aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/aio.c70
-rw-r--r--fs/btrfs/ctree.h13
-rw-r--r--fs/btrfs/extent-tree.c143
-rw-r--r--fs/btrfs/extent_io.c39
-rw-r--r--fs/btrfs/extent_io.h4
-rw-r--r--fs/btrfs/extent_map.c2
-rw-r--r--fs/btrfs/extent_map.h1
-rw-r--r--fs/btrfs/free-space-cache.c192
-rw-r--r--fs/btrfs/inode.c41
-rw-r--r--fs/btrfs/ioctl.c147
-rw-r--r--fs/btrfs/locking.c80
-rw-r--r--fs/btrfs/qgroup.c4
-rw-r--r--fs/btrfs/reada.c9
-rw-r--r--fs/btrfs/scrub.c19
-rw-r--r--fs/btrfs/tests/btrfs-tests.c2
-rw-r--r--fs/btrfs/tests/qgroup-tests.c2
-rw-r--r--fs/btrfs/transaction.c12
-rw-r--r--fs/btrfs/volumes.c36
-rw-r--r--fs/btrfs/volumes.h3
-rw-r--r--fs/ceph/acl.c6
-rw-r--r--fs/ceph/addr.c17
-rw-r--r--fs/ceph/caps.c246
-rw-r--r--fs/ceph/export.c2
-rw-r--r--fs/ceph/inode.c247
-rw-r--r--fs/ceph/mds_client.c9
-rw-r--r--fs/ceph/mds_client.h1
-rw-r--r--fs/ceph/super.h13
-rw-r--r--fs/dlm/lowcomms.c5
-rw-r--r--fs/eventpoll.c4
-rw-r--r--fs/locks.c2
-rw-r--r--fs/nfsd/nfs4state.c78
-rw-r--r--fs/nfsd/nfs4xdr.c1
32 files changed, 974 insertions, 476 deletions
diff --git a/fs/aio.c b/fs/aio.c
index 56b28607c32d..4f078c054b41 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -477,7 +477,7 @@ void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel)
}
EXPORT_SYMBOL(kiocb_set_cancel_fn);
-static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb)
+static int kiocb_cancel(struct kiocb *kiocb)
{
kiocb_cancel_fn *old, *cancel;
@@ -538,7 +538,7 @@ static void free_ioctx_users(struct percpu_ref *ref)
struct kiocb, ki_list);
list_del_init(&req->ki_list);
- kiocb_cancel(ctx, req);
+ kiocb_cancel(req);
}
spin_unlock_irq(&ctx->ctx_lock);
@@ -727,42 +727,42 @@ err:
* when the processes owning a context have all exited to encourage
* the rapid destruction of the kioctx.
*/
-static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
+static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
struct completion *requests_done)
{
- if (!atomic_xchg(&ctx->dead, 1)) {
- struct kioctx_table *table;
+ struct kioctx_table *table;
- spin_lock(&mm->ioctx_lock);
- rcu_read_lock();
- table = rcu_dereference(mm->ioctx_table);
+ if (atomic_xchg(&ctx->dead, 1))
+ return -EINVAL;
- WARN_ON(ctx != table->table[ctx->id]);
- table->table[ctx->id] = NULL;
- rcu_read_unlock();
- spin_unlock(&mm->ioctx_lock);
- /* percpu_ref_kill() will do the necessary call_rcu() */
- wake_up_all(&ctx->wait);
+ spin_lock(&mm->ioctx_lock);
+ rcu_read_lock();
+ table = rcu_dereference(mm->ioctx_table);
- /*
- * It'd be more correct to do this in free_ioctx(), after all
- * the outstanding kiocbs have finished - but by then io_destroy
- * has already returned, so io_setup() could potentially return
- * -EAGAIN with no ioctxs actually in use (as far as userspace
- * could tell).
- */
- aio_nr_sub(ctx->max_reqs);
+ WARN_ON(ctx != table->table[ctx->id]);
+ table->table[ctx->id] = NULL;
+ rcu_read_unlock();
+ spin_unlock(&mm->ioctx_lock);
- if (ctx->mmap_size)
- vm_munmap(ctx->mmap_base, ctx->mmap_size);
+ /* percpu_ref_kill() will do the necessary call_rcu() */
+ wake_up_all(&ctx->wait);
- ctx->requests_done = requests_done;
- percpu_ref_kill(&ctx->users);
- } else {
- if (requests_done)
- complete(requests_done);
- }
+ /*
+ * It'd be more correct to do this in free_ioctx(), after all
+ * the outstanding kiocbs have finished - but by then io_destroy
+ * has already returned, so io_setup() could potentially return
+ * -EAGAIN with no ioctxs actually in use (as far as userspace
+ * could tell).
+ */
+ aio_nr_sub(ctx->max_reqs);
+
+ if (ctx->mmap_size)
+ vm_munmap(ctx->mmap_base, ctx->mmap_size);
+
+ ctx->requests_done = requests_done;
+ percpu_ref_kill(&ctx->users);
+ return 0;
}
/* wait_on_sync_kiocb:
@@ -1219,21 +1219,23 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
if (likely(NULL != ioctx)) {
struct completion requests_done =
COMPLETION_INITIALIZER_ONSTACK(requests_done);
+ int ret;
/* Pass requests_done to kill_ioctx() where it can be set
* in a thread-safe way. If we try to set it here then we have
* a race condition if two io_destroy() called simultaneously.
*/
- kill_ioctx(current->mm, ioctx, &requests_done);
+ ret = kill_ioctx(current->mm, ioctx, &requests_done);
percpu_ref_put(&ioctx->users);
/* Wait until all IO for the context are done. Otherwise kernel
* keep using user-space buffers even if user thinks the context
* is destroyed.
*/
- wait_for_completion(&requests_done);
+ if (!ret)
+ wait_for_completion(&requests_done);
- return 0;
+ return ret;
}
pr_debug("EINVAL: io_destroy: invalid context id\n");
return -EINVAL;
@@ -1595,7 +1597,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
kiocb = lookup_kiocb(ctx, iocb, key);
if (kiocb)
- ret = kiocb_cancel(ctx, kiocb);
+ ret = kiocb_cancel(kiocb);
else
ret = -EINVAL;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b7e2c1c1ef36..be91397f4e92 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1259,11 +1259,19 @@ struct btrfs_block_group_cache {
spinlock_t lock;
u64 pinned;
u64 reserved;
+ u64 delalloc_bytes;
u64 bytes_super;
u64 flags;
u64 sectorsize;
u64 cache_generation;
+ /*
+ * It is just used for the delayed data space allocation because
+ * only the data space allocation and the relative metadata update
+ * can be done cross the transaction.
+ */
+ struct rw_semaphore data_rwsem;
+
/* for raid56, this is a full stripe, without parity */
unsigned long full_stripe_len;
@@ -3316,7 +3324,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_key *ins);
int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
u64 min_alloc_size, u64 empty_size, u64 hint_byte,
- struct btrfs_key *ins, int is_data);
+ struct btrfs_key *ins, int is_data, int delalloc);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf, int full_backref, int no_quota);
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
@@ -3330,7 +3338,8 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
u64 owner, u64 offset, int no_quota);
-int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
+int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len,
+ int delalloc);
int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
u64 start, u64 len);
void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index fafb3e53ecde..99c253918208 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -105,7 +105,8 @@ static int find_next_key(struct btrfs_path *path, int level,
static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
int dump_block_groups);
static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve);
+ u64 num_bytes, int reserve,
+ int delalloc);
static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
u64 num_bytes);
int btrfs_pin_extent(struct btrfs_root *root,
@@ -3260,7 +3261,8 @@ again:
spin_lock(&block_group->lock);
if (block_group->cached != BTRFS_CACHE_FINISHED ||
- !btrfs_test_opt(root, SPACE_CACHE)) {
+ !btrfs_test_opt(root, SPACE_CACHE) ||
+ block_group->delalloc_bytes) {
/*
* don't bother trying to write stuff out _if_
* a) we're not cached,
@@ -5613,6 +5615,7 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log,
* @cache: The cache we are manipulating
* @num_bytes: The number of bytes in question
* @reserve: One of the reservation enums
+ * @delalloc: The blocks are allocated for the delalloc write
*
* This is called by the allocator when it reserves space, or by somebody who is
* freeing space that was never actually used on disk. For example if you
@@ -5631,7 +5634,7 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log,
* succeeds.
*/
static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve)
+ u64 num_bytes, int reserve, int delalloc)
{
struct btrfs_space_info *space_info = cache->space_info;
int ret = 0;
@@ -5650,12 +5653,18 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
num_bytes, 0);
space_info->bytes_may_use -= num_bytes;
}
+
+ if (delalloc)
+ cache->delalloc_bytes += num_bytes;
}
} else {
if (cache->ro)
space_info->bytes_readonly += num_bytes;
cache->reserved -= num_bytes;
space_info->bytes_reserved -= num_bytes;
+
+ if (delalloc)
+ cache->delalloc_bytes -= num_bytes;
}
spin_unlock(&cache->lock);
spin_unlock(&space_info->lock);
@@ -6206,7 +6215,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
btrfs_add_free_space(cache, buf->start, buf->len);
- btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE);
+ btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
trace_btrfs_reserved_extent_free(root, buf->start, buf->len);
pin = 0;
}
@@ -6365,6 +6374,70 @@ enum btrfs_loop_type {
LOOP_NO_EMPTY_SIZE = 3,
};
+static inline void
+btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
+ int delalloc)
+{
+ if (delalloc)
+ down_read(&cache->data_rwsem);
+}
+
+static inline void
+btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
+ int delalloc)
+{
+ btrfs_get_block_group(cache);
+ if (delalloc)
+ down_read(&cache->data_rwsem);
+}
+
+static struct btrfs_block_group_cache *
+btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
+ struct btrfs_free_cluster *cluster,
+ int delalloc)
+{
+ struct btrfs_block_group_cache *used_bg;
+ bool locked = false;
+again:
+ spin_lock(&cluster->refill_lock);
+ if (locked) {
+ if (used_bg == cluster->block_group)
+ return used_bg;
+
+ up_read(&used_bg->data_rwsem);
+ btrfs_put_block_group(used_bg);
+ }
+
+ used_bg = cluster->block_group;
+ if (!used_bg)
+ return NULL;
+
+ if (used_bg == block_group)
+ return used_bg;
+
+ btrfs_get_block_group(used_bg);
+
+ if (!delalloc)
+ return used_bg;
+
+ if (down_read_trylock(&used_bg->data_rwsem))
+ return used_bg;
+
+ spin_unlock(&cluster->refill_lock);
+ down_read(&used_bg->data_rwsem);
+ locked = true;
+ goto again;
+}
+
+static inline void
+btrfs_release_block_group(struct btrfs_block_group_cache *cache,
+ int delalloc)
+{
+ if (delalloc)
+ up_read(&cache->data_rwsem);
+ btrfs_put_block_group(cache);
+}
+
/*
* walks the btree of allocated extents and find a hole of a given size.
* The key ins is changed to record the hole:
@@ -6379,7 +6452,7 @@ enum btrfs_loop_type {
static noinline int find_free_extent(struct btrfs_root *orig_root,
u64 num_bytes, u64 empty_size,
u64 hint_byte, struct btrfs_key *ins,
- u64 flags)
+ u64 flags, int delalloc)
{
int ret = 0;
struct btrfs_root *root = orig_root->fs_info->extent_root;
@@ -6467,6 +6540,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
up_read(&space_info->groups_sem);
} else {
index = get_block_group_index(block_group);
+ btrfs_lock_block_group(block_group, delalloc);
goto have_block_group;
}
} else if (block_group) {
@@ -6481,7 +6555,7 @@ search:
u64 offset;
int cached;
- btrfs_get_block_group(block_group);
+ btrfs_grab_block_group(block_group, delalloc);
search_start = block_group->key.objectid;
/*
@@ -6529,16 +6603,16 @@ have_block_group:
* the refill lock keeps out other
* people trying to start a new cluster
*/
- spin_lock(&last_ptr->refill_lock);
- used_block_group = last_ptr->block_group;
- if (used_block_group != block_group &&
- (!used_block_group ||
- used_block_group->ro ||
- !block_group_bits(used_block_group, flags)))
+ used_block_group = btrfs_lock_cluster(block_group,
+ last_ptr,
+ delalloc);
+ if (!used_block_group)
goto refill_cluster;
- if (used_block_group != block_group)
- btrfs_get_block_group(used_block_group);
+ if (used_block_group != block_group &&
+ (used_block_group->ro ||
+ !block_group_bits(used_block_group, flags)))
+ goto release_cluster;
offset = btrfs_alloc_from_cluster(used_block_group,
last_ptr,
@@ -6552,16 +6626,15 @@ have_block_group:
used_block_group,
search_start, num_bytes);
if (used_block_group != block_group) {
- btrfs_put_block_group(block_group);
+ btrfs_release_block_group(block_group,
+ delalloc);
block_group = used_block_group;
}
goto checks;
}
WARN_ON(last_ptr->block_group != used_block_group);
- if (used_block_group != block_group)
- btrfs_put_block_group(used_block_group);
-refill_cluster:
+release_cluster:
/* If we are on LOOP_NO_EMPTY_SIZE, we can't
* set up a new clusters, so lets just skip it
* and let the allocator find whatever block
@@ -6578,8 +6651,10 @@ refill_cluster:
* succeeding in the unclustered
* allocation. */
if (loop >= LOOP_NO_EMPTY_SIZE &&
- last_ptr->block_group != block_group) {
+ used_block_group != block_group) {
spin_unlock(&last_ptr->refill_lock);
+ btrfs_release_block_group(used_block_group,
+ delalloc);
goto unclustered_alloc;
}
@@ -6589,6 +6664,10 @@ refill_cluster:
*/
btrfs_return_cluster_to_free_space(NULL, last_ptr);
+ if (used_block_group != block_group)
+ btrfs_release_block_group(used_block_group,
+ delalloc);
+refill_cluster:
if (loop >= LOOP_NO_EMPTY_SIZE) {
spin_unlock(&last_ptr->refill_lock);
goto unclustered_alloc;
@@ -6696,7 +6775,7 @@ checks:
BUG_ON(offset > search_start);
ret = btrfs_update_reserved_bytes(block_group, num_bytes,
- alloc_type);
+ alloc_type, delalloc);
if (ret == -EAGAIN) {
btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
@@ -6708,13 +6787,13 @@ checks:
trace_btrfs_reserve_extent(orig_root, block_group,
search_start, num_bytes);
- btrfs_put_block_group(block_group);
+ btrfs_release_block_group(block_group, delalloc);
break;
loop:
failed_cluster_refill = false;
failed_alloc = false;
BUG_ON(index != get_block_group_index(block_group));
- btrfs_put_block_group(block_group);
+ btrfs_release_block_group(block_group, delalloc);
}
up_read(&space_info->groups_sem);
@@ -6827,7 +6906,7 @@ again:
int btrfs_reserve_extent(struct btrfs_root *root,
u64 num_bytes, u64 min_alloc_size,
u64 empty_size, u64 hint_byte,
- struct btrfs_key *ins, int is_data)
+ struct btrfs_key *ins, int is_data, int delalloc)
{
bool final_tried = false;
u64 flags;
@@ -6837,7 +6916,7 @@ int btrfs_reserve_extent(struct btrfs_root *root,
again:
WARN_ON(num_bytes < root->sectorsize);
ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
- flags);
+ flags, delalloc);
if (ret == -ENOSPC) {
if (!final_tried && ins->offset) {
@@ -6862,7 +6941,8 @@ again:
}
static int __btrfs_free_reserved_extent(struct btrfs_root *root,
- u64 start, u64 len, int pin)
+ u64 start, u64 len,
+ int pin, int delalloc)
{
struct btrfs_block_group_cache *cache;
int ret = 0;
@@ -6881,7 +6961,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
pin_down_extent(root, cache, start, len, 1);
else {
btrfs_add_free_space(cache, start, len);
- btrfs_update_reserved_bytes(cache, len, RESERVE_FREE);
+ btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
}
btrfs_put_block_group(cache);
@@ -6891,15 +6971,15 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root,
}
int btrfs_free_reserved_extent(struct btrfs_root *root,
- u64 start, u64 len)
+ u64 start, u64 len, int delalloc)
{
- return __btrfs_free_reserved_extent(root, start, len, 0);
+ return __btrfs_free_reserved_extent(root, start, len, 0, delalloc);
}
int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root,
u64 start, u64 len)
{
- return __btrfs_free_reserved_extent(root, start, len, 1);
+ return __btrfs_free_reserved_extent(root, start, len, 1, 0);
}
static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
@@ -7114,7 +7194,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
return -EINVAL;
ret = btrfs_update_reserved_bytes(block_group, ins->offset,
- RESERVE_ALLOC_NO_ACCOUNT);
+ RESERVE_ALLOC_NO_ACCOUNT, 0);
BUG_ON(ret); /* logic error */
ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
0, owner, offset, ins, 1);
@@ -7256,7 +7336,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
return ERR_CAST(block_rsv);
ret = btrfs_reserve_extent(root, blocksize, blocksize,
- empty_size, hint, &ins, 0);
+ empty_size, hint, &ins, 0, 0);
if (ret) {
unuse_block_rsv(root->fs_info, block_rsv, blocksize);
return ERR_PTR(ret);
@@ -8659,6 +8739,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
start);
atomic_set(&cache->count, 1);
spin_lock_init(&cache->lock);
+ init_rwsem(&cache->data_rwsem);
INIT_LIST_HEAD(&cache->list);
INIT_LIST_HEAD(&cache->cluster_list);
INIT_LIST_HEAD(&cache->new_bg_list);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f25a9092b946..a389820d158b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2354,7 +2354,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
{
int uptodate = (err == 0);
struct extent_io_tree *tree;
- int ret;
+ int ret = 0;
tree = &BTRFS_I(page->mapping->host)->io_tree;
@@ -5068,6 +5068,43 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
}
}
+int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
+ unsigned long start,
+ unsigned long len)
+{
+ size_t cur;
+ size_t offset;
+ struct page *page;
+ char *kaddr;
+ char __user *dst = (char __user *)dstv;
+ size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
+ unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+ int ret = 0;
+
+ WARN_ON(start > eb->len);
+ WARN_ON(start + len > eb->start + eb->len);
+
+ offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+
+ while (len > 0) {
+ page = extent_buffer_page(eb, i);
+
+ cur = min(len, (PAGE_CACHE_SIZE - offset));
+ kaddr = page_address(page);
+ if (copy_to_user(dst, kaddr + offset, cur)) {
+ ret = -EFAULT;
+ break;
+ }
+
+ dst += cur;
+ len -= cur;
+ offset = 0;
+ i++;
+ }
+
+ return ret;
+}
+
int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
unsigned long min_len, char **map,
unsigned long *map_start,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 8b63f2d46518..ccc264e7bde1 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -158,7 +158,6 @@ struct extent_buffer {
* to unlock
*/
wait_queue_head_t read_lock_wq;
- wait_queue_head_t lock_wq;
struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
#ifdef CONFIG_BTRFS_DEBUG
struct list_head leak_list;
@@ -304,6 +303,9 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
void read_extent_buffer(struct extent_buffer *eb, void *dst,
unsigned long start,
unsigned long len);
+int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst,
+ unsigned long start,
+ unsigned long len);
void write_extent_buffer(struct extent_buffer *eb, const void *src,
unsigned long start, unsigned long len);
void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 1874aee69c86..225302b39afb 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -75,6 +75,8 @@ void free_extent_map(struct extent_map *em)
if (atomic_dec_and_test(&em->refs)) {
WARN_ON(extent_map_in_tree(em));
WARN_ON(!list_empty(&em->list));
+ if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
+ kfree(em->bdev);
kmem_cache_free(extent_map_cache, em);
}
}
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index e7fd8a56a140..b2991fd8583e 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -15,6 +15,7 @@
#define EXTENT_FLAG_PREALLOC 3 /* pre-allocated extent */
#define EXTENT_FLAG_LOGGING 4 /* Logging this extent */
#define EXTENT_FLAG_FILLING 5 /* Filling in a preallocated extent */
+#define EXTENT_FLAG_FS_MAPPING 6 /* filesystem extent mapping type */
struct extent_map {
struct rb_node rb_node;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 372b05ff1943..2b0a627cb5f9 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -274,18 +274,32 @@ struct io_ctl {
};
static int io_ctl_init(struct io_ctl *io_ctl, struct inode *inode,
- struct btrfs_root *root)
+ struct btrfs_root *root, int write)
{
+ int num_pages;
+ int check_crcs = 0;
+
+ num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT;
+
+ if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
+ check_crcs = 1;
+
+ /* Make sure we can fit our crcs into the first page */
+ if (write && check_crcs &&
+ (num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE)
+ return -ENOSPC;
+
memset(io_ctl, 0, sizeof(struct io_ctl));
- io_ctl->num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
- io_ctl->pages = kzalloc(sizeof(struct page *) * io_ctl->num_pages,
- GFP_NOFS);
+
+ io_ctl->pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS);
if (!io_ctl->pages)
return -ENOMEM;
+
+ io_ctl->num_pages = num_pages;
io_ctl->root = root;
- if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
- io_ctl->check_crcs = 1;
+ io_ctl->check_crcs = check_crcs;
+
return 0;
}
@@ -666,6 +680,13 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
generation = btrfs_free_space_generation(leaf, header);
btrfs_release_path(path);
+ if (!BTRFS_I(inode)->generation) {
+ btrfs_info(root->fs_info,
+ "The free space cache file (%llu) is invalid. skip it\n",
+ offset);
+ return 0;
+ }
+
if (BTRFS_I(inode)->generation != generation) {
btrfs_err(root->fs_info,
"free space inode generation (%llu) "
@@ -677,7 +698,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
if (!num_entries)
return 0;
- ret = io_ctl_init(&io_ctl, inode, root);
+ ret = io_ctl_init(&io_ctl, inode, root, 0);
if (ret)
return ret;
@@ -957,19 +978,18 @@ fail:
}
static noinline_for_stack int
-add_ioctl_entries(struct btrfs_root *root,
- struct inode *inode,
- struct btrfs_block_group_cache *block_group,
- struct io_ctl *io_ctl,
- struct extent_state **cached_state,
- struct list_head *bitmap_list,
- int *entries)
+write_pinned_extent_entries(struct btrfs_root *root,
+ struct btrfs_block_group_cache *block_group,
+ struct io_ctl *io_ctl,
+ int *entries)
{
u64 start, extent_start, extent_end, len;
- struct list_head *pos, *n;
struct extent_io_tree *unpin = NULL;
int ret;
+ if (!block_group)
+ return 0;
+
/*
* We want to add any pinned extents to our free space cache
* so we don't leak the space
@@ -979,23 +999,19 @@ add_ioctl_entries(struct btrfs_root *root,
*/
unpin = root->fs_info->pinned_extents;
- if (block_group)
- start = block_group->key.objectid;
+ start = block_group->key.objectid;
- while (block_group && (start < block_group->key.objectid +
- block_group->key.offset)) {
+ while (start < block_group->key.objectid + block_group->key.offset) {
ret = find_first_extent_bit(unpin, start,
&extent_start, &extent_end,
EXTENT_DIRTY, NULL);
- if (ret) {
- ret = 0;
- break;
- }
+ if (ret)
+ return 0;
/* This pinned extent is out of our range */
if (extent_start >= block_group->key.objectid +
block_group->key.offset)
- break;
+ return 0;
extent_start = max(extent_start, start);
extent_end = min(block_group->key.objectid +
@@ -1005,11 +1021,20 @@ add_ioctl_entries(struct btrfs_root *root,
*entries += 1;
ret = io_ctl_add_entry(io_ctl, extent_start, len, NULL);
if (ret)
- goto out_nospc;
+ return -ENOSPC;
start = extent_end;
}
+ return 0;
+}
+
+static noinline_for_stack int
+write_bitmap_entries(struct io_ctl *io_ctl, struct list_head *bitmap_list)
+{
+ struct list_head *pos, *n;
+ int ret;
+
/* Write out the bitmaps */
list_for_each_safe(pos, n, bitmap_list) {
struct btrfs_free_space *entry =
@@ -1017,36 +1042,24 @@ add_ioctl_entries(struct btrfs_root *root,
ret = io_ctl_add_bitmap(io_ctl, entry->bitmap);
if (ret)
- goto out_nospc;
+ return -ENOSPC;
list_del_init(&entry->list);
}
- /* Zero out the rest of the pages just to make sure */
- io_ctl_zero_remaining_pages(io_ctl);
-
- ret = btrfs_dirty_pages(root, inode, io_ctl->pages, io_ctl->num_pages,
- 0, i_size_read(inode), cached_state);
- io_ctl_drop_pages(io_ctl);
- unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
- i_size_read(inode) - 1, cached_state, GFP_NOFS);
+ return 0;
+}
- if (ret)
- goto fail;
+static int flush_dirty_cache(struct inode *inode)
+{
+ int ret;
ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
- if (ret) {
+ if (ret)
clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1,
EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL,
GFP_NOFS);
- goto fail;
- }
- return 0;
-fail:
- return -1;
-
-out_nospc:
- return -ENOSPC;
+ return ret;
}
static void noinline_for_stack
@@ -1056,6 +1069,7 @@ cleanup_write_cache_enospc(struct inode *inode,
struct list_head *bitmap_list)
{
struct list_head *pos, *n;
+
list_for_each_safe(pos, n, bitmap_list) {
struct btrfs_free_space *entry =
list_entry(pos, struct btrfs_free_space, list);
@@ -1088,64 +1102,104 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
{
struct extent_state *cached_state = NULL;
struct io_ctl io_ctl;
- struct list_head bitmap_list;
+ LIST_HEAD(bitmap_list);
int entries = 0;
int bitmaps = 0;
int ret;
- int err = -1;
-
- INIT_LIST_HEAD(&bitmap_list);
if (!i_size_read(inode))
return -1;
- ret = io_ctl_init(&io_ctl, inode, root);
+ ret = io_ctl_init(&io_ctl, inode, root, 1);
if (ret)
return -1;
+ if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) {
+ down_write(&block_group->data_rwsem);
+ spin_lock(&block_group->lock);
+ if (block_group->delalloc_bytes) {
+ block_group->disk_cache_state = BTRFS_DC_WRITTEN;
+ spin_unlock(&block_group->lock);
+ up_write(&block_group->data_rwsem);
+ BTRFS_I(inode)->generation = 0;
+ ret = 0;
+ goto out;
+ }
+ spin_unlock(&block_group->lock);
+ }
+
/* Lock all pages first so we can lock the extent safely. */
io_ctl_prepare_pages(&io_ctl, inode, 0);
lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
0, &cached_state);
-
- /* Make sure we can fit our crcs into the first page */
- if (io_ctl.check_crcs &&
- (io_ctl.num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE)
- goto out_nospc;
-
io_ctl_set_generation(&io_ctl, trans->transid);
+ /* Write out the extent entries in the free space cache */
ret = write_cache_extent_entries(&io_ctl, ctl,
block_group, &entries, &bitmaps,
&bitmap_list);
if (ret)
goto out_nospc;
- ret = add_ioctl_entries(root, inode, block_group, &io_ctl,
- &cached_state, &bitmap_list, &entries);
+ /*
+ * Some spaces that are freed in the current transaction are pinned,
+ * they will be added into free space cache after the transaction is
+ * committed, we shouldn't lose them.
+ */
+ ret = write_pinned_extent_entries(root, block_group, &io_ctl, &entries);
+ if (ret)
+ goto out_nospc;
- if (ret == -ENOSPC)
+ /* At last, we write out all the bitmaps. */
+ ret = write_bitmap_entries(&io_ctl, &bitmap_list);
+ if (ret)
goto out_nospc;
- else if (ret)
+
+ /* Zero out the rest of the pages just to make sure */
+ io_ctl_zero_remaining_pages(&io_ctl);
+
+ /* Everything is written out, now we dirty the pages in the file. */
+ ret = btrfs_dirty_pages(root, inode, io_ctl.pages, io_ctl.num_pages,
+ 0, i_size_read(inode), &cached_state);
+ if (ret)
+ goto out_nospc;
+
+ if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+ up_write(&block_group->data_rwsem);
+ /*
+ * Release the pages and unlock the extent, we will flush
+ * them out later
+ */
+ io_ctl_drop_pages(&io_ctl);
+
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
+ i_size_read(inode) - 1, &cached_state, GFP_NOFS);
+
+ /* Flush the dirty pages in the cache file. */
+ ret = flush_dirty_cache(inode);
+ if (ret)
goto out;
- err = update_cache_item(trans, root, inode, path, offset,
+ /* Update the cache item to tell everyone this cache file is valid. */
+ ret = update_cache_item(trans, root, inode, path, offset,
entries, bitmaps);
-
out:
io_ctl_free(&io_ctl);
- if (err) {
+ if (ret) {
invalidate_inode_pages2(inode->i_mapping);
BTRFS_I(inode)->generation = 0;
}
btrfs_update_inode(trans, root, inode);
- return err;
+ return ret;
out_nospc:
-
cleanup_write_cache_enospc(inode, &io_ctl, &cached_state, &bitmap_list);
+
+ if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
+ up_write(&block_group->data_rwsem);
+
goto out;
}
@@ -1165,6 +1219,12 @@ int btrfs_write_out_cache(struct btrfs_root *root,
spin_unlock(&block_group->lock);
return 0;
}
+
+ if (block_group->delalloc_bytes) {
+ block_group->disk_cache_state = BTRFS_DC_WRITTEN;
+ spin_unlock(&block_group->lock);
+ return 0;
+ }
spin_unlock(&block_group->lock);
inode = lookup_free_space_inode(root, block_group, path);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8925f66a1411..3668048e16f8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -693,7 +693,7 @@ retry:
ret = btrfs_reserve_extent(root,
async_extent->compressed_size,
async_extent->compressed_size,
- 0, alloc_hint, &ins, 1);
+ 0, alloc_hint, &ins, 1, 1);
if (ret) {
int i;
@@ -794,7 +794,7 @@ retry:
out:
return ret;
out_free_reserve:
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_free:
extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
@@ -917,7 +917,7 @@ static noinline int cow_file_range(struct inode *inode,
cur_alloc_size = disk_num_bytes;
ret = btrfs_reserve_extent(root, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
- &ins, 1);
+ &ins, 1, 1);
if (ret < 0)
goto out_unlock;
@@ -995,7 +995,7 @@ out:
return ret;
out_reserve:
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_unlock:
extent_clear_unlock_delalloc(inode, start, end, locked_page,
EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
@@ -2599,6 +2599,21 @@ out_kfree:
return NULL;
}
+static void btrfs_release_delalloc_bytes(struct btrfs_root *root,
+ u64 start, u64 len)
+{
+ struct btrfs_block_group_cache *cache;
+
+ cache = btrfs_lookup_block_group(root->fs_info, start);
+ ASSERT(cache);
+
+ spin_lock(&cache->lock);
+ cache->delalloc_bytes -= len;
+ spin_unlock(&cache->lock);
+
+ btrfs_put_block_group(cache);
+}
+
/* as ordered data IO finishes, this gets called so we can finish
* an ordered extent if the range of bytes in the file it covers are
* fully written.
@@ -2698,6 +2713,10 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
logical_len, logical_len,
compress_type, 0, 0,
BTRFS_FILE_EXTENT_REG);
+ if (!ret)
+ btrfs_release_delalloc_bytes(root,
+ ordered_extent->start,
+ ordered_extent->disk_len);
}
unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
ordered_extent->file_offset, ordered_extent->len,
@@ -2750,7 +2769,7 @@ out:
!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
!test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
btrfs_free_reserved_extent(root, ordered_extent->start,
- ordered_extent->disk_len);
+ ordered_extent->disk_len, 1);
}
@@ -6535,21 +6554,21 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
alloc_hint = get_extent_allocation_hint(inode, start, len);
ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
- alloc_hint, &ins, 1);
+ alloc_hint, &ins, 1, 1);
if (ret)
return ERR_PTR(ret);
em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
ins.offset, ins.offset, ins.offset, 0);
if (IS_ERR(em)) {
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
return em;
}
ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
ins.offset, ins.offset, 0);
if (ret) {
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
free_extent_map(em);
return ERR_PTR(ret);
}
@@ -7437,7 +7456,7 @@ free_ordered:
if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) &&
!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
btrfs_free_reserved_extent(root, ordered->start,
- ordered->disk_len);
+ ordered->disk_len, 1);
btrfs_put_ordered_extent(ordered);
btrfs_put_ordered_extent(ordered);
}
@@ -8808,7 +8827,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
cur_bytes = min(num_bytes, 256ULL * 1024 * 1024);
cur_bytes = max(cur_bytes, min_size);
ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
- *alloc_hint, &ins, 1);
+ *alloc_hint, &ins, 1, 0);
if (ret) {
if (own_trans)
btrfs_end_transaction(trans, root);
@@ -8822,7 +8841,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
BTRFS_FILE_EXTENT_PREALLOC);
if (ret) {
btrfs_free_reserved_extent(root, ins.objectid,
- ins.offset);
+ ins.offset, 0);
btrfs_abort_transaction(trans, root, ret);
if (own_trans)
btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 82c18ba12e3f..0d321c23069a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1957,7 +1957,8 @@ static noinline int copy_to_sk(struct btrfs_root *root,
struct btrfs_path *path,
struct btrfs_key *key,
struct btrfs_ioctl_search_key *sk,
- char *buf,
+ size_t *buf_size,
+ char __user *ubuf,
unsigned long *sk_offset,
int *num_found)
{
@@ -1989,13 +1990,25 @@ static noinline int copy_to_sk(struct btrfs_root *root,
if (!key_in_sk(key, sk))
continue;
- if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE)
+ if (sizeof(sh) + item_len > *buf_size) {
+ if (*num_found) {
+ ret = 1;
+ goto out;
+ }
+
+ /*
+ * return one empty item back for v1, which does not
+ * handle -EOVERFLOW
+ */
+
+ *buf_size = sizeof(sh) + item_len;
item_len = 0;
+ ret = -EOVERFLOW;
+ }
- if (sizeof(sh) + item_len + *sk_offset >
- BTRFS_SEARCH_ARGS_BUFSIZE) {
+ if (sizeof(sh) + item_len + *sk_offset > *buf_size) {
ret = 1;
- goto overflow;
+ goto out;
}
sh.objectid = key->objectid;
@@ -2005,20 +2018,33 @@ static noinline int copy_to_sk(struct btrfs_root *root,
sh.transid = found_transid;
/* copy search result header */
- memcpy(buf + *sk_offset, &sh, sizeof(sh));
+ if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
*sk_offset += sizeof(sh);
if (item_len) {
- char *p = buf + *sk_offset;
+ char __user *up = ubuf + *sk_offset;
/* copy the item */
- read_extent_buffer(leaf, p,
- item_off, item_len);
+ if (read_extent_buffer_to_user(leaf, up,
+ item_off, item_len)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
*sk_offset += item_len;
}
(*num_found)++;
- if (*num_found >= sk->nr_items)
- break;
+ if (ret) /* -EOVERFLOW from above */
+ goto out;
+
+ if (*num_found >= sk->nr_items) {
+ ret = 1;
+ goto out;
+ }
}
advance_key:
ret = 0;
@@ -2033,22 +2059,37 @@ advance_key:
key->objectid++;
} else
ret = 1;
-overflow:
+out:
+ /*
+ * 0: all items from this leaf copied, continue with next
+ * 1: * more items can be copied, but unused buffer is too small
+ * * all items were found
+ * Either way, it will stops the loop which iterates to the next
+ * leaf
+ * -EOVERFLOW: item was to large for buffer
+ * -EFAULT: could not copy extent buffer back to userspace
+ */
return ret;
}
static noinline int search_ioctl(struct inode *inode,
- struct btrfs_ioctl_search_args *args)
+ struct btrfs_ioctl_search_key *sk,
+ size_t *buf_size,
+ char __user *ubuf)
{
struct btrfs_root *root;
struct btrfs_key key;
struct btrfs_path *path;
- struct btrfs_ioctl_search_key *sk = &args->key;
struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info;
int ret;
int num_found = 0;
unsigned long sk_offset = 0;
+ if (*buf_size < sizeof(struct btrfs_ioctl_search_header)) {
+ *buf_size = sizeof(struct btrfs_ioctl_search_header);
+ return -EOVERFLOW;
+ }
+
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
@@ -2082,14 +2123,15 @@ static noinline int search_ioctl(struct inode *inode,
ret = 0;
goto err;
}
- ret = copy_to_sk(root, path, &key, sk, args->buf,
+ ret = copy_to_sk(root, path, &key, sk, buf_size, ubuf,
&sk_offset, &num_found);
btrfs_release_path(path);
- if (ret || num_found >= sk->nr_items)
+ if (ret)
break;
}
- ret = 0;
+ if (ret > 0)
+ ret = 0;
err:
sk->nr_items = num_found;
btrfs_free_path(path);
@@ -2099,22 +2141,73 @@ err:
static noinline int btrfs_ioctl_tree_search(struct file *file,
void __user *argp)
{
- struct btrfs_ioctl_search_args *args;
- struct inode *inode;
- int ret;
+ struct btrfs_ioctl_search_args __user *uargs;
+ struct btrfs_ioctl_search_key sk;
+ struct inode *inode;
+ int ret;
+ size_t buf_size;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- args = memdup_user(argp, sizeof(*args));
- if (IS_ERR(args))
- return PTR_ERR(args);
+ uargs = (struct btrfs_ioctl_search_args __user *)argp;
+
+ if (copy_from_user(&sk, &uargs->key, sizeof(sk)))
+ return -EFAULT;
+
+ buf_size = sizeof(uargs->buf);
inode = file_inode(file);
- ret = search_ioctl(inode, args);
- if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
+ ret = search_ioctl(inode, &sk, &buf_size, uargs->buf);
+
+ /*
+ * In the origin implementation an overflow is handled by returning a
+ * search header with a len of zero, so reset ret.
+ */
+ if (ret == -EOVERFLOW)
+ ret = 0;
+
+ if (ret == 0 && copy_to_user(&uargs->key, &sk, sizeof(sk)))
ret = -EFAULT;
- kfree(args);
+ return ret;
+}
+
+static noinline int btrfs_ioctl_tree_search_v2(struct file *file,
+ void __user *argp)
+{
+ struct btrfs_ioctl_search_args_v2 __user *uarg;
+ struct btrfs_ioctl_search_args_v2 args;
+ struct inode *inode;
+ int ret;
+ size_t buf_size;
+ const size_t buf_limit = 16 * 1024 * 1024;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ /* copy search header and buffer size */
+ uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp;
+ if (copy_from_user(&args, uarg, sizeof(args)))
+ return -EFAULT;
+
+ buf_size = args.buf_size;
+
+ if (buf_size < sizeof(struct btrfs_ioctl_search_header))
+ return -EOVERFLOW;
+
+ /* limit result size to 16MB */
+ if (buf_size > buf_limit)
+ buf_size = buf_limit;
+
+ inode = file_inode(file);
+ ret = search_ioctl(inode, &args.key, &buf_size,
+ (char *)(&uarg->buf[0]));
+ if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key)))
+ ret = -EFAULT;
+ else if (ret == -EOVERFLOW &&
+ copy_to_user(&uarg->buf_size, &buf_size, sizeof(buf_size)))
+ ret = -EFAULT;
+
return ret;
}
@@ -5198,6 +5291,8 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_trans_end(file);
case BTRFS_IOC_TREE_SEARCH:
return btrfs_ioctl_tree_search(file, argp);
+ case BTRFS_IOC_TREE_SEARCH_V2:
+ return btrfs_ioctl_tree_search_v2(file, argp);
case BTRFS_IOC_INO_LOOKUP:
return btrfs_ioctl_ino_lookup(file, argp);
case BTRFS_IOC_INO_PATHS:
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 01277b8f2373..5665d2149249 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -33,14 +33,14 @@ static void btrfs_assert_tree_read_locked(struct extent_buffer *eb);
*/
void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
{
- if (eb->lock_nested) {
- read_lock(&eb->lock);
- if (eb->lock_nested && current->pid == eb->lock_owner) {
- read_unlock(&eb->lock);
- return;
- }
- read_unlock(&eb->lock);
- }
+ /*
+ * no lock is required. The lock owner may change if
+ * we have a read lock, but it won't change to or away
+ * from us. If we have the write lock, we are the owner
+ * and it'll never change.
+ */
+ if (eb->lock_nested && current->pid == eb->lock_owner)
+ return;
if (rw == BTRFS_WRITE_LOCK) {
if (atomic_read(&eb->blocking_writers) == 0) {
WARN_ON(atomic_read(&eb->spinning_writers) != 1);
@@ -65,14 +65,15 @@ void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw)
*/
void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
{
- if (eb->lock_nested) {
- read_lock(&eb->lock);
- if (eb->lock_nested && current->pid == eb->lock_owner) {
- read_unlock(&eb->lock);
- return;
- }
- read_unlock(&eb->lock);
- }
+ /*
+ * no lock is required. The lock owner may change if
+ * we have a read lock, but it won't change to or away
+ * from us. If we have the write lock, we are the owner
+ * and it'll never change.
+ */
+ if (eb->lock_nested && current->pid == eb->lock_owner)
+ return;
+
if (rw == BTRFS_WRITE_LOCK_BLOCKING) {
BUG_ON(atomic_read(&eb->blocking_writers) != 1);
write_lock(&eb->lock);
@@ -99,6 +100,9 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
void btrfs_tree_read_lock(struct extent_buffer *eb)
{
again:
+ BUG_ON(!atomic_read(&eb->blocking_writers) &&
+ current->pid == eb->lock_owner);
+
read_lock(&eb->lock);
if (atomic_read(&eb->blocking_writers) &&
current->pid == eb->lock_owner) {
@@ -132,7 +136,9 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb)
if (atomic_read(&eb->blocking_writers))
return 0;
- read_lock(&eb->lock);
+ if (!read_trylock(&eb->lock))
+ return 0;
+
if (atomic_read(&eb->blocking_writers)) {
read_unlock(&eb->lock);
return 0;
@@ -151,7 +157,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
if (atomic_read(&eb->blocking_writers) ||
atomic_read(&eb->blocking_readers))
return 0;
- write_lock(&eb->lock);
+
+ if (!write_trylock(&eb->lock))
+ return 0;
+
if (atomic_read(&eb->blocking_writers) ||
atomic_read(&eb->blocking_readers)) {
write_unlock(&eb->lock);
@@ -168,14 +177,15 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
*/
void btrfs_tree_read_unlock(struct extent_buffer *eb)
{
- if (eb->lock_nested) {
- read_lock(&eb->lock);
- if (eb->lock_nested && current->pid == eb->lock_owner) {
- eb->lock_nested = 0;
- read_unlock(&eb->lock);
- return;
- }
- read_unlock(&eb->lock);
+ /*
+ * if we're nested, we have the write lock. No new locking
+ * is needed as long as we are the lock owner.
+ * The write unlock will do a barrier for us, and the lock_nested
+ * field only matters to the lock owner.
+ */
+ if (eb->lock_nested && current->pid == eb->lock_owner) {
+ eb->lock_nested = 0;
+ return;
}
btrfs_assert_tree_read_locked(eb);
WARN_ON(atomic_read(&eb->spinning_readers) == 0);
@@ -189,14 +199,15 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb)
*/
void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
{
- if (eb->lock_nested) {
- read_lock(&eb->lock);
- if (eb->lock_nested && current->pid == eb->lock_owner) {
- eb->lock_nested = 0;
- read_unlock(&eb->lock);
- return;
- }
- read_unlock(&eb->lock);
+ /*
+ * if we're nested, we have the write lock. No new locking
+ * is needed as long as we are the lock owner.
+ * The write unlock will do a barrier for us, and the lock_nested
+ * field only matters to the lock owner.
+ */
+ if (eb->lock_nested && current->pid == eb->lock_owner) {
+ eb->lock_nested = 0;
+ return;
}
btrfs_assert_tree_read_locked(eb);
WARN_ON(atomic_read(&eb->blocking_readers) == 0);
@@ -244,6 +255,7 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
BUG_ON(blockers > 1);
btrfs_assert_tree_locked(eb);
+ eb->lock_owner = 0;
atomic_dec(&eb->write_locks);
if (blockers) {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index cf5aead95a7f..98cb6b2630f9 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1798,8 +1798,10 @@ static int qgroup_shared_accounting(struct btrfs_trans_handle *trans,
return -ENOMEM;
tmp = ulist_alloc(GFP_NOFS);
- if (!tmp)
+ if (!tmp) {
+ ulist_free(qgroups);
return -ENOMEM;
+ }
btrfs_get_tree_mod_seq(fs_info, &elem);
ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, elem.seq,
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 30947f923620..09230cf3a244 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -428,8 +428,13 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
continue;
}
if (!dev->bdev) {
- /* cannot read ahead on missing device */
- continue;
+ /*
+ * cannot read ahead on missing device, but for RAID5/6,
+ * REQ_GET_READ_MIRRORS return 1. So don't skip missing
+ * device for such case.
+ */
+ if (nzones > 1)
+ continue;
}
if (dev_replace_is_ongoing &&
dev == fs_info->dev_replace.tgtdev) {
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index ac80188eec88..b6d198f5181e 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2725,11 +2725,8 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
length = btrfs_dev_extent_length(l, dev_extent);
- if (found_key.offset + length <= start) {
- key.offset = found_key.offset + length;
- btrfs_release_path(path);
- continue;
- }
+ if (found_key.offset + length <= start)
+ goto skip;
chunk_tree = btrfs_dev_extent_chunk_tree(l, dev_extent);
chunk_objectid = btrfs_dev_extent_chunk_objectid(l, dev_extent);
@@ -2740,10 +2737,12 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
* the chunk from going away while we scrub it
*/
cache = btrfs_lookup_block_group(fs_info, chunk_offset);
- if (!cache) {
- ret = -ENOENT;
- break;
- }
+
+ /* some chunks are removed but not committed to disk yet,
+ * continue scrubbing */
+ if (!cache)
+ goto skip;
+
dev_replace->cursor_right = found_key.offset + length;
dev_replace->cursor_left = found_key.offset;
dev_replace->item_needs_writeback = 1;
@@ -2802,7 +2801,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
dev_replace->cursor_left = dev_replace->cursor_right;
dev_replace->item_needs_writeback = 1;
-
+skip:
key.offset = found_key.offset + length;
btrfs_release_path(path);
}
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index a5dcacb5df9c..9626252ee6b4 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -135,7 +135,7 @@ restart:
radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) {
struct extent_buffer *eb;
- eb = radix_tree_deref_slot(slot);
+ eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock);
if (!eb)
continue;
/* Shouldn't happen but that kind of thinking creates CVE's */
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index fa691b754aaf..ec3dcb202357 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -415,6 +415,8 @@ int btrfs_test_qgroups(void)
ret = -ENOMEM;
goto out;
}
+ btrfs_set_header_level(root->node, 0);
+ btrfs_set_header_nritems(root->node, 0);
root->alloc_bytenr += 8192;
tmp_root = btrfs_alloc_dummy_root();
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 9630f10f8e1e..511839c04f11 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1284,11 +1284,13 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
goto fail;
}
- pending->error = btrfs_qgroup_inherit(trans, fs_info,
- root->root_key.objectid,
- objectid, pending->inherit);
- if (pending->error)
- goto no_free_objectid;
+ ret = btrfs_qgroup_inherit(trans, fs_info,
+ root->root_key.objectid,
+ objectid, pending->inherit);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto fail;
+ }
/* see comments in should_cow_block() */
set_bit(BTRFS_ROOT_FORCE_COW, &root->state);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ffeed6d6326f..c83b24251e53 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2543,9 +2543,6 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
remove_extent_mapping(em_tree, em);
write_unlock(&em_tree->lock);
- kfree(map);
- em->bdev = NULL;
-
/* once for the tree */
free_extent_map(em);
/* once for us */
@@ -4301,9 +4298,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
em = alloc_extent_map();
if (!em) {
+ kfree(map);
ret = -ENOMEM;
goto error;
}
+ set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
em->bdev = (struct block_device *)map;
em->start = start;
em->len = num_bytes;
@@ -4346,7 +4345,6 @@ error_del_extent:
/* One for the tree reference */
free_extent_map(em);
error:
- kfree(map);
kfree(devices_info);
return ret;
}
@@ -4558,7 +4556,6 @@ void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree)
write_unlock(&tree->map_tree.lock);
if (!em)
break;
- kfree(em->bdev);
/* once for us */
free_extent_map(em);
/* once for the tree */
@@ -5362,6 +5359,15 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
return 0;
}
+static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err)
+{
+ if (likely(bbio->flags & BTRFS_BIO_ORIG_BIO_SUBMITTED))
+ bio_endio_nodec(bio, err);
+ else
+ bio_endio(bio, err);
+ kfree(bbio);
+}
+
static void btrfs_end_bio(struct bio *bio, int err)
{
struct btrfs_bio *bbio = bio->bi_private;
@@ -5402,12 +5408,6 @@ static void btrfs_end_bio(struct bio *bio, int err)
bio = bbio->orig_bio;
}
- /*
- * We have original bio now. So increment bi_remaining to
- * account for it in endio
- */
- atomic_inc(&bio->bi_remaining);
-
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
@@ -5424,9 +5424,8 @@ static void btrfs_end_bio(struct bio *bio, int err)
set_bit(BIO_UPTODATE, &bio->bi_flags);
err = 0;
}
- kfree(bbio);
- bio_endio(bio, err);
+ btrfs_end_bbio(bbio, bio, err);
} else if (!is_orig_bio) {
bio_put(bio);
}
@@ -5589,12 +5588,15 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
{
atomic_inc(&bbio->error);
if (atomic_dec_and_test(&bbio->stripes_pending)) {
+ /* Shoud be the original bio. */
+ WARN_ON(bio != bbio->orig_bio);
+
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
bio->bi_iter.bi_sector = logical >> 9;
- kfree(bbio);
- bio_endio(bio, -EIO);
+
+ btrfs_end_bbio(bbio, bio, -EIO);
}
}
@@ -5681,6 +5683,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
BUG_ON(!bio); /* -ENOMEM */
} else {
bio = first_bio;
+ bbio->flags |= BTRFS_BIO_ORIG_BIO_SUBMITTED;
}
submit_stripe_bio(root, bbio, bio,
@@ -5822,6 +5825,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
return -ENOMEM;
}
+ set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
em->bdev = (struct block_device *)map;
em->start = logical;
em->len = length;
@@ -5846,7 +5850,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
map->stripes[i].dev = btrfs_find_device(root->fs_info, devid,
uuid, NULL);
if (!map->stripes[i].dev && !btrfs_test_opt(root, DEGRADED)) {
- kfree(map);
free_extent_map(em);
return -EIO;
}
@@ -5854,7 +5857,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
map->stripes[i].dev =
add_missing_dev(root, devid, uuid);
if (!map->stripes[i].dev) {
- kfree(map);
free_extent_map(em);
return -EIO;
}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1a15bbeb65e2..2aaa00c47816 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -190,11 +190,14 @@ struct btrfs_bio_stripe {
struct btrfs_bio;
typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
+#define BTRFS_BIO_ORIG_BIO_SUBMITTED 0x1
+
struct btrfs_bio {
atomic_t stripes_pending;
struct btrfs_fs_info *fs_info;
bio_end_io_t *end_io;
struct bio *orig_bio;
+ unsigned long flags;
void *private;
atomic_t error;
int max_errors;
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 21887d63dad5..469f2e8657e8 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -104,12 +104,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
struct dentry *dentry;
- if (acl) {
- ret = posix_acl_valid(acl);
- if (ret < 0)
- goto out;
- }
-
switch (type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 4f3f69079f36..90b3954d48ed 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -211,18 +211,15 @@ static int readpage_nounlock(struct file *filp, struct page *page)
SetPageError(page);
ceph_fscache_readpage_cancel(inode, page);
goto out;
- } else {
- if (err < PAGE_CACHE_SIZE) {
- /* zero fill remainder of page */
- zero_user_segment(page, err, PAGE_CACHE_SIZE);
- } else {
- flush_dcache_page(page);
- }
}
- SetPageUptodate(page);
+ if (err < PAGE_CACHE_SIZE)
+ /* zero fill remainder of page */
+ zero_user_segment(page, err, PAGE_CACHE_SIZE);
+ else
+ flush_dcache_page(page);
- if (err >= 0)
- ceph_readpage_to_fscache(inode, page);
+ SetPageUptodate(page);
+ ceph_readpage_to_fscache(inode, page);
out:
return err < 0 ? err : 0;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index c561b628ebce..1fde164b74b5 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -221,8 +221,8 @@ int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
return 0;
}
-static struct ceph_cap *get_cap(struct ceph_mds_client *mdsc,
- struct ceph_cap_reservation *ctx)
+struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+ struct ceph_cap_reservation *ctx)
{
struct ceph_cap *cap = NULL;
@@ -508,15 +508,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap,
* it is < 0. (This is so we can atomically add the cap and add an
* open file reference to it.)
*/
-int ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
- unsigned seq, unsigned mseq, u64 realmino, int flags,
- struct ceph_cap_reservation *caps_reservation)
+void ceph_add_cap(struct inode *inode,
+ struct ceph_mds_session *session, u64 cap_id,
+ int fmode, unsigned issued, unsigned wanted,
+ unsigned seq, unsigned mseq, u64 realmino, int flags,
+ struct ceph_cap **new_cap)
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_cap *new_cap = NULL;
struct ceph_cap *cap;
int mds = session->s_mds;
int actual_wanted;
@@ -531,20 +530,10 @@ int ceph_add_cap(struct inode *inode,
if (fmode >= 0)
wanted |= ceph_caps_for_mode(fmode);
-retry:
- spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
if (!cap) {
- if (new_cap) {
- cap = new_cap;
- new_cap = NULL;
- } else {
- spin_unlock(&ci->i_ceph_lock);
- new_cap = get_cap(mdsc, caps_reservation);
- if (new_cap == NULL)
- return -ENOMEM;
- goto retry;
- }
+ cap = *new_cap;
+ *new_cap = NULL;
cap->issued = 0;
cap->implemented = 0;
@@ -562,9 +551,6 @@ retry:
session->s_nr_caps++;
spin_unlock(&session->s_cap_lock);
} else {
- if (new_cap)
- ceph_put_cap(mdsc, new_cap);
-
/*
* auth mds of the inode changed. we received the cap export
* message, but still haven't received the cap import message.
@@ -626,7 +612,6 @@ retry:
ci->i_auth_cap = cap;
cap->mds_wanted = wanted;
}
- ci->i_cap_exporting_issued = 0;
} else {
WARN_ON(ci->i_auth_cap == cap);
}
@@ -648,9 +633,6 @@ retry:
if (fmode >= 0)
__ceph_get_fmode(ci, fmode);
- spin_unlock(&ci->i_ceph_lock);
- wake_up_all(&ci->i_cap_wq);
- return 0;
}
/*
@@ -685,7 +667,7 @@ static int __cap_is_valid(struct ceph_cap *cap)
*/
int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented)
{
- int have = ci->i_snap_caps | ci->i_cap_exporting_issued;
+ int have = ci->i_snap_caps;
struct ceph_cap *cap;
struct rb_node *p;
@@ -900,7 +882,7 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
*/
static int __ceph_is_any_caps(struct ceph_inode_info *ci)
{
- return !RB_EMPTY_ROOT(&ci->i_caps) || ci->i_cap_exporting_issued;
+ return !RB_EMPTY_ROOT(&ci->i_caps);
}
int ceph_is_any_caps(struct inode *inode)
@@ -2397,32 +2379,30 @@ static void invalidate_aliases(struct inode *inode)
* actually be a revocation if it specifies a smaller cap set.)
*
* caller holds s_mutex and i_ceph_lock, we drop both.
- *
- * return value:
- * 0 - ok
- * 1 - check_caps on auth cap only (writeback)
- * 2 - check_caps (ack revoke)
*/
-static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
+static void handle_cap_grant(struct ceph_mds_client *mdsc,
+ struct inode *inode, struct ceph_mds_caps *grant,
+ void *snaptrace, int snaptrace_len,
+ struct ceph_buffer *xattr_buf,
struct ceph_mds_session *session,
- struct ceph_cap *cap,
- struct ceph_buffer *xattr_buf)
- __releases(ci->i_ceph_lock)
+ struct ceph_cap *cap, int issued)
+ __releases(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
int mds = session->s_mds;
int seq = le32_to_cpu(grant->seq);
int newcaps = le32_to_cpu(grant->caps);
- int issued, implemented, used, wanted, dirty;
+ int used, wanted, dirty;
u64 size = le64_to_cpu(grant->size);
u64 max_size = le64_to_cpu(grant->max_size);
struct timespec mtime, atime, ctime;
int check_caps = 0;
- int wake = 0;
- int writeback = 0;
- int queue_invalidate = 0;
- int deleted_inode = 0;
- int queue_revalidate = 0;
+ bool wake = 0;
+ bool writeback = 0;
+ bool queue_trunc = 0;
+ bool queue_invalidate = 0;
+ bool queue_revalidate = 0;
+ bool deleted_inode = 0;
dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n",
inode, cap, mds, seq, ceph_cap_string(newcaps));
@@ -2466,16 +2446,13 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
}
/* side effects now are allowed */
-
- issued = __ceph_caps_issued(ci, &implemented);
- issued |= implemented | __ceph_caps_dirty(ci);
-
cap->cap_gen = session->s_cap_gen;
cap->seq = seq;
__check_cap_issue(ci, cap, newcaps);
- if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+ if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+ (issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(grant->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid));
@@ -2484,7 +2461,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
from_kgid(&init_user_ns, inode->i_gid));
}
- if ((issued & CEPH_CAP_LINK_EXCL) == 0) {
+ if ((newcaps & CEPH_CAP_AUTH_SHARED) &&
+ (issued & CEPH_CAP_LINK_EXCL) == 0) {
set_nlink(inode, le32_to_cpu(grant->nlink));
if (inode->i_nlink == 0 &&
(newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL)))
@@ -2511,30 +2489,35 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1)
queue_revalidate = 1;
- /* size/ctime/mtime/atime? */
- ceph_fill_file_size(inode, issued,
- le32_to_cpu(grant->truncate_seq),
- le64_to_cpu(grant->truncate_size), size);
- ceph_decode_timespec(&mtime, &grant->mtime);
- ceph_decode_timespec(&atime, &grant->atime);
- ceph_decode_timespec(&ctime, &grant->ctime);
- ceph_fill_file_time(inode, issued,
- le32_to_cpu(grant->time_warp_seq), &ctime, &mtime,
- &atime);
-
-
- /* file layout may have changed */
- ci->i_layout = grant->layout;
-
- /* max size increase? */
- if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
- dout("max_size %lld -> %llu\n", ci->i_max_size, max_size);
- ci->i_max_size = max_size;
- if (max_size >= ci->i_wanted_max_size) {
- ci->i_wanted_max_size = 0; /* reset */
- ci->i_requested_max_size = 0;
+ if (newcaps & CEPH_CAP_ANY_RD) {
+ /* ctime/mtime/atime? */
+ ceph_decode_timespec(&mtime, &grant->mtime);
+ ceph_decode_timespec(&atime, &grant->atime);
+ ceph_decode_timespec(&ctime, &grant->ctime);
+ ceph_fill_file_time(inode, issued,
+ le32_to_cpu(grant->time_warp_seq),
+ &ctime, &mtime, &atime);
+ }
+
+ if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) {
+ /* file layout may have changed */
+ ci->i_layout = grant->layout;
+ /* size/truncate_seq? */
+ queue_trunc = ceph_fill_file_size(inode, issued,
+ le32_to_cpu(grant->truncate_seq),
+ le64_to_cpu(grant->truncate_size),
+ size);
+ /* max size increase? */
+ if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
+ dout("max_size %lld -> %llu\n",
+ ci->i_max_size, max_size);
+ ci->i_max_size = max_size;
+ if (max_size >= ci->i_wanted_max_size) {
+ ci->i_wanted_max_size = 0; /* reset */
+ ci->i_requested_max_size = 0;
+ }
+ wake = 1;
}
- wake = 1;
}
/* check cap bits */
@@ -2595,6 +2578,23 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
spin_unlock(&ci->i_ceph_lock);
+ if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) {
+ down_write(&mdsc->snap_rwsem);
+ ceph_update_snap_trace(mdsc, snaptrace,
+ snaptrace + snaptrace_len, false);
+ downgrade_write(&mdsc->snap_rwsem);
+ kick_flushing_inode_caps(mdsc, session, inode);
+ up_read(&mdsc->snap_rwsem);
+ if (newcaps & ~issued)
+ wake = 1;
+ }
+
+ if (queue_trunc) {
+ ceph_queue_vmtruncate(inode);
+ ceph_queue_revalidate(inode);
+ } else if (queue_revalidate)
+ ceph_queue_revalidate(inode);
+
if (writeback)
/*
* queue inode for writeback: we can't actually call
@@ -2606,8 +2606,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant,
ceph_queue_invalidate(inode);
if (deleted_inode)
invalidate_aliases(inode);
- if (queue_revalidate)
- ceph_queue_revalidate(inode);
if (wake)
wake_up_all(&ci->i_cap_wq);
@@ -2784,7 +2782,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
{
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_session *tsession = NULL;
- struct ceph_cap *cap, *tcap;
+ struct ceph_cap *cap, *tcap, *new_cap = NULL;
struct ceph_inode_info *ci = ceph_inode(inode);
u64 t_cap_id;
unsigned mseq = le32_to_cpu(ex->migrate_seq);
@@ -2807,7 +2805,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex,
retry:
spin_lock(&ci->i_ceph_lock);
cap = __get_cap_for_mds(ci, mds);
- if (!cap)
+ if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id))
goto out_unlock;
if (target < 0) {
@@ -2846,15 +2844,14 @@ retry:
}
__ceph_remove_cap(cap, false);
goto out_unlock;
- }
-
- if (tsession) {
- int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
- spin_unlock(&ci->i_ceph_lock);
+ } else if (tsession) {
/* add placeholder for the export tagert */
+ int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
- t_seq - 1, t_mseq, (u64)-1, flag, NULL);
- goto retry;
+ t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
+
+ __ceph_remove_cap(cap, false);
+ goto out_unlock;
}
spin_unlock(&ci->i_ceph_lock);
@@ -2873,6 +2870,7 @@ retry:
SINGLE_DEPTH_NESTING);
}
ceph_add_cap_releases(mdsc, tsession);
+ new_cap = ceph_get_cap(mdsc, NULL);
} else {
WARN_ON(1);
tsession = NULL;
@@ -2887,24 +2885,27 @@ out_unlock:
mutex_unlock(&tsession->s_mutex);
ceph_put_mds_session(tsession);
}
+ if (new_cap)
+ ceph_put_cap(mdsc, new_cap);
}
/*
- * Handle cap IMPORT. If there are temp bits from an older EXPORT,
- * clean them up.
+ * Handle cap IMPORT.
*
- * caller holds s_mutex.
+ * caller holds s_mutex. acquires i_ceph_lock
*/
static void handle_cap_import(struct ceph_mds_client *mdsc,
struct inode *inode, struct ceph_mds_caps *im,
struct ceph_mds_cap_peer *ph,
struct ceph_mds_session *session,
- void *snaptrace, int snaptrace_len)
+ struct ceph_cap **target_cap, int *old_issued)
+ __acquires(ci->i_ceph_lock)
{
struct ceph_inode_info *ci = ceph_inode(inode);
- struct ceph_cap *cap;
+ struct ceph_cap *cap, *ocap, *new_cap = NULL;
int mds = session->s_mds;
- unsigned issued = le32_to_cpu(im->caps);
+ int issued;
+ unsigned caps = le32_to_cpu(im->caps);
unsigned wanted = le32_to_cpu(im->wanted);
unsigned seq = le32_to_cpu(im->seq);
unsigned mseq = le32_to_cpu(im->migrate_seq);
@@ -2924,40 +2925,52 @@ static void handle_cap_import(struct ceph_mds_client *mdsc,
dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n",
inode, ci, mds, mseq, peer);
+retry:
spin_lock(&ci->i_ceph_lock);
- cap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
- if (cap && cap->cap_id == p_cap_id) {
+ cap = __get_cap_for_mds(ci, mds);
+ if (!cap) {
+ if (!new_cap) {
+ spin_unlock(&ci->i_ceph_lock);
+ new_cap = ceph_get_cap(mdsc, NULL);
+ goto retry;
+ }
+ cap = new_cap;
+ } else {
+ if (new_cap) {
+ ceph_put_cap(mdsc, new_cap);
+ new_cap = NULL;
+ }
+ }
+
+ __ceph_caps_issued(ci, &issued);
+ issued |= __ceph_caps_dirty(ci);
+
+ ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq,
+ realmino, CEPH_CAP_FLAG_AUTH, &new_cap);
+
+ ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL;
+ if (ocap && ocap->cap_id == p_cap_id) {
dout(" remove export cap %p mds%d flags %d\n",
- cap, peer, ph->flags);
+ ocap, peer, ph->flags);
if ((ph->flags & CEPH_CAP_FLAG_AUTH) &&
- (cap->seq != le32_to_cpu(ph->seq) ||
- cap->mseq != le32_to_cpu(ph->mseq))) {
+ (ocap->seq != le32_to_cpu(ph->seq) ||
+ ocap->mseq != le32_to_cpu(ph->mseq))) {
pr_err("handle_cap_import: mismatched seq/mseq: "
"ino (%llx.%llx) mds%d seq %d mseq %d "
"importer mds%d has peer seq %d mseq %d\n",
- ceph_vinop(inode), peer, cap->seq,
- cap->mseq, mds, le32_to_cpu(ph->seq),
+ ceph_vinop(inode), peer, ocap->seq,
+ ocap->mseq, mds, le32_to_cpu(ph->seq),
le32_to_cpu(ph->mseq));
}
- ci->i_cap_exporting_issued = cap->issued;
- __ceph_remove_cap(cap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
+ __ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE));
}
/* make sure we re-request max_size, if necessary */
ci->i_wanted_max_size = 0;
ci->i_requested_max_size = 0;
- spin_unlock(&ci->i_ceph_lock);
-
- down_write(&mdsc->snap_rwsem);
- ceph_update_snap_trace(mdsc, snaptrace, snaptrace+snaptrace_len,
- false);
- downgrade_write(&mdsc->snap_rwsem);
- ceph_add_cap(inode, session, cap_id, -1,
- issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH,
- NULL /* no caps context */);
- kick_flushing_inode_caps(mdsc, session, inode);
- up_read(&mdsc->snap_rwsem);
+ *old_issued = issued;
+ *target_cap = cap;
}
/*
@@ -2977,7 +2990,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_mds_caps *h;
struct ceph_mds_cap_peer *peer = NULL;
int mds = session->s_mds;
- int op;
+ int op, issued;
u32 seq, mseq;
struct ceph_vino vino;
u64 cap_id;
@@ -3069,7 +3082,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
case CEPH_CAP_OP_IMPORT:
handle_cap_import(mdsc, inode, h, peer, session,
- snaptrace, snaptrace_len);
+ &cap, &issued);
+ handle_cap_grant(mdsc, inode, h, snaptrace, snaptrace_len,
+ msg->middle, session, cap, issued);
+ goto done_unlocked;
}
/* the rest require a cap */
@@ -3086,8 +3102,10 @@ void ceph_handle_caps(struct ceph_mds_session *session,
switch (op) {
case CEPH_CAP_OP_REVOKE:
case CEPH_CAP_OP_GRANT:
- case CEPH_CAP_OP_IMPORT:
- handle_cap_grant(inode, h, session, cap, msg->middle);
+ __ceph_caps_issued(ci, &issued);
+ issued |= __ceph_caps_dirty(ci);
+ handle_cap_grant(mdsc, inode, h, NULL, 0, msg->middle,
+ session, cap, issued);
goto done_unlocked;
case CEPH_CAP_OP_FLUSH_ACK:
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 00d6af6a32ec..8d7d782f4382 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -169,7 +169,7 @@ static struct dentry *__get_parent(struct super_block *sb,
return dentry;
}
-struct dentry *ceph_get_parent(struct dentry *child)
+static struct dentry *ceph_get_parent(struct dentry *child)
{
/* don't re-export snaps */
if (ceph_snap(child->d_inode) != CEPH_NOSNAP)
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e4fff9ff1c27..04c89c266cec 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -10,6 +10,7 @@
#include <linux/writeback.h>
#include <linux/vmalloc.h>
#include <linux/posix_acl.h>
+#include <linux/random.h>
#include "super.h"
#include "mds_client.h"
@@ -179,9 +180,8 @@ struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f)
* specified, copy the frag delegation info to the caller if
* it is present.
*/
-u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
- struct ceph_inode_frag *pfrag,
- int *found)
+static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+ struct ceph_inode_frag *pfrag, int *found)
{
u32 t = ceph_frag_make(0, 0);
struct ceph_inode_frag *frag;
@@ -191,7 +191,6 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
if (found)
*found = 0;
- mutex_lock(&ci->i_fragtree_mutex);
while (1) {
WARN_ON(!ceph_frag_contains_value(t, v));
frag = __ceph_find_frag(ci, t);
@@ -220,10 +219,19 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
}
dout("choose_frag(%x) = %x\n", v, t);
- mutex_unlock(&ci->i_fragtree_mutex);
return t;
}
+u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
+ struct ceph_inode_frag *pfrag, int *found)
+{
+ u32 ret;
+ mutex_lock(&ci->i_fragtree_mutex);
+ ret = __ceph_choose_frag(ci, v, pfrag, found);
+ mutex_unlock(&ci->i_fragtree_mutex);
+ return ret;
+}
+
/*
* Process dirfrag (delegation) info from the mds. Include leaf
* fragment in tree ONLY if ndist > 0. Otherwise, only
@@ -237,11 +245,17 @@ static int ceph_fill_dirfrag(struct inode *inode,
u32 id = le32_to_cpu(dirinfo->frag);
int mds = le32_to_cpu(dirinfo->auth);
int ndist = le32_to_cpu(dirinfo->ndist);
+ int diri_auth = -1;
int i;
int err = 0;
+ spin_lock(&ci->i_ceph_lock);
+ if (ci->i_auth_cap)
+ diri_auth = ci->i_auth_cap->mds;
+ spin_unlock(&ci->i_ceph_lock);
+
mutex_lock(&ci->i_fragtree_mutex);
- if (ndist == 0) {
+ if (ndist == 0 && mds == diri_auth) {
/* no delegation info needed. */
frag = __ceph_find_frag(ci, id);
if (!frag)
@@ -286,6 +300,75 @@ out:
return err;
}
+static int ceph_fill_fragtree(struct inode *inode,
+ struct ceph_frag_tree_head *fragtree,
+ struct ceph_mds_reply_dirfrag *dirinfo)
+{
+ struct ceph_inode_info *ci = ceph_inode(inode);
+ struct ceph_inode_frag *frag;
+ struct rb_node *rb_node;
+ int i;
+ u32 id, nsplits;
+ bool update = false;
+
+ mutex_lock(&ci->i_fragtree_mutex);
+ nsplits = le32_to_cpu(fragtree->nsplits);
+ if (nsplits) {
+ i = prandom_u32() % nsplits;
+ id = le32_to_cpu(fragtree->splits[i].frag);
+ if (!__ceph_find_frag(ci, id))
+ update = true;
+ } else if (!RB_EMPTY_ROOT(&ci->i_fragtree)) {
+ rb_node = rb_first(&ci->i_fragtree);
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ if (frag->frag != ceph_frag_make(0, 0) || rb_next(rb_node))
+ update = true;
+ }
+ if (!update && dirinfo) {
+ id = le32_to_cpu(dirinfo->frag);
+ if (id != __ceph_choose_frag(ci, id, NULL, NULL))
+ update = true;
+ }
+ if (!update)
+ goto out_unlock;
+
+ dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode));
+ rb_node = rb_first(&ci->i_fragtree);
+ for (i = 0; i < nsplits; i++) {
+ id = le32_to_cpu(fragtree->splits[i].frag);
+ frag = NULL;
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ if (ceph_frag_compare(frag->frag, id) >= 0) {
+ if (frag->frag != id)
+ frag = NULL;
+ else
+ rb_node = rb_next(rb_node);
+ break;
+ }
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ frag = NULL;
+ }
+ if (!frag) {
+ frag = __get_or_create_frag(ci, id);
+ if (IS_ERR(frag))
+ continue;
+ }
+ frag->split_by = le32_to_cpu(fragtree->splits[i].by);
+ dout(" frag %x split by %d\n", frag->frag, frag->split_by);
+ }
+ while (rb_node) {
+ frag = rb_entry(rb_node, struct ceph_inode_frag, node);
+ rb_node = rb_next(rb_node);
+ rb_erase(&frag->node, &ci->i_fragtree);
+ kfree(frag);
+ }
+out_unlock:
+ mutex_unlock(&ci->i_fragtree_mutex);
+ return 0;
+}
/*
* initialize a newly allocated inode.
@@ -341,7 +424,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&ci->i_cap_snaps);
ci->i_head_snapc = NULL;
ci->i_snap_caps = 0;
- ci->i_cap_exporting_issued = 0;
for (i = 0; i < CEPH_FILE_MODE_NUM; i++)
ci->i_nr_by_mode[i] = 0;
@@ -407,7 +489,7 @@ void ceph_destroy_inode(struct inode *inode)
/*
* we may still have a snap_realm reference if there are stray
- * caps in i_cap_exporting_issued or i_snap_caps.
+ * caps in i_snap_caps.
*/
if (ci->i_snap_realm) {
struct ceph_mds_client *mdsc =
@@ -582,22 +664,26 @@ static int fill_inode(struct inode *inode,
unsigned long ttl_from, int cap_fmode,
struct ceph_cap_reservation *caps_reservation)
{
+ struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
struct ceph_mds_reply_inode *info = iinfo->in;
struct ceph_inode_info *ci = ceph_inode(inode);
- int i;
- int issued = 0, implemented;
+ int issued = 0, implemented, new_issued;
struct timespec mtime, atime, ctime;
- u32 nsplits;
- struct ceph_inode_frag *frag;
- struct rb_node *rb_node;
struct ceph_buffer *xattr_blob = NULL;
+ struct ceph_cap *new_cap = NULL;
int err = 0;
- int queue_trunc = 0;
+ bool wake = false;
+ bool queue_trunc = false;
+ bool new_version = false;
dout("fill_inode %p ino %llx.%llx v %llu had %llu\n",
inode, ceph_vinop(inode), le64_to_cpu(info->version),
ci->i_version);
+ /* prealloc new cap struct */
+ if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP)
+ new_cap = ceph_get_cap(mdsc, caps_reservation);
+
/*
* prealloc xattr data, if it looks like we'll need it. only
* if len > 4 (meaning there are actually xattrs; the first 4
@@ -623,19 +709,23 @@ static int fill_inode(struct inode *inode,
* 3 2 skip
* 3 3 update
*/
- if (le64_to_cpu(info->version) > 0 &&
- (ci->i_version & ~1) >= le64_to_cpu(info->version))
- goto no_change;
-
+ if (ci->i_version == 0 ||
+ ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+ le64_to_cpu(info->version) > (ci->i_version & ~1)))
+ new_version = true;
+
issued = __ceph_caps_issued(ci, &implemented);
issued |= implemented | __ceph_caps_dirty(ci);
+ new_issued = ~issued & le32_to_cpu(info->cap.caps);
/* update inode */
ci->i_version = le64_to_cpu(info->version);
inode->i_version++;
inode->i_rdev = le32_to_cpu(info->rdev);
+ inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
- if ((issued & CEPH_CAP_AUTH_EXCL) == 0) {
+ if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) &&
+ (issued & CEPH_CAP_AUTH_EXCL) == 0) {
inode->i_mode = le32_to_cpu(info->mode);
inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid));
inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid));
@@ -644,23 +734,35 @@ static int fill_inode(struct inode *inode,
from_kgid(&init_user_ns, inode->i_gid));
}
- if ((issued & CEPH_CAP_LINK_EXCL) == 0)
+ if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) &&
+ (issued & CEPH_CAP_LINK_EXCL) == 0)
set_nlink(inode, le32_to_cpu(info->nlink));
- /* be careful with mtime, atime, size */
- ceph_decode_timespec(&atime, &info->atime);
- ceph_decode_timespec(&mtime, &info->mtime);
- ceph_decode_timespec(&ctime, &info->ctime);
- queue_trunc = ceph_fill_file_size(inode, issued,
- le32_to_cpu(info->truncate_seq),
- le64_to_cpu(info->truncate_size),
- le64_to_cpu(info->size));
- ceph_fill_file_time(inode, issued,
- le32_to_cpu(info->time_warp_seq),
- &ctime, &mtime, &atime);
-
- ci->i_layout = info->layout;
- inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1;
+ if (new_version || (new_issued & CEPH_CAP_ANY_RD)) {
+ /* be careful with mtime, atime, size */
+ ceph_decode_timespec(&atime, &info->atime);
+ ceph_decode_timespec(&mtime, &info->mtime);
+ ceph_decode_timespec(&ctime, &info->ctime);
+ ceph_fill_file_time(inode, issued,
+ le32_to_cpu(info->time_warp_seq),
+ &ctime, &mtime, &atime);
+ }
+
+ if (new_version ||
+ (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) {
+ ci->i_layout = info->layout;
+ queue_trunc = ceph_fill_file_size(inode, issued,
+ le32_to_cpu(info->truncate_seq),
+ le64_to_cpu(info->truncate_size),
+ le64_to_cpu(info->size));
+ /* only update max_size on auth cap */
+ if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
+ ci->i_max_size != le64_to_cpu(info->max_size)) {
+ dout("max_size %lld -> %llu\n", ci->i_max_size,
+ le64_to_cpu(info->max_size));
+ ci->i_max_size = le64_to_cpu(info->max_size);
+ }
+ }
/* xattrs */
/* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */
@@ -745,58 +847,6 @@ static int fill_inode(struct inode *inode,
dout(" marking %p complete (empty)\n", inode);
__ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count));
}
-no_change:
- /* only update max_size on auth cap */
- if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) &&
- ci->i_max_size != le64_to_cpu(info->max_size)) {
- dout("max_size %lld -> %llu\n", ci->i_max_size,
- le64_to_cpu(info->max_size));
- ci->i_max_size = le64_to_cpu(info->max_size);
- }
-
- spin_unlock(&ci->i_ceph_lock);
-
- /* queue truncate if we saw i_size decrease */
- if (queue_trunc)
- ceph_queue_vmtruncate(inode);
-
- /* populate frag tree */
- /* FIXME: move me up, if/when version reflects fragtree changes */
- nsplits = le32_to_cpu(info->fragtree.nsplits);
- mutex_lock(&ci->i_fragtree_mutex);
- rb_node = rb_first(&ci->i_fragtree);
- for (i = 0; i < nsplits; i++) {
- u32 id = le32_to_cpu(info->fragtree.splits[i].frag);
- frag = NULL;
- while (rb_node) {
- frag = rb_entry(rb_node, struct ceph_inode_frag, node);
- if (ceph_frag_compare(frag->frag, id) >= 0) {
- if (frag->frag != id)
- frag = NULL;
- else
- rb_node = rb_next(rb_node);
- break;
- }
- rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
- frag = NULL;
- }
- if (!frag) {
- frag = __get_or_create_frag(ci, id);
- if (IS_ERR(frag))
- continue;
- }
- frag->split_by = le32_to_cpu(info->fragtree.splits[i].by);
- dout(" frag %x split by %d\n", frag->frag, frag->split_by);
- }
- while (rb_node) {
- frag = rb_entry(rb_node, struct ceph_inode_frag, node);
- rb_node = rb_next(rb_node);
- rb_erase(&frag->node, &ci->i_fragtree);
- kfree(frag);
- }
- mutex_unlock(&ci->i_fragtree_mutex);
/* were we issued a capability? */
if (info->cap.caps) {
@@ -809,30 +859,41 @@ no_change:
le32_to_cpu(info->cap.seq),
le32_to_cpu(info->cap.mseq),
le64_to_cpu(info->cap.realm),
- info->cap.flags,
- caps_reservation);
+ info->cap.flags, &new_cap);
+ wake = true;
} else {
- spin_lock(&ci->i_ceph_lock);
dout(" %p got snap_caps %s\n", inode,
ceph_cap_string(le32_to_cpu(info->cap.caps)));
ci->i_snap_caps |= le32_to_cpu(info->cap.caps);
if (cap_fmode >= 0)
__ceph_get_fmode(ci, cap_fmode);
- spin_unlock(&ci->i_ceph_lock);
}
} else if (cap_fmode >= 0) {
pr_warn("mds issued no caps on %llx.%llx\n",
ceph_vinop(inode));
__ceph_get_fmode(ci, cap_fmode);
}
+ spin_unlock(&ci->i_ceph_lock);
+
+ if (wake)
+ wake_up_all(&ci->i_cap_wq);
+
+ /* queue truncate if we saw i_size decrease */
+ if (queue_trunc)
+ ceph_queue_vmtruncate(inode);
+
+ /* populate frag tree */
+ if (S_ISDIR(inode->i_mode))
+ ceph_fill_fragtree(inode, &info->fragtree, dirinfo);
/* update delegation info? */
if (dirinfo)
ceph_fill_dirfrag(inode, dirinfo);
err = 0;
-
out:
+ if (new_cap)
+ ceph_put_cap(mdsc, new_cap);
if (xattr_blob)
ceph_buffer_put(xattr_blob);
return err;
@@ -1485,7 +1546,7 @@ static void ceph_invalidate_work(struct work_struct *work)
orig_gen = ci->i_rdcache_gen;
spin_unlock(&ci->i_ceph_lock);
- truncate_inode_pages(inode->i_mapping, 0);
+ truncate_pagecache(inode, 0);
spin_lock(&ci->i_ceph_lock);
if (orig_gen == ci->i_rdcache_gen &&
@@ -1588,7 +1649,7 @@ retry:
ci->i_truncate_pending, to);
spin_unlock(&ci->i_ceph_lock);
- truncate_inode_pages(inode->i_mapping, to);
+ truncate_pagecache(inode, to);
spin_lock(&ci->i_ceph_lock);
if (to == ci->i_truncate_size) {
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 9a33b98cb000..92a2548278fc 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1558,6 +1558,8 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
init_completion(&req->r_safe_completion);
INIT_LIST_HEAD(&req->r_unsafe_item);
+ req->r_stamp = CURRENT_TIME;
+
req->r_op = op;
req->r_direct_mode = mode;
return req;
@@ -1783,7 +1785,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
}
len = sizeof(*head) +
- pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64));
+ pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
+ sizeof(struct timespec);
/* calculate (max) length for cap releases */
len += sizeof(struct ceph_mds_request_release) *
@@ -1800,6 +1803,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
goto out_free2;
}
+ msg->hdr.version = 2;
msg->hdr.tid = cpu_to_le64(req->r_tid);
head = msg->front.iov_base;
@@ -1836,6 +1840,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
mds, req->r_old_inode_drop, req->r_old_inode_unless, 0);
head->num_releases = cpu_to_le16(releases);
+ /* time stamp */
+ ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp));
+
BUG_ON(p > end);
msg->front.iov_len = p - msg->front.iov_base;
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index e90cfccf93bd..e00737cf523c 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -194,6 +194,7 @@ struct ceph_mds_request {
int r_fmode; /* file mode, if expecting cap */
kuid_t r_uid;
kgid_t r_gid;
+ struct timespec r_stamp;
/* for choosing which mds to send this request to */
int r_direct_mode;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index ead05cc1f447..12b20744e386 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -292,7 +292,6 @@ struct ceph_inode_info {
struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or
dirty|flushing caps */
unsigned i_snap_caps; /* cap bits for snapped files */
- unsigned i_cap_exporting_issued;
int i_nr_by_mode[CEPH_FILE_MODE_NUM]; /* open file counts */
@@ -775,11 +774,13 @@ static inline void ceph_forget_all_cached_acls(struct inode *inode)
extern const char *ceph_cap_string(int c);
extern void ceph_handle_caps(struct ceph_mds_session *session,
struct ceph_msg *msg);
-extern int ceph_add_cap(struct inode *inode,
- struct ceph_mds_session *session, u64 cap_id,
- int fmode, unsigned issued, unsigned wanted,
- unsigned cap, unsigned seq, u64 realmino, int flags,
- struct ceph_cap_reservation *caps_reservation);
+extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc,
+ struct ceph_cap_reservation *ctx);
+extern void ceph_add_cap(struct inode *inode,
+ struct ceph_mds_session *session, u64 cap_id,
+ int fmode, unsigned issued, unsigned wanted,
+ unsigned cap, unsigned seq, u64 realmino, int flags,
+ struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 1e5b45359509..d08e079ea5d3 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -617,6 +617,11 @@ static void retry_failed_sctp_send(struct connection *recv_con,
int nodeid = sn_send_failed->ssf_info.sinfo_ppid;
log_print("Retry sending %d bytes to node id %d", len, nodeid);
+
+ if (!nodeid) {
+ log_print("Shouldn't resend data via listening connection.");
+ return;
+ }
con = nodeid2con(nodeid, 0);
if (!con) {
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index b73e0621ce9e..b10b48c2a7af 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -910,7 +910,7 @@ static const struct file_operations eventpoll_fops = {
void eventpoll_release_file(struct file *file)
{
struct eventpoll *ep;
- struct epitem *epi;
+ struct epitem *epi, *next;
/*
* We don't want to get "file->f_lock" because it is not
@@ -926,7 +926,7 @@ void eventpoll_release_file(struct file *file)
* Besides, ep_remove() acquires the lock, so we can't hold it here.
*/
mutex_lock(&epmutex);
- list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) {
+ list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
ep = epi->ep;
mutex_lock_nested(&ep->mtx, 0);
ep_remove(ep, epi);
diff --git a/fs/locks.c b/fs/locks.c
index da57c9b7e844..717fbc404e6b 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -431,7 +431,7 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl)
if (assign_type(fl, type) != 0)
return -EINVAL;
- fl->fl_owner = (fl_owner_t)filp;
+ fl->fl_owner = (fl_owner_t)current->files;
fl->fl_pid = current->tgid;
fl->fl_file = filp;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c0d45cec9958..2204e1fe5725 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -41,6 +41,7 @@
#include <linux/ratelimit.h>
#include <linux/sunrpc/svcauth_gss.h>
#include <linux/sunrpc/addr.h>
+#include <linux/hash.h>
#include "xdr4.h"
#include "xdr4cb.h"
#include "vfs.h"
@@ -364,6 +365,79 @@ static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
return openlockstateid(nfs4_alloc_stid(clp, stateid_slab));
}
+/*
+ * When we recall a delegation, we should be careful not to hand it
+ * out again straight away.
+ * To ensure this we keep a pair of bloom filters ('new' and 'old')
+ * in which the filehandles of recalled delegations are "stored".
+ * If a filehandle appear in either filter, a delegation is blocked.
+ * When a delegation is recalled, the filehandle is stored in the "new"
+ * filter.
+ * Every 30 seconds we swap the filters and clear the "new" one,
+ * unless both are empty of course.
+ *
+ * Each filter is 256 bits. We hash the filehandle to 32bit and use the
+ * low 3 bytes as hash-table indices.
+ *
+ * 'state_lock', which is always held when block_delegations() is called,
+ * is used to manage concurrent access. Testing does not need the lock
+ * except when swapping the two filters.
+ */
+static struct bloom_pair {
+ int entries, old_entries;
+ time_t swap_time;
+ int new; /* index into 'set' */
+ DECLARE_BITMAP(set[2], 256);
+} blocked_delegations;
+
+static int delegation_blocked(struct knfsd_fh *fh)
+{
+ u32 hash;
+ struct bloom_pair *bd = &blocked_delegations;
+
+ if (bd->entries == 0)
+ return 0;
+ if (seconds_since_boot() - bd->swap_time > 30) {
+ spin_lock(&state_lock);
+ if (seconds_since_boot() - bd->swap_time > 30) {
+ bd->entries -= bd->old_entries;
+ bd->old_entries = bd->entries;
+ memset(bd->set[bd->new], 0,
+ sizeof(bd->set[0]));
+ bd->new = 1-bd->new;
+ bd->swap_time = seconds_since_boot();
+ }
+ spin_unlock(&state_lock);
+ }
+ hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0);
+ if (test_bit(hash&255, bd->set[0]) &&
+ test_bit((hash>>8)&255, bd->set[0]) &&
+ test_bit((hash>>16)&255, bd->set[0]))
+ return 1;
+
+ if (test_bit(hash&255, bd->set[1]) &&
+ test_bit((hash>>8)&255, bd->set[1]) &&
+ test_bit((hash>>16)&255, bd->set[1]))
+ return 1;
+
+ return 0;
+}
+
+static void block_delegations(struct knfsd_fh *fh)
+{
+ u32 hash;
+ struct bloom_pair *bd = &blocked_delegations;
+
+ hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0);
+
+ __set_bit(hash&255, bd->set[bd->new]);
+ __set_bit((hash>>8)&255, bd->set[bd->new]);
+ __set_bit((hash>>16)&255, bd->set[bd->new]);
+ if (bd->entries == 0)
+ bd->swap_time = seconds_since_boot();
+ bd->entries += 1;
+}
+
static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh)
{
@@ -372,6 +446,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
dprintk("NFSD alloc_init_deleg\n");
if (num_delegations > max_delegations)
return NULL;
+ if (delegation_blocked(&current_fh->fh_handle))
+ return NULL;
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
if (dp == NULL)
return dp;
@@ -2770,6 +2846,8 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
/* Only place dl_time is set; protected by i_lock: */
dp->dl_time = get_seconds();
+ block_delegations(&dp->dl_fh);
+
nfsd4_cb_recall(dp);
}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2d305a121f37..83baf2bfe9e9 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2687,6 +2687,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
nfserr = nfserr_toosmall;
goto fail;
case nfserr_noent:
+ xdr_truncate_encode(xdr, start_offset);
goto skip_entry;
default:
/*
generated by cgit (git 2.34.1) at 2025-05-30 18:42:53 +0000