* 'for-linus-unmerged' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (45 commits)
Btrfs: fix __btrfs_map_block on 32 bit machines
btrfs: fix possible deadlock by clearing __GFP_FS flag
btrfs: check link counter overflow in link(2)
btrfs: don't mess with i_nlink of unlocked inode in rename()
Btrfs: check return value of btrfs_alloc_path()
Btrfs: fix OOPS of empty filesystem after balance
Btrfs: fix memory leak of empty filesystem after balance
Btrfs: fix return value of setflags ioctl
Btrfs: fix uncheck memory allocations
btrfs: make inode ref log recovery faster
Btrfs: add btrfs_trim_fs() to handle FITRIM
Btrfs: adjust btrfs_discard_extent() return errors and trimmed bytes
Btrfs: make btrfs_map_block() return entire free extent for each device of RAID0/1/10/DUP
Btrfs: make update_reserved_bytes() public
btrfs: return EXDEV when linking from different subvolumes
Btrfs: Per file/directory controls for COW and compression
Btrfs: add datacow flag in inode flag
btrfs: use GFP_NOFS instead of GFP_KERNEL
Btrfs: check return value of read_tree_block()
btrfs: properly access unaligned checksum buffer
...
Fix up trivial conflicts in fs/btrfs/volumes.c due to plug removal in
the block layer.
#include <linux/crc32c.h>
#include <linux/slab.h>
#include <linux/migrate.h>
+ #include <asm/unaligned.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
void btrfs_csum_final(u32 crc, char *result)
{
- *(__le32 *)result = ~cpu_to_le32(crc);
+ put_unaligned_le32(~crc, result);
}
/*
int num_copies = 0;
int mirror_num = 0;
+ clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
while (1) {
ret = read_extent_buffer_pages(io_tree, eb, start, 1,
!verify_parent_transid(io_tree, eb, parent_transid))
return ret;
+ /*
+ * This buffer's crc is fine, but its contents are corrupted, so
+ * there is no reason to read the other copies, they won't be
+ * any less wrong.
+ */
+ if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
+ return ret;
+
num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
eb->start, eb->len);
if (num_copies == 1)
return ret;
}
+ #define CORRUPT(reason, eb, root, slot) \
+ printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \
+ "root=%llu, slot=%d\n", reason, \
+ (unsigned long long)btrfs_header_bytenr(eb), \
+ (unsigned long long)root->objectid, slot)
+
+ static noinline int check_leaf(struct btrfs_root *root,
+ struct extent_buffer *leaf)
+ {
+ struct btrfs_key key;
+ struct btrfs_key leaf_key;
+ u32 nritems = btrfs_header_nritems(leaf);
+ int slot;
+
+ if (nritems == 0)
+ return 0;
+
+ /* Check the 0 item */
+ if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
+ BTRFS_LEAF_DATA_SIZE(root)) {
+ CORRUPT("invalid item offset size pair", leaf, root, 0);
+ return -EIO;
+ }
+
+ /*
+ * Check to make sure each items keys are in the correct order and their
+ * offsets make sense. We only have to loop through nritems-1 because
+ * we check the current slot against the next slot, which verifies the
+ * next slot's offset+size makes sense and that the current's slot
+ * offset is correct.
+ */
+ for (slot = 0; slot < nritems - 1; slot++) {
+ btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
+ btrfs_item_key_to_cpu(leaf, &key, slot + 1);
+
+ /* Make sure the keys are in the right order */
+ if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
+ CORRUPT("bad key order", leaf, root, slot);
+ return -EIO;
+ }
+
+ /*
+ * Make sure the offset and ends are right, remember that the
+ * item data starts at the end of the leaf and grows towards the
+ * front.
+ */
+ if (btrfs_item_offset_nr(leaf, slot) !=
+ btrfs_item_end_nr(leaf, slot + 1)) {
+ CORRUPT("slot offset bad", leaf, root, slot);
+ return -EIO;
+ }
+
+ /*
+ * Check to make sure that we don't point outside of the leaf,
+ * just incase all the items are consistent to eachother, but
+ * all point outside of the leaf.
+ */
+ if (btrfs_item_end_nr(leaf, slot) >
+ BTRFS_LEAF_DATA_SIZE(root)) {
+ CORRUPT("slot end outside of leaf", leaf, root, slot);
+ return -EIO;
+ }
+ }
+
+ return 0;
+ }
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb, int level)
{
btrfs_set_buffer_lockdep_class(eb, found_level);
ret = csum_tree_block(root, eb, 1);
- if (ret)
+ if (ret) {
ret = -EIO;
+ goto err;
+ }
+
+ /*
+ * If this is a leaf block and it is corrupt, set the corrupt bit so
+ * that we don't try and read the other copies of this block, just
+ * return -EIO.
+ */
+ if (found_level == 0 && check_leaf(root, eb)) {
+ set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
+ ret = -EIO;
+ }
end = min_t(u64, eb->len, PAGE_CACHE_SIZE);
end = eb->start + end - 1;
.writepages = btree_writepages,
.releasepage = btree_releasepage,
.invalidatepage = btree_invalidatepage,
- .sync_page = block_sync_page,
#ifdef CONFIG_MIGRATION
.migratepage = btree_migratepage,
#endif
root, fs_info, location->objectid);
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path) {
+ kfree(root);
+ return ERR_PTR(-ENOMEM);
+ }
ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0);
if (ret == 0) {
l = path->nodes[0];
}
/*
- * this unplugs every device on the box, and it is only used when page
- * is null
- */
-static void __unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
- struct btrfs_device *device;
- struct btrfs_fs_info *info;
-
- info = (struct btrfs_fs_info *)bdi->unplug_io_data;
- list_for_each_entry(device, &info->fs_devices->devices, dev_list) {
- if (!device->bdev)
- continue;
-
- bdi = blk_get_backing_dev_info(device->bdev);
- if (bdi->unplug_io_fn)
- bdi->unplug_io_fn(bdi, page);
- }
-}
-
-static void btrfs_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
- struct inode *inode;
- struct extent_map_tree *em_tree;
- struct extent_map *em;
- struct address_space *mapping;
- u64 offset;
-
- /* the generic O_DIRECT read code does this */
- if (1 || !page) {
- __unplug_io_fn(bdi, page);
- return;
- }
-
- /*
- * page->mapping may change at any time. Get a consistent copy
- * and use that for everything below
- */
- smp_mb();
- mapping = page->mapping;
- if (!mapping)
- return;
-
- inode = mapping->host;
-
- /*
- * don't do the expensive searching for a small number of
- * devices
- */
- if (BTRFS_I(inode)->root->fs_info->fs_devices->open_devices <= 2) {
- __unplug_io_fn(bdi, page);
- return;
- }
-
- offset = page_offset(page);
-
- em_tree = &BTRFS_I(inode)->extent_tree;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE);
- read_unlock(&em_tree->lock);
- if (!em) {
- __unplug_io_fn(bdi, page);
- return;
- }
-
- if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
- free_extent_map(em);
- __unplug_io_fn(bdi, page);
- return;
- }
- offset = offset - em->start;
- btrfs_unplug_page(&BTRFS_I(inode)->root->fs_info->mapping_tree,
- em->block_start + offset, page);
- free_extent_map(em);
-}
-
-/*
* If this fails, caller must call bdi_destroy() to get rid of the
* bdi again.
*/
return err;
bdi->ra_pages = default_backing_dev_info.ra_pages;
- bdi->unplug_io_fn = btrfs_unplug_io_fn;
- bdi->unplug_io_data = info;
bdi->congested_fn = btrfs_congested_fn;
bdi->congested_data = info;
return 0;
goto fail_bdi;
}
+ fs_info->btree_inode->i_mapping->flags &= ~__GFP_FS;
+
INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
+ /*
+ * In the long term, we'll store the compression type in the super
+ * block, and it'll be used for per file compression control.
+ */
+ fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
+
ret = btrfs_parse_options(tree_root, options);
if (ret) {
err = ret;
fs_info->metadata_alloc_profile = (u64)-1;
fs_info->system_alloc_profile = fs_info->metadata_alloc_profile;
+ ret = btrfs_init_space_info(fs_info);
+ if (ret) {
+ printk(KERN_ERR "Failed to initial space info: %d\n", ret);
+ goto fail_block_groups;
+ }
+
ret = btrfs_read_block_groups(extent_root);
if (ret) {
printk(KERN_ERR "Failed to read block groups: %d\n", ret);
if (!(sb->s_flags & MS_RDONLY)) {
down_read(&fs_info->cleanup_work_sem);
- btrfs_orphan_cleanup(fs_info->fs_root);
- btrfs_orphan_cleanup(fs_info->tree_root);
+ err = btrfs_orphan_cleanup(fs_info->fs_root);
+ if (!err)
+ err = btrfs_orphan_cleanup(fs_info->tree_root);
up_read(&fs_info->cleanup_work_sem);
+ if (err) {
+ close_ctree(tree_root);
+ return ERR_PTR(err);
+ }
}
return tree_root;
root_objectid = gang[ret - 1]->root_key.objectid + 1;
for (i = 0; i < ret; i++) {
+ int err;
+
root_objectid = gang[i]->root_key.objectid;
- btrfs_orphan_cleanup(gang[i]);
+ err = btrfs_orphan_cleanup(gang[i]);
+ if (err)
+ return err;
}
root_objectid++;
}
* ERROR state on disk.
*
* 2. when btrfs flips readonly just in btrfs_commit_super,
- * and in such case, btrfs cannnot write sb via btrfs_commit_super,
+ * and in such case, btrfs cannot write sb via btrfs_commit_super,
* and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag,
* btrfs will cleanup all FS resources first and write sb then.
*/
break;
/* opt_discard */
- ret = btrfs_error_discard_extent(root, start, end + 1 - start);
+ if (btrfs_test_opt(root, DISCARD))
+ ret = btrfs_error_discard_extent(root, start,
+ end + 1 - start,
+ NULL);
clear_extent_dirty(unpin, start, end, GFP_NOFS);
btrfs_error_unpin_extent_range(root, start, end);
unsigned long nr_written = 0;
if (wbc->sync_mode == WB_SYNC_ALL)
- write_flags = WRITE_SYNC_PLUG;
+ write_flags = WRITE_SYNC;
else
write_flags = WRITE;
+ trace___extent_writepage(page, inode, wbc);
+
WARN_ON(!PageLocked(page));
pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
if (page->index > end_index ||
"wanted %lu %lu\n", (unsigned long long)eb->start,
eb->len, start, min_len);
WARN_ON(1);
+ return -EINVAL;
}
p = extent_buffer_page(eb, i);
#include "tree-log.h"
#include "compression.h"
#include "locking.h"
+ #include "free-space-cache.h"
struct btrfs_iget_args {
u64 ino;
struct kmem_cache *btrfs_trans_handle_cachep;
struct kmem_cache *btrfs_transaction_cachep;
struct kmem_cache *btrfs_path_cachep;
+ struct kmem_cache *btrfs_free_space_cachep;
#define S_SHIFT 12
static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFLNK >> S_SHIFT] = BTRFS_FT_SYMLINK,
};
- static void btrfs_truncate(struct inode *inode);
+ static int btrfs_setsize(struct inode *inode, loff_t newsize);
+ static int btrfs_truncate(struct inode *inode);
static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end);
static noinline int cow_file_range(struct inode *inode,
struct page *locked_page,
unsigned long *nr_written, int unlock);
static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
- struct inode *inode, struct inode *dir)
+ struct inode *inode, struct inode *dir,
+ const struct qstr *qstr)
{
int err;
err = btrfs_init_acl(trans, inode, dir);
if (!err)
- err = btrfs_xattr_security_init(trans, inode, dir);
+ err = btrfs_xattr_security_init(trans, inode, dir, qstr);
return err;
}
struct async_extent *async_extent;
async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
+ BUG_ON(!async_extent);
async_extent->start = start;
async_extent->ram_size = ram_size;
async_extent->compressed_size = compressed_size;
*/
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) &&
(btrfs_test_opt(root, COMPRESS) ||
- (BTRFS_I(inode)->force_compress))) {
+ (BTRFS_I(inode)->force_compress) ||
+ (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))) {
WARN_ON(pages);
pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+ BUG_ON(!pages);
if (BTRFS_I(inode)->force_compress)
compress_type = BTRFS_I(inode)->force_compress;
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 0, nr_written);
else if (!btrfs_test_opt(root, COMPRESS) &&
- !(BTRFS_I(inode)->force_compress))
+ !(BTRFS_I(inode)->force_compress) &&
+ !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))
ret = cow_file_range(inode, locked_page, start, end,
page_started, nr_written, 1);
else
if (bio_flags & EXTENT_BIO_COMPRESSED) {
return btrfs_submit_compressed_read(inode, bio,
mirror_num, bio_flags);
- } else if (!skip_sum)
- btrfs_lookup_bio_sums(root, inode, bio, NULL);
+ } else if (!skip_sum) {
+ ret = btrfs_lookup_bio_sums(root, inode, bio, NULL);
+ if (ret)
+ return ret;
+ }
goto mapit;
} else if (!skip_sum) {
/* csum items have already been cloned */
static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
struct extent_state *state, int uptodate)
{
+ trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
+
ClearPagePrivate2(page);
return btrfs_finish_ordered_io(page->mapping->host, start, end);
}
else
rw = READ;
- BTRFS_I(inode)->io_tree.ops->submit_bio_hook(inode, rw, bio,
+ ret = BTRFS_I(inode)->io_tree.ops->submit_bio_hook(inode, rw, bio,
failrec->last_mirror,
failrec->bio_flags, 0);
- return 0;
+ return ret;
}
/*
* this cleans up any orphans that may be left on the list from the last use
* of this root.
*/
- void btrfs_orphan_cleanup(struct btrfs_root *root)
+ int btrfs_orphan_cleanup(struct btrfs_root *root)
{
struct btrfs_path *path;
struct extent_buffer *leaf;
int ret = 0, nr_unlink = 0, nr_truncate = 0;
if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED))
- return;
+ return 0;
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
path->reada = -1;
key.objectid = BTRFS_ORPHAN_OBJECTID;
while (1) {
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret < 0) {
- printk(KERN_ERR "Error searching slot for orphan: %d"
- "\n", ret);
- break;
- }
+ if (ret < 0)
+ goto out;
/*
* if ret == 0 means we found what we were searching for, which
* find the key and see if we have stuff that matches
*/
if (ret > 0) {
+ ret = 0;
if (path->slots[0] == 0)
break;
path->slots[0]--;
found_key.type = BTRFS_INODE_ITEM_KEY;
found_key.offset = 0;
inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
- BUG_ON(IS_ERR(inode));
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ goto out;
+ }
/*
* add this inode to the orphan list so btrfs_orphan_del does
*/
if (is_bad_inode(inode)) {
trans = btrfs_start_transaction(root, 0);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
btrfs_orphan_del(trans, inode);
btrfs_end_transaction(trans, root);
iput(inode);
/* if we have links, this was a truncate, lets do that */
if (inode->i_nlink) {
+ if (!S_ISREG(inode->i_mode)) {
+ WARN_ON(1);
+ iput(inode);
+ continue;
+ }
nr_truncate++;
- btrfs_truncate(inode);
+ ret = btrfs_truncate(inode);
} else {
nr_unlink++;
}
/* this will do delete_inode and everything for us */
iput(inode);
+ if (ret)
+ goto out;
}
- btrfs_free_path(path);
-
root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE;
if (root->orphan_block_rsv)
if (root->orphan_block_rsv || root->orphan_item_inserted) {
trans = btrfs_join_transaction(root, 1);
- BUG_ON(IS_ERR(trans));
- btrfs_end_transaction(trans, root);
+ if (!IS_ERR(trans))
+ btrfs_end_transaction(trans, root);
}
if (nr_unlink)
printk(KERN_INFO "btrfs: unlinked %d orphans\n", nr_unlink);
if (nr_truncate)
printk(KERN_INFO "btrfs: truncated %d orphans\n", nr_truncate);
+
+ out:
+ if (ret)
+ printk(KERN_CRIT "btrfs: could not do orphan cleanup %d\n", ret);
+ btrfs_free_path(path);
+ return ret;
}
/*
BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
alloc_group_block = btrfs_inode_block_group(leaf, inode_item);
+ if (location.objectid == BTRFS_FREE_SPACE_OBJECTID)
+ inode->i_mapping->flags &= ~__GFP_FS;
/*
* try to precache a NULL acl entry for files that don't have
* recovery code. It remove a link in a directory with a given name, and
* also drops the back refs in the inode to the directory
*/
- int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct inode *dir, struct inode *inode,
- const char *name, int name_len)
+ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct inode *dir, struct inode *inode,
+ const char *name, int name_len)
{
struct btrfs_path *path;
int ret = 0;
btrfs_i_size_write(dir, dir->i_size - name_len * 2);
inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
btrfs_update_inode(trans, root, dir);
- btrfs_drop_nlink(inode);
- ret = btrfs_update_inode(trans, root, inode);
out:
return ret;
}
+ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct inode *dir, struct inode *inode,
+ const char *name, int name_len)
+ {
+ int ret;
+ ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
+ if (!ret) {
+ btrfs_drop_nlink(inode);
+ ret = btrfs_update_inode(trans, root, inode);
+ }
+ return ret;
+ }
+
+
/* helper to check if there is any shared block in the path */
static int check_path_shared(struct btrfs_root *root,
struct btrfs_path *path)
return ret;
}
- int btrfs_cont_expand(struct inode *inode, loff_t size)
+ /*
+ * 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
+ * these file extents so that btrfs_get_extent will return a EXTENT_MAP_HOLE for
+ * the range between oldsize and size
+ */
+ 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_map *em = NULL;
struct extent_state *cached_state = NULL;
u64 mask = root->sectorsize - 1;
- u64 hole_start = (inode->i_size + mask) & ~mask;
+ u64 hole_start = (oldsize + mask) & ~mask;
u64 block_end = (size + mask) & ~mask;
u64 last_byte;
u64 cur_offset;
err = btrfs_drop_extents(trans, inode, cur_offset,
cur_offset + hole_size,
&hint_byte, 1);
- BUG_ON(err);
+ if (err)
+ break;
err = btrfs_insert_file_extent(trans, root,
inode->i_ino, cur_offset, 0,
0, hole_size, 0, hole_size,
0, 0, 0);
- BUG_ON(err);
+ if (err)
+ break;
btrfs_drop_extent_cache(inode, hole_start,
last_byte - 1, 0);
return err;
}
- static int btrfs_setattr_size(struct inode *inode, struct iattr *attr)
+ static int btrfs_setsize(struct inode *inode, loff_t newsize)
{
- struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_trans_handle *trans;
- unsigned long nr;
+ loff_t oldsize = i_size_read(inode);
int ret;
- if (attr->ia_size == inode->i_size)
+ if (newsize == oldsize)
return 0;
- if (attr->ia_size > inode->i_size) {
- unsigned long limit;
- limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
- if (attr->ia_size > inode->i_sb->s_maxbytes)
- return -EFBIG;
- if (limit != RLIM_INFINITY && attr->ia_size > limit) {
- send_sig(SIGXFSZ, current, 0);
- return -EFBIG;
- }
- }
-
- trans = btrfs_start_transaction(root, 5);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
-
- btrfs_set_trans_block_group(trans, inode);
-
- ret = btrfs_orphan_add(trans, inode);
- BUG_ON(ret);
-
- nr = trans->blocks_used;
- btrfs_end_transaction(trans, root);
- btrfs_btree_balance_dirty(root, nr);
-
- if (attr->ia_size > inode->i_size) {
- ret = btrfs_cont_expand(inode, attr->ia_size);
+ if (newsize > oldsize) {
+ i_size_write(inode, newsize);
+ btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ truncate_pagecache(inode, oldsize, newsize);
+ ret = btrfs_cont_expand(inode, oldsize, newsize);
if (ret) {
- btrfs_truncate(inode);
+ btrfs_setsize(inode, oldsize);
return ret;
}
- i_size_write(inode, attr->ia_size);
- btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
+ mark_inode_dirty(inode);
+ } else {
- trans = btrfs_start_transaction(root, 0);
- BUG_ON(IS_ERR(trans));
- btrfs_set_trans_block_group(trans, inode);
- trans->block_rsv = root->orphan_block_rsv;
- BUG_ON(!trans->block_rsv);
+ /*
+ * We're truncating a file that used to have good data down to
+ * zero. Make sure it gets into the ordered flush list so that
+ * any new writes get down to disk quickly.
+ */
+ if (newsize == 0)
+ BTRFS_I(inode)->ordered_data_close = 1;
- ret = btrfs_update_inode(trans, root, inode);
- BUG_ON(ret);
- if (inode->i_nlink > 0) {
- ret = btrfs_orphan_del(trans, inode);
- BUG_ON(ret);
- }
- nr = trans->blocks_used;
- btrfs_end_transaction(trans, root);
- btrfs_btree_balance_dirty(root, nr);
- return 0;
+ /* we don't support swapfiles, so vmtruncate shouldn't fail */
+ truncate_setsize(inode, newsize);
+ ret = btrfs_truncate(inode);
}
- /*
- * We're truncating a file that used to have good data down to
- * zero. Make sure it gets into the ordered flush list so that
- * any new writes get down to disk quickly.
- */
- if (attr->ia_size == 0)
- BTRFS_I(inode)->ordered_data_close = 1;
-
- /* we don't support swapfiles, so vmtruncate shouldn't fail */
- ret = vmtruncate(inode, attr->ia_size);
- BUG_ON(ret);
-
- return 0;
+ return ret;
}
static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
return err;
if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
- err = btrfs_setattr_size(inode, attr);
+ err = btrfs_setsize(inode, attr->ia_size);
if (err)
return err;
}
unsigned long nr;
int ret;
+ trace_btrfs_inode_evict(inode);
+
truncate_inode_pages(&inode->i_data, 0);
if (inode->i_nlink && (btrfs_root_refs(&root->root_item) != 0 ||
root == root->fs_info->tree_root))
BTRFS_I(inode)->root = root;
memcpy(&BTRFS_I(inode)->location, location, sizeof(*location));
btrfs_read_locked_inode(inode);
-
inode_tree_add(inode);
unlock_new_inode(inode);
if (new)
if (!IS_ERR(inode) && root != sub_root) {
down_read(&root->fs_info->cleanup_work_sem);
if (!(inode->i_sb->s_flags & MS_RDONLY))
- btrfs_orphan_cleanup(sub_root);
+ ret = btrfs_orphan_cleanup(sub_root);
up_read(&root->fs_info->cleanup_work_sem);
+ if (ret)
+ inode = ERR_PTR(ret);
}
return inode;
while (di_cur < di_total) {
struct btrfs_key location;
+ if (verify_dir_item(root, leaf, di))
+ break;
+
name_len = btrfs_dir_name_len(leaf, di);
if (name_len <= sizeof(tmp_name)) {
name_ptr = tmp_name;
return ERR_PTR(-ENOMEM);
if (dir) {
+ trace_btrfs_inode_request(dir);
+
ret = btrfs_set_inode_index(dir, index);
if (ret) {
iput(inode);
if ((mode & S_IFREG)) {
if (btrfs_test_opt(root, NODATASUM))
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
- if (btrfs_test_opt(root, NODATACOW))
+ if (btrfs_test_opt(root, NODATACOW) ||
+ (BTRFS_I(dir)->flags & BTRFS_INODE_NODATACOW))
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
}
insert_inode_hash(inode);
inode_tree_add(inode);
+
+ trace_btrfs_inode_new(inode);
+
return inode;
fail:
if (dir)
if (IS_ERR(inode))
goto out_unlock;
- err = btrfs_init_inode_security(trans, inode, dir);
+ err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err) {
drop_inode = 1;
goto out_unlock;
if (IS_ERR(inode))
goto out_unlock;
- err = btrfs_init_inode_security(trans, inode, dir);
+ err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err) {
drop_inode = 1;
goto out_unlock;
int err;
int drop_inode = 0;
- if (inode->i_nlink == 0)
- return -ENOENT;
-
/* do not allow sys_link's with other subvols of the same device */
if (root->objectid != BTRFS_I(inode)->root->objectid)
- return -EPERM;
+ return -EXDEV;
+
+ if (inode->i_nlink == ~0U)
+ return -EMLINK;
btrfs_inc_nlink(inode);
inode->i_ctime = CURRENT_TIME;
drop_on_err = 1;
- err = btrfs_init_inode_security(trans, inode, dir);
+ err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err)
goto out_fail;
}
write_unlock(&em_tree->lock);
out:
+
+ trace_btrfs_get_extent(root, em);
+
if (path)
btrfs_free_path(path);
if (trans) {
kfree(dip->csums);
kfree(dip);
+
+ /* If we had a csum failure make sure to clear the uptodate flag */
+ if (err)
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
dio_end_io(bio, err);
}
kfree(dip->csums);
kfree(dip);
+
+ /* If we had an error make sure to clear the uptodate flag */
+ if (err)
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
dio_end_io(bio, err);
}
__btrfs_submit_bio_start_direct_io,
__btrfs_submit_bio_done);
goto err;
- } else if (!skip_sum)
- btrfs_lookup_bio_sums_dio(root, inode, bio,
+ } else if (!skip_sum) {
+ ret = btrfs_lookup_bio_sums_dio(root, inode, bio,
file_offset, csums);
+ if (ret)
+ goto err;
+ }
ret = btrfs_map_bio(root, rw, bio, 0, 1);
err:
int nr_pages = 0;
u32 *csums = dip->csums;
int ret = 0;
+ int write = rw & REQ_WRITE;
bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
if (!bio)
goto out_err;
}
- if (!skip_sum)
+ /* Write's use the ordered csums */
+ if (!write && !skip_sum)
csums = csums + nr_pages;
start_sector += submit_len >> 9;
file_offset += submit_len;
}
dip->csums = NULL;
- if (!skip_sum) {
+ /* Write's use the ordered csum stuff, so we don't need dip->csums */
+ if (!write && !skip_sum) {
dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS);
if (!dip->csums) {
kfree(dip);
return ret;
}
- static void btrfs_truncate(struct inode *inode)
+ static int btrfs_truncate(struct inode *inode)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
+ int err = 0;
struct btrfs_trans_handle *trans;
unsigned long nr;
u64 mask = root->sectorsize - 1;
- if (!S_ISREG(inode->i_mode)) {
- WARN_ON(1);
- return;
- }
-
ret = btrfs_truncate_page(inode->i_mapping, inode->i_size);
if (ret)
- return;
+ return ret;
btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
+ trans = btrfs_start_transaction(root, 5);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ btrfs_set_trans_block_group(trans, inode);
+
+ ret = btrfs_orphan_add(trans, inode);
+ if (ret) {
+ btrfs_end_transaction(trans, root);
+ return ret;
+ }
+
+ nr = trans->blocks_used;
+ btrfs_end_transaction(trans, root);
+ btrfs_btree_balance_dirty(root, nr);
+
+ /* Now start a transaction for the truncate */
trans = btrfs_start_transaction(root, 0);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
btrfs_set_trans_block_group(trans, inode);
trans->block_rsv = root->orphan_block_rsv;
while (1) {
if (!trans) {
trans = btrfs_start_transaction(root, 0);
- BUG_ON(IS_ERR(trans));
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
btrfs_set_trans_block_group(trans, inode);
trans->block_rsv = root->orphan_block_rsv;
}
ret = btrfs_block_rsv_check(trans, root,
root->orphan_block_rsv, 0, 5);
- if (ret) {
- BUG_ON(ret != -EAGAIN);
+ if (ret == -EAGAIN) {
ret = btrfs_commit_transaction(trans, root);
- BUG_ON(ret);
+ if (ret)
+ return ret;
trans = NULL;
continue;
+ } else if (ret) {
+ err = ret;
+ break;
}
ret = btrfs_truncate_inode_items(trans, root, inode,
inode->i_size,
BTRFS_EXTENT_DATA_KEY);
- if (ret != -EAGAIN)
+ if (ret != -EAGAIN) {
+ err = ret;
break;
+ }
ret = btrfs_update_inode(trans, root, inode);
- BUG_ON(ret);
+ if (ret) {
+ err = ret;
+ break;
+ }
nr = trans->blocks_used;
btrfs_end_transaction(trans, root);
if (ret == 0 && inode->i_nlink > 0) {
ret = btrfs_orphan_del(trans, inode);
- BUG_ON(ret);
+ if (ret)
+ err = ret;
+ } else if (ret && inode->i_nlink > 0) {
+ /*
+ * Failed to do the truncate, remove us from the in memory
+ * orphan list.
+ */
+ ret = btrfs_orphan_del(NULL, inode);
}
ret = btrfs_update_inode(trans, root, inode);
- BUG_ON(ret);
+ if (ret && !err)
+ err = ret;
nr = trans->blocks_used;
ret = btrfs_end_transaction_throttle(trans, root);
- BUG_ON(ret);
+ if (ret && !err)
+ err = ret;
btrfs_btree_balance_dirty(root, nr);
+
+ return err;
}
/*
ei->index_cnt = (u64)-1;
ei->last_unlink_trans = 0;
- spin_lock_init(&ei->accounting_lock);
atomic_set(&ei->outstanding_extents, 0);
- ei->reserved_extents = 0;
+ atomic_set(&ei->reserved_extents, 0);
ei->ordered_data_close = 0;
ei->orphan_meta_reserved = 0;
WARN_ON(!list_empty(&inode->i_dentry));
WARN_ON(inode->i_data.nrpages);
WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents));
- WARN_ON(BTRFS_I(inode)->reserved_extents);
+ WARN_ON(atomic_read(&BTRFS_I(inode)->reserved_extents));
/*
* This can happen where we create an inode, but somebody else also
kmem_cache_destroy(btrfs_transaction_cachep);
if (btrfs_path_cachep)
kmem_cache_destroy(btrfs_path_cachep);
+ if (btrfs_free_space_cachep)
+ kmem_cache_destroy(btrfs_free_space_cachep);
}
int btrfs_init_cachep(void)
if (!btrfs_path_cachep)
goto fail;
+ btrfs_free_space_cachep = kmem_cache_create("btrfs_free_space_cache",
+ sizeof(struct btrfs_free_space), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ if (!btrfs_free_space_cachep)
+ goto fail;
+
return 0;
fail:
btrfs_destroy_cachep();
return 0;
}
+ /*
+ * If a file is moved, it will inherit the cow and compression flags of the new
+ * directory.
+ */
+ static void fixup_inode_flags(struct inode *dir, struct inode *inode)
+ {
+ struct btrfs_inode *b_dir = BTRFS_I(dir);
+ struct btrfs_inode *b_inode = BTRFS_I(inode);
+
+ if (b_dir->flags & BTRFS_INODE_NODATACOW)
+ b_inode->flags |= BTRFS_INODE_NODATACOW;
+ else
+ b_inode->flags &= ~BTRFS_INODE_NODATACOW;
+
+ if (b_dir->flags & BTRFS_INODE_COMPRESS)
+ b_inode->flags |= BTRFS_INODE_COMPRESS;
+ else
+ b_inode->flags &= ~BTRFS_INODE_COMPRESS;
+ }
+
static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
old_dentry->d_name.name,
old_dentry->d_name.len);
} else {
- btrfs_inc_nlink(old_dentry->d_inode);
- ret = btrfs_unlink_inode(trans, root, old_dir,
- old_dentry->d_inode,
- old_dentry->d_name.name,
- old_dentry->d_name.len);
+ ret = __btrfs_unlink_inode(trans, root, old_dir,
+ old_dentry->d_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, root, old_inode);
}
BUG_ON(ret);
}
}
+ fixup_inode_flags(new_dir, old_inode);
+
ret = btrfs_add_link(trans, new_dir, old_inode,
new_dentry->d_name.name,
new_dentry->d_name.len, 0, index);
if (IS_ERR(inode))
goto out_unlock;
- err = btrfs_init_inode_security(trans, inode, dir);
+ err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
if (err) {
drop_inode = 1;
goto out_unlock;
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
.readpages = btrfs_readpages,
- .sync_page = block_sync_page,
.direct_IO = btrfs_direct_IO,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
};
static const struct inode_operations btrfs_file_inode_operations = {
- .truncate = btrfs_truncate,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.setxattr = btrfs_setxattr,
#include <linux/xattr.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
+ #include <linux/blkdev.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
return 0;
}
+ static int check_flags(unsigned int flags)
+ {
+ if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
+ FS_NOATIME_FL | FS_NODUMP_FL | \
+ FS_SYNC_FL | FS_DIRSYNC_FL | \
+ FS_NOCOMP_FL | FS_COMPR_FL | \
+ FS_NOCOW_FL | FS_COW_FL))
+ return -EOPNOTSUPP;
+
+ if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL))
+ return -EINVAL;
+
+ if ((flags & FS_NOCOW_FL) && (flags & FS_COW_FL))
+ return -EINVAL;
+
+ return 0;
+ }
+
static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
{
struct inode *inode = file->f_path.dentry->d_inode;
if (copy_from_user(&flags, arg, sizeof(flags)))
return -EFAULT;
- if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
- FS_NOATIME_FL | FS_NODUMP_FL | \
- FS_SYNC_FL | FS_DIRSYNC_FL))
- return -EOPNOTSUPP;
+ ret = check_flags(flags);
+ if (ret)
+ return ret;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
return -EACCES;
mutex_lock(&inode->i_mutex);
else
ip->flags &= ~BTRFS_INODE_DIRSYNC;
+ /*
+ * The COMPRESS flag can only be changed by users, while the NOCOMPRESS
+ * flag may be changed automatically if compression code won't make
+ * things smaller.
+ */
+ if (flags & FS_NOCOMP_FL) {
+ ip->flags &= ~BTRFS_INODE_COMPRESS;
+ ip->flags |= BTRFS_INODE_NOCOMPRESS;
+ } else if (flags & FS_COMPR_FL) {
+ ip->flags |= BTRFS_INODE_COMPRESS;
+ ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
+ }
+ if (flags & FS_NOCOW_FL)
+ ip->flags |= BTRFS_INODE_NODATACOW;
+ else if (flags & FS_COW_FL)
+ ip->flags &= ~BTRFS_INODE_NODATACOW;
trans = btrfs_join_transaction(root, 1);
BUG_ON(IS_ERR(trans));
btrfs_end_transaction(trans, root);
mnt_drop_write(file->f_path.mnt);
+
+ ret = 0;
out_unlock:
mutex_unlock(&inode->i_mutex);
- return 0;
+ return ret;
}
static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
return put_user(inode->i_generation, arg);
}
+ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
+ {
+ struct btrfs_root *root = fdentry(file)->d_sb->s_fs_info;
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_device *device;
+ struct request_queue *q;
+ struct fstrim_range range;
+ u64 minlen = ULLONG_MAX;
+ u64 num_devices = 0;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ mutex_lock(&fs_info->fs_devices->device_list_mutex);
+ list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
+ if (!device->bdev)
+ continue;
+ q = bdev_get_queue(device->bdev);
+ if (blk_queue_discard(q)) {
+ num_devices++;
+ minlen = min((u64)q->limits.discard_granularity,
+ minlen);
+ }
+ }
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ if (!num_devices)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&range, arg, sizeof(range)))
+ return -EFAULT;
+
+ range.minlen = max(range.minlen, minlen);
+ ret = btrfs_trim_fs(root, &range);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(arg, &range, sizeof(range)))
+ return -EFAULT;
+
+ return 0;
+ }
+
static noinline int create_subvol(struct btrfs_root *root,
struct dentry *dentry,
char *name, int namelen,
if (ret)
goto fail;
- btrfs_orphan_cleanup(pending_snapshot->snap);
+ ret = btrfs_orphan_cleanup(pending_snapshot->snap);
+ if (ret)
+ goto fail;
parent = dget_parent(dentry);
inode = btrfs_lookup_dentry(parent->d_inode, dentry);
if (flags & ~BTRFS_SUBVOL_RDONLY)
return -EOPNOTSUPP;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
return -EACCES;
down_write(&root->fs_info->subvol_sem);
struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root;
struct btrfs_trans_handle *trans;
u64 transid;
+ int ret;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans))
return PTR_ERR(trans);
transid = trans->transid;
- btrfs_commit_transaction_async(trans, root, 0);
+ ret = btrfs_commit_transaction_async(trans, root, 0);
+ if (ret)
+ return ret;
if (argp)
if (copy_to_user(argp, &transid, sizeof(transid)))
return btrfs_ioctl_setflags(file, argp);
case FS_IOC_GETVERSION:
return btrfs_ioctl_getversion(file, argp);
+ case FITRIM:
+ return btrfs_ioctl_fitrim(file, argp);
case BTRFS_IOC_SNAP_CREATE:
return btrfs_ioctl_snap_create(file, argp, 0);
case BTRFS_IOC_SNAP_CREATE_V2:
#include "volumes.h"
#include "async-thread.h"
- struct map_lookup {
- u64 type;
- int io_align;
- int io_width;
- int stripe_len;
- int sector_size;
- int num_stripes;
- int sub_stripes;
- struct btrfs_bio_stripe stripes[];
- };
-
static int init_first_rw_device(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_device *device);
struct bio *cur;
int again = 0;
unsigned long num_run;
- unsigned long num_sync_run;
unsigned long batch_run = 0;
unsigned long limit;
unsigned long last_waited = 0;
limit = btrfs_async_submit_limit(fs_info);
limit = limit * 2 / 3;
- /* we want to make sure that every time we switch from the sync
- * list to the normal list, we unplug
- */
- num_sync_run = 0;
-
loop:
spin_lock(&device->io_lock);
spin_unlock(&device->io_lock);
- /*
- * if we're doing the regular priority list, make sure we unplug
- * for any high prio bios we've sent down
- */
- if (pending_bios == &device->pending_bios && num_sync_run > 0) {
- num_sync_run = 0;
- blk_run_backing_dev(bdi, NULL);
- }
-
while (pending) {
rmb();
BUG_ON(atomic_read(&cur->bi_cnt) == 0);
- if (cur->bi_rw & REQ_SYNC)
- num_sync_run++;
-
submit_bio(cur->bi_rw, cur);
num_run++;
batch_run++;
- if (need_resched()) {
- if (num_sync_run) {
- blk_run_backing_dev(bdi, NULL);
- num_sync_run = 0;
- }
+ if (need_resched())
cond_resched();
- }
/*
* we made progress, there is more work to do and the bdi
* against it before looping
*/
last_waited = ioc->last_waited;
- if (need_resched()) {
- if (num_sync_run) {
- blk_run_backing_dev(bdi, NULL);
- num_sync_run = 0;
- }
+ if (need_resched())
cond_resched();
- }
continue;
}
spin_lock(&device->io_lock);
}
}
- if (num_sync_run) {
- num_sync_run = 0;
- blk_run_backing_dev(bdi, NULL);
- }
- /*
- * IO has already been through a long path to get here. Checksumming,
- * async helper threads, perhaps compression. We've done a pretty
- * good job of collecting a batch of IO and should just unplug
- * the device right away.
- *
- * This will help anyone who is waiting on the IO, they might have
- * already unplugged, but managed to do so before the bio they
- * cared about found its way down here.
- */
- blk_run_backing_dev(bdi, NULL);
-
cond_resched();
if (again)
goto loop;
BUG_ON(ret);
+ trace_btrfs_chunk_free(root, map, chunk_offset, em->len);
+
if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
ret = btrfs_del_sys_chunk(root, chunk_objectid, chunk_offset);
BUG_ON(ret);
*num_bytes = chunk_bytes_by_type(type, calc_size,
map->num_stripes, sub_stripes);
+ trace_btrfs_chunk_alloc(info->chunk_root, map, start, *num_bytes);
+
em = alloc_extent_map(GFP_NOFS);
if (!em) {
ret = -ENOMEM;
item_size);
BUG_ON(ret);
}
+
kfree(chunk);
return 0;
}
static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
u64 logical, u64 *length,
struct btrfs_multi_bio **multi_ret,
- int mirror_num, struct page *unplug_page)
+ int mirror_num)
{
struct extent_map *em;
struct map_lookup *map;
struct extent_map_tree *em_tree = &map_tree->map_tree;
u64 offset;
u64 stripe_offset;
+ u64 stripe_end_offset;
u64 stripe_nr;
+ u64 stripe_nr_orig;
+ u64 stripe_nr_end;
int stripes_allocated = 8;
int stripes_required = 1;
int stripe_index;
int max_errors = 0;
struct btrfs_multi_bio *multi = NULL;
- if (multi_ret && !(rw & REQ_WRITE))
+ if (multi_ret && !(rw & (REQ_WRITE | REQ_DISCARD)))
stripes_allocated = 1;
again:
if (multi_ret) {
em = lookup_extent_mapping(em_tree, logical, *length);
read_unlock(&em_tree->lock);
- if (!em && unplug_page) {
- kfree(multi);
- return 0;
- }
-
if (!em) {
printk(KERN_CRIT "unable to find logical %llu len %llu\n",
(unsigned long long)logical,
max_errors = 1;
}
}
- if (multi_ret && (rw & REQ_WRITE) &&
+ if (rw & REQ_DISCARD) {
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_DUP |
+ BTRFS_BLOCK_GROUP_RAID10)) {
+ stripes_required = map->num_stripes;
+ }
+ }
+ if (multi_ret && (rw & (REQ_WRITE | REQ_DISCARD)) &&
stripes_allocated < stripes_required) {
stripes_allocated = map->num_stripes;
free_extent_map(em);
/* stripe_offset is the offset of this block in its stripe*/
stripe_offset = offset - stripe_offset;
- if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10 |
- BTRFS_BLOCK_GROUP_DUP)) {
+ if (rw & REQ_DISCARD)
+ *length = min_t(u64, em->len - offset, *length);
+ else if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID10 |
+ BTRFS_BLOCK_GROUP_DUP)) {
/* we limit the length of each bio to what fits in a stripe */
*length = min_t(u64, em->len - offset,
- map->stripe_len - stripe_offset);
+ map->stripe_len - stripe_offset);
} else {
*length = em->len - offset;
}
- if (!multi_ret && !unplug_page)
+ if (!multi_ret)
goto out;
num_stripes = 1;
stripe_index = 0;
- if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
- if (rw & REQ_WRITE)
+ stripe_nr_orig = stripe_nr;
+ stripe_nr_end = (offset + *length + map->stripe_len - 1) &
+ (~(map->stripe_len - 1));
+ do_div(stripe_nr_end, map->stripe_len);
+ stripe_end_offset = stripe_nr_end * map->stripe_len -
+ (offset + *length);
+ if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+ if (rw & REQ_DISCARD)
+ num_stripes = min_t(u64, map->num_stripes,
+ stripe_nr_end - stripe_nr_orig);
+ stripe_index = do_div(stripe_nr, map->num_stripes);
+ } else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
- if (unplug_page || (rw & (REQ_WRITE | REQ_DISCARD)))
++ if (rw & (REQ_WRITE | REQ_DISCARD))
num_stripes = map->num_stripes;
else if (mirror_num)
stripe_index = mirror_num - 1;
}
} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
- if (rw & REQ_WRITE)
+ if (rw & (REQ_WRITE | REQ_DISCARD))
num_stripes = map->num_stripes;
else if (mirror_num)
stripe_index = mirror_num - 1;
stripe_index = do_div(stripe_nr, factor);
stripe_index *= map->sub_stripes;
- if (unplug_page || (rw & REQ_WRITE))
+ if (rw & REQ_WRITE)
num_stripes = map->sub_stripes;
+ else if (rw & REQ_DISCARD)
+ num_stripes = min_t(u64, map->sub_stripes *
+ (stripe_nr_end - stripe_nr_orig),
+ map->num_stripes);
else if (mirror_num)
stripe_index += mirror_num - 1;
else {
}
BUG_ON(stripe_index >= map->num_stripes);
- for (i = 0; i < num_stripes; i++) {
- multi->stripes[i].physical =
- map->stripes[stripe_index].physical +
- stripe_offset + stripe_nr * map->stripe_len;
- multi->stripes[i].dev = map->stripes[stripe_index].dev;
- stripe_index++;
+ if (rw & REQ_DISCARD) {
+ for (i = 0; i < num_stripes; i++) {
+ multi->stripes[i].physical =
+ map->stripes[stripe_index].physical +
+ stripe_offset + stripe_nr * map->stripe_len;
+ multi->stripes[i].dev = map->stripes[stripe_index].dev;
+
+ if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+ u64 stripes;
+ u32 last_stripe = 0;
+ int j;
+
+ div_u64_rem(stripe_nr_end - 1,
+ map->num_stripes,
+ &last_stripe);
+
+ for (j = 0; j < map->num_stripes; j++) {
+ u32 test;
+
+ div_u64_rem(stripe_nr_end - 1 - j,
+ map->num_stripes, &test);
+ if (test == stripe_index)
+ break;
+ }
+ stripes = stripe_nr_end - 1 - j;
+ do_div(stripes, map->num_stripes);
+ multi->stripes[i].length = map->stripe_len *
+ (stripes - stripe_nr + 1);
+
+ if (i == 0) {
+ multi->stripes[i].length -=
+ stripe_offset;
+ stripe_offset = 0;
+ }
+ if (stripe_index == last_stripe)
+ multi->stripes[i].length -=
+ stripe_end_offset;
+ } else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
+ u64 stripes;
+ int j;
+ int factor = map->num_stripes /
+ map->sub_stripes;
+ u32 last_stripe = 0;
+
+ div_u64_rem(stripe_nr_end - 1,
+ factor, &last_stripe);
+ last_stripe *= map->sub_stripes;
+
+ for (j = 0; j < factor; j++) {
+ u32 test;
+
+ div_u64_rem(stripe_nr_end - 1 - j,
+ factor, &test);
+
+ if (test ==
+ stripe_index / map->sub_stripes)
+ break;
+ }
+ stripes = stripe_nr_end - 1 - j;
+ do_div(stripes, factor);
+ multi->stripes[i].length = map->stripe_len *
+ (stripes - stripe_nr + 1);
+
+ if (i < map->sub_stripes) {
+ multi->stripes[i].length -=
+ stripe_offset;
+ if (i == map->sub_stripes - 1)
+ stripe_offset = 0;
+ }
+ if (stripe_index >= last_stripe &&
+ stripe_index <= (last_stripe +
+ map->sub_stripes - 1)) {
+ multi->stripes[i].length -=
+ stripe_end_offset;
+ }
+ } else
+ multi->stripes[i].length = *length;
+
+ stripe_index++;
+ if (stripe_index == map->num_stripes) {
+ /* This could only happen for RAID0/10 */
+ stripe_index = 0;
+ stripe_nr++;
+ }
+ }
+ } else {
+ for (i = 0; i < num_stripes; i++) {
- if (unplug_page) {
- struct btrfs_device *device;
- struct backing_dev_info *bdi;
-
- device = map->stripes[stripe_index].dev;
- if (device->bdev) {
- bdi = blk_get_backing_dev_info(device->
- bdev);
- if (bdi->unplug_io_fn)
- bdi->unplug_io_fn(bdi,
- unplug_page);
- }
- } else {
- multi->stripes[i].physical =
- map->stripes[stripe_index].physical +
- stripe_offset +
- stripe_nr * map->stripe_len;
- multi->stripes[i].dev =
- map->stripes[stripe_index].dev;
- }
++ multi->stripes[i].physical =
++ map->stripes[stripe_index].physical +
++ stripe_offset +
++ stripe_nr * map->stripe_len;
++ multi->stripes[i].dev =
++ map->stripes[stripe_index].dev;
+ stripe_index++;
+ }
}
if (multi_ret) {
*multi_ret = multi;
struct btrfs_multi_bio **multi_ret, int mirror_num)
{
return __btrfs_map_block(map_tree, rw, logical, length, multi_ret,
- mirror_num, NULL);
+ mirror_num);
}
int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
free_extent_map(em);
return 0;
-}
-
-int btrfs_unplug_page(struct btrfs_mapping_tree *map_tree,
- u64 logical, struct page *page)
-{
- u64 length = PAGE_CACHE_SIZE;
- return __btrfs_map_block(map_tree, READ, logical, &length,
- NULL, 0, page);
}
static void end_bio_multi_stripe(struct bio *bio, int err)
break;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
+ if (verify_dir_item(root, leaf, di))
+ continue;
name_len = btrfs_dir_name_len(leaf, di);
total_size += name_len + 1;
}
int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
- struct inode *inode, struct inode *dir)
+ struct inode *inode, struct inode *dir,
+ const struct qstr *qstr)
{
int err;
size_t len;
char *suffix;
char *name;
- err = security_inode_init_security(inode, dir, &suffix, &value, &len);
+ err = security_inode_init_security(inode, dir, qstr, &suffix, &value,
+ &len);
if (err) {
if (err == -EOPNOTSUPP)
return 0;
/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
+/* File is opened with O_PATH; almost nothing can be done with it */
+#define FMODE_PATH ((__force fmode_t)0x4000)
+
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
* block layer could (in theory) choose to ignore this
* request if it runs into resource problems.
* WRITE A normal async write. Device will be plugged.
- * WRITE_SYNC_PLUG Synchronous write. Identical to WRITE, but passes down
+ * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down
* the hint that someone will be waiting on this IO
- * shortly. The device must still be unplugged explicitly,
- * WRITE_SYNC_PLUG does not do this as we could be
- * submitting more writes before we actually wait on any
- * of them.
- * WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device
- * immediately after submission. The write equivalent
- * of READ_SYNC.
- * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only.
+ * shortly. The write equivalent of READ_SYNC.
+ * WRITE_ODIRECT Special case write for O_DIRECT only.
* WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush.
* WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on
* non-volatile media on completion.
#define WRITE RW_MASK
#define READA RWA_MASK
-#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG)
+#define READ_SYNC (READ | REQ_SYNC)
#define READ_META (READ | REQ_META)
-#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE)
-#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
-#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC)
+#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
+#define WRITE_ODIRECT (WRITE | REQ_SYNC)
#define WRITE_META (WRITE | REQ_META)
-#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
- REQ_FLUSH)
-#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
- REQ_FUA)
-#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
- REQ_FLUSH | REQ_FUA)
+#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
+#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
+#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
#define SEL_IN 1
#define SEL_OUT 2
#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define FS_EXTENT_FL 0x00080000 /* Extents */
#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */
+ #define FS_NOCOW_FL 0x00800000 /* Do not cow file */
+ #define FS_COW_FL 0x02000000 /* Cow file */
#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */
#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*readpage)(struct file *, struct page *);
- void (*sync_page)(struct page *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
struct block_device {
dev_t bd_dev; /* not a kdev_t - it's a search key */
+ int bd_openers;
struct inode * bd_inode; /* will die */
struct super_block * bd_super;
- int bd_openers;
struct mutex bd_mutex; /* open/close mutex */
struct list_head bd_inodes;
void * bd_claiming;
#endif
#ifdef CONFIG_IMA
- /* protected by i_lock */
- unsigned int i_readcount; /* struct files open RO */
+ atomic_t i_readcount; /* struct files open RO */
#endif
atomic_t i_writecount;
#ifdef CONFIG_SECURITY
#endif
};
+struct file_handle {
+ __u32 handle_bytes;
+ int handle_type;
+ /* file identifier */
+ unsigned char f_handle[0];
+};
+
#define get_file(x) atomic_long_inc(&(x)->f_count)
#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
#define file_count(x) atomic_long_read(&(x)->f_count)
wait_queue_head_t s_wait_unfrozen;
char s_id[32]; /* Informational name */
+ u8 s_uuid[16]; /* UUID */
void *s_fs_info; /* Filesystem private info */
fmode_t s_mode;
#define put_fs_excl() atomic_dec(¤t->fs_excl)
#define has_fs_excl() atomic_read(¤t->fs_excl)
-#define is_owner_or_cap(inode) \
- ((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
+/*
+ * until VFS tracks user namespaces for inodes, just make all files
+ * belong to init_user_ns
+ */
+extern struct user_namespace init_user_ns;
+#define inode_userns(inode) (&init_user_ns)
+extern bool inode_owner_or_capable(const struct inode *inode);
/* not quite ready to be deprecated, but... */
extern void lock_super(struct super_block *);
void (*umount_begin) (struct super_block *);
int (*show_options)(struct seq_file *, struct vfsmount *);
+ int (*show_devname)(struct seq_file *, struct vfsmount *);
+ int (*show_path)(struct seq_file *, struct vfsmount *);
int (*show_stats)(struct seq_file *, struct vfsmount *);
#ifdef CONFIG_QUOTA
ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
};
/*
- * Inode state bits. Protected by inode_lock.
+ * Inode state bits. Protected by inode->i_lock
*
* Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
* I_DIRTY_DATASYNC and I_DIRTY_PAGES.
struct file_system_type {
const char *name;
int fs_flags;
- int (*get_sb) (struct file_system_type *, int,
- const char *, void *, struct vfsmount *);
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
void (*kill_sb) (struct super_block *);
extern struct dentry *mount_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
int (*fill_super)(struct super_block *, void *, int));
-extern int get_sb_bdev(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data,
- int (*fill_super)(struct super_block *, void *, int),
- struct vfsmount *mnt);
extern struct dentry *mount_single(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
-extern int get_sb_single(struct file_system_type *fs_type,
- int flags, void *data,
- int (*fill_super)(struct super_block *, void *, int),
- struct vfsmount *mnt);
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
-extern int get_sb_nodev(struct file_system_type *fs_type,
- int flags, void *data,
- int (*fill_super)(struct super_block *, void *, int),
- struct vfsmount *mnt);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
const struct super_operations *ops,
const struct dentry_operations *dops,
unsigned long);
-extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
static inline void sb_mark_dirty(struct super_block *sb)
{
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
struct vfsmount *);
extern int vfs_statfs(struct path *, struct kstatfs *);
+extern int user_statfs(const char __user *, struct kstatfs *);
+extern int fd_statfs(int, struct kstatfs *);
extern int statfs_by_dentry(struct dentry *, struct kstatfs *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
int mode);
extern struct file *filp_open(const char *, int, int);
+extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+ const char *, int);
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
const struct cred *);
extern int filp_close(struct file *, fl_owner_t id);
if (file)
atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
}
+#ifdef CONFIG_IMA
+static inline void i_readcount_dec(struct inode *inode)
+{
+ BUG_ON(!atomic_read(&inode->i_readcount));
+ atomic_dec(&inode->i_readcount);
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+ atomic_inc(&inode->i_readcount);
+}
+#else
+static inline void i_readcount_dec(struct inode *inode)
+{
+ return;
+}
+static inline void i_readcount_inc(struct inode *inode)
+{
+ return;
+}
+#endif
extern int do_pipe_flags(int *, int);
extern struct file *create_read_pipe(struct file *f, int flags);
extern struct file *create_write_pipe(int flags);
extern void free_write_pipe(struct file *);
-extern struct file *do_filp_open(int dfd, const char *pathname,
- int open_flag, int mode, int acc_mode);
-extern int may_open(struct path *, int, int);
-
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
extern struct file * open_exec(const char *);