From 4693c9668fdcec229825b3763876b4744f9e6d5e Mon Sep 17 00:00:00 2001 From: Mandeep Singh Baines Date: Mon, 31 Oct 2011 20:18:50 +0000 Subject: [PATCH 01/14] dm table: propagate non rotational flag Allow QUEUE_FLAG_NONROT to propagate up the device stack if all underlying devices are non-rotational. Tools like ureadahead will schedule IOs differently based on the rotational flag. With this patch, I see boot time go from 7.75 s to 7.46 s on my device. Suggested-by: J. Richard Barnette Signed-off-by: Mandeep Singh Baines Signed-off-by: Mike Snitzer Cc: Neil Brown Cc: Jens Axboe Cc: Martin K. Petersen Cc: dm-devel@redhat.com Signed-off-by: Alasdair G Kergon --- drivers/md/dm-table.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index bc04518e9d8b..81cbbf375bd7 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1299,6 +1299,31 @@ static bool dm_table_discard_zeroes_data(struct dm_table *t) return 1; } +static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return q && blk_queue_nonrot(q); +} + +static bool dm_table_is_nonrot(struct dm_table *t) +{ + struct dm_target *ti; + unsigned i = 0; + + /* Ensure that all underlying device are non-rotational. */ + while (i < dm_table_get_num_targets(t)) { + ti = dm_table_get_target(t, i++); + + if (!ti->type->iterate_devices || + !ti->type->iterate_devices(ti, device_is_nonrot, NULL)) + return 0; + } + + return 1; +} + void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { @@ -1324,6 +1349,11 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (!dm_table_discard_zeroes_data(t)) q->limits.discard_zeroes_data = 0; + if (dm_table_is_nonrot(t)) + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); + else + queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, q); + dm_table_set_integrity(t); /* From 71a16736a15e3fd11d283c42aa86bf704f6d25ff Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 31 Oct 2011 20:18:54 +0000 Subject: [PATCH 02/14] dm: use local printk ratelimit printk_ratelimit() shares global ratelimiting state with all other subsystems, so its usage is discouraged. Instead, define and use dm's local state. Signed-off-by: Namhyung Kim Signed-off-by: Alasdair G Kergon --- drivers/md/dm.c | 10 ++++++++++ include/linux/device-mapper.h | 17 +++++++++++++---- 2 files changed, 23 insertions(+), 4 deletions(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 52b39f335bb3..52a8fd8eb17f 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -25,6 +25,16 @@ #define DM_MSG_PREFIX "core" +#ifdef CONFIG_PRINTK +/* + * ratelimit state to be used in DMXXX_LIMIT(). + */ +DEFINE_RATELIMIT_STATE(dm_ratelimit_state, + DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); +EXPORT_SYMBOL(dm_ratelimit_state); +#endif + /* * Cookies are numeric values sent with CHANGE and REMOVE * uevents while resuming, removing or renaming the device. diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 99e3e50b5c57..622678ccb5e0 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -10,6 +10,7 @@ #include #include +#include struct dm_dev; struct dm_target; @@ -375,6 +376,14 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); *---------------------------------------------------------------*/ #define DM_NAME "device-mapper" +#ifdef CONFIG_PRINTK +extern struct ratelimit_state dm_ratelimit_state; + +#define dm_ratelimit() __ratelimit(&dm_ratelimit_state) +#else +#define dm_ratelimit() 0 +#endif + #define DMCRIT(f, arg...) \ printk(KERN_CRIT DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) @@ -382,7 +391,7 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) #define DMERR_LIMIT(f, arg...) \ do { \ - if (printk_ratelimit()) \ + if (dm_ratelimit()) \ printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " \ f "\n", ## arg); \ } while (0) @@ -391,7 +400,7 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) #define DMWARN_LIMIT(f, arg...) \ do { \ - if (printk_ratelimit()) \ + if (dm_ratelimit()) \ printk(KERN_WARNING DM_NAME ": " DM_MSG_PREFIX ": " \ f "\n", ## arg); \ } while (0) @@ -400,7 +409,7 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg) #define DMINFO_LIMIT(f, arg...) \ do { \ - if (printk_ratelimit()) \ + if (dm_ratelimit()) \ printk(KERN_INFO DM_NAME ": " DM_MSG_PREFIX ": " f \ "\n", ## arg); \ } while (0) @@ -410,7 +419,7 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX " DEBUG: " f "\n", ## arg) # define DMDEBUG_LIMIT(f, arg...) \ do { \ - if (printk_ratelimit()) \ + if (dm_ratelimit()) \ printk(KERN_DEBUG DM_NAME ": " DM_MSG_PREFIX ": " f \ "\n", ## arg); \ } while (0) From fbdc86f3bd597e108fa03d998132d04fcfe1d669 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Mon, 31 Oct 2011 20:18:56 +0000 Subject: [PATCH 03/14] dm: remove superfluous smp_mb Since set_current_state() contains a memory barrier in it, an additional barrier isn't needed. Signed-off-by: Namhyung Kim Signed-off-by: Alasdair G Kergon --- drivers/md/dm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 52a8fd8eb17f..2fe3017ba97c 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2326,7 +2326,6 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) while (1) { set_current_state(interruptible); - smp_mb(); if (!md_in_flight(md)) break; From 7f06965390e4a10fb6906c886324bfd0a96961be Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 31 Oct 2011 20:18:58 +0000 Subject: [PATCH 04/14] dm kcopyd: add dm_kcopyd_zero to zero an area This patch introduces dm_kcopyd_zero() to make it easy to use kcopyd to write zeros into the requested areas instead instead of copying. It is implemented by passing a NULL copying source to dm_kcopyd_copy(). The forthcoming thin provisioning target uses this. Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- drivers/md/dm-kcopyd.c | 31 ++++++++++++++++++++++++++----- include/linux/dm-kcopyd.h | 4 ++++ 2 files changed, 30 insertions(+), 5 deletions(-) diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 32ac70861d66..bed444c93d8d 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -66,6 +66,8 @@ struct dm_kcopyd_client { struct list_head pages_jobs; }; +static struct page_list zero_page_list; + static void wake(struct dm_kcopyd_client *kc) { queue_work(kc->kcopyd_wq, &kc->kcopyd_work); @@ -254,6 +256,9 @@ int __init dm_kcopyd_init(void) if (!_job_cache) return -ENOMEM; + zero_page_list.next = &zero_page_list; + zero_page_list.page = ZERO_PAGE(0); + return 0; } @@ -322,7 +327,7 @@ static int run_complete_job(struct kcopyd_job *job) dm_kcopyd_notify_fn fn = job->fn; struct dm_kcopyd_client *kc = job->kc; - if (job->pages) + if (job->pages && job->pages != &zero_page_list) kcopyd_put_pages(kc, job->pages); /* * If this is the master job, the sub jobs have already @@ -484,6 +489,8 @@ static void dispatch_job(struct kcopyd_job *job) atomic_inc(&kc->nr_jobs); if (unlikely(!job->source.count)) push(&kc->complete_jobs, job); + else if (job->pages == &zero_page_list) + push(&kc->io_jobs, job); else push(&kc->pages_jobs, job); wake(kc); @@ -592,14 +599,20 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, job->flags = flags; job->read_err = 0; job->write_err = 0; - job->rw = READ; - - job->source = *from; job->num_dests = num_dests; memcpy(&job->dests, dests, sizeof(*dests) * num_dests); - job->pages = NULL; + if (from) { + job->source = *from; + job->pages = NULL; + job->rw = READ; + } else { + memset(&job->source, 0, sizeof job->source); + job->source.count = job->dests[0].count; + job->pages = &zero_page_list; + job->rw = WRITE; + } job->fn = fn; job->context = context; @@ -617,6 +630,14 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, } EXPORT_SYMBOL(dm_kcopyd_copy); +int dm_kcopyd_zero(struct dm_kcopyd_client *kc, + unsigned num_dests, struct dm_io_region *dests, + unsigned flags, dm_kcopyd_notify_fn fn, void *context) +{ + return dm_kcopyd_copy(kc, NULL, num_dests, dests, flags, fn, context); +} +EXPORT_SYMBOL(dm_kcopyd_zero); + void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, dm_kcopyd_notify_fn fn, void *context) { diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index 5e54458e920f..47d9d376e4e7 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -57,5 +57,9 @@ void *dm_kcopyd_prepare_callback(struct dm_kcopyd_client *kc, dm_kcopyd_notify_fn fn, void *context); void dm_kcopyd_do_callback(void *job, int read_err, unsigned long write_err); +int dm_kcopyd_zero(struct dm_kcopyd_client *kc, + unsigned num_dests, struct dm_io_region *dests, + unsigned flags, dm_kcopyd_notify_fn fn, void *context); + #endif /* __KERNEL__ */ #endif /* _LINUX_DM_KCOPYD_H */ From 3791e2fc0e4b40d4188e79b0a99bfa6bce714a10 Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Mon, 31 Oct 2011 20:19:00 +0000 Subject: [PATCH 05/14] dm table: add singleton feature Introduce the concept of a singleton table which contains exactly one target. If a target type sets the DM_TARGET_SINGLETON feature bit device-mapper will ensure that any table that includes that target contains no others. The thin provisioning pool target uses this. Signed-off-by: Alasdair G Kergon --- drivers/md/dm-table.c | 16 ++++++++++++++++ include/linux/device-mapper.h | 14 ++++++++++---- 2 files changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 81cbbf375bd7..2ec3482e942a 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -55,6 +55,7 @@ struct dm_table { struct dm_target *targets; unsigned integrity_supported:1; + unsigned singleton:1; /* * Indicates the rw permissions for the new logical @@ -740,6 +741,12 @@ int dm_table_add_target(struct dm_table *t, const char *type, char **argv; struct dm_target *tgt; + if (t->singleton) { + DMERR("%s: target type %s must appear alone in table", + dm_device_name(t->md), t->targets->type->name); + return -EINVAL; + } + if ((r = check_space(t))) return r; @@ -758,6 +765,15 @@ int dm_table_add_target(struct dm_table *t, const char *type, return -EINVAL; } + if (dm_target_needs_singleton(tgt->type)) { + if (t->num_targets) { + DMERR("%s: target type %s must appear alone in table", + dm_device_name(t->md), type); + return -EINVAL; + } + t->singleton = 1; + } + tgt->table = t; tgt->begin = start; tgt->len = len; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 622678ccb5e0..294e78a7fccd 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -128,10 +128,6 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d); * Information about a target type */ -/* - * Target features - */ - struct target_type { uint64_t features; const char *name; @@ -160,6 +156,16 @@ struct target_type { struct list_head list; }; +/* + * Target features + */ + +/* + * Any table that contains an instance of this target must have only one. + */ +#define DM_TARGET_SINGLETON 0x00000001 +#define dm_target_needs_singleton(type) ((type)->features & DM_TARGET_SINGLETON) + struct dm_target { struct dm_table *table; struct target_type *type; From cc6cbe141a20f6d876b161b60af38d93935bfa85 Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Mon, 31 Oct 2011 20:19:02 +0000 Subject: [PATCH 06/14] dm table: add always writeable feature Add a target feature flag DM_TARGET_ALWAYS_WRITEABLE to indicate that a target does not support read-only mode. The initial implementation of the thin provisioning target uses this. Signed-off-by: Alasdair G Kergon --- drivers/md/dm-table.c | 6 ++++++ include/linux/device-mapper.h | 7 +++++++ 2 files changed, 13 insertions(+) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 2ec3482e942a..9917141729ef 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -774,6 +774,12 @@ int dm_table_add_target(struct dm_table *t, const char *type, t->singleton = 1; } + if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) { + DMERR("%s: target type %s may not be included in read-only tables", + dm_device_name(t->md), type); + return -EINVAL; + } + tgt->table = t; tgt->begin = start; tgt->len = len; diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 294e78a7fccd..cc58e2d7c032 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -166,6 +166,13 @@ struct target_type { #define DM_TARGET_SINGLETON 0x00000001 #define dm_target_needs_singleton(type) ((type)->features & DM_TARGET_SINGLETON) +/* + * Indicates that a target does not support read-only devices. + */ +#define DM_TARGET_ALWAYS_WRITEABLE 0x00000002 +#define dm_target_always_writeable(type) \ + ((type)->features & DM_TARGET_ALWAYS_WRITEABLE) + struct dm_target { struct dm_table *table; struct target_type *type; From 36a0456fbf2d9680bf9af81b39daf4a8e22cb1b8 Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Mon, 31 Oct 2011 20:19:04 +0000 Subject: [PATCH 07/14] dm table: add immutable feature Introduce DM_TARGET_IMMUTABLE to indicate that the target type cannot be mixed with any other target type, and once loaded into a device, it cannot be replaced with a table containing a different type. The thin provisioning pool device will use this. Signed-off-by: Alasdair G Kergon --- drivers/md/dm-ioctl.c | 11 +++++++++++ drivers/md/dm-table.c | 21 +++++++++++++++++++++ drivers/md/dm.c | 9 +++++++++ drivers/md/dm.h | 2 ++ include/linux/device-mapper.h | 7 +++++++ include/linux/dm-ioctl.h | 4 ++-- 6 files changed, 52 insertions(+), 2 deletions(-) diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 2e9a3ca37bdd..31c2dc25886d 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1215,6 +1215,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size) struct hash_cell *hc; struct dm_table *t; struct mapped_device *md; + struct target_type *immutable_target_type; md = find_device(param); if (!md) @@ -1230,6 +1231,16 @@ static int table_load(struct dm_ioctl *param, size_t param_size) goto out; } + immutable_target_type = dm_get_immutable_target_type(md); + if (immutable_target_type && + (immutable_target_type != dm_table_get_immutable_target_type(t))) { + DMWARN("can't replace immutable target type %s", + immutable_target_type->name); + dm_table_destroy(t); + r = -EINVAL; + goto out; + } + /* Protect md->type and md->queue against concurrent table loads. */ dm_lock_md_type(md); if (dm_get_md_type(md) == DM_TYPE_NONE) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 9917141729ef..8e9132130142 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -54,6 +54,7 @@ struct dm_table { sector_t *highs; struct dm_target *targets; + struct target_type *immutable_target_type; unsigned integrity_supported:1; unsigned singleton:1; @@ -780,6 +781,21 @@ int dm_table_add_target(struct dm_table *t, const char *type, return -EINVAL; } + if (t->immutable_target_type) { + if (t->immutable_target_type != tgt->type) { + DMERR("%s: immutable target type %s cannot be mixed with other target types", + dm_device_name(t->md), t->immutable_target_type->name); + return -EINVAL; + } + } else if (dm_target_is_immutable(tgt->type)) { + if (t->num_targets) { + DMERR("%s: immutable target type %s cannot be mixed with other target types", + dm_device_name(t->md), tgt->type->name); + return -EINVAL; + } + t->immutable_target_type = tgt->type; + } + tgt->table = t; tgt->begin = start; tgt->len = len; @@ -937,6 +953,11 @@ unsigned dm_table_get_type(struct dm_table *t) return t->type; } +struct target_type *dm_table_get_immutable_target_type(struct dm_table *t) +{ + return t->immutable_target_type; +} + bool dm_table_request_based(struct dm_table *t) { return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 2fe3017ba97c..9836324e2118 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -140,6 +140,8 @@ struct mapped_device { /* Protect queue and type against concurrent access. */ struct mutex type_lock; + struct target_type *immutable_target_type; + struct gendisk *disk; char name[16]; @@ -2096,6 +2098,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, write_lock_irqsave(&md->map_lock, flags); old_map = md->map; md->map = t; + md->immutable_target_type = dm_table_get_immutable_target_type(t); + dm_table_set_restrictions(t, q, limits); if (merge_is_optional) set_bit(DMF_MERGE_IS_OPTIONAL, &md->flags); @@ -2166,6 +2170,11 @@ unsigned dm_get_md_type(struct mapped_device *md) return md->type; } +struct target_type *dm_get_immutable_target_type(struct mapped_device *md) +{ + return md->immutable_target_type; +} + /* * Fully initialize a request-based queue (->elevator, ->request_fn, etc). */ diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 6745dbd278a4..b7dacd59d8d7 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -60,6 +60,7 @@ int dm_table_resume_targets(struct dm_table *t); int dm_table_any_congested(struct dm_table *t, int bdi_bits); int dm_table_any_busy_target(struct dm_table *t); unsigned dm_table_get_type(struct dm_table *t); +struct target_type *dm_table_get_immutable_target_type(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); bool dm_table_supports_discards(struct dm_table *t); int dm_table_alloc_md_mempools(struct dm_table *t); @@ -72,6 +73,7 @@ void dm_lock_md_type(struct mapped_device *md); void dm_unlock_md_type(struct mapped_device *md); void dm_set_md_type(struct mapped_device *md, unsigned type); unsigned dm_get_md_type(struct mapped_device *md); +struct target_type *dm_get_immutable_target_type(struct mapped_device *md); int dm_setup_md_queue(struct mapped_device *md); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index cc58e2d7c032..98f34b886f95 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -173,6 +173,13 @@ struct target_type { #define dm_target_always_writeable(type) \ ((type)->features & DM_TARGET_ALWAYS_WRITEABLE) +/* + * Any device that contains a table with an instance of this target may never + * have tables containing any different target type. + */ +#define DM_TARGET_IMMUTABLE 0x00000004 +#define dm_target_is_immutable(type) ((type)->features & DM_TARGET_IMMUTABLE) + struct dm_target { struct dm_table *table; struct target_type *type; diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h index 0cb8eff76bd6..75fd5573516e 100644 --- a/include/linux/dm-ioctl.h +++ b/include/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 21 +#define DM_VERSION_MINOR 22 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2011-07-06)" +#define DM_VERSION_EXTRA "-ioctl (2011-10-19)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ From 3cf2e4ba74ca1bf5d8ad26cd18592f02b32964f5 Mon Sep 17 00:00:00 2001 From: Alasdair G Kergon Date: Mon, 31 Oct 2011 20:19:06 +0000 Subject: [PATCH 08/14] dm: export dm get md Export dm_get_md() for the new thin provisioning target to use. Signed-off-by: Alasdair G Kergon --- drivers/md/dm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9836324e2118..6b6616a41baa 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2250,6 +2250,7 @@ struct mapped_device *dm_get_md(dev_t dev) return md; } +EXPORT_SYMBOL_GPL(dm_get_md); void *dm_get_mdptr(struct mapped_device *md) { From 95d402f057f2e208e4631893f6cd4a59c7c05e41 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Mon, 31 Oct 2011 20:19:09 +0000 Subject: [PATCH 09/14] dm: add bufio The dm-bufio interface allows you to do cached I/O on devices, holding recently-read blocks in memory and performing delayed writes. We don't use buffer cache or page cache already present in the kernel, because: * we need to handle block sizes larger than a page * we can't allocate memory to perform reads or we'd have deadlocks Currently, when a cache is required, we limit its size to a fraction of available memory. Usage can be viewed and changed in /sys/module/dm_bufio/parameters/ . The first user is thin provisioning, but more dm users are planned. Signed-off-by: Mikulas Patocka Signed-off-by: Alasdair G Kergon --- drivers/md/Kconfig | 8 + drivers/md/Makefile | 1 + drivers/md/dm-bufio.c | 1699 +++++++++++++++++++++++++++++++++++++++++ drivers/md/dm-bufio.h | 112 +++ 4 files changed, 1820 insertions(+) create mode 100644 drivers/md/dm-bufio.c create mode 100644 drivers/md/dm-bufio.h diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index f75a66e7d312..b1a921497043 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -208,6 +208,14 @@ config DM_DEBUG If unsure, say N. +config DM_BUFIO + tristate + depends on BLK_DEV_DM && EXPERIMENTAL + ---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 + delayed writes. + config DM_CRYPT tristate "Crypt target support" depends on BLK_DEV_DM diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 448838b1f92a..56661c4272f2 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_MD_MULTIPATH) += multipath.o obj-$(CONFIG_MD_FAULTY) += faulty.o obj-$(CONFIG_BLK_DEV_MD) += md-mod.o obj-$(CONFIG_BLK_DEV_DM) += dm-mod.o +obj-$(CONFIG_DM_BUFIO) += dm-bufio.o obj-$(CONFIG_DM_CRYPT) += dm-crypt.o obj-$(CONFIG_DM_DELAY) += dm-delay.o obj-$(CONFIG_DM_FLAKEY) += dm-flakey.o diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c new file mode 100644 index 000000000000..cb246667dd52 --- /dev/null +++ b/drivers/md/dm-bufio.c @@ -0,0 +1,1699 @@ +/* + * Copyright (C) 2009-2011 Red Hat, Inc. + * + * Author: Mikulas Patocka + * + * This file is released under the GPL. + */ + +#include "dm-bufio.h" + +#include +#include +#include +#include +#include +#include + +#define DM_MSG_PREFIX "bufio" + +/* + * Memory management policy: + * Limit the number of buffers to DM_BUFIO_MEMORY_PERCENT of main memory + * or DM_BUFIO_VMALLOC_PERCENT of vmalloc memory (whichever is lower). + * Always allocate at least DM_BUFIO_MIN_BUFFERS buffers. + * Start background writeback when there are DM_BUFIO_WRITEBACK_PERCENT + * dirty buffers. + */ +#define DM_BUFIO_MIN_BUFFERS 8 + +#define DM_BUFIO_MEMORY_PERCENT 2 +#define DM_BUFIO_VMALLOC_PERCENT 25 +#define DM_BUFIO_WRITEBACK_PERCENT 75 + +/* + * Check buffer ages in this interval (seconds) + */ +#define DM_BUFIO_WORK_TIMER_SECS 10 + +/* + * Free buffers when they are older than this (seconds) + */ +#define DM_BUFIO_DEFAULT_AGE_SECS 60 + +/* + * The number of bvec entries that are embedded directly in the buffer. + * If the chunk size is larger, dm-io is used to do the io. + */ +#define DM_BUFIO_INLINE_VECS 16 + +/* + * Buffer hash + */ +#define DM_BUFIO_HASH_BITS 20 +#define DM_BUFIO_HASH(block) \ + ((((block) >> DM_BUFIO_HASH_BITS) ^ (block)) & \ + ((1 << DM_BUFIO_HASH_BITS) - 1)) + +/* + * Don't try to use kmem_cache_alloc for blocks larger than this. + * For explanation, see alloc_buffer_data below. + */ +#define DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT (PAGE_SIZE >> 1) +#define DM_BUFIO_BLOCK_SIZE_GFP_LIMIT (PAGE_SIZE << (MAX_ORDER - 1)) + +/* + * dm_buffer->list_mode + */ +#define LIST_CLEAN 0 +#define LIST_DIRTY 1 +#define LIST_SIZE 2 + +/* + * Linking of buffers: + * All buffers are linked to cache_hash with their hash_list field. + * + * Clean buffers that are not being written (B_WRITING not set) + * are linked to lru[LIST_CLEAN] with their lru_list field. + * + * Dirty and clean buffers that are being written are linked to + * lru[LIST_DIRTY] with their lru_list field. When the write + * finishes, the buffer cannot be relinked immediately (because we + * are in an interrupt context and relinking requires process + * context), so some clean-not-writing buffers can be held on + * dirty_lru too. They are later added to lru in the process + * context. + */ +struct dm_bufio_client { + struct mutex lock; + + struct list_head lru[LIST_SIZE]; + unsigned long n_buffers[LIST_SIZE]; + + struct block_device *bdev; + unsigned block_size; + unsigned char sectors_per_block_bits; + unsigned char pages_per_block_bits; + unsigned char blocks_per_page_bits; + unsigned aux_size; + void (*alloc_callback)(struct dm_buffer *); + void (*write_callback)(struct dm_buffer *); + + struct dm_io_client *dm_io; + + struct list_head reserved_buffers; + unsigned need_reserved_buffers; + + struct hlist_head *cache_hash; + wait_queue_head_t free_buffer_wait; + + int async_write_error; + + struct list_head client_list; + struct shrinker shrinker; +}; + +/* + * Buffer state bits. + */ +#define B_READING 0 +#define B_WRITING 1 +#define B_DIRTY 2 + +/* + * Describes how the block was allocated: + * kmem_cache_alloc(), __get_free_pages() or vmalloc(). + * See the comment at alloc_buffer_data. + */ +enum data_mode { + DATA_MODE_SLAB = 0, + DATA_MODE_GET_FREE_PAGES = 1, + DATA_MODE_VMALLOC = 2, + DATA_MODE_LIMIT = 3 +}; + +struct dm_buffer { + struct hlist_node hash_list; + struct list_head lru_list; + sector_t block; + void *data; + enum data_mode data_mode; + unsigned char list_mode; /* LIST_* */ + unsigned hold_count; + int read_error; + int write_error; + unsigned long state; + unsigned long last_accessed; + struct dm_bufio_client *c; + struct bio bio; + struct bio_vec bio_vec[DM_BUFIO_INLINE_VECS]; +}; + +/*----------------------------------------------------------------*/ + +static struct kmem_cache *dm_bufio_caches[PAGE_SHIFT - SECTOR_SHIFT]; +static char *dm_bufio_cache_names[PAGE_SHIFT - SECTOR_SHIFT]; + +static inline int dm_bufio_cache_index(struct dm_bufio_client *c) +{ + unsigned ret = c->blocks_per_page_bits - 1; + + BUG_ON(ret >= ARRAY_SIZE(dm_bufio_caches)); + + return ret; +} + +#define DM_BUFIO_CACHE(c) (dm_bufio_caches[dm_bufio_cache_index(c)]) +#define DM_BUFIO_CACHE_NAME(c) (dm_bufio_cache_names[dm_bufio_cache_index(c)]) + +#define dm_bufio_in_request() (!!current->bio_list) + +static void dm_bufio_lock(struct dm_bufio_client *c) +{ + mutex_lock_nested(&c->lock, dm_bufio_in_request()); +} + +static int dm_bufio_trylock(struct dm_bufio_client *c) +{ + return mutex_trylock(&c->lock); +} + +static void dm_bufio_unlock(struct dm_bufio_client *c) +{ + mutex_unlock(&c->lock); +} + +/* + * FIXME Move to sched.h? + */ +#ifdef CONFIG_PREEMPT_VOLUNTARY +# define dm_bufio_cond_resched() \ +do { \ + if (unlikely(need_resched())) \ + _cond_resched(); \ +} while (0) +#else +# define dm_bufio_cond_resched() do { } while (0) +#endif + +/*----------------------------------------------------------------*/ + +/* + * Default cache size: available memory divided by the ratio. + */ +static unsigned long dm_bufio_default_cache_size; + +/* + * Total cache size set by the user. + */ +static unsigned long dm_bufio_cache_size; + +/* + * A copy of dm_bufio_cache_size because dm_bufio_cache_size can change + * at any time. If it disagrees, the user has changed cache size. + */ +static unsigned long dm_bufio_cache_size_latch; + +static DEFINE_SPINLOCK(param_spinlock); + +/* + * Buffers are freed after this timeout + */ +static unsigned dm_bufio_max_age = DM_BUFIO_DEFAULT_AGE_SECS; + +static unsigned long dm_bufio_peak_allocated; +static unsigned long dm_bufio_allocated_kmem_cache; +static unsigned long dm_bufio_allocated_get_free_pages; +static unsigned long dm_bufio_allocated_vmalloc; +static unsigned long dm_bufio_current_allocated; + +/*----------------------------------------------------------------*/ + +/* + * Per-client cache: dm_bufio_cache_size / dm_bufio_client_count + */ +static unsigned long dm_bufio_cache_size_per_client; + +/* + * The current number of clients. + */ +static int dm_bufio_client_count; + +/* + * The list of all clients. + */ +static LIST_HEAD(dm_bufio_all_clients); + +/* + * This mutex protects dm_bufio_cache_size_latch, + * dm_bufio_cache_size_per_client and dm_bufio_client_count + */ +static DEFINE_MUTEX(dm_bufio_clients_lock); + +/*----------------------------------------------------------------*/ + +static void adjust_total_allocated(enum data_mode data_mode, long diff) +{ + static unsigned long * const class_ptr[DATA_MODE_LIMIT] = { + &dm_bufio_allocated_kmem_cache, + &dm_bufio_allocated_get_free_pages, + &dm_bufio_allocated_vmalloc, + }; + + spin_lock(¶m_spinlock); + + *class_ptr[data_mode] += diff; + + dm_bufio_current_allocated += diff; + + if (dm_bufio_current_allocated > dm_bufio_peak_allocated) + dm_bufio_peak_allocated = dm_bufio_current_allocated; + + spin_unlock(¶m_spinlock); +} + +/* + * Change the number of clients and recalculate per-client limit. + */ +static void __cache_size_refresh(void) +{ + BUG_ON(!mutex_is_locked(&dm_bufio_clients_lock)); + BUG_ON(dm_bufio_client_count < 0); + + dm_bufio_cache_size_latch = dm_bufio_cache_size; + + barrier(); + + /* + * Use default if set to 0 and report the actual cache size used. + */ + if (!dm_bufio_cache_size_latch) { + (void)cmpxchg(&dm_bufio_cache_size, 0, + dm_bufio_default_cache_size); + dm_bufio_cache_size_latch = dm_bufio_default_cache_size; + } + + dm_bufio_cache_size_per_client = dm_bufio_cache_size_latch / + (dm_bufio_client_count ? : 1); +} + +/* + * Allocating buffer data. + * + * Small buffers are allocated with kmem_cache, to use space optimally. + * + * For large buffers, we choose between get_free_pages and vmalloc. + * Each has advantages and disadvantages. + * + * __get_free_pages can randomly fail if the memory is fragmented. + * __vmalloc won't randomly fail, but vmalloc space is limited (it may be + * as low as 128M) so using it for caching is not appropriate. + * + * If the allocation may fail we use __get_free_pages. Memory fragmentation + * won't have a fatal effect here, but it just causes flushes of some other + * buffers and more I/O will be performed. Don't use __get_free_pages if it + * always fails (i.e. order >= MAX_ORDER). + * + * If the allocation shouldn't fail we use __vmalloc. This is only for the + * initial reserve allocation, so there's no risk of wasting all vmalloc + * space. + */ +static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask, + enum data_mode *data_mode) +{ + if (c->block_size <= DM_BUFIO_BLOCK_SIZE_SLAB_LIMIT) { + *data_mode = DATA_MODE_SLAB; + return kmem_cache_alloc(DM_BUFIO_CACHE(c), gfp_mask); + } + + if (c->block_size <= DM_BUFIO_BLOCK_SIZE_GFP_LIMIT && + gfp_mask & __GFP_NORETRY) { + *data_mode = DATA_MODE_GET_FREE_PAGES; + return (void *)__get_free_pages(gfp_mask, + c->pages_per_block_bits); + } + + *data_mode = DATA_MODE_VMALLOC; + return __vmalloc(c->block_size, gfp_mask, PAGE_KERNEL); +} + +/* + * Free buffer's data. + */ +static void free_buffer_data(struct dm_bufio_client *c, + void *data, enum data_mode data_mode) +{ + switch (data_mode) { + case DATA_MODE_SLAB: + kmem_cache_free(DM_BUFIO_CACHE(c), data); + break; + + case DATA_MODE_GET_FREE_PAGES: + free_pages((unsigned long)data, c->pages_per_block_bits); + break; + + case DATA_MODE_VMALLOC: + vfree(data); + break; + + default: + DMCRIT("dm_bufio_free_buffer_data: bad data mode: %d", + data_mode); + BUG(); + } +} + +/* + * Allocate buffer and its data. + */ +static struct dm_buffer *alloc_buffer(struct dm_bufio_client *c, gfp_t gfp_mask) +{ + struct dm_buffer *b = kmalloc(sizeof(struct dm_buffer) + c->aux_size, + gfp_mask); + + if (!b) + return NULL; + + b->c = c; + + b->data = alloc_buffer_data(c, gfp_mask, &b->data_mode); + if (!b->data) { + kfree(b); + return NULL; + } + + adjust_total_allocated(b->data_mode, (long)c->block_size); + + return b; +} + +/* + * Free buffer and its data. + */ +static void free_buffer(struct dm_buffer *b) +{ + struct dm_bufio_client *c = b->c; + + adjust_total_allocated(b->data_mode, -(long)c->block_size); + + free_buffer_data(c, b->data, b->data_mode); + kfree(b); +} + +/* + * Link buffer to the hash list and clean or dirty queue. + */ +static void __link_buffer(struct dm_buffer *b, sector_t block, int dirty) +{ + struct dm_bufio_client *c = b->c; + + c->n_buffers[dirty]++; + b->block = block; + b->list_mode = dirty; + list_add(&b->lru_list, &c->lru[dirty]); + hlist_add_head(&b->hash_list, &c->cache_hash[DM_BUFIO_HASH(block)]); + b->last_accessed = jiffies; +} + +/* + * Unlink buffer from the hash list and dirty or clean queue. + */ +static void __unlink_buffer(struct dm_buffer *b) +{ + struct dm_bufio_client *c = b->c; + + BUG_ON(!c->n_buffers[b->list_mode]); + + c->n_buffers[b->list_mode]--; + hlist_del(&b->hash_list); + list_del(&b->lru_list); +} + +/* + * Place the buffer to the head of dirty or clean LRU queue. + */ +static void __relink_lru(struct dm_buffer *b, int dirty) +{ + struct dm_bufio_client *c = b->c; + + BUG_ON(!c->n_buffers[b->list_mode]); + + c->n_buffers[b->list_mode]--; + c->n_buffers[dirty]++; + b->list_mode = dirty; + list_del(&b->lru_list); + list_add(&b->lru_list, &c->lru[dirty]); +} + +/*---------------------------------------------------------------- + * Submit I/O on the buffer. + * + * Bio interface is faster but it has some problems: + * the vector list is limited (increasing this limit increases + * memory-consumption per buffer, so it is not viable); + * + * the memory must be direct-mapped, not vmalloced; + * + * the I/O driver can reject requests spuriously if it thinks that + * the requests are too big for the device or if they cross a + * controller-defined memory boundary. + * + * If the buffer is small enough (up to DM_BUFIO_INLINE_VECS pages) and + * it is not vmalloced, try using the bio interface. + * + * If the buffer is big, if it is vmalloced or if the underlying device + * rejects the bio because it is too large, use dm-io layer to do the I/O. + * The dm-io layer splits the I/O into multiple requests, avoiding the above + * shortcomings. + *--------------------------------------------------------------*/ + +/* + * dm-io completion routine. It just calls b->bio.bi_end_io, pretending + * that the request was handled directly with bio interface. + */ +static void dmio_complete(unsigned long error, void *context) +{ + struct dm_buffer *b = context; + + b->bio.bi_end_io(&b->bio, error ? -EIO : 0); +} + +static void use_dmio(struct dm_buffer *b, int rw, sector_t block, + bio_end_io_t *end_io) +{ + int r; + struct dm_io_request io_req = { + .bi_rw = rw, + .notify.fn = dmio_complete, + .notify.context = b, + .client = b->c->dm_io, + }; + struct dm_io_region region = { + .bdev = b->c->bdev, + .sector = block << b->c->sectors_per_block_bits, + .count = b->c->block_size >> SECTOR_SHIFT, + }; + + if (b->data_mode != DATA_MODE_VMALLOC) { + io_req.mem.type = DM_IO_KMEM; + io_req.mem.ptr.addr = b->data; + } else { + io_req.mem.type = DM_IO_VMA; + io_req.mem.ptr.vma = b->data; + } + + b->bio.bi_end_io = end_io; + + r = dm_io(&io_req, 1, ®ion, NULL); + if (r) + end_io(&b->bio, r); +} + +static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block, + bio_end_io_t *end_io) +{ + char *ptr; + int len; + + bio_init(&b->bio); + b->bio.bi_io_vec = b->bio_vec; + b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS; + b->bio.bi_sector = block << b->c->sectors_per_block_bits; + b->bio.bi_bdev = b->c->bdev; + b->bio.bi_end_io = end_io; + + /* + * We assume that if len >= PAGE_SIZE ptr is page-aligned. + * If len < PAGE_SIZE the buffer doesn't cross page boundary. + */ + ptr = b->data; + len = b->c->block_size; + + if (len >= PAGE_SIZE) + BUG_ON((unsigned long)ptr & (PAGE_SIZE - 1)); + else + BUG_ON((unsigned long)ptr & (len - 1)); + + do { + if (!bio_add_page(&b->bio, virt_to_page(ptr), + len < PAGE_SIZE ? len : PAGE_SIZE, + virt_to_phys(ptr) & (PAGE_SIZE - 1))) { + BUG_ON(b->c->block_size <= PAGE_SIZE); + use_dmio(b, rw, block, end_io); + return; + } + + len -= PAGE_SIZE; + ptr += PAGE_SIZE; + } while (len > 0); + + submit_bio(rw, &b->bio); +} + +static void submit_io(struct dm_buffer *b, int rw, sector_t block, + bio_end_io_t *end_io) +{ + if (rw == WRITE && b->c->write_callback) + b->c->write_callback(b); + + if (b->c->block_size <= DM_BUFIO_INLINE_VECS * PAGE_SIZE && + b->data_mode != DATA_MODE_VMALLOC) + use_inline_bio(b, rw, block, end_io); + else + use_dmio(b, rw, block, end_io); +} + +/*---------------------------------------------------------------- + * Writing dirty buffers + *--------------------------------------------------------------*/ + +/* + * The endio routine for write. + * + * Set the error, clear B_WRITING bit and wake anyone who was waiting on + * it. + */ +static void write_endio(struct bio *bio, int error) +{ + struct dm_buffer *b = container_of(bio, struct dm_buffer, bio); + + b->write_error = error; + if (error) { + struct dm_bufio_client *c = b->c; + (void)cmpxchg(&c->async_write_error, 0, error); + } + + BUG_ON(!test_bit(B_WRITING, &b->state)); + + smp_mb__before_clear_bit(); + clear_bit(B_WRITING, &b->state); + smp_mb__after_clear_bit(); + + wake_up_bit(&b->state, B_WRITING); +} + +/* + * This function is called when wait_on_bit is actually waiting. + */ +static int do_io_schedule(void *word) +{ + io_schedule(); + + return 0; +} + +/* + * Initiate a write on a dirty buffer, but don't wait for it. + * + * - If the buffer is not dirty, exit. + * - If there some previous write going on, wait for it to finish (we can't + * have two writes on the same buffer simultaneously). + * - Submit our write and don't wait on it. We set B_WRITING indicating + * that there is a write in progress. + */ +static void __write_dirty_buffer(struct dm_buffer *b) +{ + if (!test_bit(B_DIRTY, &b->state)) + return; + + clear_bit(B_DIRTY, &b->state); + wait_on_bit_lock(&b->state, B_WRITING, + do_io_schedule, TASK_UNINTERRUPTIBLE); + + submit_io(b, WRITE, b->block, write_endio); +} + +/* + * Wait until any activity on the buffer finishes. Possibly write the + * buffer if it is dirty. When this function finishes, there is no I/O + * running on the buffer and the buffer is not dirty. + */ +static void __make_buffer_clean(struct dm_buffer *b) +{ + BUG_ON(b->hold_count); + + if (!b->state) /* fast case */ + return; + + wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + __write_dirty_buffer(b); + wait_on_bit(&b->state, B_WRITING, do_io_schedule, TASK_UNINTERRUPTIBLE); +} + +/* + * Find some buffer that is not held by anybody, clean it, unlink it and + * return it. + */ +static struct dm_buffer *__get_unclaimed_buffer(struct dm_bufio_client *c) +{ + struct dm_buffer *b; + + list_for_each_entry_reverse(b, &c->lru[LIST_CLEAN], lru_list) { + BUG_ON(test_bit(B_WRITING, &b->state)); + BUG_ON(test_bit(B_DIRTY, &b->state)); + + if (!b->hold_count) { + __make_buffer_clean(b); + __unlink_buffer(b); + return b; + } + dm_bufio_cond_resched(); + } + + list_for_each_entry_reverse(b, &c->lru[LIST_DIRTY], lru_list) { + BUG_ON(test_bit(B_READING, &b->state)); + + if (!b->hold_count) { + __make_buffer_clean(b); + __unlink_buffer(b); + return b; + } + dm_bufio_cond_resched(); + } + + return NULL; +} + +/* + * Wait until some other threads free some buffer or release hold count on + * some buffer. + * + * This function is entered with c->lock held, drops it and regains it + * before exiting. + */ +static void __wait_for_free_buffer(struct dm_bufio_client *c) +{ + DECLARE_WAITQUEUE(wait, current); + + add_wait_queue(&c->free_buffer_wait, &wait); + set_task_state(current, TASK_UNINTERRUPTIBLE); + dm_bufio_unlock(c); + + io_schedule(); + + set_task_state(current, TASK_RUNNING); + remove_wait_queue(&c->free_buffer_wait, &wait); + + dm_bufio_lock(c); +} + +/* + * Allocate a new buffer. If the allocation is not possible, wait until + * some other thread frees a buffer. + * + * May drop the lock and regain it. + */ +static struct dm_buffer *__alloc_buffer_wait_no_callback(struct dm_bufio_client *c) +{ + struct dm_buffer *b; + + /* + * dm-bufio is resistant to allocation failures (it just keeps + * one buffer reserved in cases all the allocations fail). + * So set flags to not try too hard: + * GFP_NOIO: don't recurse into the I/O layer + * __GFP_NORETRY: don't retry and rather return failure + * __GFP_NOMEMALLOC: don't use emergency reserves + * __GFP_NOWARN: don't print a warning in case of failure + * + * For debugging, if we set the cache size to 1, no new buffers will + * be allocated. + */ + while (1) { + if (dm_bufio_cache_size_latch != 1) { + b = alloc_buffer(c, GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (b) + return b; + } + + if (!list_empty(&c->reserved_buffers)) { + b = list_entry(c->reserved_buffers.next, + struct dm_buffer, lru_list); + list_del(&b->lru_list); + c->need_reserved_buffers++; + + return b; + } + + b = __get_unclaimed_buffer(c); + if (b) + return b; + + __wait_for_free_buffer(c); + } +} + +static struct dm_buffer *__alloc_buffer_wait(struct dm_bufio_client *c) +{ + struct dm_buffer *b = __alloc_buffer_wait_no_callback(c); + + if (c->alloc_callback) + c->alloc_callback(b); + + return b; +} + +/* + * Free a buffer and wake other threads waiting for free buffers. + */ +static void __free_buffer_wake(struct dm_buffer *b) +{ + struct dm_bufio_client *c = b->c; + + if (!c->need_reserved_buffers) + free_buffer(b); + else { + list_add(&b->lru_list, &c->reserved_buffers); + c->need_reserved_buffers--; + } + + wake_up(&c->free_buffer_wait); +} + +static void __write_dirty_buffers_async(struct dm_bufio_client *c, int no_wait) +{ + struct dm_buffer *b, *tmp; + + list_for_each_entry_safe_reverse(b, tmp, &c->lru[LIST_DIRTY], lru_list) { + BUG_ON(test_bit(B_READING, &b->state)); + + if (!test_bit(B_DIRTY, &b->state) && + !test_bit(B_WRITING, &b->state)) { + __relink_lru(b, LIST_CLEAN); + continue; + } + + if (no_wait && test_bit(B_WRITING, &b->state)) + return; + + __write_dirty_buffer(b); + dm_bufio_cond_resched(); + } +} + +/* + * Get writeback threshold and buffer limit for a given client. + */ +static void __get_memory_limit(struct dm_bufio_client *c, + unsigned long *threshold_buffers, + unsigned long *limit_buffers) +{ + unsigned long buffers; + + if (dm_bufio_cache_size != dm_bufio_cache_size_latch) { + mutex_lock(&dm_bufio_clients_lock); + __cache_size_refresh(); + mutex_unlock(&dm_bufio_clients_lock); + } + + buffers = dm_bufio_cache_size_per_client >> + (c->sectors_per_block_bits + SECTOR_SHIFT); + + if (buffers < DM_BUFIO_MIN_BUFFERS) + buffers = DM_BUFIO_MIN_BUFFERS; + + *limit_buffers = buffers; + *threshold_buffers = buffers * DM_BUFIO_WRITEBACK_PERCENT / 100; +} + +/* + * Check if we're over watermark. + * If we are over threshold_buffers, start freeing buffers. + * If we're over "limit_buffers", block until we get under the limit. + */ +static void __check_watermark(struct dm_bufio_client *c) +{ + unsigned long threshold_buffers, limit_buffers; + + __get_memory_limit(c, &threshold_buffers, &limit_buffers); + + while (c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY] > + limit_buffers) { + + struct dm_buffer *b = __get_unclaimed_buffer(c); + + if (!b) + return; + + __free_buffer_wake(b); + dm_bufio_cond_resched(); + } + + if (c->n_buffers[LIST_DIRTY] > threshold_buffers) + __write_dirty_buffers_async(c, 1); +} + +/* + * Find a buffer in the hash. + */ +static struct dm_buffer *__find(struct dm_bufio_client *c, sector_t block) +{ + struct dm_buffer *b; + struct hlist_node *hn; + + hlist_for_each_entry(b, hn, &c->cache_hash[DM_BUFIO_HASH(block)], + hash_list) { + dm_bufio_cond_resched(); + if (b->block == block) + return b; + } + + return NULL; +} + +/*---------------------------------------------------------------- + * Getting a buffer + *--------------------------------------------------------------*/ + +enum new_flag { + NF_FRESH = 0, + NF_READ = 1, + NF_GET = 2 +}; + +static struct dm_buffer *__bufio_new(struct dm_bufio_client *c, sector_t block, + enum new_flag nf, struct dm_buffer **bp, + int *need_submit) +{ + struct dm_buffer *b, *new_b = NULL; + + *need_submit = 0; + + b = __find(c, block); + if (b) { + b->hold_count++; + __relink_lru(b, test_bit(B_DIRTY, &b->state) || + test_bit(B_WRITING, &b->state)); + return b; + } + + if (nf == NF_GET) + return NULL; + + new_b = __alloc_buffer_wait(c); + + /* + * We've had a period where the mutex was unlocked, so need to + * recheck the hash table. + */ + b = __find(c, block); + if (b) { + __free_buffer_wake(new_b); + b->hold_count++; + __relink_lru(b, test_bit(B_DIRTY, &b->state) || + test_bit(B_WRITING, &b->state)); + return b; + } + + __check_watermark(c); + + b = new_b; + b->hold_count = 1; + b->read_error = 0; + b->write_error = 0; + __link_buffer(b, block, LIST_CLEAN); + + if (nf == NF_FRESH) { + b->state = 0; + return b; + } + + b->state = 1 << B_READING; + *need_submit = 1; + + return b; +} + +/* + * The endio routine for reading: set the error, clear the bit and wake up + * anyone waiting on the buffer. + */ +static void read_endio(struct bio *bio, int error) +{ + struct dm_buffer *b = container_of(bio, struct dm_buffer, bio); + + b->read_error = error; + + BUG_ON(!test_bit(B_READING, &b->state)); + + smp_mb__before_clear_bit(); + clear_bit(B_READING, &b->state); + smp_mb__after_clear_bit(); + + wake_up_bit(&b->state, B_READING); +} + +/* + * A common routine for dm_bufio_new and dm_bufio_read. Operation of these + * functions is similar except that dm_bufio_new doesn't read the + * buffer from the disk (assuming that the caller overwrites all the data + * and uses dm_bufio_mark_buffer_dirty to write new data back). + */ +static void *new_read(struct dm_bufio_client *c, sector_t block, + enum new_flag nf, struct dm_buffer **bp) +{ + int need_submit; + struct dm_buffer *b; + + dm_bufio_lock(c); + b = __bufio_new(c, block, nf, bp, &need_submit); + dm_bufio_unlock(c); + + if (!b || IS_ERR(b)) + return b; + + if (need_submit) + submit_io(b, READ, b->block, read_endio); + + wait_on_bit(&b->state, B_READING, do_io_schedule, TASK_UNINTERRUPTIBLE); + + if (b->read_error) { + int error = b->read_error; + + dm_bufio_release(b); + + return ERR_PTR(error); + } + + *bp = b; + + return b->data; +} + +void *dm_bufio_get(struct dm_bufio_client *c, sector_t block, + struct dm_buffer **bp) +{ + return new_read(c, block, NF_GET, bp); +} +EXPORT_SYMBOL_GPL(dm_bufio_get); + +void *dm_bufio_read(struct dm_bufio_client *c, sector_t block, + struct dm_buffer **bp) +{ + BUG_ON(dm_bufio_in_request()); + + return new_read(c, block, NF_READ, bp); +} +EXPORT_SYMBOL_GPL(dm_bufio_read); + +void *dm_bufio_new(struct dm_bufio_client *c, sector_t block, + struct dm_buffer **bp) +{ + BUG_ON(dm_bufio_in_request()); + + return new_read(c, block, NF_FRESH, bp); +} +EXPORT_SYMBOL_GPL(dm_bufio_new); + +void dm_bufio_release(struct dm_buffer *b) +{ + struct dm_bufio_client *c = b->c; + + dm_bufio_lock(c); + + BUG_ON(test_bit(B_READING, &b->state)); + BUG_ON(!b->hold_count); + + b->hold_count--; + if (!b->hold_count) { + wake_up(&c->free_buffer_wait); + + /* + * If there were errors on the buffer, and the buffer is not + * to be written, free the buffer. There is no point in caching + * invalid buffer. + */ + if ((b->read_error || b->write_error) && + !test_bit(B_WRITING, &b->state) && + !test_bit(B_DIRTY, &b->state)) { + __unlink_buffer(b); + __free_buffer_wake(b); + } + } + + dm_bufio_unlock(c); +} +EXPORT_SYMBOL_GPL(dm_bufio_release); + +void dm_bufio_mark_buffer_dirty(struct dm_buffer *b) +{ + struct dm_bufio_client *c = b->c; + + dm_bufio_lock(c); + + if (!test_and_set_bit(B_DIRTY, &b->state)) + __relink_lru(b, LIST_DIRTY); + + dm_bufio_unlock(c); +} +EXPORT_SYMBOL_GPL(dm_bufio_mark_buffer_dirty); + +void dm_bufio_write_dirty_buffers_async(struct dm_bufio_client *c) +{ + BUG_ON(dm_bufio_in_request()); + + dm_bufio_lock(c); + __write_dirty_buffers_async(c, 0); + dm_bufio_unlock(c); +} +EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers_async); + +/* + * For performance, it is essential that the buffers are written asynchronously + * and simultaneously (so that the block layer can merge the writes) and then + * waited upon. + * + * Finally, we flush hardware disk cache. + */ +int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c) +{ + int a, f; + unsigned long buffers_processed = 0; + struct dm_buffer *b, *tmp; + + dm_bufio_lock(c); + __write_dirty_buffers_async(c, 0); + +again: + list_for_each_entry_safe_reverse(b, tmp, &c->lru[LIST_DIRTY], lru_list) { + int dropped_lock = 0; + + if (buffers_processed < c->n_buffers[LIST_DIRTY]) + buffers_processed++; + + BUG_ON(test_bit(B_READING, &b->state)); + + if (test_bit(B_WRITING, &b->state)) { + if (buffers_processed < c->n_buffers[LIST_DIRTY]) { + dropped_lock = 1; + b->hold_count++; + dm_bufio_unlock(c); + wait_on_bit(&b->state, B_WRITING, + do_io_schedule, + TASK_UNINTERRUPTIBLE); + dm_bufio_lock(c); + b->hold_count--; + } else + wait_on_bit(&b->state, B_WRITING, + do_io_schedule, + TASK_UNINTERRUPTIBLE); + } + + if (!test_bit(B_DIRTY, &b->state) && + !test_bit(B_WRITING, &b->state)) + __relink_lru(b, LIST_CLEAN); + + dm_bufio_cond_resched(); + + /* + * If we dropped the lock, the list is no longer consistent, + * so we must restart the search. + * + * In the most common case, the buffer just processed is + * relinked to the clean list, so we won't loop scanning the + * same buffer again and again. + * + * This may livelock if there is another thread simultaneously + * dirtying buffers, so we count the number of buffers walked + * and if it exceeds the total number of buffers, it means that + * someone is doing some writes simultaneously with us. In + * this case, stop, dropping the lock. + */ + if (dropped_lock) + goto again; + } + wake_up(&c->free_buffer_wait); + dm_bufio_unlock(c); + + a = xchg(&c->async_write_error, 0); + f = dm_bufio_issue_flush(c); + if (a) + return a; + + return f; +} +EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers); + +/* + * Use dm-io to send and empty barrier flush the device. + */ +int dm_bufio_issue_flush(struct dm_bufio_client *c) +{ + struct dm_io_request io_req = { + .bi_rw = REQ_FLUSH, + .mem.type = DM_IO_KMEM, + .mem.ptr.addr = NULL, + .client = c->dm_io, + }; + struct dm_io_region io_reg = { + .bdev = c->bdev, + .sector = 0, + .count = 0, + }; + + BUG_ON(dm_bufio_in_request()); + + return dm_io(&io_req, 1, &io_reg, NULL); +} +EXPORT_SYMBOL_GPL(dm_bufio_issue_flush); + +/* + * We first delete any other buffer that may be at that new location. + * + * Then, we write the buffer to the original location if it was dirty. + * + * Then, if we are the only one who is holding the buffer, relink the buffer + * in the hash queue for the new location. + * + * If there was someone else holding the buffer, we write it to the new + * location but not relink it, because that other user needs to have the buffer + * at the same place. + */ +void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block) +{ + struct dm_bufio_client *c = b->c; + struct dm_buffer *new; + + BUG_ON(dm_bufio_in_request()); + + dm_bufio_lock(c); + +retry: + new = __find(c, new_block); + if (new) { + if (new->hold_count) { + __wait_for_free_buffer(c); + goto retry; + } + + /* + * FIXME: Is there any point waiting for a write that's going + * to be overwritten in a bit? + */ + __make_buffer_clean(new); + __unlink_buffer(new); + __free_buffer_wake(new); + } + + BUG_ON(!b->hold_count); + BUG_ON(test_bit(B_READING, &b->state)); + + __write_dirty_buffer(b); + if (b->hold_count == 1) { + wait_on_bit(&b->state, B_WRITING, + do_io_schedule, TASK_UNINTERRUPTIBLE); + set_bit(B_DIRTY, &b->state); + __unlink_buffer(b); + __link_buffer(b, new_block, LIST_DIRTY); + } else { + sector_t old_block; + wait_on_bit_lock(&b->state, B_WRITING, + do_io_schedule, TASK_UNINTERRUPTIBLE); + /* + * Relink buffer to "new_block" so that write_callback + * sees "new_block" as a block number. + * After the write, link the buffer back to old_block. + * All this must be done in bufio lock, so that block number + * change isn't visible to other threads. + */ + old_block = b->block; + __unlink_buffer(b); + __link_buffer(b, new_block, b->list_mode); + submit_io(b, WRITE, new_block, write_endio); + wait_on_bit(&b->state, B_WRITING, + do_io_schedule, TASK_UNINTERRUPTIBLE); + __unlink_buffer(b); + __link_buffer(b, old_block, b->list_mode); + } + + dm_bufio_unlock(c); + dm_bufio_release(b); +} +EXPORT_SYMBOL_GPL(dm_bufio_release_move); + +unsigned dm_bufio_get_block_size(struct dm_bufio_client *c) +{ + return c->block_size; +} +EXPORT_SYMBOL_GPL(dm_bufio_get_block_size); + +sector_t dm_bufio_get_device_size(struct dm_bufio_client *c) +{ + return i_size_read(c->bdev->bd_inode) >> + (SECTOR_SHIFT + c->sectors_per_block_bits); +} +EXPORT_SYMBOL_GPL(dm_bufio_get_device_size); + +sector_t dm_bufio_get_block_number(struct dm_buffer *b) +{ + return b->block; +} +EXPORT_SYMBOL_GPL(dm_bufio_get_block_number); + +void *dm_bufio_get_block_data(struct dm_buffer *b) +{ + return b->data; +} +EXPORT_SYMBOL_GPL(dm_bufio_get_block_data); + +void *dm_bufio_get_aux_data(struct dm_buffer *b) +{ + return b + 1; +} +EXPORT_SYMBOL_GPL(dm_bufio_get_aux_data); + +struct dm_bufio_client *dm_bufio_get_client(struct dm_buffer *b) +{ + return b->c; +} +EXPORT_SYMBOL_GPL(dm_bufio_get_client); + +static void drop_buffers(struct dm_bufio_client *c) +{ + struct dm_buffer *b; + int i; + + BUG_ON(dm_bufio_in_request()); + + /* + * An optimization so that the buffers are not written one-by-one. + */ + dm_bufio_write_dirty_buffers_async(c); + + dm_bufio_lock(c); + + while ((b = __get_unclaimed_buffer(c))) + __free_buffer_wake(b); + + for (i = 0; i < LIST_SIZE; i++) + list_for_each_entry(b, &c->lru[i], lru_list) + DMERR("leaked buffer %llx, hold count %u, list %d", + (unsigned long long)b->block, b->hold_count, i); + + for (i = 0; i < LIST_SIZE; i++) + BUG_ON(!list_empty(&c->lru[i])); + + dm_bufio_unlock(c); +} + +/* + * Test if the buffer is unused and too old, and commit it. + * At if noio is set, we must not do any I/O because we hold + * dm_bufio_clients_lock and we would risk deadlock if the I/O gets rerouted to + * different bufio client. + */ +static int __cleanup_old_buffer(struct dm_buffer *b, gfp_t gfp, + unsigned long max_jiffies) +{ + if (jiffies - b->last_accessed < max_jiffies) + return 1; + + if (!(gfp & __GFP_IO)) { + if (test_bit(B_READING, &b->state) || + test_bit(B_WRITING, &b->state) || + test_bit(B_DIRTY, &b->state)) + return 1; + } + + if (b->hold_count) + return 1; + + __make_buffer_clean(b); + __unlink_buffer(b); + __free_buffer_wake(b); + + return 0; +} + +static void __scan(struct dm_bufio_client *c, unsigned long nr_to_scan, + struct shrink_control *sc) +{ + int l; + struct dm_buffer *b, *tmp; + + for (l = 0; l < LIST_SIZE; l++) { + list_for_each_entry_safe_reverse(b, tmp, &c->lru[l], lru_list) + if (!__cleanup_old_buffer(b, sc->gfp_mask, 0) && + !--nr_to_scan) + return; + dm_bufio_cond_resched(); + } +} + +static int shrink(struct shrinker *shrinker, struct shrink_control *sc) +{ + struct dm_bufio_client *c = + container_of(shrinker, struct dm_bufio_client, shrinker); + unsigned long r; + unsigned long nr_to_scan = sc->nr_to_scan; + + if (sc->gfp_mask & __GFP_IO) + dm_bufio_lock(c); + else if (!dm_bufio_trylock(c)) + return !nr_to_scan ? 0 : -1; + + if (nr_to_scan) + __scan(c, nr_to_scan, sc); + + r = c->n_buffers[LIST_CLEAN] + c->n_buffers[LIST_DIRTY]; + if (r > INT_MAX) + r = INT_MAX; + + dm_bufio_unlock(c); + + return r; +} + +/* + * Create the buffering interface + */ +struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsigned block_size, + unsigned reserved_buffers, unsigned aux_size, + void (*alloc_callback)(struct dm_buffer *), + void (*write_callback)(struct dm_buffer *)) +{ + int r; + struct dm_bufio_client *c; + unsigned i; + + BUG_ON(block_size < 1 << SECTOR_SHIFT || + (block_size & (block_size - 1))); + + c = kmalloc(sizeof(*c), GFP_KERNEL); + if (!c) { + r = -ENOMEM; + goto bad_client; + } + c->cache_hash = vmalloc(sizeof(struct hlist_head) << DM_BUFIO_HASH_BITS); + if (!c->cache_hash) { + r = -ENOMEM; + goto bad_hash; + } + + c->bdev = bdev; + c->block_size = block_size; + c->sectors_per_block_bits = ffs(block_size) - 1 - SECTOR_SHIFT; + c->pages_per_block_bits = (ffs(block_size) - 1 >= PAGE_SHIFT) ? + ffs(block_size) - 1 - PAGE_SHIFT : 0; + c->blocks_per_page_bits = (ffs(block_size) - 1 < PAGE_SHIFT ? + PAGE_SHIFT - (ffs(block_size) - 1) : 0); + + c->aux_size = aux_size; + c->alloc_callback = alloc_callback; + c->write_callback = write_callback; + + for (i = 0; i < LIST_SIZE; i++) { + INIT_LIST_HEAD(&c->lru[i]); + c->n_buffers[i] = 0; + } + + for (i = 0; i < 1 << DM_BUFIO_HASH_BITS; i++) + INIT_HLIST_HEAD(&c->cache_hash[i]); + + mutex_init(&c->lock); + INIT_LIST_HEAD(&c->reserved_buffers); + c->need_reserved_buffers = reserved_buffers; + + init_waitqueue_head(&c->free_buffer_wait); + c->async_write_error = 0; + + c->dm_io = dm_io_client_create(); + if (IS_ERR(c->dm_io)) { + r = PTR_ERR(c->dm_io); + goto bad_dm_io; + } + + mutex_lock(&dm_bufio_clients_lock); + if (c->blocks_per_page_bits) { + if (!DM_BUFIO_CACHE_NAME(c)) { + DM_BUFIO_CACHE_NAME(c) = kasprintf(GFP_KERNEL, "dm_bufio_cache-%u", c->block_size); + if (!DM_BUFIO_CACHE_NAME(c)) { + r = -ENOMEM; + mutex_unlock(&dm_bufio_clients_lock); + goto bad_cache; + } + } + + if (!DM_BUFIO_CACHE(c)) { + DM_BUFIO_CACHE(c) = kmem_cache_create(DM_BUFIO_CACHE_NAME(c), + c->block_size, + c->block_size, 0, NULL); + if (!DM_BUFIO_CACHE(c)) { + r = -ENOMEM; + mutex_unlock(&dm_bufio_clients_lock); + goto bad_cache; + } + } + } + mutex_unlock(&dm_bufio_clients_lock); + + while (c->need_reserved_buffers) { + struct dm_buffer *b = alloc_buffer(c, GFP_KERNEL); + + if (!b) { + r = -ENOMEM; + goto bad_buffer; + } + __free_buffer_wake(b); + } + + mutex_lock(&dm_bufio_clients_lock); + dm_bufio_client_count++; + list_add(&c->client_list, &dm_bufio_all_clients); + __cache_size_refresh(); + mutex_unlock(&dm_bufio_clients_lock); + + c->shrinker.shrink = shrink; + c->shrinker.seeks = 1; + c->shrinker.batch = 0; + register_shrinker(&c->shrinker); + + return c; + +bad_buffer: +bad_cache: + while (!list_empty(&c->reserved_buffers)) { + struct dm_buffer *b = list_entry(c->reserved_buffers.next, + struct dm_buffer, lru_list); + list_del(&b->lru_list); + free_buffer(b); + } + dm_io_client_destroy(c->dm_io); +bad_dm_io: + vfree(c->cache_hash); +bad_hash: + kfree(c); +bad_client: + return ERR_PTR(r); +} +EXPORT_SYMBOL_GPL(dm_bufio_client_create); + +/* + * Free the buffering interface. + * It is required that there are no references on any buffers. + */ +void dm_bufio_client_destroy(struct dm_bufio_client *c) +{ + unsigned i; + + drop_buffers(c); + + unregister_shrinker(&c->shrinker); + + mutex_lock(&dm_bufio_clients_lock); + + list_del(&c->client_list); + dm_bufio_client_count--; + __cache_size_refresh(); + + mutex_unlock(&dm_bufio_clients_lock); + + for (i = 0; i < 1 << DM_BUFIO_HASH_BITS; i++) + BUG_ON(!hlist_empty(&c->cache_hash[i])); + + BUG_ON(c->need_reserved_buffers); + + while (!list_empty(&c->reserved_buffers)) { + struct dm_buffer *b = list_entry(c->reserved_buffers.next, + struct dm_buffer, lru_list); + list_del(&b->lru_list); + free_buffer(b); + } + + for (i = 0; i < LIST_SIZE; i++) + if (c->n_buffers[i]) + DMERR("leaked buffer count %d: %ld", i, c->n_buffers[i]); + + for (i = 0; i < LIST_SIZE; i++) + BUG_ON(c->n_buffers[i]); + + dm_io_client_destroy(c->dm_io); + vfree(c->cache_hash); + kfree(c); +} +EXPORT_SYMBOL_GPL(dm_bufio_client_destroy); + +static void cleanup_old_buffers(void) +{ + unsigned long max_age = dm_bufio_max_age; + struct dm_bufio_client *c; + + barrier(); + + if (max_age > ULONG_MAX / HZ) + max_age = ULONG_MAX / HZ; + + mutex_lock(&dm_bufio_clients_lock); + list_for_each_entry(c, &dm_bufio_all_clients, client_list) { + if (!dm_bufio_trylock(c)) + continue; + + while (!list_empty(&c->lru[LIST_CLEAN])) { + struct dm_buffer *b; + b = list_entry(c->lru[LIST_CLEAN].prev, + struct dm_buffer, lru_list); + if (__cleanup_old_buffer(b, 0, max_age * HZ)) + break; + dm_bufio_cond_resched(); + } + + dm_bufio_unlock(c); + dm_bufio_cond_resched(); + } + mutex_unlock(&dm_bufio_clients_lock); +} + +static struct workqueue_struct *dm_bufio_wq; +static struct delayed_work dm_bufio_work; + +static void work_fn(struct work_struct *w) +{ + cleanup_old_buffers(); + + queue_delayed_work(dm_bufio_wq, &dm_bufio_work, + DM_BUFIO_WORK_TIMER_SECS * HZ); +} + +/*---------------------------------------------------------------- + * Module setup + *--------------------------------------------------------------*/ + +/* + * This is called only once for the whole dm_bufio module. + * It initializes memory limit. + */ +static int __init dm_bufio_init(void) +{ + __u64 mem; + + memset(&dm_bufio_caches, 0, sizeof dm_bufio_caches); + memset(&dm_bufio_cache_names, 0, sizeof dm_bufio_cache_names); + + mem = (__u64)((totalram_pages - totalhigh_pages) * + DM_BUFIO_MEMORY_PERCENT / 100) << PAGE_SHIFT; + + if (mem > ULONG_MAX) + mem = ULONG_MAX; + +#ifdef CONFIG_MMU + /* + * Get the size of vmalloc space the same way as VMALLOC_TOTAL + * in fs/proc/internal.h + */ + if (mem > (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100) + mem = (VMALLOC_END - VMALLOC_START) * DM_BUFIO_VMALLOC_PERCENT / 100; +#endif + + dm_bufio_default_cache_size = mem; + + mutex_lock(&dm_bufio_clients_lock); + __cache_size_refresh(); + mutex_unlock(&dm_bufio_clients_lock); + + dm_bufio_wq = create_singlethread_workqueue("dm_bufio_cache"); + if (!dm_bufio_wq) + return -ENOMEM; + + INIT_DELAYED_WORK(&dm_bufio_work, work_fn); + queue_delayed_work(dm_bufio_wq, &dm_bufio_work, + DM_BUFIO_WORK_TIMER_SECS * HZ); + + return 0; +} + +/* + * This is called once when unloading the dm_bufio module. + */ +static void __exit dm_bufio_exit(void) +{ + int bug = 0; + int i; + + cancel_delayed_work_sync(&dm_bufio_work); + destroy_workqueue(dm_bufio_wq); + + for (i = 0; i < ARRAY_SIZE(dm_bufio_caches); i++) { + struct kmem_cache *kc = dm_bufio_caches[i]; + + if (kc) + kmem_cache_destroy(kc); + } + + for (i = 0; i < ARRAY_SIZE(dm_bufio_cache_names); i++) + kfree(dm_bufio_cache_names[i]); + + if (dm_bufio_client_count) { + DMCRIT("%s: dm_bufio_client_count leaked: %d", + __func__, dm_bufio_client_count); + bug = 1; + } + + if (dm_bufio_current_allocated) { + DMCRIT("%s: dm_bufio_current_allocated leaked: %lu", + __func__, dm_bufio_current_allocated); + bug = 1; + } + + if (dm_bufio_allocated_get_free_pages) { + DMCRIT("%s: dm_bufio_allocated_get_free_pages leaked: %lu", + __func__, dm_bufio_allocated_get_free_pages); + bug = 1; + } + + if (dm_bufio_allocated_vmalloc) { + DMCRIT("%s: dm_bufio_vmalloc leaked: %lu", + __func__, dm_bufio_allocated_vmalloc); + bug = 1; + } + + if (bug) + BUG(); +} + +module_init(dm_bufio_init) +module_exit(dm_bufio_exit) + +module_param_named(max_cache_size_bytes, dm_bufio_cache_size, ulong, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(max_cache_size_bytes, "Size of metadata cache"); + +module_param_named(max_age_seconds, dm_bufio_max_age, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(max_age_seconds, "Max age of a buffer in seconds"); + +module_param_named(peak_allocated_bytes, dm_bufio_peak_allocated, ulong, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(peak_allocated_bytes, "Tracks the maximum allocated memory"); + +module_param_named(allocated_kmem_cache_bytes, dm_bufio_allocated_kmem_cache, ulong, S_IRUGO); +MODULE_PARM_DESC(allocated_kmem_cache_bytes, "Memory allocated with kmem_cache_alloc"); + +module_param_named(allocated_get_free_pages_bytes, dm_bufio_allocated_get_free_pages, ulong, S_IRUGO); +MODULE_PARM_DESC(allocated_get_free_pages_bytes, "Memory allocated with get_free_pages"); + +module_param_named(allocated_vmalloc_bytes, dm_bufio_allocated_vmalloc, ulong, S_IRUGO); +MODULE_PARM_DESC(allocated_vmalloc_bytes, "Memory allocated with vmalloc"); + +module_param_named(current_allocated_bytes, dm_bufio_current_allocated, ulong, S_IRUGO); +MODULE_PARM_DESC(current_allocated_bytes, "Memory currently used by the cache"); + +MODULE_AUTHOR("Mikulas Patocka "); +MODULE_DESCRIPTION(DM_NAME " buffered I/O library"); +MODULE_LICENSE("GPL"); diff --git a/drivers/md/dm-bufio.h b/drivers/md/dm-bufio.h new file mode 100644 index 000000000000..5c4c3a04e381 --- /dev/null +++ b/drivers/md/dm-bufio.h @@ -0,0 +1,112 @@ +/* + * Copyright (C) 2009-2011 Red Hat, Inc. + * + * Author: Mikulas Patocka + * + * This file is released under the GPL. + */ + +#ifndef DM_BUFIO_H +#define DM_BUFIO_H + +#include +#include + +/*----------------------------------------------------------------*/ + +struct dm_bufio_client; +struct dm_buffer; + +/* + * Create a buffered IO cache on a given device + */ +struct dm_bufio_client * +dm_bufio_client_create(struct block_device *bdev, unsigned block_size, + unsigned reserved_buffers, unsigned aux_size, + void (*alloc_callback)(struct dm_buffer *), + void (*write_callback)(struct dm_buffer *)); + +/* + * Release a buffered IO cache. + */ +void dm_bufio_client_destroy(struct dm_bufio_client *c); + +/* + * WARNING: to avoid deadlocks, these conditions are observed: + * + * - At most one thread can hold at most "reserved_buffers" simultaneously. + * - Each other threads can hold at most one buffer. + * - Threads which call only dm_bufio_get can hold unlimited number of + * buffers. + */ + +/* + * Read a given block from disk. Returns pointer to data. Returns a + * pointer to dm_buffer that can be used to release the buffer or to make + * it dirty. + */ +void *dm_bufio_read(struct dm_bufio_client *c, sector_t block, + struct dm_buffer **bp); + +/* + * Like dm_bufio_read, but return buffer from cache, don't read + * it. If the buffer is not in the cache, return NULL. + */ +void *dm_bufio_get(struct dm_bufio_client *c, sector_t block, + struct dm_buffer **bp); + +/* + * Like dm_bufio_read, but don't read anything from the disk. It is + * expected that the caller initializes the buffer and marks it dirty. + */ +void *dm_bufio_new(struct dm_bufio_client *c, sector_t block, + struct dm_buffer **bp); + +/* + * Release a reference obtained with dm_bufio_{read,get,new}. The data + * pointer and dm_buffer pointer is no longer valid after this call. + */ +void dm_bufio_release(struct dm_buffer *b); + +/* + * Mark a buffer dirty. It should be called after the buffer is modified. + * + * In case of memory pressure, the buffer may be written after + * dm_bufio_mark_buffer_dirty, but before dm_bufio_write_dirty_buffers. So + * dm_bufio_write_dirty_buffers guarantees that the buffer is on-disk but + * the actual writing may occur earlier. + */ +void dm_bufio_mark_buffer_dirty(struct dm_buffer *b); + +/* + * Initiate writing of dirty buffers, without waiting for completion. + */ +void dm_bufio_write_dirty_buffers_async(struct dm_bufio_client *c); + +/* + * Write all dirty buffers. Guarantees that all dirty buffers created prior + * to this call are on disk when this call exits. + */ +int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c); + +/* + * Send an empty write barrier to the device to flush hardware disk cache. + */ +int dm_bufio_issue_flush(struct dm_bufio_client *c); + +/* + * Like dm_bufio_release but also move the buffer to the new + * block. dm_bufio_write_dirty_buffers is needed to commit the new block. + */ +void dm_bufio_release_move(struct dm_buffer *b, sector_t new_block); + +unsigned dm_bufio_get_block_size(struct dm_bufio_client *c); +sector_t dm_bufio_get_device_size(struct dm_bufio_client *c); +sector_t dm_bufio_get_block_number(struct dm_buffer *b); +void *dm_bufio_get_block_data(struct dm_buffer *b); +void *dm_bufio_get_aux_data(struct dm_buffer *b); +struct dm_bufio_client *dm_bufio_get_client(struct dm_buffer *b); + +/*----------------------------------------------------------------*/ + +#endif From 3241b1d3e0aaafbfcd320f4d71ade629728cc4f4 Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Mon, 31 Oct 2011 20:19:11 +0000 Subject: [PATCH 10/14] dm: add persistent data library The persistent-data library offers a re-usable framework for the storage and management of on-disk metadata in device-mapper targets. It's used by the thin-provisioning target in the next patch and in an upcoming hierarchical storage target. For further information, please read Documentation/device-mapper/persistent-data.txt Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- .../device-mapper/persistent-data.txt | 84 ++ drivers/md/persistent-data/Kconfig | 8 + drivers/md/persistent-data/Makefile | 11 + drivers/md/persistent-data/dm-block-manager.c | 620 ++++++++++++++ drivers/md/persistent-data/dm-block-manager.h | 123 +++ .../md/persistent-data/dm-btree-internal.h | 137 +++ drivers/md/persistent-data/dm-btree-remove.c | 566 ++++++++++++ drivers/md/persistent-data/dm-btree-spine.c | 244 ++++++ drivers/md/persistent-data/dm-btree.c | 805 ++++++++++++++++++ drivers/md/persistent-data/dm-btree.h | 145 ++++ .../dm-persistent-data-internal.h | 19 + .../md/persistent-data/dm-space-map-checker.c | 437 ++++++++++ .../md/persistent-data/dm-space-map-checker.h | 26 + .../md/persistent-data/dm-space-map-common.c | 705 +++++++++++++++ .../md/persistent-data/dm-space-map-common.h | 126 +++ .../md/persistent-data/dm-space-map-disk.c | 335 ++++++++ .../md/persistent-data/dm-space-map-disk.h | 25 + .../persistent-data/dm-space-map-metadata.c | 596 +++++++++++++ .../persistent-data/dm-space-map-metadata.h | 33 + drivers/md/persistent-data/dm-space-map.h | 134 +++ .../persistent-data/dm-transaction-manager.c | 400 +++++++++ .../persistent-data/dm-transaction-manager.h | 130 +++ 22 files changed, 5709 insertions(+) create mode 100644 Documentation/device-mapper/persistent-data.txt create mode 100644 drivers/md/persistent-data/Kconfig create mode 100644 drivers/md/persistent-data/Makefile create mode 100644 drivers/md/persistent-data/dm-block-manager.c create mode 100644 drivers/md/persistent-data/dm-block-manager.h create mode 100644 drivers/md/persistent-data/dm-btree-internal.h create mode 100644 drivers/md/persistent-data/dm-btree-remove.c create mode 100644 drivers/md/persistent-data/dm-btree-spine.c create mode 100644 drivers/md/persistent-data/dm-btree.c create mode 100644 drivers/md/persistent-data/dm-btree.h create mode 100644 drivers/md/persistent-data/dm-persistent-data-internal.h create mode 100644 drivers/md/persistent-data/dm-space-map-checker.c create mode 100644 drivers/md/persistent-data/dm-space-map-checker.h create mode 100644 drivers/md/persistent-data/dm-space-map-common.c create mode 100644 drivers/md/persistent-data/dm-space-map-common.h create mode 100644 drivers/md/persistent-data/dm-space-map-disk.c create mode 100644 drivers/md/persistent-data/dm-space-map-disk.h create mode 100644 drivers/md/persistent-data/dm-space-map-metadata.c create mode 100644 drivers/md/persistent-data/dm-space-map-metadata.h create mode 100644 drivers/md/persistent-data/dm-space-map.h create mode 100644 drivers/md/persistent-data/dm-transaction-manager.c create mode 100644 drivers/md/persistent-data/dm-transaction-manager.h diff --git a/Documentation/device-mapper/persistent-data.txt b/Documentation/device-mapper/persistent-data.txt new file mode 100644 index 000000000000..0e5df9b04ad2 --- /dev/null +++ b/Documentation/device-mapper/persistent-data.txt @@ -0,0 +1,84 @@ +Introduction +============ + +The more-sophisticated device-mapper targets require complex metadata +that is managed in kernel. In late 2010 we were seeing that various +different targets were rolling their own data strutures, for example: + +- Mikulas Patocka's multisnap implementation +- Heinz Mauelshagen's thin provisioning target +- Another btree-based caching target posted to dm-devel +- Another multi-snapshot target based on a design of Daniel Phillips + +Maintaining these data structures takes a lot of work, so if possible +we'd like to reduce the number. + +The persistent-data library is an attempt to provide a re-usable +framework for people who want to store metadata in device-mapper +targets. It's currently used by the thin-provisioning target and an +upcoming hierarchical storage target. + +Overview +======== + +The main documentation is in the header files which can all be found +under drivers/md/persistent-data. + +The block manager +----------------- + +dm-block-manager.[hc] + +This provides access to the data on disk in fixed sized-blocks. There +is a read/write locking interface to prevent concurrent accesses, and +keep data that is being used in the cache. + +Clients of persistent-data are unlikely to use this directly. + +The transaction manager +----------------------- + +dm-transaction-manager.[hc] + +This restricts access to blocks and enforces copy-on-write semantics. +The only way you can get hold of a writable block through the +transaction manager is by shadowing an existing block (ie. doing +copy-on-write) or allocating a fresh one. Shadowing is elided within +the same transaction so performance is reasonable. The commit method +ensures that all data is flushed before it writes the superblock. +On power failure your metadata will be as it was when last committed. + +The Space Maps +-------------- + +dm-space-map.h +dm-space-map-metadata.[hc] +dm-space-map-disk.[hc] + +On-disk data structures that keep track of reference counts of blocks. +Also acts as the allocator of new blocks. Currently two +implementations: a simpler one for managing blocks on a different +device (eg. thinly-provisioned data blocks); and one for managing +the metadata space. The latter is complicated by the need to store +its own data within the space it's managing. + +The data structures +------------------- + +dm-btree.[hc] +dm-btree-remove.c +dm-btree-spine.c +dm-btree-internal.h + +Currently there is only one data structure, a hierarchical btree. +There are plans to add more. For example, something with an +array-like interface would see a lot of use. + +The btree is 'hierarchical' in that you can define it to be composed +of nested btrees, and take multiple keys. For example, the +thin-provisioning target uses a btree with two levels of nesting. +The first maps a device id to a mapping tree, and that in turn maps a +virtual block to a physical block. + +Values stored in the btrees can have arbitrary size. Keys are always +64bits, although nesting allows you to use multiple keys. diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig new file mode 100644 index 000000000000..ceb359050a59 --- /dev/null +++ b/drivers/md/persistent-data/Kconfig @@ -0,0 +1,8 @@ +config DM_PERSISTENT_DATA + tristate + depends on BLK_DEV_DM && EXPERIMENTAL + select LIBCRC32C + select DM_BUFIO + ---help--- + Library providing immutable on-disk data structure support for + device-mapper targets such as the thin provisioning target. diff --git a/drivers/md/persistent-data/Makefile b/drivers/md/persistent-data/Makefile new file mode 100644 index 000000000000..cfa95f662230 --- /dev/null +++ b/drivers/md/persistent-data/Makefile @@ -0,0 +1,11 @@ +obj-$(CONFIG_DM_PERSISTENT_DATA) += dm-persistent-data.o +dm-persistent-data-objs := \ + dm-block-manager.o \ + dm-space-map-checker.o \ + dm-space-map-common.o \ + dm-space-map-disk.o \ + dm-space-map-metadata.o \ + dm-transaction-manager.o \ + dm-btree.o \ + dm-btree-remove.o \ + dm-btree-spine.o diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c new file mode 100644 index 000000000000..0317ecdc6e53 --- /dev/null +++ b/drivers/md/persistent-data/dm-block-manager.c @@ -0,0 +1,620 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ +#include "dm-block-manager.h" +#include "dm-persistent-data-internal.h" +#include "../dm-bufio.h" + +#include +#include +#include +#include +#include +#include + +#define DM_MSG_PREFIX "block manager" + +/*----------------------------------------------------------------*/ + +/* + * This is a read/write semaphore with a couple of differences. + * + * i) There is a restriction on the number of concurrent read locks that + * may be held at once. This is just an implementation detail. + * + * ii) Recursive locking attempts are detected and return EINVAL. A stack + * trace is also emitted for the previous lock aquisition. + * + * iii) Priority is given to write locks. + */ +#define MAX_HOLDERS 4 +#define MAX_STACK 10 + +typedef unsigned long stack_entries[MAX_STACK]; + +struct block_lock { + spinlock_t lock; + __s32 count; + struct list_head waiters; + struct task_struct *holders[MAX_HOLDERS]; + +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + struct stack_trace traces[MAX_HOLDERS]; + stack_entries entries[MAX_HOLDERS]; +#endif +}; + +struct waiter { + struct list_head list; + struct task_struct *task; + int wants_write; +}; + +static unsigned __find_holder(struct block_lock *lock, + struct task_struct *task) +{ + unsigned i; + + for (i = 0; i < MAX_HOLDERS; i++) + if (lock->holders[i] == task) + break; + + BUG_ON(i == MAX_HOLDERS); + return i; +} + +/* call this *after* you increment lock->count */ +static void __add_holder(struct block_lock *lock, struct task_struct *task) +{ + unsigned h = __find_holder(lock, NULL); +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + struct stack_trace *t; +#endif + + get_task_struct(task); + lock->holders[h] = task; + +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + t = lock->traces + h; + t->nr_entries = 0; + t->max_entries = MAX_STACK; + t->entries = lock->entries[h]; + t->skip = 2; + save_stack_trace(t); +#endif +} + +/* call this *before* you decrement lock->count */ +static void __del_holder(struct block_lock *lock, struct task_struct *task) +{ + unsigned h = __find_holder(lock, task); + lock->holders[h] = NULL; + put_task_struct(task); +} + +static int __check_holder(struct block_lock *lock) +{ + unsigned i; +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + static struct stack_trace t; + static stack_entries entries; +#endif + + for (i = 0; i < MAX_HOLDERS; i++) { + if (lock->holders[i] == current) { + DMERR("recursive lock detected in pool metadata"); +#ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING + DMERR("previously held here:"); + print_stack_trace(lock->traces + i, 4); + + DMERR("subsequent aquisition attempted here:"); + t.nr_entries = 0; + t.max_entries = MAX_STACK; + t.entries = entries; + t.skip = 3; + save_stack_trace(&t); + print_stack_trace(&t, 4); +#endif + return -EINVAL; + } + } + + return 0; +} + +static void __wait(struct waiter *w) +{ + for (;;) { + set_task_state(current, TASK_UNINTERRUPTIBLE); + + if (!w->task) + break; + + schedule(); + } + + set_task_state(current, TASK_RUNNING); +} + +static void __wake_waiter(struct waiter *w) +{ + struct task_struct *task; + + list_del(&w->list); + task = w->task; + smp_mb(); + w->task = NULL; + wake_up_process(task); +} + +/* + * We either wake a few readers or a single writer. + */ +static void __wake_many(struct block_lock *lock) +{ + struct waiter *w, *tmp; + + BUG_ON(lock->count < 0); + list_for_each_entry_safe(w, tmp, &lock->waiters, list) { + if (lock->count >= MAX_HOLDERS) + return; + + if (w->wants_write) { + if (lock->count > 0) + return; /* still read locked */ + + lock->count = -1; + __add_holder(lock, w->task); + __wake_waiter(w); + return; + } + + lock->count++; + __add_holder(lock, w->task); + __wake_waiter(w); + } +} + +static void bl_init(struct block_lock *lock) +{ + int i; + + spin_lock_init(&lock->lock); + lock->count = 0; + INIT_LIST_HEAD(&lock->waiters); + for (i = 0; i < MAX_HOLDERS; i++) + lock->holders[i] = NULL; +} + +static int __available_for_read(struct block_lock *lock) +{ + return lock->count >= 0 && + lock->count < MAX_HOLDERS && + list_empty(&lock->waiters); +} + +static int bl_down_read(struct block_lock *lock) +{ + int r; + struct waiter w; + + spin_lock(&lock->lock); + r = __check_holder(lock); + if (r) { + spin_unlock(&lock->lock); + return r; + } + + if (__available_for_read(lock)) { + lock->count++; + __add_holder(lock, current); + spin_unlock(&lock->lock); + return 0; + } + + get_task_struct(current); + + w.task = current; + w.wants_write = 0; + list_add_tail(&w.list, &lock->waiters); + spin_unlock(&lock->lock); + + __wait(&w); + put_task_struct(current); + return 0; +} + +static int bl_down_read_nonblock(struct block_lock *lock) +{ + int r; + + spin_lock(&lock->lock); + r = __check_holder(lock); + if (r) + goto out; + + if (__available_for_read(lock)) { + lock->count++; + __add_holder(lock, current); + r = 0; + } else + r = -EWOULDBLOCK; + +out: + spin_unlock(&lock->lock); + return r; +} + +static void bl_up_read(struct block_lock *lock) +{ + spin_lock(&lock->lock); + BUG_ON(lock->count <= 0); + __del_holder(lock, current); + --lock->count; + if (!list_empty(&lock->waiters)) + __wake_many(lock); + spin_unlock(&lock->lock); +} + +static int bl_down_write(struct block_lock *lock) +{ + int r; + struct waiter w; + + spin_lock(&lock->lock); + r = __check_holder(lock); + if (r) { + spin_unlock(&lock->lock); + return r; + } + + if (lock->count == 0 && list_empty(&lock->waiters)) { + lock->count = -1; + __add_holder(lock, current); + spin_unlock(&lock->lock); + return 0; + } + + get_task_struct(current); + w.task = current; + w.wants_write = 1; + + /* + * Writers given priority. We know there's only one mutator in the + * system, so ignoring the ordering reversal. + */ + list_add(&w.list, &lock->waiters); + spin_unlock(&lock->lock); + + __wait(&w); + put_task_struct(current); + + return 0; +} + +static void bl_up_write(struct block_lock *lock) +{ + spin_lock(&lock->lock); + __del_holder(lock, current); + lock->count = 0; + if (!list_empty(&lock->waiters)) + __wake_many(lock); + spin_unlock(&lock->lock); +} + +static void report_recursive_bug(dm_block_t b, int r) +{ + if (r == -EINVAL) + DMERR("recursive acquisition of block %llu requested.", + (unsigned long long) b); +} + +/*----------------------------------------------------------------*/ + +/* + * Block manager is currently implemented using dm-bufio. struct + * dm_block_manager and struct dm_block map directly onto a couple of + * structs in the bufio interface. I want to retain the freedom to move + * away from bufio in the future. So these structs are just cast within + * this .c file, rather than making it through to the public interface. + */ +static struct dm_buffer *to_buffer(struct dm_block *b) +{ + return (struct dm_buffer *) b; +} + +static struct dm_bufio_client *to_bufio(struct dm_block_manager *bm) +{ + return (struct dm_bufio_client *) bm; +} + +dm_block_t dm_block_location(struct dm_block *b) +{ + return dm_bufio_get_block_number(to_buffer(b)); +} +EXPORT_SYMBOL_GPL(dm_block_location); + +void *dm_block_data(struct dm_block *b) +{ + return dm_bufio_get_block_data(to_buffer(b)); +} +EXPORT_SYMBOL_GPL(dm_block_data); + +struct buffer_aux { + struct dm_block_validator *validator; + struct block_lock lock; + int write_locked; +}; + +static void dm_block_manager_alloc_callback(struct dm_buffer *buf) +{ + struct buffer_aux *aux = dm_bufio_get_aux_data(buf); + aux->validator = NULL; + bl_init(&aux->lock); +} + +static void dm_block_manager_write_callback(struct dm_buffer *buf) +{ + struct buffer_aux *aux = dm_bufio_get_aux_data(buf); + if (aux->validator) { + aux->validator->prepare_for_write(aux->validator, (struct dm_block *) buf, + dm_bufio_get_block_size(dm_bufio_get_client(buf))); + } +} + +/*---------------------------------------------------------------- + * Public interface + *--------------------------------------------------------------*/ +struct dm_block_manager *dm_block_manager_create(struct block_device *bdev, + unsigned block_size, + unsigned cache_size, + unsigned max_held_per_thread) +{ + return (struct dm_block_manager *) + dm_bufio_client_create(bdev, block_size, max_held_per_thread, + sizeof(struct buffer_aux), + dm_block_manager_alloc_callback, + dm_block_manager_write_callback); +} +EXPORT_SYMBOL_GPL(dm_block_manager_create); + +void dm_block_manager_destroy(struct dm_block_manager *bm) +{ + return dm_bufio_client_destroy(to_bufio(bm)); +} +EXPORT_SYMBOL_GPL(dm_block_manager_destroy); + +unsigned dm_bm_block_size(struct dm_block_manager *bm) +{ + return dm_bufio_get_block_size(to_bufio(bm)); +} +EXPORT_SYMBOL_GPL(dm_bm_block_size); + +dm_block_t dm_bm_nr_blocks(struct dm_block_manager *bm) +{ + return dm_bufio_get_device_size(to_bufio(bm)); +} + +static int dm_bm_validate_buffer(struct dm_block_manager *bm, + struct dm_buffer *buf, + struct buffer_aux *aux, + struct dm_block_validator *v) +{ + if (unlikely(!aux->validator)) { + int r; + if (!v) + return 0; + r = v->check(v, (struct dm_block *) buf, dm_bufio_get_block_size(to_bufio(bm))); + if (unlikely(r)) + return r; + aux->validator = v; + } else { + if (unlikely(aux->validator != v)) { + DMERR("validator mismatch (old=%s vs new=%s) for block %llu", + aux->validator->name, v ? v->name : "NULL", + (unsigned long long) + dm_bufio_get_block_number(buf)); + return -EINVAL; + } + } + + return 0; +} +int dm_bm_read_lock(struct dm_block_manager *bm, dm_block_t b, + struct dm_block_validator *v, + struct dm_block **result) +{ + struct buffer_aux *aux; + void *p; + int r; + + p = dm_bufio_read(to_bufio(bm), b, (struct dm_buffer **) result); + if (unlikely(IS_ERR(p))) + return PTR_ERR(p); + + aux = dm_bufio_get_aux_data(to_buffer(*result)); + r = bl_down_read(&aux->lock); + if (unlikely(r)) { + dm_bufio_release(to_buffer(*result)); + report_recursive_bug(b, r); + return r; + } + + aux->write_locked = 0; + + r = dm_bm_validate_buffer(bm, to_buffer(*result), aux, v); + if (unlikely(r)) { + bl_up_read(&aux->lock); + dm_bufio_release(to_buffer(*result)); + return r; + } + + return 0; +} +EXPORT_SYMBOL_GPL(dm_bm_read_lock); + +int dm_bm_write_lock(struct dm_block_manager *bm, + dm_block_t b, struct dm_block_validator *v, + struct dm_block **result) +{ + struct buffer_aux *aux; + void *p; + int r; + + p = dm_bufio_read(to_bufio(bm), b, (struct dm_buffer **) result); + if (unlikely(IS_ERR(p))) + return PTR_ERR(p); + + aux = dm_bufio_get_aux_data(to_buffer(*result)); + r = bl_down_write(&aux->lock); + if (r) { + dm_bufio_release(to_buffer(*result)); + report_recursive_bug(b, r); + return r; + } + + aux->write_locked = 1; + + r = dm_bm_validate_buffer(bm, to_buffer(*result), aux, v); + if (unlikely(r)) { + bl_up_write(&aux->lock); + dm_bufio_release(to_buffer(*result)); + return r; + } + + return 0; +} +EXPORT_SYMBOL_GPL(dm_bm_write_lock); + +int dm_bm_read_try_lock(struct dm_block_manager *bm, + dm_block_t b, struct dm_block_validator *v, + struct dm_block **result) +{ + struct buffer_aux *aux; + void *p; + int r; + + p = dm_bufio_get(to_bufio(bm), b, (struct dm_buffer **) result); + if (unlikely(IS_ERR(p))) + return PTR_ERR(p); + if (unlikely(!p)) + return -EWOULDBLOCK; + + aux = dm_bufio_get_aux_data(to_buffer(*result)); + r = bl_down_read_nonblock(&aux->lock); + if (r < 0) { + dm_bufio_release(to_buffer(*result)); + report_recursive_bug(b, r); + return r; + } + aux->write_locked = 0; + + r = dm_bm_validate_buffer(bm, to_buffer(*result), aux, v); + if (unlikely(r)) { + bl_up_read(&aux->lock); + dm_bufio_release(to_buffer(*result)); + return r; + } + + return 0; +} + +int dm_bm_write_lock_zero(struct dm_block_manager *bm, + dm_block_t b, struct dm_block_validator *v, + struct dm_block **result) +{ + int r; + struct buffer_aux *aux; + void *p; + + p = dm_bufio_new(to_bufio(bm), b, (struct dm_buffer **) result); + if (unlikely(IS_ERR(p))) + return PTR_ERR(p); + + memset(p, 0, dm_bm_block_size(bm)); + + aux = dm_bufio_get_aux_data(to_buffer(*result)); + r = bl_down_write(&aux->lock); + if (r) { + dm_bufio_release(to_buffer(*result)); + return r; + } + + aux->write_locked = 1; + aux->validator = v; + + return 0; +} + +int dm_bm_unlock(struct dm_block *b) +{ + struct buffer_aux *aux; + aux = dm_bufio_get_aux_data(to_buffer(b)); + + if (aux->write_locked) { + dm_bufio_mark_buffer_dirty(to_buffer(b)); + bl_up_write(&aux->lock); + } else + bl_up_read(&aux->lock); + + dm_bufio_release(to_buffer(b)); + + return 0; +} +EXPORT_SYMBOL_GPL(dm_bm_unlock); + +int dm_bm_unlock_move(struct dm_block *b, dm_block_t n) +{ + struct buffer_aux *aux; + + aux = dm_bufio_get_aux_data(to_buffer(b)); + + if (aux->write_locked) { + dm_bufio_mark_buffer_dirty(to_buffer(b)); + bl_up_write(&aux->lock); + } else + bl_up_read(&aux->lock); + + dm_bufio_release_move(to_buffer(b), n); + return 0; +} + +int dm_bm_flush_and_unlock(struct dm_block_manager *bm, + struct dm_block *superblock) +{ + int r; + + r = dm_bufio_write_dirty_buffers(to_bufio(bm)); + if (unlikely(r)) + return r; + r = dm_bufio_issue_flush(to_bufio(bm)); + if (unlikely(r)) + return r; + + dm_bm_unlock(superblock); + + r = dm_bufio_write_dirty_buffers(to_bufio(bm)); + if (unlikely(r)) + return r; + r = dm_bufio_issue_flush(to_bufio(bm)); + if (unlikely(r)) + return r; + + return 0; +} + +u32 dm_bm_checksum(const void *data, size_t len, u32 init_xor) +{ + return crc32c(~(u32) 0, data, len) ^ init_xor; +} +EXPORT_SYMBOL_GPL(dm_bm_checksum); + +/*----------------------------------------------------------------*/ + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Joe Thornber "); +MODULE_DESCRIPTION("Immutable metadata library for dm"); + +/*----------------------------------------------------------------*/ diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h new file mode 100644 index 000000000000..924833d2dfa6 --- /dev/null +++ b/drivers/md/persistent-data/dm-block-manager.h @@ -0,0 +1,123 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef _LINUX_DM_BLOCK_MANAGER_H +#define _LINUX_DM_BLOCK_MANAGER_H + +#include +#include + +/*----------------------------------------------------------------*/ + +/* + * Block number. + */ +typedef uint64_t dm_block_t; +struct dm_block; + +dm_block_t dm_block_location(struct dm_block *b); +void *dm_block_data(struct dm_block *b); + +/*----------------------------------------------------------------*/ + +/* + * @name should be a unique identifier for the block manager, no longer + * than 32 chars. + * + * @max_held_per_thread should be the maximum number of locks, read or + * write, that an individual thread holds at any one time. + */ +struct dm_block_manager; +struct dm_block_manager *dm_block_manager_create( + struct block_device *bdev, unsigned block_size, + unsigned cache_size, unsigned max_held_per_thread); +void dm_block_manager_destroy(struct dm_block_manager *bm); + +unsigned dm_bm_block_size(struct dm_block_manager *bm); +dm_block_t dm_bm_nr_blocks(struct dm_block_manager *bm); + +/*----------------------------------------------------------------*/ + +/* + * The validator allows the caller to verify newly-read data and modify + * the data just before writing, e.g. to calculate checksums. It's + * important to be consistent with your use of validators. The only time + * you can change validators is if you call dm_bm_write_lock_zero. + */ +struct dm_block_validator { + const char *name; + void (*prepare_for_write)(struct dm_block_validator *v, struct dm_block *b, size_t block_size); + + /* + * Return 0 if the checksum is valid or < 0 on error. + */ + int (*check)(struct dm_block_validator *v, struct dm_block *b, size_t block_size); +}; + +/*----------------------------------------------------------------*/ + +/* + * You can have multiple concurrent readers or a single writer holding a + * block lock. + */ + +/* + * dm_bm_lock() locks a block and returns through @result a pointer to + * memory that holds a copy of that block. If you have write-locked the + * block then any changes you make to memory pointed to by @result will be + * written back to the disk sometime after dm_bm_unlock is called. + */ +int dm_bm_read_lock(struct dm_block_manager *bm, dm_block_t b, + struct dm_block_validator *v, + struct dm_block **result); + +int dm_bm_write_lock(struct dm_block_manager *bm, dm_block_t b, + struct dm_block_validator *v, + struct dm_block **result); + +/* + * The *_try_lock variants return -EWOULDBLOCK if the block isn't + * available immediately. + */ +int dm_bm_read_try_lock(struct dm_block_manager *bm, dm_block_t b, + struct dm_block_validator *v, + struct dm_block **result); + +/* + * Use dm_bm_write_lock_zero() when you know you're going to + * overwrite the block completely. It saves a disk read. + */ +int dm_bm_write_lock_zero(struct dm_block_manager *bm, dm_block_t b, + struct dm_block_validator *v, + struct dm_block **result); + +int dm_bm_unlock(struct dm_block *b); + +/* + * An optimisation; we often want to copy a block's contents to a new + * block. eg, as part of the shadowing operation. It's far better for + * bufio to do this move behind the scenes than hold 2 locks and memcpy the + * data. + */ +int dm_bm_unlock_move(struct dm_block *b, dm_block_t n); + +/* + * It's a common idiom to have a superblock that should be committed last. + * + * @superblock should be write-locked on entry. It will be unlocked during + * this function. All dirty blocks are guaranteed to be written and flushed + * before the superblock. + * + * This method always blocks. + */ +int dm_bm_flush_and_unlock(struct dm_block_manager *bm, + struct dm_block *superblock); + +u32 dm_bm_checksum(const void *data, size_t len, u32 init_xor); + +/*----------------------------------------------------------------*/ + +#endif /* _LINUX_DM_BLOCK_MANAGER_H */ diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h new file mode 100644 index 000000000000..d279c768f8f1 --- /dev/null +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -0,0 +1,137 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef DM_BTREE_INTERNAL_H +#define DM_BTREE_INTERNAL_H + +#include "dm-btree.h" + +/*----------------------------------------------------------------*/ + +/* + * We'll need 2 accessor functions for n->csum and n->blocknr + * to support dm-btree-spine.c in that case. + */ + +enum node_flags { + INTERNAL_NODE = 1, + LEAF_NODE = 1 << 1 +}; + +/* + * Every btree node begins with this structure. Make sure it's a multiple + * of 8-bytes in size, otherwise the 64bit keys will be mis-aligned. + */ +struct node_header { + __le32 csum; + __le32 flags; + __le64 blocknr; /* Block this node is supposed to live in. */ + + __le32 nr_entries; + __le32 max_entries; + __le32 value_size; + __le32 padding; +} __packed; + +struct node { + struct node_header header; + __le64 keys[0]; +} __packed; + + +void inc_children(struct dm_transaction_manager *tm, struct node *n, + struct dm_btree_value_type *vt); + +int new_block(struct dm_btree_info *info, struct dm_block **result); +int unlock_block(struct dm_btree_info *info, struct dm_block *b); + +/* + * Spines keep track of the rolling locks. There are 2 variants, read-only + * and one that uses shadowing. These are separate structs to allow the + * type checker to spot misuse, for example accidentally calling read_lock + * on a shadow spine. + */ +struct ro_spine { + struct dm_btree_info *info; + + int count; + struct dm_block *nodes[2]; +}; + +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); +struct node *ro_node(struct ro_spine *s); + +struct shadow_spine { + struct dm_btree_info *info; + + int count; + struct dm_block *nodes[2]; + + dm_block_t root; +}; + +void init_shadow_spine(struct shadow_spine *s, struct dm_btree_info *info); +int exit_shadow_spine(struct shadow_spine *s); + +int shadow_step(struct shadow_spine *s, dm_block_t b, + struct dm_btree_value_type *vt); + +/* + * The spine must have at least one entry before calling this. + */ +struct dm_block *shadow_current(struct shadow_spine *s); + +/* + * The spine must have at least two entries before calling this. + */ +struct dm_block *shadow_parent(struct shadow_spine *s); + +int shadow_has_parent(struct shadow_spine *s); + +int shadow_root(struct shadow_spine *s); + +/* + * Some inlines. + */ +static inline __le64 *key_ptr(struct node *n, uint32_t index) +{ + return n->keys + index; +} + +static inline void *value_base(struct node *n) +{ + return &n->keys[le32_to_cpu(n->header.max_entries)]; +} + +/* + * FIXME: Now that value size is stored in node we don't need the third parm. + */ +static inline void *value_ptr(struct node *n, uint32_t index, size_t value_size) +{ + BUG_ON(value_size != le32_to_cpu(n->header.value_size)); + return value_base(n) + (value_size * index); +} + +/* + * Assumes the values are suitably-aligned and converts to core format. + */ +static inline uint64_t value64(struct node *n, uint32_t index) +{ + __le64 *values_le = value_base(n); + + return le64_to_cpu(values_le[index]); +} + +/* + * Searching for a key within a single node. + */ +int lower_bound(struct node *n, uint64_t key); + +extern struct dm_block_validator btree_node_validator; + +#endif /* DM_BTREE_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c new file mode 100644 index 000000000000..65fd85ec6514 --- /dev/null +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -0,0 +1,566 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-btree.h" +#include "dm-btree-internal.h" +#include "dm-transaction-manager.h" + +#include + +/* + * Removing an entry from a btree + * ============================== + * + * A very important constraint for our btree is that no node, except the + * root, may have fewer than a certain number of entries. + * (MIN_ENTRIES <= nr_entries <= MAX_ENTRIES). + * + * Ensuring this is complicated by the way we want to only ever hold the + * locks on 2 nodes concurrently, and only change nodes in a top to bottom + * fashion. + * + * Each node may have a left or right sibling. When decending the spine, + * if a node contains only MIN_ENTRIES then we try and increase this to at + * least MIN_ENTRIES + 1. We do this in the following ways: + * + * [A] No siblings => this can only happen if the node is the root, in which + * case we copy the childs contents over the root. + * + * [B] No left sibling + * ==> rebalance(node, right sibling) + * + * [C] No right sibling + * ==> rebalance(left sibling, node) + * + * [D] Both siblings, total_entries(left, node, right) <= DEL_THRESHOLD + * ==> delete node adding it's contents to left and right + * + * [E] Both siblings, total_entries(left, node, right) > DEL_THRESHOLD + * ==> rebalance(left, node, right) + * + * After these operations it's possible that the our original node no + * longer contains the desired sub tree. For this reason this rebalancing + * is performed on the children of the current node. This also avoids + * having a special case for the root. + * + * Once this rebalancing has occurred we can then step into the child node + * for internal nodes. Or delete the entry for leaf nodes. + */ + +/* + * Some little utilities for moving node data around. + */ +static void node_shift(struct node *n, int shift) +{ + uint32_t nr_entries = le32_to_cpu(n->header.nr_entries); + uint32_t value_size = le32_to_cpu(n->header.value_size); + + if (shift < 0) { + shift = -shift; + BUG_ON(shift > nr_entries); + BUG_ON((void *) key_ptr(n, shift) >= value_ptr(n, shift, value_size)); + memmove(key_ptr(n, 0), + key_ptr(n, shift), + (nr_entries - shift) * sizeof(__le64)); + memmove(value_ptr(n, 0, value_size), + value_ptr(n, shift, value_size), + (nr_entries - shift) * value_size); + } else { + BUG_ON(nr_entries + shift > le32_to_cpu(n->header.max_entries)); + memmove(key_ptr(n, shift), + key_ptr(n, 0), + nr_entries * sizeof(__le64)); + memmove(value_ptr(n, shift, value_size), + value_ptr(n, 0, value_size), + nr_entries * value_size); + } +} + +static void node_copy(struct node *left, struct node *right, int shift) +{ + uint32_t nr_left = le32_to_cpu(left->header.nr_entries); + uint32_t value_size = le32_to_cpu(left->header.value_size); + BUG_ON(value_size != le32_to_cpu(right->header.value_size)); + + if (shift < 0) { + shift = -shift; + BUG_ON(nr_left + shift > le32_to_cpu(left->header.max_entries)); + memcpy(key_ptr(left, nr_left), + key_ptr(right, 0), + shift * sizeof(__le64)); + memcpy(value_ptr(left, nr_left, value_size), + value_ptr(right, 0, value_size), + shift * value_size); + } else { + BUG_ON(shift > le32_to_cpu(right->header.max_entries)); + memcpy(key_ptr(right, 0), + key_ptr(left, nr_left - shift), + shift * sizeof(__le64)); + memcpy(value_ptr(right, 0, value_size), + value_ptr(left, nr_left - shift, value_size), + shift * value_size); + } +} + +/* + * Delete a specific entry from a leaf node. + */ +static void delete_at(struct node *n, unsigned index) +{ + unsigned nr_entries = le32_to_cpu(n->header.nr_entries); + unsigned nr_to_copy = nr_entries - (index + 1); + uint32_t value_size = le32_to_cpu(n->header.value_size); + BUG_ON(index >= nr_entries); + + if (nr_to_copy) { + memmove(key_ptr(n, index), + key_ptr(n, index + 1), + nr_to_copy * sizeof(__le64)); + + memmove(value_ptr(n, index, value_size), + value_ptr(n, index + 1, value_size), + nr_to_copy * value_size); + } + + n->header.nr_entries = cpu_to_le32(nr_entries - 1); +} + +static unsigned del_threshold(struct node *n) +{ + return le32_to_cpu(n->header.max_entries) / 3; +} + +static unsigned merge_threshold(struct node *n) +{ + /* + * The extra one is because we know we're potentially going to + * delete an entry. + */ + return 2 * (le32_to_cpu(n->header.max_entries) / 3) + 1; +} + +struct child { + unsigned index; + struct dm_block *block; + struct node *n; +}; + +static struct dm_btree_value_type le64_type = { + .context = NULL, + .size = sizeof(__le64), + .inc = NULL, + .dec = NULL, + .equal = NULL +}; + +static int init_child(struct dm_btree_info *info, struct node *parent, + unsigned index, struct child *result) +{ + int r, inc; + dm_block_t root; + + result->index = index; + root = value64(parent, index); + + r = dm_tm_shadow_block(info->tm, root, &btree_node_validator, + &result->block, &inc); + if (r) + return r; + + result->n = dm_block_data(result->block); + + if (inc) + inc_children(info->tm, result->n, &le64_type); + + *((__le64 *) value_ptr(parent, index, sizeof(__le64))) = + cpu_to_le64(dm_block_location(result->block)); + + return 0; +} + +static int exit_child(struct dm_btree_info *info, struct child *c) +{ + return dm_tm_unlock(info->tm, c->block); +} + +static void shift(struct node *left, struct node *right, int count) +{ + if (!count) + return; + + if (count > 0) { + node_shift(right, count); + node_copy(left, right, count); + } else { + node_copy(left, right, count); + node_shift(right, count); + } + + left->header.nr_entries = + cpu_to_le32(le32_to_cpu(left->header.nr_entries) - count); + BUG_ON(le32_to_cpu(left->header.nr_entries) > le32_to_cpu(left->header.max_entries)); + + right->header.nr_entries = + cpu_to_le32(le32_to_cpu(right->header.nr_entries) + count); + BUG_ON(le32_to_cpu(right->header.nr_entries) > le32_to_cpu(right->header.max_entries)); +} + +static void __rebalance2(struct dm_btree_info *info, struct node *parent, + struct child *l, struct child *r) +{ + struct node *left = l->n; + struct node *right = r->n; + uint32_t nr_left = le32_to_cpu(left->header.nr_entries); + uint32_t nr_right = le32_to_cpu(right->header.nr_entries); + + if (nr_left + nr_right <= merge_threshold(left)) { + /* + * Merge + */ + node_copy(left, right, -nr_right); + left->header.nr_entries = cpu_to_le32(nr_left + nr_right); + delete_at(parent, r->index); + + /* + * We need to decrement the right block, but not it's + * children, since they're still referenced by left. + */ + dm_tm_dec(info->tm, dm_block_location(r->block)); + } else { + /* + * Rebalance. + */ + unsigned target_left = (nr_left + nr_right) / 2; + unsigned shift_ = nr_left - target_left; + BUG_ON(le32_to_cpu(left->header.max_entries) <= nr_left - shift_); + BUG_ON(le32_to_cpu(right->header.max_entries) <= nr_right + shift_); + shift(left, right, nr_left - target_left); + *key_ptr(parent, r->index) = right->keys[0]; + } +} + +static int rebalance2(struct shadow_spine *s, struct dm_btree_info *info, + unsigned left_index) +{ + int r; + struct node *parent; + struct child left, right; + + parent = dm_block_data(shadow_current(s)); + + r = init_child(info, parent, left_index, &left); + if (r) + return r; + + r = init_child(info, parent, left_index + 1, &right); + if (r) { + exit_child(info, &left); + return r; + } + + __rebalance2(info, parent, &left, &right); + + r = exit_child(info, &left); + if (r) { + exit_child(info, &right); + return r; + } + + return exit_child(info, &right); +} + +static void __rebalance3(struct dm_btree_info *info, struct node *parent, + struct child *l, struct child *c, struct child *r) +{ + struct node *left = l->n; + struct node *center = c->n; + struct node *right = r->n; + + uint32_t nr_left = le32_to_cpu(left->header.nr_entries); + uint32_t nr_center = le32_to_cpu(center->header.nr_entries); + uint32_t nr_right = le32_to_cpu(right->header.nr_entries); + uint32_t max_entries = le32_to_cpu(left->header.max_entries); + + unsigned target; + + BUG_ON(left->header.max_entries != center->header.max_entries); + BUG_ON(center->header.max_entries != right->header.max_entries); + + if (((nr_left + nr_center + nr_right) / 2) < merge_threshold(center)) { + /* + * Delete center node: + * + * We dump as many entries from center as possible into + * left, then the rest in right, then rebalance2. This + * wastes some cpu, but I want something simple atm. + */ + unsigned shift = min(max_entries - nr_left, nr_center); + + BUG_ON(nr_left + shift > max_entries); + node_copy(left, center, -shift); + left->header.nr_entries = cpu_to_le32(nr_left + shift); + + if (shift != nr_center) { + shift = nr_center - shift; + BUG_ON((nr_right + shift) >= max_entries); + node_shift(right, shift); + node_copy(center, right, shift); + right->header.nr_entries = cpu_to_le32(nr_right + shift); + } + *key_ptr(parent, r->index) = right->keys[0]; + + delete_at(parent, c->index); + r->index--; + + dm_tm_dec(info->tm, dm_block_location(c->block)); + __rebalance2(info, parent, l, r); + + return; + } + + /* + * Rebalance + */ + target = (nr_left + nr_center + nr_right) / 3; + BUG_ON(target > max_entries); + + /* + * Adjust the left node + */ + shift(left, center, nr_left - target); + + /* + * Adjust the right node + */ + shift(center, right, target - nr_right); + *key_ptr(parent, c->index) = center->keys[0]; + *key_ptr(parent, r->index) = right->keys[0]; +} + +static int rebalance3(struct shadow_spine *s, struct dm_btree_info *info, + unsigned left_index) +{ + int r; + struct node *parent = dm_block_data(shadow_current(s)); + struct child left, center, right; + + /* + * FIXME: fill out an array? + */ + r = init_child(info, parent, left_index, &left); + if (r) + return r; + + r = init_child(info, parent, left_index + 1, ¢er); + if (r) { + exit_child(info, &left); + return r; + } + + r = init_child(info, parent, left_index + 2, &right); + if (r) { + exit_child(info, &left); + exit_child(info, ¢er); + return r; + } + + __rebalance3(info, parent, &left, ¢er, &right); + + r = exit_child(info, &left); + if (r) { + exit_child(info, ¢er); + exit_child(info, &right); + return r; + } + + r = exit_child(info, ¢er); + if (r) { + exit_child(info, &right); + return r; + } + + r = exit_child(info, &right); + if (r) + return r; + + return 0; +} + +static int get_nr_entries(struct dm_transaction_manager *tm, + dm_block_t b, uint32_t *result) +{ + int r; + struct dm_block *block; + struct node *n; + + r = dm_tm_read_lock(tm, b, &btree_node_validator, &block); + if (r) + return r; + + n = dm_block_data(block); + *result = le32_to_cpu(n->header.nr_entries); + + return dm_tm_unlock(tm, block); +} + +static int rebalance_children(struct shadow_spine *s, + struct dm_btree_info *info, uint64_t key) +{ + int i, r, has_left_sibling, has_right_sibling; + uint32_t child_entries; + struct node *n; + + n = dm_block_data(shadow_current(s)); + + if (le32_to_cpu(n->header.nr_entries) == 1) { + struct dm_block *child; + dm_block_t b = value64(n, 0); + + r = dm_tm_read_lock(info->tm, b, &btree_node_validator, &child); + if (r) + return r; + + memcpy(n, dm_block_data(child), + dm_bm_block_size(dm_tm_get_bm(info->tm))); + r = dm_tm_unlock(info->tm, child); + if (r) + return r; + + dm_tm_dec(info->tm, dm_block_location(child)); + return 0; + } + + i = lower_bound(n, key); + if (i < 0) + return -ENODATA; + + r = get_nr_entries(info->tm, value64(n, i), &child_entries); + if (r) + return r; + + if (child_entries > del_threshold(n)) + return 0; + + has_left_sibling = i > 0; + has_right_sibling = i < (le32_to_cpu(n->header.nr_entries) - 1); + + if (!has_left_sibling) + r = rebalance2(s, info, i); + + else if (!has_right_sibling) + r = rebalance2(s, info, i - 1); + + else + r = rebalance3(s, info, i - 1); + + return r; +} + +static int do_leaf(struct node *n, uint64_t key, unsigned *index) +{ + int i = lower_bound(n, key); + + if ((i < 0) || + (i >= le32_to_cpu(n->header.nr_entries)) || + (le64_to_cpu(n->keys[i]) != key)) + return -ENODATA; + + *index = i; + + return 0; +} + +/* + * Prepares for removal from one level of the hierarchy. The caller must + * call delete_at() to remove the entry at index. + */ +static int remove_raw(struct shadow_spine *s, struct dm_btree_info *info, + struct dm_btree_value_type *vt, dm_block_t root, + uint64_t key, unsigned *index) +{ + int i = *index, r; + struct node *n; + + for (;;) { + r = shadow_step(s, root, vt); + if (r < 0) + break; + + /* + * We have to patch up the parent node, ugly, but I don't + * see a way to do this automatically as part of the spine + * op. + */ + if (shadow_has_parent(s)) { + __le64 location = cpu_to_le64(dm_block_location(shadow_current(s))); + memcpy(value_ptr(dm_block_data(shadow_parent(s)), i, sizeof(__le64)), + &location, sizeof(__le64)); + } + + n = dm_block_data(shadow_current(s)); + + if (le32_to_cpu(n->header.flags) & LEAF_NODE) + return do_leaf(n, key, index); + + r = rebalance_children(s, info, key); + if (r) + break; + + n = dm_block_data(shadow_current(s)); + if (le32_to_cpu(n->header.flags) & LEAF_NODE) + return do_leaf(n, key, index); + + i = lower_bound(n, key); + + /* + * We know the key is present, or else + * rebalance_children would have returned + * -ENODATA + */ + root = value64(n, i); + } + + return r; +} + +int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, dm_block_t *new_root) +{ + unsigned level, last_level = info->levels - 1; + int index = 0, r = 0; + struct shadow_spine spine; + struct node *n; + + init_shadow_spine(&spine, info); + for (level = 0; level < info->levels; level++) { + r = remove_raw(&spine, info, + (level == last_level ? + &info->value_type : &le64_type), + root, keys[level], (unsigned *)&index); + if (r < 0) + break; + + n = dm_block_data(shadow_current(&spine)); + if (level != last_level) { + root = value64(n, index); + continue; + } + + BUG_ON(index < 0 || index >= le32_to_cpu(n->header.nr_entries)); + + if (info->value_type.dec) + info->value_type.dec(info->value_type.context, + value_ptr(n, index, info->value_type.size)); + + delete_at(n, index); + } + + *new_root = shadow_root(&spine); + exit_shadow_spine(&spine); + + return r; +} +EXPORT_SYMBOL_GPL(dm_btree_remove); diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c new file mode 100644 index 000000000000..d9a7912ee8ee --- /dev/null +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -0,0 +1,244 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-btree-internal.h" +#include "dm-transaction-manager.h" + +#include + +#define DM_MSG_PREFIX "btree spine" + +/*----------------------------------------------------------------*/ + +#define BTREE_CSUM_XOR 121107 + +static int node_check(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size); + +static void node_prepare_for_write(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct node *n = dm_block_data(b); + struct node_header *h = &n->header; + + h->blocknr = cpu_to_le64(dm_block_location(b)); + h->csum = cpu_to_le32(dm_bm_checksum(&h->flags, + block_size - sizeof(__le32), + BTREE_CSUM_XOR)); + + BUG_ON(node_check(v, b, 4096)); +} + +static int node_check(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct node *n = dm_block_data(b); + struct node_header *h = &n->header; + size_t value_size; + __le32 csum_disk; + uint32_t flags; + + if (dm_block_location(b) != le64_to_cpu(h->blocknr)) { + DMERR("node_check failed blocknr %llu wanted %llu", + le64_to_cpu(h->blocknr), dm_block_location(b)); + return -ENOTBLK; + } + + csum_disk = cpu_to_le32(dm_bm_checksum(&h->flags, + block_size - sizeof(__le32), + BTREE_CSUM_XOR)); + if (csum_disk != h->csum) { + DMERR("node_check failed csum %u wanted %u", + le32_to_cpu(csum_disk), le32_to_cpu(h->csum)); + return -EILSEQ; + } + + value_size = le32_to_cpu(h->value_size); + + if (sizeof(struct node_header) + + (sizeof(__le64) + value_size) * le32_to_cpu(h->max_entries) > block_size) { + DMERR("node_check failed: max_entries too large"); + return -EILSEQ; + } + + if (le32_to_cpu(h->nr_entries) > le32_to_cpu(h->max_entries)) { + DMERR("node_check failed, too many entries"); + return -EILSEQ; + } + + /* + * The node must be either INTERNAL or LEAF. + */ + flags = le32_to_cpu(h->flags); + if (!(flags & INTERNAL_NODE) && !(flags & LEAF_NODE)) { + DMERR("node_check failed, node is neither INTERNAL or LEAF"); + return -EILSEQ; + } + + return 0; +} + +struct dm_block_validator btree_node_validator = { + .name = "btree_node", + .prepare_for_write = node_prepare_for_write, + .check = node_check +}; + +/*----------------------------------------------------------------*/ + +static int bn_read_lock(struct dm_btree_info *info, dm_block_t b, + struct dm_block **result) +{ + return dm_tm_read_lock(info->tm, b, &btree_node_validator, result); +} + +static int bn_shadow(struct dm_btree_info *info, dm_block_t orig, + struct dm_btree_value_type *vt, + struct dm_block **result) +{ + int r, inc; + + r = dm_tm_shadow_block(info->tm, orig, &btree_node_validator, + result, &inc); + if (!r && inc) + inc_children(info->tm, dm_block_data(*result), vt); + + return r; +} + +int new_block(struct dm_btree_info *info, struct dm_block **result) +{ + return dm_tm_new_block(info->tm, &btree_node_validator, result); +} + +int unlock_block(struct dm_btree_info *info, struct dm_block *b) +{ + return dm_tm_unlock(info->tm, b); +} + +/*----------------------------------------------------------------*/ + +void init_ro_spine(struct ro_spine *s, struct dm_btree_info *info) +{ + s->info = info; + s->count = 0; + s->nodes[0] = NULL; + s->nodes[1] = NULL; +} + +int exit_ro_spine(struct ro_spine *s) +{ + int r = 0, i; + + for (i = 0; i < s->count; i++) { + int r2 = unlock_block(s->info, s->nodes[i]); + if (r2 < 0) + r = r2; + } + + return r; +} + +int ro_step(struct ro_spine *s, dm_block_t new_child) +{ + int r; + + if (s->count == 2) { + r = unlock_block(s->info, s->nodes[0]); + if (r < 0) + return r; + s->nodes[0] = s->nodes[1]; + s->count--; + } + + r = bn_read_lock(s->info, new_child, s->nodes + s->count); + if (!r) + s->count++; + + return r; +} + +struct node *ro_node(struct ro_spine *s) +{ + struct dm_block *block; + + BUG_ON(!s->count); + block = s->nodes[s->count - 1]; + + return dm_block_data(block); +} + +/*----------------------------------------------------------------*/ + +void init_shadow_spine(struct shadow_spine *s, struct dm_btree_info *info) +{ + s->info = info; + s->count = 0; +} + +int exit_shadow_spine(struct shadow_spine *s) +{ + int r = 0, i; + + for (i = 0; i < s->count; i++) { + int r2 = unlock_block(s->info, s->nodes[i]); + if (r2 < 0) + r = r2; + } + + return r; +} + +int shadow_step(struct shadow_spine *s, dm_block_t b, + struct dm_btree_value_type *vt) +{ + int r; + + if (s->count == 2) { + r = unlock_block(s->info, s->nodes[0]); + if (r < 0) + return r; + s->nodes[0] = s->nodes[1]; + s->count--; + } + + r = bn_shadow(s->info, b, vt, s->nodes + s->count); + if (!r) { + if (!s->count) + s->root = dm_block_location(s->nodes[0]); + + s->count++; + } + + return r; +} + +struct dm_block *shadow_current(struct shadow_spine *s) +{ + BUG_ON(!s->count); + + return s->nodes[s->count - 1]; +} + +struct dm_block *shadow_parent(struct shadow_spine *s) +{ + BUG_ON(s->count != 2); + + return s->count == 2 ? s->nodes[0] : NULL; +} + +int shadow_has_parent(struct shadow_spine *s) +{ + return s->count >= 2; +} + +int shadow_root(struct shadow_spine *s) +{ + return s->root; +} diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c new file mode 100644 index 000000000000..e0638be53ea4 --- /dev/null +++ b/drivers/md/persistent-data/dm-btree.c @@ -0,0 +1,805 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-btree-internal.h" +#include "dm-space-map.h" +#include "dm-transaction-manager.h" + +#include +#include + +#define DM_MSG_PREFIX "btree" + +/*---------------------------------------------------------------- + * Array manipulation + *--------------------------------------------------------------*/ +static void memcpy_disk(void *dest, const void *src, size_t len) + __dm_written_to_disk(src) +{ + memcpy(dest, src, len); + __dm_unbless_for_disk(src); +} + +static void array_insert(void *base, size_t elt_size, unsigned nr_elts, + unsigned index, void *elt) + __dm_written_to_disk(elt) +{ + if (index < nr_elts) + memmove(base + (elt_size * (index + 1)), + base + (elt_size * index), + (nr_elts - index) * elt_size); + + memcpy_disk(base + (elt_size * index), elt, elt_size); +} + +/*----------------------------------------------------------------*/ + +/* makes the assumption that no two keys are the same. */ +static int bsearch(struct node *n, uint64_t key, int want_hi) +{ + int lo = -1, hi = le32_to_cpu(n->header.nr_entries); + + while (hi - lo > 1) { + int mid = lo + ((hi - lo) / 2); + uint64_t mid_key = le64_to_cpu(n->keys[mid]); + + if (mid_key == key) + return mid; + + if (mid_key < key) + lo = mid; + else + hi = mid; + } + + return want_hi ? hi : lo; +} + +int lower_bound(struct node *n, uint64_t key) +{ + return bsearch(n, key, 0); +} + +void inc_children(struct dm_transaction_manager *tm, struct node *n, + struct dm_btree_value_type *vt) +{ + unsigned i; + uint32_t nr_entries = le32_to_cpu(n->header.nr_entries); + + if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) + for (i = 0; i < nr_entries; i++) + dm_tm_inc(tm, value64(n, i)); + else if (vt->inc) + for (i = 0; i < nr_entries; i++) + vt->inc(vt->context, + value_ptr(n, i, vt->size)); +} + +static int insert_at(size_t value_size, struct node *node, unsigned index, + uint64_t key, void *value) + __dm_written_to_disk(value) +{ + uint32_t nr_entries = le32_to_cpu(node->header.nr_entries); + __le64 key_le = cpu_to_le64(key); + + if (index > nr_entries || + index >= le32_to_cpu(node->header.max_entries)) { + DMERR("too many entries in btree node for insert"); + __dm_unbless_for_disk(value); + return -ENOMEM; + } + + __dm_bless_for_disk(&key_le); + + array_insert(node->keys, sizeof(*node->keys), nr_entries, index, &key_le); + array_insert(value_base(node), value_size, nr_entries, index, value); + node->header.nr_entries = cpu_to_le32(nr_entries + 1); + + return 0; +} + +/*----------------------------------------------------------------*/ + +/* + * We want 3n entries (for some n). This works more nicely for repeated + * insert remove loops than (2n + 1). + */ +static uint32_t calc_max_entries(size_t value_size, size_t block_size) +{ + uint32_t total, n; + size_t elt_size = sizeof(uint64_t) + value_size; /* key + value */ + + block_size -= sizeof(struct node_header); + total = block_size / elt_size; + n = total / 3; /* rounds down */ + + return 3 * n; +} + +int dm_btree_empty(struct dm_btree_info *info, dm_block_t *root) +{ + int r; + struct dm_block *b; + struct node *n; + size_t block_size; + uint32_t max_entries; + + r = new_block(info, &b); + if (r < 0) + return r; + + block_size = dm_bm_block_size(dm_tm_get_bm(info->tm)); + max_entries = calc_max_entries(info->value_type.size, block_size); + + n = dm_block_data(b); + memset(n, 0, block_size); + n->header.flags = cpu_to_le32(LEAF_NODE); + n->header.nr_entries = cpu_to_le32(0); + n->header.max_entries = cpu_to_le32(max_entries); + n->header.value_size = cpu_to_le32(info->value_type.size); + + *root = dm_block_location(b); + return unlock_block(info, b); +} +EXPORT_SYMBOL_GPL(dm_btree_empty); + +/*----------------------------------------------------------------*/ + +/* + * Deletion uses a recursive algorithm, since we have limited stack space + * we explicitly manage our own stack on the heap. + */ +#define MAX_SPINE_DEPTH 64 +struct frame { + struct dm_block *b; + struct node *n; + unsigned level; + unsigned nr_children; + unsigned current_child; +}; + +struct del_stack { + struct dm_transaction_manager *tm; + int top; + struct frame spine[MAX_SPINE_DEPTH]; +}; + +static int top_frame(struct del_stack *s, struct frame **f) +{ + if (s->top < 0) { + DMERR("btree deletion stack empty"); + return -EINVAL; + } + + *f = s->spine + s->top; + + return 0; +} + +static int unprocessed_frames(struct del_stack *s) +{ + return s->top >= 0; +} + +static int push_frame(struct del_stack *s, dm_block_t b, unsigned level) +{ + int r; + uint32_t ref_count; + + if (s->top >= MAX_SPINE_DEPTH - 1) { + DMERR("btree deletion stack out of memory"); + return -ENOMEM; + } + + r = dm_tm_ref(s->tm, b, &ref_count); + if (r) + return r; + + if (ref_count > 1) + /* + * This is a shared node, so we can just decrement it's + * reference counter and leave the children. + */ + dm_tm_dec(s->tm, b); + + else { + struct frame *f = s->spine + ++s->top; + + r = dm_tm_read_lock(s->tm, b, &btree_node_validator, &f->b); + if (r) { + s->top--; + return r; + } + + f->n = dm_block_data(f->b); + f->level = level; + f->nr_children = le32_to_cpu(f->n->header.nr_entries); + f->current_child = 0; + } + + return 0; +} + +static void pop_frame(struct del_stack *s) +{ + struct frame *f = s->spine + s->top--; + + dm_tm_dec(s->tm, dm_block_location(f->b)); + dm_tm_unlock(s->tm, f->b); +} + +int dm_btree_del(struct dm_btree_info *info, dm_block_t root) +{ + int r; + struct del_stack *s; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + s->tm = info->tm; + s->top = -1; + + r = push_frame(s, root, 1); + if (r) + goto out; + + while (unprocessed_frames(s)) { + uint32_t flags; + struct frame *f; + dm_block_t b; + + r = top_frame(s, &f); + if (r) + goto out; + + if (f->current_child >= f->nr_children) { + pop_frame(s); + continue; + } + + flags = le32_to_cpu(f->n->header.flags); + if (flags & INTERNAL_NODE) { + b = value64(f->n, f->current_child); + f->current_child++; + r = push_frame(s, b, f->level); + if (r) + goto out; + + } else if (f->level != (info->levels - 1)) { + b = value64(f->n, f->current_child); + f->current_child++; + r = push_frame(s, b, f->level + 1); + if (r) + goto out; + + } else { + if (info->value_type.dec) { + unsigned i; + + for (i = 0; i < f->nr_children; i++) + info->value_type.dec(info->value_type.context, + value_ptr(f->n, i, info->value_type.size)); + } + f->current_child = f->nr_children; + } + } + +out: + kfree(s); + return r; +} +EXPORT_SYMBOL_GPL(dm_btree_del); + +/*----------------------------------------------------------------*/ + +static int btree_lookup_raw(struct ro_spine *s, dm_block_t block, uint64_t key, + int (*search_fn)(struct node *, uint64_t), + uint64_t *result_key, void *v, size_t value_size) +{ + int i, r; + uint32_t flags, nr_entries; + + do { + r = ro_step(s, block); + if (r < 0) + return r; + + i = search_fn(ro_node(s), key); + + flags = le32_to_cpu(ro_node(s)->header.flags); + nr_entries = le32_to_cpu(ro_node(s)->header.nr_entries); + if (i < 0 || i >= nr_entries) + return -ENODATA; + + if (flags & INTERNAL_NODE) + block = value64(ro_node(s), i); + + } while (!(flags & LEAF_NODE)); + + *result_key = le64_to_cpu(ro_node(s)->keys[i]); + memcpy(v, value_ptr(ro_node(s), i, value_size), value_size); + + return 0; +} + +int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, void *value_le) +{ + unsigned level, last_level = info->levels - 1; + int r = -ENODATA; + uint64_t rkey; + __le64 internal_value_le; + struct ro_spine spine; + + init_ro_spine(&spine, info); + for (level = 0; level < info->levels; level++) { + size_t size; + void *value_p; + + if (level == last_level) { + value_p = value_le; + size = info->value_type.size; + + } else { + value_p = &internal_value_le; + size = sizeof(uint64_t); + } + + r = btree_lookup_raw(&spine, root, keys[level], + lower_bound, &rkey, + value_p, size); + + if (!r) { + if (rkey != keys[level]) { + exit_ro_spine(&spine); + return -ENODATA; + } + } else { + exit_ro_spine(&spine); + return r; + } + + root = le64_to_cpu(internal_value_le); + } + exit_ro_spine(&spine); + + return r; +} +EXPORT_SYMBOL_GPL(dm_btree_lookup); + +/* + * Splits a node by creating a sibling node and shifting half the nodes + * contents across. Assumes there is a parent node, and it has room for + * another child. + * + * Before: + * +--------+ + * | Parent | + * +--------+ + * | + * v + * +----------+ + * | A ++++++ | + * +----------+ + * + * + * After: + * +--------+ + * | Parent | + * +--------+ + * | | + * v +------+ + * +---------+ | + * | A* +++ | v + * +---------+ +-------+ + * | B +++ | + * +-------+ + * + * Where A* is a shadow of A. + */ +static int btree_split_sibling(struct shadow_spine *s, dm_block_t root, + unsigned parent_index, uint64_t key) +{ + int r; + size_t size; + unsigned nr_left, nr_right; + struct dm_block *left, *right, *parent; + struct node *ln, *rn, *pn; + __le64 location; + + left = shadow_current(s); + + r = new_block(s->info, &right); + if (r < 0) + return r; + + ln = dm_block_data(left); + rn = dm_block_data(right); + + nr_left = le32_to_cpu(ln->header.nr_entries) / 2; + nr_right = le32_to_cpu(ln->header.nr_entries) - nr_left; + + ln->header.nr_entries = cpu_to_le32(nr_left); + + rn->header.flags = ln->header.flags; + rn->header.nr_entries = cpu_to_le32(nr_right); + rn->header.max_entries = ln->header.max_entries; + rn->header.value_size = ln->header.value_size; + memcpy(rn->keys, ln->keys + nr_left, nr_right * sizeof(rn->keys[0])); + + size = le32_to_cpu(ln->header.flags) & INTERNAL_NODE ? + sizeof(uint64_t) : s->info->value_type.size; + memcpy(value_ptr(rn, 0, size), value_ptr(ln, nr_left, size), + size * nr_right); + + /* + * Patch up the parent + */ + parent = shadow_parent(s); + + pn = dm_block_data(parent); + location = cpu_to_le64(dm_block_location(left)); + __dm_bless_for_disk(&location); + memcpy_disk(value_ptr(pn, parent_index, sizeof(__le64)), + &location, sizeof(__le64)); + + location = cpu_to_le64(dm_block_location(right)); + __dm_bless_for_disk(&location); + + r = insert_at(sizeof(__le64), pn, parent_index + 1, + le64_to_cpu(rn->keys[0]), &location); + if (r) + return r; + + if (key < le64_to_cpu(rn->keys[0])) { + unlock_block(s->info, right); + s->nodes[1] = left; + } else { + unlock_block(s->info, left); + s->nodes[1] = right; + } + + return 0; +} + +/* + * Splits a node by creating two new children beneath the given node. + * + * Before: + * +----------+ + * | A ++++++ | + * +----------+ + * + * + * After: + * +------------+ + * | A (shadow) | + * +------------+ + * | | + * +------+ +----+ + * | | + * v v + * +-------+ +-------+ + * | B +++ | | C +++ | + * +-------+ +-------+ + */ +static int btree_split_beneath(struct shadow_spine *s, uint64_t key) +{ + int r; + size_t size; + unsigned nr_left, nr_right; + struct dm_block *left, *right, *new_parent; + struct node *pn, *ln, *rn; + __le64 val; + + new_parent = shadow_current(s); + + r = new_block(s->info, &left); + if (r < 0) + return r; + + r = new_block(s->info, &right); + if (r < 0) { + /* FIXME: put left */ + return r; + } + + pn = dm_block_data(new_parent); + ln = dm_block_data(left); + rn = dm_block_data(right); + + nr_left = le32_to_cpu(pn->header.nr_entries) / 2; + nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left; + + ln->header.flags = pn->header.flags; + ln->header.nr_entries = cpu_to_le32(nr_left); + ln->header.max_entries = pn->header.max_entries; + ln->header.value_size = pn->header.value_size; + + rn->header.flags = pn->header.flags; + rn->header.nr_entries = cpu_to_le32(nr_right); + rn->header.max_entries = pn->header.max_entries; + rn->header.value_size = pn->header.value_size; + + memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0])); + memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0])); + + size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ? + sizeof(__le64) : s->info->value_type.size; + memcpy(value_ptr(ln, 0, size), value_ptr(pn, 0, size), nr_left * size); + memcpy(value_ptr(rn, 0, size), value_ptr(pn, nr_left, size), + nr_right * size); + + /* new_parent should just point to l and r now */ + pn->header.flags = cpu_to_le32(INTERNAL_NODE); + pn->header.nr_entries = cpu_to_le32(2); + pn->header.max_entries = cpu_to_le32( + calc_max_entries(sizeof(__le64), + dm_bm_block_size( + dm_tm_get_bm(s->info->tm)))); + pn->header.value_size = cpu_to_le32(sizeof(__le64)); + + val = cpu_to_le64(dm_block_location(left)); + __dm_bless_for_disk(&val); + pn->keys[0] = ln->keys[0]; + memcpy_disk(value_ptr(pn, 0, sizeof(__le64)), &val, sizeof(__le64)); + + val = cpu_to_le64(dm_block_location(right)); + __dm_bless_for_disk(&val); + pn->keys[1] = rn->keys[0]; + memcpy_disk(value_ptr(pn, 1, sizeof(__le64)), &val, sizeof(__le64)); + + /* + * rejig the spine. This is ugly, since it knows too + * much about the spine + */ + if (s->nodes[0] != new_parent) { + unlock_block(s->info, s->nodes[0]); + s->nodes[0] = new_parent; + } + if (key < le64_to_cpu(rn->keys[0])) { + unlock_block(s->info, right); + s->nodes[1] = left; + } else { + unlock_block(s->info, left); + s->nodes[1] = right; + } + s->count = 2; + + return 0; +} + +static int btree_insert_raw(struct shadow_spine *s, dm_block_t root, + struct dm_btree_value_type *vt, + uint64_t key, unsigned *index) +{ + int r, i = *index, top = 1; + struct node *node; + + for (;;) { + r = shadow_step(s, root, vt); + if (r < 0) + return r; + + node = dm_block_data(shadow_current(s)); + + /* + * We have to patch up the parent node, ugly, but I don't + * see a way to do this automatically as part of the spine + * op. + */ + if (shadow_has_parent(s) && i >= 0) { /* FIXME: second clause unness. */ + __le64 location = cpu_to_le64(dm_block_location(shadow_current(s))); + + __dm_bless_for_disk(&location); + memcpy_disk(value_ptr(dm_block_data(shadow_parent(s)), i, sizeof(uint64_t)), + &location, sizeof(__le64)); + } + + node = dm_block_data(shadow_current(s)); + + if (node->header.nr_entries == node->header.max_entries) { + if (top) + r = btree_split_beneath(s, key); + else + r = btree_split_sibling(s, root, i, key); + + if (r < 0) + return r; + } + + node = dm_block_data(shadow_current(s)); + + i = lower_bound(node, key); + + if (le32_to_cpu(node->header.flags) & LEAF_NODE) + break; + + if (i < 0) { + /* change the bounds on the lowest key */ + node->keys[0] = cpu_to_le64(key); + i = 0; + } + + root = value64(node, i); + top = 0; + } + + if (i < 0 || le64_to_cpu(node->keys[i]) != key) + i++; + + *index = i; + return 0; +} + +static int insert(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, void *value, dm_block_t *new_root, + int *inserted) + __dm_written_to_disk(value) +{ + int r, need_insert; + unsigned level, index = -1, last_level = info->levels - 1; + dm_block_t block = root; + struct shadow_spine spine; + struct node *n; + struct dm_btree_value_type le64_type; + + le64_type.context = NULL; + le64_type.size = sizeof(__le64); + le64_type.inc = NULL; + le64_type.dec = NULL; + le64_type.equal = NULL; + + init_shadow_spine(&spine, info); + + for (level = 0; level < (info->levels - 1); level++) { + r = btree_insert_raw(&spine, block, &le64_type, keys[level], &index); + if (r < 0) + goto bad; + + n = dm_block_data(shadow_current(&spine)); + need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) || + (le64_to_cpu(n->keys[index]) != keys[level])); + + if (need_insert) { + dm_block_t new_tree; + __le64 new_le; + + r = dm_btree_empty(info, &new_tree); + if (r < 0) + goto bad; + + new_le = cpu_to_le64(new_tree); + __dm_bless_for_disk(&new_le); + + r = insert_at(sizeof(uint64_t), n, index, + keys[level], &new_le); + if (r) + goto bad; + } + + if (level < last_level) + block = value64(n, index); + } + + r = btree_insert_raw(&spine, block, &info->value_type, + keys[level], &index); + if (r < 0) + goto bad; + + n = dm_block_data(shadow_current(&spine)); + need_insert = ((index >= le32_to_cpu(n->header.nr_entries)) || + (le64_to_cpu(n->keys[index]) != keys[level])); + + if (need_insert) { + if (inserted) + *inserted = 1; + + r = insert_at(info->value_type.size, n, index, + keys[level], value); + if (r) + goto bad_unblessed; + } else { + if (inserted) + *inserted = 0; + + if (info->value_type.dec && + (!info->value_type.equal || + !info->value_type.equal( + info->value_type.context, + value_ptr(n, index, info->value_type.size), + value))) { + info->value_type.dec(info->value_type.context, + value_ptr(n, index, info->value_type.size)); + } + memcpy_disk(value_ptr(n, index, info->value_type.size), + value, info->value_type.size); + } + + *new_root = shadow_root(&spine); + exit_shadow_spine(&spine); + + return 0; + +bad: + __dm_unbless_for_disk(value); +bad_unblessed: + exit_shadow_spine(&spine); + return r; +} + +int dm_btree_insert(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, void *value, dm_block_t *new_root) + __dm_written_to_disk(value) +{ + return insert(info, root, keys, value, new_root, NULL); +} +EXPORT_SYMBOL_GPL(dm_btree_insert); + +int dm_btree_insert_notify(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, void *value, dm_block_t *new_root, + int *inserted) + __dm_written_to_disk(value) +{ + return insert(info, root, keys, value, new_root, inserted); +} +EXPORT_SYMBOL_GPL(dm_btree_insert_notify); + +/*----------------------------------------------------------------*/ + +static int find_highest_key(struct ro_spine *s, dm_block_t block, + uint64_t *result_key, dm_block_t *next_block) +{ + int i, r; + uint32_t flags; + + do { + r = ro_step(s, block); + if (r < 0) + return r; + + flags = le32_to_cpu(ro_node(s)->header.flags); + i = le32_to_cpu(ro_node(s)->header.nr_entries); + if (!i) + return -ENODATA; + else + i--; + + *result_key = le64_to_cpu(ro_node(s)->keys[i]); + if (next_block || flags & INTERNAL_NODE) + block = value64(ro_node(s), i); + + } while (flags & INTERNAL_NODE); + + if (next_block) + *next_block = block; + return 0; +} + +int dm_btree_find_highest_key(struct dm_btree_info *info, dm_block_t root, + uint64_t *result_keys) +{ + int r = 0, count = 0, level; + struct ro_spine spine; + + init_ro_spine(&spine, info); + for (level = 0; level < info->levels; level++) { + r = find_highest_key(&spine, root, result_keys + level, + level == info->levels - 1 ? NULL : &root); + if (r == -ENODATA) { + r = 0; + break; + + } else if (r) + break; + + count++; + } + exit_ro_spine(&spine); + + return r ? r : count; +} +EXPORT_SYMBOL_GPL(dm_btree_find_highest_key); diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h new file mode 100644 index 000000000000..ae02c84410ff --- /dev/null +++ b/drivers/md/persistent-data/dm-btree.h @@ -0,0 +1,145 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ +#ifndef _LINUX_DM_BTREE_H +#define _LINUX_DM_BTREE_H + +#include "dm-block-manager.h" + +struct dm_transaction_manager; + +/*----------------------------------------------------------------*/ + +/* + * Annotations used to check on-disk metadata is handled as little-endian. + */ +#ifdef __CHECKER__ +# define __dm_written_to_disk(x) __releases(x) +# define __dm_reads_from_disk(x) __acquires(x) +# define __dm_bless_for_disk(x) __acquire(x) +# define __dm_unbless_for_disk(x) __release(x) +#else +# define __dm_written_to_disk(x) +# define __dm_reads_from_disk(x) +# define __dm_bless_for_disk(x) +# define __dm_unbless_for_disk(x) +#endif + +/*----------------------------------------------------------------*/ + +/* + * Manipulates hierarchical B+ trees with 64-bit keys and arbitrary-sized + * values. + */ + +/* + * Infomation about the values stored within the btree. + */ +struct dm_btree_value_type { + void *context; + + /* + * The size in bytes of each value. + */ + uint32_t size; + + /* + * Any of these methods can be safely set to NULL if you do not + * need the corresponding feature. + */ + + /* + * The btree is making a duplicate of the value, for instance + * because previously-shared btree nodes have now diverged. + * @value argument is the new copy that the copy function may modify. + * (Probably it just wants to increment a reference count + * 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); + + /* + * 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); + + /* + * 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); +}; + +/* + * The shape and contents of a btree. + */ +struct dm_btree_info { + struct dm_transaction_manager *tm; + + /* + * Number of nested btrees. (Not the depth of a single tree.) + */ + unsigned levels; + struct dm_btree_value_type value_type; +}; + +/* + * Set up an empty tree. O(1). + */ +int dm_btree_empty(struct dm_btree_info *info, dm_block_t *root); + +/* + * Delete a tree. O(n) - this is the slow one! It can also block, so + * please don't call it on an IO path. + */ +int dm_btree_del(struct dm_btree_info *info, dm_block_t root); + +/* + * All the lookup functions return -ENODATA if the key cannot be found. + */ + +/* + * Tries to find a key that matches exactly. O(ln(n)) + */ +int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, void *value_le); + +/* + * Insertion (or overwrite an existing value). O(ln(n)) + */ +int dm_btree_insert(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, void *value, dm_block_t *new_root) + __dm_written_to_disk(value); + +/* + * A variant of insert that indicates whether it actually inserted or just + * overwrote. Useful if you're keeping track of the number of entries in a + * tree. + */ +int dm_btree_insert_notify(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, void *value, dm_block_t *new_root, + int *inserted) + __dm_written_to_disk(value); + +/* + * Remove a key if present. This doesn't remove empty sub trees. Normally + * subtrees represent a separate entity, like a snapshot map, so this is + * correct behaviour. O(ln(n)). + */ +int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, + uint64_t *keys, dm_block_t *new_root); + +/* + * Returns < 0 on failure. Otherwise the number of key entries that have + * been filled out. Remember trees can have zero entries, and as such have + * no highest key. + */ +int dm_btree_find_highest_key(struct dm_btree_info *info, dm_block_t root, + uint64_t *result_keys); + +#endif /* _LINUX_DM_BTREE_H */ diff --git a/drivers/md/persistent-data/dm-persistent-data-internal.h b/drivers/md/persistent-data/dm-persistent-data-internal.h new file mode 100644 index 000000000000..c49e26fff36c --- /dev/null +++ b/drivers/md/persistent-data/dm-persistent-data-internal.h @@ -0,0 +1,19 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef _DM_PERSISTENT_DATA_INTERNAL_H +#define _DM_PERSISTENT_DATA_INTERNAL_H + +#include "dm-block-manager.h" + +static inline unsigned dm_hash_block(dm_block_t b, unsigned hash_mask) +{ + const unsigned BIG_PRIME = 4294967291UL; + + return (((unsigned) b) * BIG_PRIME) & hash_mask; +} + +#endif /* _PERSISTENT_DATA_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-space-map-checker.c b/drivers/md/persistent-data/dm-space-map-checker.c new file mode 100644 index 000000000000..bb44a937fe63 --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-checker.c @@ -0,0 +1,437 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-space-map-checker.h" + +#include + +#ifdef CONFIG_DM_DEBUG_SPACE_MAPS + +#define DM_MSG_PREFIX "space map checker" + +/*----------------------------------------------------------------*/ + +struct count_array { + dm_block_t nr; + dm_block_t nr_free; + + uint32_t *counts; +}; + +static int ca_get_count(struct count_array *ca, dm_block_t b, uint32_t *count) +{ + if (b >= ca->nr) + return -EINVAL; + + *count = ca->counts[b]; + return 0; +} + +static int ca_count_more_than_one(struct count_array *ca, dm_block_t b, int *r) +{ + if (b >= ca->nr) + return -EINVAL; + + *r = ca->counts[b] > 1; + return 0; +} + +static int ca_set_count(struct count_array *ca, dm_block_t b, uint32_t count) +{ + uint32_t old_count; + + if (b >= ca->nr) + return -EINVAL; + + old_count = ca->counts[b]; + + if (!count && old_count) + ca->nr_free++; + + else if (count && !old_count) + ca->nr_free--; + + ca->counts[b] = count; + return 0; +} + +static int ca_inc_block(struct count_array *ca, dm_block_t b) +{ + if (b >= ca->nr) + return -EINVAL; + + ca_set_count(ca, b, ca->counts[b] + 1); + return 0; +} + +static int ca_dec_block(struct count_array *ca, dm_block_t b) +{ + if (b >= ca->nr) + return -EINVAL; + + BUG_ON(ca->counts[b] == 0); + ca_set_count(ca, b, ca->counts[b] - 1); + return 0; +} + +static int ca_create(struct count_array *ca, struct dm_space_map *sm) +{ + int r; + dm_block_t nr_blocks; + + r = dm_sm_get_nr_blocks(sm, &nr_blocks); + if (r) + return r; + + ca->nr = nr_blocks; + ca->nr_free = nr_blocks; + ca->counts = kzalloc(sizeof(*ca->counts) * nr_blocks, GFP_KERNEL); + if (!ca->counts) + return -ENOMEM; + + return 0; +} + +static int ca_load(struct count_array *ca, struct dm_space_map *sm) +{ + int r; + uint32_t count; + dm_block_t nr_blocks, i; + + r = dm_sm_get_nr_blocks(sm, &nr_blocks); + if (r) + return r; + + BUG_ON(ca->nr != nr_blocks); + + DMWARN("Loading debug space map from disk. This may take some time"); + for (i = 0; i < nr_blocks; i++) { + r = dm_sm_get_count(sm, i, &count); + if (r) { + DMERR("load failed"); + return r; + } + + ca_set_count(ca, i, count); + } + DMWARN("Load complete"); + + return 0; +} + +static int ca_extend(struct count_array *ca, dm_block_t extra_blocks) +{ + dm_block_t nr_blocks = ca->nr + extra_blocks; + uint32_t *counts = kzalloc(sizeof(*counts) * nr_blocks, GFP_KERNEL); + if (!counts) + return -ENOMEM; + + memcpy(counts, ca->counts, sizeof(*counts) * ca->nr); + kfree(ca->counts); + ca->nr = nr_blocks; + ca->nr_free += extra_blocks; + ca->counts = counts; + return 0; +} + +static int ca_commit(struct count_array *old, struct count_array *new) +{ + if (old->nr != new->nr) { + BUG_ON(old->nr > new->nr); + ca_extend(old, new->nr - old->nr); + } + + BUG_ON(old->nr != new->nr); + old->nr_free = new->nr_free; + memcpy(old->counts, new->counts, sizeof(*old->counts) * old->nr); + return 0; +} + +static void ca_destroy(struct count_array *ca) +{ + kfree(ca->counts); +} + +/*----------------------------------------------------------------*/ + +struct sm_checker { + struct dm_space_map sm; + + struct count_array old_counts; + struct count_array counts; + + struct dm_space_map *real_sm; +}; + +static void sm_checker_destroy(struct dm_space_map *sm) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + + dm_sm_destroy(smc->real_sm); + ca_destroy(&smc->old_counts); + ca_destroy(&smc->counts); + kfree(smc); +} + +static int sm_checker_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int r = dm_sm_get_nr_blocks(smc->real_sm, count); + if (!r) + BUG_ON(smc->old_counts.nr != *count); + return r; +} + +static int sm_checker_get_nr_free(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int r = dm_sm_get_nr_free(smc->real_sm, count); + if (!r) { + /* + * Slow, but we know it's correct. + */ + dm_block_t b, n = 0; + for (b = 0; b < smc->old_counts.nr; b++) + if (smc->old_counts.counts[b] == 0 && + smc->counts.counts[b] == 0) + n++; + + if (n != *count) + DMERR("free block counts differ, checker %u, sm-disk:%u", + (unsigned) n, (unsigned) *count); + } + return r; +} + +static int sm_checker_new_block(struct dm_space_map *sm, dm_block_t *b) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int r = dm_sm_new_block(smc->real_sm, b); + + if (!r) { + BUG_ON(*b >= smc->old_counts.nr); + BUG_ON(smc->old_counts.counts[*b] != 0); + BUG_ON(*b >= smc->counts.nr); + BUG_ON(smc->counts.counts[*b] != 0); + ca_set_count(&smc->counts, *b, 1); + } + + return r; +} + +static int sm_checker_inc_block(struct dm_space_map *sm, dm_block_t b) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int r = dm_sm_inc_block(smc->real_sm, b); + int r2 = ca_inc_block(&smc->counts, b); + BUG_ON(r != r2); + return r; +} + +static int sm_checker_dec_block(struct dm_space_map *sm, dm_block_t b) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int r = dm_sm_dec_block(smc->real_sm, b); + int r2 = ca_dec_block(&smc->counts, b); + BUG_ON(r != r2); + return r; +} + +static int sm_checker_get_count(struct dm_space_map *sm, dm_block_t b, uint32_t *result) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + uint32_t result2 = 0; + int r = dm_sm_get_count(smc->real_sm, b, result); + int r2 = ca_get_count(&smc->counts, b, &result2); + + BUG_ON(r != r2); + if (!r) + BUG_ON(*result != result2); + return r; +} + +static int sm_checker_count_more_than_one(struct dm_space_map *sm, dm_block_t b, int *result) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int result2 = 0; + int r = dm_sm_count_is_more_than_one(smc->real_sm, b, result); + int r2 = ca_count_more_than_one(&smc->counts, b, &result2); + + BUG_ON(r != r2); + if (!r) + BUG_ON(!(*result) && result2); + return r; +} + +static int sm_checker_set_count(struct dm_space_map *sm, dm_block_t b, uint32_t count) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + uint32_t old_rc; + int r = dm_sm_set_count(smc->real_sm, b, count); + int r2; + + BUG_ON(b >= smc->counts.nr); + old_rc = smc->counts.counts[b]; + r2 = ca_set_count(&smc->counts, b, count); + BUG_ON(r != r2); + + return r; +} + +static int sm_checker_commit(struct dm_space_map *sm) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int r; + + r = dm_sm_commit(smc->real_sm); + if (r) + return r; + + r = ca_commit(&smc->old_counts, &smc->counts); + if (r) + return r; + + return 0; +} + +static int sm_checker_extend(struct dm_space_map *sm, dm_block_t extra_blocks) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + int r = dm_sm_extend(smc->real_sm, extra_blocks); + if (r) + return r; + + return ca_extend(&smc->counts, extra_blocks); +} + +static int sm_checker_root_size(struct dm_space_map *sm, size_t *result) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + return dm_sm_root_size(smc->real_sm, result); +} + +static int sm_checker_copy_root(struct dm_space_map *sm, void *copy_to_here_le, size_t len) +{ + struct sm_checker *smc = container_of(sm, struct sm_checker, sm); + return dm_sm_copy_root(smc->real_sm, copy_to_here_le, len); +} + +/*----------------------------------------------------------------*/ + +static struct dm_space_map ops_ = { + .destroy = sm_checker_destroy, + .get_nr_blocks = sm_checker_get_nr_blocks, + .get_nr_free = sm_checker_get_nr_free, + .inc_block = sm_checker_inc_block, + .dec_block = sm_checker_dec_block, + .new_block = sm_checker_new_block, + .get_count = sm_checker_get_count, + .count_is_more_than_one = sm_checker_count_more_than_one, + .set_count = sm_checker_set_count, + .commit = sm_checker_commit, + .extend = sm_checker_extend, + .root_size = sm_checker_root_size, + .copy_root = sm_checker_copy_root +}; + +struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm) +{ + int r; + struct sm_checker *smc; + + if (!sm) + return NULL; + + smc = kmalloc(sizeof(*smc), GFP_KERNEL); + if (!smc) + return NULL; + + memcpy(&smc->sm, &ops_, sizeof(smc->sm)); + r = ca_create(&smc->old_counts, sm); + if (r) { + kfree(smc); + return NULL; + } + + r = ca_create(&smc->counts, sm); + if (r) { + ca_destroy(&smc->old_counts); + kfree(smc); + return NULL; + } + + smc->real_sm = sm; + + r = ca_load(&smc->counts, sm); + if (r) { + ca_destroy(&smc->counts); + ca_destroy(&smc->old_counts); + kfree(smc); + return NULL; + } + + r = ca_commit(&smc->old_counts, &smc->counts); + if (r) { + ca_destroy(&smc->counts); + ca_destroy(&smc->old_counts); + kfree(smc); + return NULL; + } + + return &smc->sm; +} +EXPORT_SYMBOL_GPL(dm_sm_checker_create); + +struct dm_space_map *dm_sm_checker_create_fresh(struct dm_space_map *sm) +{ + int r; + struct sm_checker *smc; + + if (!sm) + return NULL; + + smc = kmalloc(sizeof(*smc), GFP_KERNEL); + if (!smc) + return NULL; + + memcpy(&smc->sm, &ops_, sizeof(smc->sm)); + r = ca_create(&smc->old_counts, sm); + if (r) { + kfree(smc); + return NULL; + } + + r = ca_create(&smc->counts, sm); + if (r) { + ca_destroy(&smc->old_counts); + kfree(smc); + return NULL; + } + + smc->real_sm = sm; + return &smc->sm; +} +EXPORT_SYMBOL_GPL(dm_sm_checker_create_fresh); + +/*----------------------------------------------------------------*/ + +#else + +struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm) +{ + return sm; +} +EXPORT_SYMBOL_GPL(dm_sm_checker_create); + +struct dm_space_map *dm_sm_checker_create_fresh(struct dm_space_map *sm) +{ + return sm; +} +EXPORT_SYMBOL_GPL(dm_sm_checker_create_fresh); + +/*----------------------------------------------------------------*/ + +#endif diff --git a/drivers/md/persistent-data/dm-space-map-checker.h b/drivers/md/persistent-data/dm-space-map-checker.h new file mode 100644 index 000000000000..444dccf6688c --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-checker.h @@ -0,0 +1,26 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef SNAPSHOTS_SPACE_MAP_CHECKER_H +#define SNAPSHOTS_SPACE_MAP_CHECKER_H + +#include "dm-space-map.h" + +/*----------------------------------------------------------------*/ + +/* + * This space map wraps a real on-disk space map, and verifies all of its + * operations. It uses a lot of memory, so only use if you have a specific + * problem that you're debugging. + * + * Ownership of @sm passes. + */ +struct dm_space_map *dm_sm_checker_create(struct dm_space_map *sm); +struct dm_space_map *dm_sm_checker_create_fresh(struct dm_space_map *sm); + +/*----------------------------------------------------------------*/ + +#endif diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c new file mode 100644 index 000000000000..df2494c06cdc --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-common.c @@ -0,0 +1,705 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-space-map-common.h" +#include "dm-transaction-manager.h" + +#include +#include + +#define DM_MSG_PREFIX "space map common" + +/*----------------------------------------------------------------*/ + +/* + * Index validator. + */ +#define INDEX_CSUM_XOR 160478 + +static void index_prepare_for_write(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct disk_metadata_index *mi_le = dm_block_data(b); + + mi_le->blocknr = cpu_to_le64(dm_block_location(b)); + mi_le->csum = cpu_to_le32(dm_bm_checksum(&mi_le->padding, + block_size - sizeof(__le32), + INDEX_CSUM_XOR)); +} + +static int index_check(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct disk_metadata_index *mi_le = dm_block_data(b); + __le32 csum_disk; + + if (dm_block_location(b) != le64_to_cpu(mi_le->blocknr)) { + DMERR("index_check failed blocknr %llu wanted %llu", + le64_to_cpu(mi_le->blocknr), dm_block_location(b)); + return -ENOTBLK; + } + + csum_disk = cpu_to_le32(dm_bm_checksum(&mi_le->padding, + block_size - sizeof(__le32), + INDEX_CSUM_XOR)); + if (csum_disk != mi_le->csum) { + DMERR("index_check failed csum %u wanted %u", + le32_to_cpu(csum_disk), le32_to_cpu(mi_le->csum)); + return -EILSEQ; + } + + return 0; +} + +static struct dm_block_validator index_validator = { + .name = "index", + .prepare_for_write = index_prepare_for_write, + .check = index_check +}; + +/*----------------------------------------------------------------*/ + +/* + * Bitmap validator + */ +#define BITMAP_CSUM_XOR 240779 + +static void bitmap_prepare_for_write(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct disk_bitmap_header *disk_header = dm_block_data(b); + + disk_header->blocknr = cpu_to_le64(dm_block_location(b)); + disk_header->csum = cpu_to_le32(dm_bm_checksum(&disk_header->not_used, + block_size - sizeof(__le32), + BITMAP_CSUM_XOR)); +} + +static int bitmap_check(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct disk_bitmap_header *disk_header = dm_block_data(b); + __le32 csum_disk; + + if (dm_block_location(b) != le64_to_cpu(disk_header->blocknr)) { + DMERR("bitmap check failed blocknr %llu wanted %llu", + le64_to_cpu(disk_header->blocknr), dm_block_location(b)); + return -ENOTBLK; + } + + csum_disk = cpu_to_le32(dm_bm_checksum(&disk_header->not_used, + block_size - sizeof(__le32), + BITMAP_CSUM_XOR)); + if (csum_disk != disk_header->csum) { + DMERR("bitmap check failed csum %u wanted %u", + le32_to_cpu(csum_disk), le32_to_cpu(disk_header->csum)); + return -EILSEQ; + } + + return 0; +} + +static struct dm_block_validator dm_sm_bitmap_validator = { + .name = "sm_bitmap", + .prepare_for_write = bitmap_prepare_for_write, + .check = bitmap_check +}; + +/*----------------------------------------------------------------*/ + +#define ENTRIES_PER_WORD 32 +#define ENTRIES_SHIFT 5 + +static void *dm_bitmap_data(struct dm_block *b) +{ + return dm_block_data(b) + sizeof(struct disk_bitmap_header); +} + +#define WORD_MASK_HIGH 0xAAAAAAAAAAAAAAAAULL + +static unsigned bitmap_word_used(void *addr, unsigned b) +{ + __le64 *words_le = addr; + __le64 *w_le = words_le + (b >> ENTRIES_SHIFT); + + uint64_t bits = le64_to_cpu(*w_le); + uint64_t mask = (bits + WORD_MASK_HIGH + 1) & WORD_MASK_HIGH; + + return !(~bits & mask); +} + +static unsigned sm_lookup_bitmap(void *addr, unsigned b) +{ + __le64 *words_le = addr; + __le64 *w_le = words_le + (b >> ENTRIES_SHIFT); + unsigned hi, lo; + + b = (b & (ENTRIES_PER_WORD - 1)) << 1; + hi = !!test_bit_le(b, (void *) w_le); + lo = !!test_bit_le(b + 1, (void *) w_le); + return (hi << 1) | lo; +} + +static void sm_set_bitmap(void *addr, unsigned b, unsigned val) +{ + __le64 *words_le = addr; + __le64 *w_le = words_le + (b >> ENTRIES_SHIFT); + + b = (b & (ENTRIES_PER_WORD - 1)) << 1; + + if (val & 2) + __set_bit_le(b, (void *) w_le); + else + __clear_bit_le(b, (void *) w_le); + + if (val & 1) + __set_bit_le(b + 1, (void *) w_le); + else + __clear_bit_le(b + 1, (void *) w_le); +} + +static int sm_find_free(void *addr, unsigned begin, unsigned end, + unsigned *result) +{ + while (begin < end) { + if (!(begin & (ENTRIES_PER_WORD - 1)) && + bitmap_word_used(addr, begin)) { + begin += ENTRIES_PER_WORD; + continue; + } + + if (!sm_lookup_bitmap(addr, begin)) { + *result = begin; + return 0; + } + + begin++; + } + + return -ENOSPC; +} + +/*----------------------------------------------------------------*/ + +static int sm_ll_init(struct ll_disk *ll, struct dm_transaction_manager *tm) +{ + ll->tm = tm; + + ll->bitmap_info.tm = tm; + ll->bitmap_info.levels = 1; + + /* + * Because the new bitmap blocks are created via a shadow + * operation, the old entry has already had its reference count + * decremented and we don't need the btree to do any bookkeeping. + */ + ll->bitmap_info.value_type.size = sizeof(struct disk_index_entry); + ll->bitmap_info.value_type.inc = NULL; + ll->bitmap_info.value_type.dec = NULL; + ll->bitmap_info.value_type.equal = NULL; + + ll->ref_count_info.tm = tm; + ll->ref_count_info.levels = 1; + ll->ref_count_info.value_type.size = sizeof(uint32_t); + ll->ref_count_info.value_type.inc = NULL; + ll->ref_count_info.value_type.dec = NULL; + ll->ref_count_info.value_type.equal = NULL; + + ll->block_size = dm_bm_block_size(dm_tm_get_bm(tm)); + + if (ll->block_size > (1 << 30)) { + DMERR("block size too big to hold bitmaps"); + return -EINVAL; + } + + ll->entries_per_block = (ll->block_size - sizeof(struct disk_bitmap_header)) * + ENTRIES_PER_BYTE; + ll->nr_blocks = 0; + ll->bitmap_root = 0; + ll->ref_count_root = 0; + + return 0; +} + +int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks) +{ + int r; + dm_block_t i, nr_blocks, nr_indexes; + unsigned old_blocks, blocks; + + nr_blocks = ll->nr_blocks + extra_blocks; + old_blocks = dm_sector_div_up(ll->nr_blocks, ll->entries_per_block); + blocks = dm_sector_div_up(nr_blocks, ll->entries_per_block); + + nr_indexes = dm_sector_div_up(nr_blocks, ll->entries_per_block); + if (nr_indexes > ll->max_entries(ll)) { + DMERR("space map too large"); + return -EINVAL; + } + + for (i = old_blocks; i < blocks; i++) { + struct dm_block *b; + struct disk_index_entry idx; + + r = dm_tm_new_block(ll->tm, &dm_sm_bitmap_validator, &b); + if (r < 0) + return r; + idx.blocknr = cpu_to_le64(dm_block_location(b)); + + r = dm_tm_unlock(ll->tm, b); + if (r < 0) + return r; + + idx.nr_free = cpu_to_le32(ll->entries_per_block); + idx.none_free_before = 0; + + r = ll->save_ie(ll, i, &idx); + if (r < 0) + return r; + } + + ll->nr_blocks = nr_blocks; + return 0; +} + +int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result) +{ + int r; + dm_block_t index = b; + struct disk_index_entry ie_disk; + struct dm_block *blk; + + b = do_div(index, ll->entries_per_block); + r = ll->load_ie(ll, index, &ie_disk); + if (r < 0) + return r; + + r = dm_tm_read_lock(ll->tm, le64_to_cpu(ie_disk.blocknr), + &dm_sm_bitmap_validator, &blk); + if (r < 0) + return r; + + *result = sm_lookup_bitmap(dm_bitmap_data(blk), b); + + return dm_tm_unlock(ll->tm, blk); +} + +int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result) +{ + __le32 le_rc; + int r = sm_ll_lookup_bitmap(ll, b, result); + + if (r) + return r; + + if (*result != 3) + return r; + + r = dm_btree_lookup(&ll->ref_count_info, ll->ref_count_root, &b, &le_rc); + if (r < 0) + return r; + + *result = le32_to_cpu(le_rc); + + return r; +} + +int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, + dm_block_t end, dm_block_t *result) +{ + int r; + struct disk_index_entry ie_disk; + dm_block_t i, index_begin = begin; + dm_block_t index_end = dm_sector_div_up(end, ll->entries_per_block); + + /* + * FIXME: Use shifts + */ + begin = do_div(index_begin, ll->entries_per_block); + end = do_div(end, ll->entries_per_block); + + for (i = index_begin; i < index_end; i++, begin = 0) { + struct dm_block *blk; + unsigned position; + uint32_t bit_end; + + r = ll->load_ie(ll, i, &ie_disk); + if (r < 0) + return r; + + if (le32_to_cpu(ie_disk.nr_free) == 0) + continue; + + r = dm_tm_read_lock(ll->tm, le64_to_cpu(ie_disk.blocknr), + &dm_sm_bitmap_validator, &blk); + if (r < 0) + return r; + + bit_end = (i == index_end - 1) ? end : ll->entries_per_block; + + r = sm_find_free(dm_bitmap_data(blk), + max_t(unsigned, begin, le32_to_cpu(ie_disk.none_free_before)), + bit_end, &position); + if (r == -ENOSPC) { + /* + * This might happen because we started searching + * part way through the bitmap. + */ + dm_tm_unlock(ll->tm, blk); + continue; + + } else if (r < 0) { + dm_tm_unlock(ll->tm, blk); + return r; + } + + r = dm_tm_unlock(ll->tm, blk); + if (r < 0) + return r; + + *result = i * ll->entries_per_block + (dm_block_t) position; + return 0; + } + + return -ENOSPC; +} + +int sm_ll_insert(struct ll_disk *ll, dm_block_t b, + uint32_t ref_count, enum allocation_event *ev) +{ + int r; + uint32_t bit, old; + struct dm_block *nb; + dm_block_t index = b; + struct disk_index_entry ie_disk; + void *bm_le; + int inc; + + bit = do_div(index, ll->entries_per_block); + r = ll->load_ie(ll, index, &ie_disk); + if (r < 0) + return r; + + r = dm_tm_shadow_block(ll->tm, le64_to_cpu(ie_disk.blocknr), + &dm_sm_bitmap_validator, &nb, &inc); + if (r < 0) { + DMERR("dm_tm_shadow_block() failed"); + return r; + } + ie_disk.blocknr = cpu_to_le64(dm_block_location(nb)); + + bm_le = dm_bitmap_data(nb); + old = sm_lookup_bitmap(bm_le, bit); + + if (ref_count <= 2) { + sm_set_bitmap(bm_le, bit, ref_count); + + r = dm_tm_unlock(ll->tm, nb); + if (r < 0) + return r; + +#if 0 + /* FIXME: dm_btree_remove doesn't handle this yet */ + if (old > 2) { + r = dm_btree_remove(&ll->ref_count_info, + ll->ref_count_root, + &b, &ll->ref_count_root); + if (r) + return r; + } +#endif + + } else { + __le32 le_rc = cpu_to_le32(ref_count); + + sm_set_bitmap(bm_le, bit, 3); + r = dm_tm_unlock(ll->tm, nb); + if (r < 0) + return r; + + __dm_bless_for_disk(&le_rc); + r = dm_btree_insert(&ll->ref_count_info, ll->ref_count_root, + &b, &le_rc, &ll->ref_count_root); + if (r < 0) { + DMERR("ref count insert failed"); + return r; + } + } + + if (ref_count && !old) { + *ev = SM_ALLOC; + ll->nr_allocated++; + ie_disk.nr_free = cpu_to_le32(le32_to_cpu(ie_disk.nr_free) - 1); + if (le32_to_cpu(ie_disk.none_free_before) == bit) + ie_disk.none_free_before = cpu_to_le32(bit + 1); + + } else if (old && !ref_count) { + *ev = SM_FREE; + ll->nr_allocated--; + ie_disk.nr_free = cpu_to_le32(le32_to_cpu(ie_disk.nr_free) + 1); + ie_disk.none_free_before = cpu_to_le32(min(le32_to_cpu(ie_disk.none_free_before), bit)); + } + + return ll->save_ie(ll, index, &ie_disk); +} + +int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +{ + int r; + uint32_t rc; + + r = sm_ll_lookup(ll, b, &rc); + if (r) + return r; + + return sm_ll_insert(ll, b, rc + 1, ev); +} + +int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +{ + int r; + uint32_t rc; + + r = sm_ll_lookup(ll, b, &rc); + if (r) + return r; + + if (!rc) + return -EINVAL; + + return sm_ll_insert(ll, b, rc - 1, ev); +} + +int sm_ll_commit(struct ll_disk *ll) +{ + return ll->commit(ll); +} + +/*----------------------------------------------------------------*/ + +static int metadata_ll_load_ie(struct ll_disk *ll, dm_block_t index, + struct disk_index_entry *ie) +{ + memcpy(ie, ll->mi_le.index + index, sizeof(*ie)); + return 0; +} + +static int metadata_ll_save_ie(struct ll_disk *ll, dm_block_t index, + struct disk_index_entry *ie) +{ + memcpy(ll->mi_le.index + index, ie, sizeof(*ie)); + return 0; +} + +static int metadata_ll_init_index(struct ll_disk *ll) +{ + int r; + struct dm_block *b; + + r = dm_tm_new_block(ll->tm, &index_validator, &b); + if (r < 0) + return r; + + memcpy(dm_block_data(b), &ll->mi_le, sizeof(ll->mi_le)); + ll->bitmap_root = dm_block_location(b); + + return dm_tm_unlock(ll->tm, b); +} + +static int metadata_ll_open(struct ll_disk *ll) +{ + int r; + struct dm_block *block; + + r = dm_tm_read_lock(ll->tm, ll->bitmap_root, + &index_validator, &block); + if (r) + return r; + + memcpy(&ll->mi_le, dm_block_data(block), sizeof(ll->mi_le)); + return dm_tm_unlock(ll->tm, block); +} + +static dm_block_t metadata_ll_max_entries(struct ll_disk *ll) +{ + return MAX_METADATA_BITMAPS; +} + +static int metadata_ll_commit(struct ll_disk *ll) +{ + int r, inc; + struct dm_block *b; + + r = dm_tm_shadow_block(ll->tm, ll->bitmap_root, &index_validator, &b, &inc); + if (r) + return r; + + memcpy(dm_block_data(b), &ll->mi_le, sizeof(ll->mi_le)); + ll->bitmap_root = dm_block_location(b); + + return dm_tm_unlock(ll->tm, b); +} + +int sm_ll_new_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm) +{ + int r; + + r = sm_ll_init(ll, tm); + if (r < 0) + return r; + + ll->load_ie = metadata_ll_load_ie; + ll->save_ie = metadata_ll_save_ie; + ll->init_index = metadata_ll_init_index; + ll->open_index = metadata_ll_open; + ll->max_entries = metadata_ll_max_entries; + ll->commit = metadata_ll_commit; + + ll->nr_blocks = 0; + ll->nr_allocated = 0; + + r = ll->init_index(ll); + if (r < 0) + return r; + + r = dm_btree_empty(&ll->ref_count_info, &ll->ref_count_root); + if (r < 0) + return r; + + return 0; +} + +int sm_ll_open_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm, + void *root_le, size_t len) +{ + int r; + struct disk_sm_root *smr = root_le; + + if (len < sizeof(struct disk_sm_root)) { + DMERR("sm_metadata root too small"); + return -ENOMEM; + } + + r = sm_ll_init(ll, tm); + if (r < 0) + return r; + + ll->load_ie = metadata_ll_load_ie; + ll->save_ie = metadata_ll_save_ie; + ll->init_index = metadata_ll_init_index; + ll->open_index = metadata_ll_open; + ll->max_entries = metadata_ll_max_entries; + ll->commit = metadata_ll_commit; + + ll->nr_blocks = le64_to_cpu(smr->nr_blocks); + ll->nr_allocated = le64_to_cpu(smr->nr_allocated); + ll->bitmap_root = le64_to_cpu(smr->bitmap_root); + ll->ref_count_root = le64_to_cpu(smr->ref_count_root); + + return ll->open_index(ll); +} + +/*----------------------------------------------------------------*/ + +static int disk_ll_load_ie(struct ll_disk *ll, dm_block_t index, + struct disk_index_entry *ie) +{ + return dm_btree_lookup(&ll->bitmap_info, ll->bitmap_root, &index, ie); +} + +static int disk_ll_save_ie(struct ll_disk *ll, dm_block_t index, + struct disk_index_entry *ie) +{ + __dm_bless_for_disk(ie); + return dm_btree_insert(&ll->bitmap_info, ll->bitmap_root, + &index, ie, &ll->bitmap_root); +} + +static int disk_ll_init_index(struct ll_disk *ll) +{ + return dm_btree_empty(&ll->bitmap_info, &ll->bitmap_root); +} + +static int disk_ll_open(struct ll_disk *ll) +{ + /* nothing to do */ + return 0; +} + +static dm_block_t disk_ll_max_entries(struct ll_disk *ll) +{ + return -1ULL; +} + +static int disk_ll_commit(struct ll_disk *ll) +{ + return 0; +} + +int sm_ll_new_disk(struct ll_disk *ll, struct dm_transaction_manager *tm) +{ + int r; + + r = sm_ll_init(ll, tm); + if (r < 0) + return r; + + ll->load_ie = disk_ll_load_ie; + ll->save_ie = disk_ll_save_ie; + ll->init_index = disk_ll_init_index; + ll->open_index = disk_ll_open; + ll->max_entries = disk_ll_max_entries; + ll->commit = disk_ll_commit; + + ll->nr_blocks = 0; + ll->nr_allocated = 0; + + r = ll->init_index(ll); + if (r < 0) + return r; + + r = dm_btree_empty(&ll->ref_count_info, &ll->ref_count_root); + if (r < 0) + return r; + + return 0; +} + +int sm_ll_open_disk(struct ll_disk *ll, struct dm_transaction_manager *tm, + void *root_le, size_t len) +{ + int r; + struct disk_sm_root *smr = root_le; + + if (len < sizeof(struct disk_sm_root)) { + DMERR("sm_metadata root too small"); + return -ENOMEM; + } + + r = sm_ll_init(ll, tm); + if (r < 0) + return r; + + ll->load_ie = disk_ll_load_ie; + ll->save_ie = disk_ll_save_ie; + ll->init_index = disk_ll_init_index; + ll->open_index = disk_ll_open; + ll->max_entries = disk_ll_max_entries; + ll->commit = disk_ll_commit; + + ll->nr_blocks = le64_to_cpu(smr->nr_blocks); + ll->nr_allocated = le64_to_cpu(smr->nr_allocated); + ll->bitmap_root = le64_to_cpu(smr->bitmap_root); + ll->ref_count_root = le64_to_cpu(smr->ref_count_root); + + return ll->open_index(ll); +} + +/*----------------------------------------------------------------*/ diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h new file mode 100644 index 000000000000..8f220821a9a9 --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-common.h @@ -0,0 +1,126 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef DM_SPACE_MAP_COMMON_H +#define DM_SPACE_MAP_COMMON_H + +#include "dm-btree.h" + +/*----------------------------------------------------------------*/ + +/* + * Low level disk format + * + * Bitmap btree + * ------------ + * + * Each value stored in the btree is an index_entry. This points to a + * block that is used as a bitmap. Within the bitmap hold 2 bits per + * entry, which represent UNUSED = 0, REF_COUNT = 1, REF_COUNT = 2 and + * REF_COUNT = many. + * + * Refcount btree + * -------------- + * + * Any entry that has a ref count higher than 2 gets entered in the ref + * count tree. The leaf values for this tree is the 32-bit ref count. + */ + +struct disk_index_entry { + __le64 blocknr; + __le32 nr_free; + __le32 none_free_before; +} __packed; + + +#define MAX_METADATA_BITMAPS 255 +struct disk_metadata_index { + __le32 csum; + __le32 padding; + __le64 blocknr; + + struct disk_index_entry index[MAX_METADATA_BITMAPS]; +} __packed; + +struct ll_disk; + +typedef int (*load_ie_fn)(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *result); +typedef int (*save_ie_fn)(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *ie); +typedef int (*init_index_fn)(struct ll_disk *ll); +typedef int (*open_index_fn)(struct ll_disk *ll); +typedef dm_block_t (*max_index_entries_fn)(struct ll_disk *ll); +typedef int (*commit_fn)(struct ll_disk *ll); + +struct ll_disk { + struct dm_transaction_manager *tm; + struct dm_btree_info bitmap_info; + struct dm_btree_info ref_count_info; + + uint32_t block_size; + uint32_t entries_per_block; + dm_block_t nr_blocks; + dm_block_t nr_allocated; + + /* + * bitmap_root may be a btree root or a simple index. + */ + dm_block_t bitmap_root; + + dm_block_t ref_count_root; + + struct disk_metadata_index mi_le; + load_ie_fn load_ie; + save_ie_fn save_ie; + init_index_fn init_index; + open_index_fn open_index; + max_index_entries_fn max_entries; + commit_fn commit; +}; + +struct disk_sm_root { + __le64 nr_blocks; + __le64 nr_allocated; + __le64 bitmap_root; + __le64 ref_count_root; +} __packed; + +#define ENTRIES_PER_BYTE 4 + +struct disk_bitmap_header { + __le32 csum; + __le32 not_used; + __le64 blocknr; +} __packed; + +enum allocation_event { + SM_NONE, + SM_ALLOC, + SM_FREE, +}; + +/*----------------------------------------------------------------*/ + +int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks); +int sm_ll_lookup_bitmap(struct ll_disk *ll, dm_block_t b, uint32_t *result); +int sm_ll_lookup(struct ll_disk *ll, dm_block_t b, uint32_t *result); +int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, + dm_block_t end, dm_block_t *result); +int sm_ll_insert(struct ll_disk *ll, dm_block_t b, uint32_t ref_count, enum allocation_event *ev); +int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev); +int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev); +int sm_ll_commit(struct ll_disk *ll); + +int sm_ll_new_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm); +int sm_ll_open_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm, + void *root_le, size_t len); + +int sm_ll_new_disk(struct ll_disk *ll, struct dm_transaction_manager *tm); +int sm_ll_open_disk(struct ll_disk *ll, struct dm_transaction_manager *tm, + void *root_le, size_t len); + +/*----------------------------------------------------------------*/ + +#endif /* DM_SPACE_MAP_COMMON_H */ diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c new file mode 100644 index 000000000000..aeff7852cf79 --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -0,0 +1,335 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-space-map-checker.h" +#include "dm-space-map-common.h" +#include "dm-space-map-disk.h" +#include "dm-space-map.h" +#include "dm-transaction-manager.h" + +#include +#include +#include +#include + +#define DM_MSG_PREFIX "space map disk" + +/*----------------------------------------------------------------*/ + +/* + * Space map interface. + */ +struct sm_disk { + struct dm_space_map sm; + + struct ll_disk ll; + struct ll_disk old_ll; + + dm_block_t begin; + dm_block_t nr_allocated_this_transaction; +}; + +static void sm_disk_destroy(struct dm_space_map *sm) +{ + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + + kfree(smd); +} + +static int sm_disk_extend(struct dm_space_map *sm, dm_block_t extra_blocks) +{ + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + + return sm_ll_extend(&smd->ll, extra_blocks); +} + +static int sm_disk_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + *count = smd->old_ll.nr_blocks; + + return 0; +} + +static int sm_disk_get_nr_free(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + *count = (smd->old_ll.nr_blocks - smd->old_ll.nr_allocated) - smd->nr_allocated_this_transaction; + + return 0; +} + +static int sm_disk_get_count(struct dm_space_map *sm, dm_block_t b, + uint32_t *result) +{ + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + return sm_ll_lookup(&smd->ll, b, result); +} + +static int sm_disk_count_is_more_than_one(struct dm_space_map *sm, dm_block_t b, + int *result) +{ + int r; + uint32_t count; + + r = sm_disk_get_count(sm, b, &count); + if (r) + return r; + + return count > 1; +} + +static int sm_disk_set_count(struct dm_space_map *sm, dm_block_t b, + uint32_t count) +{ + int r; + uint32_t old_count; + enum allocation_event ev; + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + + r = sm_ll_insert(&smd->ll, b, count, &ev); + if (!r) { + switch (ev) { + case SM_NONE: + break; + + case SM_ALLOC: + /* + * This _must_ be free in the prior transaction + * otherwise we've lost atomicity. + */ + smd->nr_allocated_this_transaction++; + break; + + case SM_FREE: + /* + * It's only free if it's also free in the last + * transaction. + */ + r = sm_ll_lookup(&smd->old_ll, b, &old_count); + if (r) + return r; + + if (!old_count) + smd->nr_allocated_this_transaction--; + break; + } + } + + return r; +} + +static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b) +{ + int r; + enum allocation_event ev; + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + + r = sm_ll_inc(&smd->ll, b, &ev); + if (!r && (ev == SM_ALLOC)) + /* + * This _must_ be free in the prior transaction + * otherwise we've lost atomicity. + */ + smd->nr_allocated_this_transaction++; + + return r; +} + +static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b) +{ + int r; + uint32_t old_count; + enum allocation_event ev; + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + + r = sm_ll_dec(&smd->ll, b, &ev); + if (!r && (ev == SM_FREE)) { + /* + * It's only free if it's also free in the last + * transaction. + */ + r = sm_ll_lookup(&smd->old_ll, b, &old_count); + if (r) + return r; + + if (!old_count) + smd->nr_allocated_this_transaction--; + } + + return r; +} + +static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) +{ + int r; + enum allocation_event ev; + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + + /* FIXME: we should loop round a couple of times */ + r = sm_ll_find_free_block(&smd->old_ll, smd->begin, smd->old_ll.nr_blocks, b); + if (r) + return r; + + smd->begin = *b + 1; + r = sm_ll_inc(&smd->ll, *b, &ev); + if (!r) { + BUG_ON(ev != SM_ALLOC); + smd->nr_allocated_this_transaction++; + } + + return r; +} + +static int sm_disk_commit(struct dm_space_map *sm) +{ + int r; + dm_block_t nr_free; + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + + r = sm_disk_get_nr_free(sm, &nr_free); + if (r) + return r; + + r = sm_ll_commit(&smd->ll); + if (r) + return r; + + memcpy(&smd->old_ll, &smd->ll, sizeof(smd->old_ll)); + smd->begin = 0; + smd->nr_allocated_this_transaction = 0; + + r = sm_disk_get_nr_free(sm, &nr_free); + if (r) + return r; + + return 0; +} + +static int sm_disk_root_size(struct dm_space_map *sm, size_t *result) +{ + *result = sizeof(struct disk_sm_root); + + return 0; +} + +static int sm_disk_copy_root(struct dm_space_map *sm, void *where_le, size_t max) +{ + struct sm_disk *smd = container_of(sm, struct sm_disk, sm); + struct disk_sm_root root_le; + + root_le.nr_blocks = cpu_to_le64(smd->ll.nr_blocks); + root_le.nr_allocated = cpu_to_le64(smd->ll.nr_allocated); + root_le.bitmap_root = cpu_to_le64(smd->ll.bitmap_root); + root_le.ref_count_root = cpu_to_le64(smd->ll.ref_count_root); + + if (max < sizeof(root_le)) + return -ENOSPC; + + memcpy(where_le, &root_le, sizeof(root_le)); + + return 0; +} + +/*----------------------------------------------------------------*/ + +static struct dm_space_map ops = { + .destroy = sm_disk_destroy, + .extend = sm_disk_extend, + .get_nr_blocks = sm_disk_get_nr_blocks, + .get_nr_free = sm_disk_get_nr_free, + .get_count = sm_disk_get_count, + .count_is_more_than_one = sm_disk_count_is_more_than_one, + .set_count = sm_disk_set_count, + .inc_block = sm_disk_inc_block, + .dec_block = sm_disk_dec_block, + .new_block = sm_disk_new_block, + .commit = sm_disk_commit, + .root_size = sm_disk_root_size, + .copy_root = sm_disk_copy_root +}; + +static struct dm_space_map *dm_sm_disk_create_real( + struct dm_transaction_manager *tm, + dm_block_t nr_blocks) +{ + int r; + struct sm_disk *smd; + + smd = kmalloc(sizeof(*smd), GFP_KERNEL); + if (!smd) + return ERR_PTR(-ENOMEM); + + smd->begin = 0; + smd->nr_allocated_this_transaction = 0; + memcpy(&smd->sm, &ops, sizeof(smd->sm)); + + r = sm_ll_new_disk(&smd->ll, tm); + if (r) + goto bad; + + r = sm_ll_extend(&smd->ll, nr_blocks); + if (r) + goto bad; + + r = sm_disk_commit(&smd->sm); + if (r) + goto bad; + + return &smd->sm; + +bad: + kfree(smd); + return ERR_PTR(r); +} + +struct dm_space_map *dm_sm_disk_create(struct dm_transaction_manager *tm, + dm_block_t nr_blocks) +{ + struct dm_space_map *sm = dm_sm_disk_create_real(tm, nr_blocks); + return dm_sm_checker_create_fresh(sm); +} +EXPORT_SYMBOL_GPL(dm_sm_disk_create); + +static struct dm_space_map *dm_sm_disk_open_real( + struct dm_transaction_manager *tm, + void *root_le, size_t len) +{ + int r; + struct sm_disk *smd; + + smd = kmalloc(sizeof(*smd), GFP_KERNEL); + if (!smd) + return ERR_PTR(-ENOMEM); + + smd->begin = 0; + smd->nr_allocated_this_transaction = 0; + memcpy(&smd->sm, &ops, sizeof(smd->sm)); + + r = sm_ll_open_disk(&smd->ll, tm, root_le, len); + if (r) + goto bad; + + r = sm_disk_commit(&smd->sm); + if (r) + goto bad; + + return &smd->sm; + +bad: + kfree(smd); + return ERR_PTR(r); +} + +struct dm_space_map *dm_sm_disk_open(struct dm_transaction_manager *tm, + void *root_le, size_t len) +{ + return dm_sm_checker_create( + dm_sm_disk_open_real(tm, root_le, len)); +} +EXPORT_SYMBOL_GPL(dm_sm_disk_open); + +/*----------------------------------------------------------------*/ diff --git a/drivers/md/persistent-data/dm-space-map-disk.h b/drivers/md/persistent-data/dm-space-map-disk.h new file mode 100644 index 000000000000..447a0a9a2d9f --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-disk.h @@ -0,0 +1,25 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef _LINUX_DM_SPACE_MAP_DISK_H +#define _LINUX_DM_SPACE_MAP_DISK_H + +#include "dm-block-manager.h" + +struct dm_space_map; +struct dm_transaction_manager; + +/* + * Unfortunately we have to use two-phase construction due to the cycle + * between the tm and sm. + */ +struct dm_space_map *dm_sm_disk_create(struct dm_transaction_manager *tm, + dm_block_t nr_blocks); + +struct dm_space_map *dm_sm_disk_open(struct dm_transaction_manager *tm, + void *root, size_t len); + +#endif /* _LINUX_DM_SPACE_MAP_DISK_H */ diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c new file mode 100644 index 000000000000..e89ae5e7a519 --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -0,0 +1,596 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-space-map.h" +#include "dm-space-map-common.h" +#include "dm-space-map-metadata.h" + +#include +#include +#include + +#define DM_MSG_PREFIX "space map metadata" + +/*----------------------------------------------------------------*/ + +/* + * Space map interface. + * + * The low level disk format is written using the standard btree and + * transaction manager. This means that performing disk operations may + * cause us to recurse into the space map in order to allocate new blocks. + * For this reason we have a pool of pre-allocated blocks large enough to + * service any metadata_ll_disk operation. + */ + +/* + * FIXME: we should calculate this based on the size of the device. + * Only the metadata space map needs this functionality. + */ +#define MAX_RECURSIVE_ALLOCATIONS 1024 + +enum block_op_type { + BOP_INC, + BOP_DEC +}; + +struct block_op { + enum block_op_type type; + dm_block_t block; +}; + +struct sm_metadata { + struct dm_space_map sm; + + struct ll_disk ll; + struct ll_disk old_ll; + + dm_block_t begin; + + unsigned recursion_count; + unsigned allocated_this_transaction; + unsigned nr_uncommitted; + struct block_op uncommitted[MAX_RECURSIVE_ALLOCATIONS]; +}; + +static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b) +{ + struct block_op *op; + + if (smm->nr_uncommitted == MAX_RECURSIVE_ALLOCATIONS) { + DMERR("too many recursive allocations"); + return -ENOMEM; + } + + op = smm->uncommitted + smm->nr_uncommitted++; + op->type = type; + op->block = b; + + return 0; +} + +static int commit_bop(struct sm_metadata *smm, struct block_op *op) +{ + int r = 0; + enum allocation_event ev; + + switch (op->type) { + case BOP_INC: + r = sm_ll_inc(&smm->ll, op->block, &ev); + break; + + case BOP_DEC: + r = sm_ll_dec(&smm->ll, op->block, &ev); + break; + } + + return r; +} + +static void in(struct sm_metadata *smm) +{ + smm->recursion_count++; +} + +static int out(struct sm_metadata *smm) +{ + int r = 0; + + /* + * If we're not recursing then very bad things are happening. + */ + if (!smm->recursion_count) { + DMERR("lost track of recursion depth"); + return -ENOMEM; + } + + if (smm->recursion_count == 1 && smm->nr_uncommitted) { + while (smm->nr_uncommitted && !r) { + smm->nr_uncommitted--; + r = commit_bop(smm, smm->uncommitted + + smm->nr_uncommitted); + if (r) + break; + } + } + + smm->recursion_count--; + + return r; +} + +/* + * When using the out() function above, we often want to combine an error + * code for the operation run in the recursive context with that from + * out(). + */ +static int combine_errors(int r1, int r2) +{ + return r1 ? r1 : r2; +} + +static int recursing(struct sm_metadata *smm) +{ + return smm->recursion_count; +} + +static void sm_metadata_destroy(struct dm_space_map *sm) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + kfree(smm); +} + +static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) +{ + DMERR("doesn't support extend"); + return -EINVAL; +} + +static int sm_metadata_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + *count = smm->ll.nr_blocks; + + return 0; +} + +static int sm_metadata_get_nr_free(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + *count = smm->old_ll.nr_blocks - smm->old_ll.nr_allocated - + smm->allocated_this_transaction; + + return 0; +} + +static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b, + uint32_t *result) +{ + int r, i; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + unsigned adjustment = 0; + + /* + * We may have some uncommitted adjustments to add. This list + * should always be really short. + */ + for (i = 0; i < smm->nr_uncommitted; i++) { + struct block_op *op = smm->uncommitted + i; + + if (op->block != b) + continue; + + switch (op->type) { + case BOP_INC: + adjustment++; + break; + + case BOP_DEC: + adjustment--; + break; + } + } + + r = sm_ll_lookup(&smm->ll, b, result); + if (r) + return r; + + *result += adjustment; + + return 0; +} + +static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm, + dm_block_t b, int *result) +{ + int r, i, adjustment = 0; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + uint32_t rc; + + /* + * We may have some uncommitted adjustments to add. This list + * should always be really short. + */ + for (i = 0; i < smm->nr_uncommitted; i++) { + struct block_op *op = smm->uncommitted + i; + + if (op->block != b) + continue; + + switch (op->type) { + case BOP_INC: + adjustment++; + break; + + case BOP_DEC: + adjustment--; + break; + } + } + + if (adjustment > 1) { + *result = 1; + return 0; + } + + r = sm_ll_lookup_bitmap(&smm->ll, b, &rc); + if (r) + return r; + + if (rc == 3) + /* + * We err on the side of caution, and always return true. + */ + *result = 1; + else + *result = rc + adjustment > 1; + + return 0; +} + +static int sm_metadata_set_count(struct dm_space_map *sm, dm_block_t b, + uint32_t count) +{ + int r, r2; + enum allocation_event ev; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + if (smm->recursion_count) { + DMERR("cannot recurse set_count()"); + return -EINVAL; + } + + in(smm); + r = sm_ll_insert(&smm->ll, b, count, &ev); + r2 = out(smm); + + return combine_errors(r, r2); +} + +static int sm_metadata_inc_block(struct dm_space_map *sm, dm_block_t b) +{ + int r, r2 = 0; + enum allocation_event ev; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + if (recursing(smm)) + r = add_bop(smm, BOP_INC, b); + else { + in(smm); + r = sm_ll_inc(&smm->ll, b, &ev); + r2 = out(smm); + } + + return combine_errors(r, r2); +} + +static int sm_metadata_dec_block(struct dm_space_map *sm, dm_block_t b) +{ + int r, r2 = 0; + enum allocation_event ev; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + if (recursing(smm)) + r = add_bop(smm, BOP_DEC, b); + else { + in(smm); + r = sm_ll_dec(&smm->ll, b, &ev); + r2 = out(smm); + } + + return combine_errors(r, r2); +} + +static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b) +{ + int r, r2 = 0; + enum allocation_event ev; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + r = sm_ll_find_free_block(&smm->old_ll, smm->begin, smm->old_ll.nr_blocks, b); + if (r) + return r; + + smm->begin = *b + 1; + + if (recursing(smm)) + r = add_bop(smm, BOP_INC, *b); + else { + in(smm); + r = sm_ll_inc(&smm->ll, *b, &ev); + r2 = out(smm); + } + + if (!r) + smm->allocated_this_transaction++; + + return combine_errors(r, r2); +} + +static int sm_metadata_new_block(struct dm_space_map *sm, dm_block_t *b) +{ + int r = sm_metadata_new_block_(sm, b); + if (r) + DMERR("out of metadata space"); + return r; +} + +static int sm_metadata_commit(struct dm_space_map *sm) +{ + int r; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + r = sm_ll_commit(&smm->ll); + if (r) + return r; + + memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll)); + smm->begin = 0; + smm->allocated_this_transaction = 0; + + return 0; +} + +static int sm_metadata_root_size(struct dm_space_map *sm, size_t *result) +{ + *result = sizeof(struct disk_sm_root); + + return 0; +} + +static int sm_metadata_copy_root(struct dm_space_map *sm, void *where_le, size_t max) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + struct disk_sm_root root_le; + + root_le.nr_blocks = cpu_to_le64(smm->ll.nr_blocks); + root_le.nr_allocated = cpu_to_le64(smm->ll.nr_allocated); + root_le.bitmap_root = cpu_to_le64(smm->ll.bitmap_root); + root_le.ref_count_root = cpu_to_le64(smm->ll.ref_count_root); + + if (max < sizeof(root_le)) + return -ENOSPC; + + memcpy(where_le, &root_le, sizeof(root_le)); + + return 0; +} + +static struct dm_space_map ops = { + .destroy = sm_metadata_destroy, + .extend = sm_metadata_extend, + .get_nr_blocks = sm_metadata_get_nr_blocks, + .get_nr_free = sm_metadata_get_nr_free, + .get_count = sm_metadata_get_count, + .count_is_more_than_one = sm_metadata_count_is_more_than_one, + .set_count = sm_metadata_set_count, + .inc_block = sm_metadata_inc_block, + .dec_block = sm_metadata_dec_block, + .new_block = sm_metadata_new_block, + .commit = sm_metadata_commit, + .root_size = sm_metadata_root_size, + .copy_root = sm_metadata_copy_root +}; + +/*----------------------------------------------------------------*/ + +/* + * When a new space map is created that manages its own space. We use + * this tiny bootstrap allocator. + */ +static void sm_bootstrap_destroy(struct dm_space_map *sm) +{ +} + +static int sm_bootstrap_extend(struct dm_space_map *sm, dm_block_t extra_blocks) +{ + DMERR("boostrap doesn't support extend"); + + return -EINVAL; +} + +static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + return smm->ll.nr_blocks; +} + +static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + *count = smm->ll.nr_blocks - smm->begin; + + return 0; +} + +static int sm_bootstrap_get_count(struct dm_space_map *sm, dm_block_t b, + uint32_t *result) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + return b < smm->begin ? 1 : 0; +} + +static int sm_bootstrap_count_is_more_than_one(struct dm_space_map *sm, + dm_block_t b, int *result) +{ + *result = 0; + + return 0; +} + +static int sm_bootstrap_set_count(struct dm_space_map *sm, dm_block_t b, + uint32_t count) +{ + DMERR("boostrap doesn't support set_count"); + + return -EINVAL; +} + +static int sm_bootstrap_new_block(struct dm_space_map *sm, dm_block_t *b) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + /* + * We know the entire device is unused. + */ + if (smm->begin == smm->ll.nr_blocks) + return -ENOSPC; + + *b = smm->begin++; + + return 0; +} + +static int sm_bootstrap_inc_block(struct dm_space_map *sm, dm_block_t b) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + return add_bop(smm, BOP_INC, b); +} + +static int sm_bootstrap_dec_block(struct dm_space_map *sm, dm_block_t b) +{ + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + return add_bop(smm, BOP_DEC, b); +} + +static int sm_bootstrap_commit(struct dm_space_map *sm) +{ + return 0; +} + +static int sm_bootstrap_root_size(struct dm_space_map *sm, size_t *result) +{ + DMERR("boostrap doesn't support root_size"); + + return -EINVAL; +} + +static int sm_bootstrap_copy_root(struct dm_space_map *sm, void *where, + size_t max) +{ + DMERR("boostrap doesn't support copy_root"); + + return -EINVAL; +} + +static struct dm_space_map bootstrap_ops = { + .destroy = sm_bootstrap_destroy, + .extend = sm_bootstrap_extend, + .get_nr_blocks = sm_bootstrap_get_nr_blocks, + .get_nr_free = sm_bootstrap_get_nr_free, + .get_count = sm_bootstrap_get_count, + .count_is_more_than_one = sm_bootstrap_count_is_more_than_one, + .set_count = sm_bootstrap_set_count, + .inc_block = sm_bootstrap_inc_block, + .dec_block = sm_bootstrap_dec_block, + .new_block = sm_bootstrap_new_block, + .commit = sm_bootstrap_commit, + .root_size = sm_bootstrap_root_size, + .copy_root = sm_bootstrap_copy_root +}; + +/*----------------------------------------------------------------*/ + +struct dm_space_map *dm_sm_metadata_init(void) +{ + struct sm_metadata *smm; + + smm = kmalloc(sizeof(*smm), GFP_KERNEL); + if (!smm) + return ERR_PTR(-ENOMEM); + + memcpy(&smm->sm, &ops, sizeof(smm->sm)); + + return &smm->sm; +} + +int dm_sm_metadata_create(struct dm_space_map *sm, + struct dm_transaction_manager *tm, + dm_block_t nr_blocks, + dm_block_t superblock) +{ + int r; + dm_block_t i; + enum allocation_event ev; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + smm->begin = superblock + 1; + smm->recursion_count = 0; + smm->allocated_this_transaction = 0; + smm->nr_uncommitted = 0; + + memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm)); + + r = sm_ll_new_metadata(&smm->ll, tm); + if (r) + return r; + + r = sm_ll_extend(&smm->ll, nr_blocks); + if (r) + return r; + + memcpy(&smm->sm, &ops, sizeof(smm->sm)); + + /* + * Now we need to update the newly created data structures with the + * allocated blocks that they were built from. + */ + for (i = superblock; !r && i < smm->begin; i++) + r = sm_ll_inc(&smm->ll, i, &ev); + + if (r) + return r; + + return sm_metadata_commit(sm); +} + +int dm_sm_metadata_open(struct dm_space_map *sm, + struct dm_transaction_manager *tm, + void *root_le, size_t len) +{ + int r; + struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); + + r = sm_ll_open_metadata(&smm->ll, tm, root_le, len); + if (r) + return r; + + smm->begin = 0; + smm->recursion_count = 0; + smm->allocated_this_transaction = 0; + smm->nr_uncommitted = 0; + + memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll)); + return 0; +} diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h new file mode 100644 index 000000000000..39bba0801cf2 --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map-metadata.h @@ -0,0 +1,33 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef DM_SPACE_MAP_METADATA_H +#define DM_SPACE_MAP_METADATA_H + +#include "dm-transaction-manager.h" + +/* + * Unfortunately we have to use two-phase construction due to the cycle + * between the tm and sm. + */ +struct dm_space_map *dm_sm_metadata_init(void); + +/* + * Create a fresh space map. + */ +int dm_sm_metadata_create(struct dm_space_map *sm, + struct dm_transaction_manager *tm, + dm_block_t nr_blocks, + dm_block_t superblock); + +/* + * Open from a previously-recorded root. + */ +int dm_sm_metadata_open(struct dm_space_map *sm, + struct dm_transaction_manager *tm, + void *root_le, size_t len); + +#endif /* DM_SPACE_MAP_METADATA_H */ diff --git a/drivers/md/persistent-data/dm-space-map.h b/drivers/md/persistent-data/dm-space-map.h new file mode 100644 index 000000000000..1cbfc6b1638a --- /dev/null +++ b/drivers/md/persistent-data/dm-space-map.h @@ -0,0 +1,134 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef _LINUX_DM_SPACE_MAP_H +#define _LINUX_DM_SPACE_MAP_H + +#include "dm-block-manager.h" + +/* + * struct dm_space_map keeps a record of how many times each block in a device + * is referenced. It needs to be fixed on disk as part of the transaction. + */ +struct dm_space_map { + void (*destroy)(struct dm_space_map *sm); + + /* + * You must commit before allocating the newly added space. + */ + int (*extend)(struct dm_space_map *sm, dm_block_t extra_blocks); + + /* + * Extensions do not appear in this count until after commit has + * been called. + */ + int (*get_nr_blocks)(struct dm_space_map *sm, dm_block_t *count); + + /* + * Space maps must never allocate a block from the previous + * transaction, in case we need to rollback. This complicates the + * semantics of get_nr_free(), it should return the number of blocks + * that are available for allocation _now_. For instance you may + * have blocks with a zero reference count that will not be + * available for allocation until after the next commit. + */ + int (*get_nr_free)(struct dm_space_map *sm, dm_block_t *count); + + int (*get_count)(struct dm_space_map *sm, dm_block_t b, uint32_t *result); + int (*count_is_more_than_one)(struct dm_space_map *sm, dm_block_t b, + int *result); + int (*set_count)(struct dm_space_map *sm, dm_block_t b, uint32_t count); + + int (*commit)(struct dm_space_map *sm); + + int (*inc_block)(struct dm_space_map *sm, dm_block_t b); + int (*dec_block)(struct dm_space_map *sm, dm_block_t b); + + /* + * new_block will increment the returned block. + */ + int (*new_block)(struct dm_space_map *sm, dm_block_t *b); + + /* + * The root contains all the information needed to fix the space map. + * Generally this info is small, so squirrel it away in a disk block + * along with other info. + */ + int (*root_size)(struct dm_space_map *sm, size_t *result); + int (*copy_root)(struct dm_space_map *sm, void *copy_to_here_le, size_t len); +}; + +/*----------------------------------------------------------------*/ + +static inline void dm_sm_destroy(struct dm_space_map *sm) +{ + sm->destroy(sm); +} + +static inline int dm_sm_extend(struct dm_space_map *sm, dm_block_t extra_blocks) +{ + return sm->extend(sm, extra_blocks); +} + +static inline int dm_sm_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count) +{ + return sm->get_nr_blocks(sm, count); +} + +static inline int dm_sm_get_nr_free(struct dm_space_map *sm, dm_block_t *count) +{ + return sm->get_nr_free(sm, count); +} + +static inline int dm_sm_get_count(struct dm_space_map *sm, dm_block_t b, + uint32_t *result) +{ + return sm->get_count(sm, b, result); +} + +static inline int dm_sm_count_is_more_than_one(struct dm_space_map *sm, + dm_block_t b, int *result) +{ + return sm->count_is_more_than_one(sm, b, result); +} + +static inline int dm_sm_set_count(struct dm_space_map *sm, dm_block_t b, + uint32_t count) +{ + return sm->set_count(sm, b, count); +} + +static inline int dm_sm_commit(struct dm_space_map *sm) +{ + return sm->commit(sm); +} + +static inline int dm_sm_inc_block(struct dm_space_map *sm, dm_block_t b) +{ + return sm->inc_block(sm, b); +} + +static inline int dm_sm_dec_block(struct dm_space_map *sm, dm_block_t b) +{ + return sm->dec_block(sm, b); +} + +static inline int dm_sm_new_block(struct dm_space_map *sm, dm_block_t *b) +{ + return sm->new_block(sm, b); +} + +static inline int dm_sm_root_size(struct dm_space_map *sm, size_t *result) +{ + return sm->root_size(sm, result); +} + +static inline int dm_sm_copy_root(struct dm_space_map *sm, void *copy_to_here_le, size_t len) +{ + return sm->copy_root(sm, copy_to_here_le, len); +} + +#endif /* _LINUX_DM_SPACE_MAP_H */ diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c new file mode 100644 index 000000000000..728e89a3f978 --- /dev/null +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -0,0 +1,400 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ +#include "dm-transaction-manager.h" +#include "dm-space-map.h" +#include "dm-space-map-checker.h" +#include "dm-space-map-disk.h" +#include "dm-space-map-metadata.h" +#include "dm-persistent-data-internal.h" + +#include +#include +#include + +#define DM_MSG_PREFIX "transaction manager" + +/*----------------------------------------------------------------*/ + +struct shadow_info { + struct hlist_node hlist; + dm_block_t where; +}; + +/* + * It would be nice if we scaled with the size of transaction. + */ +#define HASH_SIZE 256 +#define HASH_MASK (HASH_SIZE - 1) + +struct dm_transaction_manager { + int is_clone; + struct dm_transaction_manager *real; + + struct dm_block_manager *bm; + struct dm_space_map *sm; + + spinlock_t lock; + struct hlist_head buckets[HASH_SIZE]; +}; + +/*----------------------------------------------------------------*/ + +static int is_shadow(struct dm_transaction_manager *tm, dm_block_t b) +{ + int r = 0; + unsigned bucket = dm_hash_block(b, HASH_MASK); + struct shadow_info *si; + struct hlist_node *n; + + spin_lock(&tm->lock); + hlist_for_each_entry(si, n, tm->buckets + bucket, hlist) + if (si->where == b) { + r = 1; + break; + } + spin_unlock(&tm->lock); + + return r; +} + +/* + * This can silently fail if there's no memory. We're ok with this since + * creating redundant shadows causes no harm. + */ +static void insert_shadow(struct dm_transaction_manager *tm, dm_block_t b) +{ + unsigned bucket; + struct shadow_info *si; + + si = kmalloc(sizeof(*si), GFP_NOIO); + if (si) { + si->where = b; + bucket = dm_hash_block(b, HASH_MASK); + spin_lock(&tm->lock); + hlist_add_head(&si->hlist, tm->buckets + bucket); + spin_unlock(&tm->lock); + } +} + +static void wipe_shadow_table(struct dm_transaction_manager *tm) +{ + struct shadow_info *si; + struct hlist_node *n, *tmp; + struct hlist_head *bucket; + int i; + + spin_lock(&tm->lock); + for (i = 0; i < HASH_SIZE; i++) { + bucket = tm->buckets + i; + hlist_for_each_entry_safe(si, n, tmp, bucket, hlist) + kfree(si); + + INIT_HLIST_HEAD(bucket); + } + + spin_unlock(&tm->lock); +} + +/*----------------------------------------------------------------*/ + +static struct dm_transaction_manager *dm_tm_create(struct dm_block_manager *bm, + struct dm_space_map *sm) +{ + int i; + struct dm_transaction_manager *tm; + + tm = kmalloc(sizeof(*tm), GFP_KERNEL); + if (!tm) + return ERR_PTR(-ENOMEM); + + tm->is_clone = 0; + tm->real = NULL; + tm->bm = bm; + tm->sm = sm; + + spin_lock_init(&tm->lock); + for (i = 0; i < HASH_SIZE; i++) + INIT_HLIST_HEAD(tm->buckets + i); + + return tm; +} + +struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transaction_manager *real) +{ + struct dm_transaction_manager *tm; + + tm = kmalloc(sizeof(*tm), GFP_KERNEL); + if (tm) { + tm->is_clone = 1; + tm->real = real; + } + + return tm; +} +EXPORT_SYMBOL_GPL(dm_tm_create_non_blocking_clone); + +void dm_tm_destroy(struct dm_transaction_manager *tm) +{ + kfree(tm); +} +EXPORT_SYMBOL_GPL(dm_tm_destroy); + +int dm_tm_pre_commit(struct dm_transaction_manager *tm) +{ + int r; + + if (tm->is_clone) + return -EWOULDBLOCK; + + r = dm_sm_commit(tm->sm); + if (r < 0) + return r; + + return 0; +} +EXPORT_SYMBOL_GPL(dm_tm_pre_commit); + +int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root) +{ + if (tm->is_clone) + return -EWOULDBLOCK; + + wipe_shadow_table(tm); + + return dm_bm_flush_and_unlock(tm->bm, root); +} +EXPORT_SYMBOL_GPL(dm_tm_commit); + +int dm_tm_new_block(struct dm_transaction_manager *tm, + struct dm_block_validator *v, + struct dm_block **result) +{ + int r; + dm_block_t new_block; + + if (tm->is_clone) + return -EWOULDBLOCK; + + r = dm_sm_new_block(tm->sm, &new_block); + if (r < 0) + return r; + + r = dm_bm_write_lock_zero(tm->bm, new_block, v, result); + if (r < 0) { + dm_sm_dec_block(tm->sm, new_block); + return r; + } + + /* + * New blocks count as shadows in that they don't need to be + * shadowed again. + */ + insert_shadow(tm, new_block); + + return 0; +} + +static int __shadow_block(struct dm_transaction_manager *tm, dm_block_t orig, + struct dm_block_validator *v, + struct dm_block **result) +{ + int r; + dm_block_t new; + struct dm_block *orig_block; + + r = dm_sm_new_block(tm->sm, &new); + if (r < 0) + return r; + + r = dm_sm_dec_block(tm->sm, orig); + if (r < 0) + return r; + + r = dm_bm_read_lock(tm->bm, orig, v, &orig_block); + if (r < 0) + return r; + + r = dm_bm_unlock_move(orig_block, new); + if (r < 0) { + dm_bm_unlock(orig_block); + return r; + } + + return dm_bm_write_lock(tm->bm, new, v, result); +} + +int dm_tm_shadow_block(struct dm_transaction_manager *tm, dm_block_t orig, + struct dm_block_validator *v, struct dm_block **result, + int *inc_children) +{ + int r; + + if (tm->is_clone) + return -EWOULDBLOCK; + + r = dm_sm_count_is_more_than_one(tm->sm, orig, inc_children); + if (r < 0) + return r; + + if (is_shadow(tm, orig) && !*inc_children) + return dm_bm_write_lock(tm->bm, orig, v, result); + + r = __shadow_block(tm, orig, v, result); + if (r < 0) + return r; + insert_shadow(tm, dm_block_location(*result)); + + return r; +} + +int dm_tm_read_lock(struct dm_transaction_manager *tm, dm_block_t b, + struct dm_block_validator *v, + struct dm_block **blk) +{ + if (tm->is_clone) + return dm_bm_read_try_lock(tm->real->bm, b, v, blk); + + return dm_bm_read_lock(tm->bm, b, v, blk); +} + +int dm_tm_unlock(struct dm_transaction_manager *tm, struct dm_block *b) +{ + return dm_bm_unlock(b); +} +EXPORT_SYMBOL_GPL(dm_tm_unlock); + +void dm_tm_inc(struct dm_transaction_manager *tm, dm_block_t b) +{ + /* + * The non-blocking clone doesn't support this. + */ + BUG_ON(tm->is_clone); + + dm_sm_inc_block(tm->sm, b); +} +EXPORT_SYMBOL_GPL(dm_tm_inc); + +void dm_tm_dec(struct dm_transaction_manager *tm, dm_block_t b) +{ + /* + * The non-blocking clone doesn't support this. + */ + BUG_ON(tm->is_clone); + + dm_sm_dec_block(tm->sm, b); +} +EXPORT_SYMBOL_GPL(dm_tm_dec); + +int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b, + uint32_t *result) +{ + if (tm->is_clone) + return -EWOULDBLOCK; + + return dm_sm_get_count(tm->sm, b, result); +} + +struct dm_block_manager *dm_tm_get_bm(struct dm_transaction_manager *tm) +{ + return tm->bm; +} + +/*----------------------------------------------------------------*/ + +static int dm_tm_create_internal(struct dm_block_manager *bm, + dm_block_t sb_location, + struct dm_block_validator *sb_validator, + size_t root_offset, size_t root_max_len, + struct dm_transaction_manager **tm, + struct dm_space_map **sm, + struct dm_block **sblock, + int create) +{ + int r; + struct dm_space_map *inner; + + inner = dm_sm_metadata_init(); + if (IS_ERR(inner)) + return PTR_ERR(inner); + + *tm = dm_tm_create(bm, inner); + if (IS_ERR(*tm)) { + dm_sm_destroy(inner); + return PTR_ERR(*tm); + } + + if (create) { + r = dm_bm_write_lock_zero(dm_tm_get_bm(*tm), sb_location, + sb_validator, sblock); + if (r < 0) { + DMERR("couldn't lock superblock"); + goto bad1; + } + + r = dm_sm_metadata_create(inner, *tm, dm_bm_nr_blocks(bm), + sb_location); + if (r) { + DMERR("couldn't create metadata space map"); + goto bad2; + } + + *sm = dm_sm_checker_create(inner); + if (!*sm) + goto bad2; + + } else { + r = dm_bm_write_lock(dm_tm_get_bm(*tm), sb_location, + sb_validator, sblock); + if (r < 0) { + DMERR("couldn't lock superblock"); + goto bad1; + } + + r = dm_sm_metadata_open(inner, *tm, + dm_block_data(*sblock) + root_offset, + root_max_len); + if (r) { + DMERR("couldn't open metadata space map"); + goto bad2; + } + + *sm = dm_sm_checker_create(inner); + if (!*sm) + goto bad2; + } + + return 0; + +bad2: + dm_tm_unlock(*tm, *sblock); +bad1: + dm_tm_destroy(*tm); + dm_sm_destroy(inner); + return r; +} + +int dm_tm_create_with_sm(struct dm_block_manager *bm, dm_block_t sb_location, + struct dm_block_validator *sb_validator, + struct dm_transaction_manager **tm, + struct dm_space_map **sm, struct dm_block **sblock) +{ + return dm_tm_create_internal(bm, sb_location, sb_validator, + 0, 0, tm, sm, sblock, 1); +} +EXPORT_SYMBOL_GPL(dm_tm_create_with_sm); + +int dm_tm_open_with_sm(struct dm_block_manager *bm, dm_block_t sb_location, + struct dm_block_validator *sb_validator, + size_t root_offset, size_t root_max_len, + struct dm_transaction_manager **tm, + struct dm_space_map **sm, struct dm_block **sblock) +{ + return dm_tm_create_internal(bm, sb_location, sb_validator, root_offset, + root_max_len, tm, sm, sblock, 0); +} +EXPORT_SYMBOL_GPL(dm_tm_open_with_sm); + +/*----------------------------------------------------------------*/ diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h new file mode 100644 index 000000000000..6da784871db4 --- /dev/null +++ b/drivers/md/persistent-data/dm-transaction-manager.h @@ -0,0 +1,130 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef _LINUX_DM_TRANSACTION_MANAGER_H +#define _LINUX_DM_TRANSACTION_MANAGER_H + +#include "dm-block-manager.h" + +struct dm_transaction_manager; +struct dm_space_map; + +/*----------------------------------------------------------------*/ + +/* + * This manages the scope of a transaction. It also enforces immutability + * of the on-disk data structures by limiting access to writeable blocks. + * + * Clients should not fiddle with the block manager directly. + */ + +void dm_tm_destroy(struct dm_transaction_manager *tm); + +/* + * The non-blocking version of a transaction manager is intended for use in + * fast path code that needs to do lookups e.g. a dm mapping function. + * You create the non-blocking variant from a normal tm. The interface is + * the same, except that most functions will just return -EWOULDBLOCK. + * Methods that return void yet may block should not be called on a clone + * viz. dm_tm_inc, dm_tm_dec. Call dm_tm_destroy() as you would with a normal + * tm when you've finished with it. You may not destroy the original prior + * to clones. + */ +struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transaction_manager *real); + +/* + * We use a 2-phase commit here. + * + * i) In the first phase the block manager is told to start flushing, and + * the changes to the space map are written to disk. You should interrogate + * your particular space map to get detail of its root node etc. to be + * included in your superblock. + * + * ii) @root will be committed last. You shouldn't use more than the + * first 512 bytes of @root if you wish the transaction to survive a power + * failure. You *must* have a write lock held on @root for both stage (i) + * and (ii). The commit will drop the write lock. + */ +int dm_tm_pre_commit(struct dm_transaction_manager *tm); +int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root); + +/* + * These methods are the only way to get hold of a writeable block. + */ + +/* + * dm_tm_new_block() is pretty self-explanatory. Make sure you do actually + * write to the whole of @data before you unlock, otherwise you could get + * a data leak. (The other option is for tm_new_block() to zero new blocks + * before handing them out, which will be redundant in most, if not all, + * cases). + * Zeroes the new block and returns with write lock held. + */ +int dm_tm_new_block(struct dm_transaction_manager *tm, + struct dm_block_validator *v, + struct dm_block **result); + +/* + * dm_tm_shadow_block() allocates a new block and copies the data from @orig + * to it. It then decrements the reference count on original block. Use + * this to update the contents of a block in a data structure, don't + * confuse this with a clone - you shouldn't access the orig block after + * this operation. Because the tm knows the scope of the transaction it + * can optimise requests for a shadow of a shadow to a no-op. Don't forget + * to unlock when you've finished with the shadow. + * + * The @inc_children flag is used to tell the caller whether it needs to + * adjust reference counts for children. (Data in the block may refer to + * other blocks.) + * + * Shadowing implicitly drops a reference on @orig so you must not have + * it locked when you call this. + */ +int dm_tm_shadow_block(struct dm_transaction_manager *tm, dm_block_t orig, + struct dm_block_validator *v, + struct dm_block **result, int *inc_children); + +/* + * Read access. You can lock any block you want. If there's a write lock + * on it outstanding then it'll block. + */ +int dm_tm_read_lock(struct dm_transaction_manager *tm, dm_block_t b, + struct dm_block_validator *v, + struct dm_block **result); + +int dm_tm_unlock(struct dm_transaction_manager *tm, struct dm_block *b); + +/* + * Functions for altering the reference count of a block directly. + */ +void dm_tm_inc(struct dm_transaction_manager *tm, dm_block_t b); + +void dm_tm_dec(struct dm_transaction_manager *tm, dm_block_t b); + +int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b, + uint32_t *result); + +struct dm_block_manager *dm_tm_get_bm(struct dm_transaction_manager *tm); + +/* + * A little utility that ties the knot by producing a transaction manager + * that has a space map managed by the transaction manager... + * + * Returns a tm that has an open transaction to write the new disk sm. + * Caller should store the new sm root and commit. + */ +int dm_tm_create_with_sm(struct dm_block_manager *bm, dm_block_t sb_location, + struct dm_block_validator *sb_validator, + struct dm_transaction_manager **tm, + struct dm_space_map **sm, struct dm_block **sblock); + +int dm_tm_open_with_sm(struct dm_block_manager *bm, dm_block_t sb_location, + struct dm_block_validator *sb_validator, + size_t root_offset, size_t root_max_len, + struct dm_transaction_manager **tm, + struct dm_space_map **sm, struct dm_block **sblock); + +#endif /* _LINUX_DM_TRANSACTION_MANAGER_H */ From 991d9fa02da0dd1f843dc011376965e0c8c6c9b5 Mon Sep 17 00:00:00 2001 From: Joe Thornber Date: Mon, 31 Oct 2011 20:21:18 +0000 Subject: [PATCH 11/14] dm: add thin provisioning target Initial EXPERIMENTAL implementation of device-mapper thin provisioning with snapshot support. The 'thin' target is used to create instances of the virtual devices that are hosted in the 'thin-pool' target. The thin-pool target provides data sharing among devices. This sharing is made possible using the persistent-data library in the previous patch. The main highlight of this implementation, compared to the previous implementation of snapshots, is that it allows many virtual devices to be stored on the same data volume, simplifying administration and allowing sharing of data between volumes (thus reducing disk usage). Another big feature is support for arbitrary depth of recursive snapshots (snapshots of snapshots of snapshots ...). The previous implementation of snapshots did this by chaining together lookup tables, and so performance was O(depth). This new implementation uses a single data structure so we don't get this degradation with depth. For further information and examples of how to use this, please read Documentation/device-mapper/thin-provisioning.txt Signed-off-by: Joe Thornber Signed-off-by: Mike Snitzer Signed-off-by: Alasdair G Kergon --- .../device-mapper/thin-provisioning.txt | 285 ++ drivers/md/Kconfig | 28 + drivers/md/Makefile | 3 + drivers/md/dm-thin-metadata.c | 1391 ++++++++++ drivers/md/dm-thin-metadata.h | 156 ++ drivers/md/dm-thin.c | 2428 +++++++++++++++++ 6 files changed, 4291 insertions(+) create mode 100644 Documentation/device-mapper/thin-provisioning.txt create mode 100644 drivers/md/dm-thin-metadata.c create mode 100644 drivers/md/dm-thin-metadata.h create mode 100644 drivers/md/dm-thin.c diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt new file mode 100644 index 000000000000..801d9d1cf82b --- /dev/null +++ b/Documentation/device-mapper/thin-provisioning.txt @@ -0,0 +1,285 @@ +Introduction +============ + +This document descibes a collection of device-mapper targets that +between them implement thin-provisioning and snapshots. + +The main highlight of this implementation, compared to the previous +implementation of snapshots, is that it allows many virtual devices to +be stored on the same data volume. This simplifies administration and +allows the sharing of data between volumes, thus reducing disk usage. + +Another significant feature is support for an arbitrary depth of +recursive snapshots (snapshots of snapshots of snapshots ...). The +previous implementation of snapshots did this by chaining together +lookup tables, and so performance was O(depth). This new +implementation uses a single data structure to avoid this degradation +with depth. Fragmentation may still be an issue, however, in some +scenarios. + +Metadata is stored on a separate device from data, giving the +administrator some freedom, for example to: + +- Improve metadata resilience by storing metadata on a mirrored volume + but data on a non-mirrored one. + +- Improve performance by storing the metadata on SSD. + +Status +====== + +These targets are very much still in the EXPERIMENTAL state. Please +do not yet rely on them in production. But do experiment and offer us +feedback. Different use cases will have different performance +characteristics, for example due to fragmentation of the data volume. + +If you find this software is not performing as expected please mail +dm-devel@redhat.com with details and we'll try our best to improve +things for you. + +Userspace tools for checking and repairing the metadata are under +development. + +Cookbook +======== + +This section describes some quick recipes for using thin provisioning. +They use the dmsetup program to control the device-mapper driver +directly. End users will be advised to use a higher-level volume +manager such as LVM2 once support has been added. + +Pool device +----------- + +The pool device ties together the metadata volume and the data volume. +It maps I/O linearly to the data volume and updates the metadata via +two mechanisms: + +- Function calls from the thin targets + +- Device-mapper 'messages' from userspace which control the creation of new + virtual devices amongst other things. + +Setting up a fresh pool device +------------------------------ + +Setting up a pool device requires a valid metadata device, and a +data device. If you do not have an existing metadata device you can +make one by zeroing the first 4k to indicate empty metadata. + + dd if=/dev/zero of=$metadata_dev bs=4096 count=1 + +The amount of metadata you need will vary according to how many blocks +are shared between thin devices (i.e. through snapshots). If you have +less sharing than average you'll need a larger-than-average metadata device. + +As a guide, we suggest you calculate the number of bytes to use in the +metadata device as 48 * $data_dev_size / $data_block_size but round it up +to 2MB if the answer is smaller. The largest size supported is 16GB. + +If you're creating large numbers of snapshots which are recording large +amounts of change, you may need find you need to increase this. + +Reloading a pool table +---------------------- + +You may reload a pool's table, indeed this is how the pool is resized +if it runs out of space. (N.B. While specifying a different metadata +device when reloading is not forbidden at the moment, things will go +wrong if it does not route I/O to exactly the same on-disk location as +previously.) + +Using an existing pool device +----------------------------- + + dmsetup create pool \ + --table "0 20971520 thin-pool $metadata_dev $data_dev \ + $data_block_size $low_water_mark" + +$data_block_size gives the smallest unit of disk space that can be +allocated at a time expressed in units of 512-byte sectors. People +primarily interested in thin provisioning may want to use a value such +as 1024 (512KB). People doing lots of snapshotting may want a smaller value +such as 128 (64KB). If you are not zeroing newly-allocated data, +a larger $data_block_size in the region of 256000 (128MB) is suggested. +$data_block_size must be the same for the lifetime of the +metadata device. + +$low_water_mark is expressed in blocks of size $data_block_size. If +free space on the data device drops below this level then a dm event +will be triggered which a userspace daemon should catch allowing it to +extend the pool device. Only one such event will be sent. +Resuming a device with a new table itself triggers an event so the +userspace daemon can use this to detect a situation where a new table +already exceeds the threshold. + +Thin provisioning +----------------- + +i) Creating a new thinly-provisioned volume. + + To create a new thinly- provisioned volume you must send a message to an + active pool device, /dev/mapper/pool in this example. + + dmsetup message /dev/mapper/pool 0 "create_thin 0" + + Here '0' is an identifier for the volume, a 24-bit number. It's up + to the caller to allocate and manage these identifiers. If the + identifier is already in use, the message will fail with -EEXIST. + +ii) Using a thinly-provisioned volume. + + Thinly-provisioned volumes are activated using the 'thin' target: + + dmsetup create thin --table "0 2097152 thin /dev/mapper/pool 0" + + The last parameter is the identifier for the thinp device. + +Internal snapshots +------------------ + +i) Creating an internal snapshot. + + Snapshots are created with another message to the pool. + + N.B. If the origin device that you wish to snapshot is active, you + must suspend it before creating the snapshot to avoid corruption. + This is NOT enforced at the moment, so please be careful! + + dmsetup suspend /dev/mapper/thin + dmsetup message /dev/mapper/pool 0 "create_snap 1 0" + dmsetup resume /dev/mapper/thin + + Here '1' is the identifier for the volume, a 24-bit number. '0' is the + identifier for the origin device. + +ii) Using an internal snapshot. + + Once created, the user doesn't have to worry about any connection + between the origin and the snapshot. Indeed the snapshot is no + different from any other thinly-provisioned device and can be + snapshotted itself via the same method. It's perfectly legal to + have only one of them active, and there's no ordering requirement on + activating or removing them both. (This differs from conventional + device-mapper snapshots.) + + Activate it exactly the same way as any other thinly-provisioned volume: + + dmsetup create snap --table "0 2097152 thin /dev/mapper/pool 1" + +Deactivation +------------ + +All devices using a pool must be deactivated before the pool itself +can be. + + dmsetup remove thin + dmsetup remove snap + dmsetup remove pool + +Reference +========= + +'thin-pool' target +------------------ + +i) Constructor + + thin-pool \ + [ []*] + + Optional feature arguments: + - 'skip_block_zeroing': skips the zeroing of newly-provisioned blocks. + + Data block size must be between 64KB (128 sectors) and 1GB + (2097152 sectors) inclusive. + + +ii) Status + + / + / + + + transaction id: + A 64-bit number used by userspace to help synchronise with metadata + from volume managers. + + used data blocks / total data blocks + If the number of free blocks drops below the pool's low water mark a + dm event will be sent to userspace. This event is edge-triggered and + it will occur only once after each resume so volume manager writers + should register for the event and then check the target's status. + + held metadata root: + The location, in sectors, of the metadata root that has been + 'held' for userspace read access. '-' indicates there is no + held root. This feature is not yet implemented so '-' is + always returned. + +iii) Messages + + create_thin + + Create a new thinly-provisioned device. + is an arbitrary unique 24-bit identifier chosen by + the caller. + + create_snap + + Create a new snapshot of another thinly-provisioned device. + is an arbitrary unique 24-bit identifier chosen by + the caller. + is the identifier of the thinly-provisioned device + of which the new device will be a snapshot. + + delete + + Deletes a thin device. Irreversible. + + trim + + Delete mappings from the end of a thin device. Irreversible. + You might want to use this if you're reducing the size of + your thinly-provisioned device. In many cases, due to the + sharing of blocks between devices, it is not possible to + determine in advance how much space 'trim' will release. (In + future a userspace tool might be able to perform this + calculation.) + + set_transaction_id + + Userland volume managers, such as LVM, need a way to + synchronise their external metadata with the internal metadata of the + pool target. The thin-pool target offers to store an + arbitrary 64-bit transaction id and return it on the target's + status line. To avoid races you must provide what you think + the current transaction id is when you change it with this + compare-and-swap message. + +'thin' target +------------- + +i) Constructor + + thin + + pool dev: + the thin-pool device, e.g. /dev/mapper/my_pool or 253:0 + + dev id: + the internal device identifier of the device to be + activated. + +The pool doesn't store any size against the thin devices. If you +load a thin target that is smaller than you've been using previously, +then you'll have no access to blocks mapped beyond the end. If you +load a target that is bigger than before, then extra blocks will be +provisioned as and when needed. + +If you wish to reduce the size of your thin device and potentially +regain some space then send the 'trim' message to the pool. + +ii) Status + + diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index b1a921497043..faa4741df6d3 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -216,6 +216,8 @@ config DM_BUFIO as a cache, holding recently-read blocks in memory and performing delayed writes. +source "drivers/md/persistent-data/Kconfig" + config DM_CRYPT tristate "Crypt target support" depends on BLK_DEV_DM @@ -241,6 +243,32 @@ config DM_SNAPSHOT ---help--- 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 + select DM_PERSISTENT_DATA + ---help--- + Provides thin provisioning and snapshots that share a data store. + +config DM_DEBUG_BLOCK_STACK_TRACING + boolean "Keep stack trace of thin provisioning block lock holders" + depends on STACKTRACE_SUPPORT && DM_THIN_PROVISIONING + select STACKTRACE + ---help--- + Enable this for messages that may help debug problems with the + block manager locking used by thin provisioning. + + If unsure, say N. + +config DM_DEBUG_SPACE_MAPS + boolean "Extra validation for thin provisioning space maps" + depends on DM_THIN_PROVISIONING + ---help--- + Enable this for messages that may help debug problems with the + space maps used by thin provisioning. + + If unsure, say N. + config DM_MIRROR tristate "Mirror target" depends on BLK_DEV_DM diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 56661c4272f2..046860c7a166 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -10,6 +10,7 @@ dm-snapshot-y += dm-snap.o dm-exception-store.o dm-snap-transient.o \ 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 md-mod-y += md.o bitmap.o raid456-y += raid5.o @@ -35,10 +36,12 @@ obj-$(CONFIG_DM_MULTIPATH) += dm-multipath.o dm-round-robin.o obj-$(CONFIG_DM_MULTIPATH_QL) += dm-queue-length.o obj-$(CONFIG_DM_MULTIPATH_ST) += dm-service-time.o obj-$(CONFIG_DM_SNAPSHOT) += dm-snapshot.o +obj-$(CONFIG_DM_PERSISTENT_DATA) += persistent-data/ obj-$(CONFIG_DM_MIRROR) += dm-mirror.o dm-log.o dm-region-hash.o obj-$(CONFIG_DM_LOG_USERSPACE) += dm-log-userspace.o obj-$(CONFIG_DM_ZERO) += dm-zero.o obj-$(CONFIG_DM_RAID) += dm-raid.o +obj-$(CONFIG_DM_THIN_PROVISIONING) += dm-thin-pool.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c new file mode 100644 index 000000000000..59c4f0446ffa --- /dev/null +++ b/drivers/md/dm-thin-metadata.c @@ -0,0 +1,1391 @@ +/* + * Copyright (C) 2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#include "dm-thin-metadata.h" +#include "persistent-data/dm-btree.h" +#include "persistent-data/dm-space-map.h" +#include "persistent-data/dm-space-map-disk.h" +#include "persistent-data/dm-transaction-manager.h" + +#include +#include +#include + +/*-------------------------------------------------------------------------- + * As far as the metadata goes, there is: + * + * - A superblock in block zero, taking up fewer than 512 bytes for + * atomic writes. + * + * - A space map managing the metadata blocks. + * + * - A space map managing the data blocks. + * + * - A btree mapping our internal thin dev ids onto struct disk_device_details. + * + * - A hierarchical btree, with 2 levels which effectively maps (thin + * dev id, virtual block) -> block_time. Block time is a 64-bit + * field holding the time in the low 24 bits, and block in the top 48 + * bits. + * + * BTrees consist solely of btree_nodes, that fill a block. Some are + * internal nodes, as such their values are a __le64 pointing to other + * nodes. Leaf nodes can store data of any reasonable size (ie. much + * smaller than the block size). The nodes consist of the header, + * followed by an array of keys, followed by an array of values. We have + * to binary search on the keys so they're all held together to help the + * cpu cache. + * + * Space maps have 2 btrees: + * + * - One maps a uint64_t onto a struct index_entry. Which points to a + * bitmap block, and has some details about how many free entries there + * are etc. + * + * - The bitmap blocks have a header (for the checksum). Then the rest + * of the block is pairs of bits. With the meaning being: + * + * 0 - ref count is 0 + * 1 - ref count is 1 + * 2 - ref count is 2 + * 3 - ref count is higher than 2 + * + * - If the count is higher than 2 then the ref count is entered in a + * second btree that directly maps the block_address to a uint32_t ref + * count. + * + * The space map metadata variant doesn't have a bitmaps btree. Instead + * it has one single blocks worth of index_entries. This avoids + * recursive issues with the bitmap btree needing to allocate space in + * order to insert. With a small data block size such as 64k the + * metadata support data devices that are hundreds of terrabytes. + * + * The space maps allocate space linearly from front to back. Space that + * is freed in a transaction is never recycled within that transaction. + * To try and avoid fragmenting _free_ space the allocator always goes + * back and fills in gaps. + * + * All metadata io is in THIN_METADATA_BLOCK_SIZE sized/aligned chunks + * from the block manager. + *--------------------------------------------------------------------------*/ + +#define DM_MSG_PREFIX "thin metadata" + +#define THIN_SUPERBLOCK_MAGIC 27022010 +#define THIN_SUPERBLOCK_LOCATION 0 +#define THIN_VERSION 1 +#define THIN_METADATA_CACHE_SIZE 64 +#define SECTOR_TO_BLOCK_SHIFT 3 + +/* This should be plenty */ +#define SPACE_MAP_ROOT_SIZE 128 + +/* + * Little endian on-disk superblock and device details. + */ +struct thin_disk_superblock { + __le32 csum; /* Checksum of superblock except for this field. */ + __le32 flags; + __le64 blocknr; /* This block number, dm_block_t. */ + + __u8 uuid[16]; + __le64 magic; + __le32 version; + __le32 time; + + __le64 trans_id; + + /* + * Root held by userspace transactions. + */ + __le64 held_root; + + __u8 data_space_map_root[SPACE_MAP_ROOT_SIZE]; + __u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE]; + + /* + * 2-level btree mapping (dev_id, (dev block, time)) -> data block + */ + __le64 data_mapping_root; + + /* + * Device detail root mapping dev_id -> device_details + */ + __le64 device_details_root; + + __le32 data_block_size; /* In 512-byte sectors. */ + + __le32 metadata_block_size; /* In 512-byte sectors. */ + __le64 metadata_nr_blocks; + + __le32 compat_flags; + __le32 compat_ro_flags; + __le32 incompat_flags; +} __packed; + +struct disk_device_details { + __le64 mapped_blocks; + __le64 transaction_id; /* When created. */ + __le32 creation_time; + __le32 snapshotted_time; +} __packed; + +struct dm_pool_metadata { + struct hlist_node hash; + + struct block_device *bdev; + struct dm_block_manager *bm; + struct dm_space_map *metadata_sm; + struct dm_space_map *data_sm; + struct dm_transaction_manager *tm; + struct dm_transaction_manager *nb_tm; + + /* + * Two-level btree. + * First level holds thin_dev_t. + * Second level holds mappings. + */ + struct dm_btree_info info; + + /* + * Non-blocking version of the above. + */ + struct dm_btree_info nb_info; + + /* + * Just the top level for deleting whole devices. + */ + struct dm_btree_info tl_info; + + /* + * Just the bottom level for creating new devices. + */ + struct dm_btree_info bl_info; + + /* + * Describes the device details btree. + */ + struct dm_btree_info details_info; + + struct rw_semaphore root_lock; + uint32_t time; + int need_commit; + dm_block_t root; + dm_block_t details_root; + struct list_head thin_devices; + uint64_t trans_id; + unsigned long flags; + sector_t data_block_size; +}; + +struct dm_thin_device { + struct list_head list; + struct dm_pool_metadata *pmd; + dm_thin_id id; + + int open_count; + int changed; + uint64_t mapped_blocks; + uint64_t transaction_id; + uint32_t creation_time; + uint32_t snapshotted_time; +}; + +/*---------------------------------------------------------------- + * superblock validator + *--------------------------------------------------------------*/ + +#define SUPERBLOCK_CSUM_XOR 160774 + +static void sb_prepare_for_write(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct thin_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, + block_size - sizeof(__le32), + SUPERBLOCK_CSUM_XOR)); +} + +static int sb_check(struct dm_block_validator *v, + struct dm_block *b, + size_t block_size) +{ + struct thin_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) != THIN_SUPERBLOCK_MAGIC) { + DMERR("sb_check failed: magic %llu: " + "wanted %llu", le64_to_cpu(disk_super->magic), + (unsigned long long)THIN_SUPERBLOCK_MAGIC); + return -EILSEQ; + } + + csum_le = cpu_to_le32(dm_bm_checksum(&disk_super->flags, + 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 +}; + +/*---------------------------------------------------------------- + * Methods for the btree value types + *--------------------------------------------------------------*/ + +static uint64_t pack_block_time(dm_block_t b, uint32_t t) +{ + return (b << 24) | t; +} + +static void unpack_block_time(uint64_t v, dm_block_t *b, uint32_t *t) +{ + *b = v >> 24; + *t = v & ((1 << 24) - 1); +} + +static void data_block_inc(void *context, void *value_le) +{ + struct dm_space_map *sm = context; + __le64 v_le; + uint64_t b; + uint32_t t; + + memcpy(&v_le, value_le, sizeof(v_le)); + unpack_block_time(le64_to_cpu(v_le), &b, &t); + dm_sm_inc_block(sm, b); +} + +static void data_block_dec(void *context, void *value_le) +{ + struct dm_space_map *sm = context; + __le64 v_le; + uint64_t b; + uint32_t t; + + memcpy(&v_le, value_le, sizeof(v_le)); + unpack_block_time(le64_to_cpu(v_le), &b, &t); + dm_sm_dec_block(sm, b); +} + +static int data_block_equal(void *context, void *value1_le, void *value2_le) +{ + __le64 v1_le, v2_le; + uint64_t b1, b2; + uint32_t t; + + memcpy(&v1_le, value1_le, sizeof(v1_le)); + memcpy(&v2_le, value2_le, sizeof(v2_le)); + unpack_block_time(le64_to_cpu(v1_le), &b1, &t); + unpack_block_time(le64_to_cpu(v2_le), &b2, &t); + + return b1 == b2; +} + +static void subtree_inc(void *context, void *value) +{ + struct dm_btree_info *info = context; + __le64 root_le; + uint64_t root; + + memcpy(&root_le, value, sizeof(root_le)); + root = le64_to_cpu(root_le); + dm_tm_inc(info->tm, root); +} + +static void subtree_dec(void *context, void *value) +{ + struct dm_btree_info *info = context; + __le64 root_le; + uint64_t root; + + memcpy(&root_le, value, sizeof(root_le)); + root = le64_to_cpu(root_le); + if (dm_btree_del(info, root)) + DMERR("btree delete failed\n"); +} + +static int subtree_equal(void *context, void *value1_le, void *value2_le) +{ + __le64 v1_le, v2_le; + memcpy(&v1_le, value1_le, sizeof(v1_le)); + memcpy(&v2_le, value2_le, sizeof(v2_le)); + + return v1_le == v2_le; +} + +/*----------------------------------------------------------------*/ + +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 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, THIN_SUPERBLOCK_LOCATION, NULL, &b); + if (r) + return r; + + data_le = dm_block_data(b); + *result = 1; + for (i = 0; i < block_size; i++) { + if (data_le[i] != zero) { + *result = 0; + break; + } + } + + return dm_bm_unlock(b); +} + +static int init_pmd(struct dm_pool_metadata *pmd, + struct dm_block_manager *bm, + dm_block_t nr_blocks, int create) +{ + int r; + struct dm_space_map *sm, *data_sm; + struct dm_transaction_manager *tm; + struct dm_block *sblock; + + if (create) { + r = dm_tm_create_with_sm(bm, THIN_SUPERBLOCK_LOCATION, + &sb_validator, &tm, &sm, &sblock); + if (r < 0) { + DMERR("tm_create_with_sm failed"); + return r; + } + + data_sm = dm_sm_disk_create(tm, nr_blocks); + if (IS_ERR(data_sm)) { + DMERR("sm_disk_create failed"); + r = PTR_ERR(data_sm); + goto bad; + } + } else { + struct thin_disk_superblock *disk_super = NULL; + size_t space_map_root_offset = + offsetof(struct thin_disk_superblock, metadata_space_map_root); + + r = dm_tm_open_with_sm(bm, THIN_SUPERBLOCK_LOCATION, + &sb_validator, space_map_root_offset, + SPACE_MAP_ROOT_SIZE, &tm, &sm, &sblock); + if (r < 0) { + DMERR("tm_open_with_sm failed"); + return r; + } + + disk_super = dm_block_data(sblock); + data_sm = dm_sm_disk_open(tm, disk_super->data_space_map_root, + sizeof(disk_super->data_space_map_root)); + if (IS_ERR(data_sm)) { + DMERR("sm_disk_open failed"); + r = PTR_ERR(data_sm); + goto bad; + } + } + + + r = dm_tm_unlock(tm, sblock); + if (r < 0) { + DMERR("couldn't unlock superblock"); + goto bad_data_sm; + } + + pmd->bm = bm; + pmd->metadata_sm = sm; + pmd->data_sm = data_sm; + pmd->tm = tm; + pmd->nb_tm = dm_tm_create_non_blocking_clone(tm); + if (!pmd->nb_tm) { + DMERR("could not create clone tm"); + r = -ENOMEM; + goto bad_data_sm; + } + + pmd->info.tm = tm; + pmd->info.levels = 2; + pmd->info.value_type.context = pmd->data_sm; + pmd->info.value_type.size = sizeof(__le64); + pmd->info.value_type.inc = data_block_inc; + pmd->info.value_type.dec = data_block_dec; + pmd->info.value_type.equal = data_block_equal; + + memcpy(&pmd->nb_info, &pmd->info, sizeof(pmd->nb_info)); + pmd->nb_info.tm = pmd->nb_tm; + + pmd->tl_info.tm = tm; + pmd->tl_info.levels = 1; + pmd->tl_info.value_type.context = &pmd->info; + pmd->tl_info.value_type.size = sizeof(__le64); + pmd->tl_info.value_type.inc = subtree_inc; + pmd->tl_info.value_type.dec = subtree_dec; + pmd->tl_info.value_type.equal = subtree_equal; + + pmd->bl_info.tm = tm; + pmd->bl_info.levels = 1; + pmd->bl_info.value_type.context = pmd->data_sm; + pmd->bl_info.value_type.size = sizeof(__le64); + pmd->bl_info.value_type.inc = data_block_inc; + pmd->bl_info.value_type.dec = data_block_dec; + pmd->bl_info.value_type.equal = data_block_equal; + + pmd->details_info.tm = tm; + pmd->details_info.levels = 1; + pmd->details_info.value_type.context = NULL; + pmd->details_info.value_type.size = sizeof(struct disk_device_details); + pmd->details_info.value_type.inc = NULL; + pmd->details_info.value_type.dec = NULL; + pmd->details_info.value_type.equal = NULL; + + pmd->root = 0; + + init_rwsem(&pmd->root_lock); + pmd->time = 0; + pmd->need_commit = 0; + pmd->details_root = 0; + pmd->trans_id = 0; + pmd->flags = 0; + INIT_LIST_HEAD(&pmd->thin_devices); + + return 0; + +bad_data_sm: + dm_sm_destroy(data_sm); +bad: + dm_tm_destroy(tm); + dm_sm_destroy(sm); + + return r; +} + +static int __begin_transaction(struct dm_pool_metadata *pmd) +{ + int r; + u32 features; + struct thin_disk_superblock *disk_super; + struct dm_block *sblock; + + /* + * __maybe_commit_transaction() resets these + */ + WARN_ON(pmd->need_commit); + + /* + * We re-read the superblock every time. Shouldn't need to do this + * really. + */ + r = dm_bm_read_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION, + &sb_validator, &sblock); + if (r) + return r; + + disk_super = dm_block_data(sblock); + pmd->time = le32_to_cpu(disk_super->time); + pmd->root = le64_to_cpu(disk_super->data_mapping_root); + pmd->details_root = le64_to_cpu(disk_super->device_details_root); + pmd->trans_id = le64_to_cpu(disk_super->trans_id); + pmd->flags = le32_to_cpu(disk_super->flags); + pmd->data_block_size = le32_to_cpu(disk_super->data_block_size); + + features = le32_to_cpu(disk_super->incompat_flags) & ~THIN_FEATURE_INCOMPAT_SUPP; + if (features) { + DMERR("could not access metadata due to " + "unsupported optional features (%lx).", + (unsigned long)features); + r = -EINVAL; + goto out; + } + + /* + * Check for read-only metadata to skip the following RDWR checks. + */ + if (get_disk_ro(pmd->bdev->bd_disk)) + goto out; + + features = le32_to_cpu(disk_super->compat_ro_flags) & ~THIN_FEATURE_COMPAT_RO_SUPP; + if (features) { + DMERR("could not access metadata RDWR due to " + "unsupported optional features (%lx).", + (unsigned long)features); + r = -EINVAL; + } + +out: + dm_bm_unlock(sblock); + return r; +} + +static int __write_changed_details(struct dm_pool_metadata *pmd) +{ + int r; + struct dm_thin_device *td, *tmp; + struct disk_device_details details; + uint64_t key; + + list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) { + if (!td->changed) + continue; + + key = td->id; + + details.mapped_blocks = cpu_to_le64(td->mapped_blocks); + details.transaction_id = cpu_to_le64(td->transaction_id); + details.creation_time = cpu_to_le32(td->creation_time); + details.snapshotted_time = cpu_to_le32(td->snapshotted_time); + __dm_bless_for_disk(&details); + + r = dm_btree_insert(&pmd->details_info, pmd->details_root, + &key, &details, &pmd->details_root); + if (r) + return r; + + if (td->open_count) + td->changed = 0; + else { + list_del(&td->list); + kfree(td); + } + + pmd->need_commit = 1; + } + + return 0; +} + +static int __commit_transaction(struct dm_pool_metadata *pmd) +{ + /* + * FIXME: Associated pool should be made read-only on failure. + */ + int r; + size_t metadata_len, data_len; + struct thin_disk_superblock *disk_super; + struct dm_block *sblock; + + /* + * We need to know if the thin_disk_superblock exceeds a 512-byte sector. + */ + BUILD_BUG_ON(sizeof(struct thin_disk_superblock) > 512); + + r = __write_changed_details(pmd); + if (r < 0) + goto out; + + if (!pmd->need_commit) + goto out; + + r = dm_sm_commit(pmd->data_sm); + if (r < 0) + goto out; + + r = dm_tm_pre_commit(pmd->tm); + if (r < 0) + goto out; + + r = dm_sm_root_size(pmd->metadata_sm, &metadata_len); + if (r < 0) + goto out; + + r = dm_sm_root_size(pmd->metadata_sm, &data_len); + if (r < 0) + goto out; + + r = dm_bm_write_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION, + &sb_validator, &sblock); + if (r) + goto out; + + disk_super = dm_block_data(sblock); + disk_super->time = cpu_to_le32(pmd->time); + disk_super->data_mapping_root = cpu_to_le64(pmd->root); + disk_super->device_details_root = cpu_to_le64(pmd->details_root); + disk_super->trans_id = cpu_to_le64(pmd->trans_id); + disk_super->flags = cpu_to_le32(pmd->flags); + + r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root, + metadata_len); + if (r < 0) + goto out_locked; + + r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root, + data_len); + if (r < 0) + goto out_locked; + + r = dm_tm_commit(pmd->tm, sblock); + if (!r) + pmd->need_commit = 0; + +out: + return r; + +out_locked: + dm_bm_unlock(sblock); + return r; +} + +struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, + sector_t data_block_size) +{ + int r; + struct thin_disk_superblock *disk_super; + struct dm_pool_metadata *pmd; + sector_t bdev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + struct dm_block_manager *bm; + int create; + struct dm_block *sblock; + + pmd = kmalloc(sizeof(*pmd), GFP_KERNEL); + if (!pmd) { + DMERR("could not allocate metadata struct"); + return ERR_PTR(-ENOMEM); + } + + /* + * Max hex locks: + * 3 for btree insert + + * 2 for btree lookup used within space map + */ + bm = dm_block_manager_create(bdev, THIN_METADATA_BLOCK_SIZE, + THIN_METADATA_CACHE_SIZE, 5); + if (!bm) { + DMERR("could not create block manager"); + kfree(pmd); + return ERR_PTR(-ENOMEM); + } + + r = superblock_all_zeroes(bm, &create); + if (r) { + dm_block_manager_destroy(bm); + kfree(pmd); + return ERR_PTR(r); + } + + + r = init_pmd(pmd, bm, 0, create); + if (r) { + dm_block_manager_destroy(bm); + kfree(pmd); + return ERR_PTR(r); + } + pmd->bdev = bdev; + + if (!create) { + r = __begin_transaction(pmd); + if (r < 0) + goto bad; + return pmd; + } + + /* + * Create. + */ + r = dm_bm_write_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION, + &sb_validator, &sblock); + if (r) + goto bad; + + disk_super = dm_block_data(sblock); + disk_super->magic = cpu_to_le64(THIN_SUPERBLOCK_MAGIC); + disk_super->version = cpu_to_le32(THIN_VERSION); + disk_super->time = 0; + disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT); + disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT); + disk_super->data_block_size = cpu_to_le32(data_block_size); + + r = dm_bm_unlock(sblock); + if (r < 0) + goto bad; + + r = dm_btree_empty(&pmd->info, &pmd->root); + if (r < 0) + goto bad; + + r = dm_btree_empty(&pmd->details_info, &pmd->details_root); + if (r < 0) { + DMERR("couldn't create devices root"); + goto bad; + } + + pmd->flags = 0; + pmd->need_commit = 1; + r = dm_pool_commit_metadata(pmd); + if (r < 0) { + DMERR("%s: dm_pool_commit_metadata() failed, error = %d", + __func__, r); + goto bad; + } + + return pmd; + +bad: + if (dm_pool_metadata_close(pmd) < 0) + DMWARN("%s: dm_pool_metadata_close() failed.", __func__); + return ERR_PTR(r); +} + +int dm_pool_metadata_close(struct dm_pool_metadata *pmd) +{ + int r; + unsigned open_devices = 0; + struct dm_thin_device *td, *tmp; + + down_read(&pmd->root_lock); + list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) { + if (td->open_count) + open_devices++; + else { + list_del(&td->list); + kfree(td); + } + } + up_read(&pmd->root_lock); + + if (open_devices) { + DMERR("attempt to close pmd when %u device(s) are still open", + open_devices); + return -EBUSY; + } + + r = __commit_transaction(pmd); + if (r < 0) + DMWARN("%s: __commit_transaction() failed, error = %d", + __func__, r); + + dm_tm_destroy(pmd->tm); + dm_tm_destroy(pmd->nb_tm); + dm_block_manager_destroy(pmd->bm); + dm_sm_destroy(pmd->metadata_sm); + dm_sm_destroy(pmd->data_sm); + kfree(pmd); + + return 0; +} + +static int __open_device(struct dm_pool_metadata *pmd, + dm_thin_id dev, int create, + struct dm_thin_device **td) +{ + int r, changed = 0; + struct dm_thin_device *td2; + uint64_t key = dev; + struct disk_device_details details_le; + + /* + * Check the device isn't already open. + */ + list_for_each_entry(td2, &pmd->thin_devices, list) + if (td2->id == dev) { + td2->open_count++; + *td = td2; + return 0; + } + + /* + * Check the device exists. + */ + r = dm_btree_lookup(&pmd->details_info, pmd->details_root, + &key, &details_le); + if (r) { + if (r != -ENODATA || !create) + return r; + + changed = 1; + details_le.mapped_blocks = 0; + details_le.transaction_id = cpu_to_le64(pmd->trans_id); + details_le.creation_time = cpu_to_le32(pmd->time); + details_le.snapshotted_time = cpu_to_le32(pmd->time); + } + + *td = kmalloc(sizeof(**td), GFP_NOIO); + if (!*td) + return -ENOMEM; + + (*td)->pmd = pmd; + (*td)->id = dev; + (*td)->open_count = 1; + (*td)->changed = changed; + (*td)->mapped_blocks = le64_to_cpu(details_le.mapped_blocks); + (*td)->transaction_id = le64_to_cpu(details_le.transaction_id); + (*td)->creation_time = le32_to_cpu(details_le.creation_time); + (*td)->snapshotted_time = le32_to_cpu(details_le.snapshotted_time); + + list_add(&(*td)->list, &pmd->thin_devices); + + return 0; +} + +static void __close_device(struct dm_thin_device *td) +{ + --td->open_count; +} + +static int __create_thin(struct dm_pool_metadata *pmd, + dm_thin_id dev) +{ + int r; + dm_block_t dev_root; + uint64_t key = dev; + struct disk_device_details details_le; + struct dm_thin_device *td; + __le64 value; + + r = dm_btree_lookup(&pmd->details_info, pmd->details_root, + &key, &details_le); + if (!r) + return -EEXIST; + + /* + * Create an empty btree for the mappings. + */ + r = dm_btree_empty(&pmd->bl_info, &dev_root); + if (r) + return r; + + /* + * Insert it into the main mapping tree. + */ + value = cpu_to_le64(dev_root); + __dm_bless_for_disk(&value); + r = dm_btree_insert(&pmd->tl_info, pmd->root, &key, &value, &pmd->root); + if (r) { + dm_btree_del(&pmd->bl_info, dev_root); + return r; + } + + r = __open_device(pmd, dev, 1, &td); + if (r) { + __close_device(td); + dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root); + dm_btree_del(&pmd->bl_info, dev_root); + return r; + } + td->changed = 1; + __close_device(td); + + return r; +} + +int dm_pool_create_thin(struct dm_pool_metadata *pmd, dm_thin_id dev) +{ + int r; + + down_write(&pmd->root_lock); + r = __create_thin(pmd, dev); + up_write(&pmd->root_lock); + + return r; +} + +static int __set_snapshot_details(struct dm_pool_metadata *pmd, + struct dm_thin_device *snap, + dm_thin_id origin, uint32_t time) +{ + int r; + struct dm_thin_device *td; + + r = __open_device(pmd, origin, 0, &td); + if (r) + return r; + + td->changed = 1; + td->snapshotted_time = time; + + snap->mapped_blocks = td->mapped_blocks; + snap->snapshotted_time = time; + __close_device(td); + + return 0; +} + +static int __create_snap(struct dm_pool_metadata *pmd, + dm_thin_id dev, dm_thin_id origin) +{ + int r; + dm_block_t origin_root; + uint64_t key = origin, dev_key = dev; + struct dm_thin_device *td; + struct disk_device_details details_le; + __le64 value; + + /* check this device is unused */ + r = dm_btree_lookup(&pmd->details_info, pmd->details_root, + &dev_key, &details_le); + if (!r) + return -EEXIST; + + /* find the mapping tree for the origin */ + r = dm_btree_lookup(&pmd->tl_info, pmd->root, &key, &value); + if (r) + return r; + origin_root = le64_to_cpu(value); + + /* clone the origin, an inc will do */ + dm_tm_inc(pmd->tm, origin_root); + + /* insert into the main mapping tree */ + value = cpu_to_le64(origin_root); + __dm_bless_for_disk(&value); + key = dev; + r = dm_btree_insert(&pmd->tl_info, pmd->root, &key, &value, &pmd->root); + if (r) { + dm_tm_dec(pmd->tm, origin_root); + return r; + } + + pmd->time++; + + r = __open_device(pmd, dev, 1, &td); + if (r) + goto bad; + + r = __set_snapshot_details(pmd, td, origin, pmd->time); + if (r) + goto bad; + + __close_device(td); + return 0; + +bad: + __close_device(td); + dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root); + dm_btree_remove(&pmd->details_info, pmd->details_root, + &key, &pmd->details_root); + return r; +} + +int dm_pool_create_snap(struct dm_pool_metadata *pmd, + dm_thin_id dev, + dm_thin_id origin) +{ + int r; + + down_write(&pmd->root_lock); + r = __create_snap(pmd, dev, origin); + up_write(&pmd->root_lock); + + return r; +} + +static int __delete_device(struct dm_pool_metadata *pmd, dm_thin_id dev) +{ + int r; + uint64_t key = dev; + struct dm_thin_device *td; + + /* TODO: failure should mark the transaction invalid */ + r = __open_device(pmd, dev, 0, &td); + if (r) + return r; + + if (td->open_count > 1) { + __close_device(td); + return -EBUSY; + } + + list_del(&td->list); + kfree(td); + r = dm_btree_remove(&pmd->details_info, pmd->details_root, + &key, &pmd->details_root); + if (r) + return r; + + r = dm_btree_remove(&pmd->tl_info, pmd->root, &key, &pmd->root); + if (r) + return r; + + pmd->need_commit = 1; + + return 0; +} + +int dm_pool_delete_thin_device(struct dm_pool_metadata *pmd, + dm_thin_id dev) +{ + int r; + + down_write(&pmd->root_lock); + r = __delete_device(pmd, dev); + up_write(&pmd->root_lock); + + return r; +} + +int dm_pool_set_metadata_transaction_id(struct dm_pool_metadata *pmd, + uint64_t current_id, + uint64_t new_id) +{ + down_write(&pmd->root_lock); + if (pmd->trans_id != current_id) { + up_write(&pmd->root_lock); + DMERR("mismatched transaction id"); + return -EINVAL; + } + + pmd->trans_id = new_id; + pmd->need_commit = 1; + up_write(&pmd->root_lock); + + return 0; +} + +int dm_pool_get_metadata_transaction_id(struct dm_pool_metadata *pmd, + uint64_t *result) +{ + down_read(&pmd->root_lock); + *result = pmd->trans_id; + up_read(&pmd->root_lock); + + return 0; +} + +static int __get_held_metadata_root(struct dm_pool_metadata *pmd, + dm_block_t *result) +{ + int r; + struct thin_disk_superblock *disk_super; + struct dm_block *sblock; + + r = dm_bm_write_lock(pmd->bm, THIN_SUPERBLOCK_LOCATION, + &sb_validator, &sblock); + if (r) + return r; + + disk_super = dm_block_data(sblock); + *result = le64_to_cpu(disk_super->held_root); + + return dm_bm_unlock(sblock); +} + +int dm_pool_get_held_metadata_root(struct dm_pool_metadata *pmd, + dm_block_t *result) +{ + int r; + + down_read(&pmd->root_lock); + r = __get_held_metadata_root(pmd, result); + up_read(&pmd->root_lock); + + return r; +} + +int dm_pool_open_thin_device(struct dm_pool_metadata *pmd, dm_thin_id dev, + struct dm_thin_device **td) +{ + int r; + + down_write(&pmd->root_lock); + r = __open_device(pmd, dev, 0, td); + up_write(&pmd->root_lock); + + return r; +} + +int dm_pool_close_thin_device(struct dm_thin_device *td) +{ + down_write(&td->pmd->root_lock); + __close_device(td); + up_write(&td->pmd->root_lock); + + return 0; +} + +dm_thin_id dm_thin_dev_id(struct dm_thin_device *td) +{ + return td->id; +} + +static int __snapshotted_since(struct dm_thin_device *td, uint32_t time) +{ + return td->snapshotted_time > time; +} + +int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block, + int can_block, struct dm_thin_lookup_result *result) +{ + int r; + uint64_t block_time = 0; + __le64 value; + struct dm_pool_metadata *pmd = td->pmd; + dm_block_t keys[2] = { td->id, block }; + + if (can_block) { + down_read(&pmd->root_lock); + r = dm_btree_lookup(&pmd->info, pmd->root, keys, &value); + if (!r) + block_time = le64_to_cpu(value); + up_read(&pmd->root_lock); + + } else if (down_read_trylock(&pmd->root_lock)) { + r = dm_btree_lookup(&pmd->nb_info, pmd->root, keys, &value); + if (!r) + block_time = le64_to_cpu(value); + up_read(&pmd->root_lock); + + } else + return -EWOULDBLOCK; + + if (!r) { + dm_block_t exception_block; + uint32_t exception_time; + unpack_block_time(block_time, &exception_block, + &exception_time); + result->block = exception_block; + result->shared = __snapshotted_since(td, exception_time); + } + + return r; +} + +static int __insert(struct dm_thin_device *td, dm_block_t block, + dm_block_t data_block) +{ + int r, inserted; + __le64 value; + struct dm_pool_metadata *pmd = td->pmd; + dm_block_t keys[2] = { td->id, block }; + + pmd->need_commit = 1; + value = cpu_to_le64(pack_block_time(data_block, pmd->time)); + __dm_bless_for_disk(&value); + + r = dm_btree_insert_notify(&pmd->info, pmd->root, keys, &value, + &pmd->root, &inserted); + if (r) + return r; + + if (inserted) { + td->mapped_blocks++; + td->changed = 1; + } + + return 0; +} + +int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block, + dm_block_t data_block) +{ + int r; + + down_write(&td->pmd->root_lock); + r = __insert(td, block, data_block); + up_write(&td->pmd->root_lock); + + return r; +} + +static int __remove(struct dm_thin_device *td, dm_block_t block) +{ + int r; + struct dm_pool_metadata *pmd = td->pmd; + dm_block_t keys[2] = { td->id, block }; + + r = dm_btree_remove(&pmd->info, pmd->root, keys, &pmd->root); + if (r) + return r; + + pmd->need_commit = 1; + + return 0; +} + +int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block) +{ + int r; + + down_write(&td->pmd->root_lock); + r = __remove(td, block); + up_write(&td->pmd->root_lock); + + return r; +} + +int dm_pool_alloc_data_block(struct dm_pool_metadata *pmd, dm_block_t *result) +{ + int r; + + down_write(&pmd->root_lock); + + r = dm_sm_new_block(pmd->data_sm, result); + pmd->need_commit = 1; + + up_write(&pmd->root_lock); + + return r; +} + +int dm_pool_commit_metadata(struct dm_pool_metadata *pmd) +{ + int r; + + down_write(&pmd->root_lock); + + r = __commit_transaction(pmd); + if (r <= 0) + goto out; + + /* + * Open the next transaction. + */ + r = __begin_transaction(pmd); +out: + up_write(&pmd->root_lock); + return r; +} + +int dm_pool_get_free_block_count(struct dm_pool_metadata *pmd, dm_block_t *result) +{ + int r; + + down_read(&pmd->root_lock); + r = dm_sm_get_nr_free(pmd->data_sm, result); + up_read(&pmd->root_lock); + + return r; +} + +int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd, + dm_block_t *result) +{ + int r; + + down_read(&pmd->root_lock); + r = dm_sm_get_nr_free(pmd->metadata_sm, result); + up_read(&pmd->root_lock); + + return r; +} + +int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd, + dm_block_t *result) +{ + int r; + + down_read(&pmd->root_lock); + r = dm_sm_get_nr_blocks(pmd->metadata_sm, result); + up_read(&pmd->root_lock); + + return r; +} + +int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result) +{ + down_read(&pmd->root_lock); + *result = pmd->data_block_size; + up_read(&pmd->root_lock); + + return 0; +} + +int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result) +{ + int r; + + down_read(&pmd->root_lock); + r = dm_sm_get_nr_blocks(pmd->data_sm, result); + up_read(&pmd->root_lock); + + return r; +} + +int dm_thin_get_mapped_count(struct dm_thin_device *td, dm_block_t *result) +{ + struct dm_pool_metadata *pmd = td->pmd; + + down_read(&pmd->root_lock); + *result = td->mapped_blocks; + up_read(&pmd->root_lock); + + return 0; +} + +static int __highest_block(struct dm_thin_device *td, dm_block_t *result) +{ + int r; + __le64 value_le; + dm_block_t thin_root; + struct dm_pool_metadata *pmd = td->pmd; + + r = dm_btree_lookup(&pmd->tl_info, pmd->root, &td->id, &value_le); + if (r) + return r; + + thin_root = le64_to_cpu(value_le); + + return dm_btree_find_highest_key(&pmd->bl_info, thin_root, result); +} + +int dm_thin_get_highest_mapped_block(struct dm_thin_device *td, + dm_block_t *result) +{ + int r; + struct dm_pool_metadata *pmd = td->pmd; + + down_read(&pmd->root_lock); + r = __highest_block(td, result); + up_read(&pmd->root_lock); + + return r; +} + +static int __resize_data_dev(struct dm_pool_metadata *pmd, dm_block_t new_count) +{ + int r; + dm_block_t old_count; + + r = dm_sm_get_nr_blocks(pmd->data_sm, &old_count); + if (r) + return r; + + if (new_count == old_count) + return 0; + + if (new_count < old_count) { + DMERR("cannot reduce size of data device"); + return -EINVAL; + } + + r = dm_sm_extend(pmd->data_sm, new_count - old_count); + if (!r) + pmd->need_commit = 1; + + return r; +} + +int dm_pool_resize_data_dev(struct dm_pool_metadata *pmd, dm_block_t new_count) +{ + int r; + + down_write(&pmd->root_lock); + r = __resize_data_dev(pmd, new_count); + up_write(&pmd->root_lock); + + return r; +} diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h new file mode 100644 index 000000000000..859c16896877 --- /dev/null +++ b/drivers/md/dm-thin-metadata.h @@ -0,0 +1,156 @@ +/* + * Copyright (C) 2010-2011 Red Hat, Inc. + * + * This file is released under the GPL. + */ + +#ifndef DM_THIN_METADATA_H +#define DM_THIN_METADATA_H + +#include "persistent-data/dm-block-manager.h" + +#define THIN_METADATA_BLOCK_SIZE 4096 + +/*----------------------------------------------------------------*/ + +struct dm_pool_metadata; +struct dm_thin_device; + +/* + * Device identifier + */ +typedef uint64_t dm_thin_id; + +/* + * Reopens or creates a new, empty metadata volume. + */ +struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, + sector_t data_block_size); + +int dm_pool_metadata_close(struct dm_pool_metadata *pmd); + +/* + * Compat feature flags. Any incompat flags beyond the ones + * specified below will prevent use of the thin metadata. + */ +#define THIN_FEATURE_COMPAT_SUPP 0UL +#define THIN_FEATURE_COMPAT_RO_SUPP 0UL +#define THIN_FEATURE_INCOMPAT_SUPP 0UL + +/* + * Device creation/deletion. + */ +int dm_pool_create_thin(struct dm_pool_metadata *pmd, dm_thin_id dev); + +/* + * An internal snapshot. + * + * You can only snapshot a quiesced origin i.e. one that is either + * suspended or not instanced at all. + */ +int dm_pool_create_snap(struct dm_pool_metadata *pmd, dm_thin_id dev, + dm_thin_id origin); + +/* + * Deletes a virtual device from the metadata. It _is_ safe to call this + * when that device is open. Operations on that device will just start + * failing. You still need to call close() on the device. + */ +int dm_pool_delete_thin_device(struct dm_pool_metadata *pmd, + dm_thin_id dev); + +/* + * Commits _all_ metadata changes: device creation, deletion, mapping + * updates. + */ +int dm_pool_commit_metadata(struct dm_pool_metadata *pmd); + +/* + * Set/get userspace transaction id. + */ +int dm_pool_set_metadata_transaction_id(struct dm_pool_metadata *pmd, + uint64_t current_id, + uint64_t new_id); + +int dm_pool_get_metadata_transaction_id(struct dm_pool_metadata *pmd, + uint64_t *result); + +/* + * Hold/get root for userspace transaction. + */ +int dm_pool_hold_metadata_root(struct dm_pool_metadata *pmd); + +int dm_pool_get_held_metadata_root(struct dm_pool_metadata *pmd, + dm_block_t *result); + +/* + * Actions on a single virtual device. + */ + +/* + * Opening the same device more than once will fail with -EBUSY. + */ +int dm_pool_open_thin_device(struct dm_pool_metadata *pmd, dm_thin_id dev, + struct dm_thin_device **td); + +int dm_pool_close_thin_device(struct dm_thin_device *td); + +dm_thin_id dm_thin_dev_id(struct dm_thin_device *td); + +struct dm_thin_lookup_result { + dm_block_t block; + int shared; +}; + +/* + * Returns: + * -EWOULDBLOCK iff @can_block is set and would block. + * -ENODATA iff that mapping is not present. + * 0 success + */ +int dm_thin_find_block(struct dm_thin_device *td, dm_block_t block, + int can_block, struct dm_thin_lookup_result *result); + +/* + * Obtain an unused block. + */ +int dm_pool_alloc_data_block(struct dm_pool_metadata *pmd, dm_block_t *result); + +/* + * Insert or remove block. + */ +int dm_thin_insert_block(struct dm_thin_device *td, dm_block_t block, + dm_block_t data_block); + +int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block); + +/* + * Queries. + */ +int dm_thin_get_highest_mapped_block(struct dm_thin_device *td, + dm_block_t *highest_mapped); + +int dm_thin_get_mapped_count(struct dm_thin_device *td, dm_block_t *result); + +int dm_pool_get_free_block_count(struct dm_pool_metadata *pmd, + dm_block_t *result); + +int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd, + dm_block_t *result); + +int dm_pool_get_metadata_dev_size(struct dm_pool_metadata *pmd, + dm_block_t *result); + +int dm_pool_get_data_block_size(struct dm_pool_metadata *pmd, sector_t *result); + +int dm_pool_get_data_dev_size(struct dm_pool_metadata *pmd, dm_block_t *result); + +/* + * Returns -ENOSPC if the new size is too small and already allocated + * blocks would be lost. + */ +int dm_pool_resize_data_dev(struct dm_pool_metadata *pmd, dm_block_t new_size); + +/*----------------------------------------------------------------*/ + +#endif diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c new file mode 100644 index 000000000000..c3087575fef0 --- /dev/null +++ b/drivers/md/dm-thin.c @@ -0,0 +1,2428 @@ +/* + * Copyright (C) 2011 Red Hat UK. + * + * This file is released under the GPL. + */ + +#include "dm-thin-metadata.h" + +#include +#include +#include +#include +#include +#include +#include + +#define DM_MSG_PREFIX "thin" + +/* + * Tunable constants + */ +#define ENDIO_HOOK_POOL_SIZE 10240 +#define DEFERRED_SET_SIZE 64 +#define MAPPING_POOL_SIZE 1024 +#define PRISON_CELLS 1024 + +/* + * The block size of the device holding pool data must be + * between 64KB and 1GB. + */ +#define DATA_DEV_BLOCK_SIZE_MIN_SECTORS (64 * 1024 >> SECTOR_SHIFT) +#define DATA_DEV_BLOCK_SIZE_MAX_SECTORS (1024 * 1024 * 1024 >> SECTOR_SHIFT) + +/* + * The metadata device is currently limited in size. The limitation is + * checked lower down in dm-space-map-metadata, but we also check it here + * so we can fail early. + * + * We have one block of index, which can hold 255 index entries. Each + * index entry contains allocation info about 16k metadata blocks. + */ +#define METADATA_DEV_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT))) + +/* + * Device id is restricted to 24 bits. + */ +#define MAX_DEV_ID ((1 << 24) - 1) + +/* + * How do we handle breaking sharing of data blocks? + * ================================================= + * + * We use a standard copy-on-write btree to store the mappings for the + * devices (note I'm talking about copy-on-write of the metadata here, not + * the data). When you take an internal snapshot you clone the root node + * of the origin btree. After this there is no concept of an origin or a + * snapshot. They are just two device trees that happen to point to the + * same data blocks. + * + * When we get a write in we decide if it's to a shared data block using + * some timestamp magic. If it is, we have to break sharing. + * + * Let's say we write to a shared block in what was the origin. The + * steps are: + * + * i) plug io further to this physical block. (see bio_prison code). + * + * ii) quiesce any read io to that shared data block. Obviously + * including all devices that share this block. (see deferred_set code) + * + * iii) copy the data block to a newly allocate block. This step can be + * missed out if the io covers the block. (schedule_copy). + * + * iv) insert the new mapping into the origin's btree + * (process_prepared_mappings). This act of inserting breaks some + * sharing of btree nodes between the two devices. Breaking sharing only + * effects the btree of that specific device. Btrees for the other + * devices that share the block never change. The btree for the origin + * device as it was after the last commit is untouched, ie. we're using + * persistent data structures in the functional programming sense. + * + * v) unplug io to this physical block, including the io that triggered + * the breaking of sharing. + * + * Steps (ii) and (iii) occur in parallel. + * + * The metadata _doesn't_ need to be committed before the io continues. We + * get away with this because the io is always written to a _new_ block. + * If there's a crash, then: + * + * - The origin mapping will point to the old origin block (the shared + * one). This will contain the data as it was before the io that triggered + * the breaking of sharing came in. + * + * - The snap mapping still points to the old block. As it would after + * the commit. + * + * The downside of this scheme is the timestamp magic isn't perfect, and + * will continue to think that data block in the snapshot device is shared + * even after the write to the origin has broken sharing. I suspect data + * blocks will typically be shared by many different devices, so we're + * breaking sharing n + 1 times, rather than n, where n is the number of + * devices that reference this data block. At the moment I think the + * benefits far, far outweigh the disadvantages. + */ + +/*----------------------------------------------------------------*/ + +/* + * Sometimes we can't deal with a bio straight away. We put them in prison + * where they can't cause any mischief. Bios are put in a cell identified + * by a key, multiple bios can be in the same cell. When the cell is + * subsequently unlocked the bios become available. + */ +struct bio_prison; + +struct cell_key { + int virtual; + dm_thin_id dev; + dm_block_t block; +}; + +struct cell { + struct hlist_node list; + struct bio_prison *prison; + struct cell_key key; + unsigned count; + struct bio_list bios; +}; + +struct bio_prison { + spinlock_t lock; + mempool_t *cell_pool; + + unsigned nr_buckets; + unsigned hash_mask; + struct hlist_head *cells; +}; + +static uint32_t calc_nr_buckets(unsigned nr_cells) +{ + uint32_t n = 128; + + nr_cells /= 4; + nr_cells = min(nr_cells, 8192u); + + while (n < nr_cells) + n <<= 1; + + return n; +} + +/* + * @nr_cells should be the number of cells you want in use _concurrently_. + * Don't confuse it with the number of distinct keys. + */ +static struct bio_prison *prison_create(unsigned nr_cells) +{ + unsigned i; + uint32_t nr_buckets = calc_nr_buckets(nr_cells); + size_t len = sizeof(struct bio_prison) + + (sizeof(struct hlist_head) * nr_buckets); + struct bio_prison *prison = kmalloc(len, GFP_KERNEL); + + if (!prison) + return NULL; + + spin_lock_init(&prison->lock); + prison->cell_pool = mempool_create_kmalloc_pool(nr_cells, + sizeof(struct cell)); + if (!prison->cell_pool) { + kfree(prison); + return NULL; + } + + prison->nr_buckets = nr_buckets; + prison->hash_mask = nr_buckets - 1; + prison->cells = (struct hlist_head *) (prison + 1); + for (i = 0; i < nr_buckets; i++) + INIT_HLIST_HEAD(prison->cells + i); + + return prison; +} + +static void prison_destroy(struct bio_prison *prison) +{ + mempool_destroy(prison->cell_pool); + kfree(prison); +} + +static uint32_t hash_key(struct bio_prison *prison, struct cell_key *key) +{ + const unsigned long BIG_PRIME = 4294967291UL; + uint64_t hash = key->block * BIG_PRIME; + + return (uint32_t) (hash & prison->hash_mask); +} + +static int keys_equal(struct cell_key *lhs, struct cell_key *rhs) +{ + return (lhs->virtual == rhs->virtual) && + (lhs->dev == rhs->dev) && + (lhs->block == rhs->block); +} + +static struct cell *__search_bucket(struct hlist_head *bucket, + struct cell_key *key) +{ + struct cell *cell; + struct hlist_node *tmp; + + hlist_for_each_entry(cell, tmp, bucket, list) + if (keys_equal(&cell->key, key)) + return cell; + + 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 the number of entries in the cell prior to the new addition + * or < 0 on failure. + */ +static int bio_detain(struct bio_prison *prison, struct cell_key *key, + struct bio *inmate, struct cell **ref) +{ + int r; + unsigned long flags; + uint32_t hash = hash_key(prison, key); + struct cell *uninitialized_var(cell), *cell2 = NULL; + + BUG_ON(hash > prison->nr_buckets); + + spin_lock_irqsave(&prison->lock, flags); + cell = __search_bucket(prison->cells + hash, key); + + if (!cell) { + /* + * Allocate a new cell + */ + spin_unlock_irqrestore(&prison->lock, flags); + cell2 = mempool_alloc(prison->cell_pool, GFP_NOIO); + spin_lock_irqsave(&prison->lock, flags); + + /* + * 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) { + cell = cell2; + cell2 = NULL; + + cell->prison = prison; + memcpy(&cell->key, key, sizeof(cell->key)); + cell->count = 0; + bio_list_init(&cell->bios); + hlist_add_head(&cell->list, prison->cells + hash); + } + } + + r = cell->count++; + bio_list_add(&cell->bios, inmate); + spin_unlock_irqrestore(&prison->lock, flags); + + if (cell2) + mempool_free(cell2, prison->cell_pool); + + *ref = cell; + + return r; +} + +/* + * @inmates must have been initialised prior to this call + */ +static void __cell_release(struct cell *cell, struct bio_list *inmates) +{ + struct bio_prison *prison = cell->prison; + + hlist_del(&cell->list); + + if (inmates) + bio_list_merge(inmates, &cell->bios); + + mempool_free(cell, prison->cell_pool); +} + +static void cell_release(struct cell *cell, struct bio_list *bios) +{ + unsigned long flags; + struct bio_prison *prison = cell->prison; + + spin_lock_irqsave(&prison->lock, flags); + __cell_release(cell, bios); + spin_unlock_irqrestore(&prison->lock, flags); +} + +/* + * There are a couple of places where we put a bio into a cell briefly + * before taking it out again. In these situations we know that no other + * bio may be in the cell. This function releases the cell, and also does + * a sanity check. + */ +static void cell_release_singleton(struct cell *cell, struct bio *bio) +{ + struct bio_prison *prison = cell->prison; + struct bio_list bios; + struct bio *b; + unsigned long flags; + + bio_list_init(&bios); + + spin_lock_irqsave(&prison->lock, flags); + __cell_release(cell, &bios); + spin_unlock_irqrestore(&prison->lock, flags); + + b = bio_list_pop(&bios); + BUG_ON(b != bio); + BUG_ON(!bio_list_empty(&bios)); +} + +static void cell_error(struct cell *cell) +{ + struct bio_prison *prison = cell->prison; + struct bio_list bios; + struct bio *bio; + unsigned long flags; + + bio_list_init(&bios); + + spin_lock_irqsave(&prison->lock, flags); + __cell_release(cell, &bios); + spin_unlock_irqrestore(&prison->lock, flags); + + while ((bio = bio_list_pop(&bios))) + bio_io_error(bio); +} + +/*----------------------------------------------------------------*/ + +/* + * We use the deferred set to keep track of pending reads to shared blocks. + * We do this to ensure the new mapping caused by a write isn't performed + * until these prior reads have completed. Otherwise the insertion of the + * new mapping could free the old block that the read bios are mapped to. + */ + +struct deferred_set; +struct deferred_entry { + struct deferred_set *ds; + unsigned count; + struct list_head work_items; +}; + +struct deferred_set { + spinlock_t lock; + unsigned current_entry; + unsigned sweeper; + struct deferred_entry entries[DEFERRED_SET_SIZE]; +}; + +static void ds_init(struct deferred_set *ds) +{ + int i; + + spin_lock_init(&ds->lock); + ds->current_entry = 0; + ds->sweeper = 0; + for (i = 0; i < DEFERRED_SET_SIZE; i++) { + ds->entries[i].ds = ds; + ds->entries[i].count = 0; + INIT_LIST_HEAD(&ds->entries[i].work_items); + } +} + +static struct deferred_entry *ds_inc(struct deferred_set *ds) +{ + unsigned long flags; + struct deferred_entry *entry; + + spin_lock_irqsave(&ds->lock, flags); + entry = ds->entries + ds->current_entry; + entry->count++; + spin_unlock_irqrestore(&ds->lock, flags); + + return entry; +} + +static unsigned ds_next(unsigned index) +{ + return (index + 1) % DEFERRED_SET_SIZE; +} + +static void __sweep(struct deferred_set *ds, struct list_head *head) +{ + while ((ds->sweeper != ds->current_entry) && + !ds->entries[ds->sweeper].count) { + list_splice_init(&ds->entries[ds->sweeper].work_items, head); + ds->sweeper = ds_next(ds->sweeper); + } + + if ((ds->sweeper == ds->current_entry) && !ds->entries[ds->sweeper].count) + list_splice_init(&ds->entries[ds->sweeper].work_items, head); +} + +static void ds_dec(struct deferred_entry *entry, struct list_head *head) +{ + unsigned long flags; + + spin_lock_irqsave(&entry->ds->lock, flags); + BUG_ON(!entry->count); + --entry->count; + __sweep(entry->ds, head); + spin_unlock_irqrestore(&entry->ds->lock, flags); +} + +/* + * Returns 1 if deferred or 0 if no pending items to delay job. + */ +static int ds_add_work(struct deferred_set *ds, struct list_head *work) +{ + int r = 1; + unsigned long flags; + unsigned next_entry; + + spin_lock_irqsave(&ds->lock, flags); + if ((ds->sweeper == ds->current_entry) && + !ds->entries[ds->current_entry].count) + r = 0; + else { + list_add(work, &ds->entries[ds->current_entry].work_items); + next_entry = ds_next(ds->current_entry); + if (!ds->entries[next_entry].count) + ds->current_entry = next_entry; + } + spin_unlock_irqrestore(&ds->lock, flags); + + return r; +} + +/*----------------------------------------------------------------*/ + +/* + * Key building. + */ +static void build_data_key(struct dm_thin_device *td, + dm_block_t b, struct cell_key *key) +{ + key->virtual = 0; + key->dev = dm_thin_dev_id(td); + key->block = b; +} + +static void build_virtual_key(struct dm_thin_device *td, dm_block_t b, + struct cell_key *key) +{ + key->virtual = 1; + key->dev = dm_thin_dev_id(td); + key->block = b; +} + +/*----------------------------------------------------------------*/ + +/* + * A pool device ties together a metadata device and a data device. It + * also provides the interface for creating and destroying internal + * devices. + */ +struct new_mapping; +struct pool { + struct list_head list; + struct dm_target *ti; /* Only set if a pool target is bound */ + + struct mapped_device *pool_md; + struct block_device *md_dev; + struct dm_pool_metadata *pmd; + + uint32_t sectors_per_block; + unsigned block_shift; + dm_block_t offset_mask; + dm_block_t low_water_blocks; + + unsigned zero_new_blocks:1; + unsigned low_water_triggered:1; /* A dm event has been sent */ + unsigned no_free_space:1; /* A -ENOSPC warning has been issued */ + + struct bio_prison *prison; + struct dm_kcopyd_client *copier; + + struct workqueue_struct *wq; + struct work_struct worker; + + unsigned ref_count; + + spinlock_t lock; + struct bio_list deferred_bios; + struct bio_list deferred_flush_bios; + struct list_head prepared_mappings; + + struct bio_list retry_on_resume_list; + + struct deferred_set ds; /* FIXME: move to thin_c */ + + struct new_mapping *next_mapping; + mempool_t *mapping_pool; + mempool_t *endio_hook_pool; +}; + +/* + * Target context for a pool. + */ +struct pool_c { + struct dm_target *ti; + struct pool *pool; + struct dm_dev *data_dev; + struct dm_dev *metadata_dev; + struct dm_target_callbacks callbacks; + + dm_block_t low_water_blocks; + unsigned zero_new_blocks:1; +}; + +/* + * Target context for a thin. + */ +struct thin_c { + struct dm_dev *pool_dev; + dm_thin_id dev_id; + + struct pool *pool; + struct dm_thin_device *td; +}; + +/*----------------------------------------------------------------*/ + +/* + * A global list of pools that uses a struct mapped_device as a key. + */ +static struct dm_thin_pool_table { + struct mutex mutex; + struct list_head pools; +} dm_thin_pool_table; + +static void pool_table_init(void) +{ + mutex_init(&dm_thin_pool_table.mutex); + INIT_LIST_HEAD(&dm_thin_pool_table.pools); +} + +static void __pool_table_insert(struct pool *pool) +{ + BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex)); + list_add(&pool->list, &dm_thin_pool_table.pools); +} + +static void __pool_table_remove(struct pool *pool) +{ + BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex)); + list_del(&pool->list); +} + +static struct pool *__pool_table_lookup(struct mapped_device *md) +{ + struct pool *pool = NULL, *tmp; + + BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex)); + + list_for_each_entry(tmp, &dm_thin_pool_table.pools, list) { + if (tmp->pool_md == md) { + pool = tmp; + break; + } + } + + return pool; +} + +static struct pool *__pool_table_lookup_metadata_dev(struct block_device *md_dev) +{ + struct pool *pool = NULL, *tmp; + + BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex)); + + list_for_each_entry(tmp, &dm_thin_pool_table.pools, list) { + if (tmp->md_dev == md_dev) { + pool = tmp; + break; + } + } + + return pool; +} + +/*----------------------------------------------------------------*/ + +static void __requeue_bio_list(struct thin_c *tc, struct bio_list *master) +{ + struct bio *bio; + struct bio_list bios; + + bio_list_init(&bios); + bio_list_merge(&bios, master); + bio_list_init(master); + + while ((bio = bio_list_pop(&bios))) { + if (dm_get_mapinfo(bio)->ptr == tc) + bio_endio(bio, DM_ENDIO_REQUEUE); + else + bio_list_add(master, bio); + } +} + +static void requeue_io(struct thin_c *tc) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + spin_lock_irqsave(&pool->lock, flags); + __requeue_bio_list(tc, &pool->deferred_bios); + __requeue_bio_list(tc, &pool->retry_on_resume_list); + spin_unlock_irqrestore(&pool->lock, flags); +} + +/* + * This section of code contains the logic for processing a thin device's IO. + * Much of the code depends on pool object resources (lists, workqueues, etc) + * but most is exclusively called from the thin target rather than the thin-pool + * target. + */ + +static dm_block_t get_bio_block(struct thin_c *tc, struct bio *bio) +{ + return bio->bi_sector >> tc->pool->block_shift; +} + +static void remap(struct thin_c *tc, struct bio *bio, dm_block_t block) +{ + struct pool *pool = tc->pool; + + bio->bi_bdev = tc->pool_dev->bdev; + bio->bi_sector = (block << pool->block_shift) + + (bio->bi_sector & pool->offset_mask); +} + +static void remap_and_issue(struct thin_c *tc, struct bio *bio, + dm_block_t block) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + remap(tc, bio, block); + + /* + * Batch together any FUA/FLUSH bios we find and then issue + * a single commit for them in process_deferred_bios(). + */ + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) { + spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->deferred_flush_bios, bio); + spin_unlock_irqrestore(&pool->lock, flags); + } else + generic_make_request(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); +} + +/*----------------------------------------------------------------*/ + +/* + * Bio endio functions. + */ +struct endio_hook { + struct thin_c *tc; + bio_end_io_t *saved_bi_end_io; + struct deferred_entry *entry; +}; + +struct new_mapping { + struct list_head list; + + int prepared; + + struct thin_c *tc; + dm_block_t virt_block; + dm_block_t data_block; + struct cell *cell; + int err; + + /* + * If the bio covers the whole area of a block then we can avoid + * zeroing or copying. Instead this bio is hooked. The bio will + * still be in the cell, so care has to be taken to avoid issuing + * the bio twice. + */ + struct bio *bio; + bio_end_io_t *saved_bi_end_io; +}; + +static void __maybe_add_mapping(struct new_mapping *m) +{ + struct pool *pool = m->tc->pool; + + if (list_empty(&m->list) && m->prepared) { + list_add(&m->list, &pool->prepared_mappings); + wake_worker(pool); + } +} + +static void copy_complete(int read_err, unsigned long write_err, void *context) +{ + unsigned long flags; + struct new_mapping *m = context; + struct pool *pool = m->tc->pool; + + m->err = read_err || write_err ? -EIO : 0; + + spin_lock_irqsave(&pool->lock, flags); + m->prepared = 1; + __maybe_add_mapping(m); + spin_unlock_irqrestore(&pool->lock, flags); +} + +static void overwrite_endio(struct bio *bio, int err) +{ + unsigned long flags; + struct new_mapping *m = dm_get_mapinfo(bio)->ptr; + struct pool *pool = m->tc->pool; + + m->err = err; + + spin_lock_irqsave(&pool->lock, flags); + m->prepared = 1; + __maybe_add_mapping(m); + spin_unlock_irqrestore(&pool->lock, flags); +} + +static void shared_read_endio(struct bio *bio, int err) +{ + struct list_head mappings; + struct new_mapping *m, *tmp; + struct endio_hook *h = dm_get_mapinfo(bio)->ptr; + unsigned long flags; + struct pool *pool = h->tc->pool; + + bio->bi_end_io = h->saved_bi_end_io; + bio_endio(bio, err); + + INIT_LIST_HEAD(&mappings); + ds_dec(h->entry, &mappings); + + spin_lock_irqsave(&pool->lock, flags); + list_for_each_entry_safe(m, tmp, &mappings, list) { + list_del(&m->list); + INIT_LIST_HEAD(&m->list); + __maybe_add_mapping(m); + } + spin_unlock_irqrestore(&pool->lock, flags); + + mempool_free(h, pool->endio_hook_pool); +} + +/*----------------------------------------------------------------*/ + +/* + * Workqueue. + */ + +/* + * Prepared mapping jobs. + */ + +/* + * This sends the bios in the cell back to the deferred_bios list. + */ +static void cell_defer(struct thin_c *tc, struct cell *cell, + dm_block_t data_block) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + spin_lock_irqsave(&pool->lock, flags); + cell_release(cell, &pool->deferred_bios); + spin_unlock_irqrestore(&tc->pool->lock, flags); + + wake_worker(pool); +} + +/* + * Same as cell_defer above, except it omits one particular detainee, + * a write bio that covers the block and has already been processed. + */ +static void cell_defer_except(struct thin_c *tc, struct cell *cell, + struct bio *exception) +{ + struct bio_list bios; + struct bio *bio; + struct pool *pool = tc->pool; + unsigned long flags; + + bio_list_init(&bios); + cell_release(cell, &bios); + + spin_lock_irqsave(&pool->lock, flags); + while ((bio = bio_list_pop(&bios))) + if (bio != exception) + bio_list_add(&pool->deferred_bios, bio); + spin_unlock_irqrestore(&pool->lock, flags); + + wake_worker(pool); +} + +static void process_prepared_mapping(struct new_mapping *m) +{ + struct thin_c *tc = m->tc; + struct bio *bio; + int r; + + bio = m->bio; + if (bio) + bio->bi_end_io = m->saved_bi_end_io; + + if (m->err) { + cell_error(m->cell); + return; + } + + /* + * Commit the prepared block into the mapping btree. + * Any I/O for this block arriving after this point will get + * remapped to it directly. + */ + r = dm_thin_insert_block(tc->td, m->virt_block, m->data_block); + if (r) { + DMERR("dm_thin_insert_block() failed"); + cell_error(m->cell); + return; + } + + /* + * Release any bios held while the block was being provisioned. + * If we are processing a write bio that completely covers the block, + * we already processed it so can ignore it now when processing + * the bios in the cell. + */ + if (bio) { + cell_defer_except(tc, m->cell, bio); + bio_endio(bio, 0); + } else + cell_defer(tc, m->cell, m->data_block); + + list_del(&m->list); + mempool_free(m, tc->pool->mapping_pool); +} + +static void process_prepared_mappings(struct pool *pool) +{ + unsigned long flags; + struct list_head maps; + struct new_mapping *m, *tmp; + + INIT_LIST_HEAD(&maps); + spin_lock_irqsave(&pool->lock, flags); + list_splice_init(&pool->prepared_mappings, &maps); + spin_unlock_irqrestore(&pool->lock, flags); + + list_for_each_entry_safe(m, tmp, &maps, list) + process_prepared_mapping(m); +} + +/* + * Deferred bio jobs. + */ +static int io_overwrites_block(struct pool *pool, struct bio *bio) +{ + return ((bio_data_dir(bio) == WRITE) && + !(bio->bi_sector & pool->offset_mask)) && + (bio->bi_size == (pool->sectors_per_block << SECTOR_SHIFT)); +} + +static void save_and_set_endio(struct bio *bio, bio_end_io_t **save, + bio_end_io_t *fn) +{ + *save = bio->bi_end_io; + bio->bi_end_io = fn; +} + +static int ensure_next_mapping(struct pool *pool) +{ + if (pool->next_mapping) + return 0; + + pool->next_mapping = mempool_alloc(pool->mapping_pool, GFP_ATOMIC); + + return pool->next_mapping ? 0 : -ENOMEM; +} + +static struct new_mapping *get_next_mapping(struct pool *pool) +{ + struct new_mapping *r = pool->next_mapping; + + BUG_ON(!pool->next_mapping); + + pool->next_mapping = NULL; + + return r; +} + +static void schedule_copy(struct thin_c *tc, dm_block_t virt_block, + dm_block_t data_origin, dm_block_t data_dest, + struct cell *cell, struct bio *bio) +{ + int r; + struct pool *pool = tc->pool; + struct new_mapping *m = get_next_mapping(pool); + + INIT_LIST_HEAD(&m->list); + m->prepared = 0; + m->tc = tc; + m->virt_block = virt_block; + m->data_block = data_dest; + m->cell = cell; + m->err = 0; + m->bio = NULL; + + ds_add_work(&pool->ds, &m->list); + + /* + * IO to pool_dev remaps to the pool target's data_dev. + * + * If the whole block of data is being overwritten, we can issue the + * bio immediately. Otherwise we use kcopyd to clone the data first. + */ + if (io_overwrites_block(pool, bio)) { + m->bio = bio; + save_and_set_endio(bio, &m->saved_bi_end_io, overwrite_endio); + dm_get_mapinfo(bio)->ptr = m; + remap_and_issue(tc, bio, data_dest); + } else { + struct dm_io_region from, to; + + from.bdev = tc->pool_dev->bdev; + from.sector = data_origin * pool->sectors_per_block; + from.count = pool->sectors_per_block; + + to.bdev = tc->pool_dev->bdev; + to.sector = data_dest * pool->sectors_per_block; + to.count = pool->sectors_per_block; + + r = dm_kcopyd_copy(pool->copier, &from, 1, &to, + 0, copy_complete, m); + if (r < 0) { + mempool_free(m, pool->mapping_pool); + DMERR("dm_kcopyd_copy() failed"); + cell_error(cell); + } + } +} + +static void schedule_zero(struct thin_c *tc, dm_block_t virt_block, + dm_block_t data_block, struct cell *cell, + struct bio *bio) +{ + struct pool *pool = tc->pool; + struct new_mapping *m = get_next_mapping(pool); + + INIT_LIST_HEAD(&m->list); + m->prepared = 0; + m->tc = tc; + m->virt_block = virt_block; + m->data_block = data_block; + m->cell = cell; + m->err = 0; + m->bio = NULL; + + /* + * If the whole block of data is being overwritten or we are not + * zeroing pre-existing data, we can issue the bio immediately. + * Otherwise we use kcopyd to zero the data first. + */ + if (!pool->zero_new_blocks) + process_prepared_mapping(m); + + else if (io_overwrites_block(pool, bio)) { + m->bio = bio; + save_and_set_endio(bio, &m->saved_bi_end_io, overwrite_endio); + dm_get_mapinfo(bio)->ptr = m; + remap_and_issue(tc, bio, data_block); + + } else { + int r; + struct dm_io_region to; + + to.bdev = tc->pool_dev->bdev; + to.sector = data_block * pool->sectors_per_block; + to.count = pool->sectors_per_block; + + r = dm_kcopyd_zero(pool->copier, 1, &to, 0, copy_complete, m); + if (r < 0) { + mempool_free(m, pool->mapping_pool); + DMERR("dm_kcopyd_zero() failed"); + cell_error(cell); + } + } +} + +static int alloc_data_block(struct thin_c *tc, dm_block_t *result) +{ + int r; + dm_block_t free_blocks; + unsigned long flags; + struct pool *pool = tc->pool; + + r = dm_pool_get_free_block_count(pool->pmd, &free_blocks); + if (r) + return r; + + if (free_blocks <= pool->low_water_blocks && !pool->low_water_triggered) { + DMWARN("%s: reached low water mark, sending event.", + dm_device_name(pool->pool_md)); + spin_lock_irqsave(&pool->lock, flags); + pool->low_water_triggered = 1; + spin_unlock_irqrestore(&pool->lock, flags); + dm_table_event(pool->ti->table); + } + + if (!free_blocks) { + if (pool->no_free_space) + return -ENOSPC; + else { + /* + * Try to commit to see if that will free up some + * more space. + */ + r = dm_pool_commit_metadata(pool->pmd); + if (r) { + DMERR("%s: dm_pool_commit_metadata() failed, error = %d", + __func__, r); + return r; + } + + r = dm_pool_get_free_block_count(pool->pmd, &free_blocks); + if (r) + return r; + + /* + * If we still have no space we set a flag to avoid + * doing all this checking and return -ENOSPC. + */ + if (!free_blocks) { + DMWARN("%s: no free space available.", + dm_device_name(pool->pool_md)); + spin_lock_irqsave(&pool->lock, flags); + pool->no_free_space = 1; + spin_unlock_irqrestore(&pool->lock, flags); + return -ENOSPC; + } + } + } + + r = dm_pool_alloc_data_block(pool->pmd, result); + if (r) + return r; + + return 0; +} + +/* + * If we have run out of space, queue bios until the device is + * resumed, presumably after having been reloaded with more space. + */ +static void retry_on_resume(struct bio *bio) +{ + struct thin_c *tc = dm_get_mapinfo(bio)->ptr; + struct pool *pool = tc->pool; + unsigned long flags; + + spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->retry_on_resume_list, bio); + spin_unlock_irqrestore(&pool->lock, flags); +} + +static void no_space(struct cell *cell) +{ + struct bio *bio; + struct bio_list bios; + + bio_list_init(&bios); + cell_release(cell, &bios); + + while ((bio = bio_list_pop(&bios))) + retry_on_resume(bio); +} + +static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block, + struct cell_key *key, + struct dm_thin_lookup_result *lookup_result, + struct cell *cell) +{ + int r; + dm_block_t data_block; + + r = alloc_data_block(tc, &data_block); + switch (r) { + case 0: + schedule_copy(tc, block, lookup_result->block, + data_block, cell, bio); + break; + + case -ENOSPC: + no_space(cell); + break; + + default: + DMERR("%s: alloc_data_block() failed, error = %d", __func__, r); + cell_error(cell); + break; + } +} + +static void process_shared_bio(struct thin_c *tc, struct bio *bio, + dm_block_t block, + struct dm_thin_lookup_result *lookup_result) +{ + struct cell *cell; + struct pool *pool = tc->pool; + struct cell_key key; + + /* + * If cell is already occupied, then sharing is already in the process + * of being broken so we have nothing further to do here. + */ + build_data_key(tc->td, lookup_result->block, &key); + if (bio_detain(pool->prison, &key, bio, &cell)) + return; + + if (bio_data_dir(bio) == WRITE) + break_sharing(tc, bio, block, &key, lookup_result, cell); + else { + struct endio_hook *h; + h = mempool_alloc(pool->endio_hook_pool, GFP_NOIO); + + h->tc = tc; + h->entry = ds_inc(&pool->ds); + save_and_set_endio(bio, &h->saved_bi_end_io, shared_read_endio); + dm_get_mapinfo(bio)->ptr = h; + + cell_release_singleton(cell, bio); + remap_and_issue(tc, bio, lookup_result->block); + } +} + +static void provision_block(struct thin_c *tc, struct bio *bio, dm_block_t block, + struct cell *cell) +{ + int r; + dm_block_t data_block; + + /* + * Remap empty bios (flushes) immediately, without provisioning. + */ + if (!bio->bi_size) { + cell_release_singleton(cell, bio); + remap_and_issue(tc, bio, 0); + return; + } + + /* + * Fill read bios with zeroes and complete them immediately. + */ + if (bio_data_dir(bio) == READ) { + zero_fill_bio(bio); + cell_release_singleton(cell, bio); + bio_endio(bio, 0); + return; + } + + r = alloc_data_block(tc, &data_block); + switch (r) { + case 0: + schedule_zero(tc, block, data_block, cell, bio); + break; + + case -ENOSPC: + no_space(cell); + break; + + default: + DMERR("%s: alloc_data_block() failed, error = %d", __func__, r); + cell_error(cell); + break; + } +} + +static void process_bio(struct thin_c *tc, struct bio *bio) +{ + int r; + dm_block_t block = get_bio_block(tc, bio); + struct cell *cell; + struct cell_key key; + struct dm_thin_lookup_result lookup_result; + + /* + * If cell is already occupied, then the block is already + * being provisioned so we have nothing further to do here. + */ + build_virtual_key(tc->td, block, &key); + if (bio_detain(tc->pool->prison, &key, bio, &cell)) + return; + + r = dm_thin_find_block(tc->td, block, 1, &lookup_result); + switch (r) { + case 0: + /* + * We can release this cell now. This thread is the only + * one that puts bios into a cell, and we know there were + * no preceding bios. + */ + /* + * TODO: this will probably have to change when discard goes + * back in. + */ + cell_release_singleton(cell, bio); + + if (lookup_result.shared) + process_shared_bio(tc, bio, block, &lookup_result); + else + remap_and_issue(tc, bio, lookup_result.block); + break; + + case -ENODATA: + provision_block(tc, bio, block, cell); + break; + + default: + DMERR("dm_thin_find_block() failed, error = %d", r); + bio_io_error(bio); + break; + } +} + +static void process_deferred_bios(struct pool *pool) +{ + unsigned long flags; + struct bio *bio; + struct bio_list bios; + int r; + + bio_list_init(&bios); + + spin_lock_irqsave(&pool->lock, flags); + bio_list_merge(&bios, &pool->deferred_bios); + bio_list_init(&pool->deferred_bios); + spin_unlock_irqrestore(&pool->lock, flags); + + while ((bio = bio_list_pop(&bios))) { + struct thin_c *tc = dm_get_mapinfo(bio)->ptr; + /* + * If we've got no free new_mapping structs, and processing + * this bio might require one, we pause until there are some + * prepared mappings to process. + */ + if (ensure_next_mapping(pool)) { + spin_lock_irqsave(&pool->lock, flags); + bio_list_merge(&pool->deferred_bios, &bios); + spin_unlock_irqrestore(&pool->lock, flags); + + break; + } + process_bio(tc, bio); + } + + /* + * If there are any deferred flush bios, we must commit + * the metadata before issuing them. + */ + bio_list_init(&bios); + spin_lock_irqsave(&pool->lock, flags); + bio_list_merge(&bios, &pool->deferred_flush_bios); + bio_list_init(&pool->deferred_flush_bios); + spin_unlock_irqrestore(&pool->lock, flags); + + if (bio_list_empty(&bios)) + return; + + r = dm_pool_commit_metadata(pool->pmd); + if (r) { + DMERR("%s: dm_pool_commit_metadata() failed, error = %d", + __func__, r); + while ((bio = bio_list_pop(&bios))) + bio_io_error(bio); + return; + } + + while ((bio = bio_list_pop(&bios))) + generic_make_request(bio); +} + +static void do_worker(struct work_struct *ws) +{ + struct pool *pool = container_of(ws, struct pool, worker); + + process_prepared_mappings(pool); + process_deferred_bios(pool); +} + +/*----------------------------------------------------------------*/ + +/* + * Mapping functions. + */ + +/* + * Called only while mapping a thin bio to hand it over to the workqueue. + */ +static void thin_defer_bio(struct thin_c *tc, struct bio *bio) +{ + unsigned long flags; + struct pool *pool = tc->pool; + + spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->deferred_bios, bio); + spin_unlock_irqrestore(&pool->lock, flags); + + wake_worker(pool); +} + +/* + * Non-blocking function called from the thin target's map function. + */ +static int thin_bio_map(struct dm_target *ti, struct bio *bio, + union map_info *map_context) +{ + int r; + struct thin_c *tc = ti->private; + dm_block_t block = get_bio_block(tc, bio); + struct dm_thin_device *td = tc->td; + struct dm_thin_lookup_result result; + + /* + * Save the thin context for easy access from the deferred bio later. + */ + map_context->ptr = tc; + + if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) { + thin_defer_bio(tc, bio); + return DM_MAPIO_SUBMITTED; + } + + r = dm_thin_find_block(td, block, 0, &result); + + /* + * Note that we defer readahead too. + */ + switch (r) { + case 0: + if (unlikely(result.shared)) { + /* + * We have a race condition here between the + * result.shared value returned by the lookup and + * snapshot creation, which may cause new + * sharing. + * + * To avoid this always quiesce the origin before + * taking the snap. You want to do this anyway to + * ensure a consistent application view + * (i.e. lockfs). + * + * More distant ancestors are irrelevant. The + * shared flag will be set in their case. + */ + thin_defer_bio(tc, bio); + r = DM_MAPIO_SUBMITTED; + } else { + remap(tc, bio, result.block); + r = DM_MAPIO_REMAPPED; + } + break; + + case -ENODATA: + /* + * In future, the failed dm_thin_find_block above could + * provide the hint to load the metadata into cache. + */ + case -EWOULDBLOCK: + thin_defer_bio(tc, bio); + r = DM_MAPIO_SUBMITTED; + break; + } + + return r; +} + +static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits) +{ + int r; + unsigned long flags; + struct pool_c *pt = container_of(cb, struct pool_c, callbacks); + + spin_lock_irqsave(&pt->pool->lock, flags); + r = !bio_list_empty(&pt->pool->retry_on_resume_list); + spin_unlock_irqrestore(&pt->pool->lock, flags); + + if (!r) { + struct request_queue *q = bdev_get_queue(pt->data_dev->bdev); + r = bdi_congested(&q->backing_dev_info, bdi_bits); + } + + return r; +} + +static void __requeue_bios(struct pool *pool) +{ + bio_list_merge(&pool->deferred_bios, &pool->retry_on_resume_list); + bio_list_init(&pool->retry_on_resume_list); +} + +/*---------------------------------------------------------------- + * Binding of control targets to a pool object + *--------------------------------------------------------------*/ +static int bind_control_target(struct pool *pool, struct dm_target *ti) +{ + struct pool_c *pt = ti->private; + + pool->ti = ti; + pool->low_water_blocks = pt->low_water_blocks; + pool->zero_new_blocks = pt->zero_new_blocks; + + return 0; +} + +static void unbind_control_target(struct pool *pool, struct dm_target *ti) +{ + if (pool->ti == ti) + pool->ti = NULL; +} + +/*---------------------------------------------------------------- + * Pool creation + *--------------------------------------------------------------*/ +static void __pool_destroy(struct pool *pool) +{ + __pool_table_remove(pool); + + if (dm_pool_metadata_close(pool->pmd) < 0) + DMWARN("%s: dm_pool_metadata_close() failed.", __func__); + + prison_destroy(pool->prison); + dm_kcopyd_client_destroy(pool->copier); + + if (pool->wq) + destroy_workqueue(pool->wq); + + if (pool->next_mapping) + mempool_free(pool->next_mapping, pool->mapping_pool); + mempool_destroy(pool->mapping_pool); + mempool_destroy(pool->endio_hook_pool); + kfree(pool); +} + +static struct pool *pool_create(struct mapped_device *pool_md, + struct block_device *metadata_dev, + unsigned long block_size, char **error) +{ + int r; + void *err_p; + struct pool *pool; + struct dm_pool_metadata *pmd; + + pmd = dm_pool_metadata_open(metadata_dev, block_size); + if (IS_ERR(pmd)) { + *error = "Error creating metadata object"; + return (struct pool *)pmd; + } + + pool = kmalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) { + *error = "Error allocating memory for pool"; + err_p = ERR_PTR(-ENOMEM); + goto bad_pool; + } + + pool->pmd = pmd; + pool->sectors_per_block = block_size; + pool->block_shift = ffs(block_size) - 1; + pool->offset_mask = block_size - 1; + pool->low_water_blocks = 0; + pool->zero_new_blocks = 1; + pool->prison = prison_create(PRISON_CELLS); + if (!pool->prison) { + *error = "Error creating pool's bio prison"; + err_p = ERR_PTR(-ENOMEM); + goto bad_prison; + } + + pool->copier = dm_kcopyd_client_create(); + if (IS_ERR(pool->copier)) { + r = PTR_ERR(pool->copier); + *error = "Error creating pool's kcopyd client"; + err_p = ERR_PTR(r); + goto bad_kcopyd_client; + } + + /* + * Create singlethreaded workqueue that will service all devices + * that use this metadata. + */ + pool->wq = alloc_ordered_workqueue("dm-" DM_MSG_PREFIX, WQ_MEM_RECLAIM); + if (!pool->wq) { + *error = "Error creating pool's workqueue"; + err_p = ERR_PTR(-ENOMEM); + goto bad_wq; + } + + INIT_WORK(&pool->worker, do_worker); + spin_lock_init(&pool->lock); + bio_list_init(&pool->deferred_bios); + bio_list_init(&pool->deferred_flush_bios); + INIT_LIST_HEAD(&pool->prepared_mappings); + pool->low_water_triggered = 0; + pool->no_free_space = 0; + bio_list_init(&pool->retry_on_resume_list); + ds_init(&pool->ds); + + pool->next_mapping = NULL; + pool->mapping_pool = + mempool_create_kmalloc_pool(MAPPING_POOL_SIZE, sizeof(struct new_mapping)); + if (!pool->mapping_pool) { + *error = "Error creating pool's mapping mempool"; + err_p = ERR_PTR(-ENOMEM); + goto bad_mapping_pool; + } + + pool->endio_hook_pool = + mempool_create_kmalloc_pool(ENDIO_HOOK_POOL_SIZE, sizeof(struct endio_hook)); + if (!pool->endio_hook_pool) { + *error = "Error creating pool's endio_hook mempool"; + err_p = ERR_PTR(-ENOMEM); + goto bad_endio_hook_pool; + } + pool->ref_count = 1; + pool->pool_md = pool_md; + pool->md_dev = metadata_dev; + __pool_table_insert(pool); + + return pool; + +bad_endio_hook_pool: + mempool_destroy(pool->mapping_pool); +bad_mapping_pool: + destroy_workqueue(pool->wq); +bad_wq: + dm_kcopyd_client_destroy(pool->copier); +bad_kcopyd_client: + prison_destroy(pool->prison); +bad_prison: + kfree(pool); +bad_pool: + if (dm_pool_metadata_close(pmd)) + DMWARN("%s: dm_pool_metadata_close() failed.", __func__); + + return err_p; +} + +static void __pool_inc(struct pool *pool) +{ + BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex)); + pool->ref_count++; +} + +static void __pool_dec(struct pool *pool) +{ + BUG_ON(!mutex_is_locked(&dm_thin_pool_table.mutex)); + BUG_ON(!pool->ref_count); + if (!--pool->ref_count) + __pool_destroy(pool); +} + +static struct pool *__pool_find(struct mapped_device *pool_md, + struct block_device *metadata_dev, + unsigned long block_size, char **error) +{ + struct pool *pool = __pool_table_lookup_metadata_dev(metadata_dev); + + if (pool) { + if (pool->pool_md != pool_md) + return ERR_PTR(-EBUSY); + __pool_inc(pool); + + } else { + pool = __pool_table_lookup(pool_md); + if (pool) { + if (pool->md_dev != metadata_dev) + return ERR_PTR(-EINVAL); + __pool_inc(pool); + + } else + pool = pool_create(pool_md, metadata_dev, block_size, error); + } + + return pool; +} + +/*---------------------------------------------------------------- + * Pool target methods + *--------------------------------------------------------------*/ +static void pool_dtr(struct dm_target *ti) +{ + struct pool_c *pt = ti->private; + + mutex_lock(&dm_thin_pool_table.mutex); + + unbind_control_target(pt->pool, ti); + __pool_dec(pt->pool); + dm_put_device(ti, pt->metadata_dev); + dm_put_device(ti, pt->data_dev); + kfree(pt); + + mutex_unlock(&dm_thin_pool_table.mutex); +} + +struct pool_features { + unsigned zero_new_blocks:1; +}; + +static int parse_pool_features(struct dm_arg_set *as, struct pool_features *pf, + struct dm_target *ti) +{ + int r; + unsigned argc; + const char *arg_name; + + static struct dm_arg _args[] = { + {0, 1, "Invalid number of pool feature arguments"}, + }; + + /* + * No feature arguments supplied. + */ + if (!as->argc) + return 0; + + r = dm_read_arg_group(_args, as, &argc, &ti->error); + if (r) + return -EINVAL; + + while (argc && !r) { + arg_name = dm_shift_arg(as); + argc--; + + if (!strcasecmp(arg_name, "skip_block_zeroing")) { + pf->zero_new_blocks = 0; + continue; + } + + ti->error = "Unrecognised pool feature requested"; + r = -EINVAL; + } + + return r; +} + +/* + * thin-pool + * + * + * [<#feature args> []*] + * + * Optional feature arguments are: + * skip_block_zeroing: skips the zeroing of newly-provisioned blocks. + */ +static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) +{ + int r; + struct pool_c *pt; + struct pool *pool; + struct pool_features pf; + struct dm_arg_set as; + struct dm_dev *data_dev; + unsigned long block_size; + dm_block_t low_water_blocks; + struct dm_dev *metadata_dev; + sector_t metadata_dev_size; + + /* + * FIXME Remove validation from scope of lock. + */ + mutex_lock(&dm_thin_pool_table.mutex); + + if (argc < 4) { + ti->error = "Invalid argument count"; + r = -EINVAL; + goto out_unlock; + } + as.argc = argc; + as.argv = argv; + + r = dm_get_device(ti, argv[0], FMODE_READ | FMODE_WRITE, &metadata_dev); + if (r) { + ti->error = "Error opening metadata block device"; + goto out_unlock; + } + + metadata_dev_size = i_size_read(metadata_dev->bdev->bd_inode) >> SECTOR_SHIFT; + if (metadata_dev_size > METADATA_DEV_MAX_SECTORS) { + ti->error = "Metadata device is too large"; + r = -EINVAL; + goto out_metadata; + } + + r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev); + if (r) { + ti->error = "Error getting data device"; + goto out_metadata; + } + + if (kstrtoul(argv[2], 10, &block_size) || !block_size || + block_size < DATA_DEV_BLOCK_SIZE_MIN_SECTORS || + block_size > DATA_DEV_BLOCK_SIZE_MAX_SECTORS || + !is_power_of_2(block_size)) { + ti->error = "Invalid block size"; + r = -EINVAL; + goto out; + } + + if (kstrtoull(argv[3], 10, (unsigned long long *)&low_water_blocks)) { + ti->error = "Invalid low water mark"; + r = -EINVAL; + goto out; + } + + /* + * Set default pool features. + */ + memset(&pf, 0, sizeof(pf)); + pf.zero_new_blocks = 1; + + dm_consume_args(&as, 4); + r = parse_pool_features(&as, &pf, ti); + if (r) + goto out; + + pt = kzalloc(sizeof(*pt), GFP_KERNEL); + if (!pt) { + r = -ENOMEM; + goto out; + } + + pool = __pool_find(dm_table_get_md(ti->table), metadata_dev->bdev, + block_size, &ti->error); + if (IS_ERR(pool)) { + r = PTR_ERR(pool); + goto out_free_pt; + } + + pt->pool = pool; + pt->ti = ti; + pt->metadata_dev = metadata_dev; + pt->data_dev = data_dev; + pt->low_water_blocks = low_water_blocks; + pt->zero_new_blocks = pf.zero_new_blocks; + ti->num_flush_requests = 1; + ti->num_discard_requests = 0; + ti->private = pt; + + pt->callbacks.congested_fn = pool_is_congested; + dm_table_add_target_callbacks(ti->table, &pt->callbacks); + + mutex_unlock(&dm_thin_pool_table.mutex); + + return 0; + +out_free_pt: + kfree(pt); +out: + dm_put_device(ti, data_dev); +out_metadata: + dm_put_device(ti, metadata_dev); +out_unlock: + mutex_unlock(&dm_thin_pool_table.mutex); + + return r; +} + +static int pool_map(struct dm_target *ti, struct bio *bio, + union map_info *map_context) +{ + int r; + struct pool_c *pt = ti->private; + struct pool *pool = pt->pool; + unsigned long flags; + + /* + * As this is a singleton target, ti->begin is always zero. + */ + spin_lock_irqsave(&pool->lock, flags); + bio->bi_bdev = pt->data_dev->bdev; + r = DM_MAPIO_REMAPPED; + spin_unlock_irqrestore(&pool->lock, flags); + + return r; +} + +/* + * Retrieves the number of blocks of the data device from + * the superblock and compares it to the actual device size, + * thus resizing the data device in case it has grown. + * + * This both copes with opening preallocated data devices in the ctr + * being followed by a resume + * -and- + * calling the resume method individually after userspace has + * grown the data device in reaction to a table event. + */ +static int pool_preresume(struct dm_target *ti) +{ + int r; + struct pool_c *pt = ti->private; + struct pool *pool = pt->pool; + dm_block_t data_size, sb_data_size; + + /* + * Take control of the pool object. + */ + r = bind_control_target(pool, ti); + if (r) + return r; + + data_size = ti->len >> pool->block_shift; + r = dm_pool_get_data_dev_size(pool->pmd, &sb_data_size); + if (r) { + DMERR("failed to retrieve data device size"); + return r; + } + + if (data_size < sb_data_size) { + DMERR("pool target too small, is %llu blocks (expected %llu)", + data_size, sb_data_size); + return -EINVAL; + + } else if (data_size > sb_data_size) { + r = dm_pool_resize_data_dev(pool->pmd, data_size); + if (r) { + DMERR("failed to resize data device"); + return r; + } + + r = dm_pool_commit_metadata(pool->pmd); + if (r) { + DMERR("%s: dm_pool_commit_metadata() failed, error = %d", + __func__, r); + return r; + } + } + + return 0; +} + +static void pool_resume(struct dm_target *ti) +{ + struct pool_c *pt = ti->private; + struct pool *pool = pt->pool; + unsigned long flags; + + spin_lock_irqsave(&pool->lock, flags); + pool->low_water_triggered = 0; + pool->no_free_space = 0; + __requeue_bios(pool); + spin_unlock_irqrestore(&pool->lock, flags); + + wake_worker(pool); +} + +static void pool_postsuspend(struct dm_target *ti) +{ + int r; + struct pool_c *pt = ti->private; + struct pool *pool = pt->pool; + + flush_workqueue(pool->wq); + + r = dm_pool_commit_metadata(pool->pmd); + if (r < 0) { + DMERR("%s: dm_pool_commit_metadata() failed, error = %d", + __func__, r); + /* FIXME: invalidate device? error the next FUA or FLUSH bio ?*/ + } +} + +static int check_arg_count(unsigned argc, unsigned args_required) +{ + if (argc != args_required) { + DMWARN("Message received with %u arguments instead of %u.", + argc, args_required); + return -EINVAL; + } + + return 0; +} + +static int read_dev_id(char *arg, dm_thin_id *dev_id, int warning) +{ + if (!kstrtoull(arg, 10, (unsigned long long *)dev_id) && + *dev_id <= MAX_DEV_ID) + return 0; + + if (warning) + DMWARN("Message received with invalid device id: %s", arg); + + return -EINVAL; +} + +static int process_create_thin_mesg(unsigned argc, char **argv, struct pool *pool) +{ + dm_thin_id dev_id; + int r; + + r = check_arg_count(argc, 2); + if (r) + return r; + + r = read_dev_id(argv[1], &dev_id, 1); + if (r) + return r; + + r = dm_pool_create_thin(pool->pmd, dev_id); + if (r) { + DMWARN("Creation of new thinly-provisioned device with id %s failed.", + argv[1]); + return r; + } + + return 0; +} + +static int process_create_snap_mesg(unsigned argc, char **argv, struct pool *pool) +{ + dm_thin_id dev_id; + dm_thin_id origin_dev_id; + int r; + + r = check_arg_count(argc, 3); + if (r) + return r; + + r = read_dev_id(argv[1], &dev_id, 1); + if (r) + return r; + + r = read_dev_id(argv[2], &origin_dev_id, 1); + if (r) + return r; + + r = dm_pool_create_snap(pool->pmd, dev_id, origin_dev_id); + if (r) { + DMWARN("Creation of new snapshot %s of device %s failed.", + argv[1], argv[2]); + return r; + } + + return 0; +} + +static int process_delete_mesg(unsigned argc, char **argv, struct pool *pool) +{ + dm_thin_id dev_id; + int r; + + r = check_arg_count(argc, 2); + if (r) + return r; + + r = read_dev_id(argv[1], &dev_id, 1); + if (r) + return r; + + r = dm_pool_delete_thin_device(pool->pmd, dev_id); + if (r) + DMWARN("Deletion of thin device %s failed.", argv[1]); + + return r; +} + +static int process_set_transaction_id_mesg(unsigned argc, char **argv, struct pool *pool) +{ + dm_thin_id old_id, new_id; + int r; + + r = check_arg_count(argc, 3); + if (r) + return r; + + if (kstrtoull(argv[1], 10, (unsigned long long *)&old_id)) { + DMWARN("set_transaction_id message: Unrecognised id %s.", argv[1]); + return -EINVAL; + } + + if (kstrtoull(argv[2], 10, (unsigned long long *)&new_id)) { + DMWARN("set_transaction_id message: Unrecognised new id %s.", argv[2]); + return -EINVAL; + } + + r = dm_pool_set_metadata_transaction_id(pool->pmd, old_id, new_id); + if (r) { + DMWARN("Failed to change transaction id from %s to %s.", + argv[1], argv[2]); + return r; + } + + return 0; +} + +/* + * Messages supported: + * create_thin + * create_snap + * delete + * trim + * set_transaction_id + */ +static int pool_message(struct dm_target *ti, unsigned argc, char **argv) +{ + int r = -EINVAL; + struct pool_c *pt = ti->private; + struct pool *pool = pt->pool; + + if (!strcasecmp(argv[0], "create_thin")) + r = process_create_thin_mesg(argc, argv, pool); + + else if (!strcasecmp(argv[0], "create_snap")) + r = process_create_snap_mesg(argc, argv, pool); + + else if (!strcasecmp(argv[0], "delete")) + r = process_delete_mesg(argc, argv, pool); + + else if (!strcasecmp(argv[0], "set_transaction_id")) + r = process_set_transaction_id_mesg(argc, argv, pool); + + else + DMWARN("Unrecognised thin pool target message received: %s", argv[0]); + + if (!r) { + r = dm_pool_commit_metadata(pool->pmd); + if (r) + DMERR("%s message: dm_pool_commit_metadata() failed, error = %d", + argv[0], r); + } + + return r; +} + +/* + * Status line is: + * / + * / + */ +static int pool_status(struct dm_target *ti, status_type_t type, + char *result, unsigned maxlen) +{ + int r; + unsigned sz = 0; + uint64_t transaction_id; + dm_block_t nr_free_blocks_data; + dm_block_t nr_free_blocks_metadata; + dm_block_t nr_blocks_data; + dm_block_t nr_blocks_metadata; + dm_block_t held_root; + char buf[BDEVNAME_SIZE]; + char buf2[BDEVNAME_SIZE]; + struct pool_c *pt = ti->private; + struct pool *pool = pt->pool; + + switch (type) { + case STATUSTYPE_INFO: + r = dm_pool_get_metadata_transaction_id(pool->pmd, + &transaction_id); + if (r) + return r; + + r = dm_pool_get_free_metadata_block_count(pool->pmd, + &nr_free_blocks_metadata); + if (r) + return r; + + r = dm_pool_get_metadata_dev_size(pool->pmd, &nr_blocks_metadata); + if (r) + return r; + + r = dm_pool_get_free_block_count(pool->pmd, + &nr_free_blocks_data); + if (r) + return r; + + r = dm_pool_get_data_dev_size(pool->pmd, &nr_blocks_data); + if (r) + return r; + + r = dm_pool_get_held_metadata_root(pool->pmd, &held_root); + if (r) + return r; + + DMEMIT("%llu %llu/%llu %llu/%llu ", + (unsigned long long)transaction_id, + (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata), + (unsigned long long)nr_blocks_metadata, + (unsigned long long)(nr_blocks_data - nr_free_blocks_data), + (unsigned long long)nr_blocks_data); + + if (held_root) + DMEMIT("%llu", held_root); + else + DMEMIT("-"); + + break; + + case STATUSTYPE_TABLE: + DMEMIT("%s %s %lu %llu ", + format_dev_t(buf, pt->metadata_dev->bdev->bd_dev), + format_dev_t(buf2, pt->data_dev->bdev->bd_dev), + (unsigned long)pool->sectors_per_block, + (unsigned long long)pt->low_water_blocks); + + DMEMIT("%u ", !pool->zero_new_blocks); + + if (!pool->zero_new_blocks) + DMEMIT("skip_block_zeroing "); + break; + } + + return 0; +} + +static int pool_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct pool_c *pt = ti->private; + + return fn(ti, pt->data_dev, 0, ti->len, data); +} + +static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm, + struct bio_vec *biovec, int max_size) +{ + struct pool_c *pt = ti->private; + struct request_queue *q = bdev_get_queue(pt->data_dev->bdev); + + if (!q->merge_bvec_fn) + return max_size; + + bvm->bi_bdev = pt->data_dev->bdev; + + return min(max_size, q->merge_bvec_fn(q, bvm, biovec)); +} + +static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits) +{ + struct pool_c *pt = ti->private; + struct pool *pool = pt->pool; + + blk_limits_io_min(limits, 0); + blk_limits_io_opt(limits, pool->sectors_per_block << SECTOR_SHIFT); +} + +static struct target_type pool_target = { + .name = "thin-pool", + .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | + DM_TARGET_IMMUTABLE, + .version = {1, 0, 0}, + .module = THIS_MODULE, + .ctr = pool_ctr, + .dtr = pool_dtr, + .map = pool_map, + .postsuspend = pool_postsuspend, + .preresume = pool_preresume, + .resume = pool_resume, + .message = pool_message, + .status = pool_status, + .merge = pool_merge, + .iterate_devices = pool_iterate_devices, + .io_hints = pool_io_hints, +}; + +/*---------------------------------------------------------------- + * Thin target methods + *--------------------------------------------------------------*/ +static void thin_dtr(struct dm_target *ti) +{ + struct thin_c *tc = ti->private; + + mutex_lock(&dm_thin_pool_table.mutex); + + __pool_dec(tc->pool); + dm_pool_close_thin_device(tc->td); + dm_put_device(ti, tc->pool_dev); + kfree(tc); + + mutex_unlock(&dm_thin_pool_table.mutex); +} + +/* + * Thin target parameters: + * + * + * + * pool_dev: the path to the pool (eg, /dev/mapper/my_pool) + * dev_id: the internal device identifier + */ +static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) +{ + int r; + struct thin_c *tc; + struct dm_dev *pool_dev; + struct mapped_device *pool_md; + + mutex_lock(&dm_thin_pool_table.mutex); + + if (argc != 2) { + ti->error = "Invalid argument count"; + r = -EINVAL; + goto out_unlock; + } + + tc = ti->private = kzalloc(sizeof(*tc), GFP_KERNEL); + if (!tc) { + ti->error = "Out of memory"; + r = -ENOMEM; + goto out_unlock; + } + + r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &pool_dev); + if (r) { + ti->error = "Error opening pool device"; + goto bad_pool_dev; + } + tc->pool_dev = pool_dev; + + if (read_dev_id(argv[1], (unsigned long long *)&tc->dev_id, 0)) { + ti->error = "Invalid device id"; + r = -EINVAL; + goto bad_common; + } + + pool_md = dm_get_md(tc->pool_dev->bdev->bd_dev); + if (!pool_md) { + ti->error = "Couldn't get pool mapped device"; + r = -EINVAL; + goto bad_common; + } + + tc->pool = __pool_table_lookup(pool_md); + if (!tc->pool) { + ti->error = "Couldn't find pool object"; + r = -EINVAL; + goto bad_pool_lookup; + } + __pool_inc(tc->pool); + + r = dm_pool_open_thin_device(tc->pool->pmd, tc->dev_id, &tc->td); + if (r) { + ti->error = "Couldn't open thin internal device"; + goto bad_thin_open; + } + + ti->split_io = tc->pool->sectors_per_block; + ti->num_flush_requests = 1; + ti->num_discard_requests = 0; + ti->discards_supported = 0; + + dm_put(pool_md); + + mutex_unlock(&dm_thin_pool_table.mutex); + + return 0; + +bad_thin_open: + __pool_dec(tc->pool); +bad_pool_lookup: + dm_put(pool_md); +bad_common: + dm_put_device(ti, tc->pool_dev); +bad_pool_dev: + kfree(tc); +out_unlock: + mutex_unlock(&dm_thin_pool_table.mutex); + + return r; +} + +static int thin_map(struct dm_target *ti, struct bio *bio, + union map_info *map_context) +{ + bio->bi_sector -= ti->begin; + + return thin_bio_map(ti, bio, map_context); +} + +static void thin_postsuspend(struct dm_target *ti) +{ + if (dm_noflush_suspending(ti)) + requeue_io((struct thin_c *)ti->private); +} + +/* + * + */ +static int thin_status(struct dm_target *ti, status_type_t type, + char *result, unsigned maxlen) +{ + int r; + ssize_t sz = 0; + dm_block_t mapped, highest; + char buf[BDEVNAME_SIZE]; + struct thin_c *tc = ti->private; + + if (!tc->td) + DMEMIT("-"); + else { + switch (type) { + case STATUSTYPE_INFO: + r = dm_thin_get_mapped_count(tc->td, &mapped); + if (r) + return r; + + r = dm_thin_get_highest_mapped_block(tc->td, &highest); + if (r < 0) + return r; + + DMEMIT("%llu ", mapped * tc->pool->sectors_per_block); + if (r) + DMEMIT("%llu", ((highest + 1) * + tc->pool->sectors_per_block) - 1); + else + DMEMIT("-"); + break; + + case STATUSTYPE_TABLE: + DMEMIT("%s %lu", + format_dev_t(buf, tc->pool_dev->bdev->bd_dev), + (unsigned long) tc->dev_id); + break; + } + } + + return 0; +} + +static int thin_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + dm_block_t blocks; + struct thin_c *tc = ti->private; + + /* + * We can't call dm_pool_get_data_dev_size() since that blocks. So + * we follow a more convoluted path through to the pool's target. + */ + if (!tc->pool->ti) + return 0; /* nothing is bound */ + + blocks = tc->pool->ti->len >> tc->pool->block_shift; + if (blocks) + return fn(ti, tc->pool_dev, 0, tc->pool->sectors_per_block * blocks, data); + + return 0; +} + +static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) +{ + struct thin_c *tc = ti->private; + + blk_limits_io_min(limits, 0); + blk_limits_io_opt(limits, tc->pool->sectors_per_block << SECTOR_SHIFT); +} + +static struct target_type thin_target = { + .name = "thin", + .version = {1, 0, 0}, + .module = THIS_MODULE, + .ctr = thin_ctr, + .dtr = thin_dtr, + .map = thin_map, + .postsuspend = thin_postsuspend, + .status = thin_status, + .iterate_devices = thin_iterate_devices, + .io_hints = thin_io_hints, +}; + +/*----------------------------------------------------------------*/ + +static int __init dm_thin_init(void) +{ + int r; + + pool_table_init(); + + r = dm_register_target(&thin_target); + if (r) + return r; + + r = dm_register_target(&pool_target); + if (r) + dm_unregister_target(&thin_target); + + return r; +} + +static void dm_thin_exit(void) +{ + dm_unregister_target(&thin_target); + dm_unregister_target(&pool_target); +} + +module_init(dm_thin_init); +module_exit(dm_thin_exit); + +MODULE_DESCRIPTION(DM_NAME "device-mapper thin provisioning target"); +MODULE_AUTHOR("Joe Thornber "); +MODULE_LICENSE("GPL"); From b89544575d0096735edc9b0ad187e635487905ad Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Mon, 31 Oct 2011 20:21:22 +0000 Subject: [PATCH 12/14] dm log userspace: fix comment hyphens Fix comments: clustered-disk needs a hyphen not an underscore. Signed-off-by: Jonathan Brassow Signed-off-by: Alasdair G Kergon --- Documentation/device-mapper/dm-log.txt | 2 +- drivers/md/dm-log-userspace-base.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/device-mapper/dm-log.txt b/Documentation/device-mapper/dm-log.txt index 994dd75475a6..c155ac569c44 100644 --- a/Documentation/device-mapper/dm-log.txt +++ b/Documentation/device-mapper/dm-log.txt @@ -48,7 +48,7 @@ kernel and userspace, 'connector' is used as the interface for communication. There are currently two userspace log implementations that leverage this -framework - "clustered_disk" and "clustered_core". These implementations +framework - "clustered-disk" and "clustered-core". These implementations provide a cluster-coherent log for shared-storage. Device-mapper mirroring can be used in a shared-storage environment when the cluster log implementations are employed. diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 1021c8986011..3c27978890b7 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -146,7 +146,7 @@ static int build_constructor_string(struct dm_target *ti, * * Where 'other args' is the userspace implementation specific log * arguments. An example might be: - * clustered_disk [[no]sync] + * clustered-disk [[no]sync] * * So, this module will strip off the for identification purposes * when communicating with userspace about a log; but will pass on everything From 5a25f0eb707bbb4a5aaaf19c933605a6dbaf77a5 Mon Sep 17 00:00:00 2001 From: Jonathan E Brassow Date: Mon, 31 Oct 2011 20:21:24 +0000 Subject: [PATCH 13/14] dm log userspace: add log device dependency Allow userspace dm log implementations to register their log device so it is no longer missing from the list of device dependencies. When device mapper targets use a device they normally call dm_get_device which includes it in the device list returned to userspace applications such as LVM through the DM_TABLE_DEPS ioctl. Userspace log devices don't use dm_get_device as userspace opens them so they are missing from the list of dependencies. This patch extends the DM_ULOG_CTR operation to allow userspace to respond with the name of the log device (if appropriate) to be registered via 'dm_get_device'. DM_ULOG_REQUEST_VERSION is incremented. This is backwards compatible. If the kernel and userspace log server have both been updated, the new information will be passed down to the kernel and the device will be registered. If the kernel is new, but the log server is old, the log server will not pass down any device information and the kernel will simply bypass the device registration as before. If the kernel is old but the log server is new, the log server will see the old version number and not pass the device info. Signed-off-by: Jonathan Brassow Signed-off-by: Alasdair G Kergon --- drivers/md/dm-log-userspace-base.c | 35 +++++++++++++++++++++++++++--- include/linux/dm-log-userspace.h | 18 ++++++++++----- 2 files changed, 45 insertions(+), 8 deletions(-) diff --git a/drivers/md/dm-log-userspace-base.c b/drivers/md/dm-log-userspace-base.c index 3c27978890b7..8db3862dade5 100644 --- a/drivers/md/dm-log-userspace-base.c +++ b/drivers/md/dm-log-userspace-base.c @@ -30,6 +30,7 @@ struct flush_entry { struct log_c { struct dm_target *ti; + struct dm_dev *log_dev; uint32_t region_size; region_t region_count; uint64_t luid; @@ -161,13 +162,15 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, struct log_c *lc = NULL; uint64_t rdata; size_t rdata_size = sizeof(rdata); + char *devices_rdata = NULL; + size_t devices_rdata_size = DM_NAME_LEN; if (argc < 3) { DMWARN("Too few arguments to userspace dirty log"); return -EINVAL; } - lc = kmalloc(sizeof(*lc), GFP_KERNEL); + lc = kzalloc(sizeof(*lc), GFP_KERNEL); if (!lc) { DMWARN("Unable to allocate userspace log context."); return -ENOMEM; @@ -195,9 +198,19 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, return str_size; } - /* Send table string */ + devices_rdata = kzalloc(devices_rdata_size, GFP_KERNEL); + if (!devices_rdata) { + DMERR("Failed to allocate memory for device information"); + r = -ENOMEM; + goto out; + } + + /* + * Send table string and get back any opened device. + */ r = dm_consult_userspace(lc->uuid, lc->luid, DM_ULOG_CTR, - ctr_str, str_size, NULL, NULL); + ctr_str, str_size, + devices_rdata, &devices_rdata_size); if (r < 0) { if (r == -ESRCH) @@ -220,7 +233,20 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti, lc->region_size = (uint32_t)rdata; lc->region_count = dm_sector_div_up(ti->len, lc->region_size); + if (devices_rdata_size) { + if (devices_rdata[devices_rdata_size - 1] != '\0') { + DMERR("DM_ULOG_CTR device return string not properly terminated"); + r = -EINVAL; + goto out; + } + r = dm_get_device(ti, devices_rdata, + dm_table_get_mode(ti->table), &lc->log_dev); + if (r) + DMERR("Failed to register %s with device-mapper", + devices_rdata); + } out: + kfree(devices_rdata); if (r) { kfree(lc); kfree(ctr_str); @@ -241,6 +267,9 @@ static void userspace_dtr(struct dm_dirty_log *log) NULL, 0, NULL, NULL); + if (lc->log_dev) + dm_put_device(lc->ti, lc->log_dev); + kfree(lc->usr_argv_str); kfree(lc); diff --git a/include/linux/dm-log-userspace.h b/include/linux/dm-log-userspace.h index eeace7d3ff15..0678c2adc421 100644 --- a/include/linux/dm-log-userspace.h +++ b/include/linux/dm-log-userspace.h @@ -52,15 +52,20 @@ * Payload-to-userspace: * A single string containing all the argv arguments separated by ' 's * Payload-to-kernel: - * None. ('data_size' in the dm_ulog_request struct should be 0.) + * A NUL-terminated string that is the name of the device that is used + * as the backing store for the log data. 'dm_get_device' will be called + * on this device. ('dm_put_device' will be called on this device + * automatically after calling DM_ULOG_DTR.) If there is no device needed + * for log data, 'data_size' in the dm_ulog_request struct should be 0. * * The UUID contained in the dm_ulog_request structure is the reference that * will be used by all request types to a specific log. The constructor must - * record this assotiation with instance created. + * record this association with the instance created. * * When the request has been processed, user-space must return the - * dm_ulog_request to the kernel - setting the 'error' field and - * 'data_size' appropriately. + * dm_ulog_request to the kernel - setting the 'error' field, filling the + * data field with the log device if necessary, and setting 'data_size' + * appropriately. */ #define DM_ULOG_CTR 1 @@ -377,8 +382,11 @@ * dm_ulog_request or a change in the way requests are * issued/handled. Changes are outlined here: * version 1: Initial implementation + * version 2: DM_ULOG_CTR allowed to return a string containing a + * device name that is to be registered with DM via + * 'dm_get_device'. */ -#define DM_ULOG_REQUEST_VERSION 1 +#define DM_ULOG_REQUEST_VERSION 2 struct dm_ulog_request { /* From 2e727c3ca1beff05f27b6207a795790f222bf8d8 Mon Sep 17 00:00:00 2001 From: Jonathan E Brassow Date: Mon, 31 Oct 2011 20:21:26 +0000 Subject: [PATCH 14/14] dm: raid fix device status indicator when array initializing When devices in a RAID array are not in-sync, they are supposed to be reported as such in the status output as an 'a' character, which means "alive, but not in-sync". But when the entire array is rebuilt 'A' is being used, which is incorrect. This patch corrects this to 'a'. Signed-off-by: Jonathan Brassow Signed-off-by: Alasdair G Kergon --- drivers/md/dm-raid.c | 48 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 11 deletions(-) diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 86df8b2cf927..7503a20d04a7 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1017,30 +1017,56 @@ static int raid_status(struct dm_target *ti, status_type_t type, struct raid_set *rs = ti->private; unsigned raid_param_cnt = 1; /* at least 1 for chunksize */ unsigned sz = 0; - int i; + int i, array_in_sync = 0; sector_t sync; switch (type) { case STATUSTYPE_INFO: DMEMIT("%s %d ", rs->raid_type->name, rs->md.raid_disks); - for (i = 0; i < rs->md.raid_disks; i++) { - if (test_bit(Faulty, &rs->dev[i].rdev.flags)) - DMEMIT("D"); - else if (test_bit(In_sync, &rs->dev[i].rdev.flags)) - DMEMIT("A"); - else - DMEMIT("a"); - } - if (test_bit(MD_RECOVERY_RUNNING, &rs->md.recovery)) sync = rs->md.curr_resync_completed; else sync = rs->md.recovery_cp; - if (sync > rs->md.resync_max_sectors) + if (sync >= rs->md.resync_max_sectors) { + array_in_sync = 1; sync = rs->md.resync_max_sectors; + } else { + /* + * The array may be doing an initial sync, or it may + * be rebuilding individual components. If all the + * devices are In_sync, then it is the array that is + * being initialized. + */ + for (i = 0; i < rs->md.raid_disks; i++) + if (!test_bit(In_sync, &rs->dev[i].rdev.flags)) + array_in_sync = 1; + } + /* + * Status characters: + * 'D' = Dead/Failed device + * 'a' = Alive but not in-sync + * 'A' = Alive and in-sync + */ + for (i = 0; i < rs->md.raid_disks; i++) { + if (test_bit(Faulty, &rs->dev[i].rdev.flags)) + DMEMIT("D"); + else if (!array_in_sync || + !test_bit(In_sync, &rs->dev[i].rdev.flags)) + DMEMIT("a"); + else + DMEMIT("A"); + } + /* + * In-sync ratio: + * The in-sync ratio shows the progress of: + * - Initializing the array + * - Rebuilding a subset of devices of the array + * The user can distinguish between the two by referring + * to the status characters. + */ DMEMIT(" %llu/%llu", (unsigned long long) sync, (unsigned long long) rs->md.resync_max_sectors);