btrfsic_read_from_block_data(block_ctx, &file_extent_item,
file_extent_item_offset,
sizeof(struct btrfs_file_extent_item));
- next_bytenr = btrfs_stack_file_extent_disk_bytenr(&file_extent_item) +
- btrfs_stack_file_extent_offset(&file_extent_item);
- generation = btrfs_stack_file_extent_generation(&file_extent_item);
- num_bytes = btrfs_stack_file_extent_num_bytes(&file_extent_item);
+ next_bytenr = btrfs_stack_file_extent_disk_bytenr(&file_extent_item);
+ if (btrfs_stack_file_extent_compression(&file_extent_item) ==
+ BTRFS_COMPRESS_NONE) {
+ next_bytenr += btrfs_stack_file_extent_offset(&file_extent_item);
+ num_bytes = btrfs_stack_file_extent_num_bytes(&file_extent_item);
+ } else {
+ num_bytes = btrfs_stack_file_extent_disk_num_bytes(&file_extent_item);
+ }
generation = btrfs_stack_file_extent_generation(&file_extent_item);
if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE)
return -1;
}
bio->bi_bdev = block_ctx->dev->bdev;
- bio->bi_sector = dev_bytenr >> 9;
+ bio->bi_iter.bi_sector = dev_bytenr >> 9;
for (j = i; j < num_pages; j++) {
ret = bio_add_page(bio, block_ctx->pagev[j],
int bio_is_patched;
char **mapped_datav;
- dev_bytenr = 512 * bio->bi_sector;
+ dev_bytenr = 512 * bio->bi_iter.bi_sector;
bio_is_patched = 0;
if (dev_state->state->print_mask &
BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
"submit_bio(rw=0x%x, bi_vcnt=%u,"
" bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
rw, bio->bi_vcnt,
- (unsigned long long)bio->bi_sector, dev_bytenr,
- bio->bi_bdev);
+ (unsigned long long)bio->bi_iter.bi_sector,
+ dev_bytenr, bio->bi_bdev);
mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt,
GFP_NOFS);
kunmap_atomic(kaddr);
if (csum != *cb_sum) {
- printk(KERN_INFO "btrfs csum failed ino %llu "
- "extent %llu csum %u "
- "wanted %u mirror %d\n",
- btrfs_ino(inode), disk_start, csum, *cb_sum,
- cb->mirror_num);
+ btrfs_info(BTRFS_I(inode)->root->fs_info,
+ "csum failed ino %llu extent %llu csum %u wanted %u mirror %d",
+ btrfs_ino(inode), disk_start, csum, *cb_sum,
+ cb->mirror_num);
ret = -EIO;
goto fail;
}
goto out;
inode = cb->inode;
- ret = check_compressed_csum(inode, cb, (u64)bio->bi_sector << 9);
+ ret = check_compressed_csum(inode, cb,
+ (u64)bio->bi_iter.bi_sector << 9);
if (ret)
goto csum_failed;
if (cb->errors) {
bio_io_error(cb->orig_bio);
} else {
- int bio_index = 0;
- struct bio_vec *bvec = cb->orig_bio->bi_io_vec;
+ int i;
+ struct bio_vec *bvec;
/*
* we have verified the checksum already, set page
* checked so the end_io handlers know about it
*/
- while (bio_index < cb->orig_bio->bi_vcnt) {
+ bio_for_each_segment_all(bvec, cb->orig_bio, i)
SetPageChecked(bvec->bv_page);
- bvec++;
- bio_index++;
- }
+
bio_endio(cb->orig_bio, 0);
}
for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) {
page = compressed_pages[pg_index];
page->mapping = inode->i_mapping;
- if (bio->bi_size)
+ if (bio->bi_iter.bi_size)
ret = io_tree->ops->merge_bio_hook(WRITE, page, 0,
PAGE_CACHE_SIZE,
bio, 0);
bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
}
if (bytes_left < PAGE_CACHE_SIZE) {
- printk("bytes left %lu compress len %lu nr %lu\n",
+ btrfs_info(BTRFS_I(inode)->root->fs_info,
+ "bytes left %lu compress len %lu nr %lu",
bytes_left, cb->compressed_len, cb->nr_pages);
}
bytes_left -= PAGE_CACHE_SIZE;
if (!em || last_offset < em->start ||
(last_offset + PAGE_CACHE_SIZE > extent_map_end(em)) ||
- (em->block_start >> 9) != cb->orig_bio->bi_sector) {
+ (em->block_start >> 9) != cb->orig_bio->bi_iter.bi_sector) {
free_extent_map(em);
unlock_extent(tree, last_offset, end);
unlock_page(page);
* in it. We don't actually do IO on those pages but allocate new ones
* to hold the compressed pages on disk.
*
- * bio->bi_sector points to the compressed extent on disk
+ * bio->bi_iter.bi_sector points to the compressed extent on disk
* bio->bi_io_vec points to all of the inode pages
* bio->bi_vcnt is a count of pages
*
struct page *page;
struct block_device *bdev;
struct bio *comp_bio;
- u64 cur_disk_byte = (u64)bio->bi_sector << 9;
+ u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9;
u64 em_len;
u64 em_start;
struct extent_map *em;
page->mapping = inode->i_mapping;
page->index = em_start >> PAGE_CACHE_SHIFT;
- if (comp_bio->bi_size)
+ if (comp_bio->bi_iter.bi_size)
ret = tree->ops->merge_bio_hook(READ, page, 0,
PAGE_CACHE_SIZE,
comp_bio, 0);
comp_bio, sums);
BUG_ON(ret); /* -ENOMEM */
}
- sums += (comp_bio->bi_size + root->sectorsize - 1) /
- root->sectorsize;
+ sums += (comp_bio->bi_iter.bi_size +
+ root->sectorsize - 1) / root->sectorsize;
ret = btrfs_map_bio(root, READ, comp_bio,
mirror_num, 0);
#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6)
#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7)
#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8)
+ #define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9)
#define BTRFS_FEATURE_COMPAT_SUPP 0ULL
+ #define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL
+ #define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SUPP 0ULL
+ #define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL
+ #define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL
+
#define BTRFS_FEATURE_INCOMPAT_SUPP \
(BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \
BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL | \
BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \
BTRFS_FEATURE_INCOMPAT_RAID56 | \
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
- BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
+ BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
+ BTRFS_FEATURE_INCOMPAT_NO_HOLES)
+
+ #define BTRFS_FEATURE_INCOMPAT_SAFE_SET \
+ (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
+ #define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL
/*
* A leaf is full of items. offset and size tell us where to find
} __attribute__ ((__packed__));
struct btrfs_space_info {
- u64 flags;
+ spinlock_t lock;
u64 total_bytes; /* total bytes in the space,
this doesn't take mirrors into account */
transaction finishes */
u64 bytes_reserved; /* total bytes the allocator has reserved for
current allocations */
- u64 bytes_readonly; /* total bytes that are read only */
-
u64 bytes_may_use; /* number of bytes that may be used for
delalloc/allocations */
+ u64 bytes_readonly; /* total bytes that are read only */
+
+ unsigned int full:1; /* indicates that we cannot allocate any more
+ chunks for this space */
+ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */
+
+ unsigned int flush:1; /* set if we are trying to make space */
+
+ unsigned int force_alloc; /* set if we need to force a chunk
+ alloc for this space */
+
u64 disk_used; /* total bytes used on disk */
u64 disk_total; /* total bytes on disk, takes mirrors into
account */
+ u64 flags;
+
/*
* bytes_pinned is kept in line with what is actually pinned, as in
* we've called update_block_group and dropped the bytes_used counter
*/
struct percpu_counter total_bytes_pinned;
- unsigned int full:1; /* indicates that we cannot allocate any more
- chunks for this space */
- unsigned int chunk_alloc:1; /* set if we are allocating a chunk */
-
- unsigned int flush:1; /* set if we are trying to make space */
-
- unsigned int force_alloc; /* set if we need to force a chunk
- alloc for this space */
-
struct list_head list;
+ struct rw_semaphore groups_sem;
/* for block groups in our same type */
struct list_head block_groups[BTRFS_NR_RAID_TYPES];
- spinlock_t lock;
- struct rw_semaphore groups_sem;
wait_queue_head_t wait;
+
+ struct kobject kobj;
+ struct kobject block_group_kobjs[BTRFS_NR_RAID_TYPES];
};
#define BTRFS_BLOCK_RSV_GLOBAL 1
u64 generation;
u64 last_trans_committed;
+ u64 avg_delayed_ref_runtime;
/*
* this is updated to the current trans every time a full commit
spinlock_t tree_mod_seq_lock;
atomic64_t tree_mod_seq;
struct list_head tree_mod_seq_list;
- struct seq_list tree_mod_seq_elem;
/* this protects tree_mod_log */
rwlock_t tree_mod_log_lock;
int thread_pool_size;
struct kobject super_kobj;
+ struct kobject *space_info_kobj;
+ struct kobject *device_dir_kobj;
struct completion kobj_unregister;
int do_barriers;
int closing;
spinlock_t reada_lock;
struct radix_tree_root reada_tree;
+ /* Extent buffer radix tree */
+ spinlock_t buffer_lock;
+ struct radix_tree_root buffer_radix;
+
/* next backup root to be overwritten */
int backup_root_index;
struct list_head ordered_extents;
struct list_head ordered_root;
u64 nr_ordered_extents;
+
+ /*
+ * Number of currently running SEND ioctls to prevent
+ * manipulation with the read-only status via SUBVOL_SETFLAGS
+ */
+ int send_in_progress;
};
struct btrfs_ioctl_defrag_range_args {
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22)
#define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23)
+ #define BTRFS_MOUNT_CHANGE_INODE_CACHE (1 << 24)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
struct btrfs_file_extent_item, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes,
struct btrfs_file_extent_item, num_bytes, 64);
+ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_num_bytes,
+ struct btrfs_file_extent_item, disk_num_bytes, 64);
+ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression,
+ struct btrfs_file_extent_item, compression, 8);
static inline unsigned long
btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e)
BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item,
other_encoding, 16);
- /* this returns the number of file bytes represented by the inline item.
- * If an item is compressed, this is the uncompressed size
- */
- static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb,
- struct btrfs_file_extent_item *e)
- {
- return btrfs_file_extent_ram_bytes(eb, e);
- }
-
/*
* this returns the number of bytes used by the item on disk, minus the
* size of any extent headers. If a file is compressed on disk, this is
return btrfs_item_size(eb, e) - offset;
}
+ /* this returns the number of file bytes represented by the inline item.
+ * If an item is compressed, this is the uncompressed size
+ */
+ static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb,
+ int slot,
+ struct btrfs_file_extent_item *fi)
+ {
+ struct btrfs_map_token token;
+
+ btrfs_init_map_token(&token);
+ /*
+ * return the space used on disk if this item isn't
+ * compressed or encoded
+ */
+ if (btrfs_token_file_extent_compression(eb, fi, &token) == 0 &&
+ btrfs_token_file_extent_encryption(eb, fi, &token) == 0 &&
+ btrfs_token_file_extent_other_encoding(eb, fi, &token) == 0) {
+ return btrfs_file_extent_inline_item_len(eb,
+ btrfs_item_nr(slot));
+ }
+
+ /* otherwise use the ram bytes field */
+ return btrfs_token_file_extent_ram_bytes(eb, fi, &token);
+ }
+
+
/* btrfs_dev_stats_item */
static inline u64 btrfs_dev_stats_value(struct extent_buffer *eb,
struct btrfs_dev_stats_item *ptr,
int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+ int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root, unsigned long count);
struct btrfs_fs_info *info,
u64 bytenr);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+ int get_block_group_index(struct btrfs_block_group_cache *cache);
struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u32 blocksize,
u64 parent, u64 root_objectid,
int btrfs_previous_item(struct btrfs_root *root,
struct btrfs_path *path, u64 min_objectid,
int type);
+ int btrfs_previous_extent_item(struct btrfs_root *root,
+ struct btrfs_path *path, u64 min_objectid);
void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *new_key);
struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
struct btrfs_root *root,
struct btrfs_path *path,
struct btrfs_key *new_key);
+ int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
+ u64 inum, u64 ioff, u8 key_type, struct btrfs_key *found_key);
int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_key *key, struct btrfs_path *p, int
ins_len, int cow);
}
int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
+ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
u64 time_seq);
static inline int btrfs_next_old_item(struct btrfs_root *root,
struct btrfs_root *root,
const char *name, int name_len,
u64 inode_objectid, u64 ref_objectid, u64 *index);
- int btrfs_get_inode_ref_index(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path,
- const char *name, int name_len,
- u64 inode_objectid, u64 ref_objectid, int mod,
- u64 *ret_index);
int btrfs_insert_empty_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 objectid);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
struct extent_state **cached_state);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
- struct btrfs_root *new_root, u64 new_dirid);
+ struct btrfs_root *new_root,
+ struct btrfs_root *parent_root,
+ u64 new_dirid);
int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
size_t size, struct bio *bio,
unsigned long bio_flags);
int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode,
struct btrfs_path *path, u64 start, u64 end,
- u64 *drop_end, int drop_cache);
+ u64 *drop_end, int drop_cache,
+ int replace_extent,
+ u32 extent_item_size,
+ int *key_inserted);
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode, u64 start,
u64 end, int drop_cache);
/* sysfs.c */
int btrfs_init_sysfs(void);
void btrfs_exit_sysfs(void);
+ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info);
+ void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info);
/* xattr.c */
ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
btrfs_printk(fs_info, KERN_NOTICE fmt, ##args)
#define btrfs_info(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_INFO fmt, ##args)
+
+ #ifdef DEBUG
#define btrfs_debug(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_DEBUG fmt, ##args)
+ #else
+ #define btrfs_debug(fs_info, fmt, args...) \
+ no_printk(KERN_DEBUG fmt, ##args)
+ #endif
#ifdef CONFIG_BTRFS_ASSERT
static inline void assfail(char *expr, char *file, int line)
{
- printk(KERN_ERR "BTRFS assertion failed: %s, file: %s, line: %d",
+ pr_err("BTRFS: assertion failed: %s, file: %s, line: %d",
expr, file, line);
BUG();
}
if (!(features & flag)) {
features |= flag;
btrfs_set_super_incompat_flags(disk_super, features);
- printk(KERN_INFO "btrfs: setting %llu feature flag\n",
+ btrfs_info(fs_info, "setting %llu feature flag",
flag);
}
spin_unlock(&fs_info->super_lock);
/* acl.c */
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
+int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir);
-int btrfs_acl_chmod(struct inode *inode);
#else
#define btrfs_get_acl NULL
+#define btrfs_set_acl NULL
static inline int btrfs_init_acl(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir)
{
return 0;
}
-static inline int btrfs_acl_chmod(struct inode *inode)
-{
- return 0;
-}
#endif
/* relocation.c */
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
+ #include "sysfs.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
memcpy(&found, result, csum_size);
read_extent_buffer(buf, &val, 0, csum_size);
- printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
- "failed on %llu wanted %X found %X "
- "level %d\n",
- root->fs_info->sb->s_id, buf->start,
- val, found, btrfs_header_level(buf));
+ printk_ratelimited(KERN_INFO
+ "BTRFS: %s checksum verify failed on %llu wanted %X found %X "
+ "level %d\n",
+ root->fs_info->sb->s_id, buf->start,
+ val, found, btrfs_header_level(buf));
if (result != (char *)&inline_result)
kfree(result);
return 1;
ret = 1;
if (ret && btrfs_super_generation(disk_sb) < 10) {
- printk(KERN_WARNING "btrfs: super block crcs don't match, older mkfs detected\n");
+ printk(KERN_WARNING
+ "BTRFS: super block crcs don't match, older mkfs detected\n");
ret = 0;
}
}
if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) {
- printk(KERN_ERR "btrfs: unsupported checksum algorithm %u\n",
+ printk(KERN_ERR "BTRFS: unsupported checksum algorithm %u\n",
csum_type);
ret = 1;
}
static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
{
- struct extent_io_tree *tree;
u64 start = page_offset(page);
u64 found_start;
struct extent_buffer *eb;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
-
eb = (struct extent_buffer *)page->private;
if (page != eb->pages[0])
return 0;
}
#define CORRUPT(reason, eb, root, slot) \
- printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \
- "root=%llu, slot=%d\n", reason, \
+ btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu," \
+ "root=%llu, slot=%d", reason, \
btrfs_header_bytenr(eb), root->objectid, slot)
static noinline int check_leaf(struct btrfs_root *root,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
{
- struct extent_io_tree *tree;
u64 found_start;
int found_level;
struct extent_buffer *eb;
if (!page->private)
goto out;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
eb = (struct extent_buffer *)page->private;
/* the pending IO might have been the only thing that kept this buffer
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
- printk_ratelimited(KERN_INFO "btrfs bad tree block start "
+ printk_ratelimited(KERN_INFO "BTRFS: bad tree block start "
"%llu %llu\n",
found_start, eb->start);
ret = -EIO;
goto err;
}
if (check_tree_block_fsid(root, eb)) {
- printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
+ printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n",
eb->start);
ret = -EIO;
goto err;
}
found_level = btrfs_header_level(eb);
if (found_level >= BTRFS_MAX_LEVEL) {
- btrfs_info(root->fs_info, "bad tree block level %d\n",
+ btrfs_info(root->fs_info, "bad tree block level %d",
(int)btrfs_header_level(eb));
ret = -EIO;
goto err;
static int btree_csum_one_bio(struct bio *bio)
{
- struct bio_vec *bvec = bio->bi_io_vec;
- int bio_index = 0;
+ struct bio_vec *bvec;
struct btrfs_root *root;
- int ret = 0;
+ int i, ret = 0;
- WARN_ON(bio->bi_vcnt <= 0);
- while (bio_index < bio->bi_vcnt) {
+ bio_for_each_segment_all(bvec, bio, i) {
root = BTRFS_I(bvec->bv_page->mapping->host)->root;
ret = csum_dirty_buffer(root, bvec->bv_page);
if (ret)
break;
- bio_index++;
- bvec++;
}
+
return ret;
}
static int btree_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct extent_io_tree *tree;
struct btrfs_fs_info *fs_info;
int ret;
- tree = &BTRFS_I(mapping->host)->io_tree;
if (wbc->sync_mode == WB_SYNC_NONE) {
if (wbc->for_kupdate)
extent_invalidatepage(tree, page, offset);
btree_releasepage(page, GFP_NOFS);
if (PagePrivate(page)) {
- printk(KERN_WARNING "btrfs warning page private not zero "
- "on page %llu\n", (unsigned long long)page_offset(page));
+ btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
+ "page private not zero on page %llu",
+ (unsigned long long)page_offset(page));
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
u64 bytenr, u32 blocksize)
{
- struct inode *btree_inode = root->fs_info->btree_inode;
- struct extent_buffer *eb;
- eb = find_extent_buffer(&BTRFS_I(btree_inode)->io_tree, bytenr);
- return eb;
+ return find_extent_buffer(root->fs_info, bytenr);
}
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
u64 bytenr, u32 blocksize)
{
- struct inode *btree_inode = root->fs_info->btree_inode;
- struct extent_buffer *eb;
-
- eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
- bytenr, blocksize);
- return eb;
+ return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
}
struct btrfs_root *root;
struct btrfs_key key;
int ret = 0;
- u64 bytenr;
uuid_le uuid;
root = btrfs_alloc_root(fs_info);
goto fail;
}
- bytenr = leaf->start;
memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
btrfs_set_header_bytenr(leaf, leaf->start);
btrfs_set_header_generation(leaf, trans->transid);
if (ret)
goto fail;
- ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid);
+ ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID,
+ location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL);
if (ret < 0)
goto fail;
if (ret == 0)
{
struct bio *bio;
struct end_io_wq *end_io_wq;
- struct btrfs_fs_info *fs_info;
int error;
end_io_wq = container_of(work, struct end_io_wq, work);
bio = end_io_wq->bio;
- fs_info = end_io_wq->info;
error = end_io_wq->error;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
kfree(end_io_wq);
- bio_endio(bio, error);
+ bio_endio_nodec(bio, error);
}
static int cleaner_kthread(void *arg)
for (i = 0; i < ret; i++)
btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
+
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
+ btrfs_free_log_root_tree(NULL, fs_info);
+ btrfs_destroy_pinned_extent(fs_info->tree_root,
+ fs_info->pinned_extents);
+ }
}
int open_ctree(struct super_block *sb,
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
spin_lock_init(&fs_info->free_chunk_lock);
spin_lock_init(&fs_info->tree_mod_seq_lock);
spin_lock_init(&fs_info->super_lock);
+ spin_lock_init(&fs_info->buffer_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->reloc_mutex);
seqlock_init(&fs_info->profiles_lock);
fs_info->free_chunk_space = 0;
fs_info->tree_mod_log = RB_ROOT;
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
-
+ fs_info->avg_delayed_ref_runtime = div64_u64(NSEC_PER_SEC, 64);
/* readahead state */
INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
spin_lock_init(&fs_info->reada_lock);
* Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
*/
if (btrfs_check_super_csum(bh->b_data)) {
- printk(KERN_ERR "btrfs: superblock checksum mismatch\n");
+ printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
err = -EINVAL;
goto fail_alloc;
}
ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
if (ret) {
- printk(KERN_ERR "btrfs: superblock contains fatal errors\n");
+ printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
err = -EINVAL;
goto fail_alloc;
}
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
- printk(KERN_ERR "btrfs: has skinny extents\n");
+ printk(KERN_ERR "BTRFS: has skinny extents\n");
/*
* flag our filesystem as having big metadata blocks if
*/
if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- printk(KERN_INFO "btrfs flagging fs with big metadata feature\n");
+ printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
}
*/
if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
(sectorsize != leafsize)) {
- printk(KERN_WARNING "btrfs: unequal leaf/node/sector sizes "
+ printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
"are not allowed for mixed block groups on %s\n",
sb->s_id);
goto fail_alloc;
sb->s_blocksize_bits = blksize_bits(sectorsize);
if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
- printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id);
+ printk(KERN_INFO "BTRFS: valid FS not found on %s\n", sb->s_id);
goto fail_sb_buffer;
}
if (sectorsize != PAGE_SIZE) {
- printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) "
+ printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) "
"found on %s\n", (unsigned long)sectorsize, sb->s_id);
goto fail_sb_buffer;
}
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to read the system "
+ printk(KERN_WARNING "BTRFS: failed to read the system "
"array on %s\n", sb->s_id);
goto fail_sb_buffer;
}
blocksize, generation);
if (!chunk_root->node ||
!test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
- printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
sb->s_id);
goto fail_tree_roots;
}
ret = btrfs_read_chunk_tree(chunk_root);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read chunk tree on %s\n",
sb->s_id);
goto fail_tree_roots;
}
btrfs_close_extra_devices(fs_info, fs_devices, 0);
if (!fs_devices->latest_bdev) {
- printk(KERN_CRIT "btrfs: failed to read devices on %s\n",
+ printk(KERN_CRIT "BTRFS: failed to read devices on %s\n",
sb->s_id);
goto fail_tree_roots;
}
blocksize, generation);
if (!tree_root->node ||
!test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) {
- printk(KERN_WARNING "btrfs: failed to read tree root on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
sb->s_id);
goto recovery_tree_root;
ret = btrfs_recover_balance(fs_info);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to recover balance\n");
+ printk(KERN_WARNING "BTRFS: failed to recover balance\n");
goto fail_block_groups;
}
ret = btrfs_init_dev_stats(fs_info);
if (ret) {
- printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n",
+ printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_replace(fs_info);
if (ret) {
- pr_err("btrfs: failed to init dev_replace: %d\n", ret);
+ pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
goto fail_block_groups;
}
btrfs_close_extra_devices(fs_info, fs_devices, 1);
- ret = btrfs_init_space_info(fs_info);
+ ret = btrfs_sysfs_add_one(fs_info);
if (ret) {
- printk(KERN_ERR "Failed to initial space info: %d\n", ret);
+ pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
goto fail_block_groups;
}
+ ret = btrfs_init_space_info(fs_info);
+ if (ret) {
+ printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
+ goto fail_sysfs;
+ }
+
ret = btrfs_read_block_groups(extent_root);
if (ret) {
- printk(KERN_ERR "Failed to read block groups: %d\n", ret);
- goto fail_block_groups;
+ printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
+ goto fail_sysfs;
}
fs_info->num_tolerated_disk_barrier_failures =
btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
if (fs_info->fs_devices->missing_devices >
fs_info->num_tolerated_disk_barrier_failures &&
!(sb->s_flags & MS_RDONLY)) {
- printk(KERN_WARNING
- "Btrfs: too many missing devices, writeable mount is not allowed\n");
- goto fail_block_groups;
+ printk(KERN_WARNING "BTRFS: "
+ "too many missing devices, writeable mount is not allowed\n");
+ goto fail_sysfs;
}
fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
"btrfs-cleaner");
if (IS_ERR(fs_info->cleaner_kthread))
- goto fail_block_groups;
+ goto fail_sysfs;
fs_info->transaction_kthread = kthread_run(transaction_kthread,
tree_root,
if (!btrfs_test_opt(tree_root, SSD) &&
!btrfs_test_opt(tree_root, NOSSD) &&
!fs_info->fs_devices->rotating) {
- printk(KERN_INFO "Btrfs detected SSD devices, enabling SSD "
+ printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
"mode\n");
btrfs_set_opt(fs_info->mount_opt, SSD);
}
+ /* Set the real inode map cache flag */
+ if (btrfs_test_opt(tree_root, CHANGE_INODE_CACHE))
+ btrfs_set_opt(tree_root->fs_info->mount_opt, INODE_MAP_CACHE);
+
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
ret = btrfsic_mount(tree_root, fs_devices,
1 : 0,
fs_info->check_integrity_print_mask);
if (ret)
- printk(KERN_WARNING "btrfs: failed to initialize"
+ printk(KERN_WARNING "BTRFS: failed to initialize"
" integrity check module %s\n", sb->s_id);
}
#endif
u64 bytenr = btrfs_super_log_root(disk_super);
if (fs_devices->rw_devices == 0) {
- printk(KERN_WARNING "Btrfs log replay required "
+ printk(KERN_WARNING "BTRFS: log replay required "
"on RO media\n");
err = -EIO;
goto fail_qgroup;
generation + 1);
if (!log_tree_root->node ||
!extent_buffer_uptodate(log_tree_root->node)) {
- printk(KERN_ERR "btrfs: failed to read log tree\n");
+ printk(KERN_ERR "BTRFS: failed to read log tree\n");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
goto fail_trans_kthread;
ret = btrfs_recover_relocation(tree_root);
if (ret < 0) {
printk(KERN_WARNING
- "btrfs: failed to recover relocation\n");
+ "BTRFS: failed to recover relocation\n");
err = -EINVAL;
goto fail_qgroup;
}
ret = btrfs_resume_balance_async(fs_info);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to resume balance\n");
+ printk(KERN_WARNING "BTRFS: failed to resume balance\n");
close_ctree(tree_root);
return ret;
}
ret = btrfs_resume_dev_replace_async(fs_info);
if (ret) {
- pr_warn("btrfs: failed to resume dev_replace\n");
+ pr_warn("BTRFS: failed to resume dev_replace\n");
close_ctree(tree_root);
return ret;
}
btrfs_qgroup_rescan_resume(fs_info);
if (create_uuid_tree) {
- pr_info("btrfs: creating UUID tree\n");
+ pr_info("BTRFS: creating UUID tree\n");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
- pr_warn("btrfs: failed to create the UUID tree %d\n",
+ pr_warn("BTRFS: failed to create the UUID tree %d\n",
ret);
close_ctree(tree_root);
return ret;
}
} else if (check_uuid_tree ||
btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) {
- pr_info("btrfs: checking UUID tree\n");
+ pr_info("BTRFS: checking UUID tree\n");
ret = btrfs_check_uuid_tree(fs_info);
if (ret) {
- pr_warn("btrfs: failed to check the UUID tree %d\n",
+ pr_warn("BTRFS: failed to check the UUID tree %d\n",
ret);
close_ctree(tree_root);
return ret;
*/
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
+ fail_sysfs:
+ btrfs_sysfs_remove_one(fs_info);
+
fail_block_groups:
btrfs_put_block_group_cache(fs_info);
btrfs_free_block_groups(fs_info);
struct btrfs_device *device = (struct btrfs_device *)
bh->b_private;
- printk_ratelimited_in_rcu(KERN_WARNING "lost page write due to "
+ printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to "
"I/O error on %s\n",
rcu_str_deref(device->name));
/* note, we dont' set_buffer_write_io_error because we have
bh = __getblk(device->bdev, bytenr / 4096,
BTRFS_SUPER_INFO_SIZE);
if (!bh) {
- printk(KERN_ERR "btrfs: couldn't get super "
+ printk(KERN_ERR "BTRFS: couldn't get super "
"buffer head for bytenr %Lu\n", bytenr);
errors++;
continue;
* we fua the first super. The others we allow
* to go down lazy.
*/
- ret = btrfsic_submit_bh(WRITE_FUA, bh);
+ if (i == 0)
+ ret = btrfsic_submit_bh(WRITE_FUA, bh);
+ else
+ ret = btrfsic_submit_bh(WRITE_SYNC, bh);
if (ret)
errors++;
}
wait_for_completion(&device->flush_wait);
if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
- printk_in_rcu("btrfs: disabling barriers on dev %s\n",
+ printk_in_rcu("BTRFS: disabling barriers on dev %s\n",
rcu_str_deref(device->name));
device->nobarriers = 1;
} else if (!bio_flagged(bio, BIO_UPTODATE)) {
total_errors++;
}
if (total_errors > max_errors) {
- printk(KERN_ERR "btrfs: %d errors while writing supers\n",
+ btrfs_err(root->fs_info, "%d errors while writing supers",
total_errors);
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
btrfs_free_log(NULL, root);
- btrfs_free_log_root_tree(NULL, fs_info);
- }
__btrfs_remove_free_space_cache(root->free_ino_pinned);
__btrfs_remove_free_space_cache(root->free_ino_ctl);
if (!(fs_info->sb->s_flags & MS_RDONLY)) {
ret = btrfs_commit_super(root);
if (ret)
- printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
+ btrfs_err(root->fs_info, "commit super ret %d", ret);
}
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
btrfs_error_commit_super(root);
- btrfs_put_block_group_cache(fs_info);
-
kthread_stop(fs_info->transaction_kthread);
kthread_stop(fs_info->cleaner_kthread);
btrfs_free_qgroup_config(root->fs_info);
if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
- printk(KERN_INFO "btrfs: at unmount delalloc count %lld\n",
+ btrfs_info(root->fs_info, "at unmount delalloc count %lld",
percpu_counter_sum(&fs_info->delalloc_bytes));
}
+ btrfs_sysfs_remove_one(fs_info);
+
del_fs_roots(fs_info);
+ btrfs_put_block_group_cache(fs_info);
+
btrfs_free_block_groups(fs_info);
btrfs_stop_all_workers(fs_info);
delayed_refs = &trans->delayed_refs;
spin_lock(&delayed_refs->lock);
- if (delayed_refs->num_entries == 0) {
+ if (atomic_read(&delayed_refs->num_entries) == 0) {
spin_unlock(&delayed_refs->lock);
- printk(KERN_INFO "delayed_refs has NO entry\n");
+ btrfs_info(root->fs_info, "delayed_refs has NO entry");
return ret;
}
- while ((node = rb_first(&delayed_refs->root)) != NULL) {
- struct btrfs_delayed_ref_head *head = NULL;
+ while ((node = rb_first(&delayed_refs->href_root)) != NULL) {
+ struct btrfs_delayed_ref_head *head;
bool pin_bytes = false;
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- atomic_set(&ref->refs, 1);
- if (btrfs_delayed_ref_is_head(ref)) {
-
- head = btrfs_delayed_node_to_head(ref);
- if (!mutex_trylock(&head->mutex)) {
- atomic_inc(&ref->refs);
- spin_unlock(&delayed_refs->lock);
-
- /* Need to wait for the delayed ref to run */
- mutex_lock(&head->mutex);
- mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(ref);
-
- spin_lock(&delayed_refs->lock);
- continue;
- }
-
- if (head->must_insert_reserved)
- pin_bytes = true;
- btrfs_free_delayed_extent_op(head->extent_op);
- delayed_refs->num_heads--;
- if (list_empty(&head->cluster))
- delayed_refs->num_heads_ready--;
- list_del_init(&head->cluster);
- }
+ head = rb_entry(node, struct btrfs_delayed_ref_head,
+ href_node);
+ if (!mutex_trylock(&head->mutex)) {
+ atomic_inc(&head->node.refs);
+ spin_unlock(&delayed_refs->lock);
- ref->in_tree = 0;
- rb_erase(&ref->rb_node, &delayed_refs->root);
- delayed_refs->num_entries--;
- spin_unlock(&delayed_refs->lock);
- if (head) {
- if (pin_bytes)
- btrfs_pin_extent(root, ref->bytenr,
- ref->num_bytes, 1);
+ mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref(&head->node);
+ spin_lock(&delayed_refs->lock);
+ continue;
+ }
+ spin_lock(&head->lock);
+ while ((node = rb_first(&head->ref_root)) != NULL) {
+ ref = rb_entry(node, struct btrfs_delayed_ref_node,
+ rb_node);
+ ref->in_tree = 0;
+ rb_erase(&ref->rb_node, &head->ref_root);
+ atomic_dec(&delayed_refs->num_entries);
+ btrfs_put_delayed_ref(ref);
+ cond_resched_lock(&head->lock);
}
- btrfs_put_delayed_ref(ref);
+ if (head->must_insert_reserved)
+ pin_bytes = true;
+ btrfs_free_delayed_extent_op(head->extent_op);
+ delayed_refs->num_heads--;
+ if (head->processing == 0)
+ delayed_refs->num_heads_ready--;
+ atomic_dec(&delayed_refs->num_entries);
+ head->node.in_tree = 0;
+ rb_erase(&head->href_node, &delayed_refs->href_root);
+ spin_unlock(&head->lock);
+ spin_unlock(&delayed_refs->lock);
+ mutex_unlock(&head->mutex);
+ if (pin_bytes)
+ btrfs_pin_extent(root, head->node.bytenr,
+ head->node.num_bytes, 1);
+ btrfs_put_delayed_ref(&head->node);
cond_resched();
spin_lock(&delayed_refs->lock);
}
while (!list_empty(&states)) {
state = list_entry(states.next, struct extent_state, leak_list);
- printk(KERN_ERR "btrfs state leak: start %llu end %llu "
+ printk(KERN_ERR "BTRFS: state leak: start %llu end %llu "
"state %lu in tree %p refs %d\n",
state->start, state->end, state->state, state->tree,
atomic_read(&state->refs));
while (!list_empty(&buffers)) {
eb = list_entry(buffers.next, struct extent_buffer, leak_list);
- printk(KERN_ERR "btrfs buffer leak start %llu len %lu "
+ printk(KERN_ERR "BTRFS: buffer leak start %llu len %lu "
"refs %d\n",
eb->start, eb->len, atomic_read(&eb->refs));
list_del(&eb->leak_list);
}
}
- #define btrfs_debug_check_extent_io_range(inode, start, end) \
- __btrfs_debug_check_extent_io_range(__func__, (inode), (start), (end))
+ #define btrfs_debug_check_extent_io_range(tree, start, end) \
+ __btrfs_debug_check_extent_io_range(__func__, (tree), (start), (end))
static inline void __btrfs_debug_check_extent_io_range(const char *caller,
- struct inode *inode, u64 start, u64 end)
+ struct extent_io_tree *tree, u64 start, u64 end)
{
- u64 isize = i_size_read(inode);
+ struct inode *inode;
+ u64 isize;
+
+ if (!tree->mapping)
+ return;
+ inode = tree->mapping->host;
+ isize = i_size_read(inode);
if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
printk_ratelimited(KERN_DEBUG
- "btrfs: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
+ "BTRFS: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
caller, btrfs_ino(inode), isize, start, end);
}
}
static inline struct btrfs_fs_info *
tree_fs_info(struct extent_io_tree *tree)
{
+ if (!tree->mapping)
+ return NULL;
return btrfs_sb(tree->mapping->host->i_sb);
}
struct address_space *mapping)
{
tree->state = RB_ROOT;
- INIT_RADIX_TREE(&tree->buffer, GFP_ATOMIC);
tree->ops = NULL;
tree->dirty_bytes = 0;
spin_lock_init(&tree->lock);
- spin_lock_init(&tree->buffer_lock);
tree->mapping = mapping;
}
}
static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
- struct rb_node *node)
+ struct rb_node *node,
+ struct rb_node ***p_in,
+ struct rb_node **parent_in)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct tree_entry *entry;
+ if (p_in && parent_in) {
+ p = *p_in;
+ parent = *parent_in;
+ goto do_insert;
+ }
+
while (*p) {
parent = *p;
entry = rb_entry(parent, struct tree_entry, rb_node);
return parent;
}
+ do_insert:
rb_link_node(node, parent, p);
rb_insert_color(node, root);
return NULL;
}
static struct rb_node *__etree_search(struct extent_io_tree *tree, u64 offset,
- struct rb_node **prev_ret,
- struct rb_node **next_ret)
+ struct rb_node **prev_ret,
+ struct rb_node **next_ret,
+ struct rb_node ***p_ret,
+ struct rb_node **parent_ret)
{
struct rb_root *root = &tree->state;
- struct rb_node *n = root->rb_node;
+ struct rb_node **n = &root->rb_node;
struct rb_node *prev = NULL;
struct rb_node *orig_prev = NULL;
struct tree_entry *entry;
struct tree_entry *prev_entry = NULL;
- while (n) {
- entry = rb_entry(n, struct tree_entry, rb_node);
- prev = n;
+ while (*n) {
+ prev = *n;
+ entry = rb_entry(prev, struct tree_entry, rb_node);
prev_entry = entry;
if (offset < entry->start)
- n = n->rb_left;
+ n = &(*n)->rb_left;
else if (offset > entry->end)
- n = n->rb_right;
+ n = &(*n)->rb_right;
else
- return n;
+ return *n;
}
+ if (p_ret)
+ *p_ret = n;
+ if (parent_ret)
+ *parent_ret = prev;
+
if (prev_ret) {
orig_prev = prev;
while (prev && offset > prev_entry->end) {
return NULL;
}
- static inline struct rb_node *tree_search(struct extent_io_tree *tree,
- u64 offset)
+ static inline struct rb_node *
+ tree_search_for_insert(struct extent_io_tree *tree,
+ u64 offset,
+ struct rb_node ***p_ret,
+ struct rb_node **parent_ret)
{
struct rb_node *prev = NULL;
struct rb_node *ret;
- ret = __etree_search(tree, offset, &prev, NULL);
+ ret = __etree_search(tree, offset, &prev, NULL, p_ret, parent_ret);
if (!ret)
return prev;
return ret;
}
+ static inline struct rb_node *tree_search(struct extent_io_tree *tree,
+ u64 offset)
+ {
+ return tree_search_for_insert(tree, offset, NULL, NULL);
+ }
+
static void merge_cb(struct extent_io_tree *tree, struct extent_state *new,
struct extent_state *other)
{
*/
static int insert_state(struct extent_io_tree *tree,
struct extent_state *state, u64 start, u64 end,
+ struct rb_node ***p,
+ struct rb_node **parent,
unsigned long *bits)
{
struct rb_node *node;
if (end < start)
- WARN(1, KERN_ERR "btrfs end < start %llu %llu\n",
+ WARN(1, KERN_ERR "BTRFS: end < start %llu %llu\n",
end, start);
state->start = start;
state->end = end;
set_state_bits(tree, state, bits);
- node = tree_insert(&tree->state, end, &state->rb_node);
+ node = tree_insert(&tree->state, end, &state->rb_node, p, parent);
if (node) {
struct extent_state *found;
found = rb_entry(node, struct extent_state, rb_node);
- printk(KERN_ERR "btrfs found node %llu %llu on insert of "
+ printk(KERN_ERR "BTRFS: found node %llu %llu on insert of "
"%llu %llu\n",
found->start, found->end, start, end);
return -EEXIST;
prealloc->state = orig->state;
orig->start = split;
- node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node);
+ node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node,
+ NULL, NULL);
if (node) {
free_extent_state(prealloc);
return -EEXIST;
int err;
int clear = 0;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
if (bits & EXTENT_DELALLOC)
bits |= EXTENT_NORESERVE;
struct extent_state *state;
struct rb_node *node;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
spin_lock(&tree->lock);
again:
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct rb_node *node;
+ struct rb_node **p;
+ struct rb_node *parent;
int err = 0;
u64 last_start;
u64 last_end;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
bits |= EXTENT_FIRST_DELALLOC;
again:
* this search will find all the extents that end after
* our range starts.
*/
- node = tree_search(tree, start);
+ node = tree_search_for_insert(tree, start, &p, &parent);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
BUG_ON(!prealloc);
- err = insert_state(tree, prealloc, start, end, &bits);
+ err = insert_state(tree, prealloc, start, end,
+ &p, &parent, &bits);
if (err)
extent_io_tree_panic(tree, err);
+ cache_state(prealloc, cached_state);
prealloc = NULL;
goto out;
}
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- &bits);
+ NULL, NULL, &bits);
if (err)
extent_io_tree_panic(tree, err);
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct rb_node *node;
+ struct rb_node **p;
+ struct rb_node *parent;
int err = 0;
u64 last_start;
u64 last_end;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
again:
if (!prealloc && (mask & __GFP_WAIT)) {
* this search will find all the extents that end after
* our range starts.
*/
- node = tree_search(tree, start);
+ node = tree_search_for_insert(tree, start, &p, &parent);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
if (!prealloc) {
err = -ENOMEM;
goto out;
}
- err = insert_state(tree, prealloc, start, end, &bits);
- prealloc = NULL;
+ err = insert_state(tree, prealloc, start, end,
+ &p, &parent, &bits);
if (err)
extent_io_tree_panic(tree, err);
+ cache_state(prealloc, cached_state);
+ prealloc = NULL;
goto out;
}
state = rb_entry(node, struct extent_state, rb_node);
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- &bits);
+ NULL, NULL, &bits);
if (err)
extent_io_tree_panic(tree, err);
cache_state(prealloc, cached_state);
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
if (!bio)
return -EIO;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
map_length = length;
ret = btrfs_map_block(fs_info, WRITE, logical,
}
BUG_ON(mirror_num != bbio->mirror_num);
sector = bbio->stripes[mirror_num-1].physical >> 9;
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
dev = bbio->stripes[mirror_num-1].dev;
kfree(bbio);
if (!dev || !dev->bdev || !dev->writeable) {
return -EIO;
}
- printk_ratelimited_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu "
- "(dev %s sector %llu)\n", page->mapping->host->i_ino,
- start, rcu_str_deref(dev->name), sector);
+ printk_ratelimited_in_rcu(KERN_INFO
+ "BTRFS: read error corrected: ino %lu off %llu "
+ "(dev %s sector %llu)\n", page->mapping->host->i_ino,
+ start, rcu_str_deref(dev->name), sector);
bio_put(bio);
return 0;
return -EIO;
}
- if (em->start > start || em->start + em->len < start) {
+ if (em->start > start || em->start + em->len <= start) {
free_extent_map(em);
em = NULL;
}
return -EIO;
}
bio->bi_end_io = failed_bio->bi_end_io;
- bio->bi_sector = failrec->logical >> 9;
+ bio->bi_iter.bi_sector = failrec->logical >> 9;
bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
btrfs_failed_bio = btrfs_io_bio(failed_bio);
if (btrfs_failed_bio->csum) {
*/
static void end_bio_extent_writepage(struct bio *bio, int err)
{
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
- struct extent_io_tree *tree;
u64 start;
u64 end;
+ int i;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
/* We always issue full-page reads, but if some block
* in a page fails to read, blk_update_request() will
* advance bv_offset and adjust bv_len to compensate.
* Print a warning for nonzero offsets, and an error
* if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE)
- printk("%s page write in btrfs with offset %u and length %u\n",
- bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE
- ? KERN_ERR "partial" : KERN_INFO "incomplete",
- bvec->bv_offset, bvec->bv_len);
+ if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
+ "partial page write in btrfs with offset %u and length %u",
+ bvec->bv_offset, bvec->bv_len);
+ else
+ btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
+ "incomplete page write in btrfs with offset %u and "
+ "length %u",
+ bvec->bv_offset, bvec->bv_len);
+ }
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
if (end_extent_writepage(page, err, start, end))
continue;
end_page_writeback(page);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
}
*/
static void end_bio_extent_readpage(struct bio *bio, int err)
{
+ struct bio_vec *bvec;
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct bio_vec *bvec = bio->bi_io_vec;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct extent_io_tree *tree;
u64 offset = 0;
u64 extent_len = 0;
int mirror;
int ret;
+ int i;
if (err)
uptodate = 0;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
struct inode *inode = page->mapping->host;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
- "mirror=%lu\n", (u64)bio->bi_sector, err,
+ "mirror=%lu\n", (u64)bio->bi_iter.bi_sector, err,
io_bio->mirror_num);
tree = &BTRFS_I(inode)->io_tree;
* advance bv_offset and adjust bv_len to compensate.
* Print a warning for nonzero offsets, and an error
* if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE)
- printk("%s page read in btrfs with offset %u and length %u\n",
- bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE
- ? KERN_ERR "partial" : KERN_INFO "incomplete",
- bvec->bv_offset, bvec->bv_len);
+ if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
+ "partial page read in btrfs with offset %u and length %u",
+ bvec->bv_offset, bvec->bv_len);
+ else
+ btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
+ "incomplete page read in btrfs with offset %u and "
+ "length %u",
+ bvec->bv_offset, bvec->bv_len);
+ }
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
len = bvec->bv_len;
- if (++bvec <= bvec_end)
- prefetchw(&bvec->bv_page->flags);
-
mirror = io_bio->mirror_num;
if (likely(uptodate && tree->ops &&
tree->ops->readpage_end_io_hook)) {
extent_start = start;
extent_len = end + 1 - start;
}
- } while (bvec <= bvec_end);
+ }
if (extent_len)
endio_readpage_release_extent(tree, extent_start, extent_len,
}
if (bio) {
- bio->bi_size = 0;
bio->bi_bdev = bdev;
- bio->bi_sector = first_sector;
+ bio->bi_iter.bi_sector = first_sector;
btrfs_bio = btrfs_io_bio(bio);
btrfs_bio->csum = NULL;
btrfs_bio->csum_allocated = NULL;
if (bio_ret && *bio_ret) {
bio = *bio_ret;
if (old_compressed)
- contig = bio->bi_sector == sector;
+ contig = bio->bi_iter.bi_sector == sector;
else
contig = bio_end_sector(bio) == sector;
set_range_writeback(tree, cur, cur + iosize - 1);
if (!PageWriteback(page)) {
- printk(KERN_ERR "btrfs warning page %lu not "
- "writeback, cur %llu end %llu\n",
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "page %lu not writeback, cur %llu end %llu",
page->index, cur, end);
}
static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
{
- int uptodate = err == 0;
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
struct extent_buffer *eb;
- int done;
+ int i, done;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- bvec--;
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
done = atomic_dec_and_test(&eb->io_pages);
- if (!uptodate || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+ if (err || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
ClearPageUptodate(page);
SetPageError(page);
continue;
end_extent_buffer_writeback(eb);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
-
}
static int write_one_eb(struct extent_buffer *eb,
struct extent_page_data *epd)
{
struct block_device *bdev = fs_info->fs_devices->latest_bdev;
+ struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
u64 offset = eb->start;
unsigned long i, num_pages;
unsigned long bio_flags = 0;
clear_page_dirty_for_io(p);
set_page_writeback(p);
- ret = submit_extent_page(rw, eb->tree, p, offset >> 9,
+ ret = submit_extent_page(rw, tree, p, offset >> 9,
PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
-1, end_bio_extent_buffer_writepage,
0, epd->bio_flags, bio_flags);
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
struct btrfs_path *path;
- struct btrfs_file_extent_item *item;
int end = 0;
u64 em_start = 0;
u64 em_len = 0;
u64 em_end = 0;
- unsigned long emflags;
if (len == 0)
return -EINVAL;
}
WARN_ON(!ret);
path->slots[0]--;
- item = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
offset_in_extent = em_start - em->start;
em_end = extent_map_end(em);
em_len = em_end - em_start;
- emflags = em->flags;
disko = 0;
flags = 0;
__free_extent_buffer(eb);
}
- static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
- u64 start,
- unsigned long len,
- gfp_t mask)
+ static struct extent_buffer *
+ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
+ unsigned long len, gfp_t mask)
{
struct extent_buffer *eb = NULL;
return NULL;
eb->start = start;
eb->len = len;
- eb->tree = tree;
+ eb->fs_info = fs_info;
eb->bflags = 0;
rwlock_init(&eb->lock);
atomic_set(&eb->write_locks, 0);
}
}
- struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
- u64 start)
+ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
+ u64 start)
{
struct extent_buffer *eb;
rcu_read_lock();
- eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> PAGE_CACHE_SHIFT);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
mark_extent_buffer_accessed(eb);
return NULL;
}
- struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
+ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, unsigned long len)
{
unsigned long num_pages = num_extent_pages(start, len);
struct extent_buffer *eb;
struct extent_buffer *exists = NULL;
struct page *p;
- struct address_space *mapping = tree->mapping;
+ struct address_space *mapping = fs_info->btree_inode->i_mapping;
int uptodate = 1;
int ret;
-
- eb = find_extent_buffer(tree, start);
+ eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
- eb = __alloc_extent_buffer(tree, start, len, GFP_NOFS);
+ eb = __alloc_extent_buffer(fs_info, start, len, GFP_NOFS);
if (!eb)
return NULL;
if (ret)
goto free_eb;
- spin_lock(&tree->buffer_lock);
- ret = radix_tree_insert(&tree->buffer, start >> PAGE_CACHE_SHIFT, eb);
- spin_unlock(&tree->buffer_lock);
+ spin_lock(&fs_info->buffer_lock);
+ ret = radix_tree_insert(&fs_info->buffer_radix,
+ start >> PAGE_CACHE_SHIFT, eb);
+ spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
- exists = find_extent_buffer(tree, start);
+ exists = find_extent_buffer(fs_info, start);
if (exists)
goto free_eb;
else
}
/* add one reference for the tree */
check_buffer_tree_ref(eb);
+ set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
/*
* there is a race where release page may have
{
WARN_ON(atomic_read(&eb->refs) == 0);
if (atomic_dec_and_test(&eb->refs)) {
- if (test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags)) {
- spin_unlock(&eb->refs_lock);
- } else {
- struct extent_io_tree *tree = eb->tree;
+ if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
+ struct btrfs_fs_info *fs_info = eb->fs_info;
spin_unlock(&eb->refs_lock);
- spin_lock(&tree->buffer_lock);
- radix_tree_delete(&tree->buffer,
+ spin_lock(&fs_info->buffer_lock);
+ radix_tree_delete(&fs_info->buffer_radix,
eb->start >> PAGE_CACHE_SHIFT);
- spin_unlock(&tree->buffer_lock);
+ spin_unlock(&fs_info->buffer_lock);
+ } else {
+ spin_unlock(&eb->refs_lock);
}
/* Should be safe to release our pages at this point */
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus src_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
"len %lu dst len %lu\n", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus dst_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
"len %lu dst len %lu\n", dst_offset, len, dst->len);
BUG_ON(1);
}
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus src_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
"len %lu len %lu\n", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus dst_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
"len %lu len %lu\n", dst_offset, len, dst->len);
BUG_ON(1);
}
if (!path)
return -ENOMEM;
- nblocks = bio->bi_size >> inode->i_sb->s_blocksize_bits;
+ nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits;
if (!dst) {
if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
btrfs_bio->csum_allocated = kmalloc(nblocks * csum_size,
csum = (u8 *)dst;
}
- if (bio->bi_size > PAGE_CACHE_SIZE * 8)
+ if (bio->bi_iter.bi_size > PAGE_CACHE_SIZE * 8)
path->reada = 2;
WARN_ON(bio->bi_vcnt <= 0);
path->skip_locking = 1;
}
- disk_bytenr = (u64)bio->bi_sector << 9;
+ disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
if (dio)
offset = logical_offset;
while (bio_index < bio->bi_vcnt) {
offset + bvec->bv_len - 1,
EXTENT_NODATASUM, GFP_NOFS);
} else {
- printk(KERN_INFO "btrfs no csum found "
- "for inode %llu start %llu\n",
+ btrfs_info(BTRFS_I(inode)->root->fs_info,
+ "no csum found for inode %llu start %llu",
btrfs_ino(inode), offset);
}
item = NULL;
struct btrfs_dio_private *dip, struct bio *bio,
u64 offset)
{
- int len = (bio->bi_sector << 9) - dip->disk_bytenr;
+ int len = (bio->bi_iter.bi_sector << 9) - dip->disk_bytenr;
u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
int ret;
u64 offset;
WARN_ON(bio->bi_vcnt <= 0);
- sums = kzalloc(btrfs_ordered_sum_size(root, bio->bi_size), GFP_NOFS);
+ sums = kzalloc(btrfs_ordered_sum_size(root, bio->bi_iter.bi_size),
+ GFP_NOFS);
if (!sums)
return -ENOMEM;
- sums->len = bio->bi_size;
+ sums->len = bio->bi_iter.bi_size;
INIT_LIST_HEAD(&sums->list);
if (contig)
ordered = btrfs_lookup_ordered_extent(inode, offset);
BUG_ON(!ordered); /* Logic error */
- sums->bytenr = (u64)bio->bi_sector << 9;
+ sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
index = 0;
while (bio_index < bio->bi_vcnt) {
btrfs_add_ordered_sum(inode, ordered, sums);
btrfs_put_ordered_extent(ordered);
- bytes_left = bio->bi_size - total_bytes;
+ bytes_left = bio->bi_iter.bi_size - total_bytes;
sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
GFP_NOFS);
sums->len = bytes_left;
ordered = btrfs_lookup_ordered_extent(inode, offset);
BUG_ON(!ordered); /* Logic error */
- sums->bytenr = ((u64)bio->bi_sector << 9) +
+ sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
total_bytes;
index = 0;
}
#include "inode-map.h"
#include "backref.h"
#include "hash.h"
+ #include "props.h"
struct btrfs_iget_args {
- u64 ino;
+ struct btrfs_key *location;
struct btrfs_root *root;
};
* no overlapping inline items exist in the btree
*/
static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_path *path, int extent_inserted,
struct btrfs_root *root, struct inode *inode,
u64 start, size_t size, size_t compressed_size,
int compress_type,
struct page **compressed_pages)
{
- struct btrfs_key key;
- struct btrfs_path *path;
struct extent_buffer *leaf;
struct page *page = NULL;
char *kaddr;
int err = 0;
int ret;
size_t cur_size = size;
- size_t datasize;
unsigned long offset;
if (compressed_size && compressed_pages)
cur_size = compressed_size;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ inode_add_bytes(inode, size);
- path->leave_spinning = 1;
+ if (!extent_inserted) {
+ struct btrfs_key key;
+ size_t datasize;
- key.objectid = btrfs_ino(inode);
- key.offset = start;
- btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
- datasize = btrfs_file_extent_calc_inline_size(cur_size);
+ key.objectid = btrfs_ino(inode);
+ key.offset = start;
+ btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
- inode_add_bytes(inode, size);
- ret = btrfs_insert_empty_item(trans, root, path, &key,
- datasize);
- if (ret) {
- err = ret;
- goto fail;
+ datasize = btrfs_file_extent_calc_inline_size(cur_size);
+ path->leave_spinning = 1;
+ ret = btrfs_insert_empty_item(trans, root, path, &key,
+ datasize);
+ if (ret) {
+ err = ret;
+ goto fail;
+ }
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
page_cache_release(page);
}
btrfs_mark_buffer_dirty(leaf);
- btrfs_free_path(path);
+ btrfs_release_path(path);
/*
* we're an inline extent, so nobody can
return ret;
fail:
- btrfs_free_path(path);
return err;
}
u64 aligned_end = ALIGN(end, root->sectorsize);
u64 data_len = inline_len;
int ret;
+ struct btrfs_path *path;
+ int extent_inserted = 0;
+ u32 extent_item_size;
if (compressed_size)
data_len = compressed_size;
return 1;
}
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
+ btrfs_free_path(path);
return PTR_ERR(trans);
+ }
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
- ret = btrfs_drop_extents(trans, root, inode, start, aligned_end, 1);
+ if (compressed_size && compressed_pages)
+ extent_item_size = btrfs_file_extent_calc_inline_size(
+ compressed_size);
+ else
+ extent_item_size = btrfs_file_extent_calc_inline_size(
+ inline_len);
+
+ ret = __btrfs_drop_extents(trans, root, inode, path,
+ start, aligned_end, NULL,
+ 1, 1, extent_item_size, &extent_inserted);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto out;
if (isize > actual_end)
inline_len = min_t(u64, isize, actual_end);
- ret = insert_inline_extent(trans, root, inode, start,
+ ret = insert_inline_extent(trans, path, extent_inserted,
+ root, inode, start,
inline_len, compressed_size,
compress_type, compressed_pages);
if (ret && ret != -ENOSPC) {
btrfs_delalloc_release_metadata(inode, end + 1 - start);
btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
out:
+ btrfs_free_path(path);
btrfs_end_transaction(trans, root);
return ret;
}
nocow = 1;
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
extent_end = found_key.offset +
- btrfs_file_extent_inline_len(leaf, fi);
+ btrfs_file_extent_inline_len(leaf,
+ path->slots[0], fi);
extent_end = ALIGN(extent_end, root->sectorsize);
} else {
BUG_ON(1);
unsigned long bio_flags)
{
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
- u64 logical = (u64)bio->bi_sector << 9;
+ u64 logical = (u64)bio->bi_iter.bi_sector << 9;
u64 length = 0;
u64 map_length;
int ret;
if (bio_flags & EXTENT_BIO_COMPRESSED)
return 0;
- length = bio->bi_size;
+ length = bio->bi_iter.bi_size;
map_length = length;
ret = btrfs_map_block(root->fs_info, rw, logical,
&map_length, NULL, 0);
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_key ins;
+ int extent_inserted = 0;
int ret;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
- path->leave_spinning = 1;
-
/*
* we may be replacing one extent in the tree with another.
* The new extent is pinned in the extent map, and we don't want
* the caller is expected to unpin it and allow it to be merged
* with the others.
*/
- ret = btrfs_drop_extents(trans, root, inode, file_pos,
- file_pos + num_bytes, 0);
+ ret = __btrfs_drop_extents(trans, root, inode, path, file_pos,
+ file_pos + num_bytes, NULL, 0,
+ 1, sizeof(*fi), &extent_inserted);
if (ret)
goto out;
- ins.objectid = btrfs_ino(inode);
- ins.offset = file_pos;
- ins.type = BTRFS_EXTENT_DATA_KEY;
- ret = btrfs_insert_empty_item(trans, root, path, &ins, sizeof(*fi));
- if (ret)
- goto out;
+ if (!extent_inserted) {
+ ins.objectid = btrfs_ino(inode);
+ ins.offset = file_pos;
+ ins.type = BTRFS_EXTENT_DATA_KEY;
+
+ path->leave_spinning = 1;
+ ret = btrfs_insert_empty_item(trans, root, path, &ins,
+ sizeof(*fi));
+ if (ret)
+ goto out;
+ }
leaf = path->nodes[0];
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
u64 extent_len;
struct btrfs_key found_key;
- ret = btrfs_search_slot(trans, root, &key, path, 1, 1);
+ ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (ret < 0)
goto out_free_path;
return NULL;
}
- /*
- * helper function for btrfs_finish_ordered_io, this
- * just reads in some of the csum leaves to prime them into ram
- * before we start the transaction. It limits the amount of btree
- * reads required while inside the transaction.
- */
/* as ordered data IO finishes, this gets called so we can finish
* an ordered extent if the range of bytes in the file it covers are
* fully written.
* slot is the slot the inode is in, objectid is the objectid of the inode
*/
static noinline int acls_after_inode_item(struct extent_buffer *leaf,
- int slot, u64 objectid)
+ int slot, u64 objectid,
+ int *first_xattr_slot)
{
u32 nritems = btrfs_header_nritems(leaf);
struct btrfs_key found_key;
}
slot++;
+ *first_xattr_slot = -1;
while (slot < nritems) {
btrfs_item_key_to_cpu(leaf, &found_key, slot);
/* we found an xattr, assume we've got an acl */
if (found_key.type == BTRFS_XATTR_ITEM_KEY) {
+ if (*first_xattr_slot == -1)
+ *first_xattr_slot = slot;
if (found_key.offset == xattr_access ||
found_key.offset == xattr_default)
return 1;
* something larger than an xattr. We have to assume the inode
* has acls
*/
+ if (*first_xattr_slot == -1)
+ *first_xattr_slot = slot;
return 1;
}
struct btrfs_timespec *tspec;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_key location;
+ unsigned long ptr;
int maybe_acls;
u32 rdev;
int ret;
bool filled = false;
+ int first_xattr_slot;
ret = btrfs_fill_inode(inode, &rdev);
if (!ret)
if (!path)
goto make_bad;
- path->leave_spinning = 1;
memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
leaf = path->nodes[0];
if (filled)
- goto cache_acl;
+ goto cache_index;
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
BTRFS_I(inode)->index_cnt = (u64)-1;
BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
+
+ cache_index:
+ path->slots[0]++;
+ if (inode->i_nlink != 1 ||
+ path->slots[0] >= btrfs_header_nritems(leaf))
+ goto cache_acl;
+
+ btrfs_item_key_to_cpu(leaf, &location, path->slots[0]);
+ if (location.objectid != btrfs_ino(inode))
+ goto cache_acl;
+
+ ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+ if (location.type == BTRFS_INODE_REF_KEY) {
+ struct btrfs_inode_ref *ref;
+
+ ref = (struct btrfs_inode_ref *)ptr;
+ BTRFS_I(inode)->dir_index = btrfs_inode_ref_index(leaf, ref);
+ } else if (location.type == BTRFS_INODE_EXTREF_KEY) {
+ struct btrfs_inode_extref *extref;
+
+ extref = (struct btrfs_inode_extref *)ptr;
+ BTRFS_I(inode)->dir_index = btrfs_inode_extref_index(leaf,
+ extref);
+ }
cache_acl:
/*
* try to precache a NULL acl entry for files that don't have
* any xattrs or acls
*/
maybe_acls = acls_after_inode_item(leaf, path->slots[0],
- btrfs_ino(inode));
+ btrfs_ino(inode), &first_xattr_slot);
+ if (first_xattr_slot != -1) {
+ path->slots[0] = first_xattr_slot;
+ ret = btrfs_load_inode_props(inode, path);
+ if (ret)
+ btrfs_err(root->fs_info,
+ "error loading props for ino %llu (root %llu): %d\n",
+ btrfs_ino(inode),
+ root->root_key.objectid, ret);
+ }
+ btrfs_free_path(path);
+
if (!maybe_acls)
cache_no_acl(inode);
- btrfs_free_path(path);
-
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &btrfs_aops;
goto failed;
}
- btrfs_unlock_up_safe(path, 1);
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
goto err;
btrfs_release_path(path);
+ /*
+ * If we don't have dir index, we have to get it by looking up
+ * the inode ref, since we get the inode ref, remove it directly,
+ * it is unnecessary to do delayed deletion.
+ *
+ * But if we have dir index, needn't search inode ref to get it.
+ * Since the inode ref is close to the inode item, it is better
+ * that we delay to delete it, and just do this deletion when
+ * we update the inode item.
+ */
+ if (BTRFS_I(inode)->dir_index) {
+ ret = btrfs_delayed_delete_inode_ref(inode);
+ if (!ret) {
+ index = BTRFS_I(inode)->dir_index;
+ goto skip_backref;
+ }
+ }
+
ret = btrfs_del_inode_ref(trans, root, name, name_len, ino,
dir_ino, &index);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto err;
}
-
+ skip_backref:
ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
btrfs_file_extent_num_bytes(leaf, fi);
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
item_end += btrfs_file_extent_inline_len(leaf,
- fi);
+ path->slots[0], fi);
}
item_end--;
}
inode_sub_bytes(inode, item_end + 1 -
new_size);
}
+
+ /*
+ * update the ram bytes to properly reflect
+ * the new size of our item
+ */
+ btrfs_set_file_extent_ram_bytes(leaf, fi, size);
size =
btrfs_file_extent_calc_inline_size(size);
btrfs_truncate_item(root, path, size, 1);
return ret;
}
+ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode,
+ u64 offset, u64 len)
+ {
+ struct btrfs_trans_handle *trans;
+ int ret;
+
+ /*
+ * Still need to make sure the inode looks like it's been updated so
+ * that any holes get logged if we fsync.
+ */
+ if (btrfs_fs_incompat(root->fs_info, NO_HOLES)) {
+ BTRFS_I(inode)->last_trans = root->fs_info->generation;
+ BTRFS_I(inode)->last_sub_trans = root->log_transid;
+ BTRFS_I(inode)->last_log_commit = root->last_log_commit;
+ return 0;
+ }
+
+ /*
+ * 1 - for the one we're dropping
+ * 1 - for the one we're adding
+ * 1 - for updating the inode.
+ */
+ trans = btrfs_start_transaction(root, 3);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ ret = btrfs_drop_extents(trans, root, inode, offset, offset + len, 1);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ btrfs_end_transaction(trans, root);
+ return ret;
+ }
+
+ ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset,
+ 0, 0, len, 0, len, 0, 0, 0);
+ if (ret)
+ btrfs_abort_transaction(trans, root, ret);
+ else
+ btrfs_update_inode(trans, root, inode);
+ btrfs_end_transaction(trans, root);
+ return ret;
+ }
+
/*
* This function puts in dummy file extents for the area we're creating a hole
* for. So if we are truncating this file to a larger size we need to insert
*/
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
{
- struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_map *em = NULL;
struct extent_map *hole_em;
hole_size = last_byte - cur_offset;
- trans = btrfs_start_transaction(root, 3);
- if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
- break;
- }
-
- err = btrfs_drop_extents(trans, root, inode,
- cur_offset,
- cur_offset + hole_size, 1);
- if (err) {
- btrfs_abort_transaction(trans, root, err);
- btrfs_end_transaction(trans, root);
- break;
- }
-
- err = btrfs_insert_file_extent(trans, root,
- btrfs_ino(inode), cur_offset, 0,
- 0, hole_size, 0, hole_size,
- 0, 0, 0);
- if (err) {
- btrfs_abort_transaction(trans, root, err);
- btrfs_end_transaction(trans, root);
+ err = maybe_insert_hole(root, inode, cur_offset,
+ hole_size);
+ if (err)
break;
- }
-
btrfs_drop_extent_cache(inode, cur_offset,
cur_offset + hole_size - 1, 0);
hole_em = alloc_extent_map();
hole_em->ram_bytes = hole_size;
hole_em->bdev = root->fs_info->fs_devices->latest_bdev;
hole_em->compress_type = BTRFS_COMPRESS_NONE;
- hole_em->generation = trans->transid;
+ hole_em->generation = root->fs_info->generation;
while (1) {
write_lock(&em_tree->lock);
hole_size - 1, 0);
}
free_extent_map(hole_em);
- next:
- btrfs_update_inode(trans, root, inode);
- btrfs_end_transaction(trans, root);
}
+ next:
free_extent_map(em);
em = NULL;
cur_offset = last_byte;
if (cur_offset >= block_end)
break;
}
-
free_extent_map(em);
unlock_extent_cached(io_tree, hole_start, block_end - 1, &cached_state,
GFP_NOFS);
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
- if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
- inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+ if (newsize != oldsize) {
+ inode_inc_iversion(inode);
+ if (!(mask & (ATTR_CTIME | ATTR_MTIME)))
+ inode->i_ctime = inode->i_mtime =
+ current_fs_time(inode->i_sb);
+ }
if (newsize > oldsize) {
truncate_pagecache(inode, newsize);
err = btrfs_dirty_inode(inode);
if (!err && attr->ia_valid & ATTR_MODE)
- err = btrfs_acl_chmod(inode);
+ err = posix_acl_chmod(inode, inode->i_mode);
}
return err;
}
+ /*
+ * While truncating the inode pages during eviction, we get the VFS calling
+ * btrfs_invalidatepage() against each page of the inode. This is slow because
+ * the calls to btrfs_invalidatepage() result in a huge amount of calls to
+ * lock_extent_bits() and clear_extent_bit(), which keep merging and splitting
+ * extent_state structures over and over, wasting lots of time.
+ *
+ * Therefore if the inode is being evicted, let btrfs_invalidatepage() skip all
+ * those expensive operations on a per page basis and do only the ordered io
+ * finishing, while we release here the extent_map and extent_state structures,
+ * without the excessive merging and splitting.
+ */
+ static void evict_inode_truncate_pages(struct inode *inode)
+ {
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ struct extent_map_tree *map_tree = &BTRFS_I(inode)->extent_tree;
+ struct rb_node *node;
+
+ ASSERT(inode->i_state & I_FREEING);
+ truncate_inode_pages(&inode->i_data, 0);
+
+ write_lock(&map_tree->lock);
+ while (!RB_EMPTY_ROOT(&map_tree->map)) {
+ struct extent_map *em;
+
+ node = rb_first(&map_tree->map);
+ em = rb_entry(node, struct extent_map, rb_node);
+ clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+ clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+ remove_extent_mapping(map_tree, em);
+ free_extent_map(em);
+ }
+ write_unlock(&map_tree->lock);
+
+ spin_lock(&io_tree->lock);
+ while (!RB_EMPTY_ROOT(&io_tree->state)) {
+ struct extent_state *state;
+ struct extent_state *cached_state = NULL;
+
+ node = rb_first(&io_tree->state);
+ state = rb_entry(node, struct extent_state, rb_node);
+ atomic_inc(&state->refs);
+ spin_unlock(&io_tree->lock);
+
+ lock_extent_bits(io_tree, state->start, state->end,
+ 0, &cached_state);
+ clear_extent_bit(io_tree, state->start, state->end,
+ EXTENT_LOCKED | EXTENT_DIRTY |
+ EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 1,
+ &cached_state, GFP_NOFS);
+ free_extent_state(state);
+
+ spin_lock(&io_tree->lock);
+ }
+ spin_unlock(&io_tree->lock);
+ }
+
void btrfs_evict_inode(struct inode *inode)
{
struct btrfs_trans_handle *trans;
trace_btrfs_inode_evict(inode);
- truncate_inode_pages(&inode->i_data, 0);
+ evict_inode_truncate_pages(inode);
+
if (inode->i_nlink &&
((btrfs_root_refs(&root->root_item) != 0 &&
root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) ||
}
err = -ENOENT;
- ret = btrfs_find_root_ref(root->fs_info->tree_root, path,
- BTRFS_I(dir)->root->root_key.objectid,
- location->objectid);
+ ret = btrfs_find_item(root->fs_info->tree_root, path,
+ BTRFS_I(dir)->root->root_key.objectid,
+ location->objectid, BTRFS_ROOT_REF_KEY, NULL);
if (ret) {
if (ret < 0)
err = ret;
static int btrfs_init_locked_inode(struct inode *inode, void *p)
{
struct btrfs_iget_args *args = p;
- inode->i_ino = args->ino;
+ inode->i_ino = args->location->objectid;
+ memcpy(&BTRFS_I(inode)->location, args->location,
+ sizeof(*args->location));
BTRFS_I(inode)->root = args->root;
return 0;
}
static int btrfs_find_actor(struct inode *inode, void *opaque)
{
struct btrfs_iget_args *args = opaque;
- return args->ino == btrfs_ino(inode) &&
+ return args->location->objectid == BTRFS_I(inode)->location.objectid &&
args->root == BTRFS_I(inode)->root;
}
static struct inode *btrfs_iget_locked(struct super_block *s,
- u64 objectid,
+ struct btrfs_key *location,
struct btrfs_root *root)
{
struct inode *inode;
struct btrfs_iget_args args;
- unsigned long hashval = btrfs_inode_hash(objectid, root);
+ unsigned long hashval = btrfs_inode_hash(location->objectid, root);
- args.ino = objectid;
+ args.location = location;
args.root = root;
inode = iget5_locked(s, hashval, btrfs_find_actor,
{
struct inode *inode;
- inode = btrfs_iget_locked(s, location->objectid, root);
+ inode = btrfs_iget_locked(s, location, root);
if (!inode)
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
- BTRFS_I(inode)->root = root;
- memcpy(&BTRFS_I(inode)->location, location, sizeof(*location));
btrfs_read_locked_inode(inode);
if (!is_bad_inode(inode)) {
inode_tree_add(inode);
return ERR_PTR(ret);
if (location.objectid == 0)
- return NULL;
+ return ERR_PTR(-ENOENT);
if (location.type == BTRFS_INODE_ITEM_KEY) {
inode = btrfs_iget(dir->i_sb, &location, root, NULL);
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
- struct dentry *ret;
+ struct inode *inode;
- ret = d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
- return ret;
+ inode = btrfs_lookup_dentry(dir, dentry);
+ if (IS_ERR(inode)) {
+ if (PTR_ERR(inode) == -ENOENT)
+ inode = NULL;
+ else
+ return ERR_CAST(inode);
+ }
+
+ return d_splice_alias(inode, dentry);
}
unsigned char btrfs_filetype_table[] = {
u32 sizes[2];
unsigned long ptr;
int ret;
- int owner;
path = btrfs_alloc_path();
if (!path)
* number
*/
BTRFS_I(inode)->index_cnt = 2;
+ BTRFS_I(inode)->dir_index = *index;
BTRFS_I(inode)->root = root;
BTRFS_I(inode)->generation = trans->transid;
inode->i_generation = BTRFS_I(inode)->generation;
*/
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
- if (S_ISDIR(mode))
- owner = 0;
- else
- owner = 1;
-
key[0].objectid = objectid;
btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
key[0].offset = 0;
btrfs_update_root_times(trans, root);
+ ret = btrfs_inode_inherit_props(trans, inode, dir);
+ if (ret)
+ btrfs_err(root->fs_info,
+ "error inheriting props for ino %llu (root %llu): %d",
+ btrfs_ino(inode), root->root_key.objectid, ret);
+
return inode;
fail:
if (dir)
goto fail;
}
+ /* There are several dir indexes for this inode, clear the cache. */
+ BTRFS_I(inode)->dir_index = 0ULL;
inc_nlink(inode);
inode_inc_iversion(inode);
inode->i_ctime = CURRENT_TIME;
btrfs_file_extent_num_bytes(leaf, item);
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
size_t size;
- size = btrfs_file_extent_inline_len(leaf, item);
+ size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_end = ALIGN(extent_start + size, root->sectorsize);
}
next:
goto out;
}
- size = btrfs_file_extent_inline_len(leaf, item);
+ size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_offset = page_offset(page) + pg_offset - extent_start;
copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset,
size - extent_offset);
int slot;
int found_type;
bool nocow = (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW);
+
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
if (!nocow && found_type == BTRFS_FILE_EXTENT_REG)
goto out;
+ extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
+ if (extent_end <= offset)
+ goto out;
+
disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
if (disk_bytenr == 0)
goto out;
*ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
}
- extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
-
if (btrfs_extent_readonly(root, disk_bytenr))
goto out;
btrfs_release_path(path);
static void btrfs_endio_direct_read(struct bio *bio, int err)
{
struct btrfs_dio_private *dip = bio->bi_private;
- struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct bio_vec *bvec = bio->bi_io_vec;
+ struct bio_vec *bvec;
struct inode *inode = dip->inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct bio *dio_bio;
u32 *csums = (u32 *)dip->csum;
- int index = 0;
u64 start;
+ int i;
start = dip->logical_offset;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
struct page *page = bvec->bv_page;
char *kaddr;
local_irq_restore(flags);
flush_dcache_page(bvec->bv_page);
- if (csum != csums[index]) {
+ if (csum != csums[i]) {
btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
btrfs_ino(inode), start, csum,
- csums[index]);
+ csums[i]);
err = -EIO;
}
}
start += bvec->bv_len;
- bvec++;
- index++;
- } while (bvec <= bvec_end);
+ }
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
struct btrfs_dio_private *dip = bio->bi_private;
if (err) {
- printk(KERN_ERR "btrfs direct IO failed ino %llu rw %lu "
- "sector %#Lx len %u err no %d\n",
+ btrfs_err(BTRFS_I(dip->inode)->root->fs_info,
+ "direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
btrfs_ino(dip->inode), bio->bi_rw,
- (unsigned long long)bio->bi_sector, bio->bi_size, err);
+ (unsigned long long)bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size, err);
dip->errors = 1;
/*
struct bio *bio;
struct bio *orig_bio = dip->orig_bio;
struct bio_vec *bvec = orig_bio->bi_io_vec;
- u64 start_sector = orig_bio->bi_sector;
+ u64 start_sector = orig_bio->bi_iter.bi_sector;
u64 file_offset = dip->logical_offset;
u64 submit_len = 0;
u64 map_length;
int ret = 0;
int async_submit = 0;
- map_length = orig_bio->bi_size;
+ 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) {
return -EIO;
}
- if (map_length >= orig_bio->bi_size) {
+ if (map_length >= orig_bio->bi_iter.bi_size) {
bio = orig_bio;
goto submit;
}
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
- map_length = orig_bio->bi_size;
+ map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw,
start_sector << 9,
&map_length, NULL, 0);
if (!skip_sum && !write) {
csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
- sum_len = dio_bio->bi_size >> inode->i_sb->s_blocksize_bits;
+ sum_len = dio_bio->bi_iter.bi_size >>
+ inode->i_sb->s_blocksize_bits;
sum_len *= csum_size;
} else {
sum_len = 0;
dip->private = dio_bio->bi_private;
dip->inode = inode;
dip->logical_offset = file_offset;
- dip->bytes = dio_bio->bi_size;
- dip->disk_bytenr = (u64)dio_bio->bi_sector << 9;
+ dip->bytes = dio_bio->bi_iter.bi_size;
+ dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
io_bio->bi_private = dip;
dip->errors = 0;
dip->orig_bio = io_bio;
struct extent_state *cached_state = NULL;
u64 page_start = page_offset(page);
u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
+ int inode_evicting = inode->i_state & I_FREEING;
/*
* we have the page locked, so new writeback can't start,
btrfs_releasepage(page, GFP_NOFS);
return;
}
- lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
- ordered = btrfs_lookup_ordered_extent(inode, page_offset(page));
+
+ if (!inode_evicting)
+ lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
+ ordered = btrfs_lookup_ordered_extent(inode, page_start);
if (ordered) {
/*
* IO on this page will never be started, so we need
* to account for any ordered extents now
*/
- clear_extent_bit(tree, page_start, page_end,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 0, &cached_state, GFP_NOFS);
+ if (!inode_evicting)
+ clear_extent_bit(tree, page_start, page_end,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 0, &cached_state,
+ GFP_NOFS);
/*
* whoever cleared the private bit is responsible
* for the finish_ordered_io
btrfs_finish_ordered_io(ordered);
}
btrfs_put_ordered_extent(ordered);
- cached_state = NULL;
- lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
+ if (!inode_evicting) {
+ cached_state = NULL;
+ lock_extent_bits(tree, page_start, page_end, 0,
+ &cached_state);
+ }
+ }
+
+ if (!inode_evicting) {
+ clear_extent_bit(tree, page_start, page_end,
+ EXTENT_LOCKED | EXTENT_DIRTY |
+ EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 1,
+ &cached_state, GFP_NOFS);
+
+ __btrfs_releasepage(page, GFP_NOFS);
}
- clear_extent_bit(tree, page_start, page_end,
- EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
- &cached_state, GFP_NOFS);
- __btrfs_releasepage(page, GFP_NOFS);
ClearPageChecked(page);
if (PagePrivate(page)) {
* create a new subvolume directory/inode (helper for the ioctl).
*/
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
- struct btrfs_root *new_root, u64 new_dirid)
+ struct btrfs_root *new_root,
+ struct btrfs_root *parent_root,
+ u64 new_dirid)
{
struct inode *inode;
int err;
set_nlink(inode, 1);
btrfs_i_size_write(inode, 0);
+ err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
+ if (err)
+ btrfs_err(new_root->fs_info,
+ "error inheriting subvolume %llu properties: %d\n",
+ new_root->root_key.objectid, err);
+
err = btrfs_update_inode(trans, new_root, inode);
iput(inode);
ei->flags = 0;
ei->csum_bytes = 0;
ei->index_cnt = (u64)-1;
+ ei->dir_index = 0;
ei->last_unlink_trans = 0;
ei->last_log_commit = 0;
if (ret)
goto out_fail;
+ BTRFS_I(old_inode)->dir_index = 0ULL;
if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
/* force full log commit if subvolume involved. */
root->fs_info->last_trans_log_full_commit = trans->transid;
goto out_fail;
}
+ if (old_inode->i_nlink == 1)
+ BTRFS_I(old_inode)->dir_index = index;
+
if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
struct dentry *parent = new_dentry->d_parent;
btrfs_log_new_name(trans, old_inode, old_dir, parent);
{
int ret;
- if (root->fs_info->sb->s_flags & MS_RDONLY)
+ if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
return -EROFS;
ret = __start_delalloc_inodes(root, delay_iput);
struct list_head splice;
int ret;
- if (fs_info->sb->s_flags & MS_RDONLY)
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
INIT_LIST_HEAD(&splice);
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_dir_ro_inode_operations = {
.lookup = btrfs_lookup,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
.permission = btrfs_permission,
.fiemap = btrfs_fiemap,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_special_inode_operations = {
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.get_acl = btrfs_get_acl,
+ .set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_symlink_inode_operations = {
.getxattr = btrfs_getxattr,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
- .get_acl = btrfs_get_acl,
.update_time = btrfs_update_time,
};
#include "rcu-string.h"
#include "send.h"
#include "dev-replace.h"
+ #include "props.h"
+ #include "sysfs.h"
static int btrfs_clone(struct inode *src, struct inode *inode,
u64 off, u64 olen, u64 olen_aligned, u64 destoff);
unsigned int i_oldflags;
umode_t mode;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
if (btrfs_root_readonly(root))
return -EROFS;
if (ret)
return ret;
- if (!inode_owner_or_capable(inode))
- return -EACCES;
-
ret = mnt_want_write_file(file);
if (ret)
return ret;
if (flags & FS_NOCOMP_FL) {
ip->flags &= ~BTRFS_INODE_COMPRESS;
ip->flags |= BTRFS_INODE_NOCOMPRESS;
+
+ ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
+ if (ret && ret != -ENODATA)
+ goto out_drop;
} else if (flags & FS_COMPR_FL) {
+ const char *comp;
+
ip->flags |= BTRFS_INODE_COMPRESS;
ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
+
+ if (root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
+ comp = "lzo";
+ else
+ comp = "zlib";
+ ret = btrfs_set_prop(inode, "btrfs.compression",
+ comp, strlen(comp), 0);
+ if (ret)
+ goto out_drop;
+
} else {
ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
}
struct btrfs_root *new_root;
struct btrfs_block_rsv block_rsv;
struct timespec cur_time = CURRENT_TIME;
+ struct inode *inode;
int ret;
int err;
u64 objectid;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- goto out;
+ btrfs_subvolume_release_metadata(root, &block_rsv,
+ qgroup_reserved);
+ return ret;
}
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
btrfs_record_root_in_trans(trans, new_root);
- ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
+ ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid);
if (ret) {
/* We potentially lose an unused inode item here */
btrfs_abort_transaction(trans, root, ret);
fail:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
+ btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
+
if (async_transid) {
*async_transid = trans->transid;
err = btrfs_commit_transaction_async(trans, root, 1);
if (err && !ret)
ret = err;
- if (!ret)
- d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
- out:
- btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
+ if (!ret) {
+ inode = btrfs_lookup_dentry(dir, dentry);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+ d_instantiate(dentry, inode);
+ }
return ret;
}
ret = PTR_ERR(inode);
goto fail;
}
- BUG_ON(!inode);
+
d_instantiate(dentry, inode);
ret = 0;
fail:
static int cluster_pages_for_defrag(struct inode *inode,
struct page **pages,
unsigned long start_index,
- int num_pages)
+ unsigned long num_pages)
{
unsigned long file_end;
u64 isize = i_size_read(inode);
int defrag_count = 0;
int compress_type = BTRFS_COMPRESS_ZLIB;
int extent_thresh = range->extent_thresh;
- int max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
- int cluster = max_cluster;
+ unsigned long max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
+ unsigned long cluster = max_cluster;
u64 new_align = ~((u64)128 * 1024 - 1);
struct page **pages = NULL;
break;
if (btrfs_defrag_cancelled(root->fs_info)) {
- printk(KERN_DEBUG "btrfs: defrag_file cancelled\n");
+ printk(KERN_DEBUG "BTRFS: defrag_file cancelled\n");
ret = -EAGAIN;
break;
}
ret = -EINVAL;
goto out_free;
}
- printk(KERN_INFO "btrfs: resizing devid %llu\n", devid);
+ btrfs_info(root->fs_info, "resizing devid %llu", devid);
}
device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
if (!device) {
- printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
+ btrfs_info(root->fs_info, "resizer unable to find device %llu",
devid);
ret = -ENODEV;
goto out_free;
}
if (!device->writeable) {
- printk(KERN_INFO "btrfs: resizer unable to apply on "
- "readonly device %llu\n",
+ btrfs_info(root->fs_info,
+ "resizer unable to apply on readonly device %llu",
devid);
ret = -EPERM;
goto out_free;
}
new_size = old_size - new_size;
} else if (mod > 0) {
+ if (new_size > ULLONG_MAX - old_size) {
+ ret = -EINVAL;
+ goto out_free;
+ }
new_size = old_size + new_size;
}
do_div(new_size, root->sectorsize);
new_size *= root->sectorsize;
- printk_in_rcu(KERN_INFO "btrfs: new size for %s is %llu\n",
+ printk_in_rcu(KERN_INFO "BTRFS: new size for %s is %llu\n",
rcu_str_deref(device->name), new_size);
if (new_size > old_size) {
src_inode = file_inode(src.file);
if (src_inode->i_sb != file_inode(file)->i_sb) {
- printk(KERN_INFO "btrfs: Snapshot src from "
- "another FS\n");
+ btrfs_info(BTRFS_I(src_inode)->root->fs_info,
+ "Snapshot src from another FS");
ret = -EINVAL;
+ } else if (!inode_owner_or_capable(src_inode)) {
+ /*
+ * Subvolume creation is not restricted, but snapshots
+ * are limited to own subvolumes only
+ */
+ ret = -EPERM;
} else {
ret = btrfs_mksubvol(&file->f_path, name, namelen,
BTRFS_I(src_inode)->root,
u64 flags;
int ret = 0;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
ret = mnt_want_write_file(file);
if (ret)
goto out;
goto out_drop_write;
}
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out_drop_write;
- }
-
down_write(&root->fs_info->subvol_sem);
/* nothing to do */
goto out_drop_sem;
root_flags = btrfs_root_flags(&root->root_item);
- if (flags & BTRFS_SUBVOL_RDONLY)
+ if (flags & BTRFS_SUBVOL_RDONLY) {
btrfs_set_root_flags(&root->root_item,
root_flags | BTRFS_ROOT_SUBVOL_RDONLY);
- else
- btrfs_set_root_flags(&root->root_item,
+ } else {
+ /*
+ * Block RO -> RW transition if this subvolume is involved in
+ * send
+ */
+ spin_lock(&root->root_item_lock);
+ if (root->send_in_progress == 0) {
+ btrfs_set_root_flags(&root->root_item,
root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);
+ spin_unlock(&root->root_item_lock);
+ } else {
+ spin_unlock(&root->root_item_lock);
+ btrfs_warn(root->fs_info,
+ "Attempt to set subvolume %llu read-write during send",
+ root->root_key.objectid);
+ ret = -EPERM;
+ goto out_drop_sem;
+ }
+ }
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
key.offset = (u64)-1;
root = btrfs_read_fs_root_no_name(info, &key);
if (IS_ERR(root)) {
- printk(KERN_ERR "could not find root %llu\n",
+ printk(KERN_ERR "BTRFS: could not find root %llu\n",
sk->tree_id);
btrfs_free_path(path);
return -ENOENT;
key.offset = (u64)-1;
root = btrfs_read_fs_root_no_name(info, &key);
if (IS_ERR(root)) {
- printk(KERN_ERR "could not find root %llu\n", tree_id);
+ printk(KERN_ERR "BTRFS: could not find root %llu\n", tree_id);
ret = -ENOENT;
goto out;
}
#define BTRFS_MAX_DEDUPE_LEN (16 * 1024 * 1024)
static long btrfs_ioctl_file_extent_same(struct file *file,
- void __user *argp)
+ struct btrfs_ioctl_same_args __user *argp)
{
- struct btrfs_ioctl_same_args tmp;
struct btrfs_ioctl_same_args *same;
struct btrfs_ioctl_same_extent_info *info;
- struct inode *src = file->f_dentry->d_inode;
- struct file *dst_file = NULL;
- struct inode *dst;
+ struct inode *src = file_inode(file);
u64 off;
u64 len;
int i;
unsigned long size;
u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
bool is_admin = capable(CAP_SYS_ADMIN);
+ u16 count;
if (!(file->f_mode & FMODE_READ))
return -EINVAL;
if (ret)
return ret;
- if (copy_from_user(&tmp,
- (struct btrfs_ioctl_same_args __user *)argp,
- sizeof(tmp))) {
+ if (get_user(count, &argp->dest_count)) {
ret = -EFAULT;
goto out;
}
- size = sizeof(tmp) +
- tmp.dest_count * sizeof(struct btrfs_ioctl_same_extent_info);
+ size = offsetof(struct btrfs_ioctl_same_args __user, info[count]);
- same = memdup_user((struct btrfs_ioctl_same_args __user *)argp, size);
+ same = memdup_user(argp, size);
if (IS_ERR(same)) {
ret = PTR_ERR(same);
goto out;
/* pre-format output fields to sane values */
- for (i = 0; i < same->dest_count; i++) {
+ for (i = 0; i < count; i++) {
same->info[i].bytes_deduped = 0ULL;
same->info[i].status = 0;
}
- ret = 0;
- for (i = 0; i < same->dest_count; i++) {
- info = &same->info[i];
-
- dst_file = fget(info->fd);
- if (!dst_file) {
+ for (i = 0, info = same->info; i < count; i++, info++) {
+ struct inode *dst;
+ struct fd dst_file = fdget(info->fd);
+ if (!dst_file.file) {
info->status = -EBADF;
- goto next;
+ continue;
}
+ dst = file_inode(dst_file.file);
- if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) {
+ if (!(is_admin || (dst_file.file->f_mode & FMODE_WRITE))) {
info->status = -EINVAL;
- goto next;
- }
-
- info->status = -EXDEV;
- if (file->f_path.mnt != dst_file->f_path.mnt)
- goto next;
-
- dst = dst_file->f_dentry->d_inode;
- if (src->i_sb != dst->i_sb)
- goto next;
-
- if (S_ISDIR(dst->i_mode)) {
+ } else if (file->f_path.mnt != dst_file.file->f_path.mnt) {
+ info->status = -EXDEV;
+ } else if (S_ISDIR(dst->i_mode)) {
info->status = -EISDIR;
- goto next;
- }
-
- if (!S_ISREG(dst->i_mode)) {
+ } else if (!S_ISREG(dst->i_mode)) {
info->status = -EACCES;
- goto next;
+ } else {
+ info->status = btrfs_extent_same(src, off, len, dst,
+ info->logical_offset);
+ if (info->status == 0)
+ info->bytes_deduped += len;
}
-
- info->status = btrfs_extent_same(src, off, len, dst,
- info->logical_offset);
- if (info->status == 0)
- info->bytes_deduped += len;
-
-next:
- if (dst_file)
- fput(dst_file);
+ fdput(dst_file);
}
ret = copy_to_user(argp, same, size);
* note the key will change type as we walk through the
* tree.
*/
+ path->leave_spinning = 1;
ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path,
0, 0);
if (ret < 0)
goto out;
nritems = btrfs_header_nritems(path->nodes[0]);
+ process_slot:
if (path->slots[0] >= nritems) {
ret = btrfs_next_leaf(BTRFS_I(src)->root, path);
if (ret < 0)
u8 comp;
u64 endoff;
- size = btrfs_item_size_nr(leaf, slot);
- read_extent_buffer(leaf, buf,
- btrfs_item_ptr_offset(leaf, slot),
- size);
-
extent = btrfs_item_ptr(leaf, slot,
struct btrfs_file_extent_item);
comp = btrfs_file_extent_compression(leaf, extent);
datal = btrfs_file_extent_ram_bytes(leaf,
extent);
}
- btrfs_release_path(path);
if (key.offset + datal <= off ||
- key.offset >= off + len - 1)
- goto next;
+ key.offset >= off + len - 1) {
+ path->slots[0]++;
+ goto process_slot;
+ }
+
+ size = btrfs_item_size_nr(leaf, slot);
+ read_extent_buffer(leaf, buf,
+ btrfs_item_ptr_offset(leaf, slot),
+ size);
+
+ btrfs_release_path(path);
+ path->leave_spinning = 0;
memcpy(&new_key, &key, sizeof(new_key));
new_key.objectid = btrfs_ino(inode);
}
ret = btrfs_end_transaction(trans, root);
}
- next:
btrfs_release_path(path);
key.offset++;
}
unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
out_unlock:
- mutex_unlock(&src->i_mutex);
- if (!same_inode)
- mutex_unlock(&inode->i_mutex);
+ if (!same_inode) {
+ if (inode < src) {
+ mutex_unlock(&src->i_mutex);
+ mutex_unlock(&inode->i_mutex);
+ } else {
+ mutex_unlock(&inode->i_mutex);
+ mutex_unlock(&src->i_mutex);
+ }
+ } else {
+ mutex_unlock(&src->i_mutex);
+ }
out_fput:
fdput(src_file);
out_drop_write:
if (IS_ERR_OR_NULL(di)) {
btrfs_free_path(path);
btrfs_end_transaction(trans, root);
- printk(KERN_ERR "Umm, you don't have the default dir item, "
- "this isn't going to work\n");
+ btrfs_err(new_root->fs_info, "Umm, you don't have the default dir"
+ "item, this isn't going to work");
ret = -ENOENT;
goto out;
}
return ret;
}
+ static long btrfs_ioctl_global_rsv(struct btrfs_root *root, void __user *arg)
+ {
+ struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv;
+ u64 reserved;
+
+ spin_lock(&block_rsv->lock);
+ reserved = block_rsv->reserved;
+ spin_unlock(&block_rsv->lock);
+
+ if (arg && copy_to_user(arg, &reserved, sizeof(reserved)))
+ return -EFAULT;
+ return 0;
+ }
+
/*
* there are many ways the trans_start and trans_end ioctls can lead
* to deadlocks. They should only be used by applications that
int ret = 0;
int received_uuid_changed;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
ret = mnt_want_write_file(file);
if (ret < 0)
return ret;
goto out;
}
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out;
- }
-
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa)) {
ret = PTR_ERR(sa);
len = strnlen(label, BTRFS_LABEL_SIZE);
if (len == BTRFS_LABEL_SIZE) {
- pr_warn("btrfs: label is too long, return the first %zu bytes\n",
- --len);
+ btrfs_warn(root->fs_info,
+ "label is too long, return the first %zu bytes", --len);
}
ret = copy_to_user(arg, label, len);
return -EFAULT;
if (strnlen(label, BTRFS_LABEL_SIZE) == BTRFS_LABEL_SIZE) {
- pr_err("btrfs: unable to set label with more than %d bytes\n",
+ btrfs_err(root->fs_info, "unable to set label with more than %d bytes",
BTRFS_LABEL_SIZE - 1);
return -EINVAL;
}
return ret;
}
+ #define INIT_FEATURE_FLAGS(suffix) \
+ { .compat_flags = BTRFS_FEATURE_COMPAT_##suffix, \
+ .compat_ro_flags = BTRFS_FEATURE_COMPAT_RO_##suffix, \
+ .incompat_flags = BTRFS_FEATURE_INCOMPAT_##suffix }
+
+ static int btrfs_ioctl_get_supported_features(struct file *file,
+ void __user *arg)
+ {
+ static struct btrfs_ioctl_feature_flags features[3] = {
+ INIT_FEATURE_FLAGS(SUPP),
+ INIT_FEATURE_FLAGS(SAFE_SET),
+ INIT_FEATURE_FLAGS(SAFE_CLEAR)
+ };
+
+ if (copy_to_user(arg, &features, sizeof(features)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ static int btrfs_ioctl_get_features(struct file *file, void __user *arg)
+ {
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+ struct btrfs_super_block *super_block = root->fs_info->super_copy;
+ struct btrfs_ioctl_feature_flags features;
+
+ features.compat_flags = btrfs_super_compat_flags(super_block);
+ features.compat_ro_flags = btrfs_super_compat_ro_flags(super_block);
+ features.incompat_flags = btrfs_super_incompat_flags(super_block);
+
+ if (copy_to_user(arg, &features, sizeof(features)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ static int check_feature_bits(struct btrfs_root *root,
+ enum btrfs_feature_set set,
+ u64 change_mask, u64 flags, u64 supported_flags,
+ u64 safe_set, u64 safe_clear)
+ {
+ const char *type = btrfs_feature_set_names[set];
+ char *names;
+ u64 disallowed, unsupported;
+ u64 set_mask = flags & change_mask;
+ u64 clear_mask = ~flags & change_mask;
+
+ unsupported = set_mask & ~supported_flags;
+ if (unsupported) {
+ names = btrfs_printable_features(set, unsupported);
+ if (names) {
+ btrfs_warn(root->fs_info,
+ "this kernel does not support the %s feature bit%s",
+ names, strchr(names, ',') ? "s" : "");
+ kfree(names);
+ } else
+ btrfs_warn(root->fs_info,
+ "this kernel does not support %s bits 0x%llx",
+ type, unsupported);
+ return -EOPNOTSUPP;
+ }
+
+ disallowed = set_mask & ~safe_set;
+ if (disallowed) {
+ names = btrfs_printable_features(set, disallowed);
+ if (names) {
+ btrfs_warn(root->fs_info,
+ "can't set the %s feature bit%s while mounted",
+ names, strchr(names, ',') ? "s" : "");
+ kfree(names);
+ } else
+ btrfs_warn(root->fs_info,
+ "can't set %s bits 0x%llx while mounted",
+ type, disallowed);
+ return -EPERM;
+ }
+
+ disallowed = clear_mask & ~safe_clear;
+ if (disallowed) {
+ names = btrfs_printable_features(set, disallowed);
+ if (names) {
+ btrfs_warn(root->fs_info,
+ "can't clear the %s feature bit%s while mounted",
+ names, strchr(names, ',') ? "s" : "");
+ kfree(names);
+ } else
+ btrfs_warn(root->fs_info,
+ "can't clear %s bits 0x%llx while mounted",
+ type, disallowed);
+ return -EPERM;
+ }
+
+ return 0;
+ }
+
+ #define check_feature(root, change_mask, flags, mask_base) \
+ check_feature_bits(root, FEAT_##mask_base, change_mask, flags, \
+ BTRFS_FEATURE_ ## mask_base ## _SUPP, \
+ BTRFS_FEATURE_ ## mask_base ## _SAFE_SET, \
+ BTRFS_FEATURE_ ## mask_base ## _SAFE_CLEAR)
+
+ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
+ {
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+ struct btrfs_super_block *super_block = root->fs_info->super_copy;
+ struct btrfs_ioctl_feature_flags flags[2];
+ struct btrfs_trans_handle *trans;
+ u64 newflags;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(flags, arg, sizeof(flags)))
+ return -EFAULT;
+
+ /* Nothing to do */
+ if (!flags[0].compat_flags && !flags[0].compat_ro_flags &&
+ !flags[0].incompat_flags)
+ return 0;
+
+ ret = check_feature(root, flags[0].compat_flags,
+ flags[1].compat_flags, COMPAT);
+ if (ret)
+ return ret;
+
+ ret = check_feature(root, flags[0].compat_ro_flags,
+ flags[1].compat_ro_flags, COMPAT_RO);
+ if (ret)
+ return ret;
+
+ ret = check_feature(root, flags[0].incompat_flags,
+ flags[1].incompat_flags, INCOMPAT);
+ if (ret)
+ return ret;
+
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ spin_lock(&root->fs_info->super_lock);
+ newflags = btrfs_super_compat_flags(super_block);
+ newflags |= flags[0].compat_flags & flags[1].compat_flags;
+ newflags &= ~(flags[0].compat_flags & ~flags[1].compat_flags);
+ btrfs_set_super_compat_flags(super_block, newflags);
+
+ newflags = btrfs_super_compat_ro_flags(super_block);
+ newflags |= flags[0].compat_ro_flags & flags[1].compat_ro_flags;
+ newflags &= ~(flags[0].compat_ro_flags & ~flags[1].compat_ro_flags);
+ btrfs_set_super_compat_ro_flags(super_block, newflags);
+
+ newflags = btrfs_super_incompat_flags(super_block);
+ newflags |= flags[0].incompat_flags & flags[1].incompat_flags;
+ newflags &= ~(flags[0].incompat_flags & ~flags[1].incompat_flags);
+ btrfs_set_super_incompat_flags(super_block, newflags);
+ spin_unlock(&root->fs_info->super_lock);
+
+ return btrfs_end_transaction(trans, root);
+ }
+
long btrfs_ioctl(struct file *file, unsigned int
cmd, unsigned long arg)
{
return btrfs_ioctl_logical_to_ino(root, argp);
case BTRFS_IOC_SPACE_INFO:
return btrfs_ioctl_space_info(root, argp);
+ case BTRFS_IOC_GLOBAL_RSV:
+ return btrfs_ioctl_global_rsv(root, argp);
case BTRFS_IOC_SYNC: {
int ret;
return btrfs_ioctl_set_fslabel(file, argp);
case BTRFS_IOC_FILE_EXTENT_SAME:
return btrfs_ioctl_file_extent_same(file, argp);
+ case BTRFS_IOC_GET_SUPPORTED_FEATURES:
+ return btrfs_ioctl_get_supported_features(file, argp);
+ case BTRFS_IOC_GET_FEATURES:
+ return btrfs_ioctl_get_features(file, argp);
+ case BTRFS_IOC_SET_FEATURES:
+ return btrfs_ioctl_set_features(file, argp);
}
return -ENOTTY;
static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
int mirror_num, u64 physical_for_dev_replace);
static void copy_nocow_pages_worker(struct btrfs_work *work);
+ static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
+ static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
wake_up(&sctx->list_wait);
}
+ static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
+ {
+ while (atomic_read(&fs_info->scrub_pause_req)) {
+ mutex_unlock(&fs_info->scrub_lock);
+ wait_event(fs_info->scrub_pause_wait,
+ atomic_read(&fs_info->scrub_pause_req) == 0);
+ mutex_lock(&fs_info->scrub_lock);
+ }
+ }
+
+ static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
+ {
+ atomic_inc(&fs_info->scrubs_paused);
+ wake_up(&fs_info->scrub_pause_wait);
+
+ mutex_lock(&fs_info->scrub_lock);
+ __scrub_blocked_if_needed(fs_info);
+ atomic_dec(&fs_info->scrubs_paused);
+ mutex_unlock(&fs_info->scrub_lock);
+
+ wake_up(&fs_info->scrub_pause_wait);
+ }
+
/*
* used for workers that require transaction commits (i.e., for the
* NOCOW case)
* hold all of the paths here
*/
for (i = 0; i < ipath->fspath->elem_cnt; ++i)
- printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev "
+ printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev "
"%s, sector %llu, root %llu, inode %llu, offset %llu, "
"length %llu, links %u (path: %s)\n", swarn->errstr,
swarn->logical, rcu_str_deref(swarn->dev->name),
return 0;
err:
- printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev "
+ printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev "
"%s, sector %llu, root %llu, inode %llu, offset %llu: path "
"resolving failed with ret=%d\n", swarn->errstr,
swarn->logical, rcu_str_deref(swarn->dev->name),
ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
&ref_root, &ref_level);
printk_in_rcu(KERN_WARNING
- "btrfs: %s at logical %llu on dev %s, "
+ "BTRFS: %s at logical %llu on dev %s, "
"sector %llu: metadata %s (level %d) in tree "
"%llu\n", errstr, swarn.logical,
rcu_str_deref(dev->name),
struct scrub_fixup_nodatasum *fixup;
struct scrub_ctx *sctx;
struct btrfs_trans_handle *trans = NULL;
- struct btrfs_fs_info *fs_info;
struct btrfs_path *path;
int uncorrectable = 0;
fixup = container_of(work, struct scrub_fixup_nodatasum, work);
sctx = fixup->sctx;
- fs_info = fixup->root->fs_info;
path = btrfs_alloc_path();
if (!path) {
btrfs_dev_replace_stats_inc(
&sctx->dev_root->fs_info->dev_replace.
num_uncorrectable_read_errors);
- printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: unable to fixup (nodatasum) error at logical %llu on dev %s\n",
+ printk_ratelimited_in_rcu(KERN_ERR "BTRFS: "
+ "unable to fixup (nodatasum) error at logical %llu on dev %s\n",
fixup->logical, rcu_str_deref(fixup->dev->name));
}
sctx->stat.corrected_errors++;
spin_unlock(&sctx->stat_lock);
printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: fixed up error at logical %llu on dev %s\n",
+ "BTRFS: fixed up error at logical %llu on dev %s\n",
logical, rcu_str_deref(dev->name));
}
} else {
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: unable to fixup (regular) error at logical %llu on dev %s\n",
+ "BTRFS: unable to fixup (regular) error at logical %llu on dev %s\n",
logical, rcu_str_deref(dev->name));
}
continue;
}
bio->bi_bdev = page->dev->bdev;
- bio->bi_sector = page->physical >> 9;
+ bio->bi_iter.bi_sector = page->physical >> 9;
bio_add_page(bio, page->page, PAGE_SIZE, 0);
if (btrfsic_submit_bio_wait(READ, bio))
int ret;
if (!page_bad->dev->bdev) {
- printk_ratelimited(KERN_WARNING
- "btrfs: scrub_repair_page_from_good_copy(bdev == NULL) is unexpected!\n");
+ printk_ratelimited(KERN_WARNING "BTRFS: "
+ "scrub_repair_page_from_good_copy(bdev == NULL) "
+ "is unexpected!\n");
return -EIO;
}
if (!bio)
return -EIO;
bio->bi_bdev = page_bad->dev->bdev;
- bio->bi_sector = page_bad->physical >> 9;
+ bio->bi_iter.bi_sector = page_bad->physical >> 9;
ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
if (PAGE_SIZE != ret) {
bio->bi_private = sbio;
bio->bi_end_io = scrub_wr_bio_end_io;
bio->bi_bdev = sbio->dev->bdev;
- bio->bi_sector = sbio->physical >> 9;
+ bio->bi_iter.bi_sector = sbio->physical >> 9;
sbio->err = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical_for_dev_replace ||
* This case is handled correctly (but _very_ slowly).
*/
printk_ratelimited(KERN_WARNING
- "btrfs: scrub_submit(bio bdev == NULL) is unexpected!\n");
+ "BTRFS: scrub_submit(bio bdev == NULL) is unexpected!\n");
bio_endio(sbio->bio, -EIO);
} else {
btrfsic_submit_bio(READ, sbio->bio);
bio->bi_private = sbio;
bio->bi_end_io = scrub_bio_end_io;
bio->bi_bdev = sbio->dev->bdev;
- bio->bi_sector = sbio->physical >> 9;
+ bio->bi_iter.bi_sector = sbio->physical >> 9;
sbio->err = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical ||
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
- atomic_inc(&fs_info->scrubs_paused);
- wake_up(&fs_info->scrub_pause_wait);
+ scrub_blocked_if_needed(fs_info);
/* FIXME it might be better to start readahead at commit root */
key_start.objectid = logical;
if (!IS_ERR(reada2))
btrfs_reada_wait(reada2);
- mutex_lock(&fs_info->scrub_lock);
- while (atomic_read(&fs_info->scrub_pause_req)) {
- mutex_unlock(&fs_info->scrub_lock);
- wait_event(fs_info->scrub_pause_wait,
- atomic_read(&fs_info->scrub_pause_req) == 0);
- mutex_lock(&fs_info->scrub_lock);
- }
- atomic_dec(&fs_info->scrubs_paused);
- mutex_unlock(&fs_info->scrub_lock);
- wake_up(&fs_info->scrub_pause_wait);
/*
* collect all data csums for the stripe to avoid seeking during
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
- atomic_inc(&fs_info->scrubs_paused);
- wake_up(&fs_info->scrub_pause_wait);
- mutex_lock(&fs_info->scrub_lock);
- while (atomic_read(&fs_info->scrub_pause_req)) {
- mutex_unlock(&fs_info->scrub_lock);
- wait_event(fs_info->scrub_pause_wait,
- atomic_read(&fs_info->scrub_pause_req) == 0);
- mutex_lock(&fs_info->scrub_lock);
- }
- atomic_dec(&fs_info->scrubs_paused);
- mutex_unlock(&fs_info->scrub_lock);
- wake_up(&fs_info->scrub_pause_wait);
+ scrub_blocked_if_needed(fs_info);
}
+ if (btrfs_fs_incompat(fs_info, SKINNY_METADATA))
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
key.objectid = logical;
- key.type = BTRFS_EXTENT_ITEM_KEY;
key.offset = (u64)-1;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
goto out;
if (ret > 0) {
- ret = btrfs_previous_item(root, path, 0,
- BTRFS_EXTENT_ITEM_KEY);
+ ret = btrfs_previous_extent_item(root, path, 0);
if (ret < 0)
goto out;
if (ret > 0) {
if (key.objectid < logical &&
(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
- printk(KERN_ERR
- "btrfs scrub: tree block %llu spanning "
- "stripes, ignored. logical=%llu\n",
+ btrfs_err(fs_info,
+ "scrub: tree block %llu spanning "
+ "stripes, ignored. logical=%llu",
key.objectid, logical);
goto next;
}
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
- atomic_inc(&fs_info->scrubs_paused);
- wake_up(&fs_info->scrub_pause_wait);
wait_event(sctx->list_wait,
atomic_read(&sctx->workers_pending) == 0);
-
- mutex_lock(&fs_info->scrub_lock);
- while (atomic_read(&fs_info->scrub_pause_req)) {
- mutex_unlock(&fs_info->scrub_lock);
- wait_event(fs_info->scrub_pause_wait,
- atomic_read(&fs_info->scrub_pause_req) == 0);
- mutex_lock(&fs_info->scrub_lock);
- }
- atomic_dec(&fs_info->scrubs_paused);
- mutex_unlock(&fs_info->scrub_lock);
- wake_up(&fs_info->scrub_pause_wait);
+ scrub_blocked_if_needed(fs_info);
btrfs_put_block_group(cache);
if (ret)
* check some assumptions
*/
if (fs_info->chunk_root->nodesize != fs_info->chunk_root->leafsize) {
- printk(KERN_ERR
- "btrfs_scrub: size assumption nodesize == leafsize (%d == %d) fails\n",
+ btrfs_err(fs_info,
+ "scrub: size assumption nodesize == leafsize (%d == %d) fails",
fs_info->chunk_root->nodesize,
fs_info->chunk_root->leafsize);
return -EINVAL;
* the way scrub is implemented. Do not handle this
* situation at all because it won't ever happen.
*/
- printk(KERN_ERR
- "btrfs_scrub: size assumption nodesize <= BTRFS_STRIPE_LEN (%d <= %d) fails\n",
+ btrfs_err(fs_info,
+ "scrub: size assumption nodesize <= BTRFS_STRIPE_LEN (%d <= %d) fails",
fs_info->chunk_root->nodesize, BTRFS_STRIPE_LEN);
return -EINVAL;
}
if (fs_info->chunk_root->sectorsize != PAGE_SIZE) {
/* not supported for data w/o checksums */
- printk(KERN_ERR
- "btrfs_scrub: size assumption sectorsize != PAGE_SIZE (%d != %lu) fails\n",
+ btrfs_err(fs_info,
+ "scrub: size assumption sectorsize != PAGE_SIZE "
+ "(%d != %lu) fails",
fs_info->chunk_root->sectorsize, PAGE_SIZE);
return -EINVAL;
}
* would exhaust the array bounds of pagev member in
* struct scrub_block
*/
- pr_err("btrfs_scrub: size assumption nodesize and sectorsize <= SCRUB_MAX_PAGES_PER_BLOCK (%d <= %d && %d <= %d) fails\n",
+ btrfs_err(fs_info, "scrub: size assumption nodesize and sectorsize "
+ "<= SCRUB_MAX_PAGES_PER_BLOCK (%d <= %d && %d <= %d) fails",
fs_info->chunk_root->nodesize,
SCRUB_MAX_PAGES_PER_BLOCK,
fs_info->chunk_root->sectorsize,
}
sctx->readonly = readonly;
dev->scrub_device = sctx;
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ /*
+ * checking @scrub_pause_req here, we can avoid
+ * race between committing transaction and scrubbing.
+ */
+ __scrub_blocked_if_needed(fs_info);
atomic_inc(&fs_info->scrubs_running);
mutex_unlock(&fs_info->scrub_lock);
* by holding device list mutex, we can
* kick off writing super in log tree sync.
*/
+ mutex_lock(&fs_info->fs_devices->device_list_mutex);
ret = scrub_supers(sctx, dev);
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
}
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
if (!ret)
ret = scrub_enumerate_chunks(sctx, dev, start, end,
ret = iterate_inodes_from_logical(logical, fs_info, path,
record_inode_for_nocow, nocow_ctx);
if (ret != 0 && ret != -ENOENT) {
- pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d\n",
+ btrfs_warn(fs_info, "iterate_inodes_from_logical() failed: log %llu, "
+ "phys %llu, len %llu, mir %u, ret %d",
logical, physical_for_dev_replace, len, mirror_num,
ret);
not_written = 1;
again:
page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
if (!page) {
- pr_err("find_or_create_page() failed\n");
+ btrfs_err(fs_info, "find_or_create_page() failed");
ret = -ENOMEM;
goto out;
}
return -EIO;
if (!dev->bdev) {
printk_ratelimited(KERN_WARNING
- "btrfs: scrub write_page_nocow(bdev == NULL) is unexpected!\n");
+ "BTRFS: scrub write_page_nocow(bdev == NULL) is unexpected!\n");
return -EIO;
}
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
spin_unlock(&sctx->stat_lock);
return -ENOMEM;
}
- bio->bi_size = 0;
- bio->bi_sector = physical_for_dev_replace >> 9;
+ bio->bi_iter.bi_size = 0;
+ bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
bio->bi_bdev = dev->bdev;
ret = bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
if (ret != PAGE_CACHE_SIZE) {
ret = kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, action);
if (ret)
- pr_warn("Sending event '%d' to kobject: '%s' (%p): failed\n",
+ pr_warn("BTRFS: Sending event '%d' to kobject: '%s' (%p): failed\n",
action,
kobject_name(&disk_to_dev(bdev->bd_disk)->kobj),
&disk_to_dev(bdev->bd_disk)->kobj);
if (IS_ERR(*bdev)) {
ret = PTR_ERR(*bdev);
- printk(KERN_INFO "btrfs: open %s failed\n", device_path);
+ printk(KERN_INFO "BTRFS: open %s failed\n", device_path);
goto error;
}
if (disk_super->label[0]) {
if (disk_super->label[BTRFS_LABEL_SIZE - 1])
disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0';
- printk(KERN_INFO "btrfs: device label %s ", disk_super->label);
+ printk(KERN_INFO "BTRFS: device label %s ", disk_super->label);
} else {
- printk(KERN_INFO "btrfs: device fsid %pU ", disk_super->fsid);
+ printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid);
}
printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path);
}
if (!*device) {
- pr_err("btrfs: no missing device found\n");
+ btrfs_err(root->fs_info, "no missing device found");
return -ENOENT;
}
error:
btrfs_free_path(path);
if (enospc_errors) {
- printk(KERN_INFO "btrfs: %d enospc errors during balance\n",
+ btrfs_info(fs_info, "%d enospc errors during balance",
enospc_errors);
if (!ret)
ret = -ENOSPC;
if (!(bctl->flags & BTRFS_BALANCE_DATA) ||
!(bctl->flags & BTRFS_BALANCE_METADATA) ||
memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) {
- printk(KERN_ERR "btrfs: with mixed groups data and "
- "metadata balance options must be the same\n");
+ btrfs_err(fs_info, "with mixed groups data and "
+ "metadata balance options must be the same");
ret = -EINVAL;
goto out;
}
if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->data.target, 1) ||
(bctl->data.target & ~allowed))) {
- printk(KERN_ERR "btrfs: unable to start balance with target "
- "data profile %llu\n",
+ btrfs_err(fs_info, "unable to start balance with target "
+ "data profile %llu",
bctl->data.target);
ret = -EINVAL;
goto out;
if ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->meta.target, 1) ||
(bctl->meta.target & ~allowed))) {
- printk(KERN_ERR "btrfs: unable to start balance with target "
- "metadata profile %llu\n",
+ btrfs_err(fs_info,
+ "unable to start balance with target metadata profile %llu",
bctl->meta.target);
ret = -EINVAL;
goto out;
if ((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->sys.target, 1) ||
(bctl->sys.target & ~allowed))) {
- printk(KERN_ERR "btrfs: unable to start balance with target "
- "system profile %llu\n",
+ btrfs_err(fs_info,
+ "unable to start balance with target system profile %llu",
bctl->sys.target);
ret = -EINVAL;
goto out;
/* allow dup'ed data chunks only in mixed mode */
if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) {
- printk(KERN_ERR "btrfs: dup for data is not allowed\n");
+ btrfs_err(fs_info, "dup for data is not allowed");
ret = -EINVAL;
goto out;
}
(fs_info->avail_metadata_alloc_bits & allowed) &&
!(bctl->meta.target & allowed))) {
if (bctl->flags & BTRFS_BALANCE_FORCE) {
- printk(KERN_INFO "btrfs: force reducing metadata "
- "integrity\n");
+ btrfs_info(fs_info, "force reducing metadata integrity");
} else {
- printk(KERN_ERR "btrfs: balance will reduce metadata "
- "integrity, use force if you want this\n");
+ btrfs_err(fs_info, "balance will reduce metadata "
+ "integrity, use force if you want this");
ret = -EINVAL;
goto out;
}
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl) {
- printk(KERN_INFO "btrfs: continuing balance\n");
+ btrfs_info(fs_info, "continuing balance");
ret = btrfs_balance(fs_info->balance_ctl, NULL);
}
spin_unlock(&fs_info->balance_lock);
if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) {
- printk(KERN_INFO "btrfs: force skipping balance\n");
+ btrfs_info(fs_info, "force skipping balance");
return 0;
}
BTRFS_UUID_KEY_SUBVOL,
key.objectid);
if (ret < 0) {
- pr_warn("btrfs: uuid_tree_add failed %d\n",
+ btrfs_warn(fs_info, "uuid_tree_add failed %d",
ret);
break;
}
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
key.objectid);
if (ret < 0) {
- pr_warn("btrfs: uuid_tree_add failed %d\n",
+ btrfs_warn(fs_info, "uuid_tree_add failed %d",
ret);
break;
}
if (trans && !IS_ERR(trans))
btrfs_end_transaction(trans, fs_info->uuid_root);
if (ret)
- pr_warn("btrfs: btrfs_uuid_scan_kthread failed %d\n", ret);
+ btrfs_warn(fs_info, "btrfs_uuid_scan_kthread failed %d", ret);
else
fs_info->update_uuid_tree_gen = 1;
up(&fs_info->uuid_tree_rescan_sem);
*/
ret = btrfs_uuid_tree_iterate(fs_info, btrfs_check_uuid_tree_entry);
if (ret < 0) {
- pr_warn("btrfs: iterating uuid_tree failed %d\n", ret);
+ btrfs_warn(fs_info, "iterating uuid_tree failed %d", ret);
up(&fs_info->uuid_tree_rescan_sem);
return ret;
}
task = kthread_run(btrfs_uuid_scan_kthread, fs_info, "btrfs-uuid");
if (IS_ERR(task)) {
/* fs_info->update_uuid_tree_gen remains 0 in all error case */
- pr_warn("btrfs: failed to start uuid_scan task\n");
+ btrfs_warn(fs_info, "failed to start uuid_scan task");
up(&fs_info->uuid_tree_rescan_sem);
return PTR_ERR(task);
}
task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
if (IS_ERR(task)) {
/* fs_info->update_uuid_tree_gen remains 0 in all error case */
- pr_warn("btrfs: failed to start uuid_rescan task\n");
+ btrfs_warn(fs_info, "failed to start uuid_rescan task");
up(&fs_info->uuid_tree_rescan_sem);
return PTR_ERR(task);
}
max_stripe_size = 32 * 1024 * 1024;
max_chunk_size = 2 * max_stripe_size;
} else {
- printk(KERN_ERR "btrfs: invalid chunk type 0x%llx requested\n",
+ btrfs_err(info, "invalid chunk type 0x%llx requested\n",
type);
BUG_ON(1);
}
if (!device->writeable) {
WARN(1, KERN_ERR
- "btrfs: read-only device in alloc_list\n");
+ "BTRFS: read-only device in alloc_list\n");
continue;
}
read_unlock(&em_tree->lock);
if (!em) {
- printk(KERN_ERR "btrfs: couldn't find em for chunk %Lu\n",
+ printk(KERN_ERR "BTRFS: couldn't find em for chunk %Lu\n",
chunk_start);
return -EIO;
}
if (em->start != chunk_start) {
- printk(KERN_ERR "btrfs: bad chunk start, em=%Lu, wanted=%Lu\n",
+ printk(KERN_ERR "BTRFS: bad chunk start, em=%Lu, wanted=%Lu\n",
em->start, chunk_start);
free_extent_map(em);
return -EIO;
bio_put(bio);
bio = bbio->orig_bio;
}
+
+ /*
+ * We have original bio now. So increment bi_remaining to
+ * account for it in endio
+ */
+ atomic_inc(&bio->bi_remaining);
+
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
if (!q->merge_bvec_fn)
return 1;
- bvm.bi_size = bio->bi_size - prev->bv_len;
+ bvm.bi_size = bio->bi_iter.bi_size - prev->bv_len;
if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len)
return 0;
return 1;
bio->bi_private = bbio;
btrfs_io_bio(bio)->stripe_index = dev_nr;
bio->bi_end_io = btrfs_end_bio;
- bio->bi_sector = physical >> 9;
+ bio->bi_iter.bi_sector = physical >> 9;
#ifdef DEBUG
{
struct rcu_string *name;
while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) {
if (bio_add_page(bio, bvec->bv_page, bvec->bv_len,
bvec->bv_offset) < bvec->bv_len) {
- u64 len = bio->bi_size;
+ u64 len = bio->bi_iter.bi_size;
atomic_inc(&bbio->stripes_pending);
submit_stripe_bio(root, bbio, bio, physical, dev_nr,
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
- bio->bi_sector = logical >> 9;
+ bio->bi_iter.bi_sector = logical >> 9;
kfree(bbio);
bio_endio(bio, -EIO);
}
{
struct btrfs_device *dev;
struct bio *first_bio = bio;
- u64 logical = (u64)bio->bi_sector << 9;
+ u64 logical = (u64)bio->bi_iter.bi_sector << 9;
u64 length = 0;
u64 map_length;
u64 *raid_map = NULL;
int total_devs = 1;
struct btrfs_bio *bbio = NULL;
- length = bio->bi_size;
+ length = bio->bi_iter.bi_size;
map_length = length;
ret = __btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
BUG_ON(!path);
ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
if (ret < 0) {
- printk_in_rcu(KERN_WARNING "btrfs: error %d while searching for dev_stats item for device %s!\n",
+ printk_in_rcu(KERN_WARNING "BTRFS: "
+ "error %d while searching for dev_stats item for device %s!\n",
ret, rcu_str_deref(device->name));
goto out;
}
/* need to delete old one and insert a new one */
ret = btrfs_del_item(trans, dev_root, path);
if (ret != 0) {
- printk_in_rcu(KERN_WARNING "btrfs: delete too small dev_stats item for device %s failed %d!\n",
+ printk_in_rcu(KERN_WARNING "BTRFS: "
+ "delete too small dev_stats item for device %s failed %d!\n",
rcu_str_deref(device->name), ret);
goto out;
}
ret = btrfs_insert_empty_item(trans, dev_root, path,
&key, sizeof(*ptr));
if (ret < 0) {
- printk_in_rcu(KERN_WARNING "btrfs: insert dev_stats item for device %s failed %d!\n",
+ printk_in_rcu(KERN_WARNING "BTRFS: "
+ "insert dev_stats item for device %s failed %d!\n",
rcu_str_deref(device->name), ret);
goto out;
}
{
if (!dev->dev_stats_valid)
return;
- printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+ printk_ratelimited_in_rcu(KERN_ERR "BTRFS: "
+ "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
rcu_str_deref(dev->name),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS),
- btrfs_dev_stat_read(dev,
- BTRFS_DEV_STAT_CORRUPTION_ERRS),
- btrfs_dev_stat_read(dev,
- BTRFS_DEV_STAT_GENERATION_ERRS));
+ btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS),
+ btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_GENERATION_ERRS));
}
static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev)
if (i == BTRFS_DEV_STAT_VALUES_MAX)
return; /* all values == 0, suppress message */
- printk_in_rcu(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+ printk_in_rcu(KERN_INFO "BTRFS: "
+ "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
rcu_str_deref(dev->name),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
mutex_unlock(&fs_devices->device_list_mutex);
if (!dev) {
- printk(KERN_WARNING
- "btrfs: get dev_stats failed, device not found\n");
+ btrfs_warn(root->fs_info, "get dev_stats failed, device not found");
return -ENODEV;
} else if (!dev->dev_stats_valid) {
- printk(KERN_WARNING
- "btrfs: get dev_stats failed, not yet valid\n");
+ btrfs_warn(root->fs_info, "get dev_stats failed, not yet valid");
return -ENODEV;
} else if (stats->flags & BTRFS_DEV_STATS_RESET) {
for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) {
#include <linux/rwsem.h>
#include <linux/xattr.h>
#include <linux/security.h>
+#include <linux/posix_acl_xattr.h>
#include "ctree.h"
#include "btrfs_inode.h"
#include "transaction.h"
#include "xattr.h"
#include "disk-io.h"
+ #include "props.h"
ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
*/
const struct xattr_handler *btrfs_xattr_handlers[] = {
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
- &btrfs_xattr_acl_access_handler,
- &btrfs_xattr_acl_default_handler,
+ &posix_acl_access_xattr_handler,
+ &posix_acl_default_xattr_handler,
#endif
NULL,
};
XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) ||
!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
- !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
+ !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) ||
+ !strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN);
}
ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
if (!btrfs_is_valid_xattr(name))
return -EOPNOTSUPP;
+ if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
+ return btrfs_set_prop(dentry->d_inode, name,
+ value, size, flags);
+
if (size == 0)
value = ""; /* empty EA, do not remove */
if (!btrfs_is_valid_xattr(name))
return -EOPNOTSUPP;
+ if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
+ return btrfs_set_prop(dentry->d_inode, name,
+ NULL, 0, XATTR_REPLACE);
+
return __btrfs_setxattr(NULL, dentry->d_inode, name, NULL, 0,
XATTR_REPLACE);
}
*/
#include <linux/kobject.h>
-#include <linux/kobj_completion.h>
#include <linux/string.h>
#include <linux/export.h>
#include <linux/stat.h>
#include <linux/slab.h>
+#include <linux/random.h>
/**
* kobject_namespace - return @kobj's namespace tag
static int create_dir(struct kobject *kobj)
{
+ const struct kobj_ns_type_operations *ops;
int error;
error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj));
- if (!error) {
- error = populate_dir(kobj);
- if (error)
- sysfs_remove_dir(kobj);
+ if (error)
+ return error;
+
+ error = populate_dir(kobj);
+ if (error) {
+ sysfs_remove_dir(kobj);
+ return error;
}
/*
*/
sysfs_get(kobj->sd);
- return error;
+ /*
+ * If @kobj has ns_ops, its children need to be filtered based on
+ * their namespace tags. Enable namespace support on @kobj->sd.
+ */
+ ops = kobj_child_ns_ops(kobj);
+ if (ops) {
+ BUG_ON(ops->type <= KOBJ_NS_TYPE_NONE);
+ BUG_ON(ops->type >= KOBJ_NS_TYPES);
+ BUG_ON(!kobj_ns_type_registered(ops->type));
+
+ kernfs_enable_ns(kobj->sd);
+ }
+
+ return 0;
}
static int get_kobj_path_length(struct kobject *kobj)
return 0;
kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs);
- if (!kobj->name)
+ if (!kobj->name) {
+ kobj->name = old_name;
return -ENOMEM;
+ }
/* ewww... some of these buggers have '/' in the name ... */
while ((s = strchr(kobj->name, '/')))
*
* If @parent is set, then the parent of the @kobj will be set to it.
* If @parent is NULL, then the parent of the @kobj will be set to the
- * kobject associted with the kset assigned to this kobject. If no kset
+ * kobject associated with the kset assigned to this kobject. If no kset
* is assigned to the kobject, then the kobject will be located in the
* root of the sysfs tree.
*
*/
void kobject_del(struct kobject *kobj)
{
- struct sysfs_dirent *sd;
+ struct kernfs_node *sd;
if (!kobj)
return;
{
struct kobject *kobj = container_of(kref, struct kobject, kref);
#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
- pr_info("kobject: '%s' (%p): %s, parent %p (delayed)\n",
- kobject_name(kobj), kobj, __func__, kobj->parent);
+ unsigned long delay = HZ + HZ * (get_random_int() & 0x3);
+ pr_info("kobject: '%s' (%p): %s, parent %p (delayed %ld)\n",
+ kobject_name(kobj), kobj, __func__, kobj->parent, delay);
INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup);
- schedule_delayed_work(&kobj->release, HZ);
+
+ schedule_delayed_work(&kobj->release, delay);
#else
kobject_cleanup(kobj);
#endif
.show = kobj_attr_show,
.store = kobj_attr_store,
};
+ EXPORT_SYMBOL_GPL(kobj_sysfs_ops);
-/**
- * kobj_completion_init - initialize a kobj_completion object.
- * @kc: kobj_completion
- * @ktype: type of kobject to initialize
- *
- * kobj_completion structures can be embedded within structures with different
- * lifetime rules. During the release of the enclosing object, we can
- * wait on the release of the kobject so that we don't free it while it's
- * still busy.
- */
-void kobj_completion_init(struct kobj_completion *kc, struct kobj_type *ktype)
-{
- init_completion(&kc->kc_unregister);
- kobject_init(&kc->kc_kobj, ktype);
-}
-EXPORT_SYMBOL_GPL(kobj_completion_init);
-
-/**
- * kobj_completion_release - release a kobj_completion object
- * @kobj: kobject embedded in kobj_completion
- *
- * Used with kobject_release to notify waiters that the kobject has been
- * released.
- */
-void kobj_completion_release(struct kobject *kobj)
-{
- struct kobj_completion *kc = kobj_to_kobj_completion(kobj);
- complete(&kc->kc_unregister);
-}
-EXPORT_SYMBOL_GPL(kobj_completion_release);
-
-/**
- * kobj_completion_del_and_wait - release the kobject and wait for it
- * @kc: kobj_completion object to release
- *
- * Delete the kobject from sysfs and drop the reference count. Then wait
- * until any other outstanding references are also dropped. This routine
- * is only necessary once other references may have been taken on the
- * kobject. Typically this happens when the kobject has been published
- * to sysfs via kobject_add.
- */
-void kobj_completion_del_and_wait(struct kobj_completion *kc)
-{
- kobject_del(&kc->kc_kobj);
- kobject_put(&kc->kc_kobj);
- wait_for_completion(&kc->kc_unregister);
-}
-EXPORT_SYMBOL_GPL(kobj_completion_del_and_wait);
-
/**
* kset_register - initialize and add a kset.
* @k: kset.
{
if (!k)
return;
+ kobject_del(&k->kobj);
kobject_put(&k->kobj);
}