summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/async-thread.c120
-rw-r--r--fs/btrfs/async-thread.h4
-rw-r--r--fs/btrfs/ctree.h208
-rw-r--r--fs/btrfs/delayed-inode.c6
-rw-r--r--fs/btrfs/disk-io.c56
-rw-r--r--fs/btrfs/extent-tree.c345
-rw-r--r--fs/btrfs/extent_io.c24
-rw-r--r--fs/btrfs/file.c10
-rw-r--r--fs/btrfs/free-space-cache.c405
-rw-r--r--fs/btrfs/inode.c193
-rw-r--r--fs/btrfs/ioctl.c252
-rw-r--r--fs/btrfs/ioctl.h54
-rw-r--r--fs/btrfs/relocation.c2
-rw-r--r--fs/btrfs/scrub.c8
-rw-r--r--fs/btrfs/super.c81
-rw-r--r--fs/btrfs/transaction.c9
-rw-r--r--fs/btrfs/tree-log.c2
-rw-r--r--fs/btrfs/volumes.c989
-rw-r--r--fs/btrfs/volumes.h54
-rw-r--r--fs/btrfs/xattr.c50
20 files changed, 2175 insertions, 697 deletions
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 7ec14097fef..0b394580d86 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -64,6 +64,8 @@ struct btrfs_worker_thread {
int idle;
};
+static int __btrfs_start_workers(struct btrfs_workers *workers);
+
/*
* btrfs_start_workers uses kthread_run, which can block waiting for memory
* for a very long time. It will actually throttle on page writeback,
@@ -88,27 +90,10 @@ static void start_new_worker_func(struct btrfs_work *work)
{
struct worker_start *start;
start = container_of(work, struct worker_start, work);
- btrfs_start_workers(start->queue, 1);
+ __btrfs_start_workers(start->queue);
kfree(start);
}
-static int start_new_worker(struct btrfs_workers *queue)
-{
- struct worker_start *start;
- int ret;
-
- start = kzalloc(sizeof(*start), GFP_NOFS);
- if (!start)
- return -ENOMEM;
-
- start->work.func = start_new_worker_func;
- start->queue = queue;
- ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work);
- if (ret)
- kfree(start);
- return ret;
-}
-
/*
* helper function to move a thread onto the idle list after it
* has finished some requests.
@@ -153,12 +138,20 @@ static void check_busy_worker(struct btrfs_worker_thread *worker)
static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
{
struct btrfs_workers *workers = worker->workers;
+ struct worker_start *start;
unsigned long flags;
rmb();
if (!workers->atomic_start_pending)
return;
+ start = kzalloc(sizeof(*start), GFP_NOFS);
+ if (!start)
+ return;
+
+ start->work.func = start_new_worker_func;
+ start->queue = workers;
+
spin_lock_irqsave(&workers->lock, flags);
if (!workers->atomic_start_pending)
goto out;
@@ -170,10 +163,11 @@ static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
workers->num_workers_starting += 1;
spin_unlock_irqrestore(&workers->lock, flags);
- start_new_worker(workers);
+ btrfs_queue_worker(workers->atomic_worker_start, &start->work);
return;
out:
+ kfree(start);
spin_unlock_irqrestore(&workers->lock, flags);
}
@@ -331,7 +325,7 @@ again:
run_ordered_completions(worker->workers, work);
check_pending_worker_creates(worker);
-
+ cond_resched();
}
spin_lock_irq(&worker->lock);
@@ -462,56 +456,55 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
* starts new worker threads. This does not enforce the max worker
* count in case you need to temporarily go past it.
*/
-static int __btrfs_start_workers(struct btrfs_workers *workers,
- int num_workers)
+static int __btrfs_start_workers(struct btrfs_workers *workers)
{
struct btrfs_worker_thread *worker;
int ret = 0;
- int i;
- for (i = 0; i < num_workers; i++) {
- worker = kzalloc(sizeof(*worker), GFP_NOFS);
- if (!worker) {
- ret = -ENOMEM;
- goto fail;
- }
+ worker = kzalloc(sizeof(*worker), GFP_NOFS);
+ if (!worker) {
+ ret = -ENOMEM;
+ goto fail;
+ }
- INIT_LIST_HEAD(&worker->pending);
- INIT_LIST_HEAD(&worker->prio_pending);
- INIT_LIST_HEAD(&worker->worker_list);
- spin_lock_init(&worker->lock);
-
- atomic_set(&worker->num_pending, 0);
- atomic_set(&worker->refs, 1);
- worker->workers = workers;
- worker->task = kthread_run(worker_loop, worker,
- "btrfs-%s-%d", workers->name,
- workers->num_workers + i);
- if (IS_ERR(worker->task)) {
- ret = PTR_ERR(worker->task);
- kfree(worker);
- goto fail;
- }
- spin_lock_irq(&workers->lock);
- list_add_tail(&worker->worker_list, &workers->idle_list);
- worker->idle = 1;
- workers->num_workers++;
- workers->num_workers_starting--;
- WARN_ON(workers->num_workers_starting < 0);
- spin_unlock_irq(&workers->lock);
+ INIT_LIST_HEAD(&worker->pending);
+ INIT_LIST_HEAD(&worker->prio_pending);
+ INIT_LIST_HEAD(&worker->worker_list);
+ spin_lock_init(&worker->lock);
+
+ atomic_set(&worker->num_pending, 0);
+ atomic_set(&worker->refs, 1);
+ worker->workers = workers;
+ worker->task = kthread_run(worker_loop, worker,
+ "btrfs-%s-%d", workers->name,
+ workers->num_workers + 1);
+ if (IS_ERR(worker->task)) {
+ ret = PTR_ERR(worker->task);
+ kfree(worker);
+ goto fail;
}
+ spin_lock_irq(&workers->lock);
+ list_add_tail(&worker->worker_list, &workers->idle_list);
+ worker->idle = 1;
+ workers->num_workers++;
+ workers->num_workers_starting--;
+ WARN_ON(workers->num_workers_starting < 0);
+ spin_unlock_irq(&workers->lock);
+
return 0;
fail:
- btrfs_stop_workers(workers);
+ spin_lock_irq(&workers->lock);
+ workers->num_workers_starting--;
+ spin_unlock_irq(&workers->lock);
return ret;
}
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+int btrfs_start_workers(struct btrfs_workers *workers)
{
spin_lock_irq(&workers->lock);
- workers->num_workers_starting += num_workers;
+ workers->num_workers_starting++;
spin_unlock_irq(&workers->lock);
- return __btrfs_start_workers(workers, num_workers);
+ return __btrfs_start_workers(workers);
}
/*
@@ -568,9 +561,10 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
struct btrfs_worker_thread *worker;
unsigned long flags;
struct list_head *fallback;
+ int ret;
-again:
spin_lock_irqsave(&workers->lock, flags);
+again:
worker = next_worker(workers);
if (!worker) {
@@ -584,7 +578,10 @@ again:
workers->num_workers_starting++;
spin_unlock_irqrestore(&workers->lock, flags);
/* we're below the limit, start another worker */
- __btrfs_start_workers(workers, 1);
+ ret = __btrfs_start_workers(workers);
+ spin_lock_irqsave(&workers->lock, flags);
+ if (ret)
+ goto fallback;
goto again;
}
}
@@ -665,7 +662,7 @@ void btrfs_set_work_high_prio(struct btrfs_work *work)
/*
* places a struct btrfs_work into the pending queue of one of the kthreads
*/
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
{
struct btrfs_worker_thread *worker;
unsigned long flags;
@@ -673,7 +670,7 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
/* don't requeue something already on a list */
if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
- goto out;
+ return;
worker = find_worker(workers);
if (workers->ordered) {
@@ -712,7 +709,4 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
if (wake)
wake_up_process(worker->task);
spin_unlock_irqrestore(&worker->lock, flags);
-
-out:
- return 0;
}
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 5077746cf85..f34cc31fa3c 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -109,8 +109,8 @@ struct btrfs_workers {
char *name;
};
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
+int btrfs_start_workers(struct btrfs_workers *workers);
int btrfs_stop_workers(struct btrfs_workers *workers);
void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
struct btrfs_workers *async_starter);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 543f60bddb3..b6d1020c457 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -86,6 +86,9 @@ struct btrfs_ordered_sum;
/* holds checksums of all the data extents */
#define BTRFS_CSUM_TREE_OBJECTID 7ULL
+/* for storing balance parameters in the root tree */
+#define BTRFS_BALANCE_OBJECTID -4ULL
+
/* orhpan objectid for tracking unlinked/truncated files */
#define BTRFS_ORPHAN_OBJECTID -5ULL
@@ -692,6 +695,54 @@ struct btrfs_root_ref {
__le16 name_len;
} __attribute__ ((__packed__));
+struct btrfs_disk_balance_args {
+ /*
+ * profiles to operate on, single is denoted by
+ * BTRFS_AVAIL_ALLOC_BIT_SINGLE
+ */
+ __le64 profiles;
+
+ /* usage filter */
+ __le64 usage;
+
+ /* devid filter */
+ __le64 devid;
+
+ /* devid subset filter [pstart..pend) */
+ __le64 pstart;
+ __le64 pend;
+
+ /* btrfs virtual address space subset filter [vstart..vend) */
+ __le64 vstart;
+ __le64 vend;
+
+ /*
+ * profile to convert to, single is denoted by
+ * BTRFS_AVAIL_ALLOC_BIT_SINGLE
+ */
+ __le64 target;
+
+ /* BTRFS_BALANCE_ARGS_* */
+ __le64 flags;
+
+ __le64 unused[8];
+} __attribute__ ((__packed__));
+
+/*
+ * store balance parameters to disk so that balance can be properly
+ * resumed after crash or unmount
+ */
+struct btrfs_balance_item {
+ /* BTRFS_BALANCE_* */
+ __le64 flags;
+
+ struct btrfs_disk_balance_args data;
+ struct btrfs_disk_balance_args meta;
+ struct btrfs_disk_balance_args sys;
+
+ __le64 unused[4];
+} __attribute__ ((__packed__));
+
#define BTRFS_FILE_EXTENT_INLINE 0
#define BTRFS_FILE_EXTENT_REG 1
#define BTRFS_FILE_EXTENT_PREALLOC 2
@@ -751,14 +802,32 @@ struct btrfs_csum_item {
} __attribute__ ((__packed__));
/* different types of block groups (and chunks) */
-#define BTRFS_BLOCK_GROUP_DATA (1 << 0)
-#define BTRFS_BLOCK_GROUP_SYSTEM (1 << 1)
-#define BTRFS_BLOCK_GROUP_METADATA (1 << 2)
-#define BTRFS_BLOCK_GROUP_RAID0 (1 << 3)
-#define BTRFS_BLOCK_GROUP_RAID1 (1 << 4)
-#define BTRFS_BLOCK_GROUP_DUP (1 << 5)
-#define BTRFS_BLOCK_GROUP_RAID10 (1 << 6)
-#define BTRFS_NR_RAID_TYPES 5
+#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0)
+#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1)
+#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2)
+#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3)
+#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4)
+#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5)
+#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6)
+#define BTRFS_BLOCK_GROUP_RESERVED BTRFS_AVAIL_ALLOC_BIT_SINGLE
+#define BTRFS_NR_RAID_TYPES 5
+
+#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \
+ BTRFS_BLOCK_GROUP_SYSTEM | \
+ BTRFS_BLOCK_GROUP_METADATA)
+
+#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \
+ BTRFS_BLOCK_GROUP_RAID1 | \
+ BTRFS_BLOCK_GROUP_DUP | \
+ BTRFS_BLOCK_GROUP_RAID10)
+/*
+ * We need a bit for restriper to be able to tell when chunks of type
+ * SINGLE are available. This "extended" profile format is used in
+ * fs_info->avail_*_alloc_bits (in-memory) and balance item fields
+ * (on-disk). The corresponding on-disk bit in chunk.type is reserved
+ * to avoid remappings between two formats in future.
+ */
+#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48)
struct btrfs_block_group_item {
__le64 used;
@@ -916,6 +985,7 @@ struct btrfs_block_group_cache {
struct reloc_control;
struct btrfs_device;
struct btrfs_fs_devices;
+struct btrfs_balance_control;
struct btrfs_delayed_root;
struct btrfs_fs_info {
u8 fsid[BTRFS_FSID_SIZE];
@@ -1132,12 +1202,23 @@ struct btrfs_fs_info {
spinlock_t ref_cache_lock;
u64 total_ref_cache_size;
+ /*
+ * these three are in extended format (availability of single
+ * chunks is denoted by BTRFS_AVAIL_ALLOC_BIT_SINGLE bit, other
+ * types are denoted by corresponding BTRFS_BLOCK_GROUP_* bits)
+ */
u64 avail_data_alloc_bits;
u64 avail_metadata_alloc_bits;
u64 avail_system_alloc_bits;
- u64 data_alloc_profile;
- u64 metadata_alloc_profile;
- u64 system_alloc_profile;
+
+ /* restriper state */
+ spinlock_t balance_lock;
+ struct mutex balance_mutex;
+ atomic_t balance_running;
+ atomic_t balance_pause_req;
+ atomic_t balance_cancel_req;
+ struct btrfs_balance_control *balance_ctl;
+ wait_queue_head_t balance_wait_q;
unsigned data_chunk_allocations;
unsigned metadata_ratio;
@@ -1383,6 +1464,8 @@ struct btrfs_ioctl_defrag_range_args {
#define BTRFS_DEV_ITEM_KEY 216
#define BTRFS_CHUNK_ITEM_KEY 228
+#define BTRFS_BALANCE_ITEM_KEY 248
+
/*
* string items are for debugging. They just store a short string of
* data in the FS
@@ -1413,6 +1496,7 @@ struct btrfs_ioctl_defrag_range_args {
#define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16)
#define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17)
#define BTRFS_MOUNT_RECOVERY (1 << 18)
+#define BTRFS_MOUNT_SKIP_BALANCE (1 << 19)
#define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt)
#define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt)
@@ -2077,8 +2161,86 @@ BTRFS_SETGET_STACK_FUNCS(backup_bytes_used, struct btrfs_root_backup,
BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup,
num_devices, 64);
-/* struct btrfs_super_block */
+/* struct btrfs_balance_item */
+BTRFS_SETGET_FUNCS(balance_flags, struct btrfs_balance_item, flags, 64);
+
+static inline void btrfs_balance_data(struct extent_buffer *eb,
+ struct btrfs_balance_item *bi,
+ struct btrfs_disk_balance_args *ba)
+{
+ read_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
+}
+
+static inline void btrfs_set_balance_data(struct extent_buffer *eb,
+ struct btrfs_balance_item *bi,
+ struct btrfs_disk_balance_args *ba)
+{
+ write_eb_member(eb, bi, struct btrfs_balance_item, data, ba);
+}
+
+static inline void btrfs_balance_meta(struct extent_buffer *eb,
+ struct btrfs_balance_item *bi,
+ struct btrfs_disk_balance_args *ba)
+{
+ read_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
+}
+static inline void btrfs_set_balance_meta(struct extent_buffer *eb,
+ struct btrfs_balance_item *bi,
+ struct btrfs_disk_balance_args *ba)
+{
+ write_eb_member(eb, bi, struct btrfs_balance_item, meta, ba);
+}
+
+static inline void btrfs_balance_sys(struct extent_buffer *eb,
+ struct btrfs_balance_item *bi,
+ struct btrfs_disk_balance_args *ba)
+{
+ read_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
+}
+
+static inline void btrfs_set_balance_sys(struct extent_buffer *eb,
+ struct btrfs_balance_item *bi,
+ struct btrfs_disk_balance_args *ba)
+{
+ write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba);
+}
+
+static inline void
+btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
+ struct btrfs_disk_balance_args *disk)
+{
+ memset(cpu, 0, sizeof(*cpu));
+
+ cpu->profiles = le64_to_cpu(disk->profiles);
+ cpu->usage = le64_to_cpu(disk->usage);
+ cpu->devid = le64_to_cpu(disk->devid);
+ cpu->pstart = le64_to_cpu(disk->pstart);
+ cpu->pend = le64_to_cpu(disk->pend);
+ cpu->vstart = le64_to_cpu(disk->vstart);
+ cpu->vend = le64_to_cpu(disk->vend);
+ cpu->target = le64_to_cpu(disk->target);
+ cpu->flags = le64_to_cpu(disk->flags);
+}
+
+static inline void
+btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
+ struct btrfs_balance_args *cpu)
+{
+ memset(disk, 0, sizeof(*disk));
+
+ disk->profiles = cpu_to_le64(cpu->profiles);
+ disk->usage = cpu_to_le64(cpu->usage);
+ disk->devid = cpu_to_le64(cpu->devid);
+ disk->pstart = cpu_to_le64(cpu->pstart);
+ disk->pend = cpu_to_le64(cpu->pend);
+ disk->vstart = cpu_to_le64(cpu->vstart);
+ disk->vend = cpu_to_le64(cpu->vend);
+ disk->target = cpu_to_le64(cpu->target);
+ disk->flags = cpu_to_le64(cpu->flags);
+}
+
+/* struct btrfs_super_block */
BTRFS_SETGET_STACK_FUNCS(super_bytenr, struct btrfs_super_block, bytenr, 64);
BTRFS_SETGET_STACK_FUNCS(super_flags, struct btrfs_super_block, flags, 64);
BTRFS_SETGET_STACK_FUNCS(super_generation, struct btrfs_super_block,
@@ -2508,6 +2670,7 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
}
static inline void free_fs_info(struct btrfs_fs_info *fs_info)
{
+ kfree(fs_info->balance_ctl);
kfree(fs_info->delayed_root);
kfree(fs_info->extent_root);
kfree(fs_info->tree_root);
@@ -2518,6 +2681,24 @@ static inline void free_fs_info(struct btrfs_fs_info *fs_info)
kfree(fs_info->super_for_commit);
kfree(fs_info);
}
+/**
+ * profile_is_valid - tests whether a given profile is valid and reduced
+ * @flags: profile to validate
+ * @extended: if true @flags is treated as an extended profile
+ */
+static inline int profile_is_valid(u64 flags, int extended)
+{
+ u64 mask = ~BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+ flags &= ~BTRFS_BLOCK_GROUP_TYPE_MASK;
+ if (extended)
+ mask &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+ if (flags & mask)
+ return 0;
+ /* true if zero or exactly one bit set */
+ return (flags & (~flags + 1)) == flags;
+}
/* root-item.c */
int btrfs_find_root_ref(struct btrfs_root *tree_root,
@@ -2700,7 +2881,8 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-void btrfs_dirty_inode(struct inode *inode, int flags);
+int btrfs_dirty_inode(struct inode *inode);
+int btrfs_update_time(struct file *file);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6a1a6800776..9c1eccc2c50 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -640,8 +640,8 @@ static int btrfs_delayed_inode_reserve_metadata(
* Now if src_rsv == delalloc_block_rsv we'll let it just steal since
* we're accounted for.
*/
- if (!trans->bytes_reserved &&
- src_rsv != &root->fs_info->delalloc_block_rsv) {
+ if (!src_rsv || (!trans->bytes_reserved &&
+ src_rsv != &root->fs_info->delalloc_block_rsv)) {
ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
/*
* Since we're under a transaction reserve_metadata_bytes could
@@ -1719,7 +1719,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
inode->i_gid = btrfs_stack_inode_gid(inode_item);
btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
inode->i_mode = btrfs_stack_inode_mode(inode_item);
- inode->i_nlink = btrfs_stack_inode_nlink(inode_item);
+ set_nlink(inode, btrfs_stack_inode_nlink(inode_item));
inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));
BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item);
BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6f8cd17c9a9..9be97716c5e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2003,12 +2003,20 @@ struct btrfs_root *open_ctree(struct super_block *sb,
init_rwsem(&fs_info->scrub_super_lock);
fs_info->scrub_workers_refcnt = 0;
+ spin_lock_init(&fs_info->balance_lock);
+ mutex_init(&fs_info->balance_mutex);
+ atomic_set(&fs_info->balance_running, 0);
+ atomic_set(&fs_info->balance_pause_req, 0);
+ atomic_set(&fs_info->balance_cancel_req, 0);
+ fs_info->balance_ctl = NULL;
+ init_waitqueue_head(&fs_info->balance_wait_q);
+
sb->s_blocksize = 4096;
sb->s_blocksize_bits = blksize_bits(4096);
sb->s_bdi = &fs_info->bdi;
fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
- fs_info->btree_inode->i_nlink = 1;
+ set_nlink(fs_info->btree_inode, 1);
/*
* we set the i_size on the btree inode to the max possible int.
* the real end of the address space is determined by all of
@@ -2195,19 +2203,27 @@ struct btrfs_root *open_ctree(struct super_block *sb,
fs_info->endio_meta_write_workers.idle_thresh = 2;
fs_info->readahead_workers.idle_thresh = 2;
- btrfs_start_workers(&fs_info->workers, 1);
- btrfs_start_workers(&fs_info->generic_worker, 1);
- btrfs_start_workers(&fs_info->submit_workers, 1);
- btrfs_start_workers(&fs_info->delalloc_workers, 1);
- btrfs_start_workers(&fs_info->fixup_workers, 1);
- btrfs_start_workers(&fs_info->endio_workers, 1);
- btrfs_start_workers(&fs_info->endio_meta_workers, 1);
- btrfs_start_workers(&fs_info->endio_meta_write_workers, 1);
- btrfs_start_workers(&fs_info->endio_write_workers, 1);
- btrfs_start_workers(&fs_info->endio_freespace_worker, 1);
- btrfs_start_workers(&fs_info->delayed_workers, 1);
- btrfs_start_workers(&fs_info->caching_workers, 1);
- btrfs_start_workers(&fs_info->readahead_workers, 1);
+ /*
+ * btrfs_start_workers can really only fail because of ENOMEM so just
+ * return -ENOMEM if any of these fail.
+ */
+ ret = btrfs_start_workers(&fs_info->workers);
+ ret |= btrfs_start_workers(&fs_info->generic_worker);
+ ret |= btrfs_start_workers(&fs_info->submit_workers);
+ ret |= btrfs_start_workers(&fs_info->delalloc_workers);
+ ret |= btrfs_start_workers(&fs_info->fixup_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_write_workers);
+ ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
+ ret |= btrfs_start_workers(&fs_info->delayed_workers);
+ ret |= btrfs_start_workers(&fs_info->caching_workers);
+ ret |= btrfs_start_workers(&fs_info->readahead_workers);
+ if (ret) {
+ ret = -ENOMEM;
+ goto fail_sb_buffer;
+ }
fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
@@ -2263,9 +2279,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
(unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node),
BTRFS_UUID_SIZE);
- mutex_lock(&fs_info->chunk_mutex);
ret = btrfs_read_chunk_tree(chunk_root);
- mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n",
sb->s_id);
@@ -2314,9 +2328,6 @@ retry_root_backup:
fs_info->generation = generation;
fs_info->last_trans_committed = generation;
- fs_info->data_alloc_profile = (u64)-1;
- fs_info->metadata_alloc_profile = (u64)-1;
- fs_info->system_alloc_profile = fs_info->metadata_alloc_profile;
ret = btrfs_init_space_info(fs_info);
if (ret) {
@@ -2419,6 +2430,10 @@ retry_root_backup:
if (!err)
err = btrfs_orphan_cleanup(fs_info->tree_root);
up_read(&fs_info->cleanup_work_sem);
+
+ if (!err)
+ err = btrfs_recover_balance(fs_info->tree_root);
+
if (err) {
close_ctree(tree_root);
return ERR_PTR(err);
@@ -2968,6 +2983,9 @@ int close_ctree(struct btrfs_root *root)
fs_info->closing = 1;
smp_mb();
+ /* pause restriper - we want to resume on mount */
+ btrfs_pause_balance(root->fs_info);
+
btrfs_scrub_cancel(root);
/* wait for any defraggers to finish */
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0a435e2e143..a44072a692a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -618,8 +618,7 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
struct list_head *head = &info->space_info;
struct btrfs_space_info *found;
- flags &= BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_SYSTEM |
- BTRFS_BLOCK_GROUP_METADATA;
+ flags &= BTRFS_BLOCK_GROUP_TYPE_MASK;
rcu_read_lock();
list_for_each_entry_rcu(found, head, list) {
@@ -2288,9 +2287,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
BUG_ON(ret);
kfree(extent_op);
- cond_resched();
- spin_lock(&delayed_refs->lock);
- continue;
+ goto next;
}
list_del_init(&locked_ref->cluster);
@@ -2315,7 +2312,11 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
btrfs_put_delayed_ref(ref);
kfree(extent_op);
count++;
-
+next:
+ do_chunk_alloc(trans, root->fs_info->extent_root,
+ 2 * 1024 * 1024,
+ btrfs_get_alloc_profile(root, 0),
+ CHUNK_ALLOC_NO_FORCE);
cond_resched();
spin_lock(&delayed_refs->lock);
}
@@ -2363,6 +2364,10 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
if (root == root->fs_info->extent_root)
root = root->fs_info->tree_root;
+ do_chunk_alloc(trans, root->fs_info->extent_root,
+ 2 * 1024 * 1024, btrfs_get_alloc_profile(root, 0),
+ CHUNK_ALLOC_NO_FORCE);
+
delayed_refs = &trans->transaction->delayed_refs;
INIT_LIST_HEAD(&cluster);
again:
@@ -2900,7 +2905,7 @@ out_free:
btrfs_release_path(path);
out:
spin_lock(&block_group->lock);
- if (!ret)
+ if (!ret && dcs == BTRFS_DC_SETUP)
block_group->cache_generation = trans->transid;
block_group->disk_cache_state = dcs;
spin_unlock(&block_group->lock);
@@ -3071,9 +3076,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
INIT_LIST_HEAD(&found->block_groups[i]);
init_rwsem(&found->groups_sem);
spin_lock_init(&found->lock);
- found->flags = flags & (BTRFS_BLOCK_GROUP_DATA |
- BTRFS_BLOCK_GROUP_SYSTEM |
- BTRFS_BLOCK_GROUP_METADATA);
+ found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
found->total_bytes = total_bytes;
found->disk_total = total_bytes * factor;
found->bytes_used = bytes_used;
@@ -3094,20 +3097,27 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
- u64 extra_flags = flags & (BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_DUP);
- if (extra_flags) {
- if (flags & BTRFS_BLOCK_GROUP_DATA)
- fs_info->avail_data_alloc_bits |= extra_flags;
- if (flags & BTRFS_BLOCK_GROUP_METADATA)
- fs_info->avail_metadata_alloc_bits |= extra_flags;
- if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
- fs_info->avail_system_alloc_bits |= extra_flags;
- }
+ u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+ /* chunk -> extended profile */
+ if (extra_flags == 0)
+ extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+ if (flags & BTRFS_BLOCK_GROUP_DATA)
+ fs_info->avail_data_alloc_bits |= extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_METADATA)
+ fs_info->avail_metadata_alloc_bits |= extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+ fs_info->avail_system_alloc_bits |= extra_flags;
}
+/*
+ * @flags: available profiles in extended format (see ctree.h)
+ *
+ * Returns reduced profile in chunk format. If profile changing is in
+ * progress (either running or paused) picks the target profile (if it's
+ * already available), otherwise falls back to plain reducing.
+ */
u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
{
/*
@@ -3118,6 +3128,34 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
u64 num_devices = root->fs_info->fs_devices->rw_devices +
root->fs_info->fs_devices->missing_devices;
+ /* pick restriper's target profile if it's available */
+ spin_lock(&root->fs_info->balance_lock);
+ if (root->fs_info->balance_ctl) {
+ struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
+ u64 tgt = 0;
+
+ if ((flags & BTRFS_BLOCK_GROUP_DATA) &&
+ (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (flags & bctl->data.target)) {
+ tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
+ } else if ((flags & BTRFS_BLOCK_GROUP_SYSTEM) &&
+ (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (flags & bctl->sys.target)) {
+ tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
+ } else if ((flags & BTRFS_BLOCK_GROUP_METADATA) &&
+ (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (flags & bctl->meta.target)) {
+ tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
+ }
+
+ if (tgt) {
+ spin_unlock(&root->fs_info->balance_lock);
+ flags = tgt;
+ goto out;
+ }
+ }
+ spin_unlock(&root->fs_info->balance_lock);
+
if (num_devices == 1)
flags &= ~(BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID0);
if (num_devices < 4)
@@ -3137,22 +3175,25 @@ u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
if ((flags & BTRFS_BLOCK_GROUP_RAID0) &&
((flags & BTRFS_BLOCK_GROUP_RAID1) |
(flags & BTRFS_BLOCK_GROUP_RAID10) |
- (flags & BTRFS_BLOCK_GROUP_DUP)))
+ (flags & BTRFS_BLOCK_GROUP_DUP))) {
flags &= ~BTRFS_BLOCK_GROUP_RAID0;
+ }
+
+out:
+ /* extended -> chunk profile */
+ flags &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
return flags;
}
static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
{
if (flags & BTRFS_BLOCK_GROUP_DATA)
- flags |= root->fs_info->avail_data_alloc_bits &
- root->fs_info->data_alloc_profile;
+ flags |= root->fs_info->avail_data_alloc_bits;
else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
- flags |= root->fs_info->avail_system_alloc_bits &
- root->fs_info->system_alloc_profile;
+ flags |= root->fs_info->avail_system_alloc_bits;
else if (flags & BTRFS_BLOCK_GROUP_METADATA)
- flags |= root->fs_info->avail_metadata_alloc_bits &
- root->fs_info->metadata_alloc_profile;
+ flags |= root->fs_info->avail_metadata_alloc_bits;
+
return btrfs_reduce_alloc_profile(root, flags);
}
@@ -3335,27 +3376,12 @@ static int should_alloc_chunk(struct btrfs_root *root,
if (num_bytes - num_allocated < thresh)
return 1;
}
-
- /*
- * we have two similar checks here, one based on percentage
- * and once based on a hard number of 256MB. The idea
- * is that if we have a good amount of free
- * room, don't allocate a chunk. A good mount is
- * less than 80% utilized of the chunks we have allocated,
- * or more than 256MB free
- */
- if (num_allocated + alloc_bytes + 256 * 1024 * 1024 < num_bytes)
- return 0;
-
- if (num_allocated + alloc_bytes < div_factor(num_bytes, 8))
- return 0;
-
thresh = btrfs_super_total_bytes(root->fs_info->super_copy);
- /* 256MB or 5% of the FS */
- thresh = max_t(u64, 256 * 1024 * 1024, div_factor_fine(thresh, 5));
+ /* 256MB or 2% of the FS */
+ thresh = max_t(u64, 256 * 1024 * 1024, div_factor_fine(thresh, 2));
- if (num_bytes > thresh && sinfo->bytes_used < div_factor(num_bytes, 3))
+ if (num_bytes > thresh && sinfo->bytes_used < div_factor(num_bytes, 8))
return 0;
return 1;
}
@@ -3369,7 +3395,7 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
int wait_for_alloc = 0;
int ret = 0;
- flags = btrfs_reduce_alloc_profile(extent_root, flags);
+ BUG_ON(!profile_is_valid(flags, 0));
space_info = __find_space_info(extent_root->fs_info, flags);
if (!space_info) {
@@ -3494,7 +3520,8 @@ static int shrink_delalloc(struct btrfs_root *root, u64 to_reclaim,
smp_mb();
nr_pages = min_t(unsigned long, nr_pages,
root->fs_info->delalloc_bytes >> PAGE_CACHE_SHIFT);
- writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages);
+ writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages,
+ WB_REASON_FS_FREE_SPACE);
spin_lock(&space_info->lock);
if (reserved > space_info->bytes_may_use)
@@ -4281,12 +4308,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
u64 to_reserve = 0;
+ u64 csum_bytes;
unsigned nr_extents = 0;
+ int extra_reserve = 0;
int flush = 1;
int ret;
+ /* Need to be holding the i_mutex here if we aren't free space cache */
if (btrfs_is_free_space_inode(root, inode))
flush = 0;
+ else
+ WARN_ON(!mutex_is_locked(&inode->i_mutex));
if (flush && btrfs_transaction_in_commit(root->fs_info))
schedule_timeout(1);
@@ -4297,11 +4329,9 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
BTRFS_I(inode)->outstanding_extents++;
if (BTRFS_I(inode)->outstanding_extents >
- BTRFS_I(inode)->reserved_extents) {
+ BTRFS_I(inode)->reserved_extents)
nr_extents = BTRFS_I(inode)->outstanding_extents -
BTRFS_I(inode)->reserved_extents;
- BTRFS_I(inode)->reserved_extents += nr_extents;
- }
/*
* Add an item to reserve for updating the inode when we complete the
@@ -4309,11 +4339,12 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
*/
if (!BTRFS_I(inode)->delalloc_meta_reserved) {
nr_extents++;
- BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ extra_reserve = 1;
}
to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents);
to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
+ csum_bytes = BTRFS_I(inode)->csum_bytes;
spin_unlock(&BTRFS_I(inode)->lock);
ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush);
@@ -4323,22 +4354,35 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
spin_lock(&BTRFS_I(inode)->lock);
dropped = drop_outstanding_extent(inode);
- to_free = calc_csum_metadata_size(inode, num_bytes, 0);
- spin_unlock(&BTRFS_I(inode)->lock);
- to_free += btrfs_calc_trans_metadata_size(root, dropped);
-
/*
- * Somebody could have come in and twiddled with the
- * reservation, so if we have to free more than we would have
- * reserved from this reservation go ahead and release those
- * bytes.
+ * If the inodes csum_bytes is the same as the original
+ * csum_bytes then we know we haven't raced with any free()ers
+ * so we can just reduce our inodes csum bytes and carry on.
+ * Otherwise we have to do the normal free thing to account for
+ * the case that the free side didn't free up its reserve
+ * because of this outstanding reservation.
*/
- to_free -= to_reserve;
+ if (BTRFS_I(inode)->csum_bytes == csum_bytes)
+ calc_csum_metadata_size(inode, num_bytes, 0);
+ else
+ to_free = calc_csum_metadata_size(inode, num_bytes, 0);
+ spin_unlock(&BTRFS_I(inode)->lock);
+ if (dropped)
+ to_free += btrfs_calc_trans_metadata_size(root, dropped);
+
if (to_free)
btrfs_block_rsv_release(root, block_rsv, to_free);
return ret;
}
+ spin_lock(&BTRFS_I(inode)->lock);
+ if (extra_reserve) {
+ BTRFS_I(inode)->delalloc_meta_reserved = 1;
+ nr_extents--;
+ }
+ BTRFS_I(inode)->reserved_extents += nr_extents;
+ spin_unlock(&BTRFS_I(inode)->lock);
+
block_rsv_add_bytes(block_rsv, to_reserve, 1);
return 0;
@@ -5190,11 +5234,11 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root = orig_root->fs_info->extent_root;
struct btrfs_free_cluster *last_ptr = NULL;
struct btrfs_block_group_cache *block_group = NULL;
+ struct btrfs_block_group_cache *used_block_group;
int empty_cluster = 2 * 1024 * 1024;
int allowed_chunk_alloc = 0;
int done_chunk_alloc = 0;
struct btrfs_space_info *space_info;
- int last_ptr_loop = 0;
int loop = 0;
int index = 0;
int alloc_type = (data & BTRFS_BLOCK_GROUP_DATA) ?
@@ -5256,6 +5300,7 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
ideal_cache:
block_group = btrfs_lookup_block_group(root->fs_info,
search_start);
+ used_block_group = block_group;
/*
* we don't want to use the block group if it doesn't match our
* allocation bits, or if its not cached.
@@ -5293,6 +5338,7 @@ search:
u64 offset;
int cached;
+ used_block_group = block_group;
btrfs_get_block_group(block_group);
search_start = block_group->key.objectid;
@@ -5359,80 +5405,74 @@ alloc:
if (unlikely(block_group->ro))
goto loop;
- spin_lock(&block_group->free_space_ctl->tree_lock);
- if (cached &&
- block_group->free_space_ctl->free_space <
- num_bytes + empty_cluster + empty_size) {
- spin_unlock(&block_group->free_space_ctl->tree_lock);
- goto loop;
- }
- spin_unlock(&block_group->free_space_ctl->tree_lock);
-
/*
- * Ok we want to try and use the cluster allocator, so lets look
- * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
- * have tried the cluster allocator plenty of times at this
- * point and not have found anything, so we are likely way too
- * fragmented for the clustering stuff to find anything, so lets
- * just skip it and let the allocator find whatever block it can
- * find
+ * Ok we want to try and use the cluster allocator, so
+ * lets look there
*/
- if (last_ptr && loop < LOOP_NO_EMPTY_SIZE) {
+ if (last_ptr) {
/*
* the refill lock keeps out other
* people trying to start a new cluster
*/
spin_lock(&last_ptr->refill_lock);
- if (!last_ptr->block_group ||
- last_ptr->block_group->ro ||
- !block_group_bits(last_ptr->block_group, data))
+ 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, data))) {
+ used_block_group = block_group;
goto refill_cluster;
+ }
+
+ if (used_block_group != block_group)
+ btrfs_get_block_group(used_block_group);
- offset = btrfs_alloc_from_cluster(block_group, last_ptr,
- num_bytes, search_start);
+ offset = btrfs_alloc_from_cluster(used_block_group,
+ last_ptr, num_bytes, used_block_group->key.objectid);
if (offset) {
/* we have a block, we're done */
spin_unlock(&last_ptr->refill_lock);
goto checks;
}
- spin_lock(&last_ptr->lock);
- /*
- * whoops, this cluster doesn't actually point to
- * this block group. Get a ref on the block
- * group is does point to and try again
- */
- if (!last_ptr_loop && last_ptr->block_group &&
- last_ptr->block_group != block_group &&
- index <=
- get_block_group_index(last_ptr->block_group)) {
-
- btrfs_put_block_group(block_group);
- block_group = last_ptr->block_group;
- btrfs_get_block_group(block_group);
- spin_unlock(&last_ptr->lock);
- spin_unlock(&last_ptr->refill_lock);
-
- last_ptr_loop = 1;
- search_start = block_group->key.objectid;
- /*
- * we know this block group is properly
- * in the list because
- * btrfs_remove_block_group, drops the
- * cluster before it removes the block
- * group from the list
- */
- goto have_block_group;
+ WARN_ON(last_ptr->block_group != used_block_group);
+ if (used_block_group != block_group) {
+ btrfs_put_block_group(used_block_group);
+ used_block_group = block_group;
}
- spin_unlock(&last_ptr->lock);
refill_cluster:
+ BUG_ON(used_block_group != block_group);
+ /* 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
+ * it can find. If we reach this point, we
+ * will have tried the cluster allocator
+ * plenty of times and not have found
+ * anything, so we are likely way too
+ * fragmented for the clustering stuff to find
+ * anything.
+ *
+ * However, if the cluster is taken from the
+ * current block group, release the cluster
+ * first, so that we stand a better chance of
+ * succeeding in the unclustered
+ * allocation. */
+ if (loop >= LOOP_NO_EMPTY_SIZE &&
+ last_ptr->block_group != block_group) {
+ spin_unlock(&last_ptr->refill_lock);
+ goto unclustered_alloc;
+ }
+
/*
* this cluster didn't work out, free it and
* start over
*/
btrfs_return_cluster_to_free_space(NULL, last_ptr);
- last_ptr_loop = 0;
+ if (loop >= LOOP_NO_EMPTY_SIZE) {
+ spin_unlock(&last_ptr->refill_lock);
+ goto unclustered_alloc;
+ }
/* allocate a cluster in this block group */
ret = btrfs_find_space_cluster(trans, root,
@@ -5473,6 +5513,16 @@ refill_cluster:
goto loop;
}
+unclustered_alloc:
+ spin_lock(&block_group->free_space_ctl->tree_lock);
+ if (cached &&
+ block_group->free_space_ctl->free_space <
+ num_bytes + empty_cluster + empty_size) {
+ spin_unlock(&block_group->free_space_ctl->tree_lock);
+ goto loop;
+ }
+ spin_unlock(&block_group->free_space_ctl->tree_lock);
+
offset = btrfs_find_space_for_alloc(block_group, search_start,
num_bytes, empty_size);
/*
@@ -5499,29 +5549,26 @@ checks:
search_start = stripe_align(root, offset);
/* move on to the next group */
if (search_start + num_bytes >= search_end) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
/* move on to the next group */
if (search_start + num_bytes >
- block_group->key.objectid + block_group->key.offset) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ used_block_group->key.objectid + used_block_group->key.offset) {
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
- ins->objectid = search_start;
- ins->offset = num_bytes;
-
if (offset < search_start)
- btrfs_add_free_space(block_group, offset,
+ btrfs_add_free_space(used_block_group, offset,
search_start - offset);
BUG_ON(offset > search_start);
- ret = btrfs_update_reserved_bytes(block_group, num_bytes,
+ ret = btrfs_update_reserved_bytes(used_block_group, num_bytes,
alloc_type);
if (ret == -EAGAIN) {
- btrfs_add_free_space(block_group, offset, num_bytes);
+ btrfs_add_free_space(used_block_group, offset, num_bytes);
goto loop;
}
@@ -5530,15 +5577,19 @@ checks:
ins->offset = num_bytes;
if (offset < search_start)
- btrfs_add_free_space(block_group, offset,
+ btrfs_add_free_space(used_block_group, offset,
search_start - offset);
BUG_ON(offset > search_start);
+ if (used_block_group != block_group)
+ btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
break;
loop:
failed_cluster_refill = false;
failed_alloc = false;
BUG_ON(index != get_block_group_index(block_group));
+ if (used_block_group != block_group)
+ btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
}
up_read(&space_info->groups_sem);
@@ -6869,6 +6920,29 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
u64 stripped = BTRFS_BLOCK_GROUP_RAID0 |
BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;
+ if (root->fs_info->balance_ctl) {
+ struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
+ u64 tgt = 0;
+
+ /* pick restriper's target profile and return */
+ if (flags & BTRFS_BLOCK_GROUP_DATA &&
+ bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+ tgt = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
+ } else if (flags & BTRFS_BLOCK_GROUP_SYSTEM &&
+ bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+ tgt = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
+ } else if (flags & BTRFS_BLOCK_GROUP_METADATA &&
+ bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) {
+ tgt = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
+ }
+
+ if (tgt) {
+ /* extended -> chunk profile */
+ tgt &= ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+ return tgt;
+ }
+ }
+
/*
* we add in the count of missing devices because we want
* to make sure that any RAID levels on a degraded FS
@@ -7162,7 +7236,7 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
* space to fit our block group in.
*/
if (device->total_bytes > device->bytes_used + min_free) {
- ret = find_free_dev_extent(NULL, device, min_free,
+ ret = find_free_dev_extent(device, min_free,
&dev_offset, NULL);
if (!ret)
dev_nr++;
@@ -7524,6 +7598,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
ret = update_space_info(root->fs_info, cache->flags, size, bytes_used,
&cache->space_info);
BUG_ON(ret);
+ update_global_block_rsv(root->fs_info);
spin_lock(&cache->space_info->lock);
cache->space_info->bytes_readonly += cache->bytes_super;
@@ -7543,6 +7618,22 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
return 0;
}
+static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
+{
+ u64 extra_flags = flags & BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+ /* chunk -> extended profile */
+ if (extra_flags == 0)
+ extra_flags = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+ if (flags & BTRFS_BLOCK_GROUP_DATA)
+ fs_info->avail_data_alloc_bits &= ~extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_METADATA)
+ fs_info->avail_metadata_alloc_bits &= ~extra_flags;
+ if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+ fs_info->avail_system_alloc_bits &= ~extra_flags;
+}
+
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 group_start)
{
@@ -7553,6 +7644,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
struct btrfs_key key;
struct inode *inode;
int ret;
+ int index;
int factor;
root = root->fs_info->extent_root;
@@ -7568,6 +7660,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
free_excluded_extents(root, block_group);
memcpy(&key, &block_group->key, sizeof(key));
+ index = get_block_group_index(block_group);
if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
BTRFS_BLOCK_GROUP_RAID1 |
BTRFS_BLOCK_GROUP_RAID10))
@@ -7642,6 +7735,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
* are still on the list after taking the semaphore
*/
list_del_init(&block_group->list);
+ if (list_empty(&block_group->space_info->block_groups[index]))
+ clear_avail_alloc_bits(root->fs_info, block_group->flags);
up_write(&block_group->space_info->groups_sem);
if (block_group->cached == BTRFS_CACHE_STARTED)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index dd8d140eb27..3622cc22ff9 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -935,8 +935,10 @@ again:
node = tree_search(tree, start);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = insert_state(tree, prealloc, start, end, &bits);
prealloc = NULL;
BUG_ON(err == -EEXIST);
@@ -992,8 +994,10 @@ hit_next:
*/
if (state->start < start) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = split_state(tree, state, prealloc, start);
BUG_ON(err == -EEXIST);
prealloc = NULL;
@@ -1024,8 +1028,10 @@ hit_next:
this_end = last_start - 1;
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
/*
* Avoid to free 'prealloc' if it can be merged with
@@ -1051,8 +1057,10 @@ hit_next:
*/
if (state->start <= end && state->end > end) {
prealloc = alloc_extent_state_atomic(prealloc);
- if (!prealloc)
- return -ENOMEM;
+ if (!prealloc) {
+ err = -ENOMEM;
+ goto out;
+ }
err = split_state(tree, state, prealloc, end + 1);
BUG_ON(err == -EEXIST);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d2b60ed6c33..fc97b00bd87 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1167,6 +1167,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
(sizeof(struct page *)));
+ nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
+ nrptrs = max(nrptrs, 8);
pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
if (!pages)
return -ENOMEM;
@@ -1387,7 +1389,11 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
goto out;
}
- file_update_time(file);
+ err = btrfs_update_time(file);
+ if (err) {
+ mutex_unlock(&inode->i_mutex);
+ goto out;
+ }
BTRFS_I(inode)->sequence++;
start_pos = round_down(pos, root->sectorsize);
@@ -1832,7 +1838,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin)
switch (origin) {
case SEEK_END:
case SEEK_CUR:
- offset = generic_file_llseek_unlocked(file, offset, origin);
+ offset = generic_file_llseek(file, offset, origin);
goto out;
case SEEK_DATA:
case SEEK_HOLE:
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index ec23d43d0c3..6c7887a7770 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -319,9 +319,11 @@ static void io_ctl_drop_pages(struct io_ctl *io_ctl)
io_ctl_unmap_page(io_ctl);
for (i = 0; i < io_ctl->num_pages; i++) {
- ClearPageChecked(io_ctl->pages[i]);
- unlock_page(io_ctl->pages[i]);
- page_cache_release(io_ctl->pages[i]);
+ if (io_ctl->pages[i]) {
+ ClearPageChecked(io_ctl->pages[i]);
+ unlock_page(io_ctl->pages[i]);
+ page_cache_release(io_ctl->pages[i]);
+ }
}
}
@@ -635,7 +637,10 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
if (!num_entries)
return 0;
- io_ctl_init(&io_ctl, inode, root);
+ ret = io_ctl_init(&io_ctl, inode, root);
+ if (ret)
+ return ret;
+
ret = readahead_cache(inode);
if (ret)
goto out;
@@ -838,7 +843,7 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
struct io_ctl io_ctl;
struct list_head bitmap_list;
struct btrfs_key key;
- u64 start, end, len;
+ u64 start, extent_start, extent_end, len;
int entries = 0;
int bitmaps = 0;
int ret;
@@ -849,7 +854,9 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
if (!i_size_read(inode))
return -1;
- io_ctl_init(&io_ctl, inode, root);
+ ret = io_ctl_init(&io_ctl, inode, root);
+ if (ret)
+ return -1;
/* Get the cluster for this block_group if it exists */
if (block_group && !list_empty(&block_group->cluster_list))
@@ -857,25 +864,12 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
struct btrfs_free_cluster,
block_group_list);
- /*
- * We shouldn't have switched the pinned extents yet so this is the
- * right one
- */
- unpin = root->fs_info->pinned_extents;
-
/* 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, GFP_NOFS);
- /*
- * When searching for pinned extents, we need to start at our start
- * offset.
- */
- if (block_group)
- start = block_group->key.objectid;
-
node = rb_first(&ctl->free_space_offset);
if (!node && cluster) {
node = rb_first(&cluster->root);
@@ -918,9 +912,20 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
* We want to add any pinned extents to our free space cache
* so we don't leak the space
*/
+
+ /*
+ * We shouldn't have switched the pinned extents yet so this is the
+ * right one
+ */
+ unpin = root->fs_info->pinned_extents;
+
+ if (block_group)
+ start = block_group->key.objectid;
+
while (block_group && (start < block_group->key.objectid +
block_group->key.offset)) {
- ret = find_first_extent_bit(unpin, start, &start, &end,
+ ret = find_first_extent_bit(unpin, start,
+ &extent_start, &extent_end,
EXTENT_DIRTY);
if (ret) {
ret = 0;
@@ -928,20 +933,21 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
}
/* This pinned extent is out of our range */
- if (start >= block_group->key.objectid +
+ if (extent_start >= block_group->key.objectid +
block_group->key.offset)
break;
- len = block_group->key.objectid +
- block_group->key.offset - start;
- len = min(len, end + 1 - start);
+ extent_start = max(extent_start, start);
+ extent_end = min(block_group->key.objectid +
+ block_group->key.offset, extent_end + 1);
+ len = extent_end - extent_start;
entries++;
- ret = io_ctl_add_entry(&io_ctl, start, len, NULL);
+ ret = io_ctl_add_entry(&io_ctl, extent_start, len, NULL);
if (ret)
goto out_nospc;
- start = end + 1;
+ start = extent_end;
}
/* Write out the bitmaps */
@@ -2283,23 +2289,23 @@ out:
static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group,
struct btrfs_free_space *entry,
struct btrfs_free_cluster *cluster,
- u64 offset, u64 bytes, u64 min_bytes)
+ u64 offset, u64 bytes,
+ u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
unsigned long next_zero;
unsigned long i;
- unsigned long search_bits;
- unsigned long total_bits;
+ unsigned long want_bits;
+ unsigned long min_bits;
unsigned long found_bits;
unsigned long start = 0;
unsigned long total_found = 0;
int ret;
- bool found = false;
i = offset_to_bit(entry->offset, block_group->sectorsize,
max_t(u64, offset, entry->offset));
- search_bits = bytes_to_bits(bytes, block_group->sectorsize);
- total_bits = bytes_to_bits(min_bytes, block_group->sectorsize);
+ want_bits = bytes_to_bits(bytes, block_group->sectorsize);
+ min_bits = bytes_to_bits(min_bytes, block_group->sectorsize);
again:
found_bits = 0;
@@ -2308,7 +2314,7 @@ again:
i = find_next_bit(entry->bitmap, BITS_PER_BITMAP, i + 1)) {
next_zero = find_next_zero_bit(entry->bitmap,
BITS_PER_BITMAP, i);
- if (next_zero - i >= search_bits) {
+ if (next_zero - i >= min_bits) {
found_bits = next_zero - i;
break;
}
@@ -2318,10 +2324,9 @@ again:
if (!found_bits)
return -ENOSPC;
- if (!found) {
+ if (!total_found) {
start = i;
cluster->max_size = 0;
- found = true;
}
total_found += found_bits;
@@ -2329,13 +2334,8 @@ again:
if (cluster->max_size < found_bits * block_group->sectorsize)
cluster->max_size = found_bits * block_group->sectorsize;
- if (total_found < total_bits) {
- i = find_next_bit(entry->bitmap, BITS_PER_BITMAP, next_zero);
- if (i - start > total_bits * 2) {
- total_found = 0;
- cluster->max_size = 0;
- found = false;
- }
+ if (total_found < want_bits || cluster->max_size < cont1_bytes) {
+ i = next_zero + 1;
goto again;
}
@@ -2351,23 +2351,23 @@ again:
/*
* This searches the block group for just extents to fill the cluster with.
+ * Try to find a cluster with at least bytes total bytes, at least one
+ * extent of cont1_bytes, and other clusters of at least min_bytes.
*/
static noinline int
setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
- u64 min_bytes)
+ u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *first = NULL;
struct btrfs_free_space *entry = NULL;
- struct btrfs_free_space *prev = NULL;
struct btrfs_free_space *last;
struct rb_node *node;
u64 window_start;
u64 window_free;
u64 max_extent;
- u64 max_gap = 128 * 1024;
entry = tree_search_offset(ctl, offset, 0, 1);
if (!entry)
@@ -2377,8 +2377,8 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
* We don't want bitmaps, so just move along until we find a normal
* extent entry.
*/
- while (entry->bitmap) {
- if (list_empty(&entry->list))
+ while (entry->bitmap || entry->bytes < min_bytes) {
+ if (entry->bitmap && list_empty(&entry->list))
list_add_tail(&entry->list, bitmaps);
node = rb_next(&entry->offset_index);
if (!node)
@@ -2391,12 +2391,9 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
max_extent = entry->bytes;
first = entry;
last = entry;
- prev = entry;
- while (window_free <= min_bytes) {
- node = rb_next(&entry->offset_index);
- if (!node)
- return -ENOSPC;
+ for (node = rb_next(&entry->offset_index); node;
+ node = rb_next(&entry->offset_index)) {
entry = rb_entry(node, struct btrfs_free_space, offset_index);
if (entry->bitmap) {
@@ -2405,26 +2402,18 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
continue;
}
- /*
- * we haven't filled the empty size and the window is
- * very large. reset and try again
- */
- if (entry->offset - (prev->offset + prev->bytes) > max_gap ||
- entry->offset - window_start > (min_bytes * 2)) {
- first = entry;
- window_start = entry->offset;
- window_free = entry->bytes;
- last = entry;
+ if (entry->bytes < min_bytes)
+ continue;
+
+ last = entry;
+ window_free += entry->bytes;
+ if (entry->bytes > max_extent)
max_extent = entry->bytes;
- } else {
- last = entry;
- window_free += entry->bytes;
- if (entry->bytes > max_extent)
- max_extent = entry->bytes;
- }
- prev = entry;
}
+ if (window_free < bytes || max_extent < cont1_bytes)
+ return -ENOSPC;
+
cluster->window_start = first->offset;
node = &first->offset_index;
@@ -2438,7 +2427,7 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
entry = rb_entry(node, struct btrfs_free_space, offset_index);
node = rb_next(&entry->offset_index);
- if (entry->bitmap)
+ if (entry->bitmap || entry->bytes < min_bytes)
continue;
rb_erase(&entry->offset_index, &ctl->free_space_offset);
@@ -2460,7 +2449,7 @@ static noinline int
setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
- u64 min_bytes)
+ u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry;
@@ -2485,7 +2474,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
if (entry->bytes < min_bytes)
continue;
ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
- bytes, min_bytes);
+ bytes, cont1_bytes, min_bytes);
if (!ret)
return 0;
}
@@ -2499,7 +2488,7 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
/*
* here we try to find a cluster of blocks in a block group. The goal
- * is to find at least bytes free and up to empty_size + bytes free.
+ * is to find at least bytes+empty_size.
* We might not find them all in one contiguous area.
*
* returns zero and sets up cluster if things worked out, otherwise
@@ -2515,23 +2504,24 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
struct btrfs_free_space *entry, *tmp;
LIST_HEAD(bitmaps);
u64 min_bytes;
+ u64 cont1_bytes;
int ret;
- /* for metadata, allow allocates with more holes */
+ /*
+ * Choose the minimum extent size we'll require for this
+ * cluster. For SSD_SPREAD, don't allow any fragmentation.
+ * For metadata, allow allocates with smaller extents. For
+ * data, keep it dense.
+ */
if (btrfs_test_opt(root, SSD_SPREAD)) {
- min_bytes = bytes + empty_size;
+ cont1_bytes = min_bytes = bytes + empty_size;
} else if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
- /*
- * we want to do larger allocations when we are
- * flushing out the delayed refs, it helps prevent
- * making more work as we go along.
- */
- if (trans->transaction->delayed_refs.flushing)
- min_bytes = max(bytes, (bytes + empty_size) >> 1);
- else
- min_bytes = max(bytes, (bytes + empty_size) >> 4);
- } else
- min_bytes = max(bytes, (bytes + empty_size) >> 2);
+ cont1_bytes = bytes;
+ min_bytes = block_group->sectorsize;
+ } else {
+ cont1_bytes = max(bytes, (bytes + empty_size) >> 2);
+ min_bytes = block_group->sectorsize;
+ }
spin_lock(&ctl->tree_lock);
@@ -2539,7 +2529,7 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
* If we know we don't have enough space to make a cluster don't even
* bother doing all the work to try and find one.
*/
- if (ctl->free_space < min_bytes) {
+ if (ctl->free_space < bytes) {
spin_unlock(&ctl->tree_lock);
return -ENOSPC;
}
@@ -2553,10 +2543,12 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
}
ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
- bytes, min_bytes);
+ bytes + empty_size,
+ cont1_bytes, min_bytes);
if (ret)
ret = setup_cluster_bitmap(block_group, cluster, &bitmaps,
- offset, bytes, min_bytes);
+ offset, bytes + empty_size,
+ cont1_bytes, min_bytes);
/* Clear our temporary list */
list_for_each_entry_safe(entry, tmp, &bitmaps, list)
@@ -2588,17 +2580,57 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
cluster->block_group = NULL;
}
-int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
- u64 *trimmed, u64 start, u64 end, u64 minlen)
+static int do_trimming(struct btrfs_block_group_cache *block_group,
+ u64 *total_trimmed, u64 start, u64 bytes,
+ u64 reserved_start, u64 reserved_bytes)
{
- struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
- struct btrfs_free_space *entry = NULL;
+ struct btrfs_space_info *space_info = block_group->space_info;
struct btrfs_fs_info *fs_info = block_group->fs_info;
- u64 bytes = 0;
- u64 actually_trimmed;
- int ret = 0;
+ int ret;
+ int update = 0;
+ u64 trimmed = 0;
- *trimmed = 0;
+ spin_lock(&space_info->lock);
+ spin_lock(&block_group->lock);
+ if (!block_group->ro) {
+ block_group->reserved += reserved_bytes;
+ space_info->bytes_reserved += reserved_bytes;
+ update = 1;
+ }
+ spin_unlock(&block_group->lock);
+ spin_unlock(&space_info->lock);
+
+ ret = btrfs_error_discard_extent(fs_info->extent_root,
+ start, bytes, &trimmed);
+ if (!ret)
+ *total_trimmed += trimmed;
+
+ btrfs_add_free_space(block_group, reserved_start, reserved_bytes);
+
+ if (update) {
+ spin_lock(&space_info->lock);
+ spin_lock(&block_group->lock);
+ if (block_group->ro)
+ space_info->bytes_readonly += reserved_bytes;
+ block_group->reserved -= reserved_bytes;
+ space_info->bytes_reserved -= reserved_bytes;
+ spin_unlock(&space_info->lock);
+ spin_unlock(&block_group->lock);
+ }
+
+ return ret;
+}
+
+static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
+ u64 *total_trimmed, u64 start, u64 end, u64 minlen)
+{
+ struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+ struct btrfs_free_space *entry;
+ struct rb_node *node;
+ int ret = 0;
+ u64 extent_start;
+ u64 extent_bytes;
+ u64 bytes;
while (start < end) {
spin_lock(&ctl->tree_lock);
@@ -2609,81 +2641,118 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
}
entry = tree_search_offset(ctl, start, 0, 1);
- if (!entry)
- entry = tree_search_offset(ctl,
- offset_to_bitmap(ctl, start),
- 1, 1);
-
- if (!entry || entry->offset >= end) {
+ if (!entry) {
spin_unlock(&ctl->tree_lock);
break;
}
- if (entry->bitmap) {
- ret = search_bitmap(ctl, entry, &start, &bytes);
- if (!ret) {
- if (start >= end) {
- spin_unlock(&ctl->tree_lock);
- break;
- }
- bytes = min(bytes, end - start);
- bitmap_clear_bits(ctl, entry, start, bytes);
- if (entry->bytes == 0)
- free_bitmap(ctl, entry);
- } else {
- start = entry->offset + BITS_PER_BITMAP *
- block_group->sectorsize;
+ /* skip bitmaps */
+ while (entry->bitmap) {
+ node = rb_next(&entry->offset_index);
+ if (!node) {
spin_unlock(&ctl->tree_lock);
- ret = 0;
- continue;
+ goto out;
}
- } else {
- start = entry->offset;
- bytes = min(entry->bytes, end - start);
- unlink_free_space(ctl, entry);
- kmem_cache_free(btrfs_free_space_cachep, entry);
+ entry = rb_entry(node, struct btrfs_free_space,
+ offset_index);
}
+ if (entry->offset >= end) {
+ spin_unlock(&ctl->tree_lock);
+ break;
+ }
+
+ extent_start = entry->offset;
+ extent_bytes = entry->bytes;
+ start = max(start, extent_start);
+ bytes = min(extent_start + extent_bytes, end) - start;
+ if (bytes < minlen) {
+ spin_unlock(&ctl->tree_lock);
+ goto next;
+ }
+
+ unlink_free_space(ctl, entry);
+ kmem_cache_free(btrfs_free_space_cachep, entry);
+
spin_unlock(&ctl->tree_lock);
- if (bytes >= minlen) {
- struct btrfs_space_info *space_info;
- int update = 0;
-
- space_info = block_group->space_info;
- spin_lock(&space_info->lock);
- spin_lock(&block_group->lock);
- if (!block_group->ro) {
- block_group->reserved += bytes;
- space_info->bytes_reserved += bytes;
- update = 1;
- }
- spin_unlock(&block_group->lock);
- spin_unlock(&space_info->lock);
-
- ret = btrfs_error_discard_extent(fs_info->extent_root,
- start,
- bytes,
- &actually_trimmed);
-
- btrfs_add_free_space(block_group, start, bytes);
- if (update) {
- spin_lock(&space_info->lock);
- spin_lock(&block_group->lock);
- if (block_group->ro)
- space_info->bytes_readonly += bytes;
- block_group->reserved -= bytes;
- space_info->bytes_reserved -= bytes;
- spin_unlock(&space_info->lock);
- spin_unlock(&block_group->lock);
- }
+ ret = do_trimming(block_group, total_trimmed, start, bytes,
+ extent_start, extent_bytes);
+ if (ret)
+ break;
+next:
+ start += bytes;
- if (ret)
- break;
- *trimmed += actually_trimmed;
+ if (fatal_signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+
+ cond_resched();
+ }
+out:
+ return ret;
+}
+
+static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
+ u64 *total_trimmed, u64 start, u64 end, u64 minlen)
+{
+ struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+ struct btrfs_free_space *entry;
+ int ret = 0;
+ int ret2;
+ u64 bytes;
+ u64 offset = offset_to_bitmap(ctl, start);
+
+ while (offset < end) {
+ bool next_bitmap = false;
+
+ spin_lock(&ctl->tree_lock);
+
+ if (ctl->free_space < minlen) {
+ spin_unlock(&ctl->tree_lock);
+ break;
+ }
+
+ entry = tree_search_offset(ctl, offset, 1, 0);
+ if (!entry) {
+ spin_unlock(&ctl->tree_lock);
+ next_bitmap = true;
+ goto next;
+ }
+
+ bytes = minlen;
+ ret2 = search_bitmap(ctl, entry, &start, &bytes);
+ if (ret2 || start >= end) {
+ spin_unlock(&ctl->tree_lock);
+ next_bitmap = true;
+ goto next;
+ }
+
+ bytes = min(bytes, end - start);
+ if (bytes < minlen) {
+ spin_unlock(&ctl->tree_lock);
+ goto next;
+ }
+
+ bitmap_clear_bits(ctl, entry, start, bytes);
+ if (entry->bytes == 0)
+ free_bitmap(ctl, entry);
+
+ spin_unlock(&ctl->tree_lock);
+
+ ret = do_trimming(block_group, total_trimmed, start, bytes,
+ start, bytes);
+ if (ret)
+ break;
+next:
+ if (next_bitmap) {
+ offset += BITS_PER_BITMAP * ctl->unit;
+ } else {
+ start += bytes;
+ if (start >= offset + BITS_PER_BITMAP * ctl->unit)
+ offset += BITS_PER_BITMAP * ctl->unit;
}
- start += bytes;
- bytes = 0;
if (fatal_signal_pending(current)) {
ret = -ERESTARTSYS;
@@ -2696,6 +2765,22 @@ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
return ret;
}
+int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+ u64 *trimmed, u64 start, u64 end, u64 minlen)
+{
+ int ret;
+
+ *trimmed = 0;
+
+ ret = trim_no_bitmap(block_group, trimmed, start, end, minlen);
+ if (ret)
+ return ret;
+
+ ret = trim_bitmaps(block_group, trimmed, start, end, minlen);
+
+ return ret;
+}
+
/*
* Find the left-most item in the cache tree, and then return the
* smallest inode number in the item.
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 603d740f0f1..acc4ff39ca4 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -38,6 +38,7 @@
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
+#include <linux/mount.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
@@ -2031,7 +2032,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
/* insert an orphan item to track this unlinked/truncated file */
if (insert >= 1) {
ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode));
- BUG_ON(ret);
+ BUG_ON(ret && ret != -EEXIST);
}
/* insert an orphan item to track subvolume contains orphan files */
@@ -2158,6 +2159,38 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
if (ret && ret != -ESTALE)
goto out;
+ if (ret == -ESTALE && root == root->fs_info->tree_root) {
+ struct btrfs_root *dead_root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ int is_dead_root = 0;
+
+ /*
+ * this is an orphan in the tree root. Currently these
+ * could come from 2 sources:
+ * a) a snapshot deletion in progress
+ * b) a free space cache inode
+ * We need to distinguish those two, as the snapshot
+ * orphan must not get deleted.
+ * find_dead_roots already ran before us, so if this
+ * is a snapshot deletion, we should find the root
+ * in the dead_roots list
+ */
+ spin_lock(&fs_info->trans_lock);
+ list_for_each_entry(dead_root, &fs_info->dead_roots,
+ root_list) {
+ if (dead_root->root_key.objectid ==
+ found_key.objectid) {
+ is_dead_root = 1;
+ break;
+ }
+ }
+ spin_unlock(&fs_info->trans_lock);
+ if (is_dead_root) {
+ /* prevent this orphan from being found again */
+ key.offset = found_key.objectid - 1;
+ continue;
+ }
+ }
/*
* Inode is already gone but the orphan item is still there,
* kill the orphan item.
@@ -2191,7 +2224,14 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
continue;
}
nr_truncate++;
+ /*
+ * Need to hold the imutex for reservation purposes, not
+ * a huge deal here but I have a WARN_ON in
+ * btrfs_delalloc_reserve_space to catch offenders.
+ */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_truncate(inode);
+ mutex_unlock(&inode->i_mutex);
} else {
nr_unlink++;
}
@@ -2318,7 +2358,7 @@ static void btrfs_read_locked_inode(struct inode *inode)
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
inode->i_mode = btrfs_inode_mode(leaf, inode_item);
- inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
+ set_nlink(inode, btrfs_inode_nlink(leaf, inode_item));
inode->i_uid = btrfs_inode_uid(leaf, inode_item);
inode->i_gid = btrfs_inode_gid(leaf, inode_item);
btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
@@ -3327,7 +3367,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
u64 hint_byte = 0;
hole_size = last_byte - cur_offset;
- trans = btrfs_start_transaction(root, 2);
+ trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
break;
@@ -3337,6 +3377,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
cur_offset + hole_size,
&hint_byte, 1);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
@@ -3346,6 +3387,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
0, hole_size, 0, hole_size,
0, 0, 0);
if (err) {
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
break;
}
@@ -3353,6 +3395,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
btrfs_drop_extent_cache(inode, hole_start,
last_byte - 1, 0);
+ btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
}
free_extent_map(em);
@@ -3370,6 +3413,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
static int btrfs_setsize(struct inode *inode, loff_t newsize)
{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_trans_handle *trans;
loff_t oldsize = i_size_read(inode);
int ret;
@@ -3377,16 +3422,19 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
return 0;
if (newsize > oldsize) {
- i_size_write(inode, newsize);
- btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
truncate_pagecache(inode, oldsize, newsize);
ret = btrfs_cont_expand(inode, oldsize, newsize);
- if (ret) {
- btrfs_setsize(inode, oldsize);
+ if (ret)
return ret;
- }
- mark_inode_dirty(inode);
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ i_size_write(inode, newsize);
+ btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ ret = btrfs_update_inode(trans, root, inode);
+ btrfs_end_transaction_throttle(trans, root);
} else {
/*
@@ -3426,9 +3474,9 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
if (attr->ia_valid) {
setattr_copy(inode, attr);
- mark_inode_dirty(inode);
+ err = btrfs_dirty_inode(inode);
- if (attr->ia_valid & ATTR_MODE)
+ if (!err && attr->ia_valid & ATTR_MODE)
err = btrfs_acl_chmod(inode);
}
@@ -4204,42 +4252,80 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
* FIXME, needs more benchmarking...there are no reasons other than performance
* to keep or drop this code.
*/
-void btrfs_dirty_inode(struct inode *inode, int flags)
+int btrfs_dirty_inode(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
int ret;
if (BTRFS_I(inode)->dummy_inode)
- return;
+ return 0;
trans = btrfs_join_transaction(root);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
if (ret && ret == -ENOSPC) {
/* whoops, lets try again with the full transaction */
btrfs_end_transaction(trans, root);
trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans)) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %ld\n",
- (unsigned long long)btrfs_ino(inode),
- PTR_ERR(trans));
- return;
- }
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_update_inode(trans, root, inode);
- if (ret) {
- printk_ratelimited(KERN_ERR "btrfs: fail to "
- "dirty inode %llu error %d\n",
- (unsigned long long)btrfs_ino(inode),
- ret);
- }
}
btrfs_end_transaction(trans, root);
if (BTRFS_I(inode)->delayed_node)
btrfs_balance_delayed_items(root);
+
+ return ret;
+}
+
+/*
+ * This is a copy of file_update_time. We need this so we can return error on
+ * ENOSPC for updating the inode in the case of file write and mmap writes.
+ */
+int btrfs_update_time(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct timespec now;
+ int ret;
+ enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
+
+ /* First try to exhaust all avenues to not sync */
+ if (IS_NOCMTIME(inode))
+ return 0;
+
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_mtime, &now))
+ sync_it = S_MTIME;
+
+ if (!timespec_equal(&inode->i_ctime, &now))
+ sync_it |= S_CTIME;
+
+ if (IS_I_VERSION(inode))
+ sync_it |= S_VERSION;
+
+ if (!sync_it)
+ return 0;
+
+ /* Finally allowed to write? Takes lock. */
+ if (mnt_want_write_file(file))
+ return 0;
+
+ /* Only change inode inside the lock region */
+ if (sync_it & S_VERSION)
+ inode_inc_iversion(inode);
+ if (sync_it & S_CTIME)
+ inode->i_ctime = now;
+ if (sync_it & S_MTIME)
+ inode->i_mtime = now;
+ ret = btrfs_dirty_inode(inode);
+ if (!ret)
+ mark_inode_dirty_sync(inode);
+ mnt_drop_write(file->f_path.mnt);
+ return ret;
}
/*
@@ -4504,10 +4590,6 @@ static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
int err = btrfs_add_link(trans, dir, inode,
dentry->d_name.name, dentry->d_name.len,
backref, index);
- if (!err) {
- d_instantiate(dentry, inode);
- return 0;
- }
if (err > 0)
err = -EEXIST;
return err;
@@ -4555,13 +4637,21 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+
+ inode->i_op = &btrfs_special_inode_operations;
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
- inode->i_op = &btrfs_special_inode_operations;
init_special_inode(inode, inode->i_mode, rdev);
btrfs_update_inode(trans, root, inode);
+ d_instantiate(dentry, inode);
}
out_unlock:
nr = trans->blocks_used;
@@ -4613,15 +4703,23 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+ d_instantiate(dentry, inode);
}
out_unlock:
nr = trans->blocks_used;
@@ -4679,6 +4777,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *parent = dentry->d_parent;
err = btrfs_update_inode(trans, root, inode);
BUG_ON(err);
+ d_instantiate(dentry, inode);
btrfs_log_new_name(trans, inode, NULL, parent);
}
@@ -6303,7 +6402,12 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
u64 page_start;
u64 page_end;
+ /* Need this to keep space reservations serialized */
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
+ if (!ret)
+ ret = btrfs_update_time(vma->vm_file);
if (ret) {
if (ret == -ENOMEM)
ret = VM_FAULT_OOM;
@@ -6515,8 +6619,9 @@ static int btrfs_truncate(struct inode *inode)
/* Just need the 1 for updating the inode */
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
- goto out;
+ ret = err = PTR_ERR(trans);
+ trans = NULL;
+ break;
}
}
@@ -6593,7 +6698,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
inode->i_op = &btrfs_dir_inode_operations;
inode->i_fop = &btrfs_dir_file_operations;
- inode->i_nlink = 1;
+ set_nlink(inode, 1);
btrfs_i_size_write(inode, 0);
err = btrfs_update_inode(trans, new_root, inode);
@@ -7076,14 +7181,21 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
+ /*
+ * If the active LSM wants to access the inode during
+ * d_instantiate it needs these. Smack checks to see
+ * if the filesystem supports xattrs by looking at the
+ * ops vector.
+ */
+ inode->i_fop = &btrfs_file_operations;
+ inode->i_op = &btrfs_file_inode_operations;
+
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
drop_inode = 1;
else {
inode->i_mapping->a_ops = &btrfs_aops;
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
- inode->i_fop = &btrfs_file_operations;
- inode->i_op = &btrfs_file_inode_operations;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
}
if (drop_inode)
@@ -7132,6 +7244,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
drop_inode = 1;
out_unlock:
+ if (!err)
+ d_instantiate(dentry, inode);
nr = trans->blocks_used;
btrfs_end_transaction_throttle(trans, root);
if (drop_inode) {
@@ -7353,6 +7467,7 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
.follow_link = page_follow_link_light,
.put_link = page_put_link,
.getattr = btrfs_getattr,
+ .setattr = btrfs_setattr,
.permission = btrfs_permission,
.setxattr = btrfs_setxattr,
.getxattr = btrfs_getxattr,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 9b0526872b7..7fdf22c2dc0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -176,6 +176,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
struct btrfs_trans_handle *trans;
unsigned int flags, oldflags;
int ret;
+ u64 ip_oldflags;
+ unsigned int i_oldflags;
if (btrfs_root_readonly(root))
return -EROFS;
@@ -192,6 +194,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
mutex_lock(&inode->i_mutex);
+ ip_oldflags = ip->flags;
+ i_oldflags = inode->i_flags;
+
flags = btrfs_mask_flags(inode->i_mode, flags);
oldflags = btrfs_flags_to_ioctl(ip->flags);
if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
@@ -249,19 +254,24 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
}
- trans = btrfs_join_transaction(root);
- BUG_ON(IS_ERR(trans));
-
- ret = btrfs_update_inode(trans, root, inode);
- BUG_ON(ret);
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_drop;
+ }
btrfs_update_iflags(inode);
inode->i_ctime = CURRENT_TIME;
+ ret = btrfs_update_inode(trans, root, inode);
+
btrfs_end_transaction(trans, root);
+ out_drop:
+ if (ret) {
+ ip->flags = ip_oldflags;
+ inode->i_flags = i_oldflags;
+ }
mnt_drop_write(file->f_path.mnt);
-
- ret = 0;
out_unlock:
mutex_unlock(&inode->i_mutex);
return ret;
@@ -858,8 +868,10 @@ static int cluster_pages_for_defrag(struct inode *inode,
return 0;
file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode,
num_pages << PAGE_CACHE_SHIFT);
+ mutex_unlock(&inode->i_mutex);
if (ret)
return ret;
again:
@@ -1201,13 +1213,21 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ mutex_lock(&root->fs_info->volume_mutex);
+ if (root->fs_info->balance_ctl) {
+ printk(KERN_INFO "btrfs: balance in progress\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
vol_args = memdup_user(arg, sizeof(*vol_args));
- if (IS_ERR(vol_args))
- return PTR_ERR(vol_args);
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
- mutex_lock(&root->fs_info->volume_mutex);
sizestr = vol_args->name;
devstr = strchr(sizestr, ':');
if (devstr) {
@@ -1224,7 +1244,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
(unsigned long long)devid);
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
if (!strcmp(sizestr, "max"))
new_size = device->bdev->bd_inode->i_size;
@@ -1239,7 +1259,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
new_size = memparse(sizestr, NULL);
if (new_size == 0) {
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
}
@@ -1248,7 +1268,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
if (mod < 0) {
if (new_size > old_size) {
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
new_size = old_size - new_size;
} else if (mod > 0) {
@@ -1257,11 +1277,11 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
if (new_size < 256 * 1024 * 1024) {
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
if (new_size > device->bdev->bd_inode->i_size) {
ret = -EFBIG;
- goto out_unlock;
+ goto out_free;
}
do_div(new_size, root->sectorsize);
@@ -1274,7 +1294,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- goto out_unlock;
+ goto out_free;
}
ret = btrfs_grow_device(trans, device, new_size);
btrfs_commit_transaction(trans, root);
@@ -1282,9 +1302,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
ret = btrfs_shrink_device(device, new_size);
}
-out_unlock:
- mutex_unlock(&root->fs_info->volume_mutex);
+out_free:
kfree(vol_args);
+out:
+ mutex_unlock(&root->fs_info->volume_mutex);
return ret;
}
@@ -2050,14 +2071,25 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ mutex_lock(&root->fs_info->volume_mutex);
+ if (root->fs_info->balance_ctl) {
+ printk(KERN_INFO "btrfs: balance in progress\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
vol_args = memdup_user(arg, sizeof(*vol_args));
- if (IS_ERR(vol_args))
- return PTR_ERR(vol_args);
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
ret = btrfs_init_new_device(root, vol_args->name);
kfree(vol_args);
+out:
+ mutex_unlock(&root->fs_info->volume_mutex);
return ret;
}
@@ -2072,14 +2104,25 @@ static long btrfs_ioctl_rm_dev(struct btrfs_root *root, void __user *arg)
if (root->fs_info->sb->s_flags & MS_RDONLY)
return -EROFS;
+ mutex_lock(&root->fs_info->volume_mutex);
+ if (root->fs_info->balance_ctl) {
+ printk(KERN_INFO "btrfs: balance in progress\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
vol_args = memdup_user(arg, sizeof(*vol_args));
- if (IS_ERR(vol_args))
- return PTR_ERR(vol_args);
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
ret = btrfs_rm_device(root, vol_args->name);
kfree(vol_args);
+out:
+ mutex_unlock(&root->fs_info->volume_mutex);
return ret;
}
@@ -3035,6 +3078,163 @@ out:
return ret;
}
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+ struct btrfs_ioctl_balance_args *bargs)
+{
+ struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+ bargs->flags = bctl->flags;
+
+ if (atomic_read(&fs_info->balance_running))
+ bargs->state |= BTRFS_BALANCE_STATE_RUNNING;
+ if (atomic_read(&fs_info->balance_pause_req))
+ bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ;
+ if (atomic_read(&fs_info->balance_cancel_req))
+ bargs->state |= BTRFS_BALANCE_STATE_CANCEL_REQ;
+
+ memcpy(&bargs->data, &bctl->data, sizeof(bargs->data));
+ memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta));
+ memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys));
+
+ if (lock) {
+ spin_lock(&fs_info->balance_lock);
+ memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+ spin_unlock(&fs_info->balance_lock);
+ } else {
+ memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+ }
+}
+
+static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_ioctl_balance_args *bargs;
+ struct btrfs_balance_control *bctl;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (fs_info->sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
+ mutex_lock(&fs_info->volume_mutex);
+ mutex_lock(&fs_info->balance_mutex);
+
+ if (arg) {
+ bargs = memdup_user(arg, sizeof(*bargs));
+ if (IS_ERR(bargs)) {
+ ret = PTR_ERR(bargs);
+ goto out;
+ }
+
+ if (bargs->flags & BTRFS_BALANCE_RESUME) {
+ if (!fs_info->balance_ctl) {
+ ret = -ENOTCONN;
+ goto out_bargs;
+ }
+
+ bctl = fs_info->balance_ctl;
+ spin_lock(&fs_info->balance_lock);
+ bctl->flags |= BTRFS_BALANCE_RESUME;
+ spin_unlock(&fs_info->balance_lock);
+
+ goto do_balance;
+ }
+ } else {
+ bargs = NULL;
+ }
+
+ if (fs_info->balance_ctl) {
+ ret = -EINPROGRESS;
+ goto out_bargs;
+ }
+
+ bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
+ if (!bctl) {
+ ret = -ENOMEM;
+ goto out_bargs;
+ }
+
+ bctl->fs_info = fs_info;
+ if (arg) {
+ memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
+ memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
+ memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys));
+
+ bctl->flags = bargs->flags;
+ } else {
+ /* balance everything - no filters */
+ bctl->flags |= BTRFS_BALANCE_TYPE_MASK;
+ }
+
+do_balance:
+ ret = btrfs_balance(bctl, bargs);
+ /*
+ * bctl is freed in __cancel_balance or in free_fs_info if
+ * restriper was paused all the way until unmount
+ */
+ if (arg) {
+ if (copy_to_user(arg, bargs, sizeof(*bargs)))
+ ret = -EFAULT;
+ }
+
+out_bargs:
+ kfree(bargs);
+out:
+ mutex_unlock(&fs_info->balance_mutex);
+ mutex_unlock(&fs_info->volume_mutex);
+ return ret;
+}
+
+static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ switch (cmd) {
+ case BTRFS_BALANCE_CTL_PAUSE:
+ return btrfs_pause_balance(root->fs_info);
+ case BTRFS_BALANCE_CTL_CANCEL:
+ return btrfs_cancel_balance(root->fs_info);
+ }
+
+ return -EINVAL;
+}
+
+static long btrfs_ioctl_balance_progress(struct btrfs_root *root,
+ void __user *arg)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_ioctl_balance_args *bargs;
+ int ret = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ mutex_lock(&fs_info->balance_mutex);
+ if (!fs_info->balance_ctl) {
+ ret = -ENOTCONN;
+ goto out;
+ }
+
+ bargs = kzalloc(sizeof(*bargs), GFP_NOFS);
+ if (!bargs) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ update_ioctl_balance_args(fs_info, 1, bargs);
+
+ if (copy_to_user(arg, bargs, sizeof(*bargs)))
+ ret = -EFAULT;
+
+ kfree(bargs);
+out:
+ mutex_unlock(&fs_info->balance_mutex);
+ return ret;
+}
+
long btrfs_ioctl(struct file *file, unsigned int
cmd, unsigned long arg)
{
@@ -3079,7 +3279,7 @@ long btrfs_ioctl(struct file *file, unsigned int
case BTRFS_IOC_DEV_INFO:
return btrfs_ioctl_dev_info(root, argp);
case BTRFS_IOC_BALANCE:
- return btrfs_balance(root->fs_info->dev_root);
+ return btrfs_ioctl_balance(root, NULL);
case BTRFS_IOC_CLONE:
return btrfs_ioctl_clone(file, arg, 0, 0, 0);
case BTRFS_IOC_CLONE_RANGE:
@@ -3111,6 +3311,12 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_scrub_cancel(root, argp);
case BTRFS_IOC_SCRUB_PROGRESS:
return btrfs_ioctl_scrub_progress(root, argp);
+ case BTRFS_IOC_BALANCE_V2:
+ return btrfs_ioctl_balance(root, argp);
+ case BTRFS_IOC_BALANCE_CTL:
+ return btrfs_ioctl_balance_ctl(root, arg);
+ case BTRFS_IOC_BALANCE_PROGRESS:
+ return btrfs_ioctl_balance_progress(root, argp);
}
return -ENOTTY;
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index 252ae9915de..4f69028a68c 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -109,6 +109,55 @@ struct btrfs_ioctl_fs_info_args {
__u64 reserved[124]; /* pad to 1k */
};
+/* balance control ioctl modes */
+#define BTRFS_BALANCE_CTL_PAUSE 1
+#define BTRFS_BALANCE_CTL_CANCEL 2
+
+/*
+ * this is packed, because it should be exactly the same as its disk
+ * byte order counterpart (struct btrfs_disk_balance_args)
+ */
+struct btrfs_balance_args {
+ __u64 profiles;
+ __u64 usage;
+ __u64 devid;
+ __u64 pstart;
+ __u64 pend;
+ __u64 vstart;
+ __u64 vend;
+
+ __u64 target;
+
+ __u64 flags;
+
+ __u64 unused[8];
+} __attribute__ ((__packed__));
+
+/* report balance progress to userspace */
+struct btrfs_balance_progress {
+ __u64 expected; /* estimated # of chunks that will be
+ * relocated to fulfill the request */
+ __u64 considered; /* # of chunks we have considered so far */
+ __u64 completed; /* # of chunks relocated so far */
+};
+
+#define BTRFS_BALANCE_STATE_RUNNING (1ULL << 0)
+#define BTRFS_BALANCE_STATE_PAUSE_REQ (1ULL << 1)
+#define BTRFS_BALANCE_STATE_CANCEL_REQ (1ULL << 2)
+
+struct btrfs_ioctl_balance_args {
+ __u64 flags; /* in/out */
+ __u64 state; /* out */
+
+ struct btrfs_balance_args data; /* in/out */
+ struct btrfs_balance_args meta; /* in/out */
+ struct btrfs_balance_args sys; /* in/out */
+
+ struct btrfs_balance_progress stat; /* out */
+
+ __u64 unused[72]; /* pad to 1k */
+};
+
#define BTRFS_INO_LOOKUP_PATH_MAX 4080
struct btrfs_ioctl_ino_lookup_args {
__u64 treeid;
@@ -272,6 +321,11 @@ struct btrfs_ioctl_logical_ino_args {
struct btrfs_ioctl_dev_info_args)
#define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \
struct btrfs_ioctl_fs_info_args)
+#define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \
+ struct btrfs_ioctl_balance_args)
+#define BTRFS_IOC_BALANCE_CTL _IOW(BTRFS_IOCTL_MAGIC, 33, int)
+#define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 34, \
+ struct btrfs_ioctl_balance_args)
#define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \
struct btrfs_ioctl_ino_path_args)
#define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 8c1aae2c845..efe9f792544 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2949,7 +2949,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
while (index <= last_index) {
+ mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
+ mutex_unlock(&inode->i_mutex);
if (ret)
goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index b5edff25a53..6a6a51a809b 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1536,18 +1536,22 @@ static noinline_for_stack int scrub_supers(struct scrub_dev *sdev)
static noinline_for_stack int scrub_workers_get(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
+ int ret = 0;
mutex_lock(&fs_info->scrub_lock);
if (fs_info->scrub_workers_refcnt == 0) {
btrfs_init_workers(&fs_info->scrub_workers, "scrub",
fs_info->thread_pool_size, &fs_info->generic_worker);
fs_info->scrub_workers.idle_thresh = 4;
- btrfs_start_workers(&fs_info->scrub_workers, 1);
+ ret = btrfs_start_workers(&fs_info->scrub_workers);
+ if (ret)
+ goto out;
}
++fs_info->scrub_workers_refcnt;
+out:
mutex_unlock(&fs_info->scrub_lock);
- return 0;
+ return ret;
}
static noinline_for_stack void scrub_workers_put(struct btrfs_root *root)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 1a3ce9e0b49..5a7227fa938 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -41,6 +41,7 @@
#include <linux/slab.h>
#include <linux/cleancache.h>
#include <linux/mnt_namespace.h>
+#include <linux/ratelimit.h>
#include "compat.h"
#include "delayed-inode.h"
#include "ctree.h"
@@ -163,8 +164,9 @@ enum {
Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
- Opt_enospc_debug, Opt_subvolrootid, Opt_defrag,
- Opt_inode_cache, Opt_no_space_cache, Opt_recovery, Opt_err,
+ Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache,
+ Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
+ Opt_err,
};
static match_table_t tokens = {
@@ -199,6 +201,7 @@ static match_table_t tokens = {
{Opt_inode_cache, "inode_cache"},
{Opt_no_space_cache, "nospace_cache"},
{Opt_recovery, "recovery"},
+ {Opt_skip_balance, "skip_balance"},
{Opt_err, NULL},
};
@@ -397,6 +400,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
printk(KERN_INFO "btrfs: enabling auto recovery");
btrfs_set_opt(info->mount_opt, RECOVERY);
break;
+ case Opt_skip_balance:
+ btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
+ break;
case Opt_err:
printk(KERN_INFO "btrfs: unrecognized mount option "
"'%s'\n", p);
@@ -722,6 +728,8 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
seq_puts(seq, ",autodefrag");
if (btrfs_test_opt(root, INODE_MAP_CACHE))
seq_puts(seq, ",inode_cache");
+ if (btrfs_test_opt(root, SKIP_BALANCE))
+ seq_puts(seq, ",skip_balance");
return 0;
}
@@ -825,13 +833,9 @@ static char *setup_root_args(char *args)
static struct dentry *mount_subvol(const char *subvol_name, int flags,
const char *device_name, char *data)
{
- struct super_block *s;
struct dentry *root;
struct vfsmount *mnt;
- struct mnt_namespace *ns_private;
char *newargs;
- struct path path;
- int error;
newargs = setup_root_args(data);
if (!newargs)
@@ -842,39 +846,17 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags,
if (IS_ERR(mnt))
return ERR_CAST(mnt);
- ns_private = create_mnt_ns(mnt);
- if (IS_ERR(ns_private)) {
- mntput(mnt);
- return ERR_CAST(ns_private);
- }
+ root = mount_subtree(mnt, subvol_name);
- /*
- * This will trigger the automount of the subvol so we can just
- * drop the mnt we have here and return the dentry that we
- * found.
- */
- error = vfs_path_lookup(mnt->mnt_root, mnt, subvol_name,
- LOOKUP_FOLLOW, &path);
- put_mnt_ns(ns_private);
- if (error)
- return ERR_PTR(error);
-
- if (!is_subvolume_inode(path.dentry->d_inode)) {
- path_put(&path);
- mntput(mnt);
- error = -EINVAL;
+ if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) {
+ struct super_block *s = root->d_sb;
+ dput(root);
+ root = ERR_PTR(-EINVAL);
+ deactivate_locked_super(s);
printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n",
subvol_name);
- return ERR_PTR(-EINVAL);
}
- /* Get a ref to the sb and the dentry we found and return it */
- s = path.mnt->mnt_sb;
- atomic_inc(&s->s_active);
- root = dget(path.dentry);
- path_put(&path);
- down_write(&s->s_umount);
-
return root;
}
@@ -1079,7 +1061,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
u64 avail_space;
u64 used_space;
u64 min_stripe_size;
- int min_stripes = 1;
+ int min_stripes = 1, num_stripes = 1;
int i = 0, nr_devices;
int ret;
@@ -1093,12 +1075,16 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
/* calc min stripe number for data space alloction */
type = btrfs_get_alloc_profile(root, 1);
- if (type & BTRFS_BLOCK_GROUP_RAID0)
+ if (type & BTRFS_BLOCK_GROUP_RAID0) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID1)
+ num_stripes = nr_devices;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID1) {
min_stripes = 2;
- else if (type & BTRFS_BLOCK_GROUP_RAID10)
+ num_stripes = 2;
+ } else if (type & BTRFS_BLOCK_GROUP_RAID10) {
min_stripes = 4;
+ num_stripes = 4;
+ }
if (type & BTRFS_BLOCK_GROUP_DUP)
min_stripe_size = 2 * BTRFS_STRIPE_LEN;
@@ -1167,13 +1153,16 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
i = nr_devices - 1;
avail_space = 0;
while (nr_devices >= min_stripes) {
+ if (num_stripes > nr_devices)
+ num_stripes = nr_devices;
+
if (devices_info[i].max_avail >= min_stripe_size) {
int j;
u64 alloc_size;
- avail_space += devices_info[i].max_avail * min_stripes;
+ avail_space += devices_info[i].max_avail * num_stripes;
alloc_size = devices_info[i].max_avail;
- for (j = i + 1 - min_stripes; j <= i; j++)
+ for (j = i + 1 - num_stripes; j <= i; j++)
devices_info[j].max_avail -= alloc_size;
}
i--;
@@ -1290,6 +1279,16 @@ static int btrfs_unfreeze(struct super_block *sb)
return 0;
}
+static void btrfs_fs_dirty_inode(struct inode *inode, int flags)
+{
+ int ret;
+
+ ret = btrfs_dirty_inode(inode);
+ if (ret)
+ printk_ratelimited(KERN_ERR "btrfs: fail to dirty inode %Lu "
+ "error %d\n", btrfs_ino(inode), ret);
+}
+
static const struct super_operations btrfs_super_ops = {
.drop_inode = btrfs_drop_inode,
.evict_inode = btrfs_evict_inode,
@@ -1297,7 +1296,7 @@ static const struct super_operations btrfs_super_ops = {
.sync_fs = btrfs_sync_fs,
.show_options = btrfs_show_options,
.write_inode = btrfs_write_inode,
- .dirty_inode = btrfs_dirty_inode,
+ .dirty_inode = btrfs_fs_dirty_inode,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
.statfs = btrfs_statfs,
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 04c5c7c2c32..d5f987b49d7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -472,19 +472,12 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
btrfs_trans_release_metadata(trans, root);
trans->block_rsv = NULL;
- while (count < 4) {
+ while (count < 2) {
unsigned long cur = trans->delayed_ref_updates;
trans->delayed_ref_updates = 0;
if (cur &&
trans->transaction->delayed_refs.num_heads_ready > 64) {
trans->delayed_ref_updates = 0;
-
- /*
- * do a full flush if the transaction is trying
- * to close
- */
- if (trans->transaction->delayed_refs.flushing)
- cur = 0;
btrfs_run_delayed_refs(trans, root, cur);
} else {
break;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fce7b9ec3bf..cb877e0886a 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1031,7 +1031,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
if (nlink != inode->i_nlink) {
- inode->i_nlink = nlink;
+ set_nlink(inode, nlink);
btrfs_update_inode(trans, root, inode);
}
BTRFS_I(inode)->index_cnt = (u64)-1;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c37433d3cd8..e0b7bb92a17 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -23,6 +23,7 @@
#include <linux/random.h>
#include <linux/iocontext.h>
#include <linux/capability.h>
+#include <linux/kthread.h>
#include <asm/div64.h>
#include "compat.h"
#include "ctree.h"
@@ -295,6 +296,12 @@ loop_lock:
btrfs_requeue_work(&device->work);
goto done;
}
+ /* unplug every 64 requests just for good measure */
+ if (batch_run % 64 == 0) {
+ blk_finish_plug(&plug);
+ blk_start_plug(&plug);
+ sync_pending = 0;
+ }
}
cond_resched();
@@ -823,7 +830,6 @@ out:
/*
* find_free_dev_extent - find free space in the specified device
- * @trans: transaction handler
* @device: the device which we search the free space in
* @num_bytes: the size of the free space that we need
* @start: store the start of the free space.
@@ -842,8 +848,7 @@ out:
* But if we don't find suitable free space, it is used to store the size of
* the max free space.
*/
-int find_free_dev_extent(struct btrfs_trans_handle *trans,
- struct btrfs_device *device, u64 num_bytes,
+int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
u64 *start, u64 *len)
{
struct btrfs_key key;
@@ -887,7 +892,7 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
key.offset = search_start;
key.type = BTRFS_DEV_EXTENT_KEY;
- ret = btrfs_search_slot(trans, root, &key, path, 0, 0);
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto out;
if (ret > 0) {
@@ -1276,7 +1281,6 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
bool clear_super = false;
mutex_lock(&uuid_mutex);
- mutex_lock(&root->fs_info->volume_mutex);
all_avail = root->fs_info->avail_data_alloc_bits |
root->fs_info->avail_system_alloc_bits |
@@ -1446,7 +1450,6 @@ error_close:
if (bdev)
blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
out:
- mutex_unlock(&root->fs_info->volume_mutex);
mutex_unlock(&uuid_mutex);
return ret;
error_undo:
@@ -1463,8 +1466,7 @@ error_undo:
/*
* does all the dirty work required for changing file system's UUID.
*/
-static int btrfs_prepare_sprout(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
+static int btrfs_prepare_sprout(struct btrfs_root *root)
{
struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
struct btrfs_fs_devices *old_devices;
@@ -1611,7 +1613,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding)
return -EINVAL;
- bdev = blkdev_get_by_path(device_path, FMODE_EXCL,
+ bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
root->fs_info->bdev_holder);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
@@ -1623,7 +1625,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
}
filemap_write_and_wait(bdev->bd_inode->i_mapping);
- mutex_lock(&root->fs_info->volume_mutex);
devices = &root->fs_info->fs_devices->devices;
/*
@@ -1689,7 +1690,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
if (seeding_dev) {
sb->s_flags &= ~MS_RDONLY;
- ret = btrfs_prepare_sprout(trans, root);
+ ret = btrfs_prepare_sprout(root);
BUG_ON(ret);
}
@@ -1751,8 +1752,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
ret = btrfs_relocate_sys_chunks(root);
BUG_ON(ret);
}
-out:
- mutex_unlock(&root->fs_info->volume_mutex);
+
return ret;
error:
blkdev_put(bdev, FMODE_EXCL);
@@ -1760,7 +1760,7 @@ error:
mutex_unlock(&uuid_mutex);
up_write(&sb->s_umount);
}
- goto out;
+ return ret;
}
static noinline int btrfs_update_device(struct btrfs_trans_handle *trans,
@@ -2071,6 +2071,362 @@ error:
return ret;
}
+static int insert_balance_item(struct btrfs_root *root,
+ struct btrfs_balance_control *bctl)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_balance_item *item;
+ struct btrfs_disk_balance_args disk_bargs;
+ struct btrfs_path *path;
+ struct extent_buffer *leaf;
+ struct btrfs_key key;
+ int ret, err;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ btrfs_free_path(path);
+ return PTR_ERR(trans);
+ }
+
+ key.objectid = BTRFS_BALANCE_OBJECTID;
+ key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.offset = 0;
+
+ ret = btrfs_insert_empty_item(trans, root, path, &key,
+ sizeof(*item));
+ if (ret)
+ goto out;
+
+ leaf = path->nodes[0];
+ item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
+
+ memset_extent_buffer(leaf, 0, (unsigned long)item, sizeof(*item));
+
+ btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->data);
+ btrfs_set_balance_data(leaf, item, &disk_bargs);
+ btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->meta);
+ btrfs_set_balance_meta(leaf, item, &disk_bargs);
+ btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->sys);
+ btrfs_set_balance_sys(leaf, item, &disk_bargs);
+
+ btrfs_set_balance_flags(leaf, item, bctl->flags);
+
+ btrfs_mark_buffer_dirty(leaf);
+out:
+ btrfs_free_path(path);
+ err = btrfs_commit_transaction(trans, root);
+ if (err && !ret)
+ ret = err;
+ return ret;
+}
+
+static int del_balance_item(struct btrfs_root *root)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ int ret, err;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ btrfs_free_path(path);
+ return PTR_ERR(trans);
+ }
+
+ key.objectid = BTRFS_BALANCE_OBJECTID;
+ key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ ret = btrfs_del_item(trans, root, path);
+out:
+ btrfs_free_path(path);
+ err = btrfs_commit_transaction(trans, root);
+ if (err && !ret)
+ ret = err;
+ return ret;
+}
+
+/*
+ * This is a heuristic used to reduce the number of chunks balanced on
+ * resume after balance was interrupted.
+ */
+static void update_balance_args(struct btrfs_balance_control *bctl)
+{
+ /*
+ * Turn on soft mode for chunk types that were being converted.
+ */
+ if (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)
+ bctl->data.flags |= BTRFS_BALANCE_ARGS_SOFT;
+ if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)
+ bctl->sys.flags |= BTRFS_BALANCE_ARGS_SOFT;
+ if (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)
+ bctl->meta.flags |= BTRFS_BALANCE_ARGS_SOFT;
+
+ /*
+ * Turn on usage filter if is not already used. The idea is
+ * that chunks that we have already balanced should be
+ * reasonably full. Don't do it for chunks that are being
+ * converted - that will keep us from relocating unconverted
+ * (albeit full) chunks.
+ */
+ if (!(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+ !(bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
+ bctl->data.flags |= BTRFS_BALANCE_ARGS_USAGE;
+ bctl->data.usage = 90;
+ }
+ if (!(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+ !(bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
+ bctl->sys.flags |= BTRFS_BALANCE_ARGS_USAGE;
+ bctl->sys.usage = 90;
+ }
+ if (!(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE) &&
+ !(bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)) {
+ bctl->meta.flags |= BTRFS_BALANCE_ARGS_USAGE;
+ bctl->meta.usage = 90;
+ }
+}
+
+/*
+ * Should be called with both balance and volume mutexes held to
+ * serialize other volume operations (add_dev/rm_dev/resize) with
+ * restriper. Same goes for unset_balance_control.
+ */
+static void set_balance_control(struct btrfs_balance_control *bctl)
+{
+ struct btrfs_fs_info *fs_info = bctl->fs_info;
+
+ BUG_ON(fs_info->balance_ctl);
+
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl = bctl;
+ spin_unlock(&fs_info->balance_lock);
+}
+
+static void unset_balance_control(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+ BUG_ON(!fs_info->balance_ctl);
+
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl = NULL;
+ spin_unlock(&fs_info->balance_lock);
+
+ kfree(bctl);
+}
+
+/*
+ * Balance filters. Return 1 if chunk should be filtered out
+ * (should not be balanced).
+ */
+static int chunk_profiles_filter(u64 chunk_profile,
+ struct btrfs_balance_args *bargs)
+{
+ chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+ if (chunk_profile == 0)
+ chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+ if (bargs->profiles & chunk_profile)
+ return 0;
+
+ return 1;
+}
+
+static u64 div_factor_fine(u64 num, int factor)
+{
+ if (factor <= 0)
+ return 0;
+ if (factor >= 100)
+ return num;
+
+ num *= factor;
+ do_div(num, 100);
+ return num;
+}
+
+static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
+ struct btrfs_balance_args *bargs)
+{
+ struct btrfs_block_group_cache *cache;
+ u64 chunk_used, user_thresh;
+ int ret = 1;
+
+ cache = btrfs_lookup_block_group(fs_info, chunk_offset);
+ chunk_used = btrfs_block_group_used(&cache->item);
+
+ user_thresh = div_factor_fine(cache->key.offset, bargs->usage);
+ if (chunk_used < user_thresh)
+ ret = 0;
+
+ btrfs_put_block_group(cache);
+ return ret;
+}
+
+static int chunk_devid_filter(struct extent_buffer *leaf,
+ struct btrfs_chunk *chunk,
+ struct btrfs_balance_args *bargs)
+{
+ struct btrfs_stripe *stripe;
+ int num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+ int i;
+
+ for (i = 0; i < num_stripes; i++) {
+ stripe = btrfs_stripe_nr(chunk, i);
+ if (btrfs_stripe_devid(leaf, stripe) == bargs->devid)
+ return 0;
+ }
+
+ return 1;
+}
+
+/* [pstart, pend) */
+static int chunk_drange_filter(struct extent_buffer *leaf,
+ struct btrfs_chunk *chunk,
+ u64 chunk_offset,
+ struct btrfs_balance_args *bargs)
+{
+ struct btrfs_stripe *stripe;
+ int num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+ u64 stripe_offset;
+ u64 stripe_length;
+ int factor;
+ int i;
+
+ if (!(bargs->flags & BTRFS_BALANCE_ARGS_DEVID))
+ return 0;
+
+ if (btrfs_chunk_type(leaf, chunk) & (BTRFS_BLOCK_GROUP_DUP |
+ BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10))
+ factor = 2;
+ else
+ factor = 1;
+ factor = num_stripes / factor;
+
+ for (i = 0; i < num_stripes; i++) {
+ stripe = btrfs_stripe_nr(chunk, i);
+ if (btrfs_stripe_devid(leaf, stripe) != bargs->devid)
+ continue;
+
+ stripe_offset = btrfs_stripe_offset(leaf, stripe);
+ stripe_length = btrfs_chunk_length(leaf, chunk);
+ do_div(stripe_length, factor);
+
+ if (stripe_offset < bargs->pend &&
+ stripe_offset + stripe_length > bargs->pstart)
+ return 0;
+ }
+
+ return 1;
+}
+
+/* [vstart, vend) */
+static int chunk_vrange_filter(struct extent_buffer *leaf,
+ struct btrfs_chunk *chunk,
+ u64 chunk_offset,
+ struct btrfs_balance_args *bargs)
+{
+ if (chunk_offset < bargs->vend &&
+ chunk_offset + btrfs_chunk_length(leaf, chunk) > bargs->vstart)
+ /* at least part of the chunk is inside this vrange */
+ return 0;
+
+ return 1;
+}
+
+static int chunk_soft_convert_filter(u64 chunk_profile,
+ struct btrfs_balance_args *bargs)
+{
+ if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT))
+ return 0;
+
+ chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
+
+ if (chunk_profile == 0)
+ chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+
+ if (bargs->target & chunk_profile)
+ return 1;
+
+ return 0;
+}
+
+static int should_balance_chunk(struct btrfs_root *root,
+ struct extent_buffer *leaf,
+ struct btrfs_chunk *chunk, u64 chunk_offset)
+{
+ struct btrfs_balance_control *bctl = root->fs_info->balance_ctl;
+ struct btrfs_balance_args *bargs = NULL;
+ u64 chunk_type = btrfs_chunk_type(leaf, chunk);
+
+ /* type filter */
+ if (!((chunk_type & BTRFS_BLOCK_GROUP_TYPE_MASK) &
+ (bctl->flags & BTRFS_BALANCE_TYPE_MASK))) {
+ return 0;
+ }
+
+ if (chunk_type & BTRFS_BLOCK_GROUP_DATA)
+ bargs = &bctl->data;
+ else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM)
+ bargs = &bctl->sys;
+ else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA)
+ bargs = &bctl->meta;
+
+ /* profiles filter */
+ if ((bargs->flags & BTRFS_BALANCE_ARGS_PROFILES) &&
+ chunk_profiles_filter(chunk_type, bargs)) {
+ return 0;
+ }
+
+ /* usage filter */
+ if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE) &&
+ chunk_usage_filter(bctl->fs_info, chunk_offset, bargs)) {
+ return 0;
+ }
+
+ /* devid filter */
+ if ((bargs->flags & BTRFS_BALANCE_ARGS_DEVID) &&
+ chunk_devid_filter(leaf, chunk, bargs)) {
+ return 0;
+ }
+
+ /* drange filter, makes sense only with devid filter */
+ if ((bargs->flags & BTRFS_BALANCE_ARGS_DRANGE) &&
+ chunk_drange_filter(leaf, chunk, chunk_offset, bargs)) {
+ return 0;
+ }
+
+ /* vrange filter */
+ if ((bargs->flags & BTRFS_BALANCE_ARGS_VRANGE) &&
+ chunk_vrange_filter(leaf, chunk, chunk_offset, bargs)) {
+ return 0;
+ }
+
+ /* soft profile changing mode */
+ if ((bargs->flags & BTRFS_BALANCE_ARGS_SOFT) &&
+ chunk_soft_convert_filter(chunk_type, bargs)) {
+ return 0;
+ }
+
+ return 1;
+}
+
static u64 div_factor(u64 num, int factor)
{
if (factor == 10)
@@ -2080,29 +2436,28 @@ static u64 div_factor(u64 num, int factor)
return num;
}
-int btrfs_balance(struct btrfs_root *dev_root)
+static int __btrfs_balance(struct btrfs_fs_info *fs_info)
{
- int ret;
- struct list_head *devices = &dev_root->fs_info->fs_devices->devices;
+ struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+ struct btrfs_root *chunk_root = fs_info->chunk_root;
+ struct btrfs_root *dev_root = fs_info->dev_root;
+ struct list_head *devices;
struct btrfs_device *device;
u64 old_size;
u64 size_to_free;
+ struct btrfs_chunk *chunk;
struct btrfs_path *path;
struct btrfs_key key;
- struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root;
- struct btrfs_trans_handle *trans;
struct btrfs_key found_key;
-
- if (dev_root->fs_info->sb->s_flags & MS_RDONLY)
- return -EROFS;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- mutex_lock(&dev_root->fs_info->volume_mutex);
- dev_root = dev_root->fs_info->dev_root;
+ struct btrfs_trans_handle *trans;
+ struct extent_buffer *leaf;
+ int slot;
+ int ret;
+ int enospc_errors = 0;
+ bool counting = true;
/* step one make some room on all the devices */
+ devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
old_size = device->total_bytes;
size_to_free = div_factor(old_size, 1);
@@ -2131,11 +2486,23 @@ int btrfs_balance(struct btrfs_root *dev_root)
ret = -ENOMEM;
goto error;
}
+
+ /* zero out stat counters */
+ spin_lock(&fs_info->balance_lock);
+ memset(&bctl->stat, 0, sizeof(bctl->stat));
+ spin_unlock(&fs_info->balance_lock);
+again:
key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
key.offset = (u64)-1;
key.type = BTRFS_CHUNK_ITEM_KEY;
while (1) {
+ if ((!counting && atomic_read(&fs_info->balance_pause_req)) ||
+ atomic_read(&fs_info->balance_cancel_req)) {
+ ret = -ECANCELED;
+ goto error;
+ }
+
ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
if (ret < 0)
goto error;
@@ -2145,15 +2512,19 @@ int btrfs_balance(struct btrfs_root *dev_root)
* failed
*/
if (ret == 0)
- break;
+ BUG(); /* FIXME break ? */
ret = btrfs_previous_item(chunk_root, path, 0,
BTRFS_CHUNK_ITEM_KEY);
- if (ret)
+ if (ret) {
+ ret = 0;
break;
+ }
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ btrfs_item_key_to_cpu(leaf, &found_key, slot);
- btrfs_item_key_to_cpu(path->nodes[0], &found_key,
- path->slots[0]);
if (found_key.objectid != key.objectid)
break;
@@ -2161,22 +2532,375 @@ int btrfs_balance(struct btrfs_root *dev_root)
if (found_key.offset == 0)
break;
+ chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
+
+ if (!counting) {
+ spin_lock(&fs_info->balance_lock);
+ bctl->stat.considered++;
+ spin_unlock(&fs_info->balance_lock);
+ }
+
+ ret = should_balance_chunk(chunk_root, leaf, chunk,
+ found_key.offset);
btrfs_release_path(path);
+ if (!ret)
+ goto loop;
+
+ if (counting) {
+ spin_lock(&fs_info->balance_lock);
+ bctl->stat.expected++;
+ spin_unlock(&fs_info->balance_lock);
+ goto loop;
+ }
+
ret = btrfs_relocate_chunk(chunk_root,
chunk_root->root_key.objectid,
found_key.objectid,
found_key.offset);
if (ret && ret != -ENOSPC)
goto error;
+ if (ret == -ENOSPC) {
+ enospc_errors++;
+ } else {
+ spin_lock(&fs_info->balance_lock);
+ bctl->stat.completed++;
+ spin_unlock(&fs_info->balance_lock);
+ }
+loop:
key.offset = found_key.offset - 1;
}
- ret = 0;
+
+ if (counting) {
+ btrfs_release_path(path);
+ counting = false;
+ goto again;
+ }
error:
btrfs_free_path(path);
- mutex_unlock(&dev_root->fs_info->volume_mutex);
+ if (enospc_errors) {
+ printk(KERN_INFO "btrfs: %d enospc errors during balance\n",
+ enospc_errors);
+ if (!ret)
+ ret = -ENOSPC;
+ }
+
return ret;
}
+static inline int balance_need_close(struct btrfs_fs_info *fs_info)
+{
+ /* cancel requested || normal exit path */
+ return atomic_read(&fs_info->balance_cancel_req) ||
+ (atomic_read(&fs_info->balance_pause_req) == 0 &&
+ atomic_read(&fs_info->balance_cancel_req) == 0);
+}
+
+static void __cancel_balance(struct btrfs_fs_info *fs_info)
+{
+ int ret;
+
+ unset_balance_control(fs_info);
+ ret = del_balance_item(fs_info->tree_root);
+ BUG_ON(ret);
+}
+
+void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+ struct btrfs_ioctl_balance_args *bargs);
+
+/*
+ * Should be called with both balance and volume mutexes held
+ */
+int btrfs_balance(struct btrfs_balance_control *bctl,
+ struct btrfs_ioctl_balance_args *bargs)
+{
+ struct btrfs_fs_info *fs_info = bctl->fs_info;
+ u64 allowed;
+ int ret;
+
+ if (btrfs_fs_closing(fs_info) ||
+ atomic_read(&fs_info->balance_pause_req) ||
+ atomic_read(&fs_info->balance_cancel_req)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * In case of mixed groups both data and meta should be picked,
+ * and identical options should be given for both of them.
+ */
+ allowed = btrfs_super_incompat_flags(fs_info->super_copy);
+ if ((allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
+ (bctl->flags & (BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA))) {
+ if (!(bctl->flags & BTRFS_BALANCE_DATA) ||
+ !(bctl->flags & BTRFS_BALANCE_METADATA) ||
+ memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) {
+ printk(KERN_ERR "btrfs: with mixed groups data and "
+ "metadata balance options must be the same\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+
+ /*
+ * Profile changing sanity checks. Skip them if a simple
+ * balance is requested.
+ */
+ if (!((bctl->data.flags | bctl->sys.flags | bctl->meta.flags) &
+ BTRFS_BALANCE_ARGS_CONVERT))
+ goto do_balance;
+
+ allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
+ if (fs_info->fs_devices->num_devices == 1)
+ allowed |= BTRFS_BLOCK_GROUP_DUP;
+ else if (fs_info->fs_devices->num_devices < 4)
+ allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
+ else
+ allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10);
+
+ if (!profile_is_valid(bctl->data.target, 1) ||
+ bctl->data.target & ~allowed) {
+ printk(KERN_ERR "btrfs: unable to start balance with target "
+ "data profile %llu\n",
+ (unsigned long long)bctl->data.target);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!profile_is_valid(bctl->meta.target, 1) ||
+ bctl->meta.target & ~allowed) {
+ printk(KERN_ERR "btrfs: unable to start balance with target "
+ "metadata profile %llu\n",
+ (unsigned long long)bctl->meta.target);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!profile_is_valid(bctl->sys.target, 1) ||
+ bctl->sys.target & ~allowed) {
+ printk(KERN_ERR "btrfs: unable to start balance with target "
+ "system profile %llu\n",
+ (unsigned long long)bctl->sys.target);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (bctl->data.target & BTRFS_BLOCK_GROUP_DUP) {
+ printk(KERN_ERR "btrfs: dup for data is not allowed\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* allow to reduce meta or sys integrity only if force set */
+ allowed = BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10;
+ if (((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (fs_info->avail_system_alloc_bits & allowed) &&
+ !(bctl->sys.target & allowed)) ||
+ ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
+ (fs_info->avail_metadata_alloc_bits & allowed) &&
+ !(bctl->meta.target & allowed))) {
+ if (bctl->flags & BTRFS_BALANCE_FORCE) {
+ printk(KERN_INFO "btrfs: force reducing metadata "
+ "integrity\n");
+ } else {
+ printk(KERN_ERR "btrfs: balance will reduce metadata "
+ "integrity, use force if you want this\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+
+do_balance:
+ ret = insert_balance_item(fs_info->tree_root, bctl);
+ if (ret && ret != -EEXIST)
+ goto out;
+
+ if (!(bctl->flags & BTRFS_BALANCE_RESUME)) {
+ BUG_ON(ret == -EEXIST);
+ set_balance_control(bctl);
+ } else {
+ BUG_ON(ret != -EEXIST);
+ spin_lock(&fs_info->balance_lock);
+ update_balance_args(bctl);
+ spin_unlock(&fs_info->balance_lock);
+ }
+
+ atomic_inc(&fs_info->balance_running);
+ mutex_unlock(&fs_info->balance_mutex);
+
+ ret = __btrfs_balance(fs_info);
+
+ mutex_lock(&fs_info->balance_mutex);
+ atomic_dec(&fs_info->balance_running);
+
+ if (bargs) {
+ memset(bargs, 0, sizeof(*bargs));
+ update_ioctl_balance_args(fs_info, 0, bargs);
+ }
+
+ if ((ret && ret != -ECANCELED && ret != -ENOSPC) ||
+ balance_need_close(fs_info)) {
+ __cancel_balance(fs_info);
+ }
+
+ wake_up(&fs_info->balance_wait_q);
+
+ return ret;
+out:
+ if (bctl->flags & BTRFS_BALANCE_RESUME)
+ __cancel_balance(fs_info);
+ else
+ kfree(bctl);
+ return ret;
+}
+
+static int balance_kthread(void *data)
+{
+ struct btrfs_balance_control *bctl =
+ (struct btrfs_balance_control *)data;
+ struct btrfs_fs_info *fs_info = bctl->fs_info;
+ int ret = 0;
+
+ mutex_lock(&fs_info->volume_mutex);
+ mutex_lock(&fs_info->balance_mutex);
+
+ set_balance_control(bctl);
+
+ if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) {
+ printk(KERN_INFO "btrfs: force skipping balance\n");
+ } else {
+ printk(KERN_INFO "btrfs: continuing balance\n");
+ ret = btrfs_balance(bctl, NULL);
+ }
+
+ mutex_unlock(&fs_info->balance_mutex);
+ mutex_unlock(&fs_info->volume_mutex);
+ return ret;
+}
+
+int btrfs_recover_balance(struct btrfs_root *tree_root)
+{
+ struct task_struct *tsk;
+ struct btrfs_balance_control *bctl;
+ struct btrfs_balance_item *item;
+ struct btrfs_disk_balance_args disk_bargs;
+ struct btrfs_path *path;
+ struct extent_buffer *leaf;
+ struct btrfs_key key;
+ int ret;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
+ if (!bctl) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ key.objectid = BTRFS_BALANCE_OBJECTID;
+ key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out_bctl;
+ if (ret > 0) { /* ret = -ENOENT; */
+ ret = 0;
+ goto out_bctl;
+ }
+
+ leaf = path->nodes[0];
+ item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
+
+ bctl->fs_info = tree_root->fs_info;
+ bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME;
+
+ btrfs_balance_data(leaf, item, &disk_bargs);
+ btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs);
+ btrfs_balance_meta(leaf, item, &disk_bargs);
+ btrfs_disk_balance_args_to_cpu(&bctl->meta, &disk_bargs);
+ btrfs_balance_sys(leaf, item, &disk_bargs);
+ btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
+
+ tsk = kthread_run(balance_kthread, bctl, "btrfs-balance");
+ if (IS_ERR(tsk))
+ ret = PTR_ERR(tsk);
+ else
+ goto out;
+
+out_bctl:
+ kfree(bctl);
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+int btrfs_pause_balance(struct btrfs_fs_info *fs_info)
+{
+ int ret = 0;
+
+ mutex_lock(&fs_info->balance_mutex);
+ if (!fs_info->balance_ctl) {
+ mutex_unlock(&fs_info->balance_mutex);
+ return -ENOTCONN;
+ }
+
+ if (atomic_read(&fs_info->balance_running)) {
+ atomic_inc(&fs_info->balance_pause_req);
+ mutex_unlock(&fs_info->balance_mutex);
+
+ wait_event(fs_info->balance_wait_q,
+ atomic_read(&fs_info->balance_running) == 0);
+
+ mutex_lock(&fs_info->balance_mutex);
+ /* we are good with balance_ctl ripped off from under us */
+ BUG_ON(atomic_read(&fs_info->balance_running));
+ atomic_dec(&fs_info->balance_pause_req);
+ } else {
+ ret = -ENOTCONN;
+ }
+
+ mutex_unlock(&fs_info->balance_mutex);
+ return ret;
+}
+
+int btrfs_cancel_balance(struct btrfs_fs_info *fs_info)
+{
+ mutex_lock(&fs_info->balance_mutex);
+ if (!fs_info->balance_ctl) {
+ mutex_unlock(&fs_info->balance_mutex);
+ return -ENOTCONN;
+ }
+
+ atomic_inc(&fs_info->balance_cancel_req);
+ /*
+ * if we are running just wait and return, balance item is
+ * deleted in btrfs_balance in this case
+ */
+ if (atomic_read(&fs_info->balance_running)) {
+ mutex_unlock(&fs_info->balance_mutex);
+ wait_event(fs_info->balance_wait_q,
+ atomic_read(&fs_info->balance_running) == 0);
+ mutex_lock(&fs_info->balance_mutex);
+ } else {
+ /* __cancel_balance needs volume_mutex */
+ mutex_unlock(&fs_info->balance_mutex);
+ mutex_lock(&fs_info->volume_mutex);
+ mutex_lock(&fs_info->balance_mutex);
+
+ if (fs_info->balance_ctl)
+ __cancel_balance(fs_info);
+
+ mutex_unlock(&fs_info->volume_mutex);
+ }
+
+ BUG_ON(fs_info->balance_ctl || atomic_read(&fs_info->balance_running));
+ atomic_dec(&fs_info->balance_cancel_req);
+ mutex_unlock(&fs_info->balance_mutex);
+ return 0;
+}
+
/*
* shrinking a device means finding all of the device extents past
* the new size, and then following the back refs to the chunks.
@@ -2317,8 +3041,7 @@ done:
return ret;
}
-static int btrfs_add_system_chunk(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+static int btrfs_add_system_chunk(struct btrfs_root *root,
struct btrfs_key *key,
struct btrfs_chunk *chunk, int item_size)
{
@@ -2435,7 +3158,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
max_stripe_size = 1024 * 1024 * 1024;
max_chunk_size = 10 * max_stripe_size;
} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
- max_stripe_size = 256 * 1024 * 1024;
+ /* for larger filesystems, use larger metadata chunks */
+ if (fs_devices->total_rw_bytes > 50ULL * 1024 * 1024 * 1024)
+ max_stripe_size = 1024 * 1024 * 1024;
+ else
+ max_stripe_size = 256 * 1024 * 1024;
max_chunk_size = max_stripe_size;
} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
max_stripe_size = 8 * 1024 * 1024;
@@ -2490,7 +3217,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
if (total_avail == 0)
continue;
- ret = find_free_dev_extent(trans, device,
+ ret = find_free_dev_extent(device,
max_stripe_size * dev_stripes,
&dev_offset, &max_avail);
if (ret && ret != -ENOSPC)
@@ -2681,7 +3408,7 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans,
BUG_ON(ret);
if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
- ret = btrfs_add_system_chunk(trans, chunk_root, &key, chunk,
+ ret = btrfs_add_system_chunk(chunk_root, &key, chunk,
item_size);
BUG_ON(ret);
}
@@ -2746,8 +3473,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
return ret;
alloc_profile = BTRFS_BLOCK_GROUP_METADATA |
- (fs_info->metadata_alloc_profile &
- fs_info->avail_metadata_alloc_bits);
+ fs_info->avail_metadata_alloc_bits;
alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile);
ret = __btrfs_alloc_chunk(trans, extent_root, &map, &chunk_size,
@@ -2757,8 +3483,7 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
sys_chunk_offset = chunk_offset + chunk_size;
alloc_profile = BTRFS_BLOCK_GROUP_SYSTEM |
- (fs_info->system_alloc_profile &
- fs_info->avail_system_alloc_bits);
+ fs_info->avail_system_alloc_bits;
alloc_profile = btrfs_reduce_alloc_profile(root, alloc_profile);
ret = __btrfs_alloc_chunk(trans, extent_root, &sys_map,
@@ -2895,26 +3620,13 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
u64 stripe_nr;
u64 stripe_nr_orig;
u64 stripe_nr_end;
- int stripes_allocated = 8;
- int stripes_required = 1;
int stripe_index;
int i;
+ int ret = 0;
int num_stripes;
int max_errors = 0;
struct btrfs_bio *bbio = NULL;
- if (bbio_ret && !(rw & (REQ_WRITE | REQ_DISCARD)))
- stripes_allocated = 1;
-again:
- if (bbio_ret) {
- bbio = kzalloc(btrfs_bio_size(stripes_allocated),
- GFP_NOFS);
- if (!bbio)
- return -ENOMEM;
-
- atomic_set(&bbio->error, 0);
- }
-
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, logical, *length);
read_unlock(&em_tree->lock);
@@ -2933,32 +3645,6 @@ again:
if (mirror_num > map->num_stripes)
mirror_num = 0;
- /* if our btrfs_bio struct is too small, back off and try again */
- if (rw & REQ_WRITE) {
- if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_DUP)) {
- stripes_required = map->num_stripes;
- max_errors = 1;
- } else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
- stripes_required = map->sub_stripes;
- max_errors = 1;
- }
- }
- if (rw & REQ_DISCARD) {
- if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_DUP |
- BTRFS_BLOCK_GROUP_RAID10)) {
- stripes_required = map->num_stripes;
- }
- }
- if (bbio_ret && (rw & (REQ_WRITE | REQ_DISCARD)) &&
- stripes_allocated < stripes_required) {
- stripes_allocated = map->num_stripes;
- free_extent_map(em);
- kfree(bbio);
- goto again;
- }
stripe_nr = offset;
/*
* stripe_nr counts the total number of stripes we have to stride
@@ -2974,10 +3660,7 @@ again:
if (rw & REQ_DISCARD)
*length = min_t(u64, em->len - offset, *length);
- else if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_DUP)) {
+ else if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
/* we limit the length of each bio to what fits in a stripe */
*length = min_t(u64, em->len - offset,
map->stripe_len - stripe_offset);
@@ -3053,81 +3736,55 @@ again:
}
BUG_ON(stripe_index >= map->num_stripes);
+ bbio = kzalloc(btrfs_bio_size(num_stripes), GFP_NOFS);
+ if (!bbio) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ atomic_set(&bbio->error, 0);
+
if (rw & REQ_DISCARD) {
+ int factor = 0;
+ int sub_stripes = 0;
+ u64 stripes_per_dev = 0;
+ u32 remaining_stripes = 0;
+
+ if (map->type &
+ (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) {
+ if (map->type & BTRFS_BLOCK_GROUP_RAID0)
+ sub_stripes = 1;
+ else
+ sub_stripes = map->sub_stripes;
+
+ factor = map->num_stripes / sub_stripes;
+ stripes_per_dev = div_u64_rem(stripe_nr_end -
+ stripe_nr_orig,
+ factor,
+ &remaining_stripes);
+ }
+
for (i = 0; i < num_stripes; i++) {
bbio->stripes[i].physical =
map->stripes[stripe_index].physical +
stripe_offset + stripe_nr * map->stripe_len;
bbio->stripes[i].dev = map->stripes[stripe_index].dev;
- if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
- u64 stripes;
- u32 last_stripe = 0;
- int j;
-
- div_u64_rem(stripe_nr_end - 1,
- map->num_stripes,
- &last_stripe);
-
- for (j = 0; j < map->num_stripes; j++) {
- u32 test;
-
- div_u64_rem(stripe_nr_end - 1 - j,
- map->num_stripes, &test);
- if (test == stripe_index)
- break;
- }
- stripes = stripe_nr_end - 1 - j;
- do_div(stripes, map->num_stripes);
- bbio->stripes[i].length = map->stripe_len *
- (stripes - stripe_nr + 1);
-
- if (i == 0) {
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID10)) {
+ bbio->stripes[i].length = stripes_per_dev *
+ map->stripe_len;
+ if (i / sub_stripes < remaining_stripes)
+ bbio->stripes[i].length +=
+ map->stripe_len;
+ if (i < sub_stripes)
bbio->stripes[i].length -=
stripe_offset;
- stripe_offset = 0;
- }
- if (stripe_index == last_stripe)
+ if ((i / sub_stripes + 1) %
+ sub_stripes == remaining_stripes)
bbio->stripes[i].length -=
stripe_end_offset;
- } else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
- u64 stripes;
- int j;
- int factor = map->num_stripes /
- map->sub_stripes;
- u32 last_stripe = 0;
-
- div_u64_rem(stripe_nr_end - 1,
- factor, &last_stripe);
- last_stripe *= map->sub_stripes;
-
- for (j = 0; j < factor; j++) {
- u32 test;
-
- div_u64_rem(stripe_nr_end - 1 - j,
- factor, &test);
-
- if (test ==
- stripe_index / map->sub_stripes)
- break;
- }
- stripes = stripe_nr_end - 1 - j;
- do_div(stripes, factor);
- bbio->stripes[i].length = map->stripe_len *
- (stripes - stripe_nr + 1);
-
- if (i < map->sub_stripes) {
- bbio->stripes[i].length -=
- stripe_offset;
- if (i == map->sub_stripes - 1)
- stripe_offset = 0;
- }
- if (stripe_index >= last_stripe &&
- stripe_index <= (last_stripe +
- map->sub_stripes - 1)) {
- bbio->stripes[i].length -=
- stripe_end_offset;
- }
+ if (i == sub_stripes - 1)
+ stripe_offset = 0;
} else
bbio->stripes[i].length = *length;
@@ -3149,15 +3806,22 @@ again:
stripe_index++;
}
}
- if (bbio_ret) {
- *bbio_ret = bbio;
- bbio->num_stripes = num_stripes;
- bbio->max_errors = max_errors;
- bbio->mirror_num = mirror_num;
+
+ if (rw & REQ_WRITE) {
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_DUP)) {
+ max_errors = 1;
+ }
}
+
+ *bbio_ret = bbio;
+ bbio->num_stripes = num_stripes;
+ bbio->max_errors = max_errors;
+ bbio->mirror_num = mirror_num;
out:
free_extent_map(em);
- return 0;
+ return ret;
}
int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
@@ -3258,7 +3922,7 @@ static void btrfs_end_bio(struct bio *bio, int err)
*/
if (atomic_read(&bbio->error) > bbio->max_errors) {
err = -EIO;
- } else if (err) {
+ } else {
/*
* this bio is actually up to date, we didn't
* go over the max number of errors
@@ -3562,7 +4226,7 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid)
struct btrfs_fs_devices *fs_devices;
int ret;
- mutex_lock(&uuid_mutex);
+ BUG_ON(!mutex_is_locked(&uuid_mutex));
fs_devices = root->fs_info->fs_devices->seed;
while (fs_devices) {
@@ -3600,7 +4264,6 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid)
fs_devices->seed = root->fs_info->fs_devices->seed;
root->fs_info->fs_devices->seed = fs_devices;
out:
- mutex_unlock(&uuid_mutex);
return ret;
}
@@ -3743,6 +4406,9 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
if (!path)
return -ENOMEM;
+ mutex_lock(&uuid_mutex);
+ lock_chunks(root);
+
/* first we search for all of the device items, and then we
* read in all of the chunk items. This way we can create chunk
* mappings that reference all of the devices that are afound
@@ -3793,6 +4459,9 @@ again:
}
ret = 0;
error:
+ unlock_chunks(root);
+ mutex_unlock(&uuid_mutex);
+
btrfs_free_path(path);
return ret;
}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 78f2d4d4f37..19ac95048b8 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -186,6 +186,51 @@ struct map_lookup {
#define map_lookup_size(n) (sizeof(struct map_lookup) + \
(sizeof(struct btrfs_bio_stripe) * (n)))
+/*
+ * Restriper's general type filter
+ */
+#define BTRFS_BALANCE_DATA (1ULL << 0)
+#define BTRFS_BALANCE_SYSTEM (1ULL << 1)
+#define BTRFS_BALANCE_METADATA (1ULL << 2)
+
+#define BTRFS_BALANCE_TYPE_MASK (BTRFS_BALANCE_DATA | \
+ BTRFS_BALANCE_SYSTEM | \
+ BTRFS_BALANCE_METADATA)
+
+#define BTRFS_BALANCE_FORCE (1ULL << 3)
+#define BTRFS_BALANCE_RESUME (1ULL << 4)
+
+/*
+ * Balance filters
+ */
+#define BTRFS_BALANCE_ARGS_PROFILES (1ULL << 0)
+#define BTRFS_BALANCE_ARGS_USAGE (1ULL << 1)
+#define BTRFS_BALANCE_ARGS_DEVID (1ULL << 2)
+#define BTRFS_BALANCE_ARGS_DRANGE (1ULL << 3)
+#define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4)
+
+/*
+ * Profile changing flags. When SOFT is set we won't relocate chunk if
+ * it already has the target profile (even though it may be
+ * half-filled).
+ */
+#define BTRFS_BALANCE_ARGS_CONVERT (1ULL << 8)
+#define BTRFS_BALANCE_ARGS_SOFT (1ULL << 9)
+
+struct btrfs_balance_args;
+struct btrfs_balance_progress;
+struct btrfs_balance_control {
+ struct btrfs_fs_info *fs_info;
+
+ struct btrfs_balance_args data;
+ struct btrfs_balance_args meta;
+ struct btrfs_balance_args sys;
+
+ u64 flags;
+
+ struct btrfs_balance_progress stat;
+};
+
int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
u64 end, u64 *length);
@@ -228,9 +273,12 @@ struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid,
u8 *uuid, u8 *fsid);
int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
int btrfs_init_new_device(struct btrfs_root *root, char *path);
-int btrfs_balance(struct btrfs_root *dev_root);
+int btrfs_balance(struct btrfs_balance_control *bctl,
+ struct btrfs_ioctl_balance_args *bargs);
+int btrfs_recover_balance(struct btrfs_root *tree_root);
+int btrfs_pause_balance(struct btrfs_fs_info *fs_info);
+int btrfs_cancel_balance(struct btrfs_fs_info *fs_info);
int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
-int find_free_dev_extent(struct btrfs_trans_handle *trans,
- struct btrfs_device *device, u64 num_bytes,
+int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes,
u64 *start, u64 *max_avail);
#endif
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index a76e41c04b7..3848b04e310 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -394,36 +394,36 @@ int btrfs_removexattr(struct dentry *dentry, const char *name)
XATTR_REPLACE);
}
-int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
- struct inode *inode, struct inode *dir,
- const struct qstr *qstr)
+int btrfs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+ void *fs_info)
{
- int err;
- size_t len;
- void *value;
- char *suffix;
+ const struct xattr *xattr;
+ struct btrfs_trans_handle *trans = fs_info;
char *name;
+ int err = 0;
- err = security_inode_init_security(inode, dir, qstr, &suffix, &value,
- &len);
- if (err) {
- if (err == -EOPNOTSUPP)
- return 0;
- return err;
- }
-
- name = kmalloc(XATTR_SECURITY_PREFIX_LEN + strlen(suffix) + 1,
- GFP_NOFS);
- if (!name) {
- err = -ENOMEM;
- } else {
+ for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+ name = kmalloc(XATTR_SECURITY_PREFIX_LEN +
+ strlen(xattr->name) + 1, GFP_NOFS);
+ if (!name) {
+ err = -ENOMEM;
+ break;
+ }
strcpy(name, XATTR_SECURITY_PREFIX);
- strcpy(name + XATTR_SECURITY_PREFIX_LEN, suffix);
- err = __btrfs_setxattr(trans, inode, name, value, len, 0);
+ strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name);
+ err = __btrfs_setxattr(trans, inode, name,
+ xattr->value, xattr->value_len, 0);
kfree(name);
+ if (err < 0)
+ break;
}
-
- kfree(suffix);
- kfree(value);
return err;
}
+
+int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
+ struct inode *inode, struct inode *dir,
+ const struct qstr *qstr)
+{
+ return security_inode_init_security(inode, dir, qstr,
+ &btrfs_initxattrs, trans);
+}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-21 00:16:37 +0000