DM_VERSION_CMD) return 0; - fn = lookup_ioctl(cmd); + fn = lookup_ioctl(cmd, &ioctl_flags); if (!fn) { DMWARN("dm_ctl_ioctl: unknown command 0x%x", command); return -ENOTTY; @@ -1686,7 +1754,7 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user) /* * Copy the parameters into kernel space. */ - r = copy_params(user, ¶m, ¶m_flags); + r = copy_params(user, ¶m_kernel, ioctl_flags, ¶m, ¶m_flags); if (r) return r; @@ -1699,6 +1767,10 @@ static int ctl_ioctl(uint command, struct dm_ioctl __user *user) param->data_size = sizeof(*param); r = fn(param, input_param_size); + if (unlikely(param->flags & DM_BUFFER_FULL_FLAG) && + unlikely(ioctl_flags & IOCTL_FLAGS_NO_PARAMS)) + DMERR("ioctl %d tried to output some data but has IOCTL_FLAGS_NO_PARAMS set", cmd); + /* * Copy the results back to userland. */ diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 68c02673263..d581fe5d2fa 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <linux/workqueue.h> #include <linux/mutex.h> +#include <linux/delay.h> #include <linux/device-mapper.h> #include <linux/dm-kcopyd.h> @@ -51,6 +52,8 @@ struct dm_kcopyd_client { struct workqueue_struct *kcopyd_wq; struct work_struct kcopyd_work; + struct dm_kcopyd_throttle *throttle; + /* * We maintain three lists of jobs: * @@ -68,6 +71,117 @@ struct dm_kcopyd_client { static struct page_list zero_page_list; +static DEFINE_SPINLOCK(throttle_spinlock); + +/* + * IO/IDLE accounting slowly decays after (1 << ACCOUNT_INTERVAL_SHIFT) period. + * When total_period >= (1 << ACCOUNT_INTERVAL_SHIFT) the counters are divided + * by 2. + */ +#define ACCOUNT_INTERVAL_SHIFT SHIFT_HZ + +/* + * Sleep this number of milliseconds. + * + * The value was decided experimentally. + * Smaller values seem to cause an increased copy rate above the limit. + * The reason for this is unknown but possibly due to jiffies rounding errors + * or read/write cache inside the disk. + */ +#define SLEEP_MSEC 100 + +/* + * Maximum number of sleep events. There is a theoretical livelock if more + * kcopyd clients do work simultaneously which this limit avoids. + */ +#define MAX_SLEEPS 10 + +static void io_job_start(struct dm_kcopyd_throttle *t) +{ + unsigned throttle, now, difference; + int slept = 0, skew; + + if (unlikely(!t)) + return; + +try_again: + spin_lock_irq(&throttle_spinlock); + + throttle = ACCESS_ONCE(t->throttle); + + if (likely(throttle >= 100)) + goto skip_limit; + + now = jiffies; + difference = now - t->last_jiffies; + t->last_jiffies = now; + if (t->num_io_jobs) + t->io_period += difference; + t->total_period += difference; + + /* + * Maintain sane values if we got a temporary overflow. + */ + if (unlikely(t->io_period > t->total_period)) + t->io_period = t->total_period; + + if (unlikely(t->total_period >= (1 << ACCOUNT_INTERVAL_SHIFT))) { + int shift = fls(t->total_period >> ACCOUNT_INTERVAL_SHIFT); + t->total_period >>= shift; + t->io_period >>= shift; + } + + skew = t->io_period - throttle * t->total_period / 100; + + if (unlikely(skew > 0) && slept < MAX_SLEEPS) { + slept++; + spin_unlock_irq(&throttle_spinlock); + msleep(SLEEP_MSEC); + goto try_again; + } + +skip_limit: + t->num_io_jobs++; + + spin_unlock_irq(&throttle_spinlock); +} + +static void io_job_finish(struct dm_kcopyd_throttle *t) +{ + unsigned long flags; + + if (unlikely(!t)) + return; + + spin_lock_irqsave(&throttle_spinlock, flags); + + t->num_io_jobs--; + + if (likely(ACCESS_ONCE(t->throttle) >= 100)) + goto skip_limit; + + if (!t->num_io_jobs) { + unsigned now, difference; + + now = jiffies; + difference = now - t->last_jiffies; + t->last_jiffies = now; + + t->io_period += difference; + t->total_period += difference; + + /* + * Maintain sane values if we got a temporary overflow. + */ + if (unlikely(t->io_period > t->total_period)) + t->io_period = t->total_period; + } + +skip_limit: + spin_unlock_irqrestore(&throttle_spinlock, flags); +} + + static void wake(struct dm_kcopyd_client *kc) { queue_work(kc->kcopyd_wq, &kc->kcopyd_work); @@ -348,6 +462,8 @@ static void complete_io(unsigned long error, void *context) struct kcopyd_job *job = (struct kcopyd_job *) context; struct dm_kcopyd_client *kc = job->kc; + io_job_finish(kc->throttle); + if (error) { if (job->rw & WRITE) job->write_err |= error; @@ -389,6 +505,8 @@ static int run_io_job(struct kcopyd_job *job) .client = job->kc->io_client, }; + io_job_start(job->kc->throttle); + if (job->rw == READ) r = dm_io(&io_req, 1, &job->source, NULL); else @@ -695,7 +813,7 @@ int kcopyd_cancel(struct kcopyd_job *job, int block) /*----------------------------------------------------------------- * Client setup *---------------------------------------------------------------*/ -struct dm_kcopyd_client *dm_kcopyd_client_create(void) +struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle) { int r = -ENOMEM; struct dm_kcopyd_client *kc; @@ -708,6 +826,7 @@ struct dm_kcopyd_client *dm_kcopyd_client_create(void) INIT_LIST_HEAD(&kc->complete_jobs); INIT_LIST_HEAD(&kc->io_jobs); INIT_LIST_HEAD(&kc->pages_jobs); + kc->throttle = throttle; kc->job_pool = mempool_create_slab_pool(MIN_JOBS, _job_cache); if (!kc->job_pool) diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 328cad5617a..4f99d267340 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -53,9 +53,9 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; } - ti->num_flush_requests = 1; - ti->num_discard_requests = 1; - ti->num_write_same_requests = 1; + ti->num_flush_bios = 1; + ti->num_discard_bios = 1; + ti->num_write_same_bios = 1; ti->private = lc; return 0; @@ -95,8 +95,8 @@ static int linear_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -static int linear_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void linear_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { struct linear_c *lc = (struct linear_c *) ti->private; @@ -110,7 +110,6 @@ static int linear_status(struct dm_target *ti, status_type_t type, (unsigned long long)lc->start); break; } - return 0; } static int linear_ioctl(struct dm_target *ti, unsigned int cmd, @@ -155,7 +154,7 @@ static int linear_iterate_devices(struct dm_target *ti, static struct target_type linear_target = { .name = "linear", - .version = {1, 2, 0}, + .version = {1, 2, 1}, .module = THIS_MODULE, .ctr = linear_ctr, .dtr = linear_dtr, diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 573bd04591b..51bb81676be 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -905,8 +905,8 @@ static int multipath_ctr(struct dm_target *ti, unsigned int argc, goto bad; } - ti->num_flush_requests = 1; - ti->num_discard_requests = 1; + ti->num_flush_bios = 1; + ti->num_discard_bios = 1; return 0; @@ -1378,8 +1378,8 @@ static void multipath_resume(struct dm_target *ti) * [priority selector-name num_ps_args [ps_args]* * num_paths num_selector_args [path_dev [selector_args]* ]+ ]+ */ -static int multipath_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void multipath_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { int sz = 0; unsigned long flags; @@ -1485,8 +1485,6 @@ static int multipath_status(struct dm_target *ti, status_type_t type, } spin_unlock_irqrestore(&m->lock, flags); - - return 0; } static int multipath_message(struct dm_target *ti, unsigned argc, char **argv) @@ -1695,7 +1693,7 @@ out: *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 5, 0}, + .version = {1, 5, 1}, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 9e58dbd8d8c..9a01d1e4c78 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1151,7 +1151,7 @@ static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv) INIT_WORK(&rs->md.event_work, do_table_event); ti->private = rs; - ti->num_flush_requests = 1; + ti->num_flush_bios = 1; mutex_lock(&rs->md.reconfig_mutex); ret = md_run(&rs->md); @@ -1201,8 +1201,8 @@ static int raid_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } -static int raid_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void raid_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { struct raid_set *rs = ti->private; unsigned raid_param_cnt = 1; /* at least 1 for chunksize */ @@ -1344,8 +1344,6 @@ static int raid_status(struct dm_target *ti, status_type_t type, DMEMIT(" -"); } } - - return 0; } static int raid_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) @@ -1405,7 +1403,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 4, 1}, + .version = {1, 4, 2}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index fa519185ebb..d053098c6a9 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -82,6 +82,9 @@ struct mirror_set { struct mirror mirror[0]; }; +DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(raid1_resync_throttle, + "A percentage of time allocated for raid resynchronization"); + static void wakeup_mirrord(void *context) { struct mirror_set *ms = context; @@ -1072,8 +1075,8 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) goto err_free_context; - ti->num_flush_requests = 1; - ti->num_discard_requests = 1; + ti->num_flush_bios = 1; + ti->num_discard_bios = 1; ti->per_bio_data_size = sizeof(struct dm_raid1_bio_record); ti->discard_zeroes_data_unsupported = true; @@ -1111,7 +1114,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto err_destroy_wq; } - ms->kcopyd_client = dm_kcopyd_client_create(); + ms->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle); if (IS_ERR(ms->kcopyd_client)) { r = PTR_ERR(ms->kcopyd_client); goto err_destroy_wq; @@ -1347,8 +1350,8 @@ static char device_status_char(struct mirror *m) } -static int mirror_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void mirror_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { unsigned int m, sz = 0; struct mirror_set *ms = (struct mirror_set *) ti->private; @@ -1383,8 +1386,6 @@ static int mirror_status(struct dm_target *ti, status_type_t type, if (ms->features & DM_RAID1_HANDLE_ERRORS) DMEMIT(" 1 handle_errors"); } - - return 0; } static int mirror_iterate_devices(struct dm_target *ti, @@ -1403,7 +1404,7 @@ static int mirror_iterate_devices(struct dm_target *ti, static struct target_type mirror_target = { .name = "mirror", - .version = {1, 13, 1}, + .version = {1, 13, 2}, .module = THIS_MODULE, .ctr = mirror_ctr, .dtr = mirror_dtr, diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 10079e07edf..c0e07026a8d 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -124,6 +124,9 @@ struct dm_snapshot { #define RUNNING_MERGE 0 #define SHUTDOWN_MERGE 1 +DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, + "A percentage of time allocated for copy on write"); + struct dm_dev *dm_snap_origin(struct dm_snapshot *s) { return s->origin; @@ -1037,7 +1040,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) int i; int r = -EINVAL; char *origin_path, *cow_path; - unsigned args_used, num_flush_requests = 1; + unsigned args_used, num_flush_bios = 1; fmode_t origin_mode = FMODE_READ; if (argc != 4) { @@ -1047,7 +1050,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) } if (dm_target_is_snapshot_merge(ti)) { - num_flush_requests = 2; + num_flush_bios = 2; origin_mode = FMODE_WRITE; } @@ -1108,7 +1111,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad_hash_tables; } - s->kcopyd_client = dm_kcopyd_client_create(); + s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle); if (IS_ERR(s->kcopyd_client)) { r = PTR_ERR(s->kcopyd_client); ti->error = "Could not create kcopyd client"; @@ -1127,7 +1130,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) spin_lock_init(&s->tracked_chunk_lock); ti->private = s; - ti->num_flush_requests = num_flush_requests; + ti->num_flush_bios = num_flush_bios; ti->per_bio_data_size = sizeof(struct dm_snap_tracked_chunk); /* Add snapshot to the list of snapshots for this origin */ @@ -1691,7 +1694,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio) init_tracked_chunk(bio); if (bio->bi_rw & REQ_FLUSH) { - if (!dm_bio_get_target_request_nr(bio)) + if (!dm_bio_get_target_bio_nr(bio)) bio->bi_bdev = s->origin->bdev; else bio->bi_bdev = s->cow->bdev; @@ -1836,8 +1839,8 @@ static void snapshot_merge_resume(struct dm_target *ti) start_merge(s); } -static int snapshot_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void snapshot_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { unsigned sz = 0; struct dm_snapshot *snap = ti->private; @@ -1883,8 +1886,6 @@ static int snapshot_status(struct dm_target *ti, status_type_t type, maxlen - sz); break; } - - return 0; } static int snapshot_iterate_devices(struct dm_target *ti, @@ -2104,7 +2105,7 @@ static int origin_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ti->private = dev; - ti->num_flush_requests = 1; + ti->num_flush_bios = 1; return 0; } @@ -2138,8 +2139,8 @@ static void origin_resume(struct dm_target *ti) ti->max_io_len = get_origin_minimum_chunksize(dev->bdev); } -static int origin_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void origin_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { struct dm_dev *dev = ti->private; @@ -2152,8 +2153,6 @@ static int origin_status(struct dm_target *ti, status_type_t type, snprintf(result, maxlen, "%s", dev->name); break; } - - return 0; } static int origin_merge(struct dm_target *ti, struct bvec_merge_data *bvm, @@ -2180,7 +2179,7 @@ static int origin_iterate_devices(struct dm_target *ti, static struct target_type origin_target = { .name = "snapshot-origin", - .version = {1, 8, 0}, + .version = {1, 8, 1}, .module = THIS_MODULE, .ctr = origin_ctr, .dtr = origin_dtr, @@ -2193,7 +2192,7 @@ static struct target_type origin_target = { static struct target_type snapshot_target = { .name = "snapshot", - .version = {1, 11, 0}, + .version = {1, 11, 1}, .module = THIS_MODULE, .ctr = snapshot_ctr, .dtr = snapshot_dtr, @@ -2306,3 +2305,5 @@ module_exit(dm_snapshot_exit); MODULE_DESCRIPTION(DM_NAME " snapshot target"); MODULE_AUTHOR("Joe Thornber"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("dm-snapshot-origin"); +MODULE_ALIAS("dm-snapshot-merge"); diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index c89cde86d40..d8837d313f5 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -160,9 +160,9 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv) if (r) return r; - ti->num_flush_requests = stripes; - ti->num_discard_requests = stripes; - ti->num_write_same_requests = stripes; + ti->num_flush_bios = stripes; + ti->num_discard_bios = stripes; + ti->num_write_same_bios = stripes; sc->chunk_size = chunk_size; if (chunk_size & (chunk_size - 1)) @@ -276,19 +276,19 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) { struct stripe_c *sc = ti->private; uint32_t stripe; - unsigned target_request_nr; + unsigned target_bio_nr; if (bio->bi_rw & REQ_FLUSH) { - target_request_nr = dm_bio_get_target_request_nr(bio); - BUG_ON(target_request_nr >= sc->stripes); - bio->bi_bdev = sc->stripe[target_request_nr].dev->bdev; + target_bio_nr = dm_bio_get_target_bio_nr(bio); + BUG_ON(target_bio_nr >= sc->stripes); + bio->bi_bdev = sc->stripe[target_bio_nr].dev->bdev; return DM_MAPIO_REMAPPED; } if (unlikely(bio->bi_rw & REQ_DISCARD) || unlikely(bio->bi_rw & REQ_WRITE_SAME)) { - target_request_nr = dm_bio_get_target_request_nr(bio); - BUG_ON(target_request_nr >= sc->stripes); - return stripe_map_range(sc, bio, target_request_nr); + target_bio_nr = dm_bio_get_target_bio_nr(bio); + BUG_ON(target_bio_nr >= sc->stripes); + return stripe_map_range(sc, bio, target_bio_nr); } stripe_map_sector(sc, bio->bi_sector, &stripe, &bio->bi_sector); @@ -312,8 +312,8 @@ static int stripe_map(struct dm_target *ti, struct bio *bio) * */ -static int stripe_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void stripe_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { struct stripe_c *sc = (struct stripe_c *) ti->private; char buffer[sc->stripes + 1]; @@ -340,7 +340,6 @@ static int stripe_status(struct dm_target *ti, status_type_t type, (unsigned long long)sc->stripe[i].physical_start); break; } - return 0; } static int stripe_end_io(struct dm_target *ti, struct bio *bio, int error) @@ -428,7 +427,7 @@ static int stripe_merge(struct dm_target *ti, struct bvec_merge_data *bvm, static struct target_type stripe_target = { .name = "striped", - .version = {1, 5, 0}, + .version = {1, 5, 1}, .module = THIS_MODULE, .ctr = stripe_ctr, .dtr = stripe_dtr, diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index daf25d0890b..e50dad0c65f 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -217,7 +217,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode, if (alloc_targets(t, num_targets)) { kfree(t); - t = NULL; return -ENOMEM; } @@ -823,8 +822,8 @@ int dm_table_add_target(struct dm_table *t, const char *type, t->highs[t->num_targets++] = tgt->begin + tgt->len - 1; - if (!tgt->num_discard_requests && tgt->discards_supported) - DMWARN("%s: %s: ignoring discards_supported because num_discard_requests is zero.", + if (!tgt->num_discard_bios && tgt->discards_supported) + DMWARN("%s: %s: ignoring discards_supported because num_discard_bios is zero.", dm_device_name(t->md), type); return 0; @@ -1360,7 +1359,7 @@ static bool dm_table_supports_flush(struct dm_table *t, unsigned flush) while (i < dm_table_get_num_targets(t)) { ti = dm_table_get_target(t, i++); - if (!ti->num_flush_requests) + if (!ti->num_flush_bios) continue; if (ti->flush_supported) @@ -1439,7 +1438,7 @@ static bool dm_table_supports_write_same(struct dm_table *t) while (i < dm_table_get_num_targets(t)) { ti = dm_table_get_target(t, i++); - if (!ti->num_write_same_requests) + if (!ti->num_write_same_bios) return false; if (!ti->type->iterate_devices || @@ -1657,7 +1656,7 @@ bool dm_table_supports_discards(struct dm_table *t) while (i < dm_table_get_num_targets(t)) { ti = dm_table_get_target(t, i++); - if (!ti->num_discard_requests) + if (!ti->num_discard_bios) continue; if (ti->discards_supported) diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c index 617d21a7725..37ba5db71cd 100644 --- a/drivers/md/dm-target.c +++ b/drivers/md/dm-target.c @@ -116,7 +116,7 @@ static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args) /* * Return error for discards instead of -EOPNOTSUPP */ - tt->num_discard_requests = 1; + tt->num_discard_bios = 1; return 0; } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 4d6e85367b8..00cee02f8fc 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -280,7 +280,7 @@ static void unpack_block_time(uint64_t v, dm_block_t *b, uint32_t *t) *t = v & ((1 << 24) - 1); } -static void data_block_inc(void *context, void *value_le) +static void data_block_inc(void *context, const void *value_le) { struct dm_space_map *sm = context; __le64 v_le; @@ -292,7 +292,7 @@ static void data_block_inc(void *context, void *value_le) dm_sm_inc_block(sm, b); } -static void data_block_dec(void *context, void *value_le) +static void data_block_dec(void *context, const void *value_le) { struct dm_space_map *sm = context; __le64 v_le; @@ -304,7 +304,7 @@ static void data_block_dec(void *context, void *value_le) dm_sm_dec_block(sm, b); } -static int data_block_equal(void *context, void *value1_le, void *value2_le) +static int data_block_equal(void *context, const void *value1_le, const void *value2_le) { __le64 v1_le, v2_le; uint64_t b1, b2; @@ -318,7 +318,7 @@ static int data_block_equal(void *context, void *value1_le, void *value2_le) return b1 == b2; } -static void subtree_inc(void *context, void *value) +static void subtree_inc(void *context, const void *value) { struct dm_btree_info *info = context; __le64 root_le; @@ -329,7 +329,7 @@ static void subtree_inc(void *context, void *value) dm_tm_inc(info->tm, root); } -static void subtree_dec(void *context, void *value) +static void subtree_dec(void *context, const void *value) { struct dm_btree_info *info = context; __le64 root_le; @@ -341,7 +341,7 @@ static void subtree_dec(void *context, void *value) DMERR("btree delete failed\n"); } -static int subtree_equal(void *context, void *value1_le, void *value2_le) +static int subtree_equal(void *context, const void *value1_le, const void *value2_le) { __le64 v1_le, v2_le; memcpy(&v1_le, value1_le, sizeof(v1_le)); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 5409607d487..009339d6282 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -26,6 +26,9 @@ #define PRISON_CELLS 1024 #define COMMIT_PERIOD HZ +DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle, + "A percentage of time allocated for copy on write"); + /* * The block size of the device holding pool data must be * between 64KB and 1GB. @@ -227,6 +230,78 @@ struct thin_c { /*----------------------------------------------------------------*/ /* + * wake_worker() is used when new work is queued and when pool_resume is + * ready to continue deferred IO processing. + */ +static void wake_worker(struct pool *pool) +{ + queue_work(pool->wq, &pool->worker); +} + +/*----------------------------------------------------------------*/ + +static int bio_detain(struct pool *pool, struct dm_cell_key *key, struct bio *bio, + struct dm_bio_prison_cell **cell_result) +{ + int r; + struct dm_bio_prison_cell *cell_prealloc; + + /* + * Allocate a cell from the prison's mempool. + * This might block but it can't fail. + */ + cell_prealloc = dm_bio_prison_alloc_cell(pool->prison, GFP_NOIO); + + r = dm_bio_detain(pool->prison, key, bio, cell_prealloc, cell_result); + if (r) + /* + * We reused an old cell; we can get rid of + * the new one. + */ + dm_bio_prison_free_cell(pool->prison, cell_prealloc); + + return r; +} + +static void cell_release(struct pool *pool, + struct dm_bio_prison_cell *cell, + struct bio_list *bios) +{ + dm_cell_release(pool->prison, cell, bios); + dm_bio_prison_free_cell(pool->prison, cell); +} + +static void cell_release_no_holder(struct pool *pool, + struct dm_bio_prison_cell *cell, + struct bio_list *bios) +{ + dm_cell_release_no_holder(pool->prison, cell, bios); + dm_bio_prison_free_cell(pool->prison, cell); +} + +static void cell_defer_no_holder_no_free(struct thin_c *tc, + struct dm_bio_prison_cell *cell) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + spin_lock_irqsave(&pool->lock, flags); + dm_cell_release_no_holder(pool->prison, cell, &pool->deferred_bios); + spin_unlock_irqrestore(&pool->lock, flags); + + wake_worker(pool); +} + +static void cell_error(struct pool *pool, + struct dm_bio_prison_cell *cell) +{ + dm_cell_error(pool->prison, cell); + dm_bio_prison_free_cell(pool->prison, cell); +} + +/*----------------------------------------------------------------*/ + +/* * A global list of pools that uses a struct mapped_device as a key. */ static struct dm_thin_pool_table { @@ -330,14 +405,20 @@ static void requeue_io(struct thin_c *tc) * target. */ +static bool block_size_is_power_of_two(struct pool *pool) +{ + return pool->sectors_per_block_shift >= 0; +} + static dm_block_t get_bio_block(struct thin_c *tc, struct bio *bio) { + struct pool *pool = tc->pool; sector_t block_nr = bio->bi_sector; - if (tc->pool->sectors_per_block_shift < 0) - (void) sector_div(block_nr, tc->pool->sectors_per_block); + if (block_size_is_power_of_two(pool)) + block_nr >>= pool->sectors_per_block_shift; else - block_nr >>= tc->pool->sectors_per_block_shift; + (void) sector_div(block_nr, pool->sectors_per_block); return block_nr; } @@ -348,12 +429,12 @@ static void remap(struct thin_c *tc, struct bio *bio, dm_block_t block) sector_t bi_sector = bio->bi_sector; bio->bi_bdev = tc->pool_dev->bdev; - if (tc->pool->sectors_per_block_shift < 0) - bio->bi_sector = (block * pool->sectors_per_block) + - sector_div(bi_sector, pool->sectors_per_block); - else + if (block_size_is_power_of_two(pool)) bio->bi_sector = (block << pool->sectors_per_block_shift) | (bi_sector & (pool->sectors_per_block - 1)); + else + bio->bi_sector = (block * pool->sectors_per_block) + + sector_div(bi_sector, pool->sectors_per_block); } static void remap_to_origin(struct thin_c *tc, struct bio *bio) @@ -420,15 +501,6 @@ static void remap_and_issue(struct thin_c *tc, struct bio *bio, issue(tc, bio); } -/* - * wake_worker() is used when new work is queued and when pool_resume is - * ready to continue deferred IO processing. - */ -static void wake_worker(struct pool *pool) -{ - queue_work(pool->wq, &pool->worker); -} - /*----------------------------------------------------------------*/ /* @@ -515,14 +587,14 @@ static void cell_defer(struct thin_c *tc, struct dm_bio_prison_cell *cell) unsigned long flags; spin_lock_irqsave(&pool->lock, flags); - dm_cell_release(cell, &pool->deferred_bios); + cell_release(pool, cell, &pool->deferred_bios); spin_unlock_irqrestore(&tc->pool->lock, flags); wake_worker(pool); } /* - * Same as cell_defer except it omits the original holder of the cell. + * Same as cell_defer above, except it omits the original holder of the cell. */ static void cell_defer_no_holder(struct thin_c *tc, struct dm_bio_prison_cell *cell) { @@ -530,7 +602,7 @@ static void cell_defer_no_holder(struct thin_c *tc, struct dm_bio_prison_cell *c unsigned long flags; spin_lock_irqsave(&pool->lock, flags); - dm_cell_release_no_holder(cell, &pool->deferred_bios); + cell_release_no_holder(pool, cell, &pool->deferred_bios); spin_unlock_irqrestore(&pool->lock, flags); wake_worker(pool); @@ -540,13 +612,15 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m) { if (m->bio) m->bio->bi_end_io = m->saved_bi_end_io; - dm_cell_error(m->cell); + cell_error(m->tc->pool, m->cell); list_del(&m->list); mempool_free(m, m->tc->pool->mapping_pool); } + static void process_prepared_mapping(struct dm_thin_new_mapping *m) { struct thin_c *tc = m->tc; + struct pool *pool = tc->pool; struct bio *bio; int r; @@ -555,7 +629,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) bio->bi_end_io = m->saved_bi_end_io; if (m->err) { - dm_cell_error(m->cell); + cell_error(pool, m->cell); goto out; } @@ -567,7 +641,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) r = dm_thin_insert_block(tc->td, m->virt_block, m->data_block); if (r) { DMERR_LIMIT("dm_thin_insert_block() failed"); - dm_cell_error(m->cell); + cell_error(pool, m->cell); goto out; } @@ -585,7 +659,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) out: list_del(&m->list); - mempool_free(m, tc->pool->mapping_pool); + mempool_free(m, pool->mapping_pool); } static void process_prepared_discard_fail(struct dm_thin_new_mapping *m) @@ -736,7 +810,7 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block, if (r < 0) { mempool_free(m, pool->mapping_pool); DMERR_LIMIT("dm_kcopyd_copy() failed"); - dm_cell_error(cell); + cell_error(pool, cell); } } } @@ -802,7 +876,7 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block, if (r < 0) { mempool_free(m, pool->mapping_pool); DMERR_LIMIT("dm_kcopyd_zero() failed"); - dm_cell_error(cell); + cell_error(pool, cell); } } } @@ -908,13 +982,13 @@ static void retry_on_resume(struct bio *bio) spin_unlock_irqrestore(&pool->lock, flags); } -static void no_space(struct dm_bio_prison_cell *cell) +static void no_space(struct pool *pool, struct dm_bio_prison_cell *cell) { struct bio *bio; struct bio_list bios; bio_list_init(&bios); - dm_cell_release(cell, &bios); + cell_release(pool, cell, &bios); while ((bio = bio_list_pop(&bios))) retry_on_resume(bio); @@ -932,7 +1006,7 @@ static void process_discard(struct thin_c *tc, struct bio *bio) struct dm_thin_new_mapping *m; build_virtual_key(tc->td, block, &key); - if (dm_bio_detain(tc->pool->prison, &key, bio, &cell)) + if (bio_detain(tc->pool, &key, bio, &cell)) return; r = dm_thin_find_block(tc->td, block, 1, &lookup_result); @@ -944,7 +1018,7 @@ static void process_discard(struct thin_c *tc, struct bio *bio) * on this block. */ build_data_key(tc->td, lookup_result.block, &key2); - if (dm_bio_detain(tc->pool->prison, &key2, bio, &cell2)) { + if (bio_detain(tc->pool, &key2, bio, &cell2)) { cell_defer_no_holder(tc, cell); break; } @@ -1020,13 +1094,13 @@ static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block, break; case -ENOSPC: - no_space(cell); + no_space(tc->pool, cell); break; default: DMERR_LIMIT("%s: alloc_data_block() failed: error = %d", __func__, r); - dm_cell_error(cell); + cell_error(tc->pool, cell); break; } } @@ -1044,7 +1118,7 @@ static void process_shared_bio(struct thin_c *tc, struct bio *bio, * of being broken so we have nothing further to do here. */ build_data_key(tc->td, lookup_result->block, &key); - if (dm_bio_detain(pool->prison, &key, bio, &cell)) + if (bio_detain(pool, &key, bio, &cell)) return; if (bio_data_dir(bio) == WRITE && bio->bi_size) @@ -1065,12 +1139,13 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block { int r; dm_block_t data_block; + struct pool *pool = tc->pool; /* * Remap empty bios (flushes) immediately, without provisioning. */ if (!bio->bi_size) { - inc_all_io_entry(tc->pool, bio); + inc_all_io_entry(pool, bio); cell_defer_no_holder(tc, cell); remap_and_issue(tc, bio, 0); @@ -1097,14 +1172,14 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block break; case -ENOSPC: - no_space(cell); + no_space(pool, cell); break; default: DMERR_LIMIT("%s: alloc_data_block() failed: error = %d", __func__, r); - set_pool_mode(tc->pool, PM_READ_ONLY); - dm_cell_error(cell); + set_pool_mode(pool, PM_READ_ONLY); + cell_error(pool, cell); break; } } @@ -1112,6 +1187,7 @@ static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block static void process_bio(struct thin_c *tc, struct bio *bio) { int r; + struct pool *pool = tc->pool; dm_block_t block = get_bio_block(tc, bio); struct dm_bio_prison_cell *cell; struct dm_cell_key key; @@ -1122,7 +1198,7 @@ static void process_bio(struct thin_c *tc, struct bio *bio) * being provisioned so we have nothing further to do here. */ build_virtual_key(tc->td, block, &key); - if (dm_bio_detain(tc->pool->prison, &key, bio, &cell)) + if (bio_detain(pool, &key, bio, &cell)) return; r = dm_thin_find_block(tc->td, block, 1, &lookup_result); @@ -1130,9 +1206,9 @@ static void process_bio(struct thin_c *tc, struct bio *bio) case 0: if (lookup_result.shared) { process_shared_bio(tc, bio, block, &lookup_result); - cell_defer_no_holder(tc, cell); + cell_defer_no_holder(tc, cell); /* FIXME: pass this cell into process_shared? */ } else { - inc_all_io_entry(tc->pool, bio); + inc_all_io_entry(pool, bio); cell_defer_no_holder(tc, cell); remap_and_issue(tc, bio, lookup_result.block); @@ -1141,7 +1217,7 @@ static void process_bio(struct thin_c *tc, struct bio *bio) case -ENODATA: if (bio_data_dir(bio) == READ && tc->origin_dev) { - inc_all_io_entry(tc->pool, bio); + inc_all_io_entry(pool, bio); cell_defer_no_holder(tc, cell); remap_to_origin_and_issue(tc, bio); @@ -1378,7 +1454,8 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) dm_block_t block = get_bio_block(tc, bio); struct dm_thin_device *td = tc->td; struct dm_thin_lookup_result result; - struct dm_bio_prison_cell *cell1, *cell2; + struct dm_bio_prison_cell cell1, cell2; + struct dm_bio_prison_cell *cell_result; struct dm_cell_key key; thin_hook_bio(tc, bio); @@ -1420,18 +1497,18 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) } build_virtual_key(tc->td, block, &key); - if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1)) + if (dm_bio_detain(tc->pool->prison, &key, bio, &cell1, &cell_result)) return DM_MAPIO_SUBMITTED; build_data_key(tc->td, result.block, &key); - if (dm_bio_detain(tc->pool->prison, &key, bio, &cell2)) { - cell_defer_no_holder(tc, cell1); + if (dm_bio_detain(tc->pool->prison, &key, bio, &cell2, &cell_result)) { + cell_defer_no_holder_no_free(tc, &cell1); return DM_MAPIO_SUBMITTED; } inc_all_io_entry(tc->pool, bio); - cell_defer_no_holder(tc, cell2); - cell_defer_no_holder(tc, cell1); + cell_defer_no_holder_no_free(tc, &cell2); + cell_defer_no_holder_no_free(tc, &cell1); remap(tc, bio, result.block); return DM_MAPIO_REMAPPED; @@ -1636,7 +1713,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, goto bad_prison; } - pool->copier = dm_kcopyd_client_create(); + pool->copier = dm_kcopyd_client_create(&dm_kcopyd_throttle); if (IS_ERR(pool->copier)) { r = PTR_ERR(pool->copier); *error = "Error creating pool's kcopyd client"; @@ -1938,7 +2015,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) pt->data_dev = data_dev; pt->low_water_blocks = low_water_blocks; pt->adjusted_pf = pt->requested_pf = pf; - ti->num_flush_requests = 1; + ti->num_flush_bios = 1; /* * Only need to enable discards if the pool should pass @@ -1946,7 +2023,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) * processing will cause mappings to be removed from the btree. */ if (pf.discard_enabled && pf.discard_passdown) { - ti->num_discard_requests = 1; + ti->num_discard_bios = 1; /* * Setting 'discards_supported' circumvents the normal @@ -2299,8 +2376,8 @@ static void emit_flags(struct pool_features *pf, char *result, * <transaction id> <used metadata sectors>/<total metadata sectors> * <used data sectors>/<total data sectors> <held metadata root> */ -static int pool_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void pool_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { int r; unsigned sz = 0; @@ -2326,32 +2403,41 @@ static int pool_status(struct dm_target *ti, status_type_t type, if (!(status_flags & DM_STATUS_NOFLUSH_FLAG) && !dm_suspended(ti)) (void) commit_or_fallback(pool); - r = dm_pool_get_metadata_transaction_id(pool->pmd, - &transaction_id); - if (r) - return r; + r = dm_pool_get_metadata_transaction_id(pool->pmd, &transaction_id); + if (r) { + DMERR("dm_pool_get_metadata_transaction_id returned %d", r); + goto err; + } - r = dm_pool_get_free_metadata_block_count(pool->pmd, - &nr_free_blocks_metadata); - if (r) - return r; + r = dm_pool_get_free_metadata_block_count(pool->pmd, &nr_free_blocks_metadata); + if (r) { + DMERR("dm_pool_get_free_metadata_block_count returned %d", r); + goto err; + } r = dm_pool_get_metadata_dev_size(pool->pmd, &nr_blocks_metadata); - if (r) - return r; + if (r) { + DMERR("dm_pool_get_metadata_dev_size returned %d", r); + goto err; + } - r = dm_pool_get_free_block_count(pool->pmd, - &nr_free_blocks_data); - if (r) - return r; + r = dm_pool_get_free_block_count(pool->pmd, &nr_free_blocks_data); + if (r) { + DMERR("dm_pool_get_free_block_count returned %d", r); + goto err; + } r = dm_pool_get_data_dev_size(pool->pmd, &nr_blocks_data); - if (r) - return r; + if (r) { + DMERR("dm_pool_get_data_dev_size returned %d", r); + goto err; + } r = dm_pool_get_metadata_snap(pool->pmd, &held_root); - if (r) - return r; + if (r) { + DMERR("dm_pool_get_metadata_snap returned %d", r); + goto err; + } DMEMIT("%llu %llu/%llu %llu/%llu ", (unsigned long long)transaction_id, @@ -2388,8 +2474,10 @@ static int pool_status(struct dm_target *ti, status_type_t type, emit_flags(&pt->requested_pf, result, sz, maxlen); break; } + return; - return 0; +err: + DMEMIT("Error"); } static int pool_iterate_devices(struct dm_target *ti, @@ -2414,11 +2502,6 @@ static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm, return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); } -static bool block_size_is_power_of_two(struct pool *pool) -{ - return pool->sectors_per_block_shift >= 0; -} - static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits) { struct pool *pool = pt->pool; @@ -2432,15 +2515,8 @@ static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits) if (pt->adjusted_pf.discard_passdown) { data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits; limits->discard_granularity = data_limits->discard_granularity; - } else if (block_size_is_power_of_two(pool)) + } else limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT; - else - /* - * Use largest power of 2 that is a factor of sectors_per_block - * but at least DATA_DEV_BLOCK_SIZE_MIN_SECTORS. - */ - limits->discard_granularity = max(1 << (ffs(pool->sectors_per_block) - 1), - DATA_DEV_BLOCK_SIZE_MIN_SECTORS) << SECTOR_SHIFT; } static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) @@ -2468,7 +2544,7 @@ static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 6, 0}, + .version = {1, 6, 1}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -2588,17 +2664,17 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) if (r) goto bad_thin_open; - ti->num_flush_requests = 1; + ti->num_flush_bios = 1; ti->flush_supported = true; ti->per_bio_data_size = sizeof(struct dm_thin_endio_hook); /* In case the pool supports discards, pass them on. */ if (tc->pool->pf.discard_enabled) { ti->discards_supported = true; - ti->num_discard_requests = 1; + ti->num_discard_bios = 1; ti->discard_zeroes_data_unsupported = true; - /* Discard requests must be split on a block boundary */ - ti->split_discard_requests = true; + /* Discard bios must be split on a block boundary */ + ti->split_discard_bios = true; } dm_put(pool_md); @@ -2676,8 +2752,8 @@ static void thin_postsuspend(struct dm_target *ti) /* * <nr mapped sectors> <highest mapped sector> */ -static int thin_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void thin_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { int r; ssize_t sz = 0; @@ -2687,7 +2763,7 @@ static int thin_status(struct dm_target *ti, status_type_t type, if (get_pool_mode(tc->pool) == PM_FAIL) { DMEMIT("Fail"); - return 0; + return; } if (!tc->td) @@ -2696,12 +2772,16 @@ static int thin_status(struct dm_target *ti, status_type_t type, switch (type) { case STATUSTYPE_INFO: r = dm_thin_get_mapped_count(tc->td, &mapped); - if (r) - return r; + if (r) { + DMERR("dm_thin_get_mapped_count returned %d", r); + goto err; + } r = dm_thin_get_highest_mapped_block(tc->td, &highest); - if (r < 0) - return r; + if (r < 0) { + DMERR("dm_thin_get_highest_mapped_block returned %d", r); + goto err; + } DMEMIT("%llu ", mapped * tc->pool->sectors_per_block); if (r) @@ -2721,7 +2801,10 @@ static int thin_status(struct dm_target *ti, status_type_t type, } } - return 0; + return; + +err: + DMEMIT("Error"); } static int thin_iterate_devices(struct dm_target *ti, @@ -2748,7 +2831,7 @@ static int thin_iterate_devices(struct dm_target *ti, static struct target_type thin_target = { .name = "thin", - .version = {1, 7, 0}, + .version = {1, 7, 1}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c index 52cde982164..6ad538375c3 100644 --- a/drivers/md/dm-verity.c +++ b/drivers/md/dm-verity.c @@ -508,8 +508,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio) /* * Status: V (valid) or C (corruption found) */ -static int verity_status(struct dm_target *ti, status_type_t type, - unsigned status_flags, char *result, unsigned maxlen) +static void verity_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen) { struct dm_verity *v = ti->private; unsigned sz = 0; @@ -540,8 +540,6 @@ static int verity_status(struct dm_target *ti, status_type_t type, DMEMIT("%02x", v->salt[x]); break; } - - return 0; } static int verity_ioctl(struct dm_target *ti, unsigned cmd, @@ -860,7 +858,7 @@ bad: static struct target_type verity_target = { .name = "verity", - .version = {1, 1, 0}, + .version = {1, 1, 1}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c index 69a5c3b3b34..c99003e0d47 100644 --- a/drivers/md/dm-zero.c +++ b/drivers/md/dm-zero.c @@ -25,7 +25,7 @@ static int zero_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* * Silently drop discards, avoiding -EOPNOTSUPP. */ - ti->num_discard_requests = 1; + ti->num_discard_bios = 1; return 0; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index bb2cd3ce9b0..7e469260fe5 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -163,7 +163,6 @@ struct mapped_device { * io objects are allocated from here. */ mempool_t *io_pool; - mempool_t *tio_pool; struct bio_set *bs; @@ -197,7 +196,6 @@ struct mapped_device { */ struct dm_md_mempools { mempool_t *io_pool; - mempool_t *tio_pool; struct bio_set *bs; }; @@ -205,12 +203,6 @@ struct dm_md_mempools { static struct kmem_cache *_io_cache; static struct kmem_cache *_rq_tio_cache; -/* - * Unused now, and needs to be deleted. But since io_pool is overloaded and it's - * still used for _io_cache, I'm leaving this for a later cleanup - */ -static struct kmem_cache *_rq_bio_info_cache; - static int __init local_init(void) { int r = -ENOMEM; @@ -224,13 +216,9 @@ static int __init local_init(void) if (!_rq_tio_cache) goto out_free_io_cache; - _rq_bio_info_cache = KMEM_CACHE(dm_rq_clone_bio_info, 0); - if (!_rq_bio_info_cache) - goto out_free_rq_tio_cache; - r = dm_uevent_init(); if (r) - goto out_free_rq_bio_info_cache; + goto out_free_rq_tio_cache; _major = major; r = register_blkdev(_major, _name); @@ -244,8 +232,6 @@ static int __init local_init(void) out_uevent_exit: dm_uevent_exit(); -out_free_rq_bio_info_cache: - kmem_cache_destroy(_rq_bio_info_cache); out_free_rq_tio_cache: kmem_cache_destroy(_rq_tio_cache); out_free_io_cache: @@ -256,7 +242,6 @@ out_free_io_cache: static void local_exit(void) { - kmem_cache_destroy(_rq_bio_info_cache); kmem_cache_destroy(_rq_tio_cache); kmem_cache_destroy(_io_cache); unregister_blkdev(_major, _name); @@ -448,12 +433,12 @@ static void free_tio(struct mapped_device *md, struct dm_target_io *tio) static struct dm_rq_target_io *alloc_rq_tio(struct mapped_device *md, gfp_t gfp_mask) { - return mempool_alloc(md->tio_pool, gfp_mask); + return mempool_alloc(md->io_pool, gfp_mask); } static void free_rq_tio(struct dm_rq_target_io *tio) { - mempool_free(tio, tio->md->tio_pool); + mempool_free(tio, tio->md->io_pool); } static int md_in_flight(struct mapped_device *md) @@ -985,12 +970,13 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len) } EXPORT_SYMBOL_GPL(dm_set_target_max_io_len); -static void __map_bio(struct dm_target *ti, struct dm_target_io *tio) +static void __map_bio(struct dm_target_io *tio) { int r; sector_t sector; struct mapped_device *md; struct bio *clone = &tio->clone; + struct dm_target *ti = tio->ti; clone->bi_end_io = clone_endio; clone->bi_private = tio; @@ -1031,32 +1017,54 @@ struct clone_info { unsigned short idx; }; +static void bio_setup_sector(struct bio *bio, sector_t sector, sector_t len) +{ + bio->bi_sector = sector; + bio->bi_size = to_bytes(len); +} + +static void bio_setup_bv(struct bio *bio, unsigned short idx, unsigned short bv_count) +{ + bio->bi_idx = idx; + bio->bi_vcnt = idx + bv_count; + bio->bi_flags &= ~(1 << BIO_SEG_VALID); +} + +static void clone_bio_integrity(struct bio *bio, struct bio *clone, + unsigned short idx, unsigned len, unsigned offset, + unsigned trim) +{ + if (!bio_integrity(bio)) + return; + + bio_integrity_clone(clone, bio, GFP_NOIO); + + if (trim) + bio_integrity_trim(clone, bio_sector_offset(bio, idx, offset), len); +} + /* * Creates a little bio that just does part of a bvec. */ -static void split_bvec(struct dm_target_io *tio, struct bio *bio, - sector_t sector, unsigned short idx, unsigned int offset, - unsigned int len, struct bio_set *bs) +static void clone_split_bio(struct dm_target_io *tio, struct bio *bio, + sector_t sector, unsigned short idx, + unsigned offset, unsigned len) { struct bio *clone = &tio->clone; struct bio_vec *bv = bio->bi_io_vec + idx; *clone->bi_io_vec = *bv; - clone->bi_sector = sector; + bio_setup_sector(clone, sector, len); + clone->bi_bdev = bio->bi_bdev; clone->bi_rw = bio->bi_rw; clone->bi_vcnt = 1; - clone->bi_size = to_bytes(len); clone->bi_io_vec->bv_offset = offset; clone->bi_io_vec->bv_len = clone->bi_size; clone->bi_flags |= 1 << BIO_CLONED; - if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO); - bio_integrity_trim(clone, - bio_sector_offset(bio, idx, offset), len); - } + clone_bio_integrity(bio, clone, idx, len, offset, 1); } /* @@ -1064,29 +1072,23 @@ static void split_bvec(struct dm_target_io *tio, struct bio *bio, */ static void clone_bio(struct dm_target_io *tio, struct bio *bio, sector_t sector, unsigned short idx, - unsigned short bv_count, unsigned int len, - struct bio_set *bs) + unsigned short bv_count, unsigned len) { struct bio *clone = &tio->clone; + unsigned trim = 0; __bio_clone(clone, bio); - clone->bi_sector = sector; - clone->bi_idx = idx; - clone->bi_vcnt = idx + bv_count; - clone->bi_size = to_bytes(len); - clone->bi_flags &= ~(1 << BIO_SEG_VALID); - - if (bio_integrity(bio)) { - bio_integrity_clone(clone, bio, GFP_NOIO); - - if (idx != bio->bi_idx || clone->bi_size < bio->bi_size) - bio_integrity_trim(clone, - bio_sector_offset(bio, idx, 0), len); - } + bio_setup_sector(clone, sector, len); + bio_setup_bv(clone, idx, bv_count); + + if (idx != bio->bi_idx || clone->bi_size < bio->bi_size) + trim = 1; + clone_bio_integrity(bio, clone, idx, len, 0, trim); } static struct dm_target_io *alloc_tio(struct clone_info *ci, - struct dm_target *ti, int nr_iovecs) + struct dm_target *ti, int nr_iovecs, + unsigned target_bio_nr) { struct dm_target_io *tio; struct bio *clone; @@ -1097,96 +1099,104 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci, tio->io = ci->io; tio->ti = ti; memset(&tio->info, 0, sizeof(tio->info)); - tio->target_request_nr = 0; + tio->target_bio_nr = target_bio_nr; return tio; } -static void __issue_target_request(struct clone_info *ci, struct dm_target *ti, - unsigned request_nr, sector_t len) +static void __clone_and_map_simple_bio(struct clone_info *ci, + struct dm_target *ti, + unsigned target_bio_nr, sector_t len) { - struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs); + struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs, target_bio_nr); struct bio *clone = &tio->clone; - tio->target_request_nr = request_nr; - /* * Discard requests require the bio's inline iovecs be initialized. * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush * and discard, so no need for concern about wasted bvec allocations. */ - __bio_clone(clone, ci->bio); - if (len) { - clone->bi_sector = ci->sector; - clone->bi_size = to_bytes(len); - } + if (len) + bio_setup_sector(clone, ci->sector, len); - __map_bio(ti, tio); + __map_bio(tio); } -static void __issue_target_requests(struct clone_info *ci, struct dm_target *ti, - unsigned num_requests, sector_t len) +static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, + unsigned num_bios, sector_t len) { - unsigned request_nr; + unsigned target_bio_nr; - for (request_nr = 0; request_nr < num_requests; request_nr++) - __issue_target_request(ci, ti, request_nr, len); + for (target_bio_nr = 0; target_bio_nr < num_bios; target_bio_nr++) + __clone_and_map_simple_bio(ci, ti, target_bio_nr, len); } -static int __clone_and_map_empty_flush(struct clone_info *ci) +static int __send_empty_flush(struct clone_info *ci) { unsigned target_nr = 0; struct dm_target *ti; BUG_ON(bio_has_data(ci->bio)); while ((ti = dm_table_get_target(ci->map, target_nr++))) - __issue_target_requests(ci, ti, ti->num_flush_requests, 0); + __send_duplicate_bios(ci, ti, ti->num_flush_bios, 0); return 0; } -/* - * Perform all io with a single clone. - */ -static void __clone_and_map_simple(struct clone_info *ci, struct dm_target *ti) +static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti, + sector_t sector, int nr_iovecs, + unsigned short idx, unsigned short bv_count, + unsigned offset, unsigned len, + unsigned split_bvec) { struct bio *bio = ci->bio; struct dm_target_io *tio; + unsigned target_bio_nr; + unsigned num_target_bios = 1; + + /* + * Does the target want to receive duplicate copies of the bio? + */ + if (bio_data_dir(bio) == WRITE && ti->num_write_bios) + num_target_bios = ti->num_write_bios(ti, bio); - tio = alloc_tio(ci, ti, bio->bi_max_vecs); - clone_bio(tio, bio, ci->sector, ci->idx, bio->bi_vcnt - ci->idx, - ci->sector_count, ci->md->bs); - __map_bio(ti, tio); - ci->sector_count = 0; + for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) { + tio = alloc_tio(ci, ti, nr_iovecs, target_bio_nr); + if (split_bvec) + clone_split_bio(tio, bio, sector, idx, offset, len); + else + clone_bio(tio, bio, sector, idx, bv_count, len); + __map_bio(tio); + } } -typedef unsigned (*get_num_requests_fn)(struct dm_target *ti); +typedef unsigned (*get_num_bios_fn)(struct dm_target *ti); -static unsigned get_num_discard_requests(struct dm_target *ti) +static unsigned get_num_discard_bios(struct dm_target *ti) { - return ti->num_discard_requests; + return ti->num_discard_bios; } -static unsigned get_num_write_same_requests(struct dm_target *ti) +static unsigned get_num_write_same_bios(struct dm_target *ti) { - return ti->num_write_same_requests; + return ti->num_write_same_bios; } typedef bool (*is_split_required_fn)(struct dm_target *ti); static bool is_split_required_for_discard(struct dm_target *ti) { - return ti->split_discard_requests; + return ti->split_discard_bios; } -static int __clone_and_map_changing_extent_only(struct clone_info *ci, - get_num_requests_fn get_num_requests, - is_split_required_fn is_split_required) +static int __send_changing_extent_only(struct clone_info *ci, + get_num_bios_fn get_num_bios, + is_split_required_fn is_split_required) { struct dm_target *ti; sector_t len; - unsigned num_requests; + unsigned num_bios; do { ti = dm_table_find_target(ci->map, ci->sector); @@ -1199,8 +1209,8 @@ static int __clone_and_map_changing_extent_only(struct clone_info *ci, * reconfiguration might also have changed that since the * check was performed. */ - num_requests = get_num_requests ? get_num_requests(ti) : 0; - if (!num_requests) + num_bios = get_num_bios ? get_num_bios(ti) : 0; + if (!num_bios) return -EOPNOTSUPP; if (is_split_required && !is_split_required(ti)) @@ -1208,7 +1218,7 @@ static int __clone_and_map_changing_extent_only(struct clone_info *ci, else len = min(ci->sector_count, max_io_len(ci->sector, ti)); - __issue_target_requests(ci, ti, num_requests, len); + __send_duplicate_bios(ci, ti, num_bios, len); ci->sector += len; } while (ci->sector_count -= len); @@ -1216,108 +1226,129 @@ static int __clone_and_map_changing_extent_only(struct clone_info *ci, return 0; } -static int __clone_and_map_discard(struct clone_info *ci) +static int __send_discard(struct clone_info *ci) { - return __clone_and_map_changing_extent_only(ci, get_num_discard_requests, - is_split_required_for_discard); + return __send_changing_extent_only(ci, get_num_discard_bios, + is_split_required_for_discard); } -static int __clone_and_map_write_same(struct clone_info *ci) +static int __send_write_same(struct clone_info *ci) { - return __clone_and_map_changing_extent_only(ci, get_num_write_same_requests, NULL); + return __send_changing_extent_only(ci, get_num_write_same_bios, NULL); } -static int __clone_and_map(struct clone_info *ci) +/* + * Find maximum number of sectors / bvecs we can process with a single bio. + */ +static sector_t __len_within_target(struct clone_info *ci, sector_t max, int *idx) { struct bio *bio = ci->bio; - struct dm_target *ti; - sector_t len = 0, max; - struct dm_target_io *tio; - - if (unlikely(bio->bi_rw & REQ_DISCARD)) - return __clone_and_map_discard(ci); - else if (unlikely(bio->bi_rw & REQ_WRITE_SAME)) - return __clone_and_map_write_same(ci); + sector_t bv_len, total_len = 0; - ti = dm_table_find_target(ci->map, ci->sector); - if (!dm_target_is_valid(ti)) - return -EIO; + for (*idx = ci->idx; max && (*idx < bio->bi_vcnt); (*idx)++) { + bv_len = to_sector(bio->bi_io_vec[*idx].bv_len); - max = max_io_len(ci->sector, ti); + if (bv_len > max) + break; - if (ci->sector_count <= max) { - /* - * Optimise for the simple case where we can do all of - * the remaining io with a single clone. - */ - __clone_and_map_simple(ci, ti); + max -= bv_len; + total_len += bv_len; + } - } else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) { - /* - * There are some bvecs that don't span targets. - * Do as many of these as possible. - */ - int i; - sector_t remaining = max; - sector_t bv_len; + return total_len; +} - for (i = ci->idx; remaining && (i < bio->bi_vcnt); i++) { - bv_len = to_sector(bio->bi_io_vec[i].bv_len); +static int __split_bvec_across_targets(struct clone_info *ci, + struct dm_target *ti, sector_t max) +{ + struct bio *bio = ci->bio; + struct bio_vec *bv = bio->bi_io_vec + ci->idx; + sector_t remaining = to_sector(bv->bv_len); + unsigned offset = 0; + sector_t len; - if (bv_len > remaining) - break; + do { + if (offset) { + ti = dm_table_find_target(ci->map, ci->sector); + if (!dm_target_is_valid(ti)) + return -EIO; - remaining -= bv_len; - len += bv_len; + max = max_io_len(ci->sector, ti); } - tio = alloc_tio(ci, ti, bio->bi_max_vecs); - clone_bio(tio, bio, ci->sector, ci->idx, i - ci->idx, len, - ci->md->bs); - __map_bio(ti, tio); + len = min(remaining, max); + + __clone_and_map_data_bio(ci, ti, ci->sector, 1, ci->idx, 0, + bv->bv_offset + offset, len, 1); ci->sector += len; ci->sector_count -= len; - ci->idx = i; + offset += to_bytes(len); + } while (remaining -= len); - } else { - /* - * Handle a bvec that must be split between two or more targets. - */ - struct bio_vec *bv = bio->bi_io_vec + ci->idx; - sector_t remaining = to_sector(bv->bv_len); - unsigned int offset = 0; + ci->idx++; + + return 0; +} + +/* + * Select the correct strategy for processing a non-flush bio. + */ +static int __split_and_process_non_flush(struct clone_info *ci) +{ + struct bio *bio = ci->bio; + struct dm_target *ti; + sector_t len, max; + int idx; + + if (unlikely(bio->bi_rw & REQ_DISCARD)) + return __send_discard(ci); + else if (unlikely(bio->bi_rw & REQ_WRITE_SAME)) + return __send_write_same(ci); - do { - if (offset) { - ti = dm_table_find_target(ci->map, ci->sector); - if (!dm_target_is_valid(ti)) - return -EIO; + ti = dm_table_find_target(ci->map, ci->sector); + if (!dm_target_is_valid(ti)) + return -EIO; - max = max_io_len(ci->sector, ti); - } + max = max_io_len(ci->sector, ti); - len = min(remaining, max); + /* + * Optimise for the simple case where we can do all of + * the remaining io with a single clone. + */ + if (ci->sector_count <= max) { + __clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs, + ci->idx, bio->bi_vcnt - ci->idx, 0, + ci->sector_count, 0); + ci->sector_count = 0; + return 0; + } - tio = alloc_tio(ci, ti, 1); - split_bvec(tio, bio, ci->sector, ci->idx, - bv->bv_offset + offset, len, ci->md->bs); + /* + * There are some bvecs that don't span targets. + * Do as many of these as possible. + */ + if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) { + len = __len_within_target(ci, max, &idx); - __map_bio(ti, tio); + __clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs, + ci->idx, idx - ci->idx, 0, len, 0); - ci->sector += len; - ci->sector_count -= len; - offset += to_bytes(len); - } while (remaining -= len); + ci->sector += len; + ci->sector_count -= len; + ci->idx = idx; - ci->idx++; + return 0; } - return 0; + /* + * Handle a bvec that must be split between two or more targets. + */ + return __split_bvec_across_targets(ci, ti, max); } /* - * Split the bio into several clones and submit it to targets. + * Entry point to split a bio into clones and submit them to the targets. */ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio) { @@ -1341,16 +1372,17 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio) ci.idx = bio->bi_idx; start_io_acct(ci.io); + if (bio->bi_rw & REQ_FLUSH) { ci.bio = &ci.md->flush_bio; ci.sector_count = 0; - error = __clone_and_map_empty_flush(&ci); + error = __send_empty_flush(&ci); /* dec_pending submits any data associated with flush */ } else { ci.bio = bio; ci.sector_count = bio_sectors(bio); while (ci.sector_count && !error) - error = __clone_and_map(&ci); + error = __split_and_process_non_flush(&ci); } /* drop the extra reference count */ @@ -1923,8 +1955,6 @@ static void free_dev(struct mapped_device *md) unlock_fs(md); bdput(md->bdev); destroy_workqueue(md->wq); - if (md->tio_pool) - mempool_destroy(md->tio_pool); if (md->io_pool) mempool_destroy(md->io_pool); if (md->bs) @@ -1947,24 +1977,33 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t) { struct dm_md_mempools *p = dm_table_get_md_mempools(t); - if (md->io_pool && (md->tio_pool || dm_table_get_type(t) == DM_TYPE_BIO_BASED) && md->bs) { - /* - * The md already has necessary mempools. Reload just the - * bioset because front_pad may have changed because - * a different table was loaded. - */ - bioset_free(md->bs); - md->bs = p->bs; - p->bs = NULL; + if (md->io_pool && md->bs) { + /* The md already has necessary mempools. */ + if (dm_table_get_type(t) == DM_TYPE_BIO_BASED) { + /* + * Reload bioset because front_pad may have changed + * because a different table was loaded. + */ + bioset_free(md->bs); + md->bs = p->bs; + p->bs = NULL; + } else if (dm_table_get_type(t) == DM_TYPE_REQUEST_BASED) { + /* + * There's no need to reload with request-based dm + * because the size of front_pad doesn't change. + * Note for future: If you are to reload bioset, + * prep-ed requests in the queue may refer + * to bio from the old bioset, so you must walk + * through the queue to unprep. + */ + } goto out; } - BUG_ON(!p || md->io_pool || md->tio_pool || md->bs); + BUG_ON(!p || md->io_pool || md->bs); md->io_pool = p->io_pool; p->io_pool = NULL; - md->tio_pool = p->tio_pool; - p->tio_pool = NULL; md->bs = p->bs; p->bs = NULL; @@ -2395,7 +2434,7 @@ static void dm_queue_flush(struct mapped_device *md) */ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) { - struct dm_table *live_map, *map = ERR_PTR(-EINVAL); + struct dm_table *live_map = NULL, *map = ERR_PTR(-EINVAL); struct queue_limits limits; int r; @@ -2418,10 +2457,12 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table) dm_table_put(live_map); } - r = dm_calculate_queue_limits(table, &limits); - if (r) { - map = ERR_PTR(r); - goto out; + if (!live_map) { + r = dm_calculate_queue_limits(table, &limits); + if (r) { + map = ERR_PTR(r); + goto out; + } } map = __bind(md, table, &limits); @@ -2719,52 +2760,42 @@ EXPORT_SYMBOL_GPL(dm_noflush_suspending); struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size) { - struct dm_md_mempools *pools = kmalloc(sizeof(*pools), GFP_KERNEL); - unsigned int pool_size = (type == DM_TYPE_BIO_BASED) ? 16 : MIN_IOS; + struct dm_md_mempools *pools = kzalloc(sizeof(*pools), GFP_KERNEL); + struct kmem_cache *cachep; + unsigned int pool_size; + unsigned int front_pad; if (!pools) return NULL; - per_bio_data_size = roundup(per_bio_data_size, __alignof__(struct dm_target_io)); + if (type == DM_TYPE_BIO_BASED) { + cachep = _io_cache; + pool_size = 16; + front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone); + } else if (type == DM_TYPE_REQUEST_BASED) { + cachep = _rq_tio_cache; + pool_size = MIN_IOS; + front_pad = offsetof(struct dm_rq_clone_bio_info, clone); + /* per_bio_data_size is not used. See __bind_mempools(). */ + WARN_ON(per_bio_data_size != 0); + } else + goto out; - pools->io_pool = (type == DM_TYPE_BIO_BASED) ? - mempool_create_slab_pool(MIN_IOS, _io_cache) : - mempool_create_slab_pool(MIN_IOS, _rq_bio_info_cache); + pools->io_pool = mempool_create_slab_pool(MIN_IOS, cachep); if (!pools->io_pool) - goto free_pools_and_out; - - pools->tio_pool = NULL; - if (type == DM_TYPE_REQUEST_BASED) { - pools->tio_pool = mempool_create_slab_pool(MIN_IOS, _rq_tio_cache); - if (!pools->tio_pool) - goto free_io_pool_and_out; - } + goto out; - pools->bs = (type == DM_TYPE_BIO_BASED) ? - bioset_create(pool_size, - per_bio_data_size + offsetof(struct dm_target_io, clone)) : - bioset_create(pool_size, - offsetof(struct dm_rq_clone_bio_info, clone)); + pools->bs = bioset_create(pool_size, front_pad); if (!pools->bs) - goto free_tio_pool_and_out; + goto out; if (integrity && bioset_integrity_create(pools->bs, pool_size)) - goto free_bioset_and_out; + goto out; return pools; -free_bioset_and_out: - bioset_free(pools->bs); - -free_tio_pool_and_out: - if (pools->tio_pool) - mempool_destroy(pools->tio_pool); - -free_io_pool_and_out: - mempool_destroy(pools->io_pool); - -free_pools_and_out: - kfree(pools); +out: + dm_free_md_mempools(pools); return NULL; } @@ -2777,9 +2808,6 @@ void dm_free_md_mempools(struct dm_md_mempools *pools) if (pools->io_pool) mempool_destroy(pools->io_pool); - if (pools->tio_pool) - mempool_destroy(pools->tio_pool); - if (pools->bs) bioset_free(pools->bs); diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig index ceb359050a5..19b26879541 100644 --- a/drivers/md/persistent-data/Kconfig +++ b/drivers/md/persistent-data/Kconfig @@ -1,6 +1,6 @@ config DM_PERSISTENT_DATA tristate - depends on BLK_DEV_DM && EXPERIMENTAL + depends on BLK_DEV_DM select LIBCRC32C select DM_BUFIO ---help--- diff --git a/drivers/md/persistent-data/Makefile b/drivers/md/persistent-data/Makefile index d8e7cb767c1..ff528792c35 100644 --- a/drivers/md/persistent-data/Makefile +++ b/drivers/md/persistent-data/Makefile @@ -1,5 +1,7 @@ obj-$(CONFIG_DM_PERSISTENT_DATA) += dm-persistent-data.o dm-persistent-data-objs := \ + dm-array.o \ + dm-bitset.o \ dm-block-manager.o \ dm-space-map-common.o \ dm-space-map-disk.o \ diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c new file mode 100644 index 00000000000..172147eb1d4 --- /dev/null +++ b/drivers/md/persistent-data/dm-array.c @@ -0,0 +1,808 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-array.h" +#include "dm-space-map.h" +#include "dm-transaction-manager.h" + +#include <linux/export.h> +#include <linux/device-mapper.h> + +#define DM_MSG_PREFIX "array" + +/*----------------------------------------------------------------*/ + +/* + * The array is implemented as a fully populated btree, which points to + * blocks that contain the packed values. This is more space efficient + * than just using a btree since we don't store 1 key per value. + */ +struct array_block { + __le32 csum; + __le32 max_entries; + __le32 nr_entries; + __le32 value_size; + __le64 blocknr; /* Block this node is supposed to live in. */ +} __packed; + +/*----------------------------------------------------------------*/ + +/* + * Validator methods. As usual we calculate a checksum, and also write the + * block location into the header (paranoia about ssds remapping areas by + * mistake). + */ +#define CSUM_XOR 595846735 + +static void array_block_prepare_for_write(struct dm_block_validator *v, + struct dm_block *b, + size_t size_of_block) +{ + struct array_block *bh_le = dm_block_data(b); + + bh_le->blocknr = cpu_to_le64(dm_block_location(b)); + bh_le->csum = cpu_to_le32(dm_bm_checksum(&bh_le->max_entries, + size_of_block - sizeof(__le32), + CSUM_XOR)); +} + +static int array_block_check(struct dm_block_validator *v, + struct dm_block *b, + size_t size_of_block) +{ + struct array_block *bh_le = dm_block_data(b); + __le32 csum_disk; + + if (dm_block_location(b) != le64_to_cpu(bh_le->blocknr)) { + DMERR_LIMIT("array_block_check failed: blocknr %llu != wanted %llu", + (unsigned long long) le64_to_cpu(bh_le->blocknr), + (unsigned long long) dm_block_location(b)); + return -ENOTBLK; + } + + csum_disk = cpu_to_le32(dm_bm_checksum(&bh_le->max_entries, + size_of_block - sizeof(__le32), + CSUM_XOR)); + if (csum_disk != bh_le->csum) { + DMERR_LIMIT("array_block_check failed: csum %u != wanted %u", + (unsigned) le32_to_cpu(csum_disk), + (unsigned) le32_to_cpu(bh_le->csum)); + return -EILSEQ; + } + + return 0; +} + +static struct dm_block_validator array_validator = { + .name = "array", + .prepare_for_write = array_block_prepare_for_write, + .check = array_block_check +}; + +/*----------------------------------------------------------------*/ + +/* + * Functions for manipulating the array blocks. + */ + +/* + * Returns a pointer to a value within an array block. + * + * index - The index into _this_ specific block. + */ +static void *element_at(struct dm_array_info *info, struct array_block *ab, + unsigned index) +{ + unsigned char *entry = (unsigned char *) (ab + 1); + + entry += index * info->value_type.size; + + return entry; +} + +/* + * Utility function that calls one of the value_type methods on every value + * in an array block. + */ +static void on_entries(struct dm_array_info *info, struct array_block *ab, + void (*fn)(void *, const void *)) +{ + unsigned i, nr_entries = le32_to_cpu(ab->nr_entries); + + for (i = 0; i < nr_entries; i++) + fn(info->value_type.context, element_at(info, ab, i)); +} + +/* + * Increment every value in an array block. + */ +static void inc_ablock_entries(struct dm_array_info *info, struct array_block *ab) +{ + struct dm_btree_value_type *vt = &info->value_type; + + if (vt->inc) + on_entries(info, ab, vt->inc); +} + +/* + * Decrement every value in an array block. + */ +static void dec_ablock_entries(struct dm_array_info *info, struct array_block *ab) +{ + struct dm_btree_value_type *vt = &info->value_type; + + if (vt->dec) + on_entries(info, ab, vt->dec); +} + +/* + * Each array block can hold this many values. + */ +static uint32_t calc_max_entries(size_t value_size, size_t size_of_block) +{ + return (size_of_block - sizeof(struct array_block)) / value_size; +} + +/* + * Allocate a new array block. The caller will need to unlock block. + */ +static int alloc_ablock(struct dm_array_info *info, size_t size_of_block, + uint32_t max_entries, + struct dm_block **block, struct array_block **ab) +{ + int r; + + r = dm_tm_new_block(info->btree_info.tm, &array_validator, block); + if (r) + return r; + + (*ab) = dm_block_data(*block); + (*ab)->max_entries = cpu_to_le32(max_entries); + (*ab)->nr_entries = cpu_to_le32(0); + (*ab)->value_size = cpu_to_le32(info->value_type.size); + + return 0; +} + +/* + * Pad an array block out with a particular value. Every instance will + * cause an increment of the value_type. new_nr must always be more than + * the current number of entries. + */ +static void fill_ablock(struct dm_array_info *info, struct array_block *ab, + const void *value, unsigned new_nr) +{ + unsigned i; + uint32_t nr_entries; + struct dm_btree_value_type *vt = &info->value_type; + + BUG_ON(new_nr > le32_to_cpu(ab->max_entries)); + BUG_ON(new_nr < le32_to_cpu(ab->nr_entries)); + + nr_entries = le32_to_cpu(ab->nr_entries); + for (i = nr_entries; i < new_nr; i++) { + if (vt->inc) + vt->inc(vt->context, value); + memcpy(element_at(info, ab, i), value, vt->size); + } + ab->nr_entries = cpu_to_le32(new_nr); +} + +/* + * Remove some entries from the back of an array block. Every value + * removed will be decremented. new_nr must be <= the current number of + * entries. + */ +static void trim_ablock(struct dm_array_info *info, struct array_block *ab, + unsigned new_nr) +{ + unsigned i; + uint32_t nr_entries; + struct dm_btree_value_type *vt = &info->value_type; + + BUG_ON(new_nr > le32_to_cpu(ab->max_entries)); + BUG_ON(new_nr > le32_to_cpu(ab->nr_entries)); + + nr_entries = le32_to_cpu(ab->nr_entries); + for (i = nr_entries; i > new_nr; i--) + if (vt->dec) + vt->dec(vt->context, element_at(info, ab, i - 1)); + ab->nr_entries = cpu_to_le32(new_nr); +} + +/* + * Read locks a block, and coerces it to an array block. The caller must + * unlock 'block' when finished. + */ +static int get_ablock(struct dm_array_info *info, dm_block_t b, + struct dm_block **block, struct array_block **ab) +{ + int r; + + r = dm_tm_read_lock(info->btree_info.tm, b, &array_validator, block); + if (r) + return r; + + *ab = dm_block_data(*block); + return 0; +} + +/* + * Unlocks an array block. + */ +static int unlock_ablock(struct dm_array_info *info, struct dm_block *block) +{ + return dm_tm_unlock(info->btree_info.tm, block); +} + +/*----------------------------------------------------------------*/ + +/* + * Btree manipulation. + */ + +/* + * Looks up an array block in the btree, and then read locks it. + * + * index is the index of the index of the array_block, (ie. the array index + * / max_entries). + */ +static int lookup_ablock(struct dm_array_info *info, dm_block_t root, + unsigned index, struct dm_block **block, + struct array_block **ab) +{ + int r; + uint64_t key = index; + __le64 block_le; + + r = dm_btree_lookup(&info->btree_info, root, &key, &block_le); + if (r) + return r; + + return get_ablock(info, le64_to_cpu(block_le), block, ab); +} + +/* + * Insert an array block into the btree. The block is _not_ unlocked. + */ +static int insert_ablock(struct dm_array_info *info, uint64_t index, + struct dm_block *block, dm_block_t *root) +{ + __le64 block_le = cpu_to_le64(dm_block_location(block)); + + __dm_bless_for_disk(block_le); + return dm_btree_insert(&info->btree_info, *root, &index, &block_le, root); +} + +/* + * Looks up an array block in the btree. Then shadows it, and updates the + * btree to point to this new shadow. 'root' is an input/output parameter + * for both the current root block, and the new one. + */ +static int shadow_ablock(struct dm_array_info *info, dm_block_t *root, + unsigned index, struct dm_block **block, + struct array_block **ab) +{ + int r, inc; + uint64_t key = index; + dm_block_t b; + __le64 block_le; + + /* + * lookup + */ + r = dm_btree_lookup(&info->btree_info, *root, &key, &block_le); + if (r) + return r; + b = le64_to_cpu(block_le); + + /* + * shadow + */ + r = dm_tm_shadow_block(info->btree_info.tm, b, + &array_validator, block, &inc); + if (r) + return r; + + *ab = dm_block_data(*block); + if (inc) + inc_ablock_entries(info, *ab); + + /* + * Reinsert. + * + * The shadow op will often be a noop. Only insert if it really + * copied data. + */ + if (dm_block_location(*block) != b) + r = insert_ablock(info, index, *block, root); + + return r; +} + +/* + * Allocate an new array block, and fill it with some values. + */ +static int insert_new_ablock(struct dm_array_info *info, size_t size_of_block, + uint32_t max_entries, + unsigned block_index, uint32_t nr, + const void *value, dm_block_t *root) +{ + int r; + struct dm_block *block; + struct array_block *ab; + + r = alloc_ablock(info, size_of_block, max_entries, &block, &ab); + if (r) + return r; + + fill_ablock(info, ab, value, nr); + r = insert_ablock(info, block_index, block, root); + unlock_ablock(info, block); + + return r; +} + +static int insert_full_ablocks(struct dm_array_info *info, size_t size_of_block, + unsigned begin_block, unsigned end_block, + unsigned max_entries, const void *value, + dm_block_t *root) +{ + int r = 0; + + for (; !r && begin_block != end_block; begin_block++) + r = insert_new_ablock(info, size_of_block, max_entries, begin_block, max_entries, value, root); + + return r; +} + +/* + * There are a bunch of functions involved with resizing an array. This + * structure holds information that commonly needed by them. Purely here + * to reduce parameter count. + */ +struct resize { + /* + * Describes the array. + */ + struct dm_array_info *info; + + /* + * The current root of the array. This gets updated. + */ + dm_block_t root; + + /* + * Metadata block size. Used to calculate the nr entries in an + * array block. + */ + size_t size_of_block; + + /* + * Maximum nr entries in an array block. + */ + unsigned max_entries; + + /* + * nr of completely full blocks in the array. + * + * 'old' refers to before the resize, 'new' after. + */ + unsigned old_nr_full_blocks, new_nr_full_blocks; + + /* + * Number of entries in the final block. 0 iff only full blocks in + * the array. + */ + unsigned old_nr_entries_in_last_block, new_nr_entries_in_last_block; + + /* + * The default value used when growing the array. + */ + const void *value; +}; + +/* + * Removes a consecutive set of array blocks from the btree. The values + * in block are decremented as a side effect of the btree remove. + * + * begin_index - the index of the first array block to remove. + * end_index - the one-past-the-end value. ie. this block is not removed. + */ +static int drop_blocks(struct resize *resize, unsigned begin_index, + unsigned end_index) +{ + int r; + + while (begin_index != end_index) { + uint64_t key = begin_index++; + r = dm_btree_remove(&resize->info->btree_info, resize->root, + &key, &resize->root); + if (r) + return r; + } + + return 0; +} + +/* + * Calculates how many blocks are needed for the array. + */ +static unsigned total_nr_blocks_needed(unsigned nr_full_blocks, + unsigned nr_entries_in_last_block) +{ + return nr_full_blocks + (nr_entries_in_last_block ? 1 : 0); +} + +/* + * Shrink an array. + */ +static int shrink(struct resize *resize) +{ + int r; + unsigned begin, end; + struct dm_block *block; + struct array_block *ab; + + /* + * Lose some blocks from the back? + */ + if (resize->new_nr_full_blocks < resize->old_nr_full_blocks) { + begin = total_nr_blocks_needed(resize->new_nr_full_blocks, + resize->new_nr_entries_in_last_block); + end = total_nr_blocks_needed(resize->old_nr_full_blocks, + resize->old_nr_entries_in_last_block); + + r = drop_blocks(resize, begin, end); + if (r) + return r; + } + + /* + * Trim the new tail block + */ + if (resize->new_nr_entries_in_last_block) { + r = shadow_ablock(resize->info, &resize->root, + resize->new_nr_full_blocks, &block, &ab); + if (r) + return r; + + trim_ablock(resize->info, ab, resize->new_nr_entries_in_last_block); + unlock_ablock(resize->info, block); + } + + return 0; +} + +/* + * Grow an array. + */ +static int grow_extend_tail_block(struct resize *resize, uint32_t new_nr_entries) +{ + int r; + struct dm_block *block; + struct array_block *ab; + + r = shadow_ablock(resize->info, &resize->root, + resize->old_nr_full_blocks, &block, &ab); + if (r) + return r; + + fill_ablock(resize->info, ab, resize->value, new_nr_entries); + unlock_ablock(resize->info, block); + + return r; +} + +static int grow_add_tail_block(struct resize *resize) +{ + return insert_new_ablock(resize->info, resize->size_of_block, + resize->max_entries, + resize->new_nr_full_blocks, + resize->new_nr_entries_in_last_block, + resize->value, &resize->root); +} + +static int grow_needs_more_blocks(struct resize *resize) +{ + int r; + + if (resize->old_nr_entries_in_last_block > 0) { + r = grow_extend_tail_block(resize, resize->max_entries); + if (r) + return r; + } + + r = insert_full_ablocks(resize->info, resize->size_of_block, + resize->old_nr_full_blocks, + resize->new_nr_full_blocks, + resize->max_entries, resize->value, + &resize->root); + if (r) + return r; + + if (resize->new_nr_entries_in_last_block) + r = grow_add_tail_block(resize); + + return r; +} + +static int grow(struct resize *resize) +{ + if (resize->new_nr_full_blocks > resize->old_nr_full_blocks) + return grow_needs_more_blocks(resize); + + else if (resize->old_nr_entries_in_last_block) + return grow_extend_tail_block(resize, resize->new_nr_entries_in_last_block); + + else + return grow_add_tail_block(resize); +} + +/*----------------------------------------------------------------*/ + +/* + * These are the value_type functions for the btree elements, which point + * to array blocks. + */ +static void block_inc(void *context, const void *value) +{ + __le64 block_le; + struct dm_array_info *info = context; + + memcpy(&block_le, value, sizeof(block_le)); + dm_tm_inc(info->btree_info.tm, le64_to_cpu(block_le)); +} + +static void block_dec(void *context, const void *value) +{ + int r; + uint64_t b; + __le64 block_le; + uint32_t ref_count; + struct dm_block *block; + struct array_block *ab; + struct dm_array_info *info = context; + + memcpy(&block_le, value, sizeof(block_le)); + b = le64_to_cpu(block_le); + + r = dm_tm_ref(info->btree_info.tm, b, &ref_count); + if (r) { + DMERR_LIMIT("couldn't get reference count for block %llu", + (unsigned long long) b); + return; + } + + if (ref_count == 1) { + /* + * We're about to drop the last reference to this ablock. + * So we need to decrement the ref count of the contents. + */ + r = get_ablock(info, b, &block, &ab); + if (r) { + DMERR_LIMIT("couldn't get array block %llu", + (unsigned long long) b); + return; + } + + dec_ablock_entries(info, ab); + unlock_ablock(info, block); + } + + dm_tm_dec(info->btree_info.tm, b); +} + +static int block_equal(void *context, const void *value1, const void *value2) +{ + return !memcmp(value1, value2, sizeof(__le64)); +} + +/*----------------------------------------------------------------*/ + +void dm_array_info_init(struct dm_array_info *info, + struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt) +{ + struct dm_btree_value_type *bvt = &info->btree_info.value_type; + + memcpy(&info->value_type, vt, sizeof(info->value_type)); + info->btree_info.tm = tm; + info->btree_info.levels = 1; + + bvt->context = info; + bvt->size = sizeof(__le64); + bvt->inc = block_inc; + bvt->dec = block_dec; + bvt->equal = block_equal; +} +EXPORT_SYMBOL_GPL(dm_array_info_init); + +int dm_array_empty(struct dm_array_info *info, dm_block_t *root) +{ + return dm_btree_empty(&info->btree_info, root); +} +EXPORT_SYMBOL_GPL(dm_array_empty); + +static int array_resize(struct dm_array_info *info, dm_block_t root, + uint32_t old_size, uint32_t new_size, + const void *value, dm_block_t *new_root) +{ + int r; + struct resize resize; + + if (old_size == new_size) + return 0; + + resize.info = info; + resize.root = root; + resize.size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm)); + resize.max_entries = calc_max_entries(info->value_type.size, + resize.size_of_block); + + resize.old_nr_full_blocks = old_size / resize.max_entries; + resize.old_nr_entries_in_last_block = old_size % resize.max_entries; + resize.new_nr_full_blocks = new_size / resize.max_entries; + resize.new_nr_entries_in_last_block = new_size % resize.max_entries; + resize.value = value; + + r = ((new_size > old_size) ? grow : shrink)(&resize); + if (r) + return r; + + *new_root = resize.root; + return 0; +} + +int dm_array_resize(struct dm_array_info *info, dm_block_t root, + uint32_t old_size, uint32_t new_size, + const void *value, dm_block_t *new_root) + __dm_written_to_disk(value) +{ + int r = array_resize(info, root, old_size, new_size, value, new_root); + __dm_unbless_for_disk(value); + return r; +} +EXPORT_SYMBOL_GPL(dm_array_resize); + +int dm_array_del(struct dm_array_info *info, dm_block_t root) +{ + return dm_btree_del(&info->btree_info, root); +} +EXPORT_SYMBOL_GPL(dm_array_del); + +int dm_array_get_value(struct dm_array_info *info, dm_block_t root, + uint32_t index, void *value_le) +{ + int r; + struct dm_block *block; + struct array_block *ab; + size_t size_of_block; + unsigned entry, max_entries; + + size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm)); + max_entries = calc_max_entries(info->value_type.size, size_of_block); + + r = lookup_ablock(info, root, index / max_entries, &block, &ab); + if (r) + return r; + + entry = index % max_entries; + if (entry >= le32_to_cpu(ab->nr_entries)) + r = -ENODATA; + else + memcpy(value_le, element_at(info, ab, entry), + info->value_type.size); + + unlock_ablock(info, block); + return r; +} +EXPORT_SYMBOL_GPL(dm_array_get_value); + +static int array_set_value(struct dm_array_info *info, dm_block_t root, + uint32_t index, const void *value, dm_block_t *new_root) +{ + int r; + struct dm_block *block; + struct array_block *ab; + size_t size_of_block; + unsigned max_entries; + unsigned entry; + void *old_value; + struct dm_btree_value_type *vt = &info->value_type; + + size_of_block = dm_bm_block_size(dm_tm_get_bm(info->btree_info.tm)); + max_entries = calc_max_entries(info->value_type.size, size_of_block); + + r = shadow_ablock(info, &root, index / max_entries, &block, &ab); + if (r) + return r; + *new_root = root; + + entry = index % max_entries; + if (entry >= le32_to_cpu(ab->nr_entries)) { + r = -ENODATA; + goto out; + } + + old_value = element_at(info, ab, entry); + if (vt->dec && + (!vt->equal || !vt->equal(vt->context, old_value, value))) { + vt->dec(vt->context, old_value); + if (vt->inc) + vt->inc(vt->context, value); + } + + memcpy(old_value, value, info->value_type.size); + +out: + unlock_ablock(info, block); + return r; +} + +int dm_array_set_value(struct dm_array_info *info, dm_block_t root, + uint32_t index, const void *value, dm_block_t *new_root) + __dm_written_to_disk(value) +{ + int r; + + r = array_set_value(info, root, index, value, new_root); + __dm_unbless_for_disk(value); + return r; +} +EXPORT_SYMBOL_GPL(dm_array_set_value); + +struct walk_info { + struct dm_array_info *info; + int (*fn)(void *context, uint64_t key, void *leaf); + void *context; +}; + +static int walk_ablock(void *context, uint64_t *keys, void *leaf) +{ + struct walk_info *wi = context; + + int r; + unsigned i; + __le64 block_le; + unsigned nr_entries, max_entries; + struct dm_block *block; + struct array_block *ab; + + memcpy(&block_le, leaf, sizeof(block_le)); + r = get_ablock(wi->info, le64_to_cpu(block_le), &block, &ab); + if (r) + return r; + + max_entries = le32_to_cpu(ab->max_entries); + nr_entries = le32_to_cpu(ab->nr_entries); + for (i = 0; i < nr_entries; i++) { + r = wi->fn(wi->context, keys[0] * max_entries + i, + element_at(wi->info, ab, i)); + + if (r) + break; + } + + unlock_ablock(wi->info, block); + return r; +} + +int dm_array_walk(struct dm_array_info *info, dm_block_t root, + int (*fn)(void *, uint64_t key, void *leaf), + void *context) +{ + struct walk_info wi; + + wi.info = info; + wi.fn = fn; + wi.context = context; + + return dm_btree_walk(&info->btree_info, root, walk_ablock, &wi); +} +EXPORT_SYMBOL_GPL(dm_array_walk); + +/*----------------------------------------------------------------*/ diff --git a/drivers/md/persistent-data/dm-array.h b/drivers/md/persistent-data/dm-array.h new file mode 100644 index 00000000000..ea177d6fa58 --- /dev/null +++ b/drivers/md/persistent-data/dm-array.h @@ -0,0 +1,166 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * + * This file is released under the GPL. + */ +#ifndef _LINUX_DM_ARRAY_H +#define _LINUX_DM_ARRAY_H + +#include "dm-btree.h" + +/*----------------------------------------------------------------*/ + +/* + * The dm-array is a persistent version of an array. It packs the data + * more efficiently than a btree which will result in less disk space use, + * and a performance boost. The element get and set operations are still + * O(ln(n)), but with a much smaller constant. + * + * The value type structure is reused from the btree type to support proper + * reference counting of values. + * + * The arrays implicitly know their length, and bounds are checked for + * lookups and updated. It doesn't store this in an accessible place + * because it would waste a whole metadata block. Make sure you store the + * size along with the array root in your encompassing data. + * + * Array entries are indexed via an unsigned integer starting from zero. + * Arrays are not sparse; if you resize an array to have 'n' entries then + * 'n - 1' will be the last valid index. + * + * Typical use: + * + * a) initialise a dm_array_info structure. This describes the array + * values and ties it into a specific transaction manager. It holds no + * instance data; the same info can be used for many similar arrays if + * you wish. + * + * b) Get yourself a root. The root is the index of a block of data on the + * disk that holds a particular instance of an array. You may have a + * pre existing root in your metadata that you wish to use, or you may + * want to create a brand new, empty array with dm_array_empty(). + * + * Like the other data structures in this library, dm_array objects are + * immutable between transactions. Update functions will return you the + * root for a _new_ array. If you've incremented the old root, via + * dm_tm_inc(), before calling the update function you may continue to use + * it in parallel with the new root. + * + * c) resize an array with dm_array_resize(). + * + * d) Get a value from the array with dm_array_get_value(). + * + * e) Set a value in the array with dm_array_set_value(). + * + * f) Walk an array of values in index order with dm_array_walk(). More + * efficient than making many calls to dm_array_get_value(). + * + * g) Destroy the array with dm_array_del(). This tells the transaction + * manager that you're no longer using this data structure so it can + * recycle it's blocks. (dm_array_dec() would be a better name for it, + * but del is in keeping with dm_btree_del()). + */ + +/* + * Describes an array. Don't initialise this structure yourself, use the + * init function below. + */ +struct dm_array_info { + struct dm_transaction_manager *tm; + struct dm_btree_value_type value_type; + struct dm_btree_info btree_info; +}; + +/* + * Sets up a dm_array_info structure. You don't need to do anything with + * this structure when you finish using it. + * + * info - the structure being filled in. + * tm - the transaction manager that should supervise this structure. + * vt - describes the leaf values. + */ +void dm_array_info_init(struct dm_array_info *info, + struct dm_transaction_manager *tm, + struct dm_btree_value_type *vt); + +/* + * Create an empty, zero length array. + * + * info - describes the array + * root - on success this will be filled out with the root block + */ +int dm_array_empty(struct dm_array_info *info, dm_block_t *root); + +/* + * Resizes the array. + * + * info - describes the array + * root - the root block of the array on disk + * old_size - the caller is responsible for remembering the size of + * the array + * new_size - can be bigger or smaller than old_size + * value - if we're growing the array the new entries will have this value + * new_root - on success, points to the new root block + * + * If growing the inc function for 'value' will be called the appropriate + * number of times. So if the caller is holding a reference they may want + * to drop it. + */ +int dm_array_resize(struct dm_array_info *info, dm_block_t root, + uint32_t old_size, uint32_t new_size, + const void *value, dm_block_t *new_root) + __dm_written_to_disk(value); + +/* + * Frees a whole array. The value_type's decrement operation will be called + * for all values in the array + */ +int dm_array_del(struct dm_array_info *info, dm_block_t root); + +/* + * Lookup a value in the array + * + * info - describes the array + * root - root block of the array + * index - array index + * value - the value to be read. Will be in on-disk format of course. + * + * -ENODATA will be returned if the index is out of bounds. + */ +int dm_array_get_value(struct dm_array_info *info, dm_block_t root, + uint32_t index, void *value); + +/* + * Set an entry in the array. + * + * info - describes the array + * root - root block of the array + * index - array index + * value - value to be written to disk. Make sure you confirm the value is + * in on-disk format with__dm_bless_for_disk() before calling. + * new_root - the new root block + * + * The old value being overwritten will be decremented, the new value + * incremented. + * + * -ENODATA will be returned if the index is out of bounds. + */ +int dm_array_set_value(struct dm_array_info *info, dm_block_t root, + uint32_t index, const void *value, dm_block_t *new_root) + __dm_written_to_disk(value); + +/* + * Walk through all the entries in an array. + * + * info - describes the array + * root - root block of the array + * fn - called back for every element + * context - passed to the callback + */ +int dm_array_walk(struct dm_array_info *info, dm_block_t root, + int (*fn)(void *context, uint64_t key, void *leaf), + void *context); + +/*----------------------------------------------------------------*/ + +#endif /* _LINUX_DM_ARRAY_H */ diff --git a/drivers/md/persistent-data/dm-bitset.c b/drivers/md/persistent-data/dm-bitset.c new file mode 100644 index 00000000000..cd9a86d4cdf --- /dev/null +++ b/drivers/md/persistent-data/dm-bitset.c @@ -0,0 +1,163 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-bitset.h" +#include "dm-transaction-manager.h" + +#include <linux/export.h> +#include <linux/device-mapper.h> + +#define DM_MSG_PREFIX "bitset" +#define BITS_PER_ARRAY_ENTRY 64 + +/*----------------------------------------------------------------*/ + +static struct dm_btree_value_type bitset_bvt = { + .context = NULL, + .size = sizeof(__le64), + .inc = NULL, + .dec = NULL, + .equal = NULL, +}; + +/*----------------------------------------------------------------*/ + +void dm_disk_bitset_init(struct dm_transaction_manager *tm, + struct dm_disk_bitset *info) +{ + dm_array_info_init(&info->array_info, tm, &bitset_bvt); + info->current_index_set = false; +} +EXPORT_SYMBOL_GPL(dm_disk_bitset_init); + +int dm_bitset_empty(struct dm_disk_bitset *info, dm_block_t *root) +{ + return dm_array_empty(&info->array_info, root); +} +EXPORT_SYMBOL_GPL(dm_bitset_empty); + +int dm_bitset_resize(struct dm_disk_bitset *info, dm_block_t root, + uint32_t old_nr_entries, uint32_t new_nr_entries, + bool default_value, dm_block_t *new_root) +{ + uint32_t old_blocks = dm_div_up(old_nr_entries, BITS_PER_ARRAY_ENTRY); + uint32_t new_blocks = dm_div_up(new_nr_entries, BITS_PER_ARRAY_ENTRY); + __le64 value = default_value ? cpu_to_le64(~0) : cpu_to_le64(0); + + __dm_bless_for_disk(&value); + return dm_array_resize(&info->array_info, root, old_blocks, new_blocks, + &value, new_root); +} +EXPORT_SYMBOL_GPL(dm_bitset_resize); + +int dm_bitset_del(struct dm_disk_bitset *info, dm_block_t root) +{ + return dm_array_del(&info->array_info, root); +} +EXPORT_SYMBOL_GPL(dm_bitset_del); + +int dm_bitset_flush(struct dm_disk_bitset *info, dm_block_t root, + dm_block_t *new_root) +{ + int r; + __le64 value; + + if (!info->current_index_set) + return 0; + + value = cpu_to_le64(info->current_bits); + + __dm_bless_for_disk(&value); + r = dm_array_set_value(&info->array_info, root, info->current_index, + &value, new_root); + if (r) + return r; + + info->current_index_set = false; + return 0; +} +EXPORT_SYMBOL_GPL(dm_bitset_flush); + +static int read_bits(struct dm_disk_bitset *info, dm_block_t root, + uint32_t array_index) +{ + int r; + __le64 value; + + r = dm_array_get_value(&info->array_info, root, array_index, &value); + if (r) + return r; + + info->current_bits = le64_to_cpu(value); + info->current_index_set = true; + info->current_index = array_index; + return 0; +} + +static int get_array_entry(struct dm_disk_bitset *info, dm_block_t root, + uint32_t index, dm_block_t *new_root) +{ + int r; + unsigned array_index = index / BITS_PER_ARRAY_ENTRY; + + if (info->current_index_set) { + if (info->current_index == array_index) + return 0; + + r = dm_bitset_flush(info, root, new_root); + if (r) + return r; + } + + return read_bits(info, root, array_index); +} + +int dm_bitset_set_bit(struct dm_disk_bitset *info, dm_block_t root, + uint32_t index, dm_block_t *new_root) +{ + int r; + unsigned b = index % BITS_PER_ARRAY_ENTRY; + + r = get_array_entry(info, root, index, new_root); + if (r) + return r; + + set_bit(b, (unsigned long *) &info->current_bits); + return 0; +} +EXPORT_SYMBOL_GPL(dm_bitset_set_bit); + +int dm_bitset_clear_bit(struct dm_disk_bitset *info, dm_block_t root, + uint32_t index, dm_block_t *new_root) +{ + int r; + unsigned b = index % BITS_PER_ARRAY_ENTRY; + + r = get_array_entry(info, root, index, new_root); + if (r) + return r; + + clear_bit(b, (unsigned long *) &info->current_bits); + return 0; +} +EXPORT_SYMBOL_GPL(dm_bitset_clear_bit); + +int dm_bitset_test_bit(struct dm_disk_bitset *info, dm_block_t root, + uint32_t index, dm_block_t *new_root, bool *result) +{ + int r; + unsigned b = index % BITS_PER_ARRAY_ENTRY; + + r = get_array_entry(info, root, index, new_root); + if (r) + return r; + + *result = test_bit(b, (unsigned long *) &info->current_bits); + return 0; +} +EXPORT_SYMBOL_GPL(dm_bitset_test_bit); + +/*----------------------------------------------------------------*/ diff --git a/drivers/md/persistent-data/dm-bitset.h b/drivers/md/persistent-data/dm-bitset.h new file mode 100644 index 00000000000..e1b9bea14aa --- /dev/null +++ b/drivers/md/persistent-data/dm-bitset.h @@ -0,0 +1,165 @@ +/* + * Copyright (C) 2012 Red Hat, Inc. + * + * This file is released under the GPL. + */ +#ifndef _LINUX_DM_BITSET_H +#define _LINUX_DM_BITSET_H + +#include "dm-array.h" + +/*----------------------------------------------------------------*/ + +/* + * This bitset type is a thin wrapper round a dm_array of 64bit words. It + * uses a tiny, one word cache to reduce the number of array lookups and so + * increase performance. + * + * Like the dm-array that it's based on, the caller needs to keep track of + * the size of the bitset separately. The underlying dm-array implicitly + * knows how many words it's storing and will return -ENODATA if you try + * and access an out of bounds word. However, an out of bounds bit in the + * final word will _not_ be detected, you have been warned. + * + * Bits are indexed from zero. + + * Typical use: + * + * a) Initialise a dm_disk_bitset structure with dm_disk_bitset_init(). + * This describes the bitset and includes the cache. It's not called it + * dm_bitset_info in line with other data structures because it does + * include instance data. + * + * b) Get yourself a root. The root is the index of a block of data on the + * disk that holds a particular instance of an bitset. You may have a + * pre existing root in your metadata that you wish to use, or you may + * want to create a brand new, empty bitset with dm_bitset_empty(). + * + * Like the other data structures in this library, dm_bitset objects are + * immutable between transactions. Update functions will return you the + * root for a _new_ array. If you've incremented the old root, via + * dm_tm_inc(), before calling the update function you may continue to use + * it in parallel with the new root. + * + * Even read operations may trigger the cache to be flushed and as such + * return a root for a new, updated bitset. + * + * c) resize a bitset with dm_bitset_resize(). + * + * d) Set a bit with dm_bitset_set_bit(). + * + * e) Clear a bit with dm_bitset_clear_bit(). + * + * f) Test a bit with dm_bitset_test_bit(). + * + * g) Flush all updates from the cache with dm_bitset_flush(). + * + * h) Destroy the bitset with dm_bitset_del(). This tells the transaction + * manager that you're no longer using this data structure so it can + * recycle it's blocks. (dm_bitset_dec() would be a better name for it, + * but del is in keeping with dm_btree_del()). + */ + +/* + * Opaque object. Unlike dm_array_info, you should have one of these per + * bitset. Initialise with dm_disk_bitset_init(). + */ +struct dm_disk_bitset { + struct dm_array_info array_info; + + uint32_t current_index; + uint64_t current_bits; + + bool current_index_set:1; +}; + +/* + * Sets up a dm_disk_bitset structure. You don't need to do anything with + * this structure when you finish using it. + * + * tm - the transaction manager that should supervise this structure + * info - the structure being initialised + */ +void dm_disk_bitset_init(struct dm_transaction_manager *tm, + struct dm_disk_bitset *info); + +/* + * Create an empty, zero length bitset. + * + * info - describes the bitset + * new_root - on success, points to the new root block + */ +int dm_bitset_empty(struct dm_disk_bitset *info, dm_block_t *new_root); + +/* + * Resize the bitset. + * + * info - describes the bitset + * old_root - the root block of the array on disk + * old_nr_entries - the number of bits in the old bitset + * new_nr_entries - the number of bits you want in the new bitset + * default_value - the value for any new bits + * new_root - on success, points to the new root block + */ +int dm_bitset_resize(struct dm_disk_bitset *info, dm_block_t old_root, + uint32_t old_nr_entries, uint32_t new_nr_entries, + bool default_value, dm_block_t *new_root); + +/* + * Frees the bitset. + */ +int dm_bitset_del(struct dm_disk_bitset *info, dm_block_t root); + +/* + * Set a bit. + * + * info - describes the bitset + * root - the root block of the bitset + * index - the bit index + * new_root - on success, points to the new root block + * + * -ENODATA will be returned if the index is out of bounds. + */ +int dm_bitset_set_bit(struct dm_disk_bitset *info, dm_block_t root, + uint32_t index, dm_block_t *new_root); + +/* + * Clears a bit. + * + * info - describes the bitset + * root - the root block of the bitset + * index - the bit index + * new_root - on success, points to the new root block + * + * -ENODATA will be returned if the index is out of bounds. + */ +int dm_bitset_clear_bit(struct dm_disk_bitset *info, dm_block_t root, + uint32_t index, dm_block_t *new_root); + +/* + * Tests a bit. + * + * info - describes the bitset + * root - the root block of the bitset + * index - the bit index + * new_root - on success, points to the new root block (cached values may have been written) + * result - the bit value you're after + * + * -ENODATA will be returned if the index is out of bounds. + */ +int dm_bitset_test_bit(struct dm_disk_bitset *info, dm_block_t root, + uint32_t index, dm_block_t *new_root, bool *result); + +/* + * Flush any cached changes to disk. + * + * info - describes the bitset + * root - the root block of the bitset + * new_root - on success, points to the new root block + */ +int dm_bitset_flush(struct dm_disk_bitset *info, dm_block_t root, + dm_block_t *new_root); + +/*----------------------------------------------------------------*/ + +#endif /* _LINUX_DM_BITSET_H */ diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index 28c3ed072a7..81b513890e2 100644 --- a/drivers/md/persistent-data/dm-block-manager.c +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -613,6 +613,7 @@ int dm_bm_flush_and_unlock(struct dm_block_manager *bm, return dm_bufio_write_dirty_buffers(bm->bufio); } +EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock); void dm_bm_set_read_only(struct dm_block_manager *bm) { diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index accbb05f17b..37d367bb9aa 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -64,6 +64,7 @@ struct ro_spine { void init_ro_spine(struct ro_spine *s, struct dm_btree_info *info); int exit_ro_spine(struct ro_spine *s); 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); struct shadow_spine { diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index f199a0c4ed0..cf9fd676ae4 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -164,6 +164,13 @@ int ro_step(struct ro_spine *s, dm_block_t new_child) return r; } +void ro_pop(struct ro_spine *s) +{ + BUG_ON(!s->count); + --s->count; + unlock_block(s->info, s->nodes[s->count]); +} + struct btree_node *ro_node(struct ro_spine *s) { struct dm_block *block; diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index 4caf66918cd..35865425e4b 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -807,3 +807,55 @@ int dm_btree_find_highest_key(struct dm_btree_info *info, dm_block_t root, return r ? r : count; } EXPORT_SYMBOL_GPL(dm_btree_find_highest_key); + +/* + * FIXME: We shouldn't use a recursive algorithm when we have limited stack + * space. Also this only works for single level trees. + */ +static int walk_node(struct ro_spine *s, dm_block_t block, + int (*fn)(void *context, uint64_t *keys, void *leaf), + void *context) +{ + int r; + unsigned i, nr; + struct btree_node *n; + uint64_t keys; + + r = ro_step(s, block); + n = ro_node(s); + + nr = le32_to_cpu(n->header.nr_entries); + for (i = 0; i < nr; i++) { + if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) { + r = walk_node(s, value64(n, i), fn, context); + if (r) + goto out; + } else { + keys = le64_to_cpu(*key_ptr(n, i)); + r = fn(context, &keys, value_ptr(n, i)); + if (r) + goto out; + } + } + +out: + ro_pop(s); + return r; +} + +int dm_btree_walk(struct dm_btree_info *info, dm_block_t root, + int (*fn)(void *context, uint64_t *keys, void *leaf), + void *context) +{ + int r; + struct ro_spine spine; + + BUG_ON(info->levels > 1); + + init_ro_spine(&spine, info); + r = walk_node(&spine, root, fn, context); + exit_ro_spine(&spine); + + return r; +} +EXPORT_SYMBOL_GPL(dm_btree_walk); diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h index a2cd50441ca..8672d159e0b 100644 --- a/drivers/md/persistent-data/dm-btree.h +++ b/drivers/md/persistent-data/dm-btree.h @@ -58,21 +58,21 @@ struct dm_btree_value_type { * somewhere.) This method is _not_ called for insertion of a new * value: It is assumed the ref count is already 1. */ - void (*inc)(void *context, void *value); + void (*inc)(void *context, const void *value); /* * This value is being deleted. The btree takes care of freeing * the memory pointed to by @value. Often the del function just * needs to decrement a reference count somewhere. */ - void (*dec)(void *context, void *value); + void (*dec)(void *context, const void *value); /* * A test for equality between two values. When a value is * overwritten with a new one, the old one has the dec method * called _unless_ the new and old value are deemed equal. */ - int (*equal)(void *context, void *value1, void *value2); + int (*equal)(void *context, const void *value1, const void *value2); }; /* @@ -142,4 +142,13 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, int dm_btree_find_highest_key(struct dm_btree_info *info, dm_block_t root, uint64_t *result_keys); +/* + * Iterate through the a btree, calling fn() on each entry. + * It only works for single level trees and is internally recursive, so + * monitor stack usage carefully. + */ +int dm_btree_walk(struct dm_btree_info *info, dm_block_t root, + int (*fn)(void *context, uint64_t *keys, void *leaf), + void *context); + #endif /* _LINUX_DM_BTREE_H */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index bf6afa2fc43..1e483fa7afb 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -68,8 +68,8 @@ typedef void (*dm_postsuspend_fn) (struct dm_target *ti); typedef int (*dm_preresume_fn) (struct dm_target *ti); typedef void (*dm_resume_fn) (struct dm_target *ti); -typedef int (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, - unsigned status_flags, char *result, unsigned maxlen); +typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type, + unsigned status_flags, char *result, unsigned maxlen); typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv); @@ -175,6 +175,14 @@ struct target_type { #define DM_TARGET_IMMUTABLE 0x00000004 #define dm_target_is_immutable(type) ((type)->features & DM_TARGET_IMMUTABLE) +/* + * Some targets need to be sent the same WRITE bio severals times so + * that they can send copies of it to different devices. This function + * examines any supplied bio and returns the number of copies of it the + * target requires. + */ +typedef unsigned (*dm_num_write_bios_fn) (struct dm_target *ti, struct bio *bio); + struct dm_target { struct dm_table *table; struct target_type *type; @@ -187,26 +195,26 @@ struct dm_target { uint32_t max_io_len; /* - * A number of zero-length barrier requests that will be submitted + * A number of zero-length barrier bios that will be submitted * to the target for the purpose of flushing cache. * - * The request number can be accessed with dm_bio_get_target_request_nr. - * It is a responsibility of the target driver to remap these requests + * The bio number can be accessed with dm_bio_get_target_bio_nr. + * It is a responsibility of the target driver to remap these bios * to the real underlying devices. */ - unsigned num_flush_requests; + unsigned num_flush_bios; /* - * The number of discard requests that will be submitted to the target. - * The request number can be accessed with dm_bio_get_target_request_nr. + * The number of discard bios that will be submitted to the target. + * The bio number can be accessed with dm_bio_get_target_bio_nr. */ - unsigned num_discard_requests; + unsigned num_discard_bios; /* - * The number of WRITE SAME requests that will be submitted to the target. - * The request number can be accessed with dm_bio_get_target_request_nr. + * The number of WRITE SAME bios that will be submitted to the target. + * The bio number can be accessed with dm_bio_get_target_bio_nr. */ - unsigned num_write_same_requests; + unsigned num_write_same_bios; /* * The minimum number of extra bytes allocated in each bio for the @@ -214,6 +222,13 @@ struct dm_target { */ unsigned per_bio_data_size; + /* + * If defined, this function is called to find out how many + * duplicate bios should be sent to the target when writing + * data. + */ + dm_num_write_bios_fn num_write_bios; + /* target specific data */ void *private; @@ -233,10 +248,10 @@ struct dm_target { bool discards_supported:1; /* - * Set if the target required discard request to be split + * Set if the target required discard bios to be split * on max_io_len boundary. */ - bool split_discard_requests:1; + bool split_discard_bios:1; /* * Set if this target does not return zeroes on discarded blocks. @@ -261,7 +276,7 @@ struct dm_target_io { struct dm_io *io; struct dm_target *ti; union map_info info; - unsigned target_request_nr; + unsigned target_bio_nr; struct bio clone; }; @@ -275,9 +290,9 @@ static inline struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size) return (struct bio *)((char *)data + data_size + offsetof(struct dm_target_io, clone)); } -static inline unsigned dm_bio_get_target_request_nr(const struct bio *bio) +static inline unsigned dm_bio_get_target_bio_nr(const struct bio *bio) { - return container_of(bio, struct dm_target_io, clone)->target_request_nr; + return container_of(bio, struct dm_target_io, clone)->target_bio_nr; } int dm_register_target(struct target_type *t); diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index 47d9d376e4e..f486d636b82 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -21,11 +21,34 @@ #define DM_KCOPYD_IGNORE_ERROR 1 +struct dm_kcopyd_throttle { + unsigned throttle; + unsigned num_io_jobs; + unsigned io_period; + unsigned total_period; + unsigned last_jiffies; +}; + +/* + * kcopyd clients that want to support throttling must pass an initialised + * dm_kcopyd_throttle struct into dm_kcopyd_client_create(). + * Two or more clients may share the same instance of this struct between + * them if they wish to be throttled as a group. + * + * This macro also creates a corresponding module parameter to configure + * the amount of throttling. + */ +#define DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(name, description) \ +static struct dm_kcopyd_throttle dm_kcopyd_throttle = { 100, 0, 0, 0, 0 }; \ +module_param_named(name, dm_kcopyd_throttle.throttle, uint, 0644); \ +MODULE_PARM_DESC(name, description) + /* * To use kcopyd you must first create a dm_kcopyd_client object. + * throttle can be NULL if you don't want any throttling. */ struct dm_kcopyd_client; -struct dm_kcopyd_client *dm_kcopyd_client_create(void); +struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle); void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc); /* diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index 539b179b349..7e75b6fd8d4 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 23 -#define DM_VERSION_PATCHLEVEL 1 -#define DM_VERSION_EXTRA "-ioctl (2012-12-18)" +#define DM_VERSION_MINOR 24 +#define DM_VERSION_PATCHLEVEL 0 +#define DM_VERSION_EXTRA "-ioctl (2013-01-15)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ @@ -336,4 +336,9 @@ enum { */ #define DM_SECURE_DATA_FLAG (1 << 15) /* In */ +/* + * If set, a message generated output data. + */ +#define DM_DATA_OUT_FLAG (1 << 16) /* Out */ + #endif /* _LINUX_DM_IOCTL_H */ |