linux/fs/btrfs/reflink.c
Filipe Manana 3660d0bcdb btrfs: fix stale data exposure after cloning a hole with NO_HOLES enabled
When using the NO_HOLES feature, if we clone a file range that spans only
a hole into a range that is at or beyond the current i_size of the
destination file, we end up not setting the full sync runtime flag on the
inode. As a result, if we then fsync the destination file and have a power
failure, after log replay we can end up exposing stale data instead of
having a hole for that range.

The conditions for this to happen are the following:

1) We have a file with a size of, for example, 1280K;

2) There is a written (non-prealloc) extent for the file range from 1024K
   to 1280K with a length of 256K;

3) This particular file extent layout is durably persisted, so that the
   existing superblock persisted on disk points to a subvolume root where
   the file has that exact file extent layout and state;

4) The file is truncated to a smaller size, to an offset lower than the
   start offset of its last extent, for example to 800K. The truncate sets
   the full sync runtime flag on the inode;

6) Fsync the file to log it and clear the full sync runtime flag;

7) Clone a region that covers only a hole (implicit hole due to NO_HOLES)
   into the file with a destination offset that starts at or beyond the
   256K file extent item we had - for example to offset 1024K;

8) Since the clone operation does not find extents in the source range,
   we end up in the if branch at the bottom of btrfs_clone() where we
   punch a hole for the file range starting at offset 1024K by calling
   btrfs_replace_file_extents(). There we end up not setting the full
   sync flag on the inode, because we don't know we are being called in
   a clone context (and not fallocate's punch hole operation), and
   neither do we create an extent map to represent a hole because the
   requested range is beyond eof;

9) A further fsync to the file will be a fast fsync, since the clone
   operation did not set the full sync flag, and therefore it relies on
   modified extent maps to correctly log the file layout. But since
   it does not find any extent map marking the range from 1024K (the
   previous eof) to the new eof, it does not log a file extent item
   for that range representing the hole;

10) After a power failure no hole for the range starting at 1024K is
   punched and we end up exposing stale data from the old 256K extent.

Turning this into exact steps:

  $ mkfs.btrfs -f -O no-holes /dev/sdi
  $ mount /dev/sdi /mnt

  # Create our test file with 3 extents of 256K and a 256K hole at offset
  # 256K. The file has a size of 1280K.
  $ xfs_io -f -s \
              -c "pwrite -S 0xab -b 256K 0 256K" \
              -c "pwrite -S 0xcd -b 256K 512K 256K" \
              -c "pwrite -S 0xef -b 256K 768K 256K" \
              -c "pwrite -S 0x73 -b 256K 1024K 256K" \
              /mnt/sdi/foobar

  # Make sure it's durably persisted. We want the last committed super
  # block to point to this particular file extent layout.
  sync

  # Now truncate our file to a smaller size, falling within a position of
  # the second extent. This sets the full sync runtime flag on the inode.
  # Then fsync the file to log it and clear the full sync flag from the
  # inode. The third extent is no longer part of the file and therefore
  # it is not logged.
  $ xfs_io -c "truncate 800K" -c "fsync" /mnt/foobar

  # Now do a clone operation that only clones the hole and sets back the
  # file size to match the size it had before the truncate operation
  # (1280K).
  $ xfs_io \
        -c "reflink /mnt/foobar 256K 1024K 256K" \
        -c "fsync" \
        /mnt/foobar

  # File data before power failure:
  $ od -A d -t x1 /mnt/foobar
  0000000 ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab
  *
  0262144 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  *
  0524288 cd cd cd cd cd cd cd cd cd cd cd cd cd cd cd cd
  *
  0786432 ef ef ef ef ef ef ef ef ef ef ef ef ef ef ef ef
  *
  0819200 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  *
  1310720

  <power fail>

  # Mount the fs again to replay the log tree.
  $ mount /dev/sdi /mnt

  # File data after power failure:
  $ od -A d -t x1 /mnt/foobar
  0000000 ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab ab
  *
  0262144 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  *
  0524288 cd cd cd cd cd cd cd cd cd cd cd cd cd cd cd cd
  *
  0786432 ef ef ef ef ef ef ef ef ef ef ef ef ef ef ef ef
  *
  0819200 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
  *
  1048576 73 73 73 73 73 73 73 73 73 73 73 73 73 73 73 73
  *
  1310720

The range from 1024K to 1280K should correspond to a hole but instead it
points to stale data, to the 256K extent that should not exist after the
truncate operation.

The issue does not exists when not using NO_HOLES, because for that case
we use file extent items to represent holes, these are found and copied
during the loop that iterates over extents at btrfs_clone(), and that
causes btrfs_replace_file_extents() to be called with a non-NULL
extent_info argument and therefore set the full sync runtime flag on the
inode.

So fix this by making the code that deals with a trailing hole during
cloning, at btrfs_clone(), to set the full sync flag on the inode, if the
range starts at or beyond the current i_size.

A test case for fstests will follow soon.

Backporting notes: for kernel 5.4 the change goes to ioctl.c into
btrfs_clone before the last call to btrfs_punch_hole_range.

CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
2021-02-22 18:07:45 +01:00

862 lines
26 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/blkdev.h>
#include <linux/iversion.h>
#include "compression.h"
#include "ctree.h"
#include "delalloc-space.h"
#include "reflink.h"
#include "transaction.h"
#define BTRFS_MAX_DEDUPE_LEN SZ_16M
static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
struct inode *inode,
u64 endoff,
const u64 destoff,
const u64 olen,
int no_time_update)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
inode_inc_iversion(inode);
if (!no_time_update)
inode->i_mtime = inode->i_ctime = current_time(inode);
/*
* We round up to the block size at eof when determining which
* extents to clone above, but shouldn't round up the file size.
*/
if (endoff > destoff + olen)
endoff = destoff + olen;
if (endoff > inode->i_size) {
i_size_write(inode, endoff);
btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
}
ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
if (ret) {
btrfs_abort_transaction(trans, ret);
btrfs_end_transaction(trans);
goto out;
}
ret = btrfs_end_transaction(trans);
out:
return ret;
}
static int copy_inline_to_page(struct btrfs_inode *inode,
const u64 file_offset,
char *inline_data,
const u64 size,
const u64 datal,
const u8 comp_type)
{
const u64 block_size = btrfs_inode_sectorsize(inode);
const u64 range_end = file_offset + block_size - 1;
const size_t inline_size = size - btrfs_file_extent_calc_inline_size(0);
char *data_start = inline_data + btrfs_file_extent_calc_inline_size(0);
struct extent_changeset *data_reserved = NULL;
struct page *page = NULL;
struct address_space *mapping = inode->vfs_inode.i_mapping;
int ret;
ASSERT(IS_ALIGNED(file_offset, block_size));
/*
* We have flushed and locked the ranges of the source and destination
* inodes, we also have locked the inodes, so we are safe to do a
* reservation here. Also we must not do the reservation while holding
* a transaction open, otherwise we would deadlock.
*/
ret = btrfs_delalloc_reserve_space(inode, &data_reserved, file_offset,
block_size);
if (ret)
goto out;
page = find_or_create_page(mapping, file_offset >> PAGE_SHIFT,
btrfs_alloc_write_mask(mapping));
if (!page) {
ret = -ENOMEM;
goto out_unlock;
}
ret = set_page_extent_mapped(page);
if (ret < 0)
goto out_unlock;
clear_extent_bit(&inode->io_tree, file_offset, range_end,
EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, NULL);
ret = btrfs_set_extent_delalloc(inode, file_offset, range_end, 0, NULL);
if (ret)
goto out_unlock;
/*
* After dirtying the page our caller will need to start a transaction,
* and if we are low on metadata free space, that can cause flushing of
* delalloc for all inodes in order to get metadata space released.
* However we are holding the range locked for the whole duration of
* the clone/dedupe operation, so we may deadlock if that happens and no
* other task releases enough space. So mark this inode as not being
* possible to flush to avoid such deadlock. We will clear that flag
* when we finish cloning all extents, since a transaction is started
* after finding each extent to clone.
*/
set_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &inode->runtime_flags);
if (comp_type == BTRFS_COMPRESS_NONE) {
char *map;
map = kmap(page);
memcpy(map, data_start, datal);
flush_dcache_page(page);
kunmap(page);
} else {
ret = btrfs_decompress(comp_type, data_start, page, 0,
inline_size, datal);
if (ret)
goto out_unlock;
flush_dcache_page(page);
}
/*
* If our inline data is smaller then the block/page size, then the
* remaining of the block/page is equivalent to zeroes. We had something
* like the following done:
*
* $ xfs_io -f -c "pwrite -S 0xab 0 500" file
* $ sync # (or fsync)
* $ xfs_io -c "falloc 0 4K" file
* $ xfs_io -c "pwrite -S 0xcd 4K 4K"
*
* So what's in the range [500, 4095] corresponds to zeroes.
*/
if (datal < block_size) {
char *map;
map = kmap(page);
memset(map + datal, 0, block_size - datal);
flush_dcache_page(page);
kunmap(page);
}
SetPageUptodate(page);
ClearPageChecked(page);
set_page_dirty(page);
out_unlock:
if (page) {
unlock_page(page);
put_page(page);
}
if (ret)
btrfs_delalloc_release_space(inode, data_reserved, file_offset,
block_size, true);
btrfs_delalloc_release_extents(inode, block_size);
out:
extent_changeset_free(data_reserved);
return ret;
}
/*
* Deal with cloning of inline extents. We try to copy the inline extent from
* the source inode to destination inode when possible. When not possible we
* copy the inline extent's data into the respective page of the inode.
*/
static int clone_copy_inline_extent(struct inode *dst,
struct btrfs_path *path,
struct btrfs_key *new_key,
const u64 drop_start,
const u64 datal,
const u64 size,
const u8 comp_type,
char *inline_data,
struct btrfs_trans_handle **trans_out)
{
struct btrfs_fs_info *fs_info = btrfs_sb(dst->i_sb);
struct btrfs_root *root = BTRFS_I(dst)->root;
const u64 aligned_end = ALIGN(new_key->offset + datal,
fs_info->sectorsize);
struct btrfs_trans_handle *trans = NULL;
struct btrfs_drop_extents_args drop_args = { 0 };
int ret;
struct btrfs_key key;
if (new_key->offset > 0) {
ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
inline_data, size, datal, comp_type);
goto out;
}
key.objectid = btrfs_ino(BTRFS_I(dst));
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = 0;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0) {
return ret;
} else if (ret > 0) {
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
ret = btrfs_next_leaf(root, path);
if (ret < 0)
return ret;
else if (ret > 0)
goto copy_inline_extent;
}
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
if (key.objectid == btrfs_ino(BTRFS_I(dst)) &&
key.type == BTRFS_EXTENT_DATA_KEY) {
/*
* There's an implicit hole at file offset 0, copy the
* inline extent's data to the page.
*/
ASSERT(key.offset > 0);
ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
inline_data, size, datal,
comp_type);
goto out;
}
} else if (i_size_read(dst) <= datal) {
struct btrfs_file_extent_item *ei;
ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_file_extent_item);
/*
* If it's an inline extent replace it with the source inline
* extent, otherwise copy the source inline extent data into
* the respective page at the destination inode.
*/
if (btrfs_file_extent_type(path->nodes[0], ei) ==
BTRFS_FILE_EXTENT_INLINE)
goto copy_inline_extent;
ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
inline_data, size, datal, comp_type);
goto out;
}
copy_inline_extent:
ret = 0;
/*
* We have no extent items, or we have an extent at offset 0 which may
* or may not be inlined. All these cases are dealt the same way.
*/
if (i_size_read(dst) > datal) {
/*
* At the destination offset 0 we have either a hole, a regular
* extent or an inline extent larger then the one we want to
* clone. Deal with all these cases by copying the inline extent
* data into the respective page at the destination inode.
*/
ret = copy_inline_to_page(BTRFS_I(dst), new_key->offset,
inline_data, size, datal, comp_type);
goto out;
}
btrfs_release_path(path);
/*
* If we end up here it means were copy the inline extent into a leaf
* of the destination inode. We know we will drop or adjust at most one
* extent item in the destination root.
*
* 1 unit - adjusting old extent (we may have to split it)
* 1 unit - add new extent
* 1 unit - inode update
*/
trans = btrfs_start_transaction(root, 3);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
goto out;
}
drop_args.path = path;
drop_args.start = drop_start;
drop_args.end = aligned_end;
drop_args.drop_cache = true;
ret = btrfs_drop_extents(trans, root, BTRFS_I(dst), &drop_args);
if (ret)
goto out;
ret = btrfs_insert_empty_item(trans, root, path, new_key, size);
if (ret)
goto out;
write_extent_buffer(path->nodes[0], inline_data,
btrfs_item_ptr_offset(path->nodes[0],
path->slots[0]),
size);
btrfs_update_inode_bytes(BTRFS_I(dst), datal, drop_args.bytes_found);
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(dst)->runtime_flags);
ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end);
out:
if (!ret && !trans) {
/*
* No transaction here means we copied the inline extent into a
* page of the destination inode.
*
* 1 unit to update inode item
*/
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
}
}
if (ret && trans) {
btrfs_abort_transaction(trans, ret);
btrfs_end_transaction(trans);
}
if (!ret)
*trans_out = trans;
return ret;
}
/**
* btrfs_clone() - clone a range from inode file to another
*
* @src: Inode to clone from
* @inode: Inode to clone to
* @off: Offset within source to start clone from
* @olen: Original length, passed by user, of range to clone
* @olen_aligned: Block-aligned value of olen
* @destoff: Offset within @inode to start clone
* @no_time_update: Whether to update mtime/ctime on the target inode
*/
static int btrfs_clone(struct inode *src, struct inode *inode,
const u64 off, const u64 olen, const u64 olen_aligned,
const u64 destoff, int no_time_update)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_path *path = NULL;
struct extent_buffer *leaf;
struct btrfs_trans_handle *trans;
char *buf = NULL;
struct btrfs_key key;
u32 nritems;
int slot;
int ret;
const u64 len = olen_aligned;
u64 last_dest_end = destoff;
ret = -ENOMEM;
buf = kvmalloc(fs_info->nodesize, GFP_KERNEL);
if (!buf)
return ret;
path = btrfs_alloc_path();
if (!path) {
kvfree(buf);
return ret;
}
path->reada = READA_FORWARD;
/* Clone data */
key.objectid = btrfs_ino(BTRFS_I(src));
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = off;
while (1) {
u64 next_key_min_offset = key.offset + 1;
struct btrfs_file_extent_item *extent;
u64 extent_gen;
int type;
u32 size;
struct btrfs_key new_key;
u64 disko = 0, diskl = 0;
u64 datao = 0, datal = 0;
u8 comp;
u64 drop_start;
/* Note the key will change type as we walk through the tree */
ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path,
0, 0);
if (ret < 0)
goto out;
/*
* First search, if no extent item that starts at offset off was
* found but the previous item is an extent item, it's possible
* it might overlap our target range, therefore process it.
*/
if (key.offset == off && ret > 0 && path->slots[0] > 0) {
btrfs_item_key_to_cpu(path->nodes[0], &key,
path->slots[0] - 1);
if (key.type == BTRFS_EXTENT_DATA_KEY)
path->slots[0]--;
}
nritems = btrfs_header_nritems(path->nodes[0]);
process_slot:
if (path->slots[0] >= nritems) {
ret = btrfs_next_leaf(BTRFS_I(src)->root, path);
if (ret < 0)
goto out;
if (ret > 0)
break;
nritems = btrfs_header_nritems(path->nodes[0]);
}
leaf = path->nodes[0];
slot = path->slots[0];
btrfs_item_key_to_cpu(leaf, &key, slot);
if (key.type > BTRFS_EXTENT_DATA_KEY ||
key.objectid != btrfs_ino(BTRFS_I(src)))
break;
ASSERT(key.type == BTRFS_EXTENT_DATA_KEY);
extent = btrfs_item_ptr(leaf, slot,
struct btrfs_file_extent_item);
extent_gen = btrfs_file_extent_generation(leaf, extent);
comp = btrfs_file_extent_compression(leaf, extent);
type = btrfs_file_extent_type(leaf, extent);
if (type == BTRFS_FILE_EXTENT_REG ||
type == BTRFS_FILE_EXTENT_PREALLOC) {
disko = btrfs_file_extent_disk_bytenr(leaf, extent);
diskl = btrfs_file_extent_disk_num_bytes(leaf, extent);
datao = btrfs_file_extent_offset(leaf, extent);
datal = btrfs_file_extent_num_bytes(leaf, extent);
} else if (type == BTRFS_FILE_EXTENT_INLINE) {
/* Take upper bound, may be compressed */
datal = btrfs_file_extent_ram_bytes(leaf, extent);
}
/*
* The first search might have left us at an extent item that
* ends before our target range's start, can happen if we have
* holes and NO_HOLES feature enabled.
*/
if (key.offset + datal <= off) {
path->slots[0]++;
goto process_slot;
} else if (key.offset >= off + len) {
break;
}
next_key_min_offset = key.offset + datal;
size = btrfs_item_size_nr(leaf, slot);
read_extent_buffer(leaf, buf, btrfs_item_ptr_offset(leaf, slot),
size);
btrfs_release_path(path);
memcpy(&new_key, &key, sizeof(new_key));
new_key.objectid = btrfs_ino(BTRFS_I(inode));
if (off <= key.offset)
new_key.offset = key.offset + destoff - off;
else
new_key.offset = destoff;
/*
* Deal with a hole that doesn't have an extent item that
* represents it (NO_HOLES feature enabled).
* This hole is either in the middle of the cloning range or at
* the beginning (fully overlaps it or partially overlaps it).
*/
if (new_key.offset != last_dest_end)
drop_start = last_dest_end;
else
drop_start = new_key.offset;
if (type == BTRFS_FILE_EXTENT_REG ||
type == BTRFS_FILE_EXTENT_PREALLOC) {
struct btrfs_replace_extent_info clone_info;
/*
* a | --- range to clone ---| b
* | ------------- extent ------------- |
*/
/* Subtract range b */
if (key.offset + datal > off + len)
datal = off + len - key.offset;
/* Subtract range a */
if (off > key.offset) {
datao += off - key.offset;
datal -= off - key.offset;
}
clone_info.disk_offset = disko;
clone_info.disk_len = diskl;
clone_info.data_offset = datao;
clone_info.data_len = datal;
clone_info.file_offset = new_key.offset;
clone_info.extent_buf = buf;
clone_info.is_new_extent = false;
ret = btrfs_replace_file_extents(inode, path, drop_start,
new_key.offset + datal - 1, &clone_info,
&trans);
if (ret)
goto out;
} else if (type == BTRFS_FILE_EXTENT_INLINE) {
/*
* Inline extents always have to start at file offset 0
* and can never be bigger then the sector size. We can
* never clone only parts of an inline extent, since all
* reflink operations must start at a sector size aligned
* offset, and the length must be aligned too or end at
* the i_size (which implies the whole inlined data).
*/
ASSERT(key.offset == 0);
ASSERT(datal <= fs_info->sectorsize);
if (key.offset != 0 || datal > fs_info->sectorsize)
return -EUCLEAN;
ret = clone_copy_inline_extent(inode, path, &new_key,
drop_start, datal, size,
comp, buf, &trans);
if (ret)
goto out;
}
btrfs_release_path(path);
/*
* If this is a new extent update the last_reflink_trans of both
* inodes. This is used by fsync to make sure it does not log
* multiple checksum items with overlapping ranges. For older
* extents we don't need to do it since inode logging skips the
* checksums for older extents. Also ignore holes and inline
* extents because they don't have checksums in the csum tree.
*/
if (extent_gen == trans->transid && disko > 0) {
BTRFS_I(src)->last_reflink_trans = trans->transid;
BTRFS_I(inode)->last_reflink_trans = trans->transid;
}
last_dest_end = ALIGN(new_key.offset + datal,
fs_info->sectorsize);
ret = clone_finish_inode_update(trans, inode, last_dest_end,
destoff, olen, no_time_update);
if (ret)
goto out;
if (new_key.offset + datal >= destoff + len)
break;
btrfs_release_path(path);
key.offset = next_key_min_offset;
if (fatal_signal_pending(current)) {
ret = -EINTR;
goto out;
}
cond_resched();
}
ret = 0;
if (last_dest_end < destoff + len) {
/*
* We have an implicit hole that fully or partially overlaps our
* cloning range at its end. This means that we either have the
* NO_HOLES feature enabled or the implicit hole happened due to
* mixing buffered and direct IO writes against this file.
*/
btrfs_release_path(path);
/*
* When using NO_HOLES and we are cloning a range that covers
* only a hole (no extents) into a range beyond the current
* i_size, punching a hole in the target range will not create
* an extent map defining a hole, because the range starts at or
* beyond current i_size. If the file previously had an i_size
* greater than the new i_size set by this clone operation, we
* need to make sure the next fsync is a full fsync, so that it
* detects and logs a hole covering a range from the current
* i_size to the new i_size. If the clone range covers extents,
* besides a hole, then we know the full sync flag was already
* set by previous calls to btrfs_replace_file_extents() that
* replaced file extent items.
*/
if (last_dest_end >= i_size_read(inode))
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags);
ret = btrfs_replace_file_extents(inode, path, last_dest_end,
destoff + len - 1, NULL, &trans);
if (ret)
goto out;
ret = clone_finish_inode_update(trans, inode, destoff + len,
destoff, olen, no_time_update);
}
out:
btrfs_free_path(path);
kvfree(buf);
clear_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &BTRFS_I(inode)->runtime_flags);
return ret;
}
static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
struct inode *inode2, u64 loff2, u64 len)
{
unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}
static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
struct inode *inode2, u64 loff2, u64 len)
{
if (inode1 < inode2) {
swap(inode1, inode2);
swap(loff1, loff2);
} else if (inode1 == inode2 && loff2 < loff1) {
swap(loff1, loff2);
}
lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}
static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 len,
struct inode *dst, u64 dst_loff)
{
const u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
int ret;
/*
* Lock destination range to serialize with concurrent readpages() and
* source range to serialize with relocation.
*/
btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
ret = btrfs_clone(src, dst, loff, len, ALIGN(len, bs), dst_loff, 1);
btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
return ret;
}
static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
struct inode *dst, u64 dst_loff)
{
int ret;
u64 i, tail_len, chunk_count;
struct btrfs_root *root_dst = BTRFS_I(dst)->root;
spin_lock(&root_dst->root_item_lock);
if (root_dst->send_in_progress) {
btrfs_warn_rl(root_dst->fs_info,
"cannot deduplicate to root %llu while send operations are using it (%d in progress)",
root_dst->root_key.objectid,
root_dst->send_in_progress);
spin_unlock(&root_dst->root_item_lock);
return -EAGAIN;
}
root_dst->dedupe_in_progress++;
spin_unlock(&root_dst->root_item_lock);
tail_len = olen % BTRFS_MAX_DEDUPE_LEN;
chunk_count = div_u64(olen, BTRFS_MAX_DEDUPE_LEN);
for (i = 0; i < chunk_count; i++) {
ret = btrfs_extent_same_range(src, loff, BTRFS_MAX_DEDUPE_LEN,
dst, dst_loff);
if (ret)
goto out;
loff += BTRFS_MAX_DEDUPE_LEN;
dst_loff += BTRFS_MAX_DEDUPE_LEN;
}
if (tail_len > 0)
ret = btrfs_extent_same_range(src, loff, tail_len, dst, dst_loff);
out:
spin_lock(&root_dst->root_item_lock);
root_dst->dedupe_in_progress--;
spin_unlock(&root_dst->root_item_lock);
return ret;
}
static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
u64 off, u64 olen, u64 destoff)
{
struct inode *inode = file_inode(file);
struct inode *src = file_inode(file_src);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
int ret;
int wb_ret;
u64 len = olen;
u64 bs = fs_info->sb->s_blocksize;
/*
* VFS's generic_remap_file_range_prep() protects us from cloning the
* eof block into the middle of a file, which would result in corruption
* if the file size is not blocksize aligned. So we don't need to check
* for that case here.
*/
if (off + len == src->i_size)
len = ALIGN(src->i_size, bs) - off;
if (destoff > inode->i_size) {
const u64 wb_start = ALIGN_DOWN(inode->i_size, bs);
ret = btrfs_cont_expand(BTRFS_I(inode), inode->i_size, destoff);
if (ret)
return ret;
/*
* We may have truncated the last block if the inode's size is
* not sector size aligned, so we need to wait for writeback to
* complete before proceeding further, otherwise we can race
* with cloning and attempt to increment a reference to an
* extent that no longer exists (writeback completed right after
* we found the previous extent covering eof and before we
* attempted to increment its reference count).
*/
ret = btrfs_wait_ordered_range(inode, wb_start,
destoff - wb_start);
if (ret)
return ret;
}
/*
* Lock destination range to serialize with concurrent readpages() and
* source range to serialize with relocation.
*/
btrfs_double_extent_lock(src, off, inode, destoff, len);
ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
btrfs_double_extent_unlock(src, off, inode, destoff, len);
/*
* We may have copied an inline extent into a page of the destination
* range, so wait for writeback to complete before truncating pages
* from the page cache. This is a rare case.
*/
wb_ret = btrfs_wait_ordered_range(inode, destoff, len);
ret = ret ? ret : wb_ret;
/*
* 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,
round_down(destoff, PAGE_SIZE),
round_up(destoff + len, PAGE_SIZE) - 1);
return ret;
}
static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
u64 bs = BTRFS_I(inode_out)->root->fs_info->sb->s_blocksize;
bool same_inode = inode_out == inode_in;
u64 wb_len;
int ret;
if (!(remap_flags & REMAP_FILE_DEDUP)) {
struct btrfs_root *root_out = BTRFS_I(inode_out)->root;
if (btrfs_root_readonly(root_out))
return -EROFS;
if (file_in->f_path.mnt != file_out->f_path.mnt ||
inode_in->i_sb != inode_out->i_sb)
return -EXDEV;
}
/* Don't make the dst file partly checksummed */
if ((BTRFS_I(inode_in)->flags & BTRFS_INODE_NODATASUM) !=
(BTRFS_I(inode_out)->flags & BTRFS_INODE_NODATASUM)) {
return -EINVAL;
}
/*
* Now that the inodes are locked, we need to start writeback ourselves
* and can not rely on the writeback from the VFS's generic helper
* generic_remap_file_range_prep() because:
*
* 1) For compression we must call filemap_fdatawrite_range() range
* twice (btrfs_fdatawrite_range() does it for us), and the generic
* helper only calls it once;
*
* 2) filemap_fdatawrite_range(), called by the generic helper only
* waits for the writeback to complete, i.e. for IO to be done, and
* not for the ordered extents to complete. We need to wait for them
* to complete so that new file extent items are in the fs tree.
*/
if (*len == 0 && !(remap_flags & REMAP_FILE_DEDUP))
wb_len = ALIGN(inode_in->i_size, bs) - ALIGN_DOWN(pos_in, bs);
else
wb_len = ALIGN(*len, bs);
/*
* Since we don't lock ranges, wait for ongoing lockless dio writes (as
* any in progress could create its ordered extents after we wait for
* existing ordered extents below).
*/
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
/*
* Workaround to make sure NOCOW buffered write reach disk as NOCOW.
*
* Btrfs' back references do not have a block level granularity, they
* work at the whole extent level.
* NOCOW buffered write without data space reserved may not be able
* to fall back to CoW due to lack of data space, thus could cause
* data loss.
*
* Here we take a shortcut by flushing the whole inode, so that all
* nocow write should reach disk as nocow before we increase the
* reference of the extent. We could do better by only flushing NOCOW
* data, but that needs extra accounting.
*
* Also we don't need to check ASYNC_EXTENT, as async extent will be
* CoWed anyway, not affecting nocow part.
*/
ret = filemap_flush(inode_in->i_mapping);
if (ret < 0)
return ret;
ret = btrfs_wait_ordered_range(inode_in, ALIGN_DOWN(pos_in, bs),
wb_len);
if (ret < 0)
return ret;
ret = btrfs_wait_ordered_range(inode_out, ALIGN_DOWN(pos_out, bs),
wb_len);
if (ret < 0)
return ret;
return generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
len, remap_flags);
}
loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
struct file *dst_file, loff_t destoff, loff_t len,
unsigned int remap_flags)
{
struct inode *src_inode = file_inode(src_file);
struct inode *dst_inode = file_inode(dst_file);
bool same_inode = dst_inode == src_inode;
int ret;
if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
return -EINVAL;
if (same_inode)
inode_lock(src_inode);
else
lock_two_nondirectories(src_inode, dst_inode);
ret = btrfs_remap_file_range_prep(src_file, off, dst_file, destoff,
&len, remap_flags);
if (ret < 0 || len == 0)
goto out_unlock;
if (remap_flags & REMAP_FILE_DEDUP)
ret = btrfs_extent_same(src_inode, off, len, dst_inode, destoff);
else
ret = btrfs_clone_files(dst_file, src_file, off, len, destoff);
out_unlock:
if (same_inode)
inode_unlock(src_inode);
else
unlock_two_nondirectories(src_inode, dst_inode);
return ret < 0 ? ret : len;
}