Commit 7a771cea authored by Linus Torvalds's avatar Linus Torvalds

Merge tag 'dm-4.11-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Fix dm-raid transient device failure processing and other smaller
   tweaks.

 - Add journal support to the DM raid target to close the 'write hole'
   on raid 4/5/6.

 - Fix dm-cache corruption, due to rounding bug, when cache exceeds 2TB.

 - Add 'metadata2' feature to dm-cache to separate the dirty bitset out
   from other cache metadata. This improves speed of shutting down a
   large cache device (which implies writing out dirty bits).

 - Fix a memory leak during dm-stats data structure destruction.

 - Fix a DM multipath round-robin path selector performance regression
   that was caused by less precise balancing across all paths.

 - Lastly, introduce a DM core fix for a long-standing DM snapshot
   deadlock that is rooted in the complexity of the device stack used in
   conjunction with block core maintaining bios on current->bio_list to
   manage recursion in generic_make_request(). A more comprehensive fix
   to block core (and its hook in the cpu scheduler) would be wonderful
   but this DM-specific fix is pragmatic considering how difficult it
   has been to make progress on a generic fix.

* tag 'dm-4.11-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (22 commits)
  dm: flush queued bios when process blocks to avoid deadlock
  dm round robin: revert "use percpu 'repeat_count' and 'current_path'"
  dm stats: fix a leaked s->histogram_boundaries array
  dm space map metadata: constify dm_space_map structures
  dm cache metadata: use cursor api in blocks_are_clean_separate_dirty()
  dm persistent data: add cursor skip functions to the cursor APIs
  dm cache metadata: use dm_bitset_new() to create the dirty bitset in format 2
  dm bitset: add dm_bitset_new()
  dm cache metadata: name the cache block that couldn't be loaded
  dm cache metadata: add "metadata2" feature
  dm cache metadata: use bitset cursor api to load discard bitset
  dm bitset: introduce cursor api
  dm btree: use GFP_NOFS in dm_btree_del()
  dm space map common: memcpy the disk root to ensure it's arch aligned
  dm block manager: add unlikely() annotations on dm_bufio error paths
  dm cache: fix corruption seen when using cache > 2TB
  dm raid: cleanup awkward branching in raid_message() option processing
  dm raid: use mddev rather than rdev->mddev
  dm raid: use read_disk_sb() throughout
  dm raid: add raid4/5/6 journaling support
  ...
parents e67bd12d d67a5f4b
......@@ -207,6 +207,10 @@ Optional feature arguments are:
block, then the cache block is invalidated.
To enable passthrough mode the cache must be clean.
metadata2 : use version 2 of the metadata. This stores the dirty bits
in a separate btree, which improves speed of shutting
down the cache.
A policy called 'default' is always registered. This is an alias for
the policy we currently think is giving best all round performance.
......
......@@ -161,6 +161,15 @@ The target is named "raid" and it accepts the following parameters:
the RAID type (i.e. the allocation algorithm) as well, e.g.
changing from raid5_ls to raid5_n.
[journal_dev <dev>]
This option adds a journal device to raid4/5/6 raid sets and
uses it to close the 'write hole' caused by the non-atomic updates
to the component devices which can cause data loss during recovery.
The journal device is used as writethrough thus causing writes to
be throttled versus non-journaled raid4/5/6 sets.
Takeover/reshape is not possible with a raid4/5/6 journal device;
it has to be deconfigured before requesting these.
<#raid_devs>: The number of devices composing the array.
Each device consists of two entries. The first is the device
containing the metadata (if any); the second is the one containing the
......@@ -245,6 +254,9 @@ recovery. Here is a fuller description of the individual fields:
<data_offset> The current data offset to the start of the user data on
each component device of a raid set (see the respective
raid parameter to support out-of-place reshaping).
<journal_char> 'A' - active raid4/5/6 journal device.
'D' - dead journal device.
'-' - no journal device.
Message Interface
......@@ -314,3 +326,8 @@ Version History
1.9.0 Add support for RAID level takeover/reshape/region size
and set size reduction.
1.9.1 Fix activation of existing RAID 4/10 mapped devices
1.9.2 Don't emit '- -' on the status table line in case the constructor
fails reading a superblock. Correctly emit 'maj:min1 maj:min2' and
'D' on the status line. If '- -' is passed into the constructor, emit
'- -' on the table line and '-' as the status line health character.
1.10.0 Add support for raid4/5/6 journal device
This diff is collapsed.
......@@ -45,18 +45,20 @@
* As these various flags are defined they should be added to the
* following masks.
*/
#define DM_CACHE_FEATURE_COMPAT_SUPP 0UL
#define DM_CACHE_FEATURE_COMPAT_RO_SUPP 0UL
#define DM_CACHE_FEATURE_INCOMPAT_SUPP 0UL
/*
* Reopens or creates a new, empty metadata volume.
* Returns an ERR_PTR on failure.
* Reopens or creates a new, empty metadata volume. Returns an ERR_PTR on
* failure. If reopening then features must match.
*/
struct dm_cache_metadata *dm_cache_metadata_open(struct block_device *bdev,
sector_t data_block_size,
bool may_format_device,
size_t policy_hint_size);
size_t policy_hint_size,
unsigned metadata_version);
void dm_cache_metadata_close(struct dm_cache_metadata *cmd);
......@@ -91,7 +93,8 @@ int dm_cache_load_mappings(struct dm_cache_metadata *cmd,
load_mapping_fn fn,
void *context);
int dm_cache_set_dirty(struct dm_cache_metadata *cmd, dm_cblock_t cblock, bool dirty);
int dm_cache_set_dirty_bits(struct dm_cache_metadata *cmd,
unsigned nr_bits, unsigned long *bits);
struct dm_cache_statistics {
uint32_t read_hits;
......
......@@ -179,6 +179,7 @@ enum cache_io_mode {
struct cache_features {
enum cache_metadata_mode mode;
enum cache_io_mode io_mode;
unsigned metadata_version;
};
struct cache_stats {
......@@ -248,7 +249,7 @@ struct cache {
/*
* Fields for converting from sectors to blocks.
*/
uint32_t sectors_per_block;
sector_t sectors_per_block;
int sectors_per_block_shift;
spinlock_t lock;
......@@ -2534,13 +2535,14 @@ static void init_features(struct cache_features *cf)
{
cf->mode = CM_WRITE;
cf->io_mode = CM_IO_WRITEBACK;
cf->metadata_version = 1;
}
static int parse_features(struct cache_args *ca, struct dm_arg_set *as,
char **error)
{
static struct dm_arg _args[] = {
{0, 1, "Invalid number of cache feature arguments"},
{0, 2, "Invalid number of cache feature arguments"},
};
int r;
......@@ -2566,6 +2568,9 @@ static int parse_features(struct cache_args *ca, struct dm_arg_set *as,
else if (!strcasecmp(arg, "passthrough"))
cf->io_mode = CM_IO_PASSTHROUGH;
else if (!strcasecmp(arg, "metadata2"))
cf->metadata_version = 2;
else {
*error = "Unrecognised cache feature requested";
return -EINVAL;
......@@ -2820,7 +2825,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
cmd = dm_cache_metadata_open(cache->metadata_dev->bdev,
ca->block_size, may_format,
dm_cache_policy_get_hint_size(cache->policy));
dm_cache_policy_get_hint_size(cache->policy),
ca->features.metadata_version);
if (IS_ERR(cmd)) {
*error = "Error creating metadata object";
r = PTR_ERR(cmd);
......@@ -3165,21 +3171,16 @@ static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
static int write_dirty_bitset(struct cache *cache)
{
unsigned i, r;
int r;
if (get_cache_mode(cache) >= CM_READ_ONLY)
return -EINVAL;
for (i = 0; i < from_cblock(cache->cache_size); i++) {
r = dm_cache_set_dirty(cache->cmd, to_cblock(i),
is_dirty(cache, to_cblock(i)));
if (r) {
metadata_operation_failed(cache, "dm_cache_set_dirty", r);
return r;
}
}
r = dm_cache_set_dirty_bits(cache->cmd, from_cblock(cache->cache_size), cache->dirty_bitset);
if (r)
metadata_operation_failed(cache, "dm_cache_set_dirty_bits", r);
return 0;
return r;
}
static int write_discard_bitset(struct cache *cache)
......@@ -3540,11 +3541,11 @@ static void cache_status(struct dm_target *ti, status_type_t type,
residency = policy_residency(cache->policy);
DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ",
DMEMIT("%u %llu/%llu %llu %llu/%llu %u %u %u %u %u %u %lu ",
(unsigned)DM_CACHE_METADATA_BLOCK_SIZE,
(unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
(unsigned long long)nr_blocks_metadata,
cache->sectors_per_block,
(unsigned long long)cache->sectors_per_block,
(unsigned long long) from_cblock(residency),
(unsigned long long) from_cblock(cache->cache_size),
(unsigned) atomic_read(&cache->stats.read_hit),
......@@ -3555,14 +3556,19 @@ static void cache_status(struct dm_target *ti, status_type_t type,
(unsigned) atomic_read(&cache->stats.promotion),
(unsigned long) atomic_read(&cache->nr_dirty));
if (cache->features.metadata_version == 2)
DMEMIT("2 metadata2 ");
else
DMEMIT("1 ");
if (writethrough_mode(&cache->features))
DMEMIT("1 writethrough ");
DMEMIT("writethrough ");
else if (passthrough_mode(&cache->features))
DMEMIT("1 passthrough ");
DMEMIT("passthrough ");
else if (writeback_mode(&cache->features))
DMEMIT("1 writeback ");
DMEMIT("writeback ");
else {
DMERR("%s: internal error: unknown io mode: %d",
......@@ -3810,7 +3816,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
static struct target_type cache_target = {
.name = "cache",
.version = {1, 9, 0},
.version = {1, 10, 0},
.module = THIS_MODULE,
.ctr = cache_ctr,
.dtr = cache_dtr,
......
This diff is collapsed.
......@@ -17,8 +17,8 @@
#include <linux/module.h>
#define DM_MSG_PREFIX "multipath round-robin"
#define RR_MIN_IO 1000
#define RR_VERSION "1.1.0"
#define RR_MIN_IO 1
#define RR_VERSION "1.2.0"
/*-----------------------------------------------------------------
* Path-handling code, paths are held in lists
......@@ -47,44 +47,19 @@ struct selector {
struct list_head valid_paths;
struct list_head invalid_paths;
spinlock_t lock;
struct dm_path * __percpu *current_path;
struct percpu_counter repeat_count;
};
static void set_percpu_current_path(struct selector *s, struct dm_path *path)
{
int cpu;
for_each_possible_cpu(cpu)
*per_cpu_ptr(s->current_path, cpu) = path;
}
static struct selector *alloc_selector(void)
{
struct selector *s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return NULL;
INIT_LIST_HEAD(&s->valid_paths);
INIT_LIST_HEAD(&s->invalid_paths);
spin_lock_init(&s->lock);
s->current_path = alloc_percpu(struct dm_path *);
if (!s->current_path)
goto out_current_path;
set_percpu_current_path(s, NULL);
if (percpu_counter_init(&s->repeat_count, 0, GFP_KERNEL))
goto out_repeat_count;
if (s) {
INIT_LIST_HEAD(&s->valid_paths);
INIT_LIST_HEAD(&s->invalid_paths);
spin_lock_init(&s->lock);
}
return s;
out_repeat_count:
free_percpu(s->current_path);
out_current_path:
kfree(s);
return NULL;;
}
static int rr_create(struct path_selector *ps, unsigned argc, char **argv)
......@@ -105,8 +80,6 @@ static void rr_destroy(struct path_selector *ps)
free_paths(&s->valid_paths);
free_paths(&s->invalid_paths);
free_percpu(s->current_path);
percpu_counter_destroy(&s->repeat_count);
kfree(s);
ps->context = NULL;
}
......@@ -157,6 +130,11 @@ static int rr_add_path(struct path_selector *ps, struct dm_path *path,
return -EINVAL;
}
if (repeat_count > 1) {
DMWARN_LIMIT("repeat_count > 1 is deprecated, using 1 instead");
repeat_count = 1;
}
/* allocate the path */
pi = kmalloc(sizeof(*pi), GFP_KERNEL);
if (!pi) {
......@@ -183,9 +161,6 @@ static void rr_fail_path(struct path_selector *ps, struct dm_path *p)
struct path_info *pi = p->pscontext;
spin_lock_irqsave(&s->lock, flags);
if (p == *this_cpu_ptr(s->current_path))
set_percpu_current_path(s, NULL);
list_move(&pi->list, &s->invalid_paths);
spin_unlock_irqrestore(&s->lock, flags);
}
......@@ -208,29 +183,15 @@ static struct dm_path *rr_select_path(struct path_selector *ps, size_t nr_bytes)
unsigned long flags;
struct selector *s = ps->context;
struct path_info *pi = NULL;
struct dm_path *current_path = NULL;
local_irq_save(flags);
current_path = *this_cpu_ptr(s->current_path);
if (current_path) {
percpu_counter_dec(&s->repeat_count);
if (percpu_counter_read_positive(&s->repeat_count) > 0) {
local_irq_restore(flags);
return current_path;
}
}
spin_lock(&s->lock);
spin_lock_irqsave(&s->lock, flags);
if (!list_empty(&s->valid_paths)) {
pi = list_entry(s->valid_paths.next, struct path_info, list);
list_move_tail(&pi->list, &s->valid_paths);
percpu_counter_set(&s->repeat_count, pi->repeat_count);
set_percpu_current_path(s, pi->path);
current_path = pi->path;
}
spin_unlock_irqrestore(&s->lock, flags);
return current_path;
return pi ? pi->path : NULL;
}
static struct path_selector_type rr_ps = {
......
......@@ -175,6 +175,7 @@ static void dm_stat_free(struct rcu_head *head)
int cpu;
struct dm_stat *s = container_of(head, struct dm_stat, rcu_head);
kfree(s->histogram_boundaries);
kfree(s->program_id);
kfree(s->aux_data);
for_each_possible_cpu(cpu) {
......
......@@ -974,10 +974,61 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
}
EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
/*
* Flush current->bio_list when the target map method blocks.
* This fixes deadlocks in snapshot and possibly in other targets.
*/
struct dm_offload {
struct blk_plug plug;
struct blk_plug_cb cb;
};
static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
{
struct dm_offload *o = container_of(cb, struct dm_offload, cb);
struct bio_list list;
struct bio *bio;
INIT_LIST_HEAD(&o->cb.list);
if (unlikely(!current->bio_list))
return;
list = *current->bio_list;
bio_list_init(current->bio_list);
while ((bio = bio_list_pop(&list))) {
struct bio_set *bs = bio->bi_pool;
if (unlikely(!bs) || bs == fs_bio_set) {
bio_list_add(current->bio_list, bio);
continue;
}
spin_lock(&bs->rescue_lock);
bio_list_add(&bs->rescue_list, bio);
queue_work(bs->rescue_workqueue, &bs->rescue_work);
spin_unlock(&bs->rescue_lock);
}
}
static void dm_offload_start(struct dm_offload *o)
{
blk_start_plug(&o->plug);
o->cb.callback = flush_current_bio_list;
list_add(&o->cb.list, &current->plug->cb_list);
}
static void dm_offload_end(struct dm_offload *o)
{
list_del(&o->cb.list);
blk_finish_plug(&o->plug);
}
static void __map_bio(struct dm_target_io *tio)
{
int r;
sector_t sector;
struct dm_offload o;
struct bio *clone = &tio->clone;
struct dm_target *ti = tio->ti;
......@@ -990,7 +1041,11 @@ static void __map_bio(struct dm_target_io *tio)
*/
atomic_inc(&tio->io->io_count);
sector = clone->bi_iter.bi_sector;
dm_offload_start(&o);
r = ti->type->map(ti, clone);
dm_offload_end(&o);
if (r == DM_MAPIO_REMAPPED) {
/* the bio has been remapped so dispatch it */
......
......@@ -976,6 +976,27 @@ int dm_array_cursor_next(struct dm_array_cursor *c)
}
EXPORT_SYMBOL_GPL(dm_array_cursor_next);
int dm_array_cursor_skip(struct dm_array_cursor *c, uint32_t count)
{
int r;
do {
uint32_t remaining = le32_to_cpu(c->ab->nr_entries) - c->index;
if (count < remaining) {
c->index += count;
return 0;
}
count -= remaining;
r = dm_array_cursor_next(c);
} while (!r);
return r;
}
EXPORT_SYMBOL_GPL(dm_array_cursor_skip);
void dm_array_cursor_get_value(struct dm_array_cursor *c, void **value_le)
{
*value_le = element_at(c->info, c->ab, c->index);
......
......@@ -207,6 +207,7 @@ void dm_array_cursor_end(struct dm_array_cursor *c);
uint32_t dm_array_cursor_index(struct dm_array_cursor *c);
int dm_array_cursor_next(struct dm_array_cursor *c);
int dm_array_cursor_skip(struct dm_array_cursor *c, uint32_t count);
/*
* value_le is only valid while the cursor points at the current value.
......
......@@ -39,6 +39,48 @@ int dm_bitset_empty(struct dm_disk_bitset *info, dm_block_t *root)
}
EXPORT_SYMBOL_GPL(dm_bitset_empty);
struct packer_context {
bit_value_fn fn;
unsigned nr_bits;
void *context;
};
static int pack_bits(uint32_t index, void *value, void *context)
{
int r;
struct packer_context *p = context;
unsigned bit, nr = min(64u, p->nr_bits - (index * 64));
uint64_t word = 0;
bool bv;
for (bit = 0; bit < nr; bit++) {
r = p->fn(index * 64 + bit, &bv, p->context);
if (r)
return r;
if (bv)
set_bit(bit, (unsigned long *) &word);
else
clear_bit(bit, (unsigned long *) &word);
}
*((__le64 *) value) = cpu_to_le64(word);
return 0;
}
int dm_bitset_new(struct dm_disk_bitset *info, dm_block_t *root,
uint32_t size, bit_value_fn fn, void *context)
{
struct packer_context p;
p.fn = fn;
p.nr_bits = size;
p.context = context;
return dm_array_new(&info->array_info, root, dm_div_up(size, 64), pack_bits, &p);
}
EXPORT_SYMBOL_GPL(dm_bitset_new);
int dm_bitset_resize(struct dm_disk_bitset *info, dm_block_t root,
uint32_t old_nr_entries, uint32_t new_nr_entries,
bool default_value, dm_block_t *new_root)
......@@ -168,4 +210,108 @@ int dm_bitset_test_bit(struct dm_disk_bitset *info, dm_block_t root,
}
EXPORT_SYMBOL_GPL(dm_bitset_test_bit);
static int cursor_next_array_entry(struct dm_bitset_cursor *c)
{
int r;
__le64 *value;
r = dm_array_cursor_next(&c->cursor);
if (r)
return r;
dm_array_cursor_get_value(&c->cursor, (void **) &value);
c->array_index++;
c->bit_index = 0;
c->current_bits = le64_to_cpu(*value);
return 0;
}
int dm_bitset_cursor_begin(struct dm_disk_bitset *info,
dm_block_t root, uint32_t nr_entries,
struct dm_bitset_cursor *c)
{
int r;
__le64 *value;
if (!nr_entries)
return -ENODATA;
c->info = info;
c->entries_remaining = nr_entries;
r = dm_array_cursor_begin(&info->array_info, root, &c->cursor);
if (r)
return r;
dm_array_cursor_get_value(&c->cursor, (void **) &value);
c->array_index = 0;
c->bit_index = 0;
c->current_bits = le64_to_cpu(*value);
return r;
}
EXPORT_SYMBOL_GPL(dm_bitset_cursor_begin);
void dm_bitset_cursor_end(struct dm_bitset_cursor *c)
{
return dm_array_cursor_end(&c->cursor);
}
EXPORT_SYMBOL_GPL(dm_bitset_cursor_end);
int dm_bitset_cursor_next(struct dm_bitset_cursor *c)
{
int r = 0;
if (!c->entries_remaining)
return -ENODATA;
c->entries_remaining--;
if (++c->bit_index > 63)
r = cursor_next_array_entry(c);
return r;
}
EXPORT_SYMBOL_GPL(dm_bitset_cursor_next);
int dm_bitset_cursor_skip(struct dm_bitset_cursor *c, uint32_t count)
{
int r;
__le64 *value;
uint32_t nr_array_skip;
uint32_t remaining_in_word = 64 - c->bit_index;
if (c->entries_remaining < count)
return -ENODATA;
if (count < remaining_in_word) {
c->bit_index += count;
c->entries_remaining -= count;
return 0;
} else {
c->entries_remaining -= remaining_in_word;
count -= remaining_in_word;
}
nr_array_skip = (count / 64) + 1;
r = dm_array_cursor_skip(&c->cursor, nr_array_skip);
if (r)
return r;
dm_array_cursor_get_value(&c->cursor, (void **) &value);
c->entries_remaining -= count;
c->array_index += nr_array_skip;
c->bit_index = count & 63;
c->current_bits = le64_to_cpu(*value);
return 0;
}
EXPORT_SYMBOL_GPL(dm_bitset_cursor_skip);
bool dm_bitset_cursor_get_value(struct dm_bitset_cursor *c)
{
return test_bit(c->bit_index, (unsigned long *) &c->current_bits);
}
EXPORT_SYMBOL_GPL(dm_bitset_cursor_get_value);
/*----------------------------------------------------------------*/
......@@ -92,6 +92,22 @@ void dm_disk_bitset_init(struct dm_transaction_manager *tm,
*/
int dm_bitset_empty(struct dm_disk_bitset *info, dm_block_t *new_root);
/*
* Creates a new bitset populated with values provided by a callback
* function. This is more efficient than creating an empty bitset,
* resizing, and then setting values since that process incurs a lot of
* copying.
*
* info - describes the array
* root - the root block of the array on disk
* size - the number of entries in the array
* fn - the callback
* context - passed to the callback
*/
typedef int (*bit_value_fn)(uint32_t index, bool *value, void *context);
int dm_bitset_new(struct dm_disk_bitset *info, dm_block_t *root,
uint32_t size, bit_value_fn fn, void *context);
/*
* Resize the bitset.
*
......@@ -161,6 +177,29 @@ int dm_bitset_test_bit(struct dm_disk_bitset *info, dm_block_t root,
int dm_bitset_flush(struct dm_disk_bitset *info, dm_block_t root,
dm_block_t *new_root);
struct dm_bitset_cursor {
struct dm_disk_bitset *info;
struct dm_array_cursor cursor;
uint32_t entries_remaining;
uint32_t array_index;
uint32_t bit_index;
uint64_t current_bits;
};
/*
* Make sure you've flush any dm_disk_bitset and updated the root before
* using this.
*/
int dm_bitset_cursor_begin(struct dm_disk_bitset *info,
dm_block_t root, uint32_t nr_entries,
struct dm_bitset_cursor *c);
void dm_bitset_cursor_end(struct dm_bitset_cursor *c);
int dm_bitset_cursor_next(struct dm_bitset_cursor *c);
int dm_bitset_cursor_skip(struct dm_bitset_cursor *c, uint32_t count);
bool dm_bitset_cursor_get_value(struct dm_bitset_cursor *c);
/*----------------------------------------------------------------*/
#endif /* _LINUX_DM_BITSET_H */
......@@ -462,7 +462,7 @@ int dm_bm_read_lock(struct dm_block_manager *bm, dm_block_t b,
int r;
p = dm_bufio_read(bm->bufio, b, (struct dm_buffer **) result);
if (IS_ERR(p))
if (unlikely(IS_ERR(p)))
return PTR_ERR(p);
aux = dm_bufio_get_aux_data(to_buffer(*result));
......@@ -498,7 +498,7 @@ int dm_bm_write_lock(struct dm_block_manager *bm,
return -EPERM;
p = dm_bufio_read(bm->bufio, b, (struct dm_buffer **) result);
if (IS_ERR(p))
if (unlikely(IS_ERR(p)))
return PTR_ERR(p);
aux = dm_bufio_get_aux_data(to_buffer(*result));
......@@ -531,7 +531,7 @@ int dm_bm_read_try_lock(struct dm_block_manager *bm,
int r;
p = dm_bufio_get(bm->bufio, b, (struct dm_buffer **) result);
if (IS_ERR(p))
if (unlikely(IS_ERR(p)))
return PTR_ERR(p);
if (unlikely(!p))
return -EWOULDBLOCK;
......@@ -567,7 +567,7 @@ int dm_bm_write_lock_zero(struct dm_block_manager *bm,
return -EPERM;
p = dm_bufio_new(bm->bufio, b, (struct dm_buffer **) result);
if (IS_ERR(p))
if (unlikely(IS_ERR(p)))
return PTR_ERR(p);
memset(p, 0, dm_bm_block_size(bm));
......
......@@ -272,7 +272,12 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
int r;
struct del_stack *s;
s = kmalloc(sizeof(*s), GFP_NOIO);
/*
* dm_btree_del() is called via an ioctl, as such should be
* considered an FS op. We can't recurse back into the FS, so we
* allocate GFP_NOFS.
*/
s = kmalloc(sizeof(*s), GFP_NOFS);
if (!s)
return -ENOMEM;
s->info = info;
......@@ -1139,6 +1144,17 @@ int dm_btree_cursor_next(struct dm_btree_cursor *c)
}
EXPORT_SYMBOL_GPL(dm_btree_cursor_next);
int dm_btree_cursor_skip(struct dm_btree_cursor *c, uint32_t count)
{
int r = 0;
while (count-- && !r)
r = dm_btree_cursor_next(c);
return r;
}
EXPORT_SYMBOL_GPL(dm_btree_cursor_skip);
int dm_btree_cursor_get_value(struct dm_btree_cursor *c, uint64_t *key, void *value_le)
{
if (c->depth) {
......
......@@ -209,6 +209,7 @@ int dm_btree_cursor_begin(struct dm_btree_info *info, dm_block_t root,
bool prefetch_leaves, struct dm_btree_cursor *c);
void dm_btree_cursor_end(struct dm_btree_cursor *c);
int dm_btree_cursor_next(struct dm_btree_cursor *c);
int dm_btree_cursor_skip(struct dm_btree_cursor *c, uint32_t count);
int dm_btree_cursor_get_value(struct dm_btree_cursor *c, uint64_t *key, void *value_le);
#endif /* _LINUX_DM_BTREE_H */
......@@ -626,13 +626,19 @@ 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;
struct disk_sm_root smr;
if (len < sizeof(struct disk_sm_root)) {
DMERR("sm_metadata root too small");
return -ENOMEM;
}
/*
* We don't know the alignment of the root_le buffer, so need to
* copy into a new structure.
*/
memcpy(&smr, root_le, sizeof(smr));
r = sm_ll_init(ll, tm);
if (r < 0)
return r;
......@@ -644,10 +650,10 @@ int sm_ll_open_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm,
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);
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);
}
......
......@@ -544,7 +544,7 @@ static int sm_metadata_copy_root(struct dm_space_map *sm, void *where_le, size_t
static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks);
static struct dm_space_map ops = {
static const struct dm_space_map ops = {
.destroy = sm_metadata_destroy,
.extend = sm_metadata_extend,
.get_nr_blocks = sm_metadata_get_nr_blocks,
......@@ -671,7 +671,7 @@ static int sm_bootstrap_copy_root(struct dm_space_map *sm, void *where,
return -EINVAL;
}
static struct dm_space_map bootstrap_ops = {
static const struct dm_space_map bootstrap_ops = {
.destroy = sm_bootstrap_destroy,
.extend = sm_bootstrap_extend,
.get_nr_blocks = sm_bootstrap_get_nr_blocks,
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment