linux/fs/ext4/move_extent.c
Linus Torvalds 7fa8a8ee94 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
switching from a user process to a kernel thread.
 
 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj Raghav.
 
 - zsmalloc performance improvements from Sergey Senozhatsky.
 
 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.
 
 - VFS rationalizations from Christoph Hellwig:
 
   - removal of most of the callers of write_one_page().
 
   - make __filemap_get_folio()'s return value more useful
 
 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing.  Use `mount -o noswap'.
 
 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.
 
 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).
 
 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.
 
 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive rather
   than exclusive, and has fixed a bunch of errors which were caused by its
   unintuitive meaning.
 
 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.
 
 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.
 
 - Cleanups to do_fault_around() by Lorenzo Stoakes.
 
 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.
 
 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.
 
 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.
 
 - Lorenzo has also contributed further cleanups of vma_merge().
 
 - Chaitanya Prakash provides some fixes to the mmap selftesting code.
 
 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.
 
 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.
 
 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.
 
 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.
 
 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.
 
 - Yosry Ahmed has improved the performance of memcg statistics flushing.
 
 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.
 
 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.
 
 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.
 
 - Pankaj Raghav has made page_endio() unneeded and has removed it.
 
 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.
 
 - Yosry Ahmed has fixed an issue around memcg's page recalim accounting.
 
 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.
 
 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.
 
 - Peter Xu fixes a few issues with uffd-wp at fork() time.
 
 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZEr3zQAKCRDdBJ7gKXxA
 jlLoAP0fpQBipwFxED0Us4SKQfupV6z4caXNJGPeay7Aj11/kQD/aMRC2uPfgr96
 eMG3kwn2pqkB9ST2QpkaRbxA//eMbQY=
 =J+Dj
 -----END PGP SIGNATURE-----

Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...
2023-04-27 19:42:02 -07:00

709 lines
21 KiB
C

// SPDX-License-Identifier: LGPL-2.1
/*
* Copyright (c) 2008,2009 NEC Software Tohoku, Ltd.
* Written by Takashi Sato <t-sato@yk.jp.nec.com>
* Akira Fujita <a-fujita@rs.jp.nec.com>
*/
#include <linux/fs.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/sched/mm.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include "ext4_extents.h"
/**
* get_ext_path() - Find an extent path for designated logical block number.
* @inode: inode to be searched
* @lblock: logical block number to find an extent path
* @ppath: pointer to an extent path pointer (for output)
*
* ext4_find_extent wrapper. Return 0 on success, or a negative error value
* on failure.
*/
static inline int
get_ext_path(struct inode *inode, ext4_lblk_t lblock,
struct ext4_ext_path **ppath)
{
struct ext4_ext_path *path;
path = ext4_find_extent(inode, lblock, ppath, EXT4_EX_NOCACHE);
if (IS_ERR(path))
return PTR_ERR(path);
if (path[ext_depth(inode)].p_ext == NULL) {
ext4_free_ext_path(path);
*ppath = NULL;
return -ENODATA;
}
*ppath = path;
return 0;
}
/**
* ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem
* @first: inode to be locked
* @second: inode to be locked
*
* Acquire write lock of i_data_sem of the two inodes
*/
void
ext4_double_down_write_data_sem(struct inode *first, struct inode *second)
{
if (first < second) {
down_write(&EXT4_I(first)->i_data_sem);
down_write_nested(&EXT4_I(second)->i_data_sem, I_DATA_SEM_OTHER);
} else {
down_write(&EXT4_I(second)->i_data_sem);
down_write_nested(&EXT4_I(first)->i_data_sem, I_DATA_SEM_OTHER);
}
}
/**
* ext4_double_up_write_data_sem - Release two inodes' write lock of i_data_sem
*
* @orig_inode: original inode structure to be released its lock first
* @donor_inode: donor inode structure to be released its lock second
* Release write lock of i_data_sem of two inodes (orig and donor).
*/
void
ext4_double_up_write_data_sem(struct inode *orig_inode,
struct inode *donor_inode)
{
up_write(&EXT4_I(orig_inode)->i_data_sem);
up_write(&EXT4_I(donor_inode)->i_data_sem);
}
/**
* mext_check_coverage - Check that all extents in range has the same type
*
* @inode: inode in question
* @from: block offset of inode
* @count: block count to be checked
* @unwritten: extents expected to be unwritten
* @err: pointer to save error value
*
* Return 1 if all extents in range has expected type, and zero otherwise.
*/
static int
mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count,
int unwritten, int *err)
{
struct ext4_ext_path *path = NULL;
struct ext4_extent *ext;
int ret = 0;
ext4_lblk_t last = from + count;
while (from < last) {
*err = get_ext_path(inode, from, &path);
if (*err)
goto out;
ext = path[ext_depth(inode)].p_ext;
if (unwritten != ext4_ext_is_unwritten(ext))
goto out;
from += ext4_ext_get_actual_len(ext);
}
ret = 1;
out:
ext4_free_ext_path(path);
return ret;
}
/**
* mext_folio_double_lock - Grab and lock folio on both @inode1 and @inode2
*
* @inode1: the inode structure
* @inode2: the inode structure
* @index1: folio index
* @index2: folio index
* @folio: result folio vector
*
* Grab two locked folio for inode's by inode order
*/
static int
mext_folio_double_lock(struct inode *inode1, struct inode *inode2,
pgoff_t index1, pgoff_t index2, struct folio *folio[2])
{
struct address_space *mapping[2];
unsigned int flags;
BUG_ON(!inode1 || !inode2);
if (inode1 < inode2) {
mapping[0] = inode1->i_mapping;
mapping[1] = inode2->i_mapping;
} else {
swap(index1, index2);
mapping[0] = inode2->i_mapping;
mapping[1] = inode1->i_mapping;
}
flags = memalloc_nofs_save();
folio[0] = __filemap_get_folio(mapping[0], index1, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping[0]));
if (IS_ERR(folio[0])) {
memalloc_nofs_restore(flags);
return PTR_ERR(folio[0]);
}
folio[1] = __filemap_get_folio(mapping[1], index2, FGP_WRITEBEGIN,
mapping_gfp_mask(mapping[1]));
memalloc_nofs_restore(flags);
if (IS_ERR(folio[1])) {
folio_unlock(folio[0]);
folio_put(folio[0]);
return PTR_ERR(folio[1]);
}
/*
* __filemap_get_folio() may not wait on folio's writeback if
* BDI not demand that. But it is reasonable to be very conservative
* here and explicitly wait on folio's writeback
*/
folio_wait_writeback(folio[0]);
folio_wait_writeback(folio[1]);
if (inode1 > inode2)
swap(folio[0], folio[1]);
return 0;
}
/* Force page buffers uptodate w/o dropping page's lock */
static int
mext_page_mkuptodate(struct folio *folio, unsigned from, unsigned to)
{
struct inode *inode = folio->mapping->host;
sector_t block;
struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE];
unsigned int blocksize, block_start, block_end;
int i, err, nr = 0, partial = 0;
BUG_ON(!folio_test_locked(folio));
BUG_ON(folio_test_writeback(folio));
if (folio_test_uptodate(folio))
return 0;
blocksize = i_blocksize(inode);
head = folio_buffers(folio);
if (!head) {
create_empty_buffers(&folio->page, blocksize, 0);
head = folio_buffers(folio);
}
block = (sector_t)folio->index << (PAGE_SHIFT - inode->i_blkbits);
for (bh = head, block_start = 0; bh != head || !block_start;
block++, block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (!buffer_uptodate(bh))
partial = 1;
continue;
}
if (buffer_uptodate(bh))
continue;
if (!buffer_mapped(bh)) {
err = ext4_get_block(inode, block, bh, 0);
if (err) {
folio_set_error(folio);
return err;
}
if (!buffer_mapped(bh)) {
folio_zero_range(folio, block_start, blocksize);
set_buffer_uptodate(bh);
continue;
}
}
BUG_ON(nr >= MAX_BUF_PER_PAGE);
arr[nr++] = bh;
}
/* No io required */
if (!nr)
goto out;
for (i = 0; i < nr; i++) {
bh = arr[i];
if (!bh_uptodate_or_lock(bh)) {
err = ext4_read_bh(bh, 0, NULL);
if (err)
return err;
}
}
out:
if (!partial)
folio_mark_uptodate(folio);
return 0;
}
/**
* move_extent_per_page - Move extent data per page
*
* @o_filp: file structure of original file
* @donor_inode: donor inode
* @orig_page_offset: page index on original file
* @donor_page_offset: page index on donor file
* @data_offset_in_page: block index where data swapping starts
* @block_len_in_page: the number of blocks to be swapped
* @unwritten: orig extent is unwritten or not
* @err: pointer to save return value
*
* Save the data in original inode blocks and replace original inode extents
* with donor inode extents by calling ext4_swap_extents().
* Finally, write out the saved data in new original inode blocks. Return
* replaced block count.
*/
static int
move_extent_per_page(struct file *o_filp, struct inode *donor_inode,
pgoff_t orig_page_offset, pgoff_t donor_page_offset,
int data_offset_in_page,
int block_len_in_page, int unwritten, int *err)
{
struct inode *orig_inode = file_inode(o_filp);
struct folio *folio[2] = {NULL, NULL};
handle_t *handle;
ext4_lblk_t orig_blk_offset, donor_blk_offset;
unsigned long blocksize = orig_inode->i_sb->s_blocksize;
unsigned int tmp_data_size, data_size, replaced_size;
int i, err2, jblocks, retries = 0;
int replaced_count = 0;
int from = data_offset_in_page << orig_inode->i_blkbits;
int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits;
struct super_block *sb = orig_inode->i_sb;
struct buffer_head *bh = NULL;
/*
* It needs twice the amount of ordinary journal buffers because
* inode and donor_inode may change each different metadata blocks.
*/
again:
*err = 0;
jblocks = ext4_writepage_trans_blocks(orig_inode) * 2;
handle = ext4_journal_start(orig_inode, EXT4_HT_MOVE_EXTENTS, jblocks);
if (IS_ERR(handle)) {
*err = PTR_ERR(handle);
return 0;
}
orig_blk_offset = orig_page_offset * blocks_per_page +
data_offset_in_page;
donor_blk_offset = donor_page_offset * blocks_per_page +
data_offset_in_page;
/* Calculate data_size */
if ((orig_blk_offset + block_len_in_page - 1) ==
((orig_inode->i_size - 1) >> orig_inode->i_blkbits)) {
/* Replace the last block */
tmp_data_size = orig_inode->i_size & (blocksize - 1);
/*
* If data_size equal zero, it shows data_size is multiples of
* blocksize. So we set appropriate value.
*/
if (tmp_data_size == 0)
tmp_data_size = blocksize;
data_size = tmp_data_size +
((block_len_in_page - 1) << orig_inode->i_blkbits);
} else
data_size = block_len_in_page << orig_inode->i_blkbits;
replaced_size = data_size;
*err = mext_folio_double_lock(orig_inode, donor_inode, orig_page_offset,
donor_page_offset, folio);
if (unlikely(*err < 0))
goto stop_journal;
/*
* If orig extent was unwritten it can become initialized
* at any time after i_data_sem was dropped, in order to
* serialize with delalloc we have recheck extent while we
* hold page's lock, if it is still the case data copy is not
* necessary, just swap data blocks between orig and donor.
*/
VM_BUG_ON_FOLIO(folio_test_large(folio[0]), folio[0]);
VM_BUG_ON_FOLIO(folio_test_large(folio[1]), folio[1]);
VM_BUG_ON_FOLIO(folio_nr_pages(folio[0]) != folio_nr_pages(folio[1]), folio[1]);
if (unwritten) {
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* If any of extents in range became initialized we have to
* fallback to data copying */
unwritten = mext_check_coverage(orig_inode, orig_blk_offset,
block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
unwritten &= mext_check_coverage(donor_inode, donor_blk_offset,
block_len_in_page, 1, err);
if (*err)
goto drop_data_sem;
if (!unwritten) {
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto data_copy;
}
if ((folio_has_private(folio[0]) &&
!filemap_release_folio(folio[0], 0)) ||
(folio_has_private(folio[1]) &&
!filemap_release_folio(folio[1], 0))) {
*err = -EBUSY;
goto drop_data_sem;
}
replaced_count = ext4_swap_extents(handle, orig_inode,
donor_inode, orig_blk_offset,
donor_blk_offset,
block_len_in_page, 1, err);
drop_data_sem:
ext4_double_up_write_data_sem(orig_inode, donor_inode);
goto unlock_folios;
}
data_copy:
*err = mext_page_mkuptodate(folio[0], from, from + replaced_size);
if (*err)
goto unlock_folios;
/* At this point all buffers in range are uptodate, old mapping layout
* is no longer required, try to drop it now. */
if ((folio_has_private(folio[0]) &&
!filemap_release_folio(folio[0], 0)) ||
(folio_has_private(folio[1]) &&
!filemap_release_folio(folio[1], 0))) {
*err = -EBUSY;
goto unlock_folios;
}
ext4_double_down_write_data_sem(orig_inode, donor_inode);
replaced_count = ext4_swap_extents(handle, orig_inode, donor_inode,
orig_blk_offset, donor_blk_offset,
block_len_in_page, 1, err);
ext4_double_up_write_data_sem(orig_inode, donor_inode);
if (*err) {
if (replaced_count) {
block_len_in_page = replaced_count;
replaced_size =
block_len_in_page << orig_inode->i_blkbits;
} else
goto unlock_folios;
}
/* Perform all necessary steps similar write_begin()/write_end()
* but keeping in mind that i_size will not change */
if (!folio_buffers(folio[0]))
create_empty_buffers(&folio[0]->page, 1 << orig_inode->i_blkbits, 0);
bh = folio_buffers(folio[0]);
for (i = 0; i < data_offset_in_page; i++)
bh = bh->b_this_page;
for (i = 0; i < block_len_in_page; i++) {
*err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0);
if (*err < 0)
break;
bh = bh->b_this_page;
}
if (!*err)
*err = block_commit_write(&folio[0]->page, from, from + replaced_size);
if (unlikely(*err < 0))
goto repair_branches;
/* Even in case of data=writeback it is reasonable to pin
* inode to transaction, to prevent unexpected data loss */
*err = ext4_jbd2_inode_add_write(handle, orig_inode,
(loff_t)orig_page_offset << PAGE_SHIFT, replaced_size);
unlock_folios:
folio_unlock(folio[0]);
folio_put(folio[0]);
folio_unlock(folio[1]);
folio_put(folio[1]);
stop_journal:
ext4_journal_stop(handle);
if (*err == -ENOSPC &&
ext4_should_retry_alloc(sb, &retries))
goto again;
/* Buffer was busy because probably is pinned to journal transaction,
* force transaction commit may help to free it. */
if (*err == -EBUSY && retries++ < 4 && EXT4_SB(sb)->s_journal &&
jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal))
goto again;
return replaced_count;
repair_branches:
/*
* This should never ever happen!
* Extents are swapped already, but we are not able to copy data.
* Try to swap extents to it's original places
*/
ext4_double_down_write_data_sem(orig_inode, donor_inode);
replaced_count = ext4_swap_extents(handle, donor_inode, orig_inode,
orig_blk_offset, donor_blk_offset,
block_len_in_page, 0, &err2);
ext4_double_up_write_data_sem(orig_inode, donor_inode);
if (replaced_count != block_len_in_page) {
ext4_error_inode_block(orig_inode, (sector_t)(orig_blk_offset),
EIO, "Unable to copy data block,"
" data will be lost.");
*err = -EIO;
}
replaced_count = 0;
goto unlock_folios;
}
/**
* mext_check_arguments - Check whether move extent can be done
*
* @orig_inode: original inode
* @donor_inode: donor inode
* @orig_start: logical start offset in block for orig
* @donor_start: logical start offset in block for donor
* @len: the number of blocks to be moved
*
* Check the arguments of ext4_move_extents() whether the files can be
* exchanged with each other.
* Return 0 on success, or a negative error value on failure.
*/
static int
mext_check_arguments(struct inode *orig_inode,
struct inode *donor_inode, __u64 orig_start,
__u64 donor_start, __u64 *len)
{
__u64 orig_eof, donor_eof;
unsigned int blkbits = orig_inode->i_blkbits;
unsigned int blocksize = 1 << blkbits;
orig_eof = (i_size_read(orig_inode) + blocksize - 1) >> blkbits;
donor_eof = (i_size_read(donor_inode) + blocksize - 1) >> blkbits;
if (donor_inode->i_mode & (S_ISUID|S_ISGID)) {
ext4_debug("ext4 move extent: suid or sgid is set"
" to donor file [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode))
return -EPERM;
/* Ext4 move extent does not support swap files */
if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
ext4_debug("ext4 move extent: The argument files should not be swap files [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -ETXTBSY;
}
if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) {
ext4_debug("ext4 move extent: The argument files should not be quota files [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EOPNOTSUPP;
}
/* Ext4 move extent supports only extent based file */
if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: orig file is not extents "
"based file [ino:orig %lu]\n", orig_inode->i_ino);
return -EOPNOTSUPP;
} else if (!(ext4_test_inode_flag(donor_inode, EXT4_INODE_EXTENTS))) {
ext4_debug("ext4 move extent: donor file is not extents "
"based file [ino:donor %lu]\n", donor_inode->i_ino);
return -EOPNOTSUPP;
}
if ((!orig_inode->i_size) || (!donor_inode->i_size)) {
ext4_debug("ext4 move extent: File size is 0 byte\n");
return -EINVAL;
}
/* Start offset should be same */
if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
(donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
ext4_debug("ext4 move extent: orig and donor's start "
"offsets are not aligned [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
if ((orig_start >= EXT_MAX_BLOCKS) ||
(donor_start >= EXT_MAX_BLOCKS) ||
(*len > EXT_MAX_BLOCKS) ||
(donor_start + *len >= EXT_MAX_BLOCKS) ||
(orig_start + *len >= EXT_MAX_BLOCKS)) {
ext4_debug("ext4 move extent: Can't handle over [%u] blocks "
"[ino:orig %lu, donor %lu]\n", EXT_MAX_BLOCKS,
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
if (orig_eof <= orig_start)
*len = 0;
else if (orig_eof < orig_start + *len - 1)
*len = orig_eof - orig_start;
if (donor_eof <= donor_start)
*len = 0;
else if (donor_eof < donor_start + *len - 1)
*len = donor_eof - donor_start;
if (!*len) {
ext4_debug("ext4 move extent: len should not be 0 "
"[ino:orig %lu, donor %lu]\n", orig_inode->i_ino,
donor_inode->i_ino);
return -EINVAL;
}
return 0;
}
/**
* ext4_move_extents - Exchange the specified range of a file
*
* @o_filp: file structure of the original file
* @d_filp: file structure of the donor file
* @orig_blk: start offset in block for orig
* @donor_blk: start offset in block for donor
* @len: the number of blocks to be moved
* @moved_len: moved block length
*
* This function returns 0 and moved block length is set in moved_len
* if succeed, otherwise returns error value.
*
*/
int
ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
__u64 donor_blk, __u64 len, __u64 *moved_len)
{
struct inode *orig_inode = file_inode(o_filp);
struct inode *donor_inode = file_inode(d_filp);
struct ext4_ext_path *path = NULL;
int blocks_per_page = PAGE_SIZE >> orig_inode->i_blkbits;
ext4_lblk_t o_end, o_start = orig_blk;
ext4_lblk_t d_start = donor_blk;
int ret;
if (orig_inode->i_sb != donor_inode->i_sb) {
ext4_debug("ext4 move extent: The argument files "
"should be in same FS [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
/* orig and donor should be different inodes */
if (orig_inode == donor_inode) {
ext4_debug("ext4 move extent: The argument files should not "
"be same inode [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
/* Regular file check */
if (!S_ISREG(orig_inode->i_mode) || !S_ISREG(donor_inode->i_mode)) {
ext4_debug("ext4 move extent: The argument files should be "
"regular file [ino:orig %lu, donor %lu]\n",
orig_inode->i_ino, donor_inode->i_ino);
return -EINVAL;
}
/* TODO: it's not obvious how to swap blocks for inodes with full
journaling enabled */
if (ext4_should_journal_data(orig_inode) ||
ext4_should_journal_data(donor_inode)) {
ext4_msg(orig_inode->i_sb, KERN_ERR,
"Online defrag not supported with data journaling");
return -EOPNOTSUPP;
}
if (IS_ENCRYPTED(orig_inode) || IS_ENCRYPTED(donor_inode)) {
ext4_msg(orig_inode->i_sb, KERN_ERR,
"Online defrag not supported for encrypted files");
return -EOPNOTSUPP;
}
/* Protect orig and donor inodes against a truncate */
lock_two_nondirectories(orig_inode, donor_inode);
/* Wait for all existing dio workers */
inode_dio_wait(orig_inode);
inode_dio_wait(donor_inode);
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(orig_inode, donor_inode);
/* Check the filesystem environment whether move_extent can be done */
ret = mext_check_arguments(orig_inode, donor_inode, orig_blk,
donor_blk, &len);
if (ret)
goto out;
o_end = o_start + len;
while (o_start < o_end) {
struct ext4_extent *ex;
ext4_lblk_t cur_blk, next_blk;
pgoff_t orig_page_index, donor_page_index;
int offset_in_page;
int unwritten, cur_len;
ret = get_ext_path(orig_inode, o_start, &path);
if (ret)
goto out;
ex = path[path->p_depth].p_ext;
cur_blk = le32_to_cpu(ex->ee_block);
cur_len = ext4_ext_get_actual_len(ex);
/* Check hole before the start pos */
if (cur_blk + cur_len - 1 < o_start) {
next_blk = ext4_ext_next_allocated_block(path);
if (next_blk == EXT_MAX_BLOCKS) {
ret = -ENODATA;
goto out;
}
d_start += next_blk - o_start;
o_start = next_blk;
continue;
/* Check hole after the start pos */
} else if (cur_blk > o_start) {
/* Skip hole */
d_start += cur_blk - o_start;
o_start = cur_blk;
/* Extent inside requested range ?*/
if (cur_blk >= o_end)
goto out;
} else { /* in_range(o_start, o_blk, o_len) */
cur_len += cur_blk - o_start;
}
unwritten = ext4_ext_is_unwritten(ex);
if (o_end - o_start < cur_len)
cur_len = o_end - o_start;
orig_page_index = o_start >> (PAGE_SHIFT -
orig_inode->i_blkbits);
donor_page_index = d_start >> (PAGE_SHIFT -
donor_inode->i_blkbits);
offset_in_page = o_start % blocks_per_page;
if (cur_len > blocks_per_page - offset_in_page)
cur_len = blocks_per_page - offset_in_page;
/*
* Up semaphore to avoid following problems:
* a. transaction deadlock among ext4_journal_start,
* ->write_begin via pagefault, and jbd2_journal_commit
* b. racing with ->read_folio, ->write_begin, and
* ext4_get_block in move_extent_per_page
*/
ext4_double_up_write_data_sem(orig_inode, donor_inode);
/* Swap original branches with new branches */
move_extent_per_page(o_filp, donor_inode,
orig_page_index, donor_page_index,
offset_in_page, cur_len,
unwritten, &ret);
ext4_double_down_write_data_sem(orig_inode, donor_inode);
if (ret < 0)
break;
o_start += cur_len;
d_start += cur_len;
}
*moved_len = o_start - orig_blk;
if (*moved_len > len)
*moved_len = len;
out:
if (*moved_len) {
ext4_discard_preallocations(orig_inode, 0);
ext4_discard_preallocations(donor_inode, 0);
}
ext4_free_ext_path(path);
ext4_double_up_write_data_sem(orig_inode, donor_inode);
unlock_two_nondirectories(orig_inode, donor_inode);
return ret;
}