apfs/linux-apfs
0
0
Fork 0
mirror of https://github.com/linux-apfs/linux-apfs.git synced 2026-05-01 15:00:59 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge tag 'f2fs-for-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Browse Source 
Pull f2fs updates from Jaegeuk Kim:
 "In this round, we've tuned f2fs to improve general performance by
  serializing block allocation and enhancing discard flows like fstrim
  which avoids user IO contention. And we've added fsync_mode=nobarrier
  which gives an option to user where it skips issuing cache_flush
  commands to underlying flash storage. And there are many bug fixes
  related to fuzzed images, revoked atomic writes, quota ops, and minor
  direct IO.

  Enhancements:
   - add fsync_mode=nobarrier which bypasses cache_flush command
   - enhance the discarding flow which avoids user IOs and issues in
     LBA order
   - readahead some encrypted blocks during GC
   - enable in-memory inode checksum to verify the blocks if
     F2FS_CHECK_FS is set
   - enhance nat_bits behavior
   - set -o discard by default
   - set REQ_RAHEAD to bio in ->readpages

  Bug fixes:
   - fix a corner case to corrupt atomic_writes revoking flow
   - revisit i_gc_rwsem to fix race conditions
   - fix some dio behaviors captured by xfstests
   - correct handling errors given by quota-related failures
   - add many sanity check flows to avoid fuzz test failures
   - add more error number propagation to their callers
   - fix several corner cases to continue fault injection w/ shutdown
     loop"

* tag 'f2fs-for-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (89 commits)
  f2fs: readahead encrypted block during GC
  f2fs: avoid fi->i_gc_rwsem[WRITE] lock in f2fs_gc
  f2fs: fix performance issue observed with multi-thread sequential read
  f2fs: fix to skip verifying block address for non-regular inode
  f2fs: rework fault injection handling to avoid a warning
  f2fs: support fault_type mount option
  f2fs: fix to return success when trimming meta area
  f2fs: fix use-after-free of dicard command entry
  f2fs: support discard submission error injection
  f2fs: split discard command in prior to block layer
  f2fs: wake up gc thread immediately when gc_urgent is set
  f2fs: fix incorrect range->len in f2fs_trim_fs()
  f2fs: refresh recent accessed nat entry in lru list
  f2fs: fix avoid race between truncate and background GC
  f2fs: avoid race between zero_range and background GC
  f2fs: fix to do sanity check with block address in main area v2
  f2fs: fix to do sanity check with inline flags
  f2fs: fix to reset i_gc_failures correctly
  f2fs: fix invalid memory access
  f2fs: fix to avoid broken of dnode block list
  ...
This commit is contained in:
Linus Torvalds
2018-08-22 13:29:39 -07:00
parent 6faf05c2b2 6aa58d8ad2
commit fe6f0ed0da
21 changed files with 1675 additions and 536 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Documentation/ABI/testing/sysfs-fs-f2fs
+8
View File
@@ -51,6 +51,14 @@ Description:
Controls the dirty page count condition for the in-place-update
policies.
What: /sys/fs/f2fs/<disk>/min_seq_blocks
Date: August 2018
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the dirty page count condition for batched sequential
writes in ->writepages.
What: /sys/fs/f2fs/<disk>/min_hot_blocks
Date: March 2017
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Documentation/filesystems/f2fs.txt
+18
View File
@@ -157,6 +157,24 @@ data_flush Enable data flushing before checkpoint in order to
persist data of regular and symlink.
fault_injection=%d Enable fault injection in all supported types with
specified injection rate.
fault_type=%d Support configuring fault injection type, should be
enabled with fault_injection option, fault type value
is shown below, it supports single or combined type.
Type_Name Type_Value
FAULT_KMALLOC 0x000000001
FAULT_KVMALLOC 0x000000002
FAULT_PAGE_ALLOC 0x000000004
FAULT_PAGE_GET 0x000000008
FAULT_ALLOC_BIO 0x000000010
FAULT_ALLOC_NID 0x000000020
FAULT_ORPHAN 0x000000040
FAULT_BLOCK 0x000000080
FAULT_DIR_DEPTH 0x000000100
FAULT_EVICT_INODE 0x000000200
FAULT_TRUNCATE 0x000000400
FAULT_IO 0x000000800
FAULT_CHECKPOINT 0x000001000
FAULT_DISCARD 0x000002000
mode=%s Control block allocation mode which supports "adaptive"
and "lfs". In "lfs" mode, there should be no random
writes towards main area.
fs/f2fs/checkpoint.c
+106 -53
View File
@@ -28,6 +28,7 @@ struct kmem_cache *f2fs_inode_entry_slab;
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
{
f2fs_build_fault_attr(sbi, 0, 0);
set_ckpt_flags(sbi, CP_ERROR_FLAG);
if (!end_io)
f2fs_flush_merged_writes(sbi);
@@ -70,6 +71,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
.encrypted_page = NULL,
.is_meta = is_meta,
};
int err;
if (unlikely(!is_meta))
fio.op_flags &= ~REQ_META;
@@ -84,9 +86,10 @@ repeat:
fio.page = page;
if (f2fs_submit_page_bio(&fio)) {
err = f2fs_submit_page_bio(&fio);
if (err) {
f2fs_put_page(page, 1);
goto repeat;
return ERR_PTR(err);
}
lock_page(page);
@@ -95,14 +98,9 @@ repeat:
goto repeat;
}
/*
* if there is any IO error when accessing device, make our filesystem
* readonly and make sure do not write checkpoint with non-uptodate
* meta page.
*/
if (unlikely(!PageUptodate(page))) {
memset(page_address(page), 0, PAGE_SIZE);
f2fs_stop_checkpoint(sbi, false);
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
out:
return page;
@@ -113,13 +111,32 @@ struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
return __get_meta_page(sbi, index, true);
}
struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct page *page;
int count = 0;
retry:
page = __get_meta_page(sbi, index, true);
if (IS_ERR(page)) {
if (PTR_ERR(page) == -EIO &&
++count <= DEFAULT_RETRY_IO_COUNT)
goto retry;
f2fs_stop_checkpoint(sbi, false);
f2fs_bug_on(sbi, 1);
}
return page;
}
/* for POR only */
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, false);
}
bool f2fs_is_valid_meta_blkaddr(struct f2fs_sb_info *sbi,
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type)
{
switch (type) {
@@ -140,8 +157,20 @@ bool f2fs_is_valid_meta_blkaddr(struct f2fs_sb_info *sbi,
return false;
break;
case META_POR:
case DATA_GENERIC:
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
blkaddr < MAIN_BLKADDR(sbi)))
blkaddr < MAIN_BLKADDR(sbi))) {
if (type == DATA_GENERIC) {
f2fs_msg(sbi->sb, KERN_WARNING,
"access invalid blkaddr:%u", blkaddr);
WARN_ON(1);
}
return false;
}
break;
case META_GENERIC:
if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
blkaddr >= MAIN_BLKADDR(sbi)))
return false;
break;
default:
@@ -176,7 +205,7 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
blk_start_plug(&plug);
for (; nrpages-- > 0; blkno++) {
if (!f2fs_is_valid_meta_blkaddr(sbi, blkno, type))
if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
goto out;
switch (type) {
@@ -242,11 +271,8 @@ static int __f2fs_write_meta_page(struct page *page,
trace_f2fs_writepage(page, META);
if (unlikely(f2fs_cp_error(sbi))) {
dec_page_count(sbi, F2FS_DIRTY_META);
unlock_page(page);
return 0;
}
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
@@ -529,13 +555,12 @@ int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
spin_lock(&im->ino_lock);
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
f2fs_show_injection_info(FAULT_ORPHAN);
return -ENOSPC;
}
#endif
if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
@@ -572,12 +597,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode;
struct node_info ni;
int err = f2fs_acquire_orphan_inode(sbi);
if (err)
goto err_out;
__add_ino_entry(sbi, ino, 0, ORPHAN_INO);
int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode)) {
@@ -600,14 +620,15 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
/* truncate all the data during iput */
iput(inode);
f2fs_get_node_info(sbi, ino, &ni);
err = f2fs_get_node_info(sbi, ino, &ni);
if (err)
goto err_out;
/* ENOMEM was fully retried in f2fs_evict_inode. */
if (ni.blk_addr != NULL_ADDR) {
err = -EIO;
goto err_out;
}
__remove_ino_entry(sbi, ino, ORPHAN_INO);
return 0;
err_out:
@@ -639,7 +660,10 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
/* Needed for iput() to work correctly and not trash data */
sbi->sb->s_flags |= SB_ACTIVE;
/* Turn on quotas so that they are updated correctly */
/*
* Turn on quotas which were not enabled for read-only mounts if
* filesystem has quota feature, so that they are updated correctly.
*/
quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
#endif
@@ -649,9 +673,15 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
for (i = 0; i < orphan_blocks; i++) {
struct page *page = f2fs_get_meta_page(sbi, start_blk + i);
struct page *page;
struct f2fs_orphan_block *orphan_blk;
page = f2fs_get_meta_page(sbi, start_blk + i);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out;
}
orphan_blk = (struct f2fs_orphan_block *)page_address(page);
for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
@@ -742,10 +772,14 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
__u32 crc = 0;
*cp_page = f2fs_get_meta_page(sbi, cp_addr);
if (IS_ERR(*cp_page))
return PTR_ERR(*cp_page);
*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
if (crc_offset > (blk_size - sizeof(__le32))) {
f2fs_put_page(*cp_page, 1);
f2fs_msg(sbi->sb, KERN_WARNING,
"invalid crc_offset: %zu", crc_offset);
return -EINVAL;
@@ -753,6 +787,7 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
crc = cur_cp_crc(*cp_block);
if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
f2fs_put_page(*cp_page, 1);
f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
return -EINVAL;
}
@@ -772,14 +807,22 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
&cp_page_1, version);
if (err)
goto invalid_cp1;
return NULL;
if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
sbi->blocks_per_seg) {
f2fs_msg(sbi->sb, KERN_WARNING,
"invalid cp_pack_total_block_count:%u",
le32_to_cpu(cp_block->cp_pack_total_block_count));
goto invalid_cp;
}
pre_version = *version;
cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
&cp_page_2, version);
if (err)
goto invalid_cp2;
goto invalid_cp;
cur_version = *version;
if (cur_version == pre_version) {
@@ -787,9 +830,8 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
f2fs_put_page(cp_page_2, 1);
return cp_page_1;
}
invalid_cp2:
f2fs_put_page(cp_page_2, 1);
invalid_cp1:
invalid_cp:
f2fs_put_page(cp_page_1, 1);
return NULL;
}
@@ -838,15 +880,15 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
memcpy(sbi->ckpt, cp_block, blk_size);
/* Sanity checking of checkpoint */
if (f2fs_sanity_check_ckpt(sbi))
goto free_fail_no_cp;
if (cur_page == cp1)
sbi->cur_cp_pack = 1;
else
sbi->cur_cp_pack = 2;
/* Sanity checking of checkpoint */
if (f2fs_sanity_check_ckpt(sbi))
goto free_fail_no_cp;
if (cp_blks <= 1)
goto done;
@@ -859,6 +901,8 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
unsigned char *ckpt = (unsigned char *)sbi->ckpt;
cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
if (IS_ERR(cur_page))
goto free_fail_no_cp;
sit_bitmap_ptr = page_address(cur_page);
memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
f2fs_put_page(cur_page, 1);
@@ -980,12 +1024,10 @@ retry:
iput(inode);
/* We need to give cpu to another writers. */
if (ino == cur_ino) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
if (ino == cur_ino)
cond_resched();
} else {
else
ino = cur_ino;
}
} else {
/*
* We should submit bio, since it exists several
@@ -1119,7 +1161,7 @@ static void unblock_operations(struct f2fs_sb_info *sbi)
f2fs_unlock_all(sbi);
}
static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
{
DEFINE_WAIT(wait);
@@ -1129,6 +1171,9 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
if (!get_pages(sbi, F2FS_WB_CP_DATA))
break;
if (unlikely(f2fs_cp_error(sbi)))
break;
io_schedule_timeout(5*HZ);
}
finish_wait(&sbi->cp_wait, &wait);
@@ -1202,8 +1247,12 @@ static void commit_checkpoint(struct f2fs_sb_info *sbi,
/* writeout cp pack 2 page */
err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO);
f2fs_bug_on(sbi, err);
if (unlikely(err && f2fs_cp_error(sbi))) {
f2fs_put_page(page, 1);
return;
}
f2fs_bug_on(sbi, err);
f2fs_put_page(page, 0);
/* submit checkpoint (with barrier if NOBARRIER is not set) */
@@ -1229,7 +1278,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
while (get_pages(sbi, F2FS_DIRTY_META)) {
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
break;
}
/*
@@ -1309,7 +1358,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_sync_meta_pages(sbi, META, LONG_MAX,
FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
break;
}
}
@@ -1348,10 +1397,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
/* wait for previous submitted meta pages writeback */
wait_on_all_pages_writeback(sbi);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
f2fs_wait_on_all_pages_writeback(sbi);
/* flush all device cache */
err = f2fs_flush_device_cache(sbi);
@@ -1360,12 +1406,19 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* barrier and flush checkpoint cp pack 2 page if it can */
commit_checkpoint(sbi, ckpt, start_blk);
wait_on_all_pages_writeback(sbi);
f2fs_wait_on_all_pages_writeback(sbi);
/*
* invalidate intermediate page cache borrowed from meta inode
* which are used for migration of encrypted inode's blocks.
*/
if (f2fs_sb_has_encrypt(sbi->sb))
invalidate_mapping_pages(META_MAPPING(sbi),
MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
f2fs_release_ino_entry(sbi, false);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
f2fs_reset_fsync_node_info(sbi);
clear_sbi_flag(sbi, SBI_IS_DIRTY);
clear_sbi_flag(sbi, SBI_NEED_CP);
@@ -1381,7 +1434,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
return 0;
return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0;
}
/*
fs/f2fs/data.c
+137 -45
View File
@@ -126,12 +126,10 @@ static bool f2fs_bio_post_read_required(struct bio *bio)
static void f2fs_read_end_io(struct bio *bio)
{
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(F2FS_P_SB(bio_first_page_all(bio)), FAULT_IO)) {
f2fs_show_injection_info(FAULT_IO);
bio->bi_status = BLK_STS_IOERR;
}
#endif
if (f2fs_bio_post_read_required(bio)) {
struct bio_post_read_ctx *ctx = bio->bi_private;
@@ -177,6 +175,8 @@ static void f2fs_write_end_io(struct bio *bio)
page->index != nid_of_node(page));
dec_page_count(sbi, type);
if (f2fs_in_warm_node_list(sbi, page))
f2fs_del_fsync_node_entry(sbi, page);
clear_cold_data(page);
end_page_writeback(page);
}
@@ -264,7 +264,7 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
if (type != DATA && type != NODE)
goto submit_io;
if (f2fs_sb_has_blkzoned(sbi->sb) && current->plug)
if (test_opt(sbi, LFS) && current->plug)
blk_finish_plug(current->plug);
start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
@@ -441,7 +441,10 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
verify_block_addr(fio, fio->new_blkaddr);
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
__is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
return -EFAULT;
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
@@ -485,7 +488,7 @@ next:
spin_unlock(&io->io_lock);
}
if (is_valid_blkaddr(fio->old_blkaddr))
if (__is_valid_data_blkaddr(fio->old_blkaddr))
verify_block_addr(fio, fio->old_blkaddr);
verify_block_addr(fio, fio->new_blkaddr);
@@ -534,19 +537,22 @@ out:
}
static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
unsigned nr_pages)
unsigned nr_pages, unsigned op_flag)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
struct bio_post_read_ctx *ctx;
unsigned int post_read_steps = 0;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
return ERR_PTR(-EFAULT);
bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false);
if (!bio)
return ERR_PTR(-ENOMEM);
f2fs_target_device(sbi, blkaddr, bio);
bio->bi_end_io = f2fs_read_end_io;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
bio_set_op_attrs(bio, REQ_OP_READ, op_flag);
if (f2fs_encrypted_file(inode))
post_read_steps |= 1 << STEP_DECRYPT;
@@ -571,7 +577,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
block_t blkaddr)
{
struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1);
struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0);
if (IS_ERR(bio))
return PTR_ERR(bio);
@@ -869,6 +875,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_summary sum;
struct node_info ni;
block_t old_blkaddr;
pgoff_t fofs;
blkcnt_t count = 1;
int err;
@@ -876,6 +883,10 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
err = f2fs_get_node_info(sbi, dn->nid, &ni);
if (err)
return err;
dn->data_blkaddr = datablock_addr(dn->inode,
dn->node_page, dn->ofs_in_node);
if (dn->data_blkaddr == NEW_ADDR)
@@ -885,11 +896,13 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
return err;
alloc:
f2fs_get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
f2fs_allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
old_blkaddr = dn->data_blkaddr;
f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
&sum, seg_type, NULL, false);
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
invalidate_mapping_pages(META_MAPPING(sbi),
old_blkaddr, old_blkaddr);
f2fs_set_data_blkaddr(dn);
/* update i_size */
@@ -1045,7 +1058,13 @@ next_dnode:
next_block:
blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
if (!is_valid_blkaddr(blkaddr)) {
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) {
err = -EFAULT;
goto sync_out;
}
if (!is_valid_data_blkaddr(sbi, blkaddr)) {
if (create) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
@@ -1282,7 +1301,11 @@ static int f2fs_xattr_fiemap(struct inode *inode,
if (!page)
return -ENOMEM;
f2fs_get_node_info(sbi, inode->i_ino, &ni);
err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = (__u64)blk_to_logical(inode, ni.blk_addr);
offset = offsetof(struct f2fs_inode, i_addr) +
@@ -1309,7 +1332,11 @@ static int f2fs_xattr_fiemap(struct inode *inode,
if (!page)
return -ENOMEM;
f2fs_get_node_info(sbi, xnid, &ni);
err = f2fs_get_node_info(sbi, xnid, &ni);
if (err) {
f2fs_put_page(page, 1);
return err;
}
phys = (__u64)blk_to_logical(inode, ni.blk_addr);
len = inode->i_sb->s_blocksize;
@@ -1425,11 +1452,11 @@ out:
* Note that the aops->readpages() function is ONLY used for read-ahead. If
* this function ever deviates from doing just read-ahead, it should either
* use ->readpage() or do the necessary surgery to decouple ->readpages()
* readom read-ahead.
* from read-ahead.
*/
static int f2fs_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages)
unsigned nr_pages, bool is_readahead)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
@@ -1500,6 +1527,10 @@ got_it:
SetPageUptodate(page);
goto confused;
}
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
DATA_GENERIC))
goto set_error_page;
} else {
zero_user_segment(page, 0, PAGE_SIZE);
if (!PageUptodate(page))
@@ -1519,7 +1550,8 @@ submit_and_realloc:
bio = NULL;
}
if (bio == NULL) {
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages);
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
is_readahead ? REQ_RAHEAD : 0);
if (IS_ERR(bio)) {
bio = NULL;
goto set_error_page;
@@ -1563,7 +1595,7 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
if (ret == -EAGAIN)
ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1);
ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1, false);
return ret;
}
@@ -1580,12 +1612,13 @@ static int f2fs_read_data_pages(struct file *file,
if (f2fs_has_inline_data(inode))
return 0;
return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true);
}
static int encrypt_one_page(struct f2fs_io_info *fio)
{
struct inode *inode = fio->page->mapping->host;
struct page *mpage;
gfp_t gfp_flags = GFP_NOFS;
if (!f2fs_encrypted_file(inode))
@@ -1597,17 +1630,25 @@ static int encrypt_one_page(struct f2fs_io_info *fio)
retry_encrypt:
fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
PAGE_SIZE, 0, fio->page->index, gfp_flags);
if (!IS_ERR(fio->encrypted_page))
return 0;
/* flush pending IOs and wait for a while in the ENOMEM case */
if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
f2fs_flush_merged_writes(fio->sbi);
congestion_wait(BLK_RW_ASYNC, HZ/50);
gfp_flags |= __GFP_NOFAIL;
goto retry_encrypt;
if (IS_ERR(fio->encrypted_page)) {
/* flush pending IOs and wait for a while in the ENOMEM case */
if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
f2fs_flush_merged_writes(fio->sbi);
congestion_wait(BLK_RW_ASYNC, HZ/50);
gfp_flags |= __GFP_NOFAIL;
goto retry_encrypt;
}
return PTR_ERR(fio->encrypted_page);
}
return PTR_ERR(fio->encrypted_page);
mpage = find_lock_page(META_MAPPING(fio->sbi), fio->old_blkaddr);
if (mpage) {
if (PageUptodate(mpage))
memcpy(page_address(mpage),
page_address(fio->encrypted_page), PAGE_SIZE);
f2fs_put_page(mpage, 1);
}
return 0;
}
static inline bool check_inplace_update_policy(struct inode *inode,
@@ -1691,6 +1732,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
struct inode *inode = page->mapping->host;
struct dnode_of_data dn;
struct extent_info ei = {0,0,0};
struct node_info ni;
bool ipu_force = false;
int err = 0;
@@ -1699,11 +1741,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
f2fs_lookup_extent_cache(inode, page->index, &ei)) {
fio->old_blkaddr = ei.blk + page->index - ei.fofs;
if (is_valid_blkaddr(fio->old_blkaddr)) {
ipu_force = true;
fio->need_lock = LOCK_DONE;
goto got_it;
}
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
DATA_GENERIC))
return -EFAULT;
ipu_force = true;
fio->need_lock = LOCK_DONE;
goto got_it;
}
/* Deadlock due to between page->lock and f2fs_lock_op */
@@ -1722,11 +1766,17 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
goto out_writepage;
}
got_it:
if (__is_valid_data_blkaddr(fio->old_blkaddr) &&
!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
DATA_GENERIC)) {
err = -EFAULT;
goto out_writepage;
}
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
if (ipu_force || (is_valid_blkaddr(fio->old_blkaddr) &&
if (ipu_force || (is_valid_data_blkaddr(fio->sbi, fio->old_blkaddr) &&
need_inplace_update(fio))) {
err = encrypt_one_page(fio);
if (err)
@@ -1751,6 +1801,12 @@ got_it:
fio->need_lock = LOCK_REQ;
}
err = f2fs_get_node_info(fio->sbi, dn.nid, &ni);
if (err)
goto out_writepage;
fio->version = ni.version;
err = encrypt_one_page(fio);
if (err)
goto out_writepage;
@@ -2079,6 +2135,18 @@ continue_unlock:
return ret;
}
static inline bool __should_serialize_io(struct inode *inode,
struct writeback_control *wbc)
{
if (!S_ISREG(inode->i_mode))
return false;
if (wbc->sync_mode != WB_SYNC_ALL)
return true;
if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks)
return true;
return false;
}
static int __f2fs_write_data_pages(struct address_space *mapping,
struct writeback_control *wbc,
enum iostat_type io_type)
@@ -2087,6 +2155,7 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct blk_plug plug;
int ret;
bool locked = false;
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
@@ -2117,10 +2186,18 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
else if (atomic_read(&sbi->wb_sync_req[DATA]))
goto skip_write;
if (__should_serialize_io(inode, wbc)) {
mutex_lock(&sbi->writepages);
locked = true;
}
blk_start_plug(&plug);
ret = f2fs_write_cache_pages(mapping, wbc, io_type);
blk_finish_plug(&plug);
if (locked)
mutex_unlock(&sbi->writepages);
if (wbc->sync_mode == WB_SYNC_ALL)
atomic_dec(&sbi->wb_sync_req[DATA]);
/*
@@ -2153,10 +2230,14 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
loff_t i_size = i_size_read(inode);
if (to > i_size) {
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
truncate_pagecache(inode, i_size);
f2fs_truncate_blocks(inode, i_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
}
}
@@ -2251,8 +2332,9 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
trace_f2fs_write_begin(inode, pos, len, flags);
if (f2fs_is_atomic_file(inode) &&
!f2fs_available_free_memory(sbi, INMEM_PAGES)) {
if ((f2fs_is_atomic_file(inode) &&
!f2fs_available_free_memory(sbi, INMEM_PAGES)) ||
is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) {
err = -ENOMEM;
drop_atomic = true;
goto fail;
@@ -2376,14 +2458,20 @@ unlock_out:
static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
loff_t offset)
{
unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
if (offset & blocksize_mask)
return -EINVAL;
if (iov_iter_alignment(iter) & blocksize_mask)
return -EINVAL;
unsigned i_blkbits = READ_ONCE(inode->i_blkbits);
unsigned blkbits = i_blkbits;
unsigned blocksize_mask = (1 << blkbits) - 1;
unsigned long align = offset | iov_iter_alignment(iter);
struct block_device *bdev = inode->i_sb->s_bdev;
if (align & blocksize_mask) {
if (bdev)
blkbits = blksize_bits(bdev_logical_block_size(bdev));
blocksize_mask = (1 << blkbits) - 1;
if (align & blocksize_mask)
return -EINVAL;
return 1;
}
return 0;
}
@@ -2401,7 +2489,7 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
err = check_direct_IO(inode, iter, offset);
if (err)
return err;
return err < 0 ? err : 0;
if (f2fs_force_buffered_io(inode, rw))
return 0;
@@ -2495,6 +2583,10 @@ static int f2fs_set_data_page_dirty(struct page *page)
if (!PageUptodate(page))
SetPageUptodate(page);
/* don't remain PG_checked flag which was set during GC */
if (is_cold_data(page))
clear_cold_data(page);
if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
f2fs_register_inmem_page(inode, page);
fs/f2fs/debug.c
+2 -1
View File
@@ -215,7 +215,8 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
si->base_mem += sizeof(struct f2fs_nm_info);
si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE;
si->base_mem += NM_I(sbi)->nat_blocks *
f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK);
si->base_mem += NM_I(sbi)->nat_blocks / 8;
si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
fs/f2fs/dir.c
+1 -2
View File
@@ -517,12 +517,11 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
}
start:
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
f2fs_show_injection_info(FAULT_DIR_DEPTH);
return -ENOSPC;
}
#endif
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
return -ENOSPC;
fs/f2fs/f2fs.h
+132 -59
View File
File diff suppressed because it is too large Load Diff
fs/f2fs/file.c
+134 -86
View File
File diff suppressed because it is too large Load Diff
fs/f2fs/gc.c
+142 -23
View File
@@ -53,12 +53,10 @@ static int gc_thread_func(void *data)
continue;
}
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
f2fs_show_injection_info(FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
}
#endif
if (!sb_start_write_trylock(sbi->sb))
continue;
@@ -517,7 +515,11 @@ next_step:
continue;
}
f2fs_get_node_info(sbi, nid, &ni);
if (f2fs_get_node_info(sbi, nid, &ni)) {
f2fs_put_page(node_page, 1);
continue;
}
if (ni.blk_addr != start_addr + off) {
f2fs_put_page(node_page, 1);
continue;
@@ -576,7 +578,10 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (IS_ERR(node_page))
return false;
f2fs_get_node_info(sbi, nid, dni);
if (f2fs_get_node_info(sbi, nid, dni)) {
f2fs_put_page(node_page, 1);
return false;
}
if (sum->version != dni->version) {
f2fs_msg(sbi->sb, KERN_WARNING,
@@ -594,6 +599,72 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
return true;
}
static int ra_data_block(struct inode *inode, pgoff_t index)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
struct extent_info ei = {0, 0, 0};
struct f2fs_io_info fio = {
.sbi = sbi,
.ino = inode->i_ino,
.type = DATA,
.temp = COLD,
.op = REQ_OP_READ,
.op_flags = 0,
.encrypted_page = NULL,
.in_list = false,
.retry = false,
};
int err;
page = f2fs_grab_cache_page(mapping, index, true);
if (!page)
return -ENOMEM;
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
dn.data_blkaddr = ei.blk + index - ei.fofs;
goto got_it;
}
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err)
goto put_page;
f2fs_put_dnode(&dn);
if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr,
DATA_GENERIC))) {
err = -EFAULT;
goto put_page;
}
got_it:
/* read page */
fio.page = page;
fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(sbi),
dn.data_blkaddr,
FGP_LOCK | FGP_CREAT, GFP_NOFS);
if (!fio.encrypted_page) {
err = -ENOMEM;
goto put_page;
}
err = f2fs_submit_page_bio(&fio);
if (err)
goto put_encrypted_page;
f2fs_put_page(fio.encrypted_page, 0);
f2fs_put_page(page, 1);
return 0;
put_encrypted_page:
f2fs_put_page(fio.encrypted_page, 1);
put_page:
f2fs_put_page(page, 1);
return err;
}
/*
* Move data block via META_MAPPING while keeping locked data page.
* This can be used to move blocks, aka LBAs, directly on disk.
@@ -615,7 +686,7 @@ static void move_data_block(struct inode *inode, block_t bidx,
struct dnode_of_data dn;
struct f2fs_summary sum;
struct node_info ni;
struct page *page;
struct page *page, *mpage;
block_t newaddr;
int err;
bool lfs_mode = test_opt(fio.sbi, LFS);
@@ -655,7 +726,10 @@ static void move_data_block(struct inode *inode, block_t bidx,
*/
f2fs_wait_on_page_writeback(page, DATA, true);
f2fs_get_node_info(fio.sbi, dn.nid, &ni);
err = f2fs_get_node_info(fio.sbi, dn.nid, &ni);
if (err)
goto put_out;
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
/* read page */
@@ -675,6 +749,23 @@ static void move_data_block(struct inode *inode, block_t bidx,
goto recover_block;
}
mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
fio.old_blkaddr, FGP_LOCK, GFP_NOFS);
if (mpage) {
bool updated = false;
if (PageUptodate(mpage)) {
memcpy(page_address(fio.encrypted_page),
page_address(mpage), PAGE_SIZE);
updated = true;
}
f2fs_put_page(mpage, 1);
invalidate_mapping_pages(META_MAPPING(fio.sbi),
fio.old_blkaddr, fio.old_blkaddr);
if (updated)
goto write_page;
}
err = f2fs_submit_page_bio(&fio);
if (err)
goto put_page_out;
@@ -691,6 +782,7 @@ static void move_data_block(struct inode *inode, block_t bidx,
goto put_page_out;
}
write_page:
set_page_dirty(fio.encrypted_page);
f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true);
if (clear_page_dirty_for_io(fio.encrypted_page))
@@ -865,22 +957,30 @@ next_step:
if (IS_ERR(inode) || is_bad_inode(inode))
continue;
/* if inode uses special I/O path, let's go phase 3 */
if (!down_write_trylock(
&F2FS_I(inode)->i_gc_rwsem[WRITE])) {
iput(inode);
sbi->skipped_gc_rwsem++;
continue;
}
start_bidx = f2fs_start_bidx_of_node(nofs, inode) +
ofs_in_node;
if (f2fs_post_read_required(inode)) {
int err = ra_data_block(inode, start_bidx);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (err) {
iput(inode);
continue;
}
add_gc_inode(gc_list, inode);
continue;
}
if (!down_write_trylock(
&F2FS_I(inode)->i_gc_rwsem[WRITE])) {
iput(inode);
continue;
}
start_bidx = f2fs_start_bidx_of_node(nofs, inode);
data_page = f2fs_get_read_data_page(inode,
start_bidx + ofs_in_node, REQ_RAHEAD,
true);
start_bidx, REQ_RAHEAD, true);
up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
if (IS_ERR(data_page)) {
iput(inode);
@@ -903,6 +1003,7 @@ next_step:
continue;
if (!down_write_trylock(
&fi->i_gc_rwsem[WRITE])) {
sbi->skipped_gc_rwsem++;
up_write(&fi->i_gc_rwsem[READ]);
continue;
}
@@ -986,7 +1087,13 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
goto next;
sum = page_address(sum_page);
f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
if (type != GET_SUM_TYPE((&sum->footer))) {
f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent segment (%u) "
"type [%d, %d] in SSA and SIT",
segno, type, GET_SUM_TYPE((&sum->footer)));
set_sbi_flag(sbi, SBI_NEED_FSCK);
goto next;
}
/*
* this is to avoid deadlock:
@@ -1034,6 +1141,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
};
unsigned long long last_skipped = sbi->skipped_atomic_files[FG_GC];
unsigned long long first_skipped;
unsigned int skipped_round = 0, round = 0;
trace_f2fs_gc_begin(sbi->sb, sync, background,
@@ -1046,6 +1154,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
prefree_segments(sbi));
cpc.reason = __get_cp_reason(sbi);
sbi->skipped_gc_rwsem = 0;
first_skipped = last_skipped;
gc_more:
if (unlikely(!(sbi->sb->s_flags & SB_ACTIVE))) {
ret = -EINVAL;
@@ -1087,7 +1197,8 @@ gc_more:
total_freed += seg_freed;
if (gc_type == FG_GC) {
if (sbi->skipped_atomic_files[FG_GC] > last_skipped)
if (sbi->skipped_atomic_files[FG_GC] > last_skipped ||
sbi->skipped_gc_rwsem)
skipped_round++;
last_skipped = sbi->skipped_atomic_files[FG_GC];
round++;
@@ -1096,15 +1207,23 @@ gc_more:
if (gc_type == FG_GC)
sbi->cur_victim_sec = NULL_SEGNO;
if (!sync) {
if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
if (skipped_round > MAX_SKIP_ATOMIC_COUNT &&
skipped_round * 2 >= round)
f2fs_drop_inmem_pages_all(sbi, true);
if (sync)
goto stop;
if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
if (skipped_round <= MAX_SKIP_GC_COUNT ||
skipped_round * 2 < round) {
segno = NULL_SEGNO;
goto gc_more;
}
if (first_skipped < last_skipped &&
(last_skipped - first_skipped) >
sbi->skipped_gc_rwsem) {
f2fs_drop_inmem_pages_all(sbi, true);
segno = NULL_SEGNO;
goto gc_more;
}
if (gc_type == FG_GC)
ret = f2fs_write_checkpoint(sbi, &cpc);
}
fs/f2fs/inline.c
+35 -1
View File
@@ -121,6 +121,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
.encrypted_page = NULL,
.io_type = FS_DATA_IO,
};
struct node_info ni;
int dirty, err;
if (!f2fs_exist_data(dn->inode))
@@ -130,6 +131,24 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
if (err)
return err;
err = f2fs_get_node_info(fio.sbi, dn->nid, &ni);
if (err) {
f2fs_put_dnode(dn);
return err;
}
fio.version = ni.version;
if (unlikely(dn->data_blkaddr != NEW_ADDR)) {
f2fs_put_dnode(dn);
set_sbi_flag(fio.sbi, SBI_NEED_FSCK);
f2fs_msg(fio.sbi->sb, KERN_WARNING,
"%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
"run fsck to fix.",
__func__, dn->inode->i_ino, dn->data_blkaddr);
return -EINVAL;
}
f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
f2fs_do_read_inline_data(page, dn->inode_page);
@@ -363,6 +382,17 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
if (err)
goto out;
if (unlikely(dn.data_blkaddr != NEW_ADDR)) {
f2fs_put_dnode(&dn);
set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
f2fs_msg(F2FS_P_SB(page)->sb, KERN_WARNING,
"%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, "
"run fsck to fix.",
__func__, dir->i_ino, dn.data_blkaddr);
err = -EINVAL;
goto out;
}
f2fs_wait_on_page_writeback(page, DATA, true);
dentry_blk = page_address(page);
@@ -477,6 +507,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
return 0;
recover:
lock_page(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true);
memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir));
f2fs_i_depth_write(dir, 0);
f2fs_i_size_write(dir, MAX_INLINE_DATA(dir));
@@ -668,7 +699,10 @@ int f2fs_inline_data_fiemap(struct inode *inode,
ilen = start + len;
ilen -= start;
f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
if (err)
goto out;
byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
byteaddr += (char *)inline_data_addr(inode, ipage) -
(char *)F2FS_INODE(ipage);
fs/f2fs/inode.c
+132 -22
View File
@@ -68,13 +68,16 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
}
}
static bool __written_first_block(struct f2fs_inode *ri)
static int __written_first_block(struct f2fs_sb_info *sbi,
struct f2fs_inode *ri)
{
block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]);
if (is_valid_blkaddr(addr))
return true;
return false;
if (!__is_valid_data_blkaddr(addr))
return 1;
if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC))
return -EFAULT;
return 0;
}
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -121,7 +124,7 @@ static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page
if (!f2fs_sb_has_inode_chksum(sbi->sb))
return false;
if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR))
if (!IS_INODE(page) || !(ri->i_inline & F2FS_EXTRA_ATTR))
return false;
if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize),
@@ -159,8 +162,15 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
struct f2fs_inode *ri;
__u32 provided, calculated;
if (unlikely(is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)))
return true;
#ifdef CONFIG_F2FS_CHECK_FS
if (!f2fs_enable_inode_chksum(sbi, page))
#else
if (!f2fs_enable_inode_chksum(sbi, page) ||
PageDirty(page) || PageWriteback(page))
#endif
return true;
ri = &F2FS_NODE(page)->i;
@@ -185,9 +195,31 @@ void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page)
ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page));
}
static bool sanity_check_inode(struct inode *inode)
static bool sanity_check_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned long long iblocks;
iblocks = le64_to_cpu(F2FS_INODE(node_page)->i_blocks);
if (!iblocks) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted inode i_blocks i_ino=%lx iblocks=%llu, "
"run fsck to fix.",
__func__, inode->i_ino, iblocks);
return false;
}
if (ino_of_node(node_page) != nid_of_node(node_page)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted inode footer i_ino=%lx, ino,nid: "
"[%u, %u] run fsck to fix.",
__func__, inode->i_ino,
ino_of_node(node_page), nid_of_node(node_page));
return false;
}
if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)
&& !f2fs_has_extra_attr(inode)) {
@@ -197,6 +229,64 @@ static bool sanity_check_inode(struct inode *inode)
__func__, inode->i_ino);
return false;
}
if (f2fs_has_extra_attr(inode) &&
!f2fs_sb_has_extra_attr(sbi->sb)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx) is with extra_attr, "
"but extra_attr feature is off",
__func__, inode->i_ino);
return false;
}
if (fi->i_extra_isize > F2FS_TOTAL_EXTRA_ATTR_SIZE ||
fi->i_extra_isize % sizeof(__le32)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx) has corrupted i_extra_isize: %d, "
"max: %zu",
__func__, inode->i_ino, fi->i_extra_isize,
F2FS_TOTAL_EXTRA_ATTR_SIZE);
return false;
}
if (F2FS_I(inode)->extent_tree) {
struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest;
if (ei->len &&
(!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC) ||
!f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
DATA_GENERIC))) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx) extent info [%u, %u, %u] "
"is incorrect, run fsck to fix",
__func__, inode->i_ino,
ei->blk, ei->fofs, ei->len);
return false;
}
}
if (f2fs_has_inline_data(inode) &&
(!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx, mode=%u) should not have "
"inline_data, run fsck to fix",
__func__, inode->i_ino, inode->i_mode);
return false;
}
if (f2fs_has_inline_dentry(inode) && !S_ISDIR(inode->i_mode)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: inode (ino=%lx, mode=%u) should not have "
"inline_dentry, run fsck to fix",
__func__, inode->i_ino, inode->i_mode);
return false;
}
return true;
}
@@ -207,6 +297,7 @@ static int do_read_inode(struct inode *inode)
struct page *node_page;
struct f2fs_inode *ri;
projid_t i_projid;
int err;
/* Check if ino is within scope */
if (f2fs_check_nid_range(sbi, inode->i_ino))
@@ -268,6 +359,11 @@ static int do_read_inode(struct inode *inode)
fi->i_inline_xattr_size = 0;
}
if (!sanity_check_inode(inode, node_page)) {
f2fs_put_page(node_page, 1);
return -EINVAL;
}
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
@@ -275,8 +371,15 @@ static int do_read_inode(struct inode *inode)
/* get rdev by using inline_info */
__get_inode_rdev(inode, ri);
if (__written_first_block(ri))
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
if (S_ISREG(inode->i_mode)) {
err = __written_first_block(sbi, ri);
if (err < 0) {
f2fs_put_page(node_page, 1);
return err;
}
if (!err)
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
}
if (!f2fs_need_inode_block_update(sbi, inode->i_ino))
fi->last_disk_size = inode->i_size;
@@ -297,9 +400,9 @@ static int do_read_inode(struct inode *inode)
fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
}
F2FS_I(inode)->i_disk_time[0] = timespec64_to_timespec(inode->i_atime);
F2FS_I(inode)->i_disk_time[1] = timespec64_to_timespec(inode->i_ctime);
F2FS_I(inode)->i_disk_time[2] = timespec64_to_timespec(inode->i_mtime);
F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
f2fs_put_page(node_page, 1);
@@ -330,10 +433,6 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
ret = do_read_inode(inode);
if (ret)
goto bad_inode;
if (!sanity_check_inode(inode)) {
ret = -EINVAL;
goto bad_inode;
}
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
@@ -470,10 +569,14 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
if (inode->i_nlink == 0)
clear_inline_node(node_page);
F2FS_I(inode)->i_disk_time[0] = timespec64_to_timespec(inode->i_atime);
F2FS_I(inode)->i_disk_time[1] = timespec64_to_timespec(inode->i_ctime);
F2FS_I(inode)->i_disk_time[2] = timespec64_to_timespec(inode->i_mtime);
F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
#ifdef CONFIG_F2FS_CHECK_FS
f2fs_inode_chksum_set(F2FS_I_SB(inode), node_page);
#endif
}
void f2fs_update_inode_page(struct inode *inode)
@@ -558,12 +661,11 @@ retry:
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode);
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
f2fs_show_injection_info(FAULT_EVICT_INODE);
err = -EIO;
}
#endif
if (!err) {
f2fs_lock_op(sbi);
err = f2fs_remove_inode_page(inode);
@@ -626,6 +728,7 @@ void f2fs_handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct node_info ni;
int err;
/*
* clear nlink of inode in order to release resource of inode
@@ -648,10 +751,16 @@ void f2fs_handle_failed_inode(struct inode *inode)
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
f2fs_get_node_info(sbi, inode->i_ino, &ni);
err = f2fs_get_node_info(sbi, inode->i_ino, &ni);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"May loss orphan inode, run fsck to fix.");
goto out;
}
if (ni.blk_addr != NULL_ADDR) {
int err = f2fs_acquire_orphan_inode(sbi);
err = f2fs_acquire_orphan_inode(sbi);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
@@ -664,6 +773,7 @@ void f2fs_handle_failed_inode(struct inode *inode)
set_inode_flag(inode, FI_FREE_NID);
}
out:
f2fs_unlock_op(sbi);
/* iput will drop the inode object */
fs/f2fs/namei.c
+3 -3
View File
@@ -51,7 +51,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
inode->i_ino = ino;
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
F2FS_I(inode)->i_crtime = timespec64_to_timespec(inode->i_mtime);
F2FS_I(inode)->i_crtime = inode->i_mtime;
inode->i_generation = sbi->s_next_generation++;
if (S_ISDIR(inode->i_mode))
@@ -246,7 +246,7 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
return -EINVAL;
if (hot) {
strncpy(extlist[count], name, strlen(name));
memcpy(extlist[count], name, strlen(name));
sbi->raw_super->hot_ext_count = hot_count + 1;
} else {
char buf[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN];
@@ -254,7 +254,7 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
memcpy(buf, &extlist[cold_count],
F2FS_EXTENSION_LEN * hot_count);
memset(extlist[cold_count], 0, F2FS_EXTENSION_LEN);
strncpy(extlist[cold_count], name, strlen(name));
memcpy(extlist[cold_count], name, strlen(name));
memcpy(&extlist[cold_count + 1], buf,
F2FS_EXTENSION_LEN * hot_count);
sbi->raw_super->extension_count = cpu_to_le32(cold_count + 1);
fs/f2fs/node.c
+308 -76
View File
File diff suppressed because it is too large Load Diff
fs/f2fs/node.h
+9
View File
@@ -135,6 +135,11 @@ static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
}
static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi)
{
return get_pages(sbi, F2FS_DIRTY_NODES) >= sbi->blocks_per_seg * 8;
}
enum mem_type {
FREE_NIDS, /* indicates the free nid list */
NAT_ENTRIES, /* indicates the cached nat entry */
@@ -444,6 +449,10 @@ static inline void set_mark(struct page *page, int mark, int type)
else
flag &= ~(0x1 << type);
rn->footer.flag = cpu_to_le32(flag);
#ifdef CONFIG_F2FS_CHECK_FS
f2fs_inode_chksum_set(F2FS_P_SB(page), page);
#endif
}
#define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT)
#define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT)
fs/f2fs/recovery.c
+21 -10
View File
@@ -241,8 +241,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
struct page *page = NULL;
block_t blkaddr;
unsigned int loop_cnt = 0;
unsigned int free_blocks = sbi->user_block_count -
valid_user_blocks(sbi);
unsigned int free_blocks = MAIN_SEGS(sbi) * sbi->blocks_per_seg -
valid_user_blocks(sbi);
int err = 0;
/* get node pages in the current segment */
@@ -252,10 +252,14 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_meta_blkaddr(sbi, blkaddr, META_POR))
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
}
if (!is_recoverable_dnode(page))
break;
@@ -471,7 +475,10 @@ retry_dn:
f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
f2fs_get_node_info(sbi, dn.nid, &ni);
err = f2fs_get_node_info(sbi, dn.nid, &ni);
if (err)
goto err;
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page));
@@ -507,14 +514,13 @@ retry_dn:
}
/* dest is valid block, try to recover from src to dest */
if (f2fs_is_valid_meta_blkaddr(sbi, dest, META_POR)) {
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = f2fs_reserve_new_block(&dn);
#ifdef CONFIG_F2FS_FAULT_INJECTION
while (err)
while (err &&
IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION))
err = f2fs_reserve_new_block(&dn);
#endif
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
if (err)
@@ -568,12 +574,16 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_meta_blkaddr(sbi, blkaddr, META_POR))
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
f2fs_ra_meta_pages_cond(sbi, blkaddr);
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
}
if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
@@ -628,7 +638,8 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
#endif
if (s_flags & SB_RDONLY) {
f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
f2fs_msg(sbi->sb, KERN_INFO,
"recover fsync data on readonly fs");
sbi->sb->s_flags &= ~SB_RDONLY;
}
fs/f2fs/segment.c
+307 -90
View File
File diff suppressed because it is too large Load Diff
fs/f2fs/segment.h
+8 -8
View File
@@ -85,7 +85,7 @@
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))
#define GET_SEGNO(sbi, blk_addr) \
((!is_valid_blkaddr(blk_addr)) ? \
((!is_valid_data_blkaddr(sbi, blk_addr)) ? \
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
#define BLKS_PER_SEC(sbi) \
@@ -215,7 +215,7 @@ struct segment_allocation {
#define IS_DUMMY_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
#define MAX_SKIP_ATOMIC_COUNT 16
#define MAX_SKIP_GC_COUNT 16
struct inmem_pages {
struct list_head list;
@@ -448,6 +448,8 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
if (test_and_clear_bit(segno, free_i->free_segmap)) {
free_i->free_segments++;
if (IS_CURSEC(sbi, secno))
goto skip_free;
next = find_next_bit(free_i->free_segmap,
start_segno + sbi->segs_per_sec, start_segno);
if (next >= start_segno + sbi->segs_per_sec) {
@@ -455,6 +457,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
free_i->free_sections++;
}
}
skip_free:
spin_unlock(&free_i->segmap_lock);
}
@@ -645,13 +648,10 @@ static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
{
struct f2fs_sb_info *sbi = fio->sbi;
if (PAGE_TYPE_OF_BIO(fio->type) == META &&
(!is_read_io(fio->op) || fio->is_meta))
BUG_ON(blk_addr < SEG0_BLKADDR(sbi) ||
blk_addr >= MAIN_BLKADDR(sbi));
if (__is_meta_io(fio))
verify_blkaddr(sbi, blk_addr, META_GENERIC);
else
BUG_ON(blk_addr < MAIN_BLKADDR(sbi) ||
blk_addr >= MAX_BLKADDR(sbi));
verify_blkaddr(sbi, blk_addr, DATA_GENERIC);
}
/*
fs/f2fs/super.c
+122 -40
View File
@@ -41,7 +41,7 @@ static struct kmem_cache *f2fs_inode_cachep;
#ifdef CONFIG_F2FS_FAULT_INJECTION
char *fault_name[FAULT_MAX] = {
char *f2fs_fault_name[FAULT_MAX] = {
[FAULT_KMALLOC] = "kmalloc",
[FAULT_KVMALLOC] = "kvmalloc",
[FAULT_PAGE_ALLOC] = "page alloc",
@@ -55,20 +55,24 @@ char *fault_name[FAULT_MAX] = {
[FAULT_TRUNCATE] = "truncate fail",
[FAULT_IO] = "IO error",
[FAULT_CHECKPOINT] = "checkpoint error",
[FAULT_DISCARD] = "discard error",
};
static void f2fs_build_fault_attr(struct f2fs_sb_info *sbi,
unsigned int rate)
void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
unsigned int type)
{
struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
if (rate) {
atomic_set(&ffi->inject_ops, 0);
ffi->inject_rate = rate;
ffi->inject_type = (1 << FAULT_MAX) - 1;
} else {
memset(ffi, 0, sizeof(struct f2fs_fault_info));
}
if (type)
ffi->inject_type = type;
if (!rate && !type)
memset(ffi, 0, sizeof(struct f2fs_fault_info));
}
#endif
@@ -113,6 +117,7 @@ enum {
Opt_mode,
Opt_io_size_bits,
Opt_fault_injection,
Opt_fault_type,
Opt_lazytime,
Opt_nolazytime,
Opt_quota,
@@ -170,6 +175,7 @@ static match_table_t f2fs_tokens = {
{Opt_mode, "mode=%s"},
{Opt_io_size_bits, "io_bits=%u"},
{Opt_fault_injection, "fault_injection=%u"},
{Opt_fault_type, "fault_type=%u"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
{Opt_quota, "quota"},
@@ -347,12 +353,6 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi)
"QUOTA feature is enabled, so ignore jquota_fmt");
F2FS_OPTION(sbi).s_jquota_fmt = 0;
}
if (f2fs_sb_has_quota_ino(sbi->sb) && f2fs_readonly(sbi->sb)) {
f2fs_msg(sbi->sb, KERN_INFO,
"Filesystem with quota feature cannot be mounted RDWR "
"without CONFIG_QUOTA");
return -1;
}
return 0;
}
#endif
@@ -606,7 +606,18 @@ static int parse_options(struct super_block *sb, char *options)
if (args->from && match_int(args, &arg))
return -EINVAL;
#ifdef CONFIG_F2FS_FAULT_INJECTION
f2fs_build_fault_attr(sbi, arg);
f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE);
set_opt(sbi, FAULT_INJECTION);
#else
f2fs_msg(sb, KERN_INFO,
"FAULT_INJECTION was not selected");
#endif
break;
case Opt_fault_type:
if (args->from && match_int(args, &arg))
return -EINVAL;
#ifdef CONFIG_F2FS_FAULT_INJECTION
f2fs_build_fault_attr(sbi, 0, arg);
set_opt(sbi, FAULT_INJECTION);
#else
f2fs_msg(sb, KERN_INFO,
@@ -775,6 +786,19 @@ static int parse_options(struct super_block *sb, char *options)
#ifdef CONFIG_QUOTA
if (f2fs_check_quota_options(sbi))
return -EINVAL;
#else
if (f2fs_sb_has_quota_ino(sbi->sb) && !f2fs_readonly(sbi->sb)) {
f2fs_msg(sbi->sb, KERN_INFO,
"Filesystem with quota feature cannot be mounted RDWR "
"without CONFIG_QUOTA");
return -EINVAL;
}
if (f2fs_sb_has_project_quota(sbi->sb) && !f2fs_readonly(sbi->sb)) {
f2fs_msg(sb, KERN_ERR,
"Filesystem with project quota feature cannot be "
"mounted RDWR without CONFIG_QUOTA");
return -EINVAL;
}
#endif
if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
@@ -1030,6 +1054,10 @@ static void f2fs_put_super(struct super_block *sb)
/* our cp_error case, we can wait for any writeback page */
f2fs_flush_merged_writes(sbi);
f2fs_wait_on_all_pages_writeback(sbi);
f2fs_bug_on(sbi, sbi->fsync_node_num);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -1118,7 +1146,7 @@ static int f2fs_statfs_project(struct super_block *sb,
dquot = dqget(sb, qid);
if (IS_ERR(dquot))
return PTR_ERR(dquot);
spin_lock(&dq_data_lock);
spin_lock(&dquot->dq_dqb_lock);
limit = (dquot->dq_dqb.dqb_bsoftlimit ?
dquot->dq_dqb.dqb_bsoftlimit :
@@ -1141,7 +1169,7 @@ static int f2fs_statfs_project(struct super_block *sb,
(buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
}
spin_unlock(&dq_data_lock);
spin_unlock(&dquot->dq_dqb_lock);
dqput(dquot);
return 0;
}
@@ -1310,9 +1338,12 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
if (F2FS_IO_SIZE_BITS(sbi))
seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi));
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (test_opt(sbi, FAULT_INJECTION))
if (test_opt(sbi, FAULT_INJECTION)) {
seq_printf(seq, ",fault_injection=%u",
F2FS_OPTION(sbi).fault_info.inject_rate);
seq_printf(seq, ",fault_type=%u",
F2FS_OPTION(sbi).fault_info.inject_type);
}
#endif
#ifdef CONFIG_QUOTA
if (test_opt(sbi, QUOTA))
@@ -1343,6 +1374,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_printf(seq, ",fsync_mode=%s", "posix");
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
seq_printf(seq, ",fsync_mode=%s", "strict");
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER)
seq_printf(seq, ",fsync_mode=%s", "nobarrier");
return 0;
}
@@ -1355,7 +1388,8 @@ static void default_options(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX;
F2FS_OPTION(sbi).test_dummy_encryption = false;
sbi->readdir_ra = 1;
F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
set_opt(sbi, BG_GC);
set_opt(sbi, INLINE_XATTR);
@@ -1365,12 +1399,12 @@ static void default_options(struct f2fs_sb_info *sbi)
set_opt(sbi, NOHEAP);
sbi->sb->s_flags |= SB_LAZYTIME;
set_opt(sbi, FLUSH_MERGE);
if (f2fs_sb_has_blkzoned(sbi->sb)) {
set_opt_mode(sbi, F2FS_MOUNT_LFS);
if (blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev)))
set_opt(sbi, DISCARD);
} else {
if (f2fs_sb_has_blkzoned(sbi->sb))
set_opt_mode(sbi, F2FS_MOUNT_LFS);
else
set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
}
#ifdef CONFIG_F2FS_FS_XATTR
set_opt(sbi, XATTR_USER);
@@ -1379,9 +1413,7 @@ static void default_options(struct f2fs_sb_info *sbi)
set_opt(sbi, POSIX_ACL);
#endif
#ifdef CONFIG_F2FS_FAULT_INJECTION
f2fs_build_fault_attr(sbi, 0);
#endif
f2fs_build_fault_attr(sbi, 0, 0);
}
#ifdef CONFIG_QUOTA
@@ -2229,9 +2261,9 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
return 1;
}
if (secs_per_zone > total_sections) {
if (secs_per_zone > total_sections || !secs_per_zone) {
f2fs_msg(sb, KERN_INFO,
"Wrong secs_per_zone (%u > %u)",
"Wrong secs_per_zone / total_sections (%u, %u)",
secs_per_zone, total_sections);
return 1;
}
@@ -2282,12 +2314,20 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned int ovp_segments, reserved_segments;
unsigned int main_segs, blocks_per_seg;
unsigned int sit_segs, nat_segs;
unsigned int sit_bitmap_size, nat_bitmap_size;
unsigned int log_blocks_per_seg;
unsigned int segment_count_main;
unsigned int cp_pack_start_sum, cp_payload;
block_t user_block_count;
int i;
total = le32_to_cpu(raw_super->segment_count);
fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
fsmeta += le32_to_cpu(raw_super->segment_count_sit);
fsmeta += le32_to_cpu(raw_super->segment_count_nat);
sit_segs = le32_to_cpu(raw_super->segment_count_sit);
fsmeta += sit_segs;
nat_segs = le32_to_cpu(raw_super->segment_count_nat);
fsmeta += nat_segs;
fsmeta += le32_to_cpu(ckpt->rsvd_segment_count);
fsmeta += le32_to_cpu(raw_super->segment_count_ssa);
@@ -2304,6 +2344,16 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
return 1;
}
user_block_count = le64_to_cpu(ckpt->user_block_count);
segment_count_main = le32_to_cpu(raw_super->segment_count_main);
log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
if (!user_block_count || user_block_count >=
segment_count_main << log_blocks_per_seg) {
f2fs_msg(sbi->sb, KERN_ERR,
"Wrong user_block_count: %u", user_block_count);
return 1;
}
main_segs = le32_to_cpu(raw_super->segment_count_main);
blocks_per_seg = sbi->blocks_per_seg;
@@ -2318,6 +2368,28 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
return 1;
}
sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 ||
nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) {
f2fs_msg(sbi->sb, KERN_ERR,
"Wrong bitmap size: sit: %u, nat:%u",
sit_bitmap_size, nat_bitmap_size);
return 1;
}
cp_pack_start_sum = __start_sum_addr(sbi);
cp_payload = __cp_payload(sbi);
if (cp_pack_start_sum < cp_payload + 1 ||
cp_pack_start_sum > blocks_per_seg - 1 -
NR_CURSEG_TYPE) {
f2fs_msg(sbi->sb, KERN_ERR,
"Wrong cp_pack_start_sum: %u",
cp_pack_start_sum);
return 1;
}
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
return 1;
@@ -2651,6 +2723,8 @@ static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi)
sm_i->dcc_info->discard_granularity = 1;
sm_i->ipu_policy = 1 << F2FS_IPU_FORCE;
}
sbi->readdir_ra = 1;
}
static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
@@ -2700,9 +2774,6 @@ try_onemore:
sb->s_fs_info = sbi;
sbi->raw_super = raw_super;
F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
/* precompute checksum seed for metadata */
if (f2fs_sb_has_inode_chksum(sb))
sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid,
@@ -2771,6 +2842,7 @@ try_onemore:
/* init f2fs-specific super block info */
sbi->valid_super_block = valid_super_block;
mutex_init(&sbi->gc_mutex);
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
init_rwsem(&sbi->node_change);
@@ -2865,6 +2937,8 @@ try_onemore:
f2fs_init_ino_entry_info(sbi);
f2fs_init_fsync_node_info(sbi);
/* setup f2fs internal modules */
err = f2fs_build_segment_manager(sbi);
if (err) {
@@ -2912,10 +2986,11 @@ try_onemore:
err = PTR_ERR(root);
goto free_stats;
}
if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
if (!S_ISDIR(root->i_mode) || !root->i_blocks ||
!root->i_size || !root->i_nlink) {
iput(root);
err = -EINVAL;
goto free_node_inode;
goto free_stats;
}
sb->s_root = d_make_root(root); /* allocate root dentry */
@@ -2929,10 +3004,7 @@ try_onemore:
goto free_root_inode;
#ifdef CONFIG_QUOTA
/*
* Turn on quotas which were not enabled for read-only mounts if
* filesystem has quota feature, so that they are updated correctly.
*/
/* Enable quota usage during mount */
if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb)) {
err = f2fs_enable_quotas(sb);
if (err) {
@@ -3090,9 +3162,19 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
static void kill_f2fs_super(struct super_block *sb)
{
if (sb->s_root) {
set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
f2fs_stop_gc_thread(F2FS_SB(sb));
f2fs_stop_discard_thread(F2FS_SB(sb));
struct f2fs_sb_info *sbi = F2FS_SB(sb);
set_sbi_flag(sbi, SBI_IS_CLOSE);
f2fs_stop_gc_thread(sbi);
f2fs_stop_discard_thread(sbi);
if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
struct cp_control cpc = {
.reason = CP_UMOUNT,
};
f2fs_write_checkpoint(sbi, &cpc);
}
}
kill_block_super(sb);
}
fs/f2fs/sysfs.c
+39 -5
View File
@@ -9,6 +9,7 @@
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/compiler.h>
#include <linux/proc_fs.h>
#include <linux/f2fs_fs.h>
#include <linux/seq_file.h>
@@ -252,6 +253,7 @@ out:
if (t >= 1) {
sbi->gc_mode = GC_URGENT;
if (sbi->gc_thread) {
sbi->gc_thread->gc_wake = 1;
wake_up_interruptible_all(
&sbi->gc_thread->gc_wait_queue_head);
wake_up_discard_thread(sbi, true);
@@ -286,8 +288,10 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
bool gc_entry = (!strcmp(a->attr.name, "gc_urgent") ||
a->struct_type == GC_THREAD);
if (gc_entry)
down_read(&sbi->sb->s_umount);
if (gc_entry) {
if (!down_read_trylock(&sbi->sb->s_umount))
return -EAGAIN;
}
ret = __sbi_store(a, sbi, buf, count);
if (gc_entry)
up_read(&sbi->sb->s_umount);
@@ -393,6 +397,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_seq_blocks, min_seq_blocks);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ssr_sections, min_ssr_sections);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
@@ -445,6 +450,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
ATTR_LIST(min_fsync_blocks),
ATTR_LIST(min_seq_blocks),
ATTR_LIST(min_hot_blocks),
ATTR_LIST(min_ssr_sections),
ATTR_LIST(max_victim_search),
@@ -516,7 +522,8 @@ static struct kobject f2fs_feat = {
.kset = &f2fs_kset,
};
static int segment_info_seq_show(struct seq_file *seq, void *offset)
static int __maybe_unused segment_info_seq_show(struct seq_file *seq,
void *offset)
{
struct super_block *sb = seq->private;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -543,7 +550,8 @@ static int segment_info_seq_show(struct seq_file *seq, void *offset)
return 0;
}
static int segment_bits_seq_show(struct seq_file *seq, void *offset)
static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
void *offset)
{
struct super_block *sb = seq->private;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -567,7 +575,8 @@ static int segment_bits_seq_show(struct seq_file *seq, void *offset)
return 0;
}
static int iostat_info_seq_show(struct seq_file *seq, void *offset)
static int __maybe_unused iostat_info_seq_show(struct seq_file *seq,
void *offset)
{
struct super_block *sb = seq->private;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -609,6 +618,28 @@ static int iostat_info_seq_show(struct seq_file *seq, void *offset)
return 0;
}
static int __maybe_unused victim_bits_seq_show(struct seq_file *seq,
void *offset)
{
struct super_block *sb = seq->private;
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
int i;
seq_puts(seq, "format: victim_secmap bitmaps\n");
for (i = 0; i < MAIN_SECS(sbi); i++) {
if ((i % 10) == 0)
seq_printf(seq, "%-10d", i);
seq_printf(seq, "%d", test_bit(i, dirty_i->victim_secmap) ? 1 : 0);
if ((i % 10) == 9 || i == (MAIN_SECS(sbi) - 1))
seq_putc(seq, '\n');
else
seq_putc(seq, ' ');
}
return 0;
}
int __init f2fs_init_sysfs(void)
{
int ret;
@@ -658,6 +689,8 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
segment_bits_seq_show, sb);
proc_create_single_data("iostat_info", S_IRUGO, sbi->s_proc,
iostat_info_seq_show, sb);
proc_create_single_data("victim_bits", S_IRUGO, sbi->s_proc,
victim_bits_seq_show, sb);
}
return 0;
}
@@ -668,6 +701,7 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
remove_proc_entry("iostat_info", sbi->s_proc);
remove_proc_entry("segment_info", sbi->s_proc);
remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry("victim_bits", sbi->s_proc);
remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
}
kobject_del(&sbi->s_kobj);
fs/f2fs/xattr.c
+11 -7
View File
@@ -37,9 +37,6 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler,
return -EOPNOTSUPP;
break;
case F2FS_XATTR_INDEX_TRUSTED:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
break;
case F2FS_XATTR_INDEX_SECURITY:
break;
default:
@@ -62,9 +59,6 @@ static int f2fs_xattr_generic_set(const struct xattr_handler *handler,
return -EOPNOTSUPP;
break;
case F2FS_XATTR_INDEX_TRUSTED:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
break;
case F2FS_XATTR_INDEX_SECURITY:
break;
default:
@@ -100,12 +94,22 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
const char *name, const void *value,
size_t size, int flags)
{
unsigned char old_advise = F2FS_I(inode)->i_advise;
unsigned char new_advise;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (value == NULL)
return -EINVAL;
F2FS_I(inode)->i_advise |= *(char *)value;
new_advise = *(char *)value;
if (new_advise & ~FADVISE_MODIFIABLE_BITS)
return -EINVAL;
new_advise = new_advise & FADVISE_MODIFIABLE_BITS;
new_advise |= old_advise & ~FADVISE_MODIFIABLE_BITS;
F2FS_I(inode)->i_advise = new_advise;
f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}

Some files were not shown because too many files have changed in this diff Show More