summaryrefslogtreecommitdiffstats
path: root/drivers/md/persistent-data
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/persistent-data')
-rw-r--r--drivers/md/persistent-data/Kconfig10
-rw-r--r--drivers/md/persistent-data/dm-bitset.c10
-rw-r--r--drivers/md/persistent-data/dm-bitset.h1
-rw-r--r--drivers/md/persistent-data/dm-block-manager.c15
-rw-r--r--drivers/md/persistent-data/dm-block-manager.h3
-rw-r--r--drivers/md/persistent-data/dm-space-map-metadata.c115
-rw-r--r--drivers/md/persistent-data/dm-space-map-metadata.h11
-rw-r--r--drivers/md/persistent-data/dm-transaction-manager.c5
-rw-r--r--drivers/md/persistent-data/dm-transaction-manager.h17
9 files changed, 139 insertions, 48 deletions
diff --git a/drivers/md/persistent-data/Kconfig b/drivers/md/persistent-data/Kconfig
index 19b26879541..0c2dec7aec2 100644
--- a/drivers/md/persistent-data/Kconfig
+++ b/drivers/md/persistent-data/Kconfig
@@ -6,3 +6,13 @@ config DM_PERSISTENT_DATA
---help---
Library providing immutable on-disk data structure support for
device-mapper targets such as the thin provisioning target.
+
+config DM_DEBUG_BLOCK_STACK_TRACING
+ boolean "Keep stack trace of persistent data block lock holders"
+ depends on STACKTRACE_SUPPORT && DM_PERSISTENT_DATA
+ select STACKTRACE
+ ---help---
+ Enable this for messages that may help debug problems with the
+ block manager locking used by thin provisioning and caching.
+
+ If unsure, say N.
diff --git a/drivers/md/persistent-data/dm-bitset.c b/drivers/md/persistent-data/dm-bitset.c
index cd9a86d4cdf..36f7cc2c710 100644
--- a/drivers/md/persistent-data/dm-bitset.c
+++ b/drivers/md/persistent-data/dm-bitset.c
@@ -65,7 +65,7 @@ int dm_bitset_flush(struct dm_disk_bitset *info, dm_block_t root,
int r;
__le64 value;
- if (!info->current_index_set)
+ if (!info->current_index_set || !info->dirty)
return 0;
value = cpu_to_le64(info->current_bits);
@@ -77,6 +77,8 @@ int dm_bitset_flush(struct dm_disk_bitset *info, dm_block_t root,
return r;
info->current_index_set = false;
+ info->dirty = false;
+
return 0;
}
EXPORT_SYMBOL_GPL(dm_bitset_flush);
@@ -94,6 +96,8 @@ static int read_bits(struct dm_disk_bitset *info, dm_block_t root,
info->current_bits = le64_to_cpu(value);
info->current_index_set = true;
info->current_index = array_index;
+ info->dirty = false;
+
return 0;
}
@@ -126,6 +130,8 @@ int dm_bitset_set_bit(struct dm_disk_bitset *info, dm_block_t root,
return r;
set_bit(b, (unsigned long *) &info->current_bits);
+ info->dirty = true;
+
return 0;
}
EXPORT_SYMBOL_GPL(dm_bitset_set_bit);
@@ -141,6 +147,8 @@ int dm_bitset_clear_bit(struct dm_disk_bitset *info, dm_block_t root,
return r;
clear_bit(b, (unsigned long *) &info->current_bits);
+ info->dirty = true;
+
return 0;
}
EXPORT_SYMBOL_GPL(dm_bitset_clear_bit);
diff --git a/drivers/md/persistent-data/dm-bitset.h b/drivers/md/persistent-data/dm-bitset.h
index e1b9bea14aa..c2287d672ef 100644
--- a/drivers/md/persistent-data/dm-bitset.h
+++ b/drivers/md/persistent-data/dm-bitset.h
@@ -71,6 +71,7 @@ struct dm_disk_bitset {
uint64_t current_bits;
bool current_index_set:1;
+ bool dirty:1;
};
/*
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 455f79279a1..087411c95ff 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -595,25 +595,14 @@ int dm_bm_unlock(struct dm_block *b)
}
EXPORT_SYMBOL_GPL(dm_bm_unlock);
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
- struct dm_block *superblock)
+int dm_bm_flush(struct dm_block_manager *bm)
{
- int r;
-
if (bm->read_only)
return -EPERM;
- r = dm_bufio_write_dirty_buffers(bm->bufio);
- if (unlikely(r)) {
- dm_bm_unlock(superblock);
- return r;
- }
-
- dm_bm_unlock(superblock);
-
return dm_bufio_write_dirty_buffers(bm->bufio);
}
-EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock);
+EXPORT_SYMBOL_GPL(dm_bm_flush);
void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b)
{
diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h
index 13cd58e1fe6..1b95dfc1778 100644
--- a/drivers/md/persistent-data/dm-block-manager.h
+++ b/drivers/md/persistent-data/dm-block-manager.h
@@ -105,8 +105,7 @@ int dm_bm_unlock(struct dm_block *b);
*
* This method always blocks.
*/
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
- struct dm_block *superblock);
+int dm_bm_flush(struct dm_block_manager *bm);
/*
* Request data is prefetched into the cache.
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
index 536782e3bcb..786b689bdfc 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -91,6 +91,69 @@ struct block_op {
dm_block_t block;
};
+struct bop_ring_buffer {
+ unsigned begin;
+ unsigned end;
+ struct block_op bops[MAX_RECURSIVE_ALLOCATIONS + 1];
+};
+
+static void brb_init(struct bop_ring_buffer *brb)
+{
+ brb->begin = 0;
+ brb->end = 0;
+}
+
+static bool brb_empty(struct bop_ring_buffer *brb)
+{
+ return brb->begin == brb->end;
+}
+
+static unsigned brb_next(struct bop_ring_buffer *brb, unsigned old)
+{
+ unsigned r = old + 1;
+ return (r >= (sizeof(brb->bops) / sizeof(*brb->bops))) ? 0 : r;
+}
+
+static int brb_push(struct bop_ring_buffer *brb,
+ enum block_op_type type, dm_block_t b)
+{
+ struct block_op *bop;
+ unsigned next = brb_next(brb, brb->end);
+
+ /*
+ * We don't allow the last bop to be filled, this way we can
+ * differentiate between full and empty.
+ */
+ if (next == brb->begin)
+ return -ENOMEM;
+
+ bop = brb->bops + brb->end;
+ bop->type = type;
+ bop->block = b;
+
+ brb->end = next;
+
+ return 0;
+}
+
+static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
+{
+ struct block_op *bop;
+
+ if (brb_empty(brb))
+ return -ENODATA;
+
+ bop = brb->bops + brb->begin;
+ result->type = bop->type;
+ result->block = bop->block;
+
+ brb->begin = brb_next(brb, brb->begin);
+
+ return 0;
+}
+
+/*----------------------------------------------------------------*/
+
struct sm_metadata {
struct dm_space_map sm;
@@ -101,25 +164,20 @@ struct sm_metadata {
unsigned recursion_count;
unsigned allocated_this_transaction;
- unsigned nr_uncommitted;
- struct block_op uncommitted[MAX_RECURSIVE_ALLOCATIONS];
+ struct bop_ring_buffer uncommitted;
struct threshold threshold;
};
static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b)
{
- struct block_op *op;
+ int r = brb_push(&smm->uncommitted, type, b);
- if (smm->nr_uncommitted == MAX_RECURSIVE_ALLOCATIONS) {
+ if (r) {
DMERR("too many recursive allocations");
return -ENOMEM;
}
- op = smm->uncommitted + smm->nr_uncommitted++;
- op->type = type;
- op->block = b;
-
return 0;
}
@@ -158,11 +216,17 @@ static int out(struct sm_metadata *smm)
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 (smm->recursion_count == 1) {
+ while (!brb_empty(&smm->uncommitted)) {
+ struct block_op bop;
+
+ r = brb_pop(&smm->uncommitted, &bop);
+ if (r) {
+ DMERR("bug in bop ring buffer");
+ break;
+ }
+
+ r = commit_bop(smm, &bop);
if (r)
break;
}
@@ -217,7 +281,8 @@ static int sm_metadata_get_nr_free(struct dm_space_map *sm, dm_block_t *count)
static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b,
uint32_t *result)
{
- int r, i;
+ int r;
+ unsigned i;
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
unsigned adjustment = 0;
@@ -225,8 +290,10 @@ static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b,
* 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;
+ for (i = smm->uncommitted.begin;
+ i != smm->uncommitted.end;
+ i = brb_next(&smm->uncommitted, i)) {
+ struct block_op *op = smm->uncommitted.bops + i;
if (op->block != b)
continue;
@@ -254,7 +321,8 @@ static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b,
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;
+ int r, adjustment = 0;
+ unsigned i;
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
uint32_t rc;
@@ -262,8 +330,11 @@ static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm,
* 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;
+ for (i = smm->uncommitted.begin;
+ i != smm->uncommitted.end;
+ i = brb_next(&smm->uncommitted, i)) {
+
+ struct block_op *op = smm->uncommitted.bops + i;
if (op->block != b)
continue;
@@ -671,7 +742,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
smm->begin = superblock + 1;
smm->recursion_count = 0;
smm->allocated_this_transaction = 0;
- smm->nr_uncommitted = 0;
+ brb_init(&smm->uncommitted);
threshold_init(&smm->threshold);
memcpy(&smm->sm, &bootstrap_ops, sizeof(smm->sm));
@@ -680,6 +751,8 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
if (r)
return r;
+ if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS)
+ nr_blocks = DM_SM_METADATA_MAX_BLOCKS;
r = sm_ll_extend(&smm->ll, nr_blocks);
if (r)
return r;
@@ -713,7 +786,7 @@ int dm_sm_metadata_open(struct dm_space_map *sm,
smm->begin = 0;
smm->recursion_count = 0;
smm->allocated_this_transaction = 0;
- smm->nr_uncommitted = 0;
+ brb_init(&smm->uncommitted);
threshold_init(&smm->threshold);
memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll));
diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h
index 39bba0801cf..64df923974d 100644
--- a/drivers/md/persistent-data/dm-space-map-metadata.h
+++ b/drivers/md/persistent-data/dm-space-map-metadata.h
@@ -9,6 +9,17 @@
#include "dm-transaction-manager.h"
+#define DM_SM_METADATA_BLOCK_SIZE (4096 >> SECTOR_SHIFT)
+
+/*
+ * The metadata device is currently limited in size.
+ *
+ * We have one block of index, which can hold 255 index entries. Each
+ * index entry contains allocation info about ~16k metadata blocks.
+ */
+#define DM_SM_METADATA_MAX_BLOCKS (255 * ((1 << 14) - 64))
+#define DM_SM_METADATA_MAX_SECTORS (DM_SM_METADATA_MAX_BLOCKS * DM_SM_METADATA_BLOCK_SIZE)
+
/*
* Unfortunately we have to use two-phase construction due to the cycle
* between the tm and sm.
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index 81da1a26042..3bc30a0ae3d 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -154,7 +154,7 @@ int dm_tm_pre_commit(struct dm_transaction_manager *tm)
if (r < 0)
return r;
- return 0;
+ return dm_bm_flush(tm->bm);
}
EXPORT_SYMBOL_GPL(dm_tm_pre_commit);
@@ -164,8 +164,9 @@ int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root)
return -EWOULDBLOCK;
wipe_shadow_table(tm);
+ dm_bm_unlock(root);
- return dm_bm_flush_and_unlock(tm->bm, root);
+ return dm_bm_flush(tm->bm);
}
EXPORT_SYMBOL_GPL(dm_tm_commit);
diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h
index b5b139076ca..2772ed2a781 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.h
+++ b/drivers/md/persistent-data/dm-transaction-manager.h
@@ -38,18 +38,17 @@ struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transac
/*
* 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.
+ * i) Make all changes for the transaction *except* for the superblock.
+ * Then call dm_tm_pre_commit() to flush them to disk.
*
- * 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.
+ * ii) Lock your superblock. Update. Then call dm_tm_commit() which will
+ * unlock the superblock and flush it. No other blocks should be updated
+ * during this period. Care should be taken to never unlock a partially
+ * updated superblock; perform any operations that could fail *before* you
+ * take the superblock lock.
*/
int dm_tm_pre_commit(struct dm_transaction_manager *tm);
-int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root);
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *superblock);
/*
* These methods are the only way to get hold of a writeable block.