summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/async-thread.c44
-rw-r--r--fs/btrfs/async-thread.h28
-rw-r--r--fs/btrfs/backref.c14
-rw-r--r--fs/btrfs/btrfs_inode.h19
-rw-r--r--fs/btrfs/ctree.c20
-rw-r--r--fs/btrfs/ctree.h4
-rw-r--r--fs/btrfs/delayed-inode.c4
-rw-r--r--fs/btrfs/disk-io.c88
-rw-r--r--fs/btrfs/extent-tree.c308
-rw-r--r--fs/btrfs/extent_io.c5
-rw-r--r--fs/btrfs/file-item.c2
-rw-r--r--fs/btrfs/file.c31
-rw-r--r--fs/btrfs/inode.c359
-rw-r--r--fs/btrfs/ioctl.c68
-rw-r--r--fs/btrfs/ordered-data.c124
-rw-r--r--fs/btrfs/ordered-data.h5
-rw-r--r--fs/btrfs/qgroup.c170
-rw-r--r--fs/btrfs/qgroup.h1
-rw-r--r--fs/btrfs/raid56.c9
-rw-r--r--fs/btrfs/reada.c3
-rw-r--r--fs/btrfs/scrub.c25
-rw-r--r--fs/btrfs/super.c51
-rw-r--r--fs/btrfs/sysfs.c2
-rw-r--r--fs/btrfs/transaction.c33
-rw-r--r--fs/btrfs/transaction.h1
-rw-r--r--fs/btrfs/tree-log.c80
-rw-r--r--fs/btrfs/tree-log.h2
-rw-r--r--fs/btrfs/ulist.h15
-rw-r--r--fs/btrfs/volumes.c64
29 files changed, 1046 insertions, 533 deletions
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 5a201d81049c..fbd76ded9a34 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -22,7 +22,6 @@
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/freezer.h>
-#include <linux/workqueue.h>
#include "async-thread.h"
#include "ctree.h"
@@ -55,8 +54,39 @@ struct btrfs_workqueue {
struct __btrfs_workqueue *high;
};
-static inline struct __btrfs_workqueue
-*__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
+static void normal_work_helper(struct btrfs_work *work);
+
+#define BTRFS_WORK_HELPER(name) \
+void btrfs_##name(struct work_struct *arg) \
+{ \
+ struct btrfs_work *work = container_of(arg, struct btrfs_work, \
+ normal_work); \
+ normal_work_helper(work); \
+}
+
+BTRFS_WORK_HELPER(worker_helper);
+BTRFS_WORK_HELPER(delalloc_helper);
+BTRFS_WORK_HELPER(flush_delalloc_helper);
+BTRFS_WORK_HELPER(cache_helper);
+BTRFS_WORK_HELPER(submit_helper);
+BTRFS_WORK_HELPER(fixup_helper);
+BTRFS_WORK_HELPER(endio_helper);
+BTRFS_WORK_HELPER(endio_meta_helper);
+BTRFS_WORK_HELPER(endio_meta_write_helper);
+BTRFS_WORK_HELPER(endio_raid56_helper);
+BTRFS_WORK_HELPER(rmw_helper);
+BTRFS_WORK_HELPER(endio_write_helper);
+BTRFS_WORK_HELPER(freespace_write_helper);
+BTRFS_WORK_HELPER(delayed_meta_helper);
+BTRFS_WORK_HELPER(readahead_helper);
+BTRFS_WORK_HELPER(qgroup_rescan_helper);
+BTRFS_WORK_HELPER(extent_refs_helper);
+BTRFS_WORK_HELPER(scrub_helper);
+BTRFS_WORK_HELPER(scrubwrc_helper);
+BTRFS_WORK_HELPER(scrubnc_helper);
+
+static struct __btrfs_workqueue *
+__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
int thresh)
{
struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
@@ -232,13 +262,11 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
spin_unlock_irqrestore(lock, flags);
}
-static void normal_work_helper(struct work_struct *arg)
+static void normal_work_helper(struct btrfs_work *work)
{
- struct btrfs_work *work;
struct __btrfs_workqueue *wq;
int need_order = 0;
- work = container_of(arg, struct btrfs_work, normal_work);
/*
* We should not touch things inside work in the following cases:
* 1) after work->func() if it has no ordered_free
@@ -262,7 +290,7 @@ static void normal_work_helper(struct work_struct *arg)
trace_btrfs_all_work_done(work);
}
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
btrfs_func_t func,
btrfs_func_t ordered_func,
btrfs_func_t ordered_free)
@@ -270,7 +298,7 @@ void btrfs_init_work(struct btrfs_work *work,
work->func = func;
work->ordered_func = ordered_func;
work->ordered_free = ordered_free;
- INIT_WORK(&work->normal_work, normal_work_helper);
+ INIT_WORK(&work->normal_work, uniq_func);
INIT_LIST_HEAD(&work->ordered_list);
work->flags = 0;
}
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 9c6b66d15fb0..e9e31c94758f 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -19,12 +19,14 @@
#ifndef __BTRFS_ASYNC_THREAD_
#define __BTRFS_ASYNC_THREAD_
+#include <linux/workqueue.h>
struct btrfs_workqueue;
/* Internal use only */
struct __btrfs_workqueue;
struct btrfs_work;
typedef void (*btrfs_func_t)(struct btrfs_work *arg);
+typedef void (*btrfs_work_func_t)(struct work_struct *arg);
struct btrfs_work {
btrfs_func_t func;
@@ -38,11 +40,35 @@ struct btrfs_work {
unsigned long flags;
};
+#define BTRFS_WORK_HELPER_PROTO(name) \
+void btrfs_##name(struct work_struct *arg)
+
+BTRFS_WORK_HELPER_PROTO(worker_helper);
+BTRFS_WORK_HELPER_PROTO(delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(cache_helper);
+BTRFS_WORK_HELPER_PROTO(submit_helper);
+BTRFS_WORK_HELPER_PROTO(fixup_helper);
+BTRFS_WORK_HELPER_PROTO(endio_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
+BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
+BTRFS_WORK_HELPER_PROTO(rmw_helper);
+BTRFS_WORK_HELPER_PROTO(endio_write_helper);
+BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
+BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
+BTRFS_WORK_HELPER_PROTO(readahead_helper);
+BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
+BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
+BTRFS_WORK_HELPER_PROTO(scrub_helper);
+BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
+BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
+
struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
int flags,
int max_active,
int thresh);
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
btrfs_func_t func,
btrfs_func_t ordered_func,
btrfs_func_t ordered_free);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index e25564bfcb46..54a201dac7f9 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -276,9 +276,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
}
if (ret > 0)
goto next;
- ret = ulist_add_merge(parents, eb->start,
- (uintptr_t)eie,
- (u64 *)&old, GFP_NOFS);
+ ret = ulist_add_merge_ptr(parents, eb->start,
+ eie, (void **)&old, GFP_NOFS);
if (ret < 0)
break;
if (!ret && extent_item_pos) {
@@ -1001,16 +1000,19 @@ again:
ret = -EIO;
goto out;
}
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
ret = find_extent_in_eb(eb, bytenr,
*extent_item_pos, &eie);
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
if (ret < 0)
goto out;
ref->inode_list = eie;
}
- ret = ulist_add_merge(refs, ref->parent,
- (uintptr_t)ref->inode_list,
- (u64 *)&eie, GFP_NOFS);
+ ret = ulist_add_merge_ptr(refs, ref->parent,
+ ref->inode_list,
+ (void **)&eie, GFP_NOFS);
if (ret < 0)
goto out;
if (!ret && extent_item_pos) {
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 4794923c410c..56b8522d5767 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -84,12 +84,6 @@ struct btrfs_inode {
*/
struct list_head delalloc_inodes;
- /*
- * list for tracking inodes that must be sent to disk before a
- * rename or truncate commit
- */
- struct list_head ordered_operations;
-
/* node for the red-black tree that links inodes in subvolume root */
struct rb_node rb_node;
@@ -240,8 +234,17 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
BTRFS_I(inode)->last_sub_trans <=
BTRFS_I(inode)->last_log_commit &&
BTRFS_I(inode)->last_sub_trans <=
- BTRFS_I(inode)->root->last_log_commit)
- return 1;
+ BTRFS_I(inode)->root->last_log_commit) {
+ /*
+ * After a ranged fsync we might have left some extent maps
+ * (that fall outside the fsync's range). So return false
+ * here if the list isn't empty, to make sure btrfs_log_inode()
+ * will be called and process those extent maps.
+ */
+ smp_mb();
+ if (list_empty(&BTRFS_I(inode)->extent_tree.modified_extents))
+ return 1;
+ }
return 0;
}
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index aeab453b8e24..44ee5d2e52a4 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -280,9 +280,9 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
WARN_ON(btrfs_header_generation(buf) > trans->transid);
if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
- ret = btrfs_inc_ref(trans, root, cow, 1, 1);
+ ret = btrfs_inc_ref(trans, root, cow, 1);
else
- ret = btrfs_inc_ref(trans, root, cow, 0, 1);
+ ret = btrfs_inc_ref(trans, root, cow, 0);
if (ret)
return ret;
@@ -1035,14 +1035,14 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
if ((owner == root->root_key.objectid ||
root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) &&
!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
- ret = btrfs_inc_ref(trans, root, buf, 1, 1);
+ ret = btrfs_inc_ref(trans, root, buf, 1);
BUG_ON(ret); /* -ENOMEM */
if (root->root_key.objectid ==
BTRFS_TREE_RELOC_OBJECTID) {
- ret = btrfs_dec_ref(trans, root, buf, 0, 1);
+ ret = btrfs_dec_ref(trans, root, buf, 0);
BUG_ON(ret); /* -ENOMEM */
- ret = btrfs_inc_ref(trans, root, cow, 1, 1);
+ ret = btrfs_inc_ref(trans, root, cow, 1);
BUG_ON(ret); /* -ENOMEM */
}
new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
@@ -1050,9 +1050,9 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
if (root->root_key.objectid ==
BTRFS_TREE_RELOC_OBJECTID)
- ret = btrfs_inc_ref(trans, root, cow, 1, 1);
+ ret = btrfs_inc_ref(trans, root, cow, 1);
else
- ret = btrfs_inc_ref(trans, root, cow, 0, 1);
+ ret = btrfs_inc_ref(trans, root, cow, 0);
BUG_ON(ret); /* -ENOMEM */
}
if (new_flags != 0) {
@@ -1069,11 +1069,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
if (root->root_key.objectid ==
BTRFS_TREE_RELOC_OBJECTID)
- ret = btrfs_inc_ref(trans, root, cow, 1, 1);
+ ret = btrfs_inc_ref(trans, root, cow, 1);
else
- ret = btrfs_inc_ref(trans, root, cow, 0, 1);
+ ret = btrfs_inc_ref(trans, root, cow, 0);
BUG_ON(ret); /* -ENOMEM */
- ret = btrfs_dec_ref(trans, root, buf, 1, 1);
+ ret = btrfs_dec_ref(trans, root, buf, 1);
BUG_ON(ret); /* -ENOMEM */
}
clean_tree_block(trans, root, buf);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index be91397f4e92..8e29b614fe93 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3326,9 +3326,9 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
u64 min_alloc_size, u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
- struct extent_buffer *buf, int full_backref, int no_quota);
+ struct extent_buffer *buf, int full_backref);
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
- struct extent_buffer *buf, int full_backref, int no_quota);
+ struct extent_buffer *buf, int full_backref);
int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 bytenr, u64 num_bytes, u64 flags,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index da775bfdebc9..a2e90f855d7d 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1395,8 +1395,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
return -ENOMEM;
async_work->delayed_root = delayed_root;
- btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root,
- NULL, NULL);
+ btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
+ btrfs_async_run_delayed_root, NULL, NULL);
async_work->nr = nr;
btrfs_queue_work(root->fs_info->delayed_workers, &async_work->work);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 61dae01788d7..d0d78dc07792 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -39,7 +39,6 @@
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
-#include "async-thread.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
@@ -60,8 +59,6 @@ static void end_workqueue_fn(struct btrfs_work *work);
static void free_fs_root(struct btrfs_root *root);
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int read_only);
-static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
- struct btrfs_root *root);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
struct btrfs_root *root);
@@ -695,35 +692,41 @@ static void end_workqueue_bio(struct bio *bio, int err)
{
struct end_io_wq *end_io_wq = bio->bi_private;
struct btrfs_fs_info *fs_info;
+ struct btrfs_workqueue *wq;
+ btrfs_work_func_t func;
fs_info = end_io_wq->info;
end_io_wq->error = err;
- btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
if (bio->bi_rw & REQ_WRITE) {
- if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
- btrfs_queue_work(fs_info->endio_meta_write_workers,
- &end_io_wq->work);
- else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
- btrfs_queue_work(fs_info->endio_freespace_worker,
- &end_io_wq->work);
- else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_work(fs_info->endio_raid56_workers,
- &end_io_wq->work);
- else
- btrfs_queue_work(fs_info->endio_write_workers,
- &end_io_wq->work);
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+ wq = fs_info->endio_meta_write_workers;
+ func = btrfs_endio_meta_write_helper;
+ } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+ wq = fs_info->endio_freespace_worker;
+ func = btrfs_freespace_write_helper;
+ } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+ wq = fs_info->endio_raid56_workers;
+ func = btrfs_endio_raid56_helper;
+ } else {
+ wq = fs_info->endio_write_workers;
+ func = btrfs_endio_write_helper;
+ }
} else {
- if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_work(fs_info->endio_raid56_workers,
- &end_io_wq->work);
- else if (end_io_wq->metadata)
- btrfs_queue_work(fs_info->endio_meta_workers,
- &end_io_wq->work);
- else
- btrfs_queue_work(fs_info->endio_workers,
- &end_io_wq->work);
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+ wq = fs_info->endio_raid56_workers;
+ func = btrfs_endio_raid56_helper;
+ } else if (end_io_wq->metadata) {
+ wq = fs_info->endio_meta_workers;
+ func = btrfs_endio_meta_helper;
+ } else {
+ wq = fs_info->endio_workers;
+ func = btrfs_endio_helper;
+ }
}
+
+ btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+ btrfs_queue_work(wq, &end_io_wq->work);
}
/*
@@ -830,7 +833,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
async->submit_bio_start = submit_bio_start;
async->submit_bio_done = submit_bio_done;
- btrfs_init_work(&async->work, run_one_async_start,
+ btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
run_one_async_done, run_one_async_free);
async->bio_flags = bio_flags;
@@ -3452,7 +3455,8 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
btrfs_set_stack_device_generation(dev_item, 0);
btrfs_set_stack_device_type(dev_item, dev->type);
btrfs_set_stack_device_id(dev_item, dev->devid);
- btrfs_set_stack_device_total_bytes(dev_item, dev->total_bytes);
+ btrfs_set_stack_device_total_bytes(dev_item,
+ dev->disk_total_bytes);
btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used);
btrfs_set_stack_device_io_align(dev_item, dev->io_align);
btrfs_set_stack_device_io_width(dev_item, dev->io_width);
@@ -3829,34 +3833,6 @@ static void btrfs_error_commit_super(struct btrfs_root *root)
btrfs_cleanup_transaction(root);
}
-static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
- struct btrfs_root *root)
-{
- struct btrfs_inode *btrfs_inode;
- struct list_head splice;
-
- INIT_LIST_HEAD(&splice);
-
- mutex_lock(&root->fs_info->ordered_operations_mutex);
- spin_lock(&root->fs_info->ordered_root_lock);
-
- list_splice_init(&t->ordered_operations, &splice);
- while (!list_empty(&splice)) {
- btrfs_inode = list_entry(splice.next, struct btrfs_inode,
- ordered_operations);
-
- list_del_init(&btrfs_inode->ordered_operations);
- spin_unlock(&root->fs_info->ordered_root_lock);
-
- btrfs_invalidate_inodes(btrfs_inode->root);
-
- spin_lock(&root->fs_info->ordered_root_lock);
- }
-
- spin_unlock(&root->fs_info->ordered_root_lock);
- mutex_unlock(&root->fs_info->ordered_operations_mutex);
-}
-
static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
{
struct btrfs_ordered_extent *ordered;
@@ -4093,8 +4069,6 @@ again:
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_root *root)
{
- btrfs_destroy_ordered_operations(cur_trans, root);
-
btrfs_destroy_delayed_refs(cur_trans, root);
cur_trans->state = TRANS_STATE_COMMIT_START;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 94ec71eda86b..caaf015d6e4b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -552,7 +552,8 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
caching_ctl->block_group = cache;
caching_ctl->progress = cache->key.objectid;
atomic_set(&caching_ctl->count, 1);
- btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
+ btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
+ caching_thread, NULL, NULL);
spin_lock(&cache->lock);
/*
@@ -2749,8 +2750,8 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
async->sync = 0;
init_completion(&async->wait);
- btrfs_init_work(&async->work, delayed_ref_async_start,
- NULL, NULL);
+ btrfs_init_work(&async->work, btrfs_extent_refs_helper,
+ delayed_ref_async_start, NULL, NULL);
btrfs_queue_work(root->fs_info->extent_workers, &async->work);
@@ -3057,7 +3058,7 @@ out:
static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
- int full_backref, int inc, int no_quota)
+ int full_backref, int inc)
{
u64 bytenr;
u64 num_bytes;
@@ -3111,7 +3112,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
key.offset -= btrfs_file_extent_offset(buf, fi);
ret = process_func(trans, root, bytenr, num_bytes,
parent, ref_root, key.objectid,
- key.offset, no_quota);
+ key.offset, 1);
if (ret)
goto fail;
} else {
@@ -3119,7 +3120,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
num_bytes = btrfs_level_size(root, level - 1);
ret = process_func(trans, root, bytenr, num_bytes,
parent, ref_root, level - 1, 0,
- no_quota);
+ 1);
if (ret)
goto fail;
}
@@ -3130,15 +3131,15 @@ fail:
}
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
- struct extent_buffer *buf, int full_backref, int no_quota)
+ struct extent_buffer *buf, int full_backref)
{
- return __btrfs_mod_ref(trans, root, buf, full_backref, 1, no_quota);
+ return __btrfs_mod_ref(trans, root, buf, full_backref, 1);
}
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
- struct extent_buffer *buf, int full_backref, int no_quota)
+ struct extent_buffer *buf, int full_backref)
{
- return __btrfs_mod_ref(trans, root, buf, full_backref, 0, no_quota);
+ return __btrfs_mod_ref(trans, root, buf, full_backref, 0);
}
static int write_one_cache_group(struct btrfs_trans_handle *trans,
@@ -3586,13 +3587,7 @@ static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
*/
static u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags)
{
- /*
- * we add in the count of missing devices because we want
- * to make sure that any RAID levels on a degraded FS
- * continue to be honored.
- */
- u64 num_devices = root->fs_info->fs_devices->rw_devices +
- root->fs_info->fs_devices->missing_devices;
+ u64 num_devices = root->fs_info->fs_devices->rw_devices;
u64 target;
u64 tmp;
@@ -7478,6 +7473,220 @@ reada:
wc->reada_slot = slot;
}
+static int account_leaf_items(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *eb)
+{
+ int nr = btrfs_header_nritems(eb);
+ int i, extent_type, ret;
+ struct btrfs_key key;
+ struct btrfs_file_extent_item *fi;
+ u64 bytenr, num_bytes;
+
+ for (i = 0; i < nr; i++) {
+ btrfs_item_key_to_cpu(eb, &key, i);
+
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ continue;
+
+ fi = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item);
+ /* filter out non qgroup-accountable extents */
+ extent_type = btrfs_file_extent_type(eb, fi);
+
+ if (extent_type == BTRFS_FILE_EXTENT_INLINE)
+ continue;
+
+ bytenr = btrfs_file_extent_disk_bytenr(eb, fi);
+ if (!bytenr)
+ continue;
+
+ num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+
+ ret = btrfs_qgroup_record_ref(trans, root->fs_info,
+ root->objectid,
+ bytenr, num_bytes,
+ BTRFS_QGROUP_OPER_SUB_SUBTREE, 0);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+/*
+ * Walk up the tree from the bottom, freeing leaves and any interior
+ * nodes which have had all slots visited. If a node (leaf or
+ * interior) is freed, the node above it will have it's slot
+ * incremented. The root node will never be freed.
+ *
+ * At the end of this function, we should have a path which has all
+ * slots incremented to the next position for a search. If we need to
+ * read a new node it will be NULL and the node above it will have the
+ * correct slot selected for a later read.
+ *
+ * If we increment the root nodes slot counter past the number of
+ * elements, 1 is returned to signal completion of the search.
+ */
+static int adjust_slots_upwards(struct btrfs_root *root,
+ struct btrfs_path *path, int root_level)
+{
+ int level = 0;
+ int nr, slot;
+ struct extent_buffer *eb;
+
+ if (root_level == 0)
+ return 1;
+
+ while (level <= root_level) {
+ eb = path->nodes[level];
+ nr = btrfs_header_nritems(eb);
+ path->slots[level]++;
+ slot = path->slots[level];
+ if (slot >= nr || level == 0) {
+ /*
+ * Don't free the root - we will detect this
+ * condition after our loop and return a
+ * positive value for caller to stop walking the tree.
+ */
+ if (level != root_level) {
+ btrfs_tree_unlock_rw(eb, path->locks[level]);
+ path->locks[level] = 0;
+
+ free_extent_buffer(eb);
+ path->nodes[level] = NULL;
+ path->slots[level] = 0;
+ }
+ } else {
+ /*
+ * We have a valid slot to walk back down
+ * from. Stop here so caller can process these
+ * new nodes.
+ */
+ break;
+ }
+
+ level++;
+ }
+
+ eb = path->nodes[root_level];
+ if (path->slots[root_level] >= btrfs_header_nritems(eb))
+ return 1;
+
+ return 0;
+}
+
+/*
+ * root_eb is the subtree root and is locked before this function is called.
+ */
+static int account_shared_subtree(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *root_eb,
+ u64 root_gen,
+ int root_level)
+{
+ int ret = 0;
+ int level;
+ struct extent_buffer *eb = root_eb;
+ struct btrfs_path *path = NULL;
+
+ BUG_ON(root_level < 0 || root_level > BTRFS_MAX_LEVEL);
+ BUG_ON(root_eb == NULL);
+
+ if (!root->fs_info->quota_enabled)
+ return 0;
+
+ if (!extent_buffer_uptodate(root_eb)) {
+ ret = btrfs_read_buffer(root_eb, root_gen);
+ if (ret)
+ goto out;
+ }
+
+ if (root_level == 0) {
+ ret = account_leaf_items(trans, root, root_eb);
+ goto out;
+ }
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
+ /*
+ * Walk down the tree. Missing extent blocks are filled in as
+ * we go. Metadata is accounted every time we read a new
+ * extent block.
+ *
+ * When we reach a leaf, we account for file extent items in it,
+ * walk back up the tree (adjusting slot pointers as we go)
+ * and restart the search process.
+ */
+ extent_buffer_get(root_eb); /* For path */
+ path->nodes[root_level] = root_eb;
+ path->slots[root_level] = 0;
+ path->locks[root_level] = 0; /* so release_path doesn't try to unlock */
+walk_down:
+ level = root_level;
+ while (level >= 0) {
+ if (path->nodes[level] == NULL) {
+ int child_bsize = root->nodesize;
+ int parent_slot;
+ u64 child_gen;
+ u64 child_bytenr;
+
+ /* We need to get child blockptr/gen from
+ * parent before we can read it. */
+ eb = path->nodes[level + 1];
+ parent_slot = path->slots[level + 1];
+ child_bytenr = btrfs_node_blockptr(eb, parent_slot);
+ child_gen = btrfs_node_ptr_generation(eb, parent_slot);
+
+ eb = read_tree_block(root, child_bytenr, child_bsize,
+ child_gen);
+ if (!eb || !extent_buffer_uptodate(eb)) {
+ ret = -EIO;
+ goto out;
+ }
+
+ path->nodes[level] = eb;
+ path->slots[level] = 0;
+
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+
+ ret = btrfs_qgroup_record_ref(trans, root->fs_info,
+ root->objectid,
+ child_bytenr,
+ child_bsize,
+ BTRFS_QGROUP_OPER_SUB_SUBTREE,
+ 0);
+ if (ret)
+ goto out;
+
+ }
+
+ if (level == 0) {
+ ret = account_leaf_items(trans, root, path->nodes[level]);
+ if (ret)
+ goto out;
+
+ /* Nonzero return here means we completed our search */
+ ret = adjust_slots_upwards(root, path, root_level);
+ if (ret)
+ break;
+
+ /* Restart search with new slots */
+ goto walk_down;
+ }
+
+ level--;
+ }
+
+ ret = 0;
+out:
+ btrfs_free_path(path);
+
+ return ret;
+}
+
/*
* helper to process tree block while walking down the tree.
*
@@ -7532,9 +7741,9 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
/* wc->stage == UPDATE_BACKREF */
if (!(wc->flags[level] & flag)) {
BUG_ON(!path->locks[level]);
- ret = btrfs_inc_ref(trans, root, eb, 1, wc->for_reloc);
+ ret = btrfs_inc_ref(trans, root, eb, 1);
BUG_ON(ret); /* -ENOMEM */
- ret = btrfs_dec_ref(trans, root, eb, 0, wc->for_reloc);
+ ret = btrfs_dec_ref(trans, root, eb, 0);
BUG_ON(ret); /* -ENOMEM */
ret = btrfs_set_disk_extent_flags(trans, root, eb->start,
eb->len, flag,
@@ -7581,6 +7790,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
int level = wc->level;
int reada = 0;
int ret = 0;
+ bool need_account = false;
generation = btrfs_node_ptr_generation(path->nodes[level],
path->slots[level]);
@@ -7626,6 +7836,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
if (wc->stage == DROP_REFERENCE) {
if (wc->refs[level - 1] > 1) {
+ need_account = true;
if (level == 1 &&
(wc->flags[0] & BTRFS_BLOCK_FLAG_FULL_BACKREF))
goto skip;
@@ -7689,6 +7900,16 @@ skip:
parent = 0;
}
+ if (need_account) {
+ ret = account_shared_subtree(trans, root, next,
+ generation, level - 1);
+ if (ret) {
+ printk_ratelimited(KERN_ERR "BTRFS: %s Error "
+ "%d accounting shared subtree. Quota "
+ "is out of sync, rescan required.\n",
+ root->fs_info->sb->s_id, ret);
+ }
+ }
ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent,
root->root_key.objectid, level - 1, 0, 0);
BUG_ON(ret); /* -ENOMEM */
@@ -7769,12 +7990,17 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
if (wc->refs[level] == 1) {
if (level == 0) {
if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
- ret = btrfs_dec_ref(trans, root, eb, 1,
- wc->for_reloc);
+ ret = btrfs_dec_ref(trans, root, eb, 1);
else
- ret = btrfs_dec_ref(trans, root, eb, 0,
- wc->for_reloc);
+ ret = btrfs_dec_ref(trans, root, eb, 0);
BUG_ON(ret); /* -ENOMEM */
+ ret = account_leaf_items(trans, root, eb);
+ if (ret) {
+ printk_ratelimited(KERN_ERR "BTRFS: %s Error "
+ "%d accounting leaf items. Quota "
+ "is out of sync, rescan required.\n",
+ root->fs_info->sb->s_id, ret);
+ }
}
/* make block locked assertion in clean_tree_block happy */
if (!path->locks[level] &&
@@ -7900,6 +8126,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
int level;
bool root_dropped = false;
+ btrfs_debug(root->fs_info, "Drop subvolume %llu", root->objectid);
+
path = btrfs_alloc_path();
if (!path) {
err = -ENOMEM;
@@ -8025,6 +8253,24 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
goto out_end_trans;
}
+ /*
+ * Qgroup update accounting is run from
+ * delayed ref handling. This usually works
+ * out because delayed refs are normally the
+ * only way qgroup updates are added. However,
+ * we may have added updates during our tree
+ * walk so run qgroups here to make sure we
+ * don't lose any updates.
+ */
+ ret = btrfs_delayed_qgroup_accounting(trans,
+ root->fs_info);
+ if (ret)
+ printk_ratelimited(KERN_ERR "BTRFS: Failure %d "
+ "running qgroup updates "
+ "during snapshot delete. "
+ "Quota is out of sync, "
+ "rescan required.\n", ret);
+
btrfs_end_transaction_throttle(trans, tree_root);
if (!for_reloc && btrfs_need_cleaner_sleep(root)) {
pr_debug("BTRFS: drop snapshot early exit\n");
@@ -8078,6 +8324,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
}
root_dropped = true;
out_end_trans:
+ ret = btrfs_delayed_qgroup_accounting(trans, tree_root->fs_info);
+ if (ret)
+ printk_ratelimited(KERN_ERR "BTRFS: Failure %d "
+ "running qgroup updates "
+ "during snapshot delete. "
+ "Quota is out of sync, "
+ "rescan required.\n", ret);
+
btrfs_end_transaction_throttle(trans, tree_root);
out_free:
kfree(wc);
@@ -8181,13 +8435,7 @@ static u64 update_block_group_flags(struct btrfs_root *root, u64 flags)
if (stripped)
return extended_to_chunk(stripped);
- /*
- * we add in the count of missing devices because we want
- * to make sure that any RAID levels on a degraded FS
- * continue to be honored.
- */
- num_devices = root->fs_info->fs_devices->rw_devices +
- root->fs_info->fs_devices->missing_devices;
+ num_devices = root->fs_info->fs_devices->rw_devices;
stripped = BTRFS_BLOCK_GROUP_RAID0 |
BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6 |
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3e11aab9f391..af0359dcf337 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2532,6 +2532,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
test_bit(BIO_UPTODATE, &bio->bi_flags);
if (err)
uptodate = 0;
+ offset += len;
continue;
}
}
@@ -4207,8 +4208,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return -ENOMEM;
path->leave_spinning = 1;
- start = ALIGN(start, BTRFS_I(inode)->root->sectorsize);
- len = ALIGN(len, BTRFS_I(inode)->root->sectorsize);
+ start = round_down(start, BTRFS_I(inode)->root->sectorsize);
+ len = round_up(max, BTRFS_I(inode)->root->sectorsize) - start;
/*
* lookup the last file extent. We're not using i_size here
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index f46cfe45d686..54c84daec9b5 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -756,7 +756,7 @@ again:
found_next = 1;
if (ret != 0)
goto insert;
- slot = 0;
+ slot = path->slots[0];
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 1f2b99cb55ea..ff1cc0399b9a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1838,6 +1838,8 @@ out:
int btrfs_release_file(struct inode *inode, struct file *filp)
{
+ if (filp->private_data)
+ btrfs_ioctl_trans_end(filp);
/*
* ordered_data_close is set by settattr when we are about to truncate
* a file from a non-zero size to a zero size. This tries to
@@ -1845,26 +1847,8 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
* application were using truncate to replace a file in place.
*/
if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
- &BTRFS_I(inode)->runtime_flags)) {
- struct btrfs_trans_handle *trans;
- struct btrfs_root *root = BTRFS_I(inode)->root;
-
- /*
- * We need to block on a committing transaction to keep us from
- * throwing a ordered operation on to the list and causing
- * something like sync to deadlock trying to flush out this
- * inode.
- */
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
- btrfs_add_ordered_operation(trans, BTRFS_I(inode)->root, inode);
- btrfs_end_transaction(trans, root);
- if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
+ &BTRFS_I(inode)->runtime_flags))
filemap_flush(inode->i_mapping);
- }
- if (filp->private_data)
- btrfs_ioctl_trans_end(filp);
return 0;
}
@@ -1982,7 +1966,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
btrfs_init_log_ctx(&ctx);
- ret = btrfs_log_dentry_safe(trans, root, dentry, &ctx);
+ ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx);
if (ret < 0) {
/* Fallthrough and commit/free transaction. */
ret = 1;
@@ -2112,10 +2096,9 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
goto out;
}
- if (hole_mergeable(inode, leaf, path->slots[0]+1, offset, end)) {
+ if (hole_mergeable(inode, leaf, path->slots[0], offset, end)) {
u64 num_bytes;
- path->slots[0]++;
key.offset = offset;
btrfs_set_item_key_safe(root, path, &key);
fi = btrfs_item_ptr(leaf, path->slots[0],
@@ -2240,7 +2223,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
goto out_only_mutex;
}
- lockstart = round_up(offset , BTRFS_I(inode)->root->sectorsize);
+ lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
lockend = round_down(offset + len,
BTRFS_I(inode)->root->sectorsize) - 1;
same_page = ((offset >> PAGE_CACHE_SHIFT) ==
@@ -2301,7 +2284,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
tail_start + tail_len, 0, 1);
if (ret)
goto out_only_mutex;
- }
+ }
}
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3183742d6f0d..016c403bfe7e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -709,6 +709,18 @@ retry:
unlock_extent(io_tree, async_extent->start,
async_extent->start +
async_extent->ram_size - 1);
+
+ /*
+ * we need to redirty the pages if we decide to
+ * fallback to uncompressed IO, otherwise we
+ * will not submit these pages down to lower
+ * layers.
+ */
+ extent_range_redirty_for_io(inode,
+ async_extent->start,
+ async_extent->start +
+ async_extent->ram_size - 1);
+
goto retry;
}
goto out_free;
@@ -766,8 +778,12 @@ retry:
ins.offset,
BTRFS_ORDERED_COMPRESSED,
async_extent->compress_type);
- if (ret)
+ if (ret) {
+ btrfs_drop_extent_cache(inode, async_extent->start,
+ async_extent->start +
+ async_extent->ram_size - 1, 0);
goto out_free_reserve;
+ }
/*
* clear dirty, set writeback and unlock the pages.
@@ -959,14 +975,14 @@ static noinline int cow_file_range(struct inode *inode,
ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
ram_size, cur_alloc_size, 0);
if (ret)
- goto out_reserve;
+ goto out_drop_extent_cache;
if (root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID) {
ret = btrfs_reloc_clone_csums(inode, start,
cur_alloc_size);
if (ret)
- goto out_reserve;
+ goto out_drop_extent_cache;
}
if (disk_num_bytes < cur_alloc_size)
@@ -994,6 +1010,8 @@ static noinline int cow_file_range(struct inode *inode,
out:
return ret;
+out_drop_extent_cache:
+ btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
out_reserve:
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_unlock:
@@ -1084,8 +1102,10 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
async_cow->end = cur_end;
INIT_LIST_HEAD(&async_cow->extents);
- btrfs_init_work(&async_cow->work, async_cow_start,
- async_cow_submit, async_cow_free);
+ btrfs_init_work(&async_cow->work,
+ btrfs_delalloc_helper,
+ async_cow_start, async_cow_submit,
+ async_cow_free);
nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
PAGE_CACHE_SHIFT;
@@ -1869,7 +1889,8 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
SetPageChecked(page);
page_cache_get(page);
- btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
+ btrfs_init_work(&fixup->work, btrfs_fixup_helper,
+ btrfs_writepage_fixup_worker, NULL, NULL);
fixup->page = page;
btrfs_queue_work(root->fs_info->fixup_workers, &fixup->work);
return -EBUSY;
@@ -2810,7 +2831,8 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
struct inode *inode = page->mapping->host;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_ordered_extent *ordered_extent = NULL;
- struct btrfs_workqueue *workers;
+ struct btrfs_workqueue *wq;
+ btrfs_work_func_t func;
trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
@@ -2819,13 +2841,17 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
end - start + 1, uptodate))
return 0;
- btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
+ if (btrfs_is_free_space_inode(inode)) {
+ wq = root->fs_info->endio_freespace_worker;
+ func = btrfs_freespace_write_helper;
+ } else {
+ wq = root->fs_info->endio_write_workers;
+ func = btrfs_endio_write_helper;
+ }
- if (btrfs_is_free_space_inode(inode))
- workers = root->fs_info->endio_freespace_worker;
- else
- workers = root->fs_info->endio_write_workers;
- btrfs_queue_work(workers, &ordered_extent->work);
+ btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
+ NULL);
+ btrfs_queue_work(wq, &ordered_extent->work);
return 0;
}
@@ -4222,7 +4248,8 @@ out:
btrfs_abort_transaction(trans, root, ret);
}
error:
- if (last_size != (u64)-1)
+ if (last_size != (u64)-1 &&
+ root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
btrfs_ordered_update_i_size(inode, last_size, NULL);
btrfs_free_path(path);
return err;
@@ -4662,6 +4689,11 @@ static void evict_inode_truncate_pages(struct inode *inode)
clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
remove_extent_mapping(map_tree, em);
free_extent_map(em);
+ if (need_resched()) {
+ write_unlock(&map_tree->lock);
+ cond_resched();
+ write_lock(&map_tree->lock);
+ }
}
write_unlock(&map_tree->lock);
@@ -4684,6 +4716,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
&cached_state, GFP_NOFS);
free_extent_state(state);
+ cond_resched();
spin_lock(&io_tree->lock);
}
spin_unlock(&io_tree->lock);
@@ -5169,6 +5202,42 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
iput(inode);
inode = ERR_PTR(ret);
}
+ /*
+ * If orphan cleanup did remove any orphans, it means the tree
+ * was modified and therefore the commit root is not the same as
+ * the current root anymore. This is a problem, because send
+ * uses the commit root and therefore can see inode items that
+ * don't exist in the current root anymore, and for example make
+ * calls to btrfs_iget, which will do tree lookups based on the
+ * current root and not on the commit root. Those lookups will
+ * fail, returning a -ESTALE error, and making send fail with
+ * that error. So make sure a send does not see any orphans we
+ * have just removed, and that it will see the same inodes
+ * regardless of whether a transaction commit happened before
+ * it started (meaning that the commit root will be the same as
+ * the current root) or not.
+ */
+ if (sub_root->node != sub_root->commit_root) {
+ u64 sub_flags = btrfs_root_flags(&sub_root->root_item);
+
+ if (sub_flags & BTRFS_ROOT_SUBVOL_RDONLY) {
+ struct extent_buffer *eb;
+
+ /*
+ * Assert we can't have races between dentry
+ * lookup called through the snapshot creation
+ * ioctl and the VFS.
+ */
+ ASSERT(mutex_is_locked(&dir->i_mutex));
+
+ down_write(&root->fs_info->commit_root_sem);
+ eb = sub_root->commit_root;
+ sub_root->commit_root =
+ btrfs_root_node(sub_root);
+ up_write(&root->fs_info->commit_root_sem);
+ free_extent_buffer(eb);
+ }
+ }
}
return inode;
@@ -5565,6 +5634,17 @@ int btrfs_set_inode_index(struct inode *dir, u64 *index)
return ret;
}
+static int btrfs_insert_inode_locked(struct inode *inode)
+{
+ struct btrfs_iget_args args;
+ args.location = &BTRFS_I(inode)->location;
+ args.root = BTRFS_I(inode)->root;
+
+ return insert_inode_locked4(inode,
+ btrfs_inode_hash(inode->i_ino, BTRFS_I(inode)->root),
+ btrfs_find_actor, &args);
+}
+
static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *dir,
@@ -5594,6 +5674,13 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
}
/*
+ * O_TMPFILE, set link count to 0, so that after this point,
+ * we fill in an inode item with the correct link count.
+ */
+ if (!name)
+ set_nlink(inode, 0);
+
+ /*
* we have to initialize this early, so we can reclaim the inode
* number if we fail afterwards in this function.
*/
@@ -5650,10 +5737,19 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
sizes[1] = name_len + sizeof(*ref);
}
+ location = &BTRFS_I(inode)->location;
+ location->objectid = objectid;
+ location->offset = 0;
+ btrfs_set_key_type(location, BTRFS_INODE_ITEM_KEY);
+
+ ret = btrfs_insert_inode_locked(inode);
+ if (ret < 0)
+ goto fail;
+
path->leave_spinning = 1;
ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
if (ret != 0)
- goto fail;
+ goto fail_unlock;
inode_init_owner(inode, dir, mode);
inode_set_bytes(inode, 0);
@@ -5676,11 +5772,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
btrfs_mark_buffer_dirty(path->nodes[0]);
btrfs_free_path(path);
- location = &BTRFS_I(inode)->location;
- location->objectid = objectid;
- location->offset = 0;
- btrfs_set_key_type(location, BTRFS_INODE_ITEM_KEY);
-
btrfs_inherit_iflags(inode, dir);
if (S_ISREG(mode)) {
@@ -5691,7 +5782,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
BTRFS_INODE_NODATASUM;
}
- btrfs_insert_inode_hash(inode);
inode_tree_add(inode);
trace_btrfs_inode_new(inode);
@@ -5706,6 +5796,9 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
btrfs_ino(inode), root->root_key.objectid, ret);
return inode;
+
+fail_unlock:
+ unlock_new_inode(inode);
fail:
if (dir && name)
BTRFS_I(dir)->index_cnt--;
@@ -5840,28 +5933,28 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
- err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
- if (err) {
- drop_inode = 1;
- 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);
+ init_special_inode(inode, inode->i_mode, rdev);
+
+ err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
- drop_inode = 1;
- else {
- init_special_inode(inode, inode->i_mode, rdev);
+ goto out_unlock_inode;
+
+ err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
+ if (err) {
+ goto out_unlock_inode;
+ } else {
btrfs_update_inode(trans, root, inode);
+ unlock_new_inode(inode);
d_instantiate(dentry, inode);
}
+
out_unlock:
btrfs_end_transaction(trans, root);
btrfs_balance_delayed_items(root);
@@ -5871,6 +5964,12 @@ out_unlock:
iput(inode);
}
return err;
+
+out_unlock_inode:
+ drop_inode = 1;
+ unlock_new_inode(inode);
+ goto out_unlock;
+
}
static int btrfs_create(struct inode *dir, struct dentry *dentry,
@@ -5905,15 +6004,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
drop_inode_on_err = 1;
-
- err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
- if (err)
- goto out_unlock;
-
- err = btrfs_update_inode(trans, root, inode);
- if (err)
- goto out_unlock;
-
/*
* If the active LSM wants to access the inode during
* d_instantiate it needs these. Smack checks to see
@@ -5922,14 +6012,23 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
*/
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
+ inode->i_mapping->a_ops = &btrfs_aops;
+ inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
+
+ err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
+ if (err)
+ goto out_unlock_inode;
+
+ err = btrfs_update_inode(trans, root, inode);
+ if (err)
+ goto out_unlock_inode;
err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
if (err)
- goto out_unlock;
+ goto out_unlock_inode;
- inode->i_mapping->a_ops = &btrfs_aops;
- inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+ unlock_new_inode(inode);
d_instantiate(dentry, inode);
out_unlock:
@@ -5941,6 +6040,11 @@ out_unlock:
btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
return err;
+
+out_unlock_inode:
+ unlock_new_inode(inode);
+ goto out_unlock;
+
}
static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
@@ -6048,25 +6152,30 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
}
drop_on_err = 1;
+ /* these must be set before we unlock the inode */
+ inode->i_op = &btrfs_dir_inode_operations;
+ inode->i_fop = &btrfs_dir_file_operations;
err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
- goto out_fail;
-
- inode->i_op = &btrfs_dir_inode_operations;
- inode->i_fop = &btrfs_dir_file_operations;
+ goto out_fail_inode;
btrfs_i_size_write(inode, 0);
err = btrfs_update_inode(trans, root, inode);
if (err)
- goto out_fail;
+ goto out_fail_inode;
err = btrfs_add_link(trans, dir, inode, dentry->d_name.name,
dentry->d_name.len, 0, index);
if (err)
- goto out_fail;
+ goto out_fail_inode;
d_instantiate(dentry, inode);
+ /*
+ * mkdir is special. We're unlocking after we call d_instantiate
+ * to avoid a race with nfsd calling d_instantiate.
+ */
+ unlock_new_inode(inode);
drop_on_err = 0;
out_fail:
@@ -6076,6 +6185,10 @@ out_fail:
btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
return err;
+
+out_fail_inode:
+ unlock_new_inode(inode);
+ goto out_fail;
}
/* helper for btfs_get_extent. Given an existing extent in the tree,
@@ -6085,14 +6198,14 @@ out_fail:
static int merge_extent_mapping(struct extent_map_tree *em_tree,
struct extent_map *existing,
struct extent_map *em,
- u64 map_start, u64 map_len)
+ u64 map_start)
{
u64 start_diff;
BUG_ON(map_start < em->start || map_start >= extent_map_end(em));
start_diff = map_start - em->start;
em->start = map_start;
- em->len = map_len;
+ em->len = existing->start - em->start;
if (em->block_start < EXTENT_MAP_LAST_BYTE &&
!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) {
em->block_start += start_diff;
@@ -6263,6 +6376,8 @@ next:
goto not_found;
if (start + len <= found_key.offset)
goto not_found;
+ if (start > found_key.offset)
+ goto next;
em->start = start;
em->orig_start = start;
em->len = found_key.offset - start;
@@ -6378,8 +6493,7 @@ insert:
em->len);
if (existing) {
err = merge_extent_mapping(em_tree, existing,
- em, start,
- root->sectorsize);
+ em, start);
free_extent_map(existing);
if (err) {
free_extent_map(em);
@@ -7146,7 +7260,8 @@ again:
if (!ret)
goto out_test;
- btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL);
+ btrfs_init_work(&ordered->work, btrfs_endio_write_helper,
+ finish_ordered_fn, NULL, NULL);
btrfs_queue_work(root->fs_info->endio_write_workers,
&ordered->work);
out_test:
@@ -7294,10 +7409,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
&map_length, NULL, 0);
- if (ret) {
- bio_put(orig_bio);
+ if (ret)
return -EIO;
- }
if (map_length >= orig_bio->bi_iter.bi_size) {
bio = orig_bio;
@@ -7314,6 +7427,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
if (!bio)
return -ENOMEM;
+
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
atomic_inc(&dip->pending_bios);
@@ -7522,7 +7636,8 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
count = iov_iter_count(iter);
if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
&BTRFS_I(inode)->runtime_flags))
- filemap_fdatawrite_range(inode->i_mapping, offset, count);
+ filemap_fdatawrite_range(inode->i_mapping, offset,
+ offset + count - 1);
if (rw & WRITE) {
/*
@@ -7939,27 +8054,6 @@ static int btrfs_truncate(struct inode *inode)
BUG_ON(ret);
/*
- * setattr is responsible for setting the ordered_data_close flag,
- * but that is only tested during the last file release. That
- * could happen well after the next commit, leaving a great big
- * window where new writes may get lost if someone chooses to write
- * to this file after truncating to zero
- *
- * The inode doesn't have any dirty data here, and so if we commit
- * this is a noop. If someone immediately starts writing to the inode
- * it is very likely we'll catch some of their writes in this
- * transaction, and the commit will find this file on the ordered
- * data list with good things to send down.
- *
- * This is a best effort solution, there is still a window where
- * using truncate to replace the contents of the file will
- * end up with a zero length file after a crash.
- */
- if (inode->i_size == 0 && test_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
- &BTRFS_I(inode)->runtime_flags))
- btrfs_add_ordered_operation(trans, root, inode);
-
- /*
* So if we truncate and then write and fsync we normally would just
* write the extents that changed, which is a problem if we need to
* first truncate that entire inode. So set this flag so we write out
@@ -8050,6 +8144,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
set_nlink(inode, 1);
btrfs_i_size_write(inode, 0);
+ unlock_new_inode(inode);
err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
if (err)
@@ -8106,7 +8201,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
mutex_init(&ei->delalloc_mutex);
btrfs_ordered_inode_tree_init(&ei->ordered_tree);
INIT_LIST_HEAD(&ei->delalloc_inodes);
- INIT_LIST_HEAD(&ei->ordered_operations);
RB_CLEAR_NODE(&ei->rb_node);
return inode;
@@ -8146,17 +8240,6 @@ void btrfs_destroy_inode(struct inode *inode)
if (!root)
goto free;
- /*
- * Make sure we're properly removed from the ordered operation
- * lists.
- */
- smp_mb();
- if (!list_empty(&BTRFS_I(inode)->ordered_operations)) {
- spin_lock(&root->fs_info->ordered_root_lock);
- list_del_init(&BTRFS_I(inode)->ordered_operations);
- spin_unlock(&root->fs_info->ordered_root_lock);
- }
-
if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
&BTRFS_I(inode)->runtime_flags)) {
btrfs_info(root->fs_info, "inode %llu still on the orphan list",
@@ -8338,12 +8421,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
ret = 0;
/*
- * we're using rename to replace one file with another.
- * and the replacement file is large. Start IO on it now so
- * we don't add too much work to the end of the transaction
+ * we're using rename to replace one file with another. Start IO on it
+ * now so we don't add too much work to the end of the transaction
*/
- if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size &&
- old_inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
+ if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size)
filemap_flush(old_inode->i_mapping);
/* close the racy window with snapshot create/destroy ioctl */
@@ -8391,12 +8472,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
*/
btrfs_pin_log_trans(root);
}
- /*
- * make sure the inode gets flushed if it is replacing
- * something.
- */
- if (new_inode && new_inode->i_size && S_ISREG(old_inode->i_mode))
- btrfs_add_ordered_operation(trans, root, old_inode);
inode_inc_iversion(old_dir);
inode_inc_iversion(new_dir);
@@ -8524,7 +8599,9 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
work->inode = inode;
work->wait = wait;
work->delay_iput = delay_iput;
- btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
+ WARN_ON_ONCE(!inode);
+ btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
+ btrfs_run_delalloc_work, NULL, NULL);
return work;
}
@@ -8728,12 +8805,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
goto out_unlock;
}
- err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
- if (err) {
- drop_inode = 1;
- goto out_unlock;
- }
-
/*
* If the active LSM wants to access the inode during
* d_instantiate it needs these. Smack checks to see
@@ -8742,23 +8813,22 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
*/
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
+ inode->i_mapping->a_ops = &btrfs_aops;
+ inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
+ BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+
+ err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
+ if (err)
+ goto out_unlock_inode;
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;
- BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
- }
- if (drop_inode)
- goto out_unlock;
+ goto out_unlock_inode;
path = btrfs_alloc_path();
if (!path) {
err = -ENOMEM;
- drop_inode = 1;
- goto out_unlock;
+ goto out_unlock_inode;
}
key.objectid = btrfs_ino(inode);
key.offset = 0;
@@ -8767,9 +8837,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
err = btrfs_insert_empty_item(trans, root, path, &key,
datasize);
if (err) {
- drop_inode = 1;
btrfs_free_path(path);
- goto out_unlock;
+ goto out_unlock_inode;
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -8793,12 +8862,15 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
inode_set_bytes(inode, name_len);
btrfs_i_size_write(inode, name_len);
err = btrfs_update_inode(trans, root, inode);
- if (err)
+ if (err) {
drop_inode = 1;
+ goto out_unlock_inode;
+ }
+
+ unlock_new_inode(inode);
+ d_instantiate(dentry, inode);
out_unlock:
- if (!err)
- d_instantiate(dentry, inode);
btrfs_end_transaction(trans, root);
if (drop_inode) {
inode_dec_link_count(inode);
@@ -8806,6 +8878,11 @@ out_unlock:
}
btrfs_btree_balance_dirty(root);
return err;
+
+out_unlock_inode:
+ drop_inode = 1;
+ unlock_new_inode(inode);
+ goto out_unlock;
}
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -8989,14 +9066,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out;
}
- ret = btrfs_init_inode_security(trans, inode, dir, NULL);
- if (ret)
- goto out;
-
- ret = btrfs_update_inode(trans, root, inode);
- if (ret)
- goto out;
-
inode->i_fop = &btrfs_file_operations;
inode->i_op = &btrfs_file_inode_operations;
@@ -9004,10 +9073,26 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+ ret = btrfs_init_inode_security(trans, inode, dir, NULL);
+ if (ret)
+ goto out_inode;
+
+ ret = btrfs_update_inode(trans, root, inode);
+ if (ret)
+ goto out_inode;
ret = btrfs_orphan_add(trans, inode);
if (ret)
- goto out;
+ goto out_inode;
+ /*
+ * We set number of links to 0 in btrfs_new_inode(), and here we set
+ * it to 1 because d_tmpfile() will issue a warning if the count is 0,
+ * through:
+ *
+ * d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
+ */
+ set_nlink(inode, 1);
+ unlock_new_inode(inode);
d_tmpfile(dentry, inode);
mark_inode_dirty(inode);
@@ -9017,8 +9102,12 @@ out:
iput(inode);
btrfs_balance_delayed_items(root);
btrfs_btree_balance_dirty(root);
-
return ret;
+
+out_inode:
+ unlock_new_inode(inode);
+ goto out;
+
}
static const struct inode_operations btrfs_dir_inode_operations = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 47aceb494d1d..8a8e29878c34 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -711,39 +711,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
if (ret)
goto fail;
- ret = btrfs_orphan_cleanup(pending_snapshot->snap);
- if (ret)
- goto fail;
-
- /*
- * If orphan cleanup did remove any orphans, it means the tree was
- * modified and therefore the commit root is not the same as the
- * current root anymore. This is a problem, because send uses the
- * commit root and therefore can see inode items that don't exist
- * in the current root anymore, and for example make calls to
- * btrfs_iget, which will do tree lookups based on the current root
- * and not on the commit root. Those lookups will fail, returning a
- * -ESTALE error, and making send fail with that error. So make sure
- * a send does not see any orphans we have just removed, and that it
- * will see the same inodes regardless of whether a transaction
- * commit happened before it started (meaning that the commit root
- * will be the same as the current root) or not.
- */
- if (readonly && pending_snapshot->snap->node !=
- pending_snapshot->snap->commit_root) {
- trans = btrfs_join_transaction(pending_snapshot->snap);
- if (IS_ERR(trans) && PTR_ERR(trans) != -ENOENT) {
- ret = PTR_ERR(trans);
- goto fail;
- }
- if (!IS_ERR(trans)) {
- ret = btrfs_commit_transaction(trans,
- pending_snapshot->snap);
- if (ret)
- goto fail;
- }
- }
-
inode = btrfs_lookup_dentry(dentry->d_parent->d_inode, dentry);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
@@ -1052,8 +1019,10 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em)
return false;
next = defrag_lookup_extent(inode, em->start + em->len);
- if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE ||
- (em->block_start + em->block_len == next->block_start))
+ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
+ ret = false;
+ else if ((em->block_start + em->block_len == next->block_start) &&
+ (em->block_len > 128 * 1024 && next->block_len > 128 * 1024))
ret = false;
free_extent_map(next);
@@ -1088,7 +1057,6 @@ static int should_defrag_range(struct inode *inode, u64 start, int thresh,
}
next_mergeable = defrag_check_next_extent(inode, em);
-
/*
* we hit a real extent, if it is big or the next extent is not a
* real extent, don't bother defragging it
@@ -1735,7 +1703,7 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
~(BTRFS_SUBVOL_CREATE_ASYNC | BTRFS_SUBVOL_RDONLY |
BTRFS_SUBVOL_QGROUP_INHERIT)) {
ret = -EOPNOTSUPP;
- goto out;
+ goto free_args;
}
if (vol_args->flags & BTRFS_SUBVOL_CREATE_ASYNC)
@@ -1745,27 +1713,31 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) {
if (vol_args->size > PAGE_CACHE_SIZE) {
ret = -EINVAL;
- goto out;
+ goto free_args;
}
inherit = memdup_user(vol_args->qgroup_inherit, vol_args->size);
if (IS_ERR(inherit)) {
ret = PTR_ERR(inherit);
- goto out;
+ goto free_args;
}
}
ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
vol_args->fd, subvol, ptr,
readonly, inherit);
+ if (ret)
+ goto free_inherit;
- if (ret == 0 && ptr &&
- copy_to_user(arg +
- offsetof(struct btrfs_ioctl_vol_args_v2,
- transid), ptr, sizeof(*ptr)))
+ if (ptr && copy_to_user(arg +
+ offsetof(struct btrfs_ioctl_vol_args_v2,
+ transid),
+ ptr, sizeof(*ptr)))
ret = -EFAULT;
-out:
- kfree(vol_args);
+
+free_inherit:
kfree(inherit);
+free_args:
+ kfree(vol_args);
return ret;
}
@@ -2685,7 +2657,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args)) {
ret = PTR_ERR(vol_args);
- goto out;
+ goto err_drop;
}
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
@@ -2703,6 +2675,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
out:
kfree(vol_args);
+err_drop:
mnt_drop_write_file(file);
return ret;
}
@@ -3527,7 +3500,8 @@ process_slot:
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
- last_dest_end = new_key.offset + datal;
+ last_dest_end = ALIGN(new_key.offset + datal,
+ root->sectorsize);
ret = clone_finish_inode_update(trans, inode,
last_dest_end,
destoff, olen);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 7187b14faa6c..ac734ec4cc20 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -571,18 +571,6 @@ void btrfs_remove_ordered_extent(struct inode *inode,
trace_btrfs_ordered_extent_remove(inode, entry);
- /*
- * we have no more ordered extents for this inode and
- * no dirty pages. We can safely remove it from the
- * list of ordered extents
- */
- if (RB_EMPTY_ROOT(&tree->tree) &&
- !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
- spin_lock(&root->fs_info->ordered_root_lock);
- list_del_init(&BTRFS_I(inode)->ordered_operations);
- spin_unlock(&root->fs_info->ordered_root_lock);
- }
-
if (!root->nr_ordered_extents) {
spin_lock(&root->fs_info->ordered_root_lock);
BUG_ON(list_empty(&root->ordered_root));
@@ -627,6 +615,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
spin_unlock(&root->ordered_extent_lock);
btrfs_init_work(&ordered->flush_work,
+ btrfs_flush_delalloc_helper,
btrfs_run_ordered_extent_work, NULL, NULL);
list_add_tail(&ordered->work_list, &works);
btrfs_queue_work(root->fs_info->flush_workers,
@@ -687,81 +676,6 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
}
/*
- * this is used during transaction commit to write all the inodes
- * added to the ordered operation list. These files must be fully on
- * disk before the transaction commits.
- *
- * we have two modes here, one is to just start the IO via filemap_flush
- * and the other is to wait for all the io. When we wait, we have an
- * extra check to make sure the ordered operation list really is empty
- * before we return
- */
-int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, int wait)
-{
- struct btrfs_inode *btrfs_inode;
- struct inode *inode;
- struct btrfs_transaction *cur_trans = trans->transaction;
- struct list_head splice;
- struct list_head works;
- struct btrfs_delalloc_work *work, *next;
- int ret = 0;
-
- INIT_LIST_HEAD(&splice);
- INIT_LIST_HEAD(&works);
-
- mutex_lock(&root->fs_info->ordered_extent_flush_mutex);
- spin_lock(&root->fs_info->ordered_root_lock);
- list_splice_init(&cur_trans->ordered_operations, &splice);
- while (!list_empty(&splice)) {
- btrfs_inode = list_entry(splice.next, struct btrfs_inode,
- ordered_operations);
- inode = &btrfs_inode->vfs_inode;
-
- list_del_init(&btrfs_inode->ordered_operations);
-
- /*
- * the inode may be getting freed (in sys_unlink path).
- */
- inode = igrab(inode);
- if (!inode)
- continue;
-
- if (!wait)
- list_add_tail(&BTRFS_I(inode)->ordered_operations,
- &cur_trans->ordered_operations);
- spin_unlock(&root->fs_info->ordered_root_lock);
-
- work = btrfs_alloc_delalloc_work(inode, wait, 1);
- if (!work) {
- spin_lock(&root->fs_info->ordered_root_lock);
- if (list_empty(&BTRFS_I(inode)->ordered_operations))
- list_add_tail(&btrfs_inode->ordered_operations,
- &splice);
- list_splice_tail(&splice,
- &cur_trans->ordered_operations);
- spin_unlock(&root->fs_info->ordered_root_lock);
- ret = -ENOMEM;
- goto out;
- }
- list_add_tail(&work->list, &works);
- btrfs_queue_work(root->fs_info->flush_workers,
- &work->work);
-
- cond_resched();
- spin_lock(&root->fs_info->ordered_root_lock);
- }
- spin_unlock(&root->fs_info->ordered_root_lock);
-out:
- list_for_each_entry_safe(work, next, &works, list) {
- list_del_init(&work->list);
- btrfs_wait_and_free_delalloc_work(work);
- }
- mutex_unlock(&root->fs_info->ordered_extent_flush_mutex);
- return ret;
-}
-
-/*
* Used to start IO or wait for a given ordered extent to finish.
*
* If wait is one, this effectively waits on page writeback for all the pages
@@ -1120,42 +1034,6 @@ out:
return index;
}
-
-/*
- * add a given inode to the list of inodes that must be fully on
- * disk before a transaction commit finishes.
- *
- * This basically gives us the ext3 style data=ordered mode, and it is mostly
- * used to make sure renamed files are fully on disk.
- *
- * It is a noop if the inode is already fully on disk.
- *
- * If trans is not null, we'll do a friendly check for a transaction that
- * is already flushing things and force the IO down ourselves.
- */
-void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, struct inode *inode)
-{
- struct btrfs_transaction *cur_trans = trans->transaction;
- u64 last_mod;
-
- last_mod = max(BTRFS_I(inode)->generation, BTRFS_I(inode)->last_trans);
-
- /*
- * if this file hasn't been changed since the last transaction
- * commit, we can safely return without doing anything
- */
- if (last_mod <= root->fs_info->last_trans_committed)
- return;
-
- spin_lock(&root->fs_info->ordered_root_lock);
- if (list_empty(&BTRFS_I(inode)->ordered_operations)) {
- list_add_tail(&BTRFS_I(inode)->ordered_operations,
- &cur_trans->ordered_operations);
- }
- spin_unlock(&root->fs_info->ordered_root_lock);
-}
-
int __init ordered_data_init(void)
{
btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 246897058efb..d81a274d621e 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -190,11 +190,6 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
struct btrfs_ordered_extent *ordered);
int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
u32 *sum, int len);
-int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, int wait);
-void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct inode *inode);
int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr);
void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr);
void btrfs_get_logged_extents(struct inode *inode,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 98cb6b2630f9..ded5c601d916 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1201,6 +1201,50 @@ out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
return ret;
}
+
+static int comp_oper_exist(struct btrfs_qgroup_operation *oper1,
+ struct btrfs_qgroup_operation *oper2)
+{
+ /*
+ * Ignore seq and type here, we're looking for any operation
+ * at all related to this extent on that root.
+ */
+ if (oper1->bytenr < oper2->bytenr)
+ return -1;
+ if (oper1->bytenr > oper2->bytenr)
+ return 1;
+ if (oper1->ref_root < oper2->ref_root)
+ return -1;
+ if (oper1->ref_root > oper2->ref_root)
+ return 1;
+ return 0;
+}
+
+static int qgroup_oper_exists(struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup_operation *oper)
+{
+ struct rb_node *n;
+ struct btrfs_qgroup_operation *cur;
+ int cmp;
+
+ spin_lock(&fs_info->qgroup_op_lock);
+ n = fs_info->qgroup_op_tree.rb_node;
+ while (n) {
+ cur = rb_entry(n, struct btrfs_qgroup_operation, n);
+ cmp = comp_oper_exist(cur, oper);
+ if (cmp < 0) {
+ n = n->rb_right;
+ } else if (cmp) {
+ n = n->rb_left;
+ } else {
+ spin_unlock(&fs_info->qgroup_op_lock);
+ return -EEXIST;
+ }
+ }
+ spin_unlock(&fs_info->qgroup_op_lock);
+ return 0;
+}
+
static int comp_oper(struct btrfs_qgroup_operation *oper1,
struct btrfs_qgroup_operation *oper2)
{
@@ -1290,6 +1334,23 @@ int btrfs_qgroup_record_ref(struct btrfs_trans_handle *trans,
oper->seq = atomic_inc_return(&fs_info->qgroup_op_seq);
INIT_LIST_HEAD(&oper->elem.list);
oper->elem.seq = 0;
+
+ if (type == BTRFS_QGROUP_OPER_SUB_SUBTREE) {
+ /*
+ * If any operation for this bytenr/ref_root combo
+ * exists, then we know it's not exclusively owned and
+ * shouldn't be queued up.
+ *
+ * This also catches the case where we have a cloned
+ * extent that gets queued up multiple times during
+ * drop snapshot.
+ */
+ if (qgroup_oper_exists(fs_info, oper)) {
+ kfree(oper);
+ return 0;
+ }
+ }
+
ret = insert_qgroup_oper(fs_info, oper);
if (ret) {
/* Shouldn't happen so have an assert for developers */
@@ -1884,6 +1945,111 @@ out:
}
/*
+ * Process a reference to a shared subtree. This type of operation is
+ * queued during snapshot removal when we encounter extents which are
+ * shared between more than one root.
+ */
+static int qgroup_subtree_accounting(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup_operation *oper)
+{
+ struct ulist *roots = NULL;
+ struct ulist_node *unode;
+ struct ulist_iterator uiter;
+ struct btrfs_qgroup_list *glist;
+ struct ulist *parents;
+ int ret = 0;
+ int err;
+ struct btrfs_qgroup *qg;
+ u64 root_obj = 0;
+ struct seq_list elem = {};
+
+ parents = ulist_alloc(GFP_NOFS);
+ if (!parents)
+ return -ENOMEM;
+
+ btrfs_get_tree_mod_seq(fs_info, &elem);
+ ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr,
+ elem.seq, &roots);
+ btrfs_put_tree_mod_seq(fs_info, &elem);
+ if (ret < 0)
+ goto out;
+
+ if (roots->nnodes != 1)
+ goto out;
+
+ ULIST_ITER_INIT(&uiter);
+ unode = ulist_next(roots, &uiter); /* Only want 1 so no need to loop */
+ /*
+ * If we find our ref root then that means all refs
+ * this extent has to the root have not yet been
+ * deleted. In that case, we do nothing and let the
+ * last ref for this bytenr drive our update.
+ *
+ * This can happen for example if an extent is
+ * referenced multiple times in a snapshot (clone,
+ * etc). If we are in the middle of snapshot removal,
+ * queued updates for such an extent will find the
+ * root if we have not yet finished removing the
+ * snapshot.
+ */
+ if (unode->val == oper->ref_root)
+ goto out;
+
+ root_obj = unode->val;
+ BUG_ON(!root_obj);
+
+ spin_lock(&fs_info->qgroup_lock);
+ qg = find_qgroup_rb(fs_info, root_obj);
+ if (!qg)
+ goto out_unlock;
+
+ qg->excl += oper->num_bytes;
+ qg->excl_cmpr += oper->num_bytes;
+ qgroup_dirty(fs_info, qg);
+
+ /*
+ * Adjust counts for parent groups. First we find all
+ * parents, then in the 2nd loop we do the adjustment
+ * while adding parents of the parents to our ulist.
+ */
+ list_for_each_entry(glist, &qg->groups, next_group) {
+ err = ulist_add(parents, glist->group->qgroupid,
+ ptr_to_u64(glist->group), GFP_ATOMIC);
+ if (err < 0) {
+ ret = err;
+ goto out_unlock;
+ }
+ }
+
+ ULIST_ITER_INIT(&uiter);
+ while ((unode = ulist_next(parents, &uiter))) {
+ qg = u64_to_ptr(unode->aux);
+ qg->excl += oper->num_bytes;
+ qg->excl_cmpr += oper->num_bytes;
+ qgroup_dirty(fs_info, qg);
+
+ /* Add any parents of the parents */
+ list_for_each_entry(glist, &qg->groups, next_group) {
+ err = ulist_add(parents, glist->group->qgroupid,
+ ptr_to_u64(glist->group), GFP_ATOMIC);
+ if (err < 0) {
+ ret = err;
+ goto out_unlock;
+ }
+ }
+ }
+
+out_unlock:
+ spin_unlock(&fs_info->qgroup_lock);
+
+out:
+ ulist_free(roots);
+ ulist_free(parents);
+ return ret;
+}
+
+/*
* btrfs_qgroup_account_ref is called for every ref that is added to or deleted
* from the fs. First, all roots referencing the extent are searched, and
* then the space is accounted accordingly to the different roots. The
@@ -1920,6 +2086,9 @@ static int btrfs_qgroup_account(struct btrfs_trans_handle *trans,
case BTRFS_QGROUP_OPER_SUB_SHARED:
ret = qgroup_shared_accounting(trans, fs_info, oper);
break;
+ case BTRFS_QGROUP_OPER_SUB_SUBTREE:
+ ret = qgroup_subtree_accounting(trans, fs_info, oper);
+ break;
default:
ASSERT(0);
}
@@ -2551,6 +2720,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
memset(&fs_info->qgroup_rescan_work, 0,
sizeof(fs_info->qgroup_rescan_work));
btrfs_init_work(&fs_info->qgroup_rescan_work,
+ btrfs_qgroup_rescan_helper,
btrfs_qgroup_rescan_worker, NULL, NULL);
if (ret) {
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 5952ff1fbd7a..18cc68ca3090 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -44,6 +44,7 @@ enum btrfs_qgroup_operation_type {
BTRFS_QGROUP_OPER_ADD_SHARED,
BTRFS_QGROUP_OPER_SUB_EXCL,
BTRFS_QGROUP_OPER_SUB_SHARED,
+ BTRFS_QGROUP_OPER_SUB_SUBTREE,
};
struct btrfs_qgroup_operation {
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 4a88f073fdd7..0a6b6e4bcbb9 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1416,7 +1416,8 @@ cleanup:
static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
{
- btrfs_init_work(&rbio->work, rmw_work, NULL, NULL);
+ btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+ rmw_work, NULL, NULL);
btrfs_queue_work(rbio->fs_info->rmw_workers,
&rbio->work);
@@ -1424,7 +1425,8 @@ static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
static void async_read_rebuild(struct btrfs_raid_bio *rbio)
{
- btrfs_init_work(&rbio->work, read_rebuild_work, NULL, NULL);
+ btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+ read_rebuild_work, NULL, NULL);
btrfs_queue_work(rbio->fs_info->rmw_workers,
&rbio->work);
@@ -1665,7 +1667,8 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
plug = container_of(cb, struct btrfs_plug_cb, cb);
if (from_schedule) {
- btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
+ btrfs_init_work(&plug->work, btrfs_rmw_helper,
+ unplug_work, NULL, NULL);
btrfs_queue_work(plug->info->rmw_workers,
&plug->work);
return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 09230cf3a244..20408c6b665a 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -798,7 +798,8 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
/* FIXME we cannot handle this properly right now */
BUG();
}
- btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
+ btrfs_init_work(&rmw->work, btrfs_readahead_helper,
+ reada_start_machine_worker, NULL, NULL);
rmw->fs_info = fs_info;
btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index b6d198f5181e..f4a41f37be22 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -428,8 +428,8 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
sbio->index = i;
sbio->sctx = sctx;
sbio->page_count = 0;
- btrfs_init_work(&sbio->work, scrub_bio_end_io_worker,
- NULL, NULL);
+ btrfs_init_work(&sbio->work, btrfs_scrub_helper,
+ scrub_bio_end_io_worker, NULL, NULL);
if (i != SCRUB_BIOS_PER_SCTX - 1)
sctx->bios[i]->next_free = i + 1;
@@ -999,8 +999,8 @@ nodatasum_case:
fixup_nodatasum->root = fs_info->extent_root;
fixup_nodatasum->mirror_num = failed_mirror_index + 1;
scrub_pending_trans_workers_inc(sctx);
- btrfs_init_work(&fixup_nodatasum->work, scrub_fixup_nodatasum,
- NULL, NULL);
+ btrfs_init_work(&fixup_nodatasum->work, btrfs_scrub_helper,
+ scrub_fixup_nodatasum, NULL, NULL);
btrfs_queue_work(fs_info->scrub_workers,
&fixup_nodatasum->work);
goto out;
@@ -1616,7 +1616,8 @@ static void scrub_wr_bio_end_io(struct bio *bio, int err)
sbio->err = err;
sbio->bio = bio;
- btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
+ btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
+ scrub_wr_bio_end_io_worker, NULL, NULL);
btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
}
@@ -2904,6 +2905,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
struct scrub_ctx *sctx;
int ret;
struct btrfs_device *dev;
+ struct rcu_string *name;
if (btrfs_fs_closing(fs_info))
return -EINVAL;
@@ -2965,6 +2967,16 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
return -ENODEV;
}
+ if (!is_dev_replace && !readonly && !dev->writeable) {
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ rcu_read_lock();
+ name = rcu_dereference(dev->name);
+ btrfs_err(fs_info, "scrub: device %s is not writable",
+ name->str);
+ rcu_read_unlock();
+ return -EROFS;
+ }
+
mutex_lock(&fs_info->scrub_lock);
if (!dev->in_fs_metadata || dev->is_tgtdev_for_dev_replace) {
mutex_unlock(&fs_info->scrub_lock);
@@ -3203,7 +3215,8 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
nocow_ctx->len = len;
nocow_ctx->mirror_num = mirror_num;
nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
- btrfs_init_work(&nocow_ctx->work, copy_nocow_pages_worker, NULL, NULL);
+ btrfs_init_work(&nocow_ctx->work, btrfs_scrubnc_helper,
+ copy_nocow_pages_worker, NULL, NULL);
INIT_LIST_HEAD(&nocow_ctx->inodes);
btrfs_queue_work(fs_info->scrub_nocow_workers,
&nocow_ctx->work);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 67b48b9a03e0..c4124de4435b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1665,6 +1665,21 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
return 0;
}
+/*
+ * Calculate numbers for 'df', pessimistic in case of mixed raid profiles.
+ *
+ * If there's a redundant raid level at DATA block groups, use the respective
+ * multiplier to scale the sizes.
+ *
+ * Unused device space usage is based on simulating the chunk allocator
+ * algorithm that respects the device sizes, order of allocations and the
+ * 'alloc_start' value, this is a close approximation of the actual use but
+ * there are other factors that may change the result (like a new metadata
+ * chunk).
+ *
+ * FIXME: not accurate for mixed block groups, total and free/used are ok,
+ * available appears slightly larger.
+ */
static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
@@ -1675,6 +1690,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
u64 total_free_data = 0;
int bits = dentry->d_sb->s_blocksize_bits;
__be32 *fsid = (__be32 *)fs_info->fsid;
+ unsigned factor = 1;
+ struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
/* holding chunk_muext to avoid allocating new chunks */
@@ -1682,30 +1699,52 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
rcu_read_lock();
list_for_each_entry_rcu(found, head, list) {
if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
+ int i;
+
total_free_data += found->disk_total - found->disk_used;
total_free_data -=
btrfs_account_ro_block_groups_free_space(found);
+
+ for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+ if (!list_empty(&found->block_groups[i])) {
+ switch (i) {
+ case BTRFS_RAID_DUP:
+ case BTRFS_RAID_RAID1:
+ case BTRFS_RAID_RAID10:
+ factor = 2;
+ }
+ }
+ }
}
total_used += found->disk_used;
}
+
rcu_read_unlock();
- buf->f_namelen = BTRFS_NAME_LEN;
- buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits;
- buf->f_bfree = buf->f_blocks - (total_used >> bits);
- buf->f_bsize = dentry->d_sb->s_blocksize;
- buf->f_type = BTRFS_SUPER_MAGIC;
+ buf->f_blocks = div_u64(btrfs_super_total_bytes(disk_super), factor);
+ buf->f_blocks >>= bits;
+ buf->f_bfree = buf->f_blocks - (div_u64(total_used, factor) >> bits);
+
+ /* Account global block reserve as used, it's in logical size already */
+ spin_lock(&block_rsv->lock);
+ buf->f_bfree -= block_rsv->size >> bits;
+ spin_unlock(&block_rsv->lock);
+
buf->f_bavail = total_free_data;
ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data);
if (ret) {
mutex_unlock(&fs_info->chunk_mutex);
return ret;
}
- buf->f_bavail += total_free_data;
+ buf->f_bavail += div_u64(total_free_data, factor);
buf->f_bavail = buf->f_bavail >> bits;
mutex_unlock(&fs_info->chunk_mutex);
+ buf->f_type = BTRFS_SUPER_MAGIC;
+ buf->f_bsize = dentry->d_sb->s_blocksize;
+ buf->f_namelen = BTRFS_NAME_LEN;
+
/* We treat it as constant endianness (it doesn't matter _which_)
because we want the fsid to come out the same whether mounted
on a big-endian or little-endian host */
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 78699364f537..12e53556e214 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -614,7 +614,7 @@ int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
if (!fs_info->device_dir_kobj)
return -EINVAL;
- if (one_device) {
+ if (one_device && one_device->bdev) {
disk = one_device->bdev->bd_part;
disk_kobj = &part_to_dev(disk)->kobj;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5f379affdf23..d89c6d3542ca 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -218,7 +218,6 @@ loop:
spin_lock_init(&cur_trans->delayed_refs.lock);
INIT_LIST_HEAD(&cur_trans->pending_snapshots);
- INIT_LIST_HEAD(&cur_trans->ordered_operations);
INIT_LIST_HEAD(&cur_trans->pending_chunks);
INIT_LIST_HEAD(&cur_trans->switch_commits);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
@@ -1612,27 +1611,6 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
kmem_cache_free(btrfs_trans_handle_cachep, trans);
}
-static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
-{
- int ret;
-
- ret = btrfs_run_delayed_items(trans, root);
- if (ret)
- return ret;
-
- /*
- * rename don't use btrfs_join_transaction, so, once we
- * set the transaction to blocked above, we aren't going
- * to get any new ordered operations. We can safely run
- * it here and no for sure that nothing new will be added
- * to the list
- */
- ret = btrfs_run_ordered_operations(trans, root, 1);
-
- return ret;
-}
-
static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
{
if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
@@ -1653,13 +1631,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
struct btrfs_transaction *prev_trans = NULL;
int ret;
- ret = btrfs_run_ordered_operations(trans, root, 0);
- if (ret) {
- btrfs_abort_transaction(trans, root, ret);
- btrfs_end_transaction(trans, root);
- return ret;
- }
-
/* Stop the commit early if ->aborted is set */
if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
ret = cur_trans->aborted;
@@ -1740,7 +1711,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
if (ret)
goto cleanup_transaction;
- ret = btrfs_flush_all_pending_stuffs(trans, root);
+ ret = btrfs_run_delayed_items(trans, root);
if (ret)
goto cleanup_transaction;
@@ -1748,7 +1719,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
extwriter_counter_read(cur_trans) == 0);
/* some pending stuffs might be added after the previous flush. */
- ret = btrfs_flush_all_pending_stuffs(trans, root);
+ ret = btrfs_run_delayed_items(trans, root);
if (ret)
goto cleanup_transaction;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 7dd558ed0716..579be51b27e5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -55,7 +55,6 @@ struct btrfs_transaction {
wait_queue_head_t writer_wait;
wait_queue_head_t commit_wait;
struct list_head pending_snapshots;
- struct list_head ordered_operations;
struct list_head pending_chunks;
struct list_head switch_commits;
struct btrfs_delayed_ref_root delayed_refs;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9e1f2cd5e67a..1d1ba083ca6e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -94,8 +94,10 @@
#define LOG_WALK_REPLAY_ALL 3
static int btrfs_log_inode(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, struct inode *inode,
- int inode_only);
+ struct btrfs_root *root, struct inode *inode,
+ int inode_only,
+ const loff_t start,
+ const loff_t end);
static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 objectid);
@@ -3298,7 +3300,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
struct list_head ordered_sums;
int skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
bool has_extents = false;
- bool need_find_last_extent = (*last_extent == 0);
+ bool need_find_last_extent = true;
bool done = false;
INIT_LIST_HEAD(&ordered_sums);
@@ -3352,8 +3354,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
*/
if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY) {
has_extents = true;
- if (need_find_last_extent &&
- first_key.objectid == (u64)-1)
+ if (first_key.objectid == (u64)-1)
first_key = ins_keys[i];
} else {
need_find_last_extent = false;
@@ -3427,6 +3428,16 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
if (!has_extents)
return ret;
+ if (need_find_last_extent && *last_extent == first_key.offset) {
+ /*
+ * We don't have any leafs between our current one and the one
+ * we processed before that can have file extent items for our
+ * inode (and have a generation number smaller than our current
+ * transaction id).
+ */
+ need_find_last_extent = false;
+ }
+
/*
* Because we use btrfs_search_forward we could skip leaves that were
* not modified and then assume *last_extent is valid when it really
@@ -3537,7 +3548,7 @@ fill_holes:
0, 0);
if (ret)
break;
- *last_extent = offset + len;
+ *last_extent = extent_end;
}
/*
* Need to let the callers know we dropped the path so they should
@@ -3849,8 +3860,10 @@ process:
* This handles both files and directories.
*/
static int btrfs_log_inode(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, struct inode *inode,
- int inode_only)
+ struct btrfs_root *root, struct inode *inode,
+ int inode_only,
+ const loff_t start,
+ const loff_t end)
{
struct btrfs_path *path;
struct btrfs_path *dst_path;
@@ -3867,6 +3880,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
int ins_nr;
bool fast_search = false;
u64 ino = btrfs_ino(inode);
+ struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
path = btrfs_alloc_path();
if (!path)
@@ -4040,13 +4054,35 @@ log_extents:
goto out_unlock;
}
} else if (inode_only == LOG_INODE_ALL) {
- struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree;
struct extent_map *em, *n;
- write_lock(&tree->lock);
- list_for_each_entry_safe(em, n, &tree->modified_extents, list)
- list_del_init(&em->list);
- write_unlock(&tree->lock);
+ write_lock(&em_tree->lock);
+ /*
+ * We can't just remove every em if we're called for a ranged
+ * fsync - that is, one that doesn't cover the whole possible
+ * file range (0 to LLONG_MAX). This is because we can have
+ * em's that fall outside the range we're logging and therefore
+ * their ordered operations haven't completed yet
+ * (btrfs_finish_ordered_io() not invoked yet). This means we
+ * didn't get their respective file extent item in the fs/subvol
+ * tree yet, and need to let the next fast fsync (one which
+ * consults the list of modified extent maps) find the em so
+ * that it logs a matching file extent item and waits for the
+ * respective ordered operation to complete (if it's still
+ * running).
+ *
+ * Removing every em outside the range we're logging would make
+ * the next fast fsync not log their matching file extent items,
+ * therefore making us lose data after a log replay.
+ */
+ list_for_each_entry_safe(em, n, &em_tree->modified_extents,
+ list) {
+ const u64 mod_end = em->mod_start + em->mod_len - 1;
+
+ if (em->mod_start >= start && mod_end <= end)
+ list_del_init(&em->list);
+ }
+ write_unlock(&em_tree->lock);
}
if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
@@ -4056,6 +4092,7 @@ log_extents:
goto out_unlock;
}
}
+
BTRFS_I(inode)->logged_trans = trans->transid;
BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans;
out_unlock:
@@ -4152,7 +4189,10 @@ out:
*/
static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode,
- struct dentry *parent, int exists_only,
+ struct dentry *parent,
+ const loff_t start,
+ const loff_t end,
+ int exists_only,
struct btrfs_log_ctx *ctx)
{
int inode_only = exists_only ? LOG_INODE_EXISTS : LOG_INODE_ALL;
@@ -4198,7 +4238,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
if (ret)
goto end_no_trans;
- ret = btrfs_log_inode(trans, root, inode, inode_only);
+ ret = btrfs_log_inode(trans, root, inode, inode_only, start, end);
if (ret)
goto end_trans;
@@ -4226,7 +4266,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
if (BTRFS_I(inode)->generation >
root->fs_info->last_trans_committed) {
- ret = btrfs_log_inode(trans, root, inode, inode_only);
+ ret = btrfs_log_inode(trans, root, inode, inode_only,
+ 0, LLONG_MAX);
if (ret)
goto end_trans;
}
@@ -4260,13 +4301,15 @@ end_no_trans:
*/
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct dentry *dentry,
+ const loff_t start,
+ const loff_t end,
struct btrfs_log_ctx *ctx)
{
struct dentry *parent = dget_parent(dentry);
int ret;
ret = btrfs_log_inode_parent(trans, root, dentry->d_inode, parent,
- 0, ctx);
+ start, end, 0, ctx);
dput(parent);
return ret;
@@ -4503,6 +4546,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
root->fs_info->last_trans_committed))
return 0;
- return btrfs_log_inode_parent(trans, root, inode, parent, 1, NULL);
+ return btrfs_log_inode_parent(trans, root, inode, parent, 0,
+ LLONG_MAX, 1, NULL);
}
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index 7f5b41bd5373..e2e798ae7cd7 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -59,6 +59,8 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
int btrfs_recover_log_trees(struct btrfs_root *tree_root);
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct dentry *dentry,
+ const loff_t start,
+ const loff_t end,
struct btrfs_log_ctx *ctx);
int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index 7f78cbf5cf41..4c29db604bbe 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -57,6 +57,21 @@ void ulist_free(struct ulist *ulist);
int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask);
int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
u64 *old_aux, gfp_t gfp_mask);
+
+/* just like ulist_add_merge() but take a pointer for the aux data */
+static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux,
+ void **old_aux, gfp_t gfp_mask)
+{
+#if BITS_PER_LONG == 32
+ u64 old64 = (uintptr_t)*old_aux;
+ int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask);
+ *old_aux = (void *)((uintptr_t)old64);
+ return ret;
+#else
+ return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask);
+#endif
+}
+
struct ulist_node *ulist_next(struct ulist *ulist,
struct ulist_iterator *uiter);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6cb82f62cb7c..2c2d6d1d8eee 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -508,6 +508,43 @@ static noinline int device_list_add(const char *path,
ret = 1;
device->fs_devices = fs_devices;
} else if (!device->name || strcmp(device->name->str, path)) {
+ /*
+ * When FS is already mounted.
+ * 1. If you are here and if the device->name is NULL that
+ * means this device was missing at time of FS mount.
+ * 2. If you are here and if the device->name is different
+ * from 'path' that means either
+ * a. The same device disappeared and reappeared with
+ * different name. or
+ * b. The missing-disk-which-was-replaced, has
+ * reappeared now.
+ *
+ * We must allow 1 and 2a above. But 2b would be a spurious
+ * and unintentional.
+ *
+ * Further in case of 1 and 2a above, the disk at 'path'
+ * would have missed some transaction when it was away and
+ * in case of 2a the stale bdev has to be updated as well.
+ * 2b must not be allowed at all time.
+ */
+
+ /*
+ * For now, we do allow update to btrfs_fs_device through the
+ * btrfs dev scan cli after FS has been mounted. We're still
+ * tracking a problem where systems fail mount by subvolume id
+ * when we reject replacement on a mounted FS.
+ */
+ if (!fs_devices->opened && found_transid < device->generation) {
+ /*
+ * That is if the FS is _not_ mounted and if you
+ * are here, that means there is more than one
+ * disk with same uuid and devid.We keep the one
+ * with larger generation number or the last-in if
+ * generation are equal.
+ */
+ return -EEXIST;
+ }
+
name = rcu_string_strdup(path, GFP_NOFS);
if (!name)
return -ENOMEM;
@@ -519,6 +556,15 @@ static noinline int device_list_add(const char *path,
}
}
+ /*
+ * Unmount does not free the btrfs_device struct but would zero
+ * generation along with most of the other members. So just update
+ * it back. We need it to pick the disk with largest generation
+ * (as above).
+ */
+ if (!fs_devices->opened)
+ device->generation = found_transid;
+
if (found_transid > fs_devices->latest_trans) {
fs_devices->latest_devid = devid;
fs_devices->latest_trans = found_transid;
@@ -1436,7 +1482,7 @@ static int btrfs_add_device(struct btrfs_trans_handle *trans,
btrfs_set_device_io_align(leaf, dev_item, device->io_align);
btrfs_set_device_io_width(leaf, dev_item, device->io_width);
btrfs_set_device_sector_size(leaf, dev_item, device->sector_size);
- btrfs_set_device_total_bytes(leaf, dev_item, device->total_bytes);
+ btrfs_set_device_total_bytes(leaf, dev_item, device->disk_total_bytes);
btrfs_set_device_bytes_used(leaf, dev_item, device->bytes_used);
btrfs_set_device_group(leaf, dev_item, 0);
btrfs_set_device_seek_speed(leaf, dev_item, 0);
@@ -1671,7 +1717,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
device->fs_devices->total_devices--;
if (device->missing)
- root->fs_info->fs_devices->missing_devices--;
+ device->fs_devices->missing_devices--;
next_device = list_entry(root->fs_info->fs_devices->devices.next,
struct btrfs_device, dev_list);
@@ -1801,8 +1847,12 @@ void btrfs_rm_dev_replace_srcdev(struct btrfs_fs_info *fs_info,
if (srcdev->bdev) {
fs_info->fs_devices->open_devices--;
- /* zero out the old super */
- btrfs_scratch_superblock(srcdev);
+ /*
+ * zero out the old super if it is not writable
+ * (e.g. seed device)
+ */
+ if (srcdev->writeable)
+ btrfs_scratch_superblock(srcdev);
}
call_rcu(&srcdev->rcu, free_device);
@@ -1941,6 +1991,9 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
fs_devices->seeding = 0;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
+ fs_devices->missing_devices = 0;
+ fs_devices->num_can_discard = 0;
+ fs_devices->rotating = 0;
fs_devices->seed = seed_devices;
generate_random_uuid(fs_devices->fsid);
@@ -5800,7 +5853,8 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
else
generate_random_uuid(dev->uuid);
- btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
+ btrfs_init_work(&dev->work, btrfs_submit_helper,
+ pending_bios_fn, NULL, NULL);
return dev;
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-13 15:04:33 +0000