Five stable fixes:

- Two DM btree bufio buffer leak fixes that resolve reported BUG_ONs
   during DM thinp metadata close's dm_bufio_client_destroy().
 
 - A DM thinp range discard fix to handle discarding a partially mapped
   range.
 
 - A DM thinp metadata snapshot fix to make sure the btree roots saved in
   the metadata snapshot are the most current.
 
 - A DM space map metadata refcounting fix that improves both DM thinp
   and DM cache metadata.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEbBAABAgAGBQJWaufCAAoJEMUj8QotnQNa4EQH93vh356VNEug+6iDpsIgRvpI
 loKaQMJOqkSfByoHuY1fRhsKKgaBsf3Nzb+u1wv/jEI2+MgNWkAWRHa0FAFBevLE
 Hk7cB5KV44NCsiB1QwOdr6OpSuZPQ2XZrrMfieLC5kxwNeP/9GslY5x+EHUHqfTj
 lTJljCBjBCG0J+8HK4BTNzqi2t5pH/Aurzzz3+uWyplC/uGa0eNobaMxM83P8Izx
 fx17rf72qAA9KcjKgyuAnwxom2mZGt5b8Jd8Btz0oK0hs3pOloJzsF9jOrSSBydF
 edvitDdLWyo3lXys04C51bMZFzzNSpiK2T6WTWfgz92cHUyM993UMqqQaKUnDA==
 =EC7n
 -----END PGP SIGNATURE-----

Merge tag 'dm-4.4-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:
 "Five stable fixes:

   - Two DM btree bufio buffer leak fixes that resolve reported BUG_ONs
     during DM thinp metadata close's dm_bufio_client_destroy().

   - A DM thinp range discard fix to handle discarding a partially
     mapped range.

   - A DM thinp metadata snapshot fix to make sure the btree roots saved
     in the metadata snapshot are the most current.

   - A DM space map metadata refcounting fix that improves both DM thinp
     and DM cache metadata"

* tag 'dm-4.4-fixes-2' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm btree: fix bufio buffer leaks in dm_btree_del() error path
  dm space map metadata: fix ref counting bug when bootstrapping a new space map
  dm thin metadata: fix bug when taking a metadata snapshot
  dm thin metadata: fix bug in dm_thin_remove_range()
  dm btree: fix leak of bufio-backed block in btree_split_sibling error path
This commit is contained in:
Linus Torvalds 2015-12-11 11:00:30 -08:00
commit b9d85451dd
4 changed files with 161 additions and 20 deletions

View File

@ -1206,6 +1206,12 @@ static int __reserve_metadata_snap(struct dm_pool_metadata *pmd)
struct dm_block *copy, *sblock;
dm_block_t held_root;
/*
* We commit to ensure the btree roots which we increment in a
* moment are up to date.
*/
__commit_transaction(pmd);
/*
* Copy the superblock.
*/
@ -1538,7 +1544,7 @@ static int __remove(struct dm_thin_device *td, dm_block_t block)
static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_t end)
{
int r;
unsigned count;
unsigned count, total_count = 0;
struct dm_pool_metadata *pmd = td->pmd;
dm_block_t keys[1] = { td->id };
__le64 value;
@ -1561,11 +1567,29 @@ static int __remove_range(struct dm_thin_device *td, dm_block_t begin, dm_block_
if (r)
return r;
r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
if (r)
return r;
/*
* Remove leaves stops at the first unmapped entry, so we have to
* loop round finding mapped ranges.
*/
while (begin < end) {
r = dm_btree_lookup_next(&pmd->bl_info, mapping_root, &begin, &begin, &value);
if (r == -ENODATA)
break;
td->mapped_blocks -= count;
if (r)
return r;
if (begin >= end)
break;
r = dm_btree_remove_leaves(&pmd->bl_info, mapping_root, &begin, end, &mapping_root, &count);
if (r)
return r;
total_count += count;
}
td->mapped_blocks -= total_count;
td->changed = 1;
/*

View File

@ -63,6 +63,11 @@ int lower_bound(struct btree_node *n, uint64_t key)
return bsearch(n, key, 0);
}
static int upper_bound(struct btree_node *n, uint64_t key)
{
return bsearch(n, key, 1);
}
void inc_children(struct dm_transaction_manager *tm, struct btree_node *n,
struct dm_btree_value_type *vt)
{
@ -252,6 +257,16 @@ static void pop_frame(struct del_stack *s)
dm_tm_unlock(s->tm, f->b);
}
static void unlock_all_frames(struct del_stack *s)
{
struct frame *f;
while (unprocessed_frames(s)) {
f = s->spine + s->top--;
dm_tm_unlock(s->tm, f->b);
}
}
int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
{
int r;
@ -308,9 +323,13 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
pop_frame(s);
}
}
out:
if (r) {
/* cleanup all frames of del_stack */
unlock_all_frames(s);
}
kfree(s);
return r;
}
EXPORT_SYMBOL_GPL(dm_btree_del);
@ -392,6 +411,82 @@ int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
}
EXPORT_SYMBOL_GPL(dm_btree_lookup);
static int dm_btree_lookup_next_single(struct dm_btree_info *info, dm_block_t root,
uint64_t key, uint64_t *rkey, void *value_le)
{
int r, i;
uint32_t flags, nr_entries;
struct dm_block *node;
struct btree_node *n;
r = bn_read_lock(info, root, &node);
if (r)
return r;
n = dm_block_data(node);
flags = le32_to_cpu(n->header.flags);
nr_entries = le32_to_cpu(n->header.nr_entries);
if (flags & INTERNAL_NODE) {
i = lower_bound(n, key);
if (i < 0 || i >= nr_entries) {
r = -ENODATA;
goto out;
}
r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le);
if (r == -ENODATA && i < (nr_entries - 1)) {
i++;
r = dm_btree_lookup_next_single(info, value64(n, i), key, rkey, value_le);
}
} else {
i = upper_bound(n, key);
if (i < 0 || i >= nr_entries) {
r = -ENODATA;
goto out;
}
*rkey = le64_to_cpu(n->keys[i]);
memcpy(value_le, value_ptr(n, i), info->value_type.size);
}
out:
dm_tm_unlock(info->tm, node);
return r;
}
int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root,
uint64_t *keys, uint64_t *rkey, void *value_le)
{
unsigned level;
int r = -ENODATA;
__le64 internal_value_le;
struct ro_spine spine;
init_ro_spine(&spine, info);
for (level = 0; level < info->levels - 1u; level++) {
r = btree_lookup_raw(&spine, root, keys[level],
lower_bound, rkey,
&internal_value_le, sizeof(uint64_t));
if (r)
goto out;
if (*rkey != keys[level]) {
r = -ENODATA;
goto out;
}
root = le64_to_cpu(internal_value_le);
}
r = dm_btree_lookup_next_single(info, root, keys[level], rkey, value_le);
out:
exit_ro_spine(&spine);
return r;
}
EXPORT_SYMBOL_GPL(dm_btree_lookup_next);
/*
* 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
@ -473,8 +568,10 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index,
r = insert_at(sizeof(__le64), pn, parent_index + 1,
le64_to_cpu(rn->keys[0]), &location);
if (r)
if (r) {
unlock_block(s->info, right);
return r;
}
if (key < le64_to_cpu(rn->keys[0])) {
unlock_block(s->info, right);

View File

@ -109,6 +109,13 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root);
int dm_btree_lookup(struct dm_btree_info *info, dm_block_t root,
uint64_t *keys, void *value_le);
/*
* Tries to find the first key where the bottom level key is >= to that
* given. Useful for skipping empty sections of the btree.
*/
int dm_btree_lookup_next(struct dm_btree_info *info, dm_block_t root,
uint64_t *keys, uint64_t *rkey, void *value_le);
/*
* Insertion (or overwrite an existing value). O(ln(n))
*/
@ -135,9 +142,10 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
uint64_t *keys, dm_block_t *new_root);
/*
* Removes values between 'keys' and keys2, where keys2 is keys with the
* final key replaced with 'end_key'. 'end_key' is the one-past-the-end
* value. 'keys' may be altered.
* Removes a _contiguous_ run of values starting from 'keys' and not
* reaching keys2 (where keys2 is keys with the final key replaced with
* 'end_key'). 'end_key' is the one-past-the-end value. 'keys' may be
* altered.
*/
int dm_btree_remove_leaves(struct dm_btree_info *info, dm_block_t root,
uint64_t *keys, uint64_t end_key,

View File

@ -136,7 +136,7 @@ static int brb_push(struct bop_ring_buffer *brb,
return 0;
}
static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
static int brb_peek(struct bop_ring_buffer *brb, struct block_op *result)
{
struct block_op *bop;
@ -147,6 +147,17 @@ static int brb_pop(struct bop_ring_buffer *brb, struct block_op *result)
result->type = bop->type;
result->block = bop->block;
return 0;
}
static int brb_pop(struct bop_ring_buffer *brb)
{
struct block_op *bop;
if (brb_empty(brb))
return -ENODATA;
bop = brb->bops + brb->begin;
brb->begin = brb_next(brb, brb->begin);
return 0;
@ -211,7 +222,7 @@ static int apply_bops(struct sm_metadata *smm)
while (!brb_empty(&smm->uncommitted)) {
struct block_op bop;
r = brb_pop(&smm->uncommitted, &bop);
r = brb_peek(&smm->uncommitted, &bop);
if (r) {
DMERR("bug in bop ring buffer");
break;
@ -220,6 +231,8 @@ static int apply_bops(struct sm_metadata *smm)
r = commit_bop(smm, &bop);
if (r)
break;
brb_pop(&smm->uncommitted);
}
return r;
@ -683,7 +696,6 @@ static struct dm_space_map bootstrap_ops = {
static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
{
int r, i;
enum allocation_event ev;
struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
dm_block_t old_len = smm->ll.nr_blocks;
@ -705,11 +717,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
* allocate any new blocks.
*/
do {
for (i = old_len; !r && i < smm->begin; i++) {
r = sm_ll_inc(&smm->ll, i, &ev);
if (r)
goto out;
}
for (i = old_len; !r && i < smm->begin; i++)
r = add_bop(smm, BOP_INC, i);
if (r)
goto out;
old_len = smm->begin;
r = apply_bops(smm);
@ -754,7 +767,6 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
{
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;
@ -782,7 +794,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
* allocated blocks that they were built from.
*/
for (i = superblock; !r && i < smm->begin; i++)
r = sm_ll_inc(&smm->ll, i, &ev);
r = add_bop(smm, BOP_INC, i);
if (r)
return r;