dm: optimize use SRCU and RCU
This patch removes "io_lock" and "map_lock" in struct mapped_device and "holders" in struct dm_table and replaces these mechanisms with sleepable-rcu. Previously, the code would call "dm_get_live_table" and "dm_table_put" to get and release table. Now, the code is changed to call "dm_get_live_table" and "dm_put_live_table". dm_get_live_table locks sleepable-rcu and dm_put_live_table unlocks it. dm_get_live_table_fast/dm_put_live_table_fast can be used instead of dm_get_live_table/dm_put_live_table. These *_fast functions use non-sleepable RCU, so the caller must not block between them. If the code changes active or inactive dm table, it must call dm_sync_table before destroying the old table. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Alasdair G Kergon <agk@redhat.com>
This commit is contained in:
Mikulas Patocka
Alasdair G Kergon
parent
2480945cd4
commit
83d5e5b0af
|
|
@ -36,6 +36,14 @@ struct hash_cell {
|
|||
struct dm_table *new_map;
|
||||
};
|
||||
|
||||
/*
|
||||
* A dummy definition to make RCU happy.
|
||||
* struct dm_table should never be dereferenced in this file.
|
||||
*/
|
||||
struct dm_table {
|
||||
int undefined__;
|
||||
};
|
||||
|
||||
struct vers_iter {
|
||||
size_t param_size;
|
||||
struct dm_target_versions *vers, *old_vers;
|
||||
|
|
@ -242,9 +250,10 @@ static int dm_hash_insert(const char *name, const char *uuid, struct mapped_devi
|
|||
return -EBUSY;
|
||||
}
|
||||
|
||||
static void __hash_remove(struct hash_cell *hc)
|
||||
static struct dm_table *__hash_remove(struct hash_cell *hc)
|
||||
{
|
||||
struct dm_table *table;
|
||||
int srcu_idx;
|
||||
|
||||
/* remove from the dev hash */
|
||||
list_del(&hc->uuid_list);
|
||||
|
|
@ -253,16 +262,18 @@ static void __hash_remove(struct hash_cell *hc)
|
|||
dm_set_mdptr(hc->md, NULL);
|
||||
mutex_unlock(&dm_hash_cells_mutex);
|
||||
|
||||
table = dm_get_live_table(hc->md);
|
||||
if (table) {
|
||||
table = dm_get_live_table(hc->md, &srcu_idx);
|
||||
if (table)
|
||||
dm_table_event(table);
|
||||
dm_table_put(table);
|
||||
}
|
||||
dm_put_live_table(hc->md, srcu_idx);
|
||||
|
||||
table = NULL;
|
||||
if (hc->new_map)
|
||||
dm_table_destroy(hc->new_map);
|
||||
table = hc->new_map;
|
||||
dm_put(hc->md);
|
||||
free_cell(hc);
|
||||
|
||||
return table;
|
||||
}
|
||||
|
||||
static void dm_hash_remove_all(int keep_open_devices)
|
||||
|
|
@ -270,6 +281,7 @@ static void dm_hash_remove_all(int keep_open_devices)
|
|||
int i, dev_skipped;
|
||||
struct hash_cell *hc;
|
||||
struct mapped_device *md;
|
||||
struct dm_table *t;
|
||||
|
||||
retry:
|
||||
dev_skipped = 0;
|
||||
|
|
@ -287,10 +299,14 @@ retry:
|
|||
continue;
|
||||
}
|
||||
|
||||
__hash_remove(hc);
|
||||
t = __hash_remove(hc);
|
||||
|
||||
up_write(&_hash_lock);
|
||||
|
||||
if (t) {
|
||||
dm_sync_table(md);
|
||||
dm_table_destroy(t);
|
||||
}
|
||||
dm_put(md);
|
||||
if (likely(keep_open_devices))
|
||||
dm_destroy(md);
|
||||
|
|
@ -356,6 +372,7 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
|
|||
struct dm_table *table;
|
||||
struct mapped_device *md;
|
||||
unsigned change_uuid = (param->flags & DM_UUID_FLAG) ? 1 : 0;
|
||||
int srcu_idx;
|
||||
|
||||
/*
|
||||
* duplicate new.
|
||||
|
|
@ -418,11 +435,10 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param,
|
|||
/*
|
||||
* Wake up any dm event waiters.
|
||||
*/
|
||||
table = dm_get_live_table(hc->md);
|
||||
if (table) {
|
||||
table = dm_get_live_table(hc->md, &srcu_idx);
|
||||
if (table)
|
||||
dm_table_event(table);
|
||||
dm_table_put(table);
|
||||
}
|
||||
dm_put_live_table(hc->md, srcu_idx);
|
||||
|
||||
if (!dm_kobject_uevent(hc->md, KOBJ_CHANGE, param->event_nr))
|
||||
param->flags |= DM_UEVENT_GENERATED_FLAG;
|
||||
|
|
@ -620,11 +636,14 @@ static int check_name(const char *name)
|
|||
* _hash_lock without first calling dm_table_put, because dm_table_destroy
|
||||
* waits for this dm_table_put and could be called under this lock.
|
||||
*/
|
||||
static struct dm_table *dm_get_inactive_table(struct mapped_device *md)
|
||||
static struct dm_table *dm_get_inactive_table(struct mapped_device *md, int *srcu_idx)
|
||||
{
|
||||
struct hash_cell *hc;
|
||||
struct dm_table *table = NULL;
|
||||
|
||||
/* increment rcu count, we don't care about the table pointer */
|
||||
dm_get_live_table(md, srcu_idx);
|
||||
|
||||
down_read(&_hash_lock);
|
||||
hc = dm_get_mdptr(md);
|
||||
if (!hc || hc->md != md) {
|
||||
|
|
@ -633,8 +652,6 @@ static struct dm_table *dm_get_inactive_table(struct mapped_device *md)
|
|||
}
|
||||
|
||||
table = hc->new_map;
|
||||
if (table)
|
||||
dm_table_get(table);
|
||||
|
||||
out:
|
||||
up_read(&_hash_lock);
|
||||
|
|
@ -643,10 +660,11 @@ out:
|
|||
}
|
||||
|
||||
static struct dm_table *dm_get_live_or_inactive_table(struct mapped_device *md,
|
||||
struct dm_ioctl *param)
|
||||
struct dm_ioctl *param,
|
||||
int *srcu_idx)
|
||||
{
|
||||
return (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) ?
|
||||
dm_get_inactive_table(md) : dm_get_live_table(md);
|
||||
dm_get_inactive_table(md, srcu_idx) : dm_get_live_table(md, srcu_idx);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -657,6 +675,7 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
|
|||
{
|
||||
struct gendisk *disk = dm_disk(md);
|
||||
struct dm_table *table;
|
||||
int srcu_idx;
|
||||
|
||||
param->flags &= ~(DM_SUSPEND_FLAG | DM_READONLY_FLAG |
|
||||
DM_ACTIVE_PRESENT_FLAG);
|
||||
|
|
@ -676,26 +695,27 @@ static void __dev_status(struct mapped_device *md, struct dm_ioctl *param)
|
|||
param->event_nr = dm_get_event_nr(md);
|
||||
param->target_count = 0;
|
||||
|
||||
table = dm_get_live_table(md);
|
||||
table = dm_get_live_table(md, &srcu_idx);
|
||||
if (table) {
|
||||
if (!(param->flags & DM_QUERY_INACTIVE_TABLE_FLAG)) {
|
||||
if (get_disk_ro(disk))
|
||||
param->flags |= DM_READONLY_FLAG;
|
||||
param->target_count = dm_table_get_num_targets(table);
|
||||
}
|
||||
dm_table_put(table);
|
||||
|
||||
param->flags |= DM_ACTIVE_PRESENT_FLAG;
|
||||
}
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
|
||||
if (param->flags & DM_QUERY_INACTIVE_TABLE_FLAG) {
|
||||
table = dm_get_inactive_table(md);
|
||||
int srcu_idx;
|
||||
table = dm_get_inactive_table(md, &srcu_idx);
|
||||
if (table) {
|
||||
if (!(dm_table_get_mode(table) & FMODE_WRITE))
|
||||
param->flags |= DM_READONLY_FLAG;
|
||||
param->target_count = dm_table_get_num_targets(table);
|
||||
dm_table_put(table);
|
||||
}
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -796,6 +816,7 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
|
|||
struct hash_cell *hc;
|
||||
struct mapped_device *md;
|
||||
int r;
|
||||
struct dm_table *t;
|
||||
|
||||
down_write(&_hash_lock);
|
||||
hc = __find_device_hash_cell(param);
|
||||
|
|
@ -819,9 +840,14 @@ static int dev_remove(struct dm_ioctl *param, size_t param_size)
|
|||
return r;
|
||||
}
|
||||
|
||||
__hash_remove(hc);
|
||||
t = __hash_remove(hc);
|
||||
up_write(&_hash_lock);
|
||||
|
||||
if (t) {
|
||||
dm_sync_table(md);
|
||||
dm_table_destroy(t);
|
||||
}
|
||||
|
||||
if (!dm_kobject_uevent(md, KOBJ_REMOVE, param->event_nr))
|
||||
param->flags |= DM_UEVENT_GENERATED_FLAG;
|
||||
|
||||
|
|
@ -986,6 +1012,7 @@ static int do_resume(struct dm_ioctl *param)
|
|||
|
||||
old_map = dm_swap_table(md, new_map);
|
||||
if (IS_ERR(old_map)) {
|
||||
dm_sync_table(md);
|
||||
dm_table_destroy(new_map);
|
||||
dm_put(md);
|
||||
return PTR_ERR(old_map);
|
||||
|
|
@ -1003,6 +1030,10 @@ static int do_resume(struct dm_ioctl *param)
|
|||
param->flags |= DM_UEVENT_GENERATED_FLAG;
|
||||
}
|
||||
|
||||
/*
|
||||
* Since dm_swap_table synchronizes RCU, nobody should be in
|
||||
* read-side critical section already.
|
||||
*/
|
||||
if (old_map)
|
||||
dm_table_destroy(old_map);
|
||||
|
||||
|
|
@ -1125,6 +1156,7 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size)
|
|||
int r = 0;
|
||||
struct mapped_device *md;
|
||||
struct dm_table *table;
|
||||
int srcu_idx;
|
||||
|
||||
md = find_device(param);
|
||||
if (!md)
|
||||
|
|
@ -1145,11 +1177,10 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size)
|
|||
*/
|
||||
__dev_status(md, param);
|
||||
|
||||
table = dm_get_live_or_inactive_table(md, param);
|
||||
if (table) {
|
||||
table = dm_get_live_or_inactive_table(md, param, &srcu_idx);
|
||||
if (table)
|
||||
retrieve_status(table, param, param_size);
|
||||
dm_table_put(table);
|
||||
}
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
|
||||
out:
|
||||
dm_put(md);
|
||||
|
|
@ -1221,7 +1252,7 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
|
|||
{
|
||||
int r;
|
||||
struct hash_cell *hc;
|
||||
struct dm_table *t;
|
||||
struct dm_table *t, *old_map = NULL;
|
||||
struct mapped_device *md;
|
||||
struct target_type *immutable_target_type;
|
||||
|
||||
|
|
@ -1277,14 +1308,14 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
|
|||
hc = dm_get_mdptr(md);
|
||||
if (!hc || hc->md != md) {
|
||||
DMWARN("device has been removed from the dev hash table.");
|
||||
dm_table_destroy(t);
|
||||
up_write(&_hash_lock);
|
||||
dm_table_destroy(t);
|
||||
r = -ENXIO;
|
||||
goto out;
|
||||
}
|
||||
|
||||
if (hc->new_map)
|
||||
dm_table_destroy(hc->new_map);
|
||||
old_map = hc->new_map;
|
||||
hc->new_map = t;
|
||||
up_write(&_hash_lock);
|
||||
|
||||
|
|
@ -1292,6 +1323,11 @@ static int table_load(struct dm_ioctl *param, size_t param_size)
|
|||
__dev_status(md, param);
|
||||
|
||||
out:
|
||||
if (old_map) {
|
||||
dm_sync_table(md);
|
||||
dm_table_destroy(old_map);
|
||||
}
|
||||
|
||||
dm_put(md);
|
||||
|
||||
return r;
|
||||
|
|
@ -1301,6 +1337,7 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
|
|||
{
|
||||
struct hash_cell *hc;
|
||||
struct mapped_device *md;
|
||||
struct dm_table *old_map = NULL;
|
||||
|
||||
down_write(&_hash_lock);
|
||||
|
||||
|
|
@ -1312,7 +1349,7 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
|
|||
}
|
||||
|
||||
if (hc->new_map) {
|
||||
dm_table_destroy(hc->new_map);
|
||||
old_map = hc->new_map;
|
||||
hc->new_map = NULL;
|
||||
}
|
||||
|
||||
|
|
@ -1321,6 +1358,10 @@ static int table_clear(struct dm_ioctl *param, size_t param_size)
|
|||
__dev_status(hc->md, param);
|
||||
md = hc->md;
|
||||
up_write(&_hash_lock);
|
||||
if (old_map) {
|
||||
dm_sync_table(md);
|
||||
dm_table_destroy(old_map);
|
||||
}
|
||||
dm_put(md);
|
||||
|
||||
return 0;
|
||||
|
|
@ -1370,6 +1411,7 @@ static int table_deps(struct dm_ioctl *param, size_t param_size)
|
|||
{
|
||||
struct mapped_device *md;
|
||||
struct dm_table *table;
|
||||
int srcu_idx;
|
||||
|
||||
md = find_device(param);
|
||||
if (!md)
|
||||
|
|
@ -1377,11 +1419,10 @@ static int table_deps(struct dm_ioctl *param, size_t param_size)
|
|||
|
||||
__dev_status(md, param);
|
||||
|
||||
table = dm_get_live_or_inactive_table(md, param);
|
||||
if (table) {
|
||||
table = dm_get_live_or_inactive_table(md, param, &srcu_idx);
|
||||
if (table)
|
||||
retrieve_deps(table, param, param_size);
|
||||
dm_table_put(table);
|
||||
}
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
|
||||
dm_put(md);
|
||||
|
||||
|
|
@ -1396,6 +1437,7 @@ static int table_status(struct dm_ioctl *param, size_t param_size)
|
|||
{
|
||||
struct mapped_device *md;
|
||||
struct dm_table *table;
|
||||
int srcu_idx;
|
||||
|
||||
md = find_device(param);
|
||||
if (!md)
|
||||
|
|
@ -1403,11 +1445,10 @@ static int table_status(struct dm_ioctl *param, size_t param_size)
|
|||
|
||||
__dev_status(md, param);
|
||||
|
||||
table = dm_get_live_or_inactive_table(md, param);
|
||||
if (table) {
|
||||
table = dm_get_live_or_inactive_table(md, param, &srcu_idx);
|
||||
if (table)
|
||||
retrieve_status(table, param, param_size);
|
||||
dm_table_put(table);
|
||||
}
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
|
||||
dm_put(md);
|
||||
|
||||
|
|
@ -1443,6 +1484,7 @@ static int target_message(struct dm_ioctl *param, size_t param_size)
|
|||
struct dm_target_msg *tmsg = (void *) param + param->data_start;
|
||||
size_t maxlen;
|
||||
char *result = get_result_buffer(param, param_size, &maxlen);
|
||||
int srcu_idx;
|
||||
|
||||
md = find_device(param);
|
||||
if (!md)
|
||||
|
|
@ -1470,9 +1512,9 @@ static int target_message(struct dm_ioctl *param, size_t param_size)
|
|||
if (r <= 1)
|
||||
goto out_argv;
|
||||
|
||||
table = dm_get_live_table(md);
|
||||
table = dm_get_live_table(md, &srcu_idx);
|
||||
if (!table)
|
||||
goto out_argv;
|
||||
goto out_table;
|
||||
|
||||
if (dm_deleting_md(md)) {
|
||||
r = -ENXIO;
|
||||
|
|
@ -1491,7 +1533,7 @@ static int target_message(struct dm_ioctl *param, size_t param_size)
|
|||
}
|
||||
|
||||
out_table:
|
||||
dm_table_put(table);
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
out_argv:
|
||||
kfree(argv);
|
||||
out:
|
||||
|
|
|
|||
|
|
@ -26,22 +26,8 @@
|
|||
#define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
|
||||
#define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
|
||||
|
||||
/*
|
||||
* The table has always exactly one reference from either mapped_device->map
|
||||
* or hash_cell->new_map. This reference is not counted in table->holders.
|
||||
* A pair of dm_create_table/dm_destroy_table functions is used for table
|
||||
* creation/destruction.
|
||||
*
|
||||
* Temporary references from the other code increase table->holders. A pair
|
||||
* of dm_table_get/dm_table_put functions is used to manipulate it.
|
||||
*
|
||||
* When the table is about to be destroyed, we wait for table->holders to
|
||||
* drop to zero.
|
||||
*/
|
||||
|
||||
struct dm_table {
|
||||
struct mapped_device *md;
|
||||
atomic_t holders;
|
||||
unsigned type;
|
||||
|
||||
/* btree table */
|
||||
|
|
@ -208,7 +194,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
|
|||
|
||||
INIT_LIST_HEAD(&t->devices);
|
||||
INIT_LIST_HEAD(&t->target_callbacks);
|
||||
atomic_set(&t->holders, 0);
|
||||
|
||||
if (!num_targets)
|
||||
num_targets = KEYS_PER_NODE;
|
||||
|
|
@ -246,10 +231,6 @@ void dm_table_destroy(struct dm_table *t)
|
|||
if (!t)
|
||||
return;
|
||||
|
||||
while (atomic_read(&t->holders))
|
||||
msleep(1);
|
||||
smp_mb();
|
||||
|
||||
/* free the indexes */
|
||||
if (t->depth >= 2)
|
||||
vfree(t->index[t->depth - 2]);
|
||||
|
|
@ -274,22 +255,6 @@ void dm_table_destroy(struct dm_table *t)
|
|||
kfree(t);
|
||||
}
|
||||
|
||||
void dm_table_get(struct dm_table *t)
|
||||
{
|
||||
atomic_inc(&t->holders);
|
||||
}
|
||||
EXPORT_SYMBOL(dm_table_get);
|
||||
|
||||
void dm_table_put(struct dm_table *t)
|
||||
{
|
||||
if (!t)
|
||||
return;
|
||||
|
||||
smp_mb__before_atomic_dec();
|
||||
atomic_dec(&t->holders);
|
||||
}
|
||||
EXPORT_SYMBOL(dm_table_put);
|
||||
|
||||
/*
|
||||
* Checks to see if we need to extend highs or targets.
|
||||
*/
|
||||
|
|
|
|||
160
drivers/md/dm.c
160
drivers/md/dm.c
|
|
@ -116,13 +116,20 @@ EXPORT_SYMBOL_GPL(dm_get_rq_mapinfo);
|
|||
#define DMF_NOFLUSH_SUSPENDING 5
|
||||
#define DMF_MERGE_IS_OPTIONAL 6
|
||||
|
||||
/*
|
||||
* A dummy definition to make RCU happy.
|
||||
* struct dm_table should never be dereferenced in this file.
|
||||
*/
|
||||
struct dm_table {
|
||||
int undefined__;
|
||||
};
|
||||
|
||||
/*
|
||||
* Work processed by per-device workqueue.
|
||||
*/
|
||||
struct mapped_device {
|
||||
struct rw_semaphore io_lock;
|
||||
struct srcu_struct io_barrier;
|
||||
struct mutex suspend_lock;
|
||||
rwlock_t map_lock;
|
||||
atomic_t holders;
|
||||
atomic_t open_count;
|
||||
|
||||
|
|
@ -156,6 +163,8 @@ struct mapped_device {
|
|||
|
||||
/*
|
||||
* The current mapping.
|
||||
* Use dm_get_live_table{_fast} or take suspend_lock for
|
||||
* dereference.
|
||||
*/
|
||||
struct dm_table *map;
|
||||
|
||||
|
|
@ -386,12 +395,14 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
|
|||
unsigned int cmd, unsigned long arg)
|
||||
{
|
||||
struct mapped_device *md = bdev->bd_disk->private_data;
|
||||
int srcu_idx;
|
||||
struct dm_table *map;
|
||||
struct dm_target *tgt;
|
||||
int r = -ENOTTY;
|
||||
|
||||
retry:
|
||||
map = dm_get_live_table(md);
|
||||
map = dm_get_live_table(md, &srcu_idx);
|
||||
|
||||
if (!map || !dm_table_get_size(map))
|
||||
goto out;
|
||||
|
||||
|
|
@ -410,7 +421,7 @@ retry:
|
|||
r = tgt->type->ioctl(tgt, cmd, arg);
|
||||
|
||||
out:
|
||||
dm_table_put(map);
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
|
||||
if (r == -ENOTCONN) {
|
||||
msleep(10);
|
||||
|
|
@ -509,20 +520,39 @@ static void queue_io(struct mapped_device *md, struct bio *bio)
|
|||
/*
|
||||
* Everyone (including functions in this file), should use this
|
||||
* function to access the md->map field, and make sure they call
|
||||
* dm_table_put() when finished.
|
||||
* dm_put_live_table() when finished.
|
||||
*/
|
||||
struct dm_table *dm_get_live_table(struct mapped_device *md)
|
||||
struct dm_table *dm_get_live_table(struct mapped_device *md, int *srcu_idx) __acquires(md->io_barrier)
|
||||
{
|
||||
struct dm_table *t;
|
||||
unsigned long flags;
|
||||
*srcu_idx = srcu_read_lock(&md->io_barrier);
|
||||
|
||||
read_lock_irqsave(&md->map_lock, flags);
|
||||
t = md->map;
|
||||
if (t)
|
||||
dm_table_get(t);
|
||||
read_unlock_irqrestore(&md->map_lock, flags);
|
||||
return srcu_dereference(md->map, &md->io_barrier);
|
||||
}
|
||||
|
||||
return t;
|
||||
void dm_put_live_table(struct mapped_device *md, int srcu_idx) __releases(md->io_barrier)
|
||||
{
|
||||
srcu_read_unlock(&md->io_barrier, srcu_idx);
|
||||
}
|
||||
|
||||
void dm_sync_table(struct mapped_device *md)
|
||||
{
|
||||
synchronize_srcu(&md->io_barrier);
|
||||
synchronize_rcu_expedited();
|
||||
}
|
||||
|
||||
/*
|
||||
* A fast alternative to dm_get_live_table/dm_put_live_table.
|
||||
* The caller must not block between these two functions.
|
||||
*/
|
||||
static struct dm_table *dm_get_live_table_fast(struct mapped_device *md) __acquires(RCU)
|
||||
{
|
||||
rcu_read_lock();
|
||||
return rcu_dereference(md->map);
|
||||
}
|
||||
|
||||
static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
|
||||
{
|
||||
rcu_read_unlock();
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1356,17 +1386,18 @@ static int __split_and_process_non_flush(struct clone_info *ci)
|
|||
/*
|
||||
* Entry point to split a bio into clones and submit them to the targets.
|
||||
*/
|
||||
static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
|
||||
static void __split_and_process_bio(struct mapped_device *md,
|
||||
struct dm_table *map, struct bio *bio)
|
||||
{
|
||||
struct clone_info ci;
|
||||
int error = 0;
|
||||
|
||||
ci.map = dm_get_live_table(md);
|
||||
if (unlikely(!ci.map)) {
|
||||
if (unlikely(!map)) {
|
||||
bio_io_error(bio);
|
||||
return;
|
||||
}
|
||||
|
||||
ci.map = map;
|
||||
ci.md = md;
|
||||
ci.io = alloc_io(md);
|
||||
ci.io->error = 0;
|
||||
|
|
@ -1393,7 +1424,6 @@ static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
|
|||
|
||||
/* drop the extra reference count */
|
||||
dec_pending(ci.io, error);
|
||||
dm_table_put(ci.map);
|
||||
}
|
||||
/*-----------------------------------------------------------------
|
||||
* CRUD END
|
||||
|
|
@ -1404,7 +1434,7 @@ static int dm_merge_bvec(struct request_queue *q,
|
|||
struct bio_vec *biovec)
|
||||
{
|
||||
struct mapped_device *md = q->queuedata;
|
||||
struct dm_table *map = dm_get_live_table(md);
|
||||
struct dm_table *map = dm_get_live_table_fast(md);
|
||||
struct dm_target *ti;
|
||||
sector_t max_sectors;
|
||||
int max_size = 0;
|
||||
|
|
@ -1414,7 +1444,7 @@ static int dm_merge_bvec(struct request_queue *q,
|
|||
|
||||
ti = dm_table_find_target(map, bvm->bi_sector);
|
||||
if (!dm_target_is_valid(ti))
|
||||
goto out_table;
|
||||
goto out;
|
||||
|
||||
/*
|
||||
* Find maximum amount of I/O that won't need splitting
|
||||
|
|
@ -1443,10 +1473,8 @@ static int dm_merge_bvec(struct request_queue *q,
|
|||
|
||||
max_size = 0;
|
||||
|
||||
out_table:
|
||||
dm_table_put(map);
|
||||
|
||||
out:
|
||||
dm_put_live_table_fast(md);
|
||||
/*
|
||||
* Always allow an entire first page
|
||||
*/
|
||||
|
|
@ -1465,8 +1493,10 @@ static void _dm_request(struct request_queue *q, struct bio *bio)
|
|||
int rw = bio_data_dir(bio);
|
||||
struct mapped_device *md = q->queuedata;
|
||||
int cpu;
|
||||
int srcu_idx;
|
||||
struct dm_table *map;
|
||||
|
||||
down_read(&md->io_lock);
|
||||
map = dm_get_live_table(md, &srcu_idx);
|
||||
|
||||
cpu = part_stat_lock();
|
||||
part_stat_inc(cpu, &dm_disk(md)->part0, ios[rw]);
|
||||
|
|
@ -1475,7 +1505,7 @@ static void _dm_request(struct request_queue *q, struct bio *bio)
|
|||
|
||||
/* if we're suspended, we have to queue this io for later */
|
||||
if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
|
||||
up_read(&md->io_lock);
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
|
||||
if (bio_rw(bio) != READA)
|
||||
queue_io(md, bio);
|
||||
|
|
@ -1484,8 +1514,8 @@ static void _dm_request(struct request_queue *q, struct bio *bio)
|
|||
return;
|
||||
}
|
||||
|
||||
__split_and_process_bio(md, bio);
|
||||
up_read(&md->io_lock);
|
||||
__split_and_process_bio(md, map, bio);
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
return;
|
||||
}
|
||||
|
||||
|
|
@ -1671,7 +1701,8 @@ static struct request *dm_start_request(struct mapped_device *md, struct request
|
|||
static void dm_request_fn(struct request_queue *q)
|
||||
{
|
||||
struct mapped_device *md = q->queuedata;
|
||||
struct dm_table *map = dm_get_live_table(md);
|
||||
int srcu_idx;
|
||||
struct dm_table *map = dm_get_live_table(md, &srcu_idx);
|
||||
struct dm_target *ti;
|
||||
struct request *rq, *clone;
|
||||
sector_t pos;
|
||||
|
|
@ -1726,7 +1757,7 @@ requeued:
|
|||
delay_and_out:
|
||||
blk_delay_queue(q, HZ / 10);
|
||||
out:
|
||||
dm_table_put(map);
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
}
|
||||
|
||||
int dm_underlying_device_busy(struct request_queue *q)
|
||||
|
|
@ -1739,14 +1770,14 @@ static int dm_lld_busy(struct request_queue *q)
|
|||
{
|
||||
int r;
|
||||
struct mapped_device *md = q->queuedata;
|
||||
struct dm_table *map = dm_get_live_table(md);
|
||||
struct dm_table *map = dm_get_live_table_fast(md);
|
||||
|
||||
if (!map || test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))
|
||||
r = 1;
|
||||
else
|
||||
r = dm_table_any_busy_target(map);
|
||||
|
||||
dm_table_put(map);
|
||||
dm_put_live_table_fast(md);
|
||||
|
||||
return r;
|
||||
}
|
||||
|
|
@ -1758,7 +1789,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
|
|||
struct dm_table *map;
|
||||
|
||||
if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
|
||||
map = dm_get_live_table(md);
|
||||
map = dm_get_live_table_fast(md);
|
||||
if (map) {
|
||||
/*
|
||||
* Request-based dm cares about only own queue for
|
||||
|
|
@ -1769,9 +1800,8 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
|
|||
bdi_bits;
|
||||
else
|
||||
r = dm_table_any_congested(map, bdi_bits);
|
||||
|
||||
dm_table_put(map);
|
||||
}
|
||||
dm_put_live_table_fast(md);
|
||||
}
|
||||
|
||||
return r;
|
||||
|
|
@ -1876,12 +1906,14 @@ static struct mapped_device *alloc_dev(int minor)
|
|||
if (r < 0)
|
||||
goto bad_minor;
|
||||
|
||||
r = init_srcu_struct(&md->io_barrier);
|
||||
if (r < 0)
|
||||
goto bad_io_barrier;
|
||||
|
||||
md->type = DM_TYPE_NONE;
|
||||
init_rwsem(&md->io_lock);
|
||||
mutex_init(&md->suspend_lock);
|
||||
mutex_init(&md->type_lock);
|
||||
spin_lock_init(&md->deferred_lock);
|
||||
rwlock_init(&md->map_lock);
|
||||
atomic_set(&md->holders, 1);
|
||||
atomic_set(&md->open_count, 0);
|
||||
atomic_set(&md->event_nr, 0);
|
||||
|
|
@ -1944,6 +1976,8 @@ bad_thread:
|
|||
bad_disk:
|
||||
blk_cleanup_queue(md->queue);
|
||||
bad_queue:
|
||||
cleanup_srcu_struct(&md->io_barrier);
|
||||
bad_io_barrier:
|
||||
free_minor(minor);
|
||||
bad_minor:
|
||||
module_put(THIS_MODULE);
|
||||
|
|
@ -1967,6 +2001,7 @@ static void free_dev(struct mapped_device *md)
|
|||
bioset_free(md->bs);
|
||||
blk_integrity_unregister(md->disk);
|
||||
del_gendisk(md->disk);
|
||||
cleanup_srcu_struct(&md->io_barrier);
|
||||
free_minor(minor);
|
||||
|
||||
spin_lock(&_minor_lock);
|
||||
|
|
@ -2109,7 +2144,6 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
|
|||
struct dm_table *old_map;
|
||||
struct request_queue *q = md->queue;
|
||||
sector_t size;
|
||||
unsigned long flags;
|
||||
int merge_is_optional;
|
||||
|
||||
size = dm_table_get_size(t);
|
||||
|
|
@ -2138,9 +2172,8 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
|
|||
|
||||
merge_is_optional = dm_table_merge_is_optional(t);
|
||||
|
||||
write_lock_irqsave(&md->map_lock, flags);
|
||||
old_map = md->map;
|
||||
md->map = t;
|
||||
rcu_assign_pointer(md->map, t);
|
||||
md->immutable_target_type = dm_table_get_immutable_target_type(t);
|
||||
|
||||
dm_table_set_restrictions(t, q, limits);
|
||||
|
|
@ -2148,7 +2181,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
|
|||
set_bit(DMF_MERGE_IS_OPTIONAL, &md->flags);
|
||||
else
|
||||
clear_bit(DMF_MERGE_IS_OPTIONAL, &md->flags);
|
||||
write_unlock_irqrestore(&md->map_lock, flags);
|
||||
dm_sync_table(md);
|
||||
|
||||
return old_map;
|
||||
}
|
||||
|
|
@ -2159,15 +2192,13 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
|
|||
static struct dm_table *__unbind(struct mapped_device *md)
|
||||
{
|
||||
struct dm_table *map = md->map;
|
||||
unsigned long flags;
|
||||
|
||||
if (!map)
|
||||
return NULL;
|
||||
|
||||
dm_table_event_callback(map, NULL, NULL);
|
||||
write_lock_irqsave(&md->map_lock, flags);
|
||||
md->map = NULL;
|
||||
write_unlock_irqrestore(&md->map_lock, flags);
|
||||
rcu_assign_pointer(md->map, NULL);
|
||||
dm_sync_table(md);
|
||||
|
||||
return map;
|
||||
}
|
||||
|
|
@ -2319,11 +2350,12 @@ EXPORT_SYMBOL_GPL(dm_device_name);
|
|||
static void __dm_destroy(struct mapped_device *md, bool wait)
|
||||
{
|
||||
struct dm_table *map;
|
||||
int srcu_idx;
|
||||
|
||||
might_sleep();
|
||||
|
||||
spin_lock(&_minor_lock);
|
||||
map = dm_get_live_table(md);
|
||||
map = dm_get_live_table(md, &srcu_idx);
|
||||
idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md))));
|
||||
set_bit(DMF_FREEING, &md->flags);
|
||||
spin_unlock(&_minor_lock);
|
||||
|
|
@ -2333,6 +2365,9 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
|
|||
dm_table_postsuspend_targets(map);
|
||||
}
|
||||
|
||||
/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
|
||||
/*
|
||||
* Rare, but there may be I/O requests still going to complete,
|
||||
* for example. Wait for all references to disappear.
|
||||
|
|
@ -2347,7 +2382,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
|
|||
dm_device_name(md), atomic_read(&md->holders));
|
||||
|
||||
dm_sysfs_exit(md);
|
||||
dm_table_put(map);
|
||||
dm_table_destroy(__unbind(md));
|
||||
free_dev(md);
|
||||
}
|
||||
|
|
@ -2404,8 +2438,10 @@ static void dm_wq_work(struct work_struct *work)
|
|||
struct mapped_device *md = container_of(work, struct mapped_device,
|
||||
work);
|
||||
struct bio *c;
|
||||
int srcu_idx;
|
||||
struct dm_table *map;
|
||||
|
||||
down_read(&md->io_lock);
|
||||
map = dm_get_live_table(md, &srcu_idx);
|
||||
|
||||
while (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
|
||||
spin_lock_irq(&md->deferred_lock);
|
||||
|
|
@ -2415,17 +2451,13 @@ static void dm_wq_work(struct work_struct *work)
|
|||
if (!c)
|
||||
break;
|
||||
|
||||
up_read(&md->io_lock);
|
||||
|
||||
if (dm_request_based(md))
|
||||
generic_make_request(c);
|
||||
else
|
||||
__split_and_process_bio(md, c);
|
||||
|
||||
down_read(&md->io_lock);
|
||||
__split_and_process_bio(md, map, c);
|
||||
}
|
||||
|
||||
up_read(&md->io_lock);
|
||||
dm_put_live_table(md, srcu_idx);
|
||||
}
|
||||
|
||||
static void dm_queue_flush(struct mapped_device *md)
|
||||
|
|
@ -2457,10 +2489,10 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
|
|||
* reappear.
|
||||
*/
|
||||
if (dm_table_has_no_data_devices(table)) {
|
||||
live_map = dm_get_live_table(md);
|
||||
live_map = dm_get_live_table_fast(md);
|
||||
if (live_map)
|
||||
limits = md->queue->limits;
|
||||
dm_table_put(live_map);
|
||||
dm_put_live_table_fast(md);
|
||||
}
|
||||
|
||||
if (!live_map) {
|
||||
|
|
@ -2540,7 +2572,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
|
|||
goto out_unlock;
|
||||
}
|
||||
|
||||
map = dm_get_live_table(md);
|
||||
map = md->map;
|
||||
|
||||
/*
|
||||
* DMF_NOFLUSH_SUSPENDING must be set before presuspend.
|
||||
|
|
@ -2561,7 +2593,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
|
|||
if (!noflush && do_lockfs) {
|
||||
r = lock_fs(md);
|
||||
if (r)
|
||||
goto out;
|
||||
goto out_unlock;
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -2576,9 +2608,8 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
|
|||
* (dm_wq_work), we set BMF_BLOCK_IO_FOR_SUSPEND and call
|
||||
* flush_workqueue(md->wq).
|
||||
*/
|
||||
down_write(&md->io_lock);
|
||||
set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
|
||||
up_write(&md->io_lock);
|
||||
synchronize_srcu(&md->io_barrier);
|
||||
|
||||
/*
|
||||
* Stop md->queue before flushing md->wq in case request-based
|
||||
|
|
@ -2596,10 +2627,9 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
|
|||
*/
|
||||
r = dm_wait_for_completion(md, TASK_INTERRUPTIBLE);
|
||||
|
||||
down_write(&md->io_lock);
|
||||
if (noflush)
|
||||
clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
|
||||
up_write(&md->io_lock);
|
||||
synchronize_srcu(&md->io_barrier);
|
||||
|
||||
/* were we interrupted ? */
|
||||
if (r < 0) {
|
||||
|
|
@ -2609,7 +2639,7 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
|
|||
start_queue(md->queue);
|
||||
|
||||
unlock_fs(md);
|
||||
goto out; /* pushback list is already flushed, so skip flush */
|
||||
goto out_unlock; /* pushback list is already flushed, so skip flush */
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -2622,9 +2652,6 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
|
|||
|
||||
dm_table_postsuspend_targets(map);
|
||||
|
||||
out:
|
||||
dm_table_put(map);
|
||||
|
||||
out_unlock:
|
||||
mutex_unlock(&md->suspend_lock);
|
||||
return r;
|
||||
|
|
@ -2639,7 +2666,7 @@ int dm_resume(struct mapped_device *md)
|
|||
if (!dm_suspended_md(md))
|
||||
goto out;
|
||||
|
||||
map = dm_get_live_table(md);
|
||||
map = md->map;
|
||||
if (!map || !dm_table_get_size(map))
|
||||
goto out;
|
||||
|
||||
|
|
@ -2663,7 +2690,6 @@ int dm_resume(struct mapped_device *md)
|
|||
|
||||
r = 0;
|
||||
out:
|
||||
dm_table_put(map);
|
||||
mutex_unlock(&md->suspend_lock);
|
||||
|
||||
return r;
|
||||
|
|
|
|||
|
|
@ -446,9 +446,9 @@ int __must_check dm_set_target_max_io_len(struct dm_target *ti, sector_t len);
|
|||
/*
|
||||
* Table reference counting.
|
||||
*/
|
||||
struct dm_table *dm_get_live_table(struct mapped_device *md);
|
||||
void dm_table_get(struct dm_table *t);
|
||||
void dm_table_put(struct dm_table *t);
|
||||
struct dm_table *dm_get_live_table(struct mapped_device *md, int *srcu_idx);
|
||||
void dm_put_live_table(struct mapped_device *md, int srcu_idx);
|
||||
void dm_sync_table(struct mapped_device *md);
|
||||
|
||||
/*
|
||||
* Queries
|
||||
|
|
|
|||
|
|
@ -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 24
|
||||
#define DM_VERSION_MINOR 25
|
||||
#define DM_VERSION_PATCHLEVEL 0
|
||||
#define DM_VERSION_EXTRA "-ioctl (2013-01-15)"
|
||||
#define DM_VERSION_EXTRA "-ioctl (2013-06-26)"
|
||||
|
||||
/* Status bits */
|
||||
#define DM_READONLY_FLAG (1 << 0) /* In/Out */
|
||||
|
|
|
|||
Loading…
Reference in New Issue