summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/filesystems/btrfs.txt19
-rw-r--r--fs/btrfs/ctree.c36
-rw-r--r--fs/btrfs/ctree.h50
-rw-r--r--fs/btrfs/dev-replace.c2
-rw-r--r--fs/btrfs/disk-io.c36
-rw-r--r--fs/btrfs/extent_io.c3
-rw-r--r--fs/btrfs/file-item.c92
-rw-r--r--fs/btrfs/file.c105
-rw-r--r--fs/btrfs/inode.c250
-rw-r--r--fs/btrfs/ioctl.c9
-rw-r--r--fs/btrfs/print-tree.c23
-rw-r--r--fs/btrfs/reada.c10
-rw-r--r--fs/btrfs/scrub.c24
-rw-r--r--fs/btrfs/send.c36
-rw-r--r--fs/btrfs/super.c45
-rw-r--r--fs/btrfs/volumes.c23
16 files changed, 512 insertions, 251 deletions
diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt
index c772b47e7ef0..6593d2e415c5 100644
--- a/Documentation/filesystems/btrfs.txt
+++ b/Documentation/filesystems/btrfs.txt
@@ -168,10 +168,23 @@ Options with (*) are default options and will not show in the mount options.
notreelog
Enable/disable the tree logging used for fsync and O_SYNC writes.
- recovery
- Enable autorecovery attempts if a bad tree root is found at mount time.
- Currently this scans a list of several previous tree roots and tries to
+ nologreplay
+ Disable the log tree replay at mount time to prevent filesystem
+ from getting modified.
+ Must be used with 'ro' mount option.
+ A filesystem mounted with this option cannot transition to a
+ read-write mount via remount,rw - the filesystem must be unmounted
+ and mounted back again if read-write access is desired.
+
+ usebackuproot
+ Enable attempts to use backup tree roots if a bad tree root is found at
+ mount time.
+ Currently this scans a list of 4 previous tree roots and tries to
use the first readable.
+ And since the mount option doesn't affect any behavior after mount,
+ it won't be shown in mount info.
+ Prior to 4.6, this was done by 'recovery' option that has been
+ deprecated, but will work.
rescan_uuid_tree
Force check and rebuild procedure of the UUID tree. This should not
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 769e0ff1b4ce..77592931ab4f 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -311,7 +311,7 @@ struct tree_mod_root {
struct tree_mod_elem {
struct rb_node node;
- u64 index; /* shifted logical */
+ u64 logical;
u64 seq;
enum mod_log_op op;
@@ -435,11 +435,11 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
/*
* key order of the log:
- * index -> sequence
+ * node/leaf start address -> sequence
*
- * the index is the shifted logical of the *new* root node for root replace
- * operations, or the shifted logical of the affected block for all other
- * operations.
+ * The 'start address' is the logical address of the *new* root node
+ * for root replace operations, or the logical address of the affected
+ * block for all other operations.
*
* Note: must be called with write lock (tree_mod_log_write_lock).
*/
@@ -460,9 +460,9 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
while (*new) {
cur = container_of(*new, struct tree_mod_elem, node);
parent = *new;
- if (cur->index < tm->index)
+ if (cur->logical < tm->logical)
new = &((*new)->rb_left);
- else if (cur->index > tm->index)
+ else if (cur->logical > tm->logical)
new = &((*new)->rb_right);
else if (cur->seq < tm->seq)
new = &((*new)->rb_left);
@@ -523,7 +523,7 @@ alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
if (!tm)
return NULL;
- tm->index = eb->start >> PAGE_CACHE_SHIFT;
+ tm->logical = eb->start;
if (op != MOD_LOG_KEY_ADD) {
btrfs_node_key(eb, &tm->key, slot);
tm->blockptr = btrfs_node_blockptr(eb, slot);
@@ -588,7 +588,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
goto free_tms;
}
- tm->index = eb->start >> PAGE_CACHE_SHIFT;
+ tm->logical = eb->start;
tm->slot = src_slot;
tm->move.dst_slot = dst_slot;
tm->move.nr_items = nr_items;
@@ -699,7 +699,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
goto free_tms;
}
- tm->index = new_root->start >> PAGE_CACHE_SHIFT;
+ tm->logical = new_root->start;
tm->old_root.logical = old_root->start;
tm->old_root.level = btrfs_header_level(old_root);
tm->generation = btrfs_header_generation(old_root);
@@ -739,16 +739,15 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
struct rb_node *node;
struct tree_mod_elem *cur = NULL;
struct tree_mod_elem *found = NULL;
- u64 index = start >> PAGE_CACHE_SHIFT;
tree_mod_log_read_lock(fs_info);
tm_root = &fs_info->tree_mod_log;
node = tm_root->rb_node;
while (node) {
cur = container_of(node, struct tree_mod_elem, node);
- if (cur->index < index) {
+ if (cur->logical < start) {
node = node->rb_left;
- } else if (cur->index > index) {
+ } else if (cur->logical > start) {
node = node->rb_right;
} else if (cur->seq < min_seq) {
node = node->rb_left;
@@ -1230,9 +1229,10 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
return NULL;
/*
- * the very last operation that's logged for a root is the replacement
- * operation (if it is replaced at all). this has the index of the *new*
- * root, making it the very first operation that's logged for this root.
+ * the very last operation that's logged for a root is the
+ * replacement operation (if it is replaced at all). this has
+ * the logical address of the *new* root, making it the very
+ * first operation that's logged for this root.
*/
while (1) {
tm = tree_mod_log_search_oldest(fs_info, root_logical,
@@ -1336,7 +1336,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
if (!next)
break;
tm = container_of(next, struct tree_mod_elem, node);
- if (tm->index != first_tm->index)
+ if (tm->logical != first_tm->logical)
break;
}
tree_mod_log_read_unlock(fs_info);
@@ -5361,7 +5361,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
goto out;
}
- tmp_buf = kmalloc(left_root->nodesize, GFP_NOFS);
+ tmp_buf = kmalloc(left_root->nodesize, GFP_KERNEL);
if (!tmp_buf) {
ret = -ENOMEM;
goto out;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e43d987e1c99..e2a5cc0d4a14 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -100,6 +100,9 @@ struct btrfs_ordered_sum;
/* tracks free space in block groups. */
#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL
+/* device stats in the device tree */
+#define BTRFS_DEV_STATS_OBJECTID 0ULL
+
/* for storing balance parameters in the root tree */
#define BTRFS_BALANCE_OBJECTID -4ULL
@@ -2188,13 +2191,43 @@ struct btrfs_ioctl_defrag_range_args {
*/
#define BTRFS_QGROUP_RELATION_KEY 246
+/*
+ * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
+ */
#define BTRFS_BALANCE_ITEM_KEY 248
/*
- * Persistantly stores the io stats in the device tree.
- * One key for all stats, (0, BTRFS_DEV_STATS_KEY, devid).
+ * The key type for tree items that are stored persistently, but do not need to
+ * exist for extended period of time. The items can exist in any tree.
+ *
+ * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - balance status item
+ * (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0)
+ */
+#define BTRFS_TEMPORARY_ITEM_KEY 248
+
+/*
+ * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY
+ */
+#define BTRFS_DEV_STATS_KEY 249
+
+/*
+ * The key type for tree items that are stored persistently and usually exist
+ * for a long period, eg. filesystem lifetime. The item kinds can be status
+ * information, stats or preference values. The item can exist in any tree.
+ *
+ * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data]
+ *
+ * Existing items:
+ *
+ * - device statistics, store IO stats in the device tree, one key for all
+ * stats
+ * (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0)
*/
-#define BTRFS_DEV_STATS_KEY 249
+#define BTRFS_PERSISTENT_ITEM_KEY 249
/*
* Persistantly stores the device replace state in the device tree.
@@ -2244,7 +2277,7 @@ struct btrfs_ioctl_defrag_range_args {
#define BTRFS_MOUNT_ENOSPC_DEBUG (1 << 15)
#define BTRFS_MOUNT_AUTO_DEFRAG (1 << 16)
#define BTRFS_MOUNT_INODE_MAP_CACHE (1 << 17)
-#define BTRFS_MOUNT_RECOVERY (1 << 18)
+#define BTRFS_MOUNT_USEBACKUPROOT (1 << 18)
#define BTRFS_MOUNT_SKIP_BALANCE (1 << 19)
#define BTRFS_MOUNT_CHECK_INTEGRITY (1 << 20)
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
@@ -2253,6 +2286,7 @@ struct btrfs_ioctl_defrag_range_args {
#define BTRFS_MOUNT_FRAGMENT_DATA (1 << 24)
#define BTRFS_MOUNT_FRAGMENT_METADATA (1 << 25)
#define BTRFS_MOUNT_FREE_SPACE_TREE (1 << 26)
+#define BTRFS_MOUNT_NOLOGREPLAY (1 << 27)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
#define BTRFS_DEFAULT_MAX_INLINE (8192)
@@ -2356,6 +2390,9 @@ struct btrfs_map_token {
unsigned long offset;
};
+#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
+ ((bytes) >> (fs_info)->sb->s_blocksize_bits)
+
static inline void btrfs_init_map_token (struct btrfs_map_token *token)
{
token->kaddr = NULL;
@@ -4030,7 +4067,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *dir, u64 objectid,
const char *name, int name_len);
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
int front);
int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
@@ -4154,7 +4191,8 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
/* super.c */
-int btrfs_parse_options(struct btrfs_root *root, char *options);
+int btrfs_parse_options(struct btrfs_root *root, char *options,
+ unsigned long new_flags);
int btrfs_sync_fs(struct super_block *sb, int wait);
#ifdef CONFIG_PRINTK
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index cbb7dbfb3fff..01ce5fcecc5c 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -802,7 +802,7 @@ static int btrfs_dev_replace_kthread(void *data)
struct btrfs_ioctl_dev_replace_args *status_args;
u64 progress;
- status_args = kzalloc(sizeof(*status_args), GFP_NOFS);
+ status_args = kzalloc(sizeof(*status_args), GFP_KERNEL);
if (status_args) {
btrfs_dev_replace_status(fs_info, status_args);
progress = status_args->status.progress_1000;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 5e3ec1fc0ac3..de68b8b61fd2 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1296,9 +1296,10 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
spin_lock_init(&root->root_item_lock);
}
-static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info)
+static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
+ gfp_t flags)
{
- struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS);
+ struct btrfs_root *root = kzalloc(sizeof(*root), flags);
if (root)
root->fs_info = fs_info;
return root;
@@ -1310,7 +1311,7 @@ struct btrfs_root *btrfs_alloc_dummy_root(void)
{
struct btrfs_root *root;
- root = btrfs_alloc_root(NULL);
+ root = btrfs_alloc_root(NULL, GFP_KERNEL);
if (!root)
return ERR_PTR(-ENOMEM);
__setup_root(4096, 4096, 4096, root, NULL, 1);
@@ -1332,7 +1333,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
int ret = 0;
uuid_le uuid;
- root = btrfs_alloc_root(fs_info);
+ root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!root)
return ERR_PTR(-ENOMEM);
@@ -1408,7 +1409,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
struct btrfs_root *tree_root = fs_info->tree_root;
struct extent_buffer *leaf;
- root = btrfs_alloc_root(fs_info);
+ root = btrfs_alloc_root(fs_info, GFP_NOFS);
if (!root)
return ERR_PTR(-ENOMEM);
@@ -1506,7 +1507,7 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
if (!path)
return ERR_PTR(-ENOMEM);
- root = btrfs_alloc_root(fs_info);
+ root = btrfs_alloc_root(fs_info, GFP_NOFS);
if (!root) {
ret = -ENOMEM;
goto alloc_fail;
@@ -2385,7 +2386,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
return -EIO;
}
- log_tree_root = btrfs_alloc_root(fs_info);
+ log_tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!log_tree_root)
return -ENOMEM;
@@ -2510,8 +2511,8 @@ int open_ctree(struct super_block *sb,
int backup_index = 0;
int max_active;
- tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info);
- chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info);
+ tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
+ chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!tree_root || !chunk_root) {
err = -ENOMEM;
goto fail;
@@ -2623,7 +2624,7 @@ int open_ctree(struct super_block *sb,
INIT_LIST_HEAD(&fs_info->ordered_roots);
spin_lock_init(&fs_info->ordered_root_lock);
fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
- GFP_NOFS);
+ GFP_KERNEL);
if (!fs_info->delayed_root) {
err = -ENOMEM;
goto fail_iput;
@@ -2751,7 +2752,7 @@ int open_ctree(struct super_block *sb,
*/
fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
- ret = btrfs_parse_options(tree_root, options);
+ ret = btrfs_parse_options(tree_root, options, sb->s_flags);
if (ret) {
err = ret;
goto fail_alloc;
@@ -3030,8 +3031,9 @@ retry_root_backup:
if (ret)
goto fail_trans_kthread;
- /* do not make disk changes in broken FS */
- if (btrfs_super_log_root(disk_super) != 0) {
+ /* do not make disk changes in broken FS or nologreplay is given */
+ if (btrfs_super_log_root(disk_super) != 0 &&
+ !btrfs_test_opt(tree_root, NOLOGREPLAY)) {
ret = btrfs_replay_log(fs_info, fs_devices);
if (ret) {
err = ret;
@@ -3147,6 +3149,12 @@ retry_root_backup:
fs_info->open = 1;
+ /*
+ * backuproot only affect mount behavior, and if open_ctree succeeded,
+ * no need to keep the flag
+ */
+ btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
+
return 0;
fail_qgroup:
@@ -3201,7 +3209,7 @@ fail:
return err;
recovery_tree_root:
- if (!btrfs_test_opt(tree_root, RECOVERY))
+ if (!btrfs_test_opt(tree_root, USEBACKUPROOT))
goto fail_tree_roots;
free_root_pointers(fs_info, 0);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2e7c97a3f344..1b2073389dc2 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3186,7 +3186,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
while (1) {
lock_extent(tree, start, end);
- ordered = btrfs_lookup_ordered_extent(inode, start);
+ ordered = btrfs_lookup_ordered_range(inode, start,
+ PAGE_CACHE_SIZE);
if (!ordered)
break;
unlock_extent(tree, start, end);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a67e1c828d0f..1c50a7b09b4e 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -172,6 +172,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
u64 item_start_offset = 0;
u64 item_last_offset = 0;
u64 disk_bytenr;
+ u64 page_bytes_left;
u32 diff;
int nblocks;
int bio_index = 0;
@@ -220,6 +221,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
if (dio)
offset = logical_offset;
+
+ page_bytes_left = bvec->bv_len;
while (bio_index < bio->bi_vcnt) {
if (!dio)
offset = page_offset(bvec->bv_page) + bvec->bv_offset;
@@ -243,7 +246,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
if (BTRFS_I(inode)->root->root_key.objectid ==
BTRFS_DATA_RELOC_TREE_OBJECTID) {
set_extent_bits(io_tree, offset,
- offset + bvec->bv_len - 1,
+ offset + root->sectorsize - 1,
EXTENT_NODATASUM, GFP_NOFS);
} else {
btrfs_info(BTRFS_I(inode)->root->fs_info,
@@ -281,11 +284,17 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
found:
csum += count * csum_size;
nblocks -= count;
- bio_index += count;
+
while (count--) {
- disk_bytenr += bvec->bv_len;
- offset += bvec->bv_len;
- bvec++;
+ disk_bytenr += root->sectorsize;
+ offset += root->sectorsize;
+ page_bytes_left -= root->sectorsize;
+ if (!page_bytes_left) {
+ bio_index++;
+ bvec++;
+ page_bytes_left = bvec->bv_len;
+ }
+
}
}
btrfs_free_path(path);
@@ -432,6 +441,8 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
struct bio_vec *bvec = bio->bi_io_vec;
int bio_index = 0;
int index;
+ int nr_sectors;
+ int i;
unsigned long total_bytes = 0;
unsigned long this_sum_bytes = 0;
u64 offset;
@@ -459,41 +470,56 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
if (!contig)
offset = page_offset(bvec->bv_page) + bvec->bv_offset;
- if (offset >= ordered->file_offset + ordered->len ||
- offset < ordered->file_offset) {
- unsigned long bytes_left;
- sums->len = this_sum_bytes;
- this_sum_bytes = 0;
- btrfs_add_ordered_sum(inode, ordered, sums);
- btrfs_put_ordered_extent(ordered);
+ data = kmap_atomic(bvec->bv_page);
- bytes_left = bio->bi_iter.bi_size - total_bytes;
+ nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ bvec->bv_len + root->sectorsize
+ - 1);
+
+ for (i = 0; i < nr_sectors; i++) {
+ if (offset >= ordered->file_offset + ordered->len ||
+ offset < ordered->file_offset) {
+ unsigned long bytes_left;
+
+ kunmap_atomic(data);
+ sums->len = this_sum_bytes;
+ this_sum_bytes = 0;
+ btrfs_add_ordered_sum(inode, ordered, sums);
+ btrfs_put_ordered_extent(ordered);
+
+ bytes_left = bio->bi_iter.bi_size - total_bytes;
+
+ sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
+ GFP_NOFS);
+ BUG_ON(!sums); /* -ENOMEM */
+ sums->len = bytes_left;
+ ordered = btrfs_lookup_ordered_extent(inode,
+ offset);
+ ASSERT(ordered); /* Logic error */
+ sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9)
+ + total_bytes;
+ index = 0;
+
+ data = kmap_atomic(bvec->bv_page);
+ }
- sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
- GFP_NOFS);
- BUG_ON(!sums); /* -ENOMEM */
- sums->len = bytes_left;
- ordered = btrfs_lookup_ordered_extent(inode, offset);
- BUG_ON(!ordered); /* Logic error */
- sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
- total_bytes;
- index = 0;
+ sums->sums[index] = ~(u32)0;
+ sums->sums[index]
+ = btrfs_csum_data(data + bvec->bv_offset
+ + (i * root->sectorsize),
+ sums->sums[index],
+ root->sectorsize);
+ btrfs_csum_final(sums->sums[index],
+ (char *)(sums->sums + index));
+ index++;
+ offset += root->sectorsize;
+ this_sum_bytes += root->sectorsize;
+ total_bytes += root->sectorsize;
}
- data = kmap_atomic(bvec->bv_page);
- sums->sums[index] = ~(u32)0;
- sums->sums[index] = btrfs_csum_data(data + bvec->bv_offset,
- sums->sums[index],
- bvec->bv_len);
kunmap_atomic(data);
- btrfs_csum_final(sums->sums[index],
- (char *)(sums->sums + index));
bio_index++;
- index++;
- total_bytes += bvec->bv_len;
- this_sum_bytes += bvec->bv_len;
- offset += bvec->bv_len;
bvec++;
}
this_sum_bytes = 0;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 098bb8f690c9..2d9e4009c7e4 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -498,7 +498,7 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
loff_t isize = i_size_read(inode);
start_pos = pos & ~((u64)root->sectorsize - 1);
- num_bytes = ALIGN(write_bytes + pos - start_pos, root->sectorsize);
+ num_bytes = round_up(write_bytes + pos - start_pos, root->sectorsize);
end_of_last_block = start_pos + num_bytes - 1;
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
@@ -1379,16 +1379,19 @@ fail:
static noinline int
lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
size_t num_pages, loff_t pos,
+ size_t write_bytes,
u64 *lockstart, u64 *lockend,
struct extent_state **cached_state)
{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
u64 start_pos;
u64 last_pos;
int i;
int ret = 0;
- start_pos = pos & ~((u64)PAGE_CACHE_SIZE - 1);
- last_pos = start_pos + ((u64)num_pages << PAGE_CACHE_SHIFT) - 1;
+ start_pos = round_down(pos, root->sectorsize);
+ last_pos = start_pos
+ + round_up(pos + write_bytes - start_pos, root->sectorsize) - 1;
if (start_pos < inode->i_size) {
struct btrfs_ordered_extent *ordered;
@@ -1503,6 +1506,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
while (iov_iter_count(i) > 0) {
size_t offset = pos & (PAGE_CACHE_SIZE - 1);
+ size_t sector_offset;
size_t write_bytes = min(iov_iter_count(i),
nrptrs * (size_t)PAGE_CACHE_SIZE -
offset);
@@ -1511,6 +1515,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
size_t reserve_bytes;
size_t dirty_pages;
size_t copied;
+ size_t dirty_sectors;
+ size_t num_sectors;
WARN_ON(num_pages > nrptrs);
@@ -1523,7 +1529,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
break;
}
- reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+ sector_offset = pos & (root->sectorsize - 1);
+ reserve_bytes = round_up(write_bytes + sector_offset,
+ root->sectorsize);
if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
BTRFS_INODE_PREALLOC)) {
@@ -1542,7 +1550,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
*/
num_pages = DIV_ROUND_UP(write_bytes + offset,
PAGE_CACHE_SIZE);
- reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+ reserve_bytes = round_up(write_bytes
+ + sector_offset,
+ root->sectorsize);
goto reserve_metadata;
}
}
@@ -1576,8 +1586,8 @@ again:
break;
ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
- pos, &lockstart, &lockend,
- &cached_state);
+ pos, write_bytes, &lockstart,
+ &lockend, &cached_state);
if (ret < 0) {
if (ret == -EAGAIN)
goto again;
@@ -1612,9 +1622,16 @@ again:
* we still have an outstanding extent for the chunk we actually
* managed to copy.
*/
- if (num_pages > dirty_pages) {
- release_bytes = (num_pages - dirty_pages) <<
- PAGE_CACHE_SHIFT;
+ num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ reserve_bytes);
+ dirty_sectors = round_up(copied + sector_offset,
+ root->sectorsize);
+ dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ dirty_sectors);
+
+ if (num_sectors > dirty_sectors) {
+ release_bytes = (write_bytes - copied)
+ & ~((u64)root->sectorsize - 1);
if (copied > 0) {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
@@ -1633,7 +1650,8 @@ again:
}
}
- release_bytes = dirty_pages << PAGE_CACHE_SHIFT;
+ release_bytes = round_up(copied + sector_offset,
+ root->sectorsize);
if (copied > 0)
ret = btrfs_dirty_pages(root, inode, pages,
@@ -1654,8 +1672,7 @@ again:
if (only_release_metadata && copied > 0) {
lockstart = round_down(pos, root->sectorsize);
- lockend = lockstart +
- (dirty_pages << PAGE_CACHE_SHIFT) - 1;
+ lockend = round_up(pos + copied, root->sectorsize) - 1;
set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
lockend, EXTENT_NORESERVE, NULL,
@@ -1761,6 +1778,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
ssize_t err;
loff_t pos;
size_t count;
+ loff_t oldsize;
+ int clean_page = 0;
inode_lock(inode);
err = generic_write_checks(iocb, from);
@@ -1799,14 +1818,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
pos = iocb->ki_pos;
count = iov_iter_count(from);
start_pos = round_down(pos, root->sectorsize);
- if (start_pos > i_size_read(inode)) {
+ oldsize = i_size_read(inode);
+ if (start_pos > oldsize) {
/* Expand hole size to cover write data, preventing empty gap */
end_pos = round_up(pos + count, root->sectorsize);
- err = btrfs_cont_expand(inode, i_size_read(inode), end_pos);
+ err = btrfs_cont_expand(inode, oldsize, end_pos);
if (err) {
inode_unlock(inode);
goto out;
}
+ if (start_pos > round_up(oldsize, root->sectorsize))
+ clean_page = 1;
}
if (sync)
@@ -1818,6 +1840,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
num_written = __btrfs_buffered_write(file, from, pos);
if (num_written > 0)
iocb->ki_pos = pos + num_written;
+ if (clean_page)
+ pagecache_isize_extended(inode, oldsize,
+ i_size_read(inode));
}
inode_unlock(inode);
@@ -2293,10 +2318,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
int ret = 0;
int err = 0;
unsigned int rsv_count;
- bool same_page;
+ bool same_block;
bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
u64 ino_size;
- bool truncated_page = false;
+ bool truncated_block = false;
bool updated_inode = false;
ret = btrfs_wait_ordered_range(inode, offset, len);
@@ -2304,7 +2329,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
return ret;
inode_lock(inode);
- ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
+ ino_size = round_up(inode->i_size, root->sectorsize);
ret = find_first_non_hole(inode, &offset, &len);
if (ret < 0)
goto out_only_mutex;
@@ -2317,31 +2342,30 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
lockend = round_down(offset + len,
BTRFS_I(inode)->root->sectorsize) - 1;
- same_page = ((offset >> PAGE_CACHE_SHIFT) ==
- ((offset + len - 1) >> PAGE_CACHE_SHIFT));
-
+ same_block = (BTRFS_BYTES_TO_BLKS(root->fs_info, offset))
+ == (BTRFS_BYTES_TO_BLKS(root->fs_info, offset + len - 1));
/*
- * We needn't truncate any page which is beyond the end of the file
+ * We needn't truncate any block which is beyond the end of the file
* because we are sure there is no data there.
*/
/*
- * Only do this if we are in the same page and we aren't doing the
- * entire page.
+ * Only do this if we are in the same block and we aren't doing the
+ * entire block.
*/
- if (same_page && len < PAGE_CACHE_SIZE) {
+ if (same_block && len < root->sectorsize) {
if (offset < ino_size) {
- truncated_page = true;
- ret = btrfs_truncate_page(inode, offset, len, 0);
+ truncated_block = true;
+ ret = btrfs_truncate_block(inode, offset, len, 0);
} else {
ret = 0;
}
goto out_only_mutex;
}
- /* zero back part of the first page */
+ /* zero back part of the first block */
if (offset < ino_size) {
- truncated_page = true;
- ret = btrfs_truncate_page(inode, offset, 0, 0);
+ truncated_block = true;
+ ret = btrfs_truncate_block(inode, offset, 0, 0);
if (ret) {
inode_unlock(inode);
return ret;
@@ -2376,9 +2400,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (!ret) {
/* zero the front end of the last page */
if (tail_start + tail_len < ino_size) {
- truncated_page = true;
- ret = btrfs_truncate_page(inode,
- tail_start + tail_len, 0, 1);
+ truncated_block = true;
+ ret = btrfs_truncate_block(inode,
+ tail_start + tail_len,
+ 0, 1);
if (ret)
goto out_only_mutex;
}
@@ -2558,7 +2583,7 @@ out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state, GFP_NOFS);
out_only_mutex:
- if (!updated_inode && truncated_page && !ret && !err) {
+ if (!updated_inode && truncated_block && !ret && !err) {
/*
* If we only end up zeroing part of a page, we still need to
* update the inode item, so that all the time fields are
@@ -2611,7 +2636,7 @@ static int add_falloc_range(struct list_head *head, u64 start, u64 len)
return 0;
}
insert:
- range = kmalloc(sizeof(*range), GFP_NOFS);
+ range = kmalloc(sizeof(*range), GFP_KERNEL);
if (!range)
return -ENOMEM;
range->start = start;
@@ -2678,10 +2703,10 @@ static long btrfs_fallocate(struct file *file, int mode,
} else if (offset + len > inode->i_size) {
/*
* If we are fallocating from the end of the file onward we
- * need to zero out the end of the page if i_size lands in the
- * middle of a page.
+ * need to zero out the end of the block if i_size lands in the
+ * middle of a block.
*/
- ret = btrfs_truncate_page(inode, inode->i_size, 0, 0);
+ ret = btrfs_truncate_block(inode, inode->i_size, 0, 0);
if (ret)
goto out;
}
@@ -2712,7 +2737,7 @@ static long btrfs_fallocate(struct file *file, int mode,
btrfs_put_ordered_extent(ordered);
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
alloc_start, locked_end,
- &cached_state, GFP_NOFS);
+ &cached_state, GFP_KERNEL);
/*
* we can't wait on the range with the transaction
* running or with the extent lock held
@@ -2806,7 +2831,7 @@ static long btrfs_fallocate(struct file *file, int mode,
}
out_unlock:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
- &cached_state, GFP_NOFS);
+ &cached_state, GFP_KERNEL);
out:
/*
* As we waited the extent range, the data_rsv_map must be empty
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5f06eb1f4384..f8be74037f34 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -263,7 +263,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
data_len = compressed_size;
if (start > 0 ||
- actual_end > PAGE_CACHE_SIZE ||
+ actual_end > root->sectorsize ||
data_len > BTRFS_MAX_INLINE_DATA_SIZE(root) ||
(!compressed_size &&
(actual_end & (root->sectorsize - 1)) == 0) ||
@@ -2002,7 +2002,8 @@ again:
if (PagePrivate2(page))
goto out;
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+ ordered = btrfs_lookup_ordered_range(inode, page_start,
+ PAGE_CACHE_SIZE);
if (ordered) {
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
page_end, &cached_state, GFP_NOFS);
@@ -4248,7 +4249,8 @@ static int truncate_inline_extent(struct inode *inode,
* read the extent item from disk (data not in the page cache).
*/
btrfs_release_path(path);
- return btrfs_truncate_page(inode, offset, page_end - offset, 0);
+ return btrfs_truncate_block(inode, offset, page_end - offset,
+ 0);
}
btrfs_set_file_extent_ram_bytes(leaf, fi, size);
@@ -4601,17 +4603,17 @@ error:
}
/*
- * btrfs_truncate_page - read, zero a chunk and write a page
+ * btrfs_truncate_block - read, zero a chunk and write a block
* @inode - inode that we're zeroing
* @from - the offset to start zeroing
* @len - the length to zero, 0 to zero the entire range respective to the
* offset
* @front - zero up to the offset instead of from the offset on
*
- * This will find the page for the "from" offset and cow the page and zero the
+ * This will find the block for the "from" offset and cow the block and zero the
* part we want to zero. This is used with truncate and hole punching.
*/
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
int front)
{
struct address_space *mapping = inode->i_mapping;
@@ -4622,18 +4624,19 @@ int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
char *kaddr;
u32 blocksize = root->sectorsize;
pgoff_t index = from >> PAGE_CACHE_SHIFT;
- unsigned offset = from & (PAGE_CACHE_SIZE-1);
+ unsigned offset = from & (blocksize - 1);
struct page *page;
gfp_t mask = btrfs_alloc_write_mask(mapping);
int ret = 0;
- u64 page_start;
- u64 page_end;
+ u64 block_start;
+ u64 block_end;
if ((offset & (blocksize - 1)) == 0 &&
(!len || ((len & (blocksize - 1)) == 0)))
goto out;
+
ret = btrfs_delalloc_reserve_space(inode,
- round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE);
+ round_down(from, blocksize), blocksize);
if (ret)
goto out;
@@ -4641,14 +4644,14 @@ again:
page = find_or_create_page(mapping, index, mask);
if (!page) {
btrfs_delalloc_release_space(inode,
- round_down(from, PAGE_CACHE_SIZE),
- PAGE_CACHE_SIZE);
+ round_down(from, blocksize),
+ blocksize);
ret = -ENOMEM;
goto out;
}
- page_start = page_offset(page);
- page_end = page_start + PAGE_CACHE_SIZE - 1;
+ block_start = round_down(from, blocksize);
+ block_end = block_start + blocksize - 1;
if (!PageUptodate(page)) {
ret = btrfs_readpage(NULL, page);
@@ -4665,12 +4668,12 @@ again:
}
wait_on_page_writeback(page);
- lock_extent_bits(io_tree, page_start, page_end, &cached_state);
+ lock_extent_bits(io_tree, block_start, block_end, &cached_state);
set_page_extent_mapped(page);
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+ ordered = btrfs_lookup_ordered_extent(inode, block_start);
if (ordered) {
- unlock_extent_cached(io_tree, page_start, page_end,
+ unlock_extent_cached(io_tree, block_start, block_end,
&cached_state, GFP_NOFS);
unlock_page(page);
page_cache_release(page);
@@ -4679,39 +4682,41 @@ again:
goto again;
}
- clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+ ret = btrfs_set_extent_delalloc(inode, block_start, block_end,
&cached_state);
if (ret) {
- unlock_extent_cached(io_tree, page_start, page_end,
+ unlock_extent_cached(io_tree, block_start, block_end,
&cached_state, GFP_NOFS);
goto out_unlock;
}
- if (offset != PAGE_CACHE_SIZE) {
+ if (offset != blocksize) {
if (!len)
- len = PAGE_CACHE_SIZE - offset;
+ len = blocksize - offset;
kaddr = kmap(page);
if (front)
- memset(kaddr, 0, offset);
+ memset(kaddr + (block_start - page_offset(page)),
+ 0, offset);
else
- memset(kaddr + offset, 0, len);
+ memset(kaddr + (block_start - page_offset(page)) + offset,
+ 0, len);
flush_dcache_page(page);
kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
- unlock_extent_cached(io_tree, page_start, page_end, &cached_state,
+ unlock_extent_cached(io_tree, block_start, block_end, &cached_state,
GFP_NOFS);
out_unlock:
if (ret)
- btrfs_delalloc_release_space(inode, page_start,
- PAGE_CACHE_SIZE);
+ btrfs_delalloc_release_space(inode, block_start,
+ blocksize);
unlock_page(page);
page_cache_release(page);
out:
@@ -4782,11 +4787,11 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
int err = 0;
/*
- * If our size started in the middle of a page we need to zero out the
- * rest of the page before we expand the i_size, otherwise we could
+ * If our size started in the middle of a block we need to zero out the
+ * rest of the block before we expand the i_size, otherwise we could
* expose stale data.
*/
- err = btrfs_truncate_page(inode, oldsize, 0, 0);
+ err = btrfs_truncate_block(inode, oldsize, 0, 0);
if (err)
return err;
@@ -4895,7 +4900,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
}
if (newsize > oldsize) {
- truncate_pagecache(inode, newsize);
/*
* Don't do an expanding truncate while snapshoting is ongoing.
* This is to ensure the snapshot captures a fully consistent
@@ -4918,6 +4922,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
i_size_write(inode, newsize);
btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ pagecache_isize_extended(inode, oldsize, newsize);
ret = btrfs_update_inode(trans, root, inode);
btrfs_end_write_no_snapshoting(root);
btrfs_end_transaction(trans, root);
@@ -5788,7 +5793,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
if (name_len <= sizeof(tmp_name)) {
name_ptr = tmp_name;
} else {
- name_ptr = kmalloc(name_len, GFP_NOFS);
+ name_ptr = kmalloc(name_len, GFP_KERNEL);
if (!name_ptr) {
ret = -ENOMEM;
goto err;
@@ -7752,9 +7757,9 @@ static int btrfs_check_dio_repairable(struct inode *inode,
}
static int dio_read_error(struct inode *inode, struct bio *failed_bio,
- struct page *page, u64 start, u64 end,
- int failed_mirror, bio_end_io_t *repair_endio,
- void *repair_arg)
+ struct page *page, unsigned int pgoff,
+ u64 start, u64 end, int failed_mirror,
+ bio_end_io_t *repair_endio, void *repair_arg)
{
struct io_failure_record *failrec;
struct bio *bio;
@@ -7775,7 +7780,9 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
return -EIO;
}
- if (failed_bio->bi_vcnt > 1)
+ if ((failed_bio->bi_vcnt > 1)
+ || (failed_bio->bi_io_vec->bv_len
+ > BTRFS_I(inode)->root->sectorsize))
read_mode = READ_SYNC | REQ_FAILFAST_DEV;
else
read_mode = READ_SYNC;
@@ -7783,7 +7790,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
isector = start - btrfs_io_bio(failed_bio)->logical;
isector >>= inode->i_sb->s_blocksize_bits;
bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
- 0, isector, repair_endio, repair_arg);
+ pgoff, isector, repair_endio, repair_arg);
if (!bio) {
free_io_failure(inode, failrec);
return -EIO;
@@ -7813,12 +7820,17 @@ struct btrfs_retry_complete {
static void btrfs_retry_endio_nocsum(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
+ struct inode *inode;
struct bio_vec *bvec;
int i;
if (bio->bi_error)
goto end;
+ ASSERT(bio->bi_vcnt == 1);
+ inode = bio->bi_io_vec->bv_page->mapping->host;
+ ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
done->uptodate = 1;
bio_for_each_segment_all(bvec, bio, i)
clean_io_failure(done->inode, done->start, bvec->bv_page, 0);
@@ -7830,25 +7842,35 @@ end:
static int __btrfs_correct_data_nocsum(struct inode *inode,
struct btrfs_io_bio *io_bio)
{
+ struct btrfs_fs_info *fs_info;
struct bio_vec *bvec;
struct btrfs_retry_complete done;
u64 start;
+ unsigned int pgoff;
+ u32 sectorsize;
+ int nr_sectors;
int i;
int ret;
+ fs_info = BTRFS_I(inode)->root->fs_info;
+ sectorsize = BTRFS_I(inode)->root->sectorsize;
+
start = io_bio->logical;
done.inode = inode;
bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-try_again:
+ nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+ pgoff = bvec->bv_offset;
+
+next_block_or_try_again:
done.uptodate = 0;
done.start = start;
init_completion(&done.done);
- ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
- start + bvec->bv_len - 1,
- io_bio->mirror_num,
- btrfs_retry_endio_nocsum, &done);
+ ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+ pgoff, start, start + sectorsize - 1,
+ io_bio->mirror_num,
+ btrfs_retry_endio_nocsum, &done);
if (ret)
return ret;
@@ -7856,10 +7878,15 @@ try_again:
if (!done.uptodate) {
/* We might have another mirror, so try again */
- goto try_again;
+ goto next_block_or_try_again;
}
- start += bvec->bv_len;
+ start += sectorsize;
+
+ if (nr_sectors--) {
+ pgoff += sectorsize;
+ goto next_block_or_try_again;
+ }
}
return 0;
@@ -7869,7 +7896,9 @@ static void btrfs_retry_endio(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+ struct inode *inode;
struct bio_vec *bvec;
+ u64 start;
int uptodate;
int ret;
int i;
@@ -7878,13 +7907,20 @@ static void btrfs_retry_endio(struct bio *bio)
goto end;
uptodate = 1;
+
+ start = done->start;
+
+ ASSERT(bio->bi_vcnt == 1);
+ inode = bio->bi_io_vec->bv_page->mapping->host;
+ ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
bio_for_each_segment_all(bvec, bio, i) {
ret = __readpage_endio_check(done->inode, io_bio, i,
- bvec->bv_page, 0,
- done->start, bvec->bv_len);
+ bvec->bv_page, bvec->bv_offset,
+ done->start, bvec->bv_len);
if (!ret)
clean_io_failure(done->inode, done->start,
- bvec->bv_page, 0);
+ bvec->bv_page, bvec->bv_offset);
else
uptodate = 0;
}
@@ -7898,20 +7934,34 @@ end:
static int __btrfs_subio_endio_read(struct inode *inode,
struct btrfs_io_bio *io_bio, int err)
{
+ struct btrfs_fs_info *fs_info;
struct bio_vec *bvec;
struct btrfs_retry_complete done;
u64 start;
u64 offset = 0;
+ u32 sectorsize;
+ int nr_sectors;
+ unsigned int pgoff;
+ int csum_pos;
int i;
int ret;
+ fs_info = BTRFS_I(inode)->root->fs_info;
+ sectorsize = BTRFS_I(inode)->root->sectorsize;
+
err = 0;
start = io_bio->logical;
done.inode = inode;
bio_for_each_segment_all(bvec, &io_bio->bio, i) {
- ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
- 0, start, bvec->bv_len);
+ nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+
+ pgoff = bvec->bv_offset;
+next_block:
+ csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
+ ret = __readpage_endio_check(inode, io_bio, csum_pos,
+ bvec->bv_page, pgoff, start,
+ sectorsize);
if (likely(!ret))
goto next;
try_again:
@@ -7919,10 +7969,10 @@ try_again:
done.start = start;
init_completion(&done.done);
- ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
- start + bvec->bv_len - 1,
- io_bio->mirror_num,
- btrfs_retry_endio, &done);
+ ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+ pgoff, start, start + sectorsize - 1,
+ io_bio->mirror_num,
+ btrfs_retry_endio, &done);
if (ret) {
err = ret;
goto next;
@@ -7935,8 +7985,15 @@ try_again:
goto try_again;
}
next:
- offset += bvec->bv_len;
- start += bvec->bv_len;
+ offset += sectorsize;
+ start += sectorsize;
+
+ ASSERT(nr_sectors);
+
+ if (--nr_sectors) {
+ pgoff += sectorsize;
+ goto next_block;
+ }
}
return err;
@@ -8188,9 +8245,11 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
u64 file_offset = dip->logical_offset;
u64 submit_len = 0;
u64 map_length;
- int nr_pages = 0;
- int ret;
+ u32 blocksize = root->sectorsize;
int async_submit = 0;
+ int nr_sectors;
+ int ret;
+ int i;
map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
@@ -8220,9 +8279,12 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
atomic_inc(&dip->pending_bios);
while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
- if (map_length < submit_len + bvec->bv_len ||
- bio_add_page(bio, bvec->bv_page, bvec->bv_len,
- bvec->bv_offset) < bvec->bv_len) {
+ nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info, bvec->bv_len);
+ i = 0;
+next_block:
+ if (unlikely(map_length < submit_len + blocksize ||
+ bio_add_page(bio, bvec->bv_page, blocksize,
+ bvec->bv_offset + (i * blocksize)) < blocksize)) {
/*
* inc the count before we submit the bio so
* we know the end IO handler won't happen before
@@ -8243,7 +8305,6 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
file_offset += submit_len;
submit_len = 0;
- nr_pages = 0;
bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
start_sector, GFP_NOFS);
@@ -8261,9 +8322,14 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
bio_put(bio);
goto out_err;
}
+
+ goto next_block;
} else {
- submit_len += bvec->bv_len;
- nr_pages++;
+ submit_len += blocksize;
+ if (--nr_sectors) {
+ i++;
+ goto next_block;
+ }
bvec++;
}
}
@@ -8628,6 +8694,8 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
struct extent_state *cached_state = NULL;
u64 page_start = page_offset(page);
u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
+ u64 start;
+ u64 end;
int inode_evicting = inode->i_state & I_FREEING;
/*
@@ -8647,14 +8715,18 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
if (!inode_evicting)
lock_extent_bits(tree, page_start, page_end, &cached_state);
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+again:
+ start = page_start;
+ ordered = btrfs_lookup_ordered_range(inode, start,
+ page_end - start + 1);
if (ordered) {
+ end = min(page_end, ordered->file_offset + ordered->len - 1);
/*
* IO on this page will never be started, so we need
* to account for any ordered extents now
*/
if (!inode_evicting)
- clear_extent_bit(tree, page_start, page_end,
+ clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, 1, 0, &cached_state,
@@ -8671,22 +8743,26 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
spin_lock_irq(&tree->lock);
set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
- new_len = page_start - ordered->file_offset;
+ new_len = start - ordered->file_offset;
if (new_len < ordered->truncated_len)
ordered->truncated_len = new_len;
spin_unlock_irq(&tree->lock);
if (btrfs_dec_test_ordered_pending(inode, &ordered,
- page_start,
- PAGE_CACHE_SIZE, 1))
+ start,
+ end - start + 1, 1))
btrfs_finish_ordered_io(ordered);
}
btrfs_put_ordered_extent(ordered);
if (!inode_evicting) {
cached_state = NULL;
- lock_extent_bits(tree, page_start, page_end,
+ lock_extent_bits(tree, start, end,
&cached_state);
}
+
+ start = end + 1;
+ if (start < page_end)
+ goto again;
}
/*
@@ -8747,15 +8823,28 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
loff_t size;
int ret;
int reserved = 0;
+ u64 reserved_space;
u64 page_start;
u64 page_end;
+ u64 end;
+
+ reserved_space = PAGE_CACHE_SIZE;
sb_start_pagefault(inode->i_sb);
page_start = page_offset(page);
page_end = page_start + PAGE_CACHE_SIZE - 1;
+ end = page_end;
+ /*
+ * Reserving delalloc space after obtaining the page lock can lead to
+ * deadlock. For example, if a dirty page is locked by this function
+ * and the call to btrfs_delalloc_reserve_space() ends up triggering
+ * dirty page write out, then the btrfs_writepage() function could
+ * end up waiting indefinitely to get a lock on the page currently
+ * being processed by btrfs_page_mkwrite() function.
+ */
ret = btrfs_delalloc_reserve_space(inode, page_start,
- PAGE_CACHE_SIZE);
+ reserved_space);
if (!ret) {
ret = file_update_time(vma->vm_file);
reserved = 1;
@@ -8789,7 +8878,7 @@ again:
* we can't set the delalloc bits if there are pending ordered
* extents. Drop our locks and wait for them to finish
*/
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+ ordered = btrfs_lookup_ordered_range(inode, page_start, page_end);
if (ordered) {
unlock_extent_cached(io_tree, page_start, page_end,
&cached_state, GFP_NOFS);
@@ -8799,6 +8888,18 @@ again:
goto again;
}
+ if (page->index == ((size - 1) >> PAGE_CACHE_SHIFT)) {
+ reserved_space = round_up(size - page_start, root->sectorsize);
+ if (reserved_space < PAGE_CACHE_SIZE) {
+ end = page_start + reserved_space - 1;
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->outstanding_extents++;
+ spin_unlock(&BTRFS_I(inode)->lock);
+ btrfs_delalloc_release_space(inode, page_start,
+ PAGE_CACHE_SIZE - reserved_space);
+ }
+ }
+
/*
* XXX - page_mkwrite gets called every time the page is dirtied, even
* if it was already dirty, so for space accounting reasons we need to
@@ -8806,12 +8907,12 @@ again:
* is probably a better way to do this, but for now keep consistent with
* prepare_pages in the normal write path.
*/
- clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+ ret = btrfs_set_extent_delalloc(inode, page_start, end,
&cached_state);
if (ret) {
unlock_extent_cached(io_tree, page_start, page_end,
@@ -8850,7 +8951,7 @@ out_unlock:
}
unlock_page(page);
out:
- btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE);
+ btrfs_delalloc_release_space(inode, page_start, reserved_space);
out_noreserve:
sb_end_pagefault(inode->i_sb);
return ret;
@@ -9236,7 +9337,6 @@ static int btrfs_getattr(struct vfsmount *mnt,
generic_fillattr(inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
- stat->blksize = PAGE_CACHE_SIZE;
spin_lock(&BTRFS_I(inode)->lock);
delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 952172ca7e45..9ba7b5be3fe5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2925,8 +2925,8 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
* of the array is bounded by len, which is in turn bounded by
* BTRFS_MAX_DEDUPE_LEN.
*/
- src_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
- dst_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
+ src_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
+ dst_pgarr = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
if (!src_pgarr || !dst_pgarr) {
kfree(src_pgarr);
kfree(dst_pgarr);
@@ -3814,8 +3814,9 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
* Truncate page cache pages so that future reads will see the cloned
* data immediately and not the previous data.
*/
- truncate_inode_pages_range(&inode->i_data, destoff,
- PAGE_CACHE_ALIGN(destoff + len) - 1);
+ truncate_inode_pages_range(&inode->i_data,
+ round_down(destoff, PAGE_CACHE_SIZE),
+ round_up(destoff + len, PAGE_CACHE_SIZE) - 1);
out_unlock:
if (!same_inode)
btrfs_double_inode_unlock(src, inode);
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 647ab12fdf5d..147dc6ca5de1 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -295,8 +295,27 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
btrfs_dev_extent_chunk_offset(l, dev_extent),
btrfs_dev_extent_length(l, dev_extent));
break;
- case BTRFS_DEV_STATS_KEY:
- printk(KERN_INFO "\t\tdevice stats\n");
+ case BTRFS_PERSISTENT_ITEM_KEY:
+ printk(KERN_INFO "\t\tpersistent item objectid %llu offset %llu\n",
+ key.objectid, key.offset);
+ switch (key.objectid) {
+ case BTRFS_DEV_STATS_OBJECTID:
+ printk(KERN_INFO "\t\tdevice stats\n");
+ break;
+ default:
+ printk(KERN_INFO "\t\tunknown persistent item\n");
+ }
+ break;
+ case BTRFS_TEMPORARY_ITEM_KEY:
+ printk(KERN_INFO "\t\ttemporary item objectid %llu offset %llu\n",
+ key.objectid, key.offset);
+ switch (key.objectid) {
+ case BTRFS_BALANCE_OBJECTID:
+ printk(KERN_INFO "\t\tbalance status\n");
+ break;
+ default:
+ printk(KERN_INFO "\t\tunknown temporary item\n");
+ }
break;
case BTRFS_DEV_REPLACE_KEY:
printk(KERN_INFO "\t\tdev replace\n");
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index dd5f361f1a8e..bf69c008249c 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -274,7 +274,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
end = start + cache->key.offset - 1;
btrfs_put_block_group(cache);
- zone = kzalloc(sizeof(*zone), GFP_NOFS);
+ zone = kzalloc(sizeof(*zone), GFP_KERNEL);
if (!zone)
return NULL;
@@ -339,7 +339,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
if (re)
return re;
- re = kzalloc(sizeof(*re), GFP_NOFS);
+ re = kzalloc(sizeof(*re), GFP_KERNEL);
if (!re)
return NULL;
@@ -562,7 +562,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical,
if (!re)
return -1;
- rec = kzalloc(sizeof(*rec), GFP_NOFS);
+ rec = kzalloc(sizeof(*rec), GFP_KERNEL);
if (!rec) {
reada_extent_put(root->fs_info, re);
return -ENOMEM;
@@ -792,7 +792,7 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
{
struct reada_machine_work *rmw;
- rmw = kzalloc(sizeof(*rmw), GFP_NOFS);
+ rmw = kzalloc(sizeof(*rmw), GFP_KERNEL);
if (!rmw) {
/* FIXME we cannot handle this properly right now */
BUG();
@@ -920,7 +920,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
.offset = (u64)-1
};
- rc = kzalloc(sizeof(*rc), GFP_NOFS);
+ rc = kzalloc(sizeof(*rc), GFP_KERNEL);
if (!rc)
return ERR_PTR(-ENOMEM);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 92bf5ee732fb..2de7817d0e1b 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -461,7 +461,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
int ret;
- sctx = kzalloc(sizeof(*sctx), GFP_NOFS);
+ sctx = kzalloc(sizeof(*sctx), GFP_KERNEL);
if (!sctx)
goto nomem;
atomic_set(&sctx->refs, 1);
@@ -472,7 +472,7 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) {
struct scrub_bio *sbio;
- sbio = kzalloc(sizeof(*sbio), GFP_NOFS);
+ sbio = kzalloc(sizeof(*sbio), GFP_KERNEL);
if (!sbio)
goto nomem;
sctx->bios[i] = sbio;
@@ -1654,7 +1654,7 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
again:
if (!wr_ctx->wr_curr_bio) {
wr_ctx->wr_curr_bio = kzalloc(sizeof(*wr_ctx->wr_curr_bio),
- GFP_NOFS);
+ GFP_KERNEL);
if (!wr_ctx->wr_curr_bio) {
mutex_unlock(&wr_ctx->wr_lock);
return -ENOMEM;
@@ -1671,7 +1671,8 @@ again:
sbio->dev = wr_ctx->tgtdev;
bio = sbio->bio;
if (!bio) {
- bio = btrfs_io_bio_alloc(GFP_NOFS, wr_ctx->pages_per_wr_bio);
+ bio = btrfs_io_bio_alloc(GFP_KERNEL,
+ wr_ctx->pages_per_wr_bio);
if (!bio) {
mutex_unlock(&wr_ctx->wr_lock);
return -ENOMEM;
@@ -2076,7 +2077,8 @@ again:
sbio->dev = spage->dev;
bio = sbio->bio;
if (!bio) {
- bio = btrfs_io_bio_alloc(GFP_NOFS, sctx->pages_per_rd_bio);
+ bio = btrfs_io_bio_alloc(GFP_KERNEL,
+ sctx->pages_per_rd_bio);
if (!bio)
return -ENOMEM;
sbio->bio = bio;
@@ -2241,7 +2243,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
struct scrub_block *sblock;
int index;
- sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+ sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
if (!sblock) {
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
@@ -2259,7 +2261,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
struct scrub_page *spage;
u64 l = min_t(u64, len, PAGE_SIZE);
- spage = kzalloc(sizeof(*spage), GFP_NOFS);
+ spage = kzalloc(sizeof(*spage), GFP_KERNEL);
if (!spage) {
leave_nomem:
spin_lock(&sctx->stat_lock);
@@ -2286,7 +2288,7 @@ leave_nomem:
spage->have_csum = 0;
}
sblock->page_count++;
- spage->page = alloc_page(GFP_NOFS);
+ spage->page = alloc_page(GFP_KERNEL);
if (!spage->page)
goto leave_nomem;
len -= l;
@@ -2541,7 +2543,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
struct scrub_block *sblock;
int index;
- sblock = kzalloc(sizeof(*sblock), GFP_NOFS);
+ sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
if (!sblock) {
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
@@ -2561,7 +2563,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
struct scrub_page *spage;
u64 l = min_t(u64, len, PAGE_SIZE);
- spage = kzalloc(sizeof(*spage), GFP_NOFS);
+ spage = kzalloc(sizeof(*spage), GFP_KERNEL);
if (!spage) {
leave_nomem:
spin_lock(&sctx->stat_lock);
@@ -2591,7 +2593,7 @@ leave_nomem:
spage->have_csum = 0;
}
sblock->page_count++;
- spage->page = alloc_page(GFP_NOFS);
+ spage->page = alloc_page(GFP_KERNEL);
if (!spage->page)
goto leave_nomem;
len -= l;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 63a6152be04b..d2e29925f1da 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -304,7 +304,7 @@ static struct fs_path *fs_path_alloc(void)
{
struct fs_path *p;
- p = kmalloc(sizeof(*p), GFP_NOFS);
+ p = kmalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return NULL;
p->reversed = 0;
@@ -363,11 +363,11 @@ static int fs_path_ensure_buf(struct fs_path *p, int len)
* First time the inline_buf does not suffice
*/
if (p->buf == p->inline_buf) {
- tmp_buf = kmalloc(len, GFP_NOFS);
+ tmp_buf = kmalloc(len, GFP_KERNEL);
if (tmp_buf)
memcpy(tmp_buf, p->buf, old_buf_len);
} else {
- tmp_buf = krealloc(p->buf, len, GFP_NOFS);
+ tmp_buf = krealloc(p->buf, len, GFP_KERNEL);
}
if (!tmp_buf)
return -ENOMEM;
@@ -995,7 +995,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
* values are small.
*/
buf_len = PATH_MAX;
- buf = kmalloc(buf_len, GFP_NOFS);
+ buf = kmalloc(buf_len, GFP_KERNEL);
if (!buf) {
ret = -ENOMEM;
goto out;
@@ -1042,7 +1042,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
buf = NULL;
} else {
char *tmp = krealloc(buf, buf_len,
- GFP_NOFS | __GFP_NOWARN);
+ GFP_KERNEL | __GFP_NOWARN);
if (!tmp)
kfree(buf);
@@ -1303,7 +1303,7 @@ static int find_extent_clone(struct send_ctx *sctx,
/* We only use this path under the commit sem */
tmp_path->need_commit_sem = 0;
- backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_NOFS);
+ backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_KERNEL);
if (!backref_ctx) {
ret = -ENOMEM;
goto out;
@@ -1984,7 +1984,7 @@ static int name_cache_insert(struct send_ctx *sctx,
nce_head = radix_tree_lookup(&sctx->name_cache,
(unsigned long)nce->ino);
if (!nce_head) {
- nce_head = kmalloc(sizeof(*nce_head), GFP_NOFS);
+ nce_head = kmalloc(sizeof(*nce_head), GFP_KERNEL);
if (!nce_head) {
kfree(nce);
return -ENOMEM;
@@ -2179,7 +2179,7 @@ out_cache:
/*
* Store the result of the lookup in the name cache.
*/
- nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_NOFS);
+ nce = kmalloc(sizeof(*nce) + fs_path_len(dest) + 1, GFP_KERNEL);
if (!nce) {
ret = -ENOMEM;
goto out;
@@ -2315,7 +2315,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
if (!path)
return -ENOMEM;
- name = kmalloc(BTRFS_PATH_NAME_MAX, GFP_NOFS);
+ name = kmalloc(BTRFS_PATH_NAME_MAX, GFP_KERNEL);
if (!name) {
btrfs_free_path(path);
return -ENOMEM;
@@ -2730,7 +2730,7 @@ static int __record_ref(struct list_head *head, u64 dir,
{
struct recorded_ref *ref;
- ref = kmalloc(sizeof(*ref), GFP_NOFS);
+ ref = kmalloc(sizeof(*ref), GFP_KERNEL);
if (!ref)
return -ENOMEM;
@@ -2755,7 +2755,7 @@ static int dup_ref(struct recorded_ref *ref, struct list_head *list)
{
struct recorded_ref *new;
- new = kmalloc(sizeof(*ref), GFP_NOFS);
+ new = kmalloc(sizeof(*ref), GFP_KERNEL);
if (!new)
return -ENOMEM;
@@ -2818,7 +2818,7 @@ add_orphan_dir_info(struct send_ctx *sctx, u64 dir_ino)
struct rb_node *parent = NULL;
struct orphan_dir_info *entry, *odi;
- odi = kmalloc(sizeof(*odi), GFP_NOFS);
+ odi = kmalloc(sizeof(*odi), GFP_KERNEL);
if (!odi)
return ERR_PTR(-ENOMEM);
odi->ino = dir_ino;
@@ -2973,7 +2973,7 @@ static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino, bool orphanized)
struct rb_node *parent = NULL;
struct waiting_dir_move *entry, *dm;
- dm = kmalloc(sizeof(*dm), GFP_NOFS);
+ dm = kmalloc(sizeof(*dm), GFP_KERNEL);
if (!dm)
return -ENOMEM;
dm->ino = ino;
@@ -3040,7 +3040,7 @@ static int add_pending_dir_move(struct send_ctx *sctx,
int exists = 0;
int ret;
- pm = kmalloc(sizeof(*pm), GFP_NOFS);
+ pm = kmalloc(sizeof(*pm), GFP_KERNEL);
if (!pm)
return -ENOMEM;
pm->parent_ino = parent_ino;
@@ -4280,7 +4280,7 @@ static int __find_xattr(int num, struct btrfs_key *di_key,
strncmp(name, ctx->name, name_len) == 0) {
ctx->found_idx = num;
ctx->found_data_len = data_len;
- ctx->found_data = kmemdup(data, data_len, GFP_NOFS);
+ ctx->found_data = kmemdup(data, data_len, GFP_KERNEL);
if (!ctx->found_data)
return -ENOMEM;
return 1;
@@ -4481,7 +4481,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
while (index <= last_index) {
unsigned cur_len = min_t(unsigned, len,
PAGE_CACHE_SIZE - pg_offset);
- page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
if (!page) {
ret = -ENOMEM;
break;
@@ -5989,7 +5989,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
goto out;
}
- sctx = kzalloc(sizeof(struct send_ctx), GFP_NOFS);
+ sctx = kzalloc(sizeof(struct send_ctx), GFP_KERNEL);
if (!sctx) {
ret = -ENOMEM;
goto out;
@@ -5997,7 +5997,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
INIT_LIST_HEAD(&sctx->new_refs);
INIT_LIST_HEAD(&sctx->deleted_refs);
- INIT_RADIX_TREE(&sctx->name_cache, GFP_NOFS);
+ INIT_RADIX_TREE(&sctx->name_cache, GFP_KERNEL);
INIT_LIST_HEAD(&sctx->name_cache_list);
sctx->flags = arg->flags;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d41e09fe8e38..bf75200c6f86 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -303,7 +303,8 @@ enum {
Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard,
Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow,
- Opt_datasum, Opt_treelog, Opt_noinode_cache,
+ Opt_datasum, Opt_treelog, Opt_noinode_cache, Opt_usebackuproot,
+ Opt_nologreplay, Opt_norecovery,
#ifdef CONFIG_BTRFS_DEBUG
Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
#endif
@@ -335,6 +336,8 @@ static const match_table_t tokens = {
{Opt_noacl, "noacl"},
{Opt_notreelog, "notreelog"},
{Opt_treelog, "treelog"},
+ {Opt_nologreplay, "nologreplay"},
+ {Opt_norecovery, "norecovery"},
{Opt_flushoncommit, "flushoncommit"},
{Opt_noflushoncommit, "noflushoncommit"},
{Opt_ratio, "metadata_ratio=%d"},
@@ -352,7 +355,8 @@ static const match_table_t tokens = {
{Opt_inode_cache, "inode_cache"},
{Opt_noinode_cache, "noinode_cache"},
{Opt_no_space_cache, "nospace_cache"},
- {Opt_recovery, "recovery"},
+ {Opt_recovery, "recovery"}, /* deprecated */
+ {Opt_usebackuproot, "usebackuproot"},
{Opt_skip_balance, "skip_balance"},
{Opt_check_integrity, "check_int"},
{Opt_check_integrity_including_extent_data, "check_int_data"},
@@ -373,7 +377,8 @@ static const match_table_t tokens = {
* reading in a new superblock is parsed here.
* XXX JDM: This needs to be cleaned up for remount.
*/
-int btrfs_parse_options(struct btrfs_root *root, char *options)
+int btrfs_parse_options(struct btrfs_root *root, char *options,
+ unsigned long new_flags)
{
struct btrfs_fs_info *info = root->fs_info;
substring_t args[MAX_OPT_ARGS];
@@ -393,8 +398,12 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
else if (cache_gen)
btrfs_set_opt(info->mount_opt, SPACE_CACHE);
+ /*
+ * Even the options are empty, we still need to do extra check
+ * against new flags
+ */
if (!options)
- goto out;
+ goto check;
/*
* strsep changes the string, duplicate it because parse_options
@@ -606,6 +615,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
btrfs_clear_and_info(root, NOTREELOG,
"enabling tree log");
break;
+ case Opt_norecovery:
+ case Opt_nologreplay:
+ btrfs_set_and_info(root, NOLOGREPLAY,
+ "disabling log replay at mount time");
+ break;
case Opt_flushoncommit:
btrfs_set_and_info(root, FLUSHONCOMMIT,
"turning on flush-on-commit");
@@ -696,8 +710,12 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
"disabling auto defrag");
break;
case Opt_recovery:
- btrfs_info(root->fs_info, "enabling auto recovery");
- btrfs_set_opt(info->mount_opt, RECOVERY);
+ btrfs_warn(root->fs_info,
+ "'recovery' is deprecated, use 'usebackuproot' instead");
+ case Opt_usebackuproot:
+ btrfs_info(root->fs_info,
+ "trying to use backup root at mount time");
+ btrfs_set_opt(info->mount_opt, USEBACKUPROOT);
break;
case Opt_skip_balance:
btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
@@ -792,6 +810,15 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
break;
}
}
+check:
+ /*
+ * Extra check for current option against current flag
+ */
+ if (btrfs_test_opt(root, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) {
+ btrfs_err(root->fs_info,
+ "nologreplay must be used with ro mount option");
+ ret = -EINVAL;
+ }
out:
if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE) &&
!btrfs_test_opt(root, FREE_SPACE_TREE) &&
@@ -1202,6 +1229,8 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
seq_puts(seq, ",ssd");
if (btrfs_test_opt(root, NOTREELOG))
seq_puts(seq, ",notreelog");
+ if (btrfs_test_opt(root, NOLOGREPLAY))
+ seq_puts(seq, ",nologreplay");
if (btrfs_test_opt(root, FLUSHONCOMMIT))
seq_puts(seq, ",flushoncommit");
if (btrfs_test_opt(root, DISCARD))
@@ -1228,8 +1257,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
seq_puts(seq, ",inode_cache");
if (btrfs_test_opt(root, SKIP_BALANCE))
seq_puts(seq, ",skip_balance");
- if (btrfs_test_opt(root, RECOVERY))
- seq_puts(seq, ",recovery");
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA))
seq_puts(seq, ",check_int_data");
@@ -1685,7 +1712,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
}
}
- ret = btrfs_parse_options(root, data);
+ ret = btrfs_parse_options(root, data, *flags);
if (ret) {
ret = -EINVAL;
goto restore;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 366b335946fa..6e0e4396d3a4 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -138,7 +138,7 @@ static struct btrfs_fs_devices *__alloc_fs_devices(void)
{
struct btrfs_fs_devices *fs_devs;
- fs_devs = kzalloc(sizeof(*fs_devs), GFP_NOFS);
+ fs_devs = kzalloc(sizeof(*fs_devs), GFP_KERNEL);
if (!fs_devs)
return ERR_PTR(-ENOMEM);
@@ -220,7 +220,7 @@ static struct btrfs_device *__alloc_device(void)
{
struct btrfs_device *dev;
- dev = kzalloc(sizeof(*dev), GFP_NOFS);
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
return ERR_PTR(-ENOMEM);
@@ -733,7 +733,8 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
* uuid mutex so nothing we touch in here is going to disappear.
*/
if (orig_dev->name) {
- name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
+ name = rcu_string_strdup(orig_dev->name->str,
+ GFP_KERNEL);
if (!name) {
kfree(device);
goto error;
@@ -2287,7 +2288,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
goto error;
}
- name = rcu_string_strdup(device_path, GFP_NOFS);
+ name = rcu_string_strdup(device_path, GFP_KERNEL);
if (!name) {
kfree(device);
ret = -ENOMEM;
@@ -2966,7 +2967,7 @@ static int insert_balance_item(struct btrfs_root *root,
}
key.objectid = BTRFS_BALANCE_OBJECTID;
- key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.type = BTRFS_TEMPORARY_ITEM_KEY;
key.offset = 0;
ret = btrfs_insert_empty_item(trans, root, path, &key,
@@ -3015,7 +3016,7 @@ static int del_balance_item(struct btrfs_root *root)
}
key.objectid = BTRFS_BALANCE_OBJECTID;
- key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.type = BTRFS_TEMPORARY_ITEM_KEY;
key.offset = 0;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
@@ -3867,7 +3868,7 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
return -ENOMEM;
key.objectid = BTRFS_BALANCE_OBJECTID;
- key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.type = BTRFS_TEMPORARY_ITEM_KEY;
key.offset = 0;
ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
@@ -6705,8 +6706,8 @@ int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info)
int item_size;
struct btrfs_dev_stats_item *ptr;
- key.objectid = 0;
- key.type = BTRFS_DEV_STATS_KEY;
+ key.objectid = BTRFS_DEV_STATS_OBJECTID;
+ key.type = BTRFS_PERSISTENT_ITEM_KEY;
key.offset = device->devid;
ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
if (ret) {
@@ -6753,8 +6754,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
int ret;
int i;
- key.objectid = 0;
- key.type = BTRFS_DEV_STATS_KEY;
+ key.objectid = BTRFS_DEV_STATS_OBJECTID;
+ key.type = BTRFS_PERSISTENT_ITEM_KEY;
key.offset = device->devid;
path = btrfs_alloc_path();
OpenPOWER on IntegriCloud