summaryrefslogtreecommitdiff
path: root/fs/f2fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/f2fs')
-rw-r--r--fs/f2fs/acl.c14
-rw-r--r--fs/f2fs/checkpoint.c168
-rw-r--r--fs/f2fs/data.c118
-rw-r--r--fs/f2fs/dir.c87
-rw-r--r--fs/f2fs/f2fs.h77
-rw-r--r--fs/f2fs/file.c24
-rw-r--r--fs/f2fs/inline.c115
-rw-r--r--fs/f2fs/inode.c68
-rw-r--r--fs/f2fs/node.c107
-rw-r--r--fs/f2fs/node.h77
-rw-r--r--fs/f2fs/recovery.c165
-rw-r--r--fs/f2fs/segment.c98
-rw-r--r--fs/f2fs/segment.h48
-rw-r--r--fs/f2fs/super.c134
14 files changed, 880 insertions, 420 deletions
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 83dcf7bfd7b8..f0ea91925343 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -350,12 +350,14 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode,
return PTR_ERR(p);
clone = f2fs_acl_clone(p, GFP_NOFS);
- if (!clone)
- goto no_mem;
+ if (!clone) {
+ ret = -ENOMEM;
+ goto release_acl;
+ }
ret = f2fs_acl_create_masq(clone, mode);
if (ret < 0)
- goto no_mem_clone;
+ goto release_clone;
if (ret == 0)
posix_acl_release(clone);
@@ -369,11 +371,11 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode,
return 0;
-no_mem_clone:
+release_clone:
posix_acl_release(clone);
-no_mem:
+release_acl:
posix_acl_release(p);
- return -ENOMEM;
+ return ret;
}
int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f661d80474be..4b2f609f376d 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -58,6 +58,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
.rw = READ_SYNC | REQ_META | REQ_PRIO,
.blk_addr = index,
.encrypted_page = NULL,
+ .is_meta = is_meta,
};
if (unlikely(!is_meta))
@@ -74,8 +75,10 @@ repeat:
fio.page = page;
if (f2fs_submit_page_bio(&fio)) {
- f2fs_put_page(page, 1);
- goto repeat;
+ memset(page_address(page), 0, PAGE_SIZE);
+ f2fs_stop_checkpoint(sbi);
+ f2fs_bug_on(sbi, 1);
+ return page;
}
lock_page(page);
@@ -106,7 +109,8 @@ struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
return __get_meta_page(sbi, index, false);
}
-bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
{
switch (type) {
case META_NAT:
@@ -126,8 +130,20 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
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:
@@ -151,6 +167,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
.type = META,
.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
.encrypted_page = NULL,
+ .is_meta = (type != META_POR),
};
if (unlikely(type == META_POR))
@@ -158,7 +175,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
for (; nrpages-- > 0; blkno++) {
- if (!is_valid_blkaddr(sbi, blkno, type))
+ if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
goto out;
switch (type) {
@@ -601,54 +618,73 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
}
}
-static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
- block_t cp_addr, unsigned long long *version)
+static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
+ struct f2fs_checkpoint **cp_block, struct page **cp_page,
+ unsigned long long *version)
{
- struct page *cp_page_1, *cp_page_2 = NULL;
unsigned long blk_size = sbi->blocksize;
- struct f2fs_checkpoint *cp_block;
- unsigned long long cur_version = 0, pre_version = 0;
- size_t crc_offset;
+ size_t crc_offset = 0;
__u32 crc = 0;
- /* Read the 1st cp block in this CP pack */
- cp_page_1 = get_meta_page(sbi, cp_addr);
+ *cp_page = get_meta_page(sbi, cp_addr);
+ *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
- /* get the version number */
- cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
- crc_offset = le32_to_cpu(cp_block->checksum_offset);
- if (crc_offset >= blk_size)
- goto invalid_cp1;
-
- crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
- if (!f2fs_crc_valid(crc, cp_block, crc_offset))
- goto invalid_cp1;
+ crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
+ if (crc_offset >= blk_size) {
+ f2fs_put_page(*cp_page, 1);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "invalid crc_offset: %zu", crc_offset);
+ return -EINVAL;
+ }
- pre_version = cur_cp_version(cp_block);
+ crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
+ + crc_offset)));
+ if (!f2fs_crc_valid(crc, *cp_block, crc_offset)) {
+ f2fs_put_page(*cp_page, 1);
+ f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
+ return -EINVAL;
+ }
- /* Read the 2nd cp block in this CP pack */
- cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
- cp_page_2 = get_meta_page(sbi, cp_addr);
+ *version = cur_cp_version(*cp_block);
+ return 0;
+}
- cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
- crc_offset = le32_to_cpu(cp_block->checksum_offset);
- if (crc_offset >= blk_size)
- goto invalid_cp2;
+static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
+ block_t cp_addr, unsigned long long *version)
+{
+ struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
+ struct f2fs_checkpoint *cp_block = NULL;
+ unsigned long long cur_version = 0, pre_version = 0;
+ int err;
- crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
- if (!f2fs_crc_valid(crc, cp_block, crc_offset))
- goto invalid_cp2;
+ err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+ &cp_page_1, version);
+ if (err)
+ 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;
- cur_version = cur_cp_version(cp_block);
+ 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_cp;
+ cur_version = *version;
if (cur_version == pre_version) {
*version = cur_version;
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;
}
@@ -696,6 +732,15 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
memcpy(sbi->ckpt, cp_block, blk_size);
+ if (cur_page == cp1)
+ sbi->cur_cp_pack = 1;
+ else
+ sbi->cur_cp_pack = 2;
+
+ /* Sanity checking of checkpoint */
+ if (sanity_check_ckpt(sbi))
+ goto free_fail_no_cp;
+
if (cp_blks <= 1)
goto done;
@@ -717,6 +762,9 @@ done:
f2fs_put_page(cp2, 1);
return 0;
+free_fail_no_cp:
+ f2fs_put_page(cp1, 1);
+ f2fs_put_page(cp2, 1);
fail_no_cp:
kfree(sbi->ckpt);
return -EINVAL;
@@ -767,24 +815,6 @@ out:
f2fs_trace_pid(page);
}
-void add_dirty_dir_inode(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct inode_entry *new =
- f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
- int ret = 0;
-
- new->inode = inode;
- INIT_LIST_HEAD(&new->list);
-
- spin_lock(&sbi->dir_inode_lock);
- ret = __add_dirty_inode(inode, new);
- spin_unlock(&sbi->dir_inode_lock);
-
- if (ret)
- kmem_cache_free(inode_entry_slab, new);
-}
-
void remove_dirty_dir_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -807,12 +837,6 @@ void remove_dirty_dir_inode(struct inode *inode)
stat_dec_dirty_dir(sbi);
spin_unlock(&sbi->dir_inode_lock);
kmem_cache_free(inode_entry_slab, entry);
-
- /* Only from the recovery routine */
- if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
- clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
- iput(inode);
- }
}
void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
@@ -922,7 +946,6 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct f2fs_nm_info *nm_i = NM_I(sbi);
unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
nid_t last_nid = nm_i->next_scan_nid;
@@ -931,15 +954,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
__u32 crc32 = 0;
int i;
int cp_payload_blks = __cp_payload(sbi);
- block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
- bool invalidate = false;
-
- /*
- * This avoids to conduct wrong roll-forward operations and uses
- * metapages, so should be called prior to sync_meta_pages below.
- */
- if (discard_next_dnode(sbi, discard_blk))
- invalidate = true;
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
@@ -1016,6 +1030,9 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+ /* set this flag to activate crc|cp_ver for recovery */
+ set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
@@ -1025,7 +1042,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
le32_to_cpu(ckpt->checksum_offset)))
= cpu_to_le32(crc32);
- start_blk = __start_cp_addr(sbi);
+ start_blk = __start_cp_next_addr(sbi);
/* need to wait for end_io results */
wait_on_all_pages_writeback(sbi);
@@ -1073,14 +1090,6 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* wait for previous submitted meta pages writeback */
wait_on_all_pages_writeback(sbi);
- /*
- * invalidate meta page which is used temporarily for zeroing out
- * block at the end of warm node chain.
- */
- if (invalidate)
- invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
- discard_blk);
-
release_dirty_inode(sbi);
if (unlikely(f2fs_cp_error(sbi)))
@@ -1088,6 +1097,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
clear_prefree_segments(sbi, cpc);
clear_sbi_flag(sbi, SBI_IS_DIRTY);
+ __set_cp_next_pack(sbi);
}
/*
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f6ccb21f286b..2b0b671484bd 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -147,6 +147,10 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
struct bio *bio;
struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+ if (!f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr,
+ __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
+ return -EFAULT;
+
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
@@ -172,7 +176,7 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
io = is_read ? &sbi->read_io : &sbi->write_io[btype];
- verify_block_addr(sbi, fio->blk_addr);
+ verify_block_addr(fio, fio->blk_addr);
down_write(&io->io_rwsem);
@@ -603,7 +607,13 @@ static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+ if (__is_valid_data_blkaddr(dn.data_blkaddr) &&
+ !f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC)) {
+ err = -EFAULT;
+ goto sync_out;
+ }
+
+ if (!is_valid_data_blkaddr(sbi, dn.data_blkaddr)) {
if (create) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
@@ -866,6 +876,40 @@ out:
return ret;
}
+struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
+ unsigned nr_pages)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_crypto_ctx *ctx = NULL;
+ struct block_device *bdev = sbi->sb->s_bdev;
+ struct bio *bio;
+
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+ return ERR_PTR(-EFAULT);
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ ctx = f2fs_get_crypto_ctx(inode);
+ if (IS_ERR(ctx))
+ return ERR_CAST(ctx);
+
+ /* wait the page to be moved by cleaning */
+ f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+ }
+
+ bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+ if (!bio) {
+ if (ctx)
+ f2fs_release_crypto_ctx(ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ bio->bi_bdev = bdev;
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blkaddr);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = ctx;
+
+ return bio;
+}
+
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
@@ -884,7 +928,6 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
- struct block_device *bdev = inode->i_sb->s_bdev;
struct f2fs_map_blocks map;
map.m_pblk = 0;
@@ -941,6 +984,10 @@ 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_CACHE_SIZE);
SetPageUptodate(page);
@@ -958,31 +1005,9 @@ submit_and_realloc:
bio = NULL;
}
if (bio == NULL) {
- struct f2fs_crypto_ctx *ctx = NULL;
-
- if (f2fs_encrypted_inode(inode) &&
- S_ISREG(inode->i_mode)) {
-
- ctx = f2fs_get_crypto_ctx(inode);
- if (IS_ERR(ctx))
- goto set_error_page;
-
- /* wait the page to be moved by cleaning */
- f2fs_wait_on_encrypted_page_writeback(
- F2FS_I_SB(inode), block_nr);
- }
-
- bio = bio_alloc(GFP_KERNEL,
- min_t(int, nr_pages, BIO_MAX_PAGES));
- if (!bio) {
- if (ctx)
- f2fs_release_crypto_ctx(ctx);
+ bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+ if (IS_ERR(bio))
goto set_error_page;
- }
- bio->bi_bdev = bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
- bio->bi_end_io = f2fs_read_end_io;
- bio->bi_private = ctx;
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
@@ -1077,11 +1102,17 @@ int do_write_data_page(struct f2fs_io_info *fio)
set_page_writeback(page);
+ if (__is_valid_data_blkaddr(fio->blk_addr) &&
+ !f2fs_is_valid_blkaddr(fio->sbi, fio->blk_addr,
+ DATA_GENERIC)) {
+ err = -EFAULT;
+ goto out_writepage;
+ }
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
- if (unlikely(fio->blk_addr != NEW_ADDR &&
+ if (unlikely(is_valid_data_blkaddr(fio->sbi, fio->blk_addr) &&
!is_cold_data(page) &&
need_inplace_update(inode))) {
rewrite_data_page(fio);
@@ -1482,17 +1513,21 @@ put_next:
if (dn.data_blkaddr == NEW_ADDR) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
} else {
- struct f2fs_io_info fio = {
- .sbi = sbi,
- .type = DATA,
- .rw = READ_SYNC,
- .blk_addr = dn.data_blkaddr,
- .page = page,
- .encrypted_page = NULL,
- };
- err = f2fs_submit_page_bio(&fio);
- if (err)
+ struct bio *bio;
+
+ bio = f2fs_grab_bio(inode, dn.data_blkaddr, 1);
+ if (IS_ERR(bio)) {
+ err = PTR_ERR(bio);
goto fail;
+ }
+
+ if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+ bio_put(bio);
+ err = -EFAULT;
+ goto fail;
+ }
+
+ submit_bio(READ_SYNC, bio);
lock_page(page);
if (unlikely(!PageUptodate(page))) {
@@ -1503,13 +1538,6 @@ put_next:
f2fs_put_page(page, 1);
goto repeat;
}
-
- /* avoid symlink page */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
- err = f2fs_decrypt_one(inode, page);
- if (err)
- goto fail;
- }
}
out_update:
SetPageUptodate(page);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 60972a559685..92a240616f52 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
[F2FS_FT_SYMLINK] = DT_LNK,
};
-#define S_SHIFT 12
static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = F2FS_FT_DIR,
@@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+ if (de->file_type < F2FS_FT_MAX)
+ return f2fs_filetype_table[de->file_type];
+ return DT_UNKNOWN;
+}
+
static unsigned long dir_block_index(unsigned int level,
int dir_level, unsigned int idx)
{
@@ -519,11 +525,7 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
}
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
struct inode *inode, nid_t ino, umode_t mode)
{
unsigned int bit_pos;
@@ -536,28 +538,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
struct f2fs_dentry_block *dentry_blk = NULL;
struct f2fs_dentry_ptr d;
struct page *page = NULL;
- struct f2fs_filename fname;
- struct qstr new_name;
- int slots, err;
-
- err = f2fs_fname_setup_filename(dir, name, 0, &fname);
- if (err)
- return err;
-
- new_name.name = fname_name(&fname);
- new_name.len = fname_len(&fname);
-
- if (f2fs_has_inline_dentry(dir)) {
- err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
- if (!err || err != -EAGAIN)
- goto out;
- else
- err = 0;
- }
+ int slots, err = 0;
level = 0;
- slots = GET_DENTRY_SLOTS(new_name.len);
- dentry_hash = f2fs_dentry_hash(&new_name, NULL);
+ slots = GET_DENTRY_SLOTS(new_name->len);
+ dentry_hash = f2fs_dentry_hash(new_name, NULL);
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
@@ -566,10 +551,8 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
}
start:
- if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
- err = -ENOSPC;
- goto out;
- }
+ if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
+ return -ENOSPC;
/* Increase the depth, if required */
if (level == current_depth)
@@ -583,10 +566,8 @@ start:
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = get_new_data_page(dir, NULL, block, true);
- if (IS_ERR(dentry_page)) {
- err = PTR_ERR(dentry_page);
- goto out;
- }
+ if (IS_ERR(dentry_page))
+ return PTR_ERR(dentry_page);
dentry_blk = kmap(dentry_page);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
@@ -606,7 +587,7 @@ add_dentry:
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, &new_name, NULL);
+ page = init_inode_metadata(inode, dir, new_name, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -616,7 +597,7 @@ add_dentry:
}
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
- f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
+ f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
set_page_dirty(dentry_page);
@@ -638,7 +619,34 @@ fail:
}
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
-out:
+
+ return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+ struct inode *inode, nid_t ino, umode_t mode)
+{
+ struct f2fs_filename fname;
+ struct qstr new_name;
+ int err;
+
+ err = f2fs_fname_setup_filename(dir, name, 0, &fname);
+ if (err)
+ return err;
+
+ new_name.name = fname_name(&fname);
+ new_name.len = fname_len(&fname);
+
+ err = -EAGAIN;
+ if (f2fs_has_inline_dentry(dir))
+ err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
+ if (err == -EAGAIN)
+ err = f2fs_add_regular_entry(dir, &new_name, inode, ino, mode);
+
f2fs_fname_free_filename(&fname);
return err;
}
@@ -792,10 +800,7 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
break;
de = &d->dentry[bit_pos];
- if (de->file_type < F2FS_FT_MAX)
- d_type = f2fs_filetype_table[de->file_type];
- else
- d_type = DT_UNKNOWN;
+ d_type = get_de_type(de);
de_name.name = d->filename[bit_pos];
de_name.len = le16_to_cpu(de->name_len);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2871576fbca4..2bfce887dce2 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -135,7 +135,7 @@ struct cp_control {
};
/*
- * For CP/NAT/SIT/SSA readahead
+ * indicate meta/data type
*/
enum {
META_CP,
@@ -143,6 +143,8 @@ enum {
META_SIT,
META_SSA,
META_POR,
+ DATA_GENERIC,
+ META_GENERIC,
};
/* for the list of ino */
@@ -684,6 +686,7 @@ struct f2fs_io_info {
block_t blk_addr; /* block address to be written */
struct page *page; /* page to be written */
struct page *encrypted_page; /* encrypted page */
+ bool is_meta; /* indicate borrow meta inode mapping or not */
};
#define is_read_io(rw) (((rw) & 1) == READ)
@@ -731,6 +734,7 @@ struct f2fs_sb_info {
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
+ int cur_cp_pack; /* remain current cp pack */
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
struct rw_semaphore cp_rwsem; /* blocking FS operations */
@@ -1140,22 +1144,27 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
- block_t start_addr;
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- unsigned long long ckpt_version = cur_cp_version(ckpt);
-
- start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+ block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
- /*
- * odd numbered checkpoint should at cp segment 0
- * and even segment must be at cp segment 1
- */
- if (!(ckpt_version & 1))
+ if (sbi->cur_cp_pack == 2)
start_addr += sbi->blocks_per_seg;
+ return start_addr;
+}
+
+static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
+{
+ block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+ if (sbi->cur_cp_pack == 1)
+ start_addr += sbi->blocks_per_seg;
return start_addr;
}
+static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
+{
+ sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
+}
+
static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
{
return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
@@ -1402,7 +1411,6 @@ enum {
FI_NO_ALLOC, /* should not allocate any blocks */
FI_FREE_NID, /* free allocated nide */
FI_UPDATE_DIR, /* should update inode block for consistency */
- FI_DELAY_IPUT, /* used for the recovery */
FI_NO_EXTENT, /* not to use the extent cache */
FI_INLINE_XATTR, /* used for inline xattr */
FI_INLINE_DATA, /* used for inline data*/
@@ -1641,6 +1649,39 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \
ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META && \
+ (!is_read_io(fio->rw) || fio->is_meta))
+
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
+{
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "invalid blkaddr: %u, type: %d, run fsck to fix.",
+ blkaddr, type);
+ f2fs_bug_on(sbi, 1);
+ }
+}
+
+static inline bool __is_valid_data_blkaddr(block_t blkaddr)
+{
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ return false;
+ return true;
+}
+
+static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr)
+{
+ if (!__is_valid_data_blkaddr(blkaddr))
+ return false;
+ verify_blkaddr(sbi, blkaddr, DATA_GENERIC);
+ return true;
+}
+
/*
* file.c
*/
@@ -1677,7 +1718,7 @@ struct dentry *f2fs_get_parent(struct dentry *child);
*/
extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
void set_de_type(struct f2fs_dir_entry *, umode_t);
-
+unsigned char get_de_type(struct f2fs_dir_entry *);
struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *,
f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
@@ -1698,6 +1739,8 @@ void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
const struct qstr *, f2fs_hash_t , unsigned int);
+int f2fs_add_regular_entry(struct inode *, const struct qstr *,
+ struct inode *, nid_t, umode_t);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
umode_t);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
@@ -1718,6 +1761,7 @@ int f2fs_commit_super(struct f2fs_sb_info *, bool);
int f2fs_sync_fs(struct super_block *, int);
extern __printf(3, 4)
void f2fs_msg(struct super_block *, const char *, const char *, ...);
+int sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
* hash.c
@@ -1778,7 +1822,6 @@ bool is_checkpointed_data(struct f2fs_sb_info *, block_t);
void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *);
void release_discard_addrs(struct f2fs_sb_info *);
-bool discard_next_dnode(struct f2fs_sb_info *, block_t);
int npages_for_summary_flush(struct f2fs_sb_info *, bool);
void allocate_new_segments(struct f2fs_sb_info *);
int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
@@ -1810,7 +1853,8 @@ void destroy_segment_manager_caches(void);
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
-bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type);
int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
@@ -1825,7 +1869,6 @@ void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
int recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
void update_dirty_page(struct inode *, struct page *);
-void add_dirty_dir_inode(struct inode *);
void remove_dirty_dir_inode(struct inode *);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
@@ -1864,7 +1907,7 @@ void build_gc_manager(struct f2fs_sb_info *);
/*
* recovery.c
*/
-int recover_fsync_data(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *, bool);
bool space_for_roll_forward(struct f2fs_sb_info *);
/*
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 01eed94b01ea..bee3bc7a16ac 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -200,6 +200,9 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
trace_f2fs_sync_file_enter(inode);
+ if (S_ISDIR(inode->i_mode))
+ goto go_write;
+
/* if fdatasync is triggered, let's do in-place-update */
if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
set_inode_flag(fi, FI_NEED_IPU);
@@ -305,13 +308,13 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping,
return pgofs;
}
-static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
- int whence)
+static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr,
+ pgoff_t dirty, pgoff_t pgofs, int whence)
{
switch (whence) {
case SEEK_DATA:
if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
- (blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
+ is_valid_data_blkaddr(sbi, blkaddr))
return true;
break;
case SEEK_HOLE:
@@ -374,7 +377,15 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
- if (__found_offset(blkaddr, dirty, pgofs, whence)) {
+ if (__is_valid_data_blkaddr(blkaddr) &&
+ !f2fs_is_valid_blkaddr(F2FS_I_SB(inode),
+ blkaddr, DATA_GENERIC)) {
+ f2fs_put_dnode(&dn);
+ goto fail;
+ }
+
+ if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty,
+ pgofs, whence)) {
f2fs_put_dnode(&dn);
goto found;
}
@@ -466,6 +477,11 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
dn->data_blkaddr = NULL_ADDR;
set_data_blkaddr(dn);
+
+ if (__is_valid_data_blkaddr(blkaddr) &&
+ !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC))
+ continue;
+
invalidate_blocks(sbi, blkaddr);
if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
clear_inode_flag(F2FS_I(dn->inode),
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index ad80f916b64d..00685a8b1418 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -127,6 +127,16 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
if (err)
return err;
+ 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_wait_on_page_writeback(page, DATA);
if (PageUptodate(page))
@@ -367,7 +377,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
* NOTE: ipage is grabbed by caller, but if any error occurs, we should
* release ipage in this function.
*/
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
@@ -386,6 +396,17 @@ static int f2fs_convert_inline_dir(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);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
@@ -428,6 +449,98 @@ out:
return err;
}
+static int f2fs_add_inline_entries(struct inode *dir,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_dentry_ptr d;
+ unsigned long bit_pos = 0;
+ int err = 0;
+
+ make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+
+ while (bit_pos < d.max) {
+ struct f2fs_dir_entry *de;
+ struct qstr new_name;
+ nid_t ino;
+ umode_t fake_mode;
+
+ if (!test_bit_le(bit_pos, d.bitmap)) {
+ bit_pos++;
+ continue;
+ }
+
+ de = &d.dentry[bit_pos];
+ new_name.name = d.filename[bit_pos];
+ new_name.len = de->name_len;
+
+ ino = le32_to_cpu(de->ino);
+ fake_mode = get_de_type(de) << S_SHIFT;
+
+ err = f2fs_add_regular_entry(dir, &new_name, NULL,
+ ino, fake_mode);
+ if (err)
+ goto punch_dentry_pages;
+
+ if (unlikely(!de->name_len))
+ d.max = -1;
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ }
+ return 0;
+punch_dentry_pages:
+ truncate_inode_pages(&dir->i_data, 0);
+ truncate_blocks(dir, 0, false);
+ remove_dirty_dir_inode(dir);
+ return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_inline_dentry *backup_dentry;
+ int err;
+
+ backup_dentry = kmalloc(sizeof(struct f2fs_inline_dentry),
+ GFP_F2FS_ZERO);
+ if (!backup_dentry)
+ return -ENOMEM;
+
+ memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+ truncate_inline_inode(ipage, 0);
+
+ unlock_page(ipage);
+
+ err = f2fs_add_inline_entries(dir, backup_dentry);
+ if (err)
+ goto recover;
+
+ lock_page(ipage);
+
+ stat_dec_inline_dir(dir);
+ clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
+ update_inode(dir, ipage);
+ kfree(backup_dentry);
+ return 0;
+recover:
+ lock_page(ipage);
+ memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ i_size_write(dir, MAX_INLINE_DATA);
+ update_inode(dir, ipage);
+ f2fs_put_page(ipage, 1);
+
+ kfree(backup_dentry);
+ return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ if (!F2FS_I(dir)->i_dir_level)
+ return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+ else
+ return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 5528801a5baf..89bf8dd7758c 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -50,13 +50,16 @@ 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[0]);
- if (addr != NEW_ADDR && addr != NULL_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)
@@ -94,12 +97,57 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
return;
}
+static bool sanity_check_inode(struct inode *inode, struct page *node_page)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(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_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;
+ }
+ }
+ return true;
+}
+
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
+ int err;
/* Check if ino is within scope */
if (check_nid_range(sbi, inode->i_ino)) {
@@ -142,6 +190,11 @@ static int do_read_inode(struct inode *inode)
get_inline_info(fi, ri);
+ 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);
@@ -149,7 +202,12 @@ static int do_read_inode(struct inode *inode)
/* get rdev by using inline_info */
__get_inode_rdev(inode, ri);
- if (__written_first_block(ri))
+ err = __written_first_block(sbi, ri);
+ if (err < 0) {
+ f2fs_put_page(node_page, 1);
+ return err;
+ }
+ if (!err)
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
f2fs_put_page(node_page, 1);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 7bcbc6e9c40d..582373849332 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -261,13 +261,11 @@ static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
{
struct nat_entry *e;
- down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (!e) {
e = grab_nat_entry(nm_i, nid);
node_info_from_raw_nat(&e->ni, ne);
}
- up_write(&nm_i->nat_tree_lock);
}
static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -298,8 +296,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
new_blkaddr == NULL_ADDR);
f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR &&
new_blkaddr == NEW_ADDR);
- f2fs_bug_on(sbi, nat_get_blkaddr(e) != NEW_ADDR &&
- nat_get_blkaddr(e) != NULL_ADDR &&
+ f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) &&
new_blkaddr == NEW_ADDR);
/* increment version no as node is removed */
@@ -314,7 +311,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
/* change address */
nat_set_blkaddr(e, new_blkaddr);
- if (new_blkaddr == NEW_ADDR || new_blkaddr == NULL_ADDR)
+ if (!is_valid_data_blkaddr(sbi, new_blkaddr))
set_nat_flag(e, IS_CHECKPOINTED, false);
__set_nat_cache_dirty(nm_i, e);
@@ -379,6 +376,8 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
memset(&ne, 0, sizeof(struct f2fs_nat_entry));
+ down_write(&nm_i->nat_tree_lock);
+
/* Check current segment summary */
mutex_lock(&curseg->curseg_mutex);
i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
@@ -399,6 +398,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
cache:
/* cache nat entry */
cache_nat_entry(NM_I(sbi), nid, &ne);
+ up_write(&nm_i->nat_tree_lock);
}
/*
@@ -590,6 +590,7 @@ static void truncate_node(struct dnode_of_data *dn)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info ni;
+ pgoff_t index;
get_node_info(sbi, dn->nid, &ni);
if (dn->inode->i_blocks == 0) {
@@ -613,10 +614,11 @@ invalidate:
clear_node_page_dirty(dn->node_page);
set_sbi_flag(sbi, SBI_IS_DIRTY);
+ index = dn->node_page->index;
f2fs_put_page(dn->node_page, 1);
invalidate_mapping_pages(NODE_MAPPING(sbi),
- dn->node_page->index, dn->node_page->index);
+ index, index);
dn->node_page = NULL;
trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
@@ -1341,6 +1343,12 @@ static int f2fs_write_node_page(struct page *page,
return 0;
}
+ if (__is_valid_data_blkaddr(ni.blk_addr) &&
+ !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) {
+ up_read(&sbi->node_write);
+ goto redirty_out;
+ }
+
set_page_writeback(page);
fio.blk_addr = ni.blk_addr;
write_node_page(nid, &fio);
@@ -1427,9 +1435,9 @@ static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct free_nid *i;
+ struct free_nid *i, *e;
struct nat_entry *ne;
- bool allocated = false;
+ int err = -EINVAL;
if (!available_free_memory(sbi, FREE_NIDS))
return -1;
@@ -1438,40 +1446,58 @@ static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
if (unlikely(nid == 0))
return 0;
- if (build) {
- /* do not add allocated nids */
- down_read(&nm_i->nat_tree_lock);
- ne = __lookup_nat_cache(nm_i, nid);
- if (ne &&
- (!get_nat_flag(ne, IS_CHECKPOINTED) ||
- nat_get_blkaddr(ne) != NULL_ADDR))
- allocated = true;
- up_read(&nm_i->nat_tree_lock);
- if (allocated)
- return 0;
- }
-
i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
i->nid = nid;
i->state = NID_NEW;
- if (radix_tree_preload(GFP_NOFS)) {
- kmem_cache_free(free_nid_slab, i);
- return 0;
- }
+ if (radix_tree_preload(GFP_NOFS))
+ goto err;
spin_lock(&nm_i->free_nid_list_lock);
- if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
- spin_unlock(&nm_i->free_nid_list_lock);
- radix_tree_preload_end();
- kmem_cache_free(free_nid_slab, i);
- return 0;
+
+ if (build) {
+ /*
+ * Thread A Thread B
+ * - f2fs_create
+ * - f2fs_new_inode
+ * - alloc_nid
+ * - __insert_nid_to_list(ALLOC_NID_LIST)
+ * - f2fs_balance_fs_bg
+ * - build_free_nids
+ * - __build_free_nids
+ * - scan_nat_page
+ * - add_free_nid
+ * - __lookup_nat_cache
+ * - f2fs_add_link
+ * - init_inode_metadata
+ * - new_inode_page
+ * - new_node_page
+ * - set_node_addr
+ * - alloc_nid_done
+ * - __remove_nid_from_list(ALLOC_NID_LIST)
+ * - __insert_nid_to_list(FREE_NID_LIST)
+ */
+ ne = __lookup_nat_cache(nm_i, nid);
+ if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
+ nat_get_blkaddr(ne) != NULL_ADDR))
+ goto err_out;
+
+ e = __lookup_free_nid_list(nm_i, nid);
+ if (e)
+ goto err_out;
}
+ if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i))
+ goto err_out;
+ err = 0;
list_add_tail(&i->list, &nm_i->free_nid_list);
nm_i->fcnt++;
+err_out:
spin_unlock(&nm_i->free_nid_list_lock);
radix_tree_preload_end();
- return 1;
+err:
+ if (err)
+ kmem_cache_free(free_nid_slab, i);
+ return !err;
}
static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
@@ -1532,6 +1558,8 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
+ down_read(&nm_i->nat_tree_lock);
+
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
@@ -1560,6 +1588,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
remove_free_nid(nm_i, nid);
}
mutex_unlock(&curseg->curseg_mutex);
+ up_read(&nm_i->nat_tree_lock);
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
@@ -1842,14 +1871,12 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
raw_ne = nat_in_journal(sum, i);
- down_write(&nm_i->nat_tree_lock);
ne = __lookup_nat_cache(nm_i, nid);
if (!ne) {
ne = grab_nat_entry(nm_i, nid);
node_info_from_raw_nat(&ne->ni, &raw_ne);
}
__set_nat_cache_dirty(nm_i, ne);
- up_write(&nm_i->nat_tree_lock);
}
update_nats_in_cursum(sum, -i);
mutex_unlock(&curseg->curseg_mutex);
@@ -1883,7 +1910,6 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
struct f2fs_nat_block *nat_blk;
struct nat_entry *ne, *cur;
struct page *page = NULL;
- struct f2fs_nm_info *nm_i = NM_I(sbi);
/*
* there are two steps to flush nat entries:
@@ -1920,12 +1946,8 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
raw_ne = &nat_blk->entries[nid - start_nid];
}
raw_nat_from_node_info(raw_ne, &ne->ni);
-
- down_write(&NM_I(sbi)->nat_tree_lock);
nat_reset_flag(ne);
__clear_nat_cache_dirty(NM_I(sbi), ne);
- up_write(&NM_I(sbi)->nat_tree_lock);
-
if (nat_get_blkaddr(ne) == NULL_ADDR)
add_free_nid(sbi, nid, false);
}
@@ -1937,9 +1959,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
f2fs_bug_on(sbi, set->entry_cnt);
- down_write(&nm_i->nat_tree_lock);
radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
- up_write(&nm_i->nat_tree_lock);
kmem_cache_free(nat_entry_set_slab, set);
}
@@ -1959,6 +1979,9 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
if (!nm_i->dirty_nat_cnt)
return;
+
+ down_write(&nm_i->nat_tree_lock);
+
/*
* if there are no enough space in journal to store dirty nat
* entries, remove all entries from journal and merge them
@@ -1967,7 +1990,6 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
remove_nats_in_journal(sbi);
- down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_set(nm_i,
set_idx, SETVEC_SIZE, setvec))) {
unsigned idx;
@@ -1976,12 +1998,13 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
__adjust_nat_entry_set(setvec[idx], &sets,
MAX_NAT_JENTRIES(sum));
}
- up_write(&nm_i->nat_tree_lock);
/* flush dirty nats in nat entry set */
list_for_each_entry_safe(set, tmp, &sets, set_list)
__flush_nat_entry_set(sbi, set);
+ up_write(&nm_i->nat_tree_lock);
+
f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index e4fffd2d98c4..0d6f0e3dc655 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -212,6 +212,37 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
f2fs_change_bit(block_off, nm_i->nat_bitmap);
}
+static inline nid_t ino_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le32_to_cpu(rn->footer.ino);
+}
+
+static inline nid_t nid_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le32_to_cpu(rn->footer.nid);
+}
+
+static inline unsigned int ofs_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ unsigned flag = le32_to_cpu(rn->footer.flag);
+ return flag >> OFFSET_BIT_SHIFT;
+}
+
+static inline __u64 cpver_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le64_to_cpu(rn->footer.cp_ver);
+}
+
+static inline block_t next_blkaddr_of_node(struct page *node_page)
+{
+ struct f2fs_node *rn = F2FS_NODE(node_page);
+ return le32_to_cpu(rn->footer.next_blkaddr);
+}
+
static inline void fill_node_footer(struct page *page, nid_t nid,
nid_t ino, unsigned int ofs, bool reset)
{
@@ -242,40 +273,30 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
struct f2fs_node *rn = F2FS_NODE(page);
+ size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+ __u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
- rn->footer.cp_ver = ckpt->checkpoint_ver;
+ if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+ __u64 crc = le32_to_cpu(*((__le32 *)
+ ((unsigned char *)ckpt + crc_offset)));
+ cp_ver |= (crc << 32);
+ }
+ rn->footer.cp_ver = cpu_to_le64(cp_ver);
rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
}
-static inline nid_t ino_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le32_to_cpu(rn->footer.ino);
-}
-
-static inline nid_t nid_of_node(struct page *node_page)
+static inline bool is_recoverable_dnode(struct page *page)
{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le32_to_cpu(rn->footer.nid);
-}
-
-static inline unsigned int ofs_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- unsigned flag = le32_to_cpu(rn->footer.flag);
- return flag >> OFFSET_BIT_SHIFT;
-}
-
-static inline unsigned long long cpver_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le64_to_cpu(rn->footer.cp_ver);
-}
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
+ size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+ __u64 cp_ver = cur_cp_version(ckpt);
-static inline block_t next_blkaddr_of_node(struct page *node_page)
-{
- struct f2fs_node *rn = F2FS_NODE(node_page);
- return le32_to_cpu(rn->footer.next_blkaddr);
+ if (is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+ __u64 crc = le32_to_cpu(*((__le32 *)
+ ((unsigned char *)ckpt + crc_offset)));
+ cp_ver |= (crc << 32);
+ }
+ return cpu_to_le64(cp_ver) == cpver_of_node(page);
}
/*
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index e32f349f341b..2878be3e448f 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -67,7 +67,30 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
return NULL;
}
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct list_head *head,
+ struct inode *inode)
+{
+ struct fsync_inode_entry *entry;
+
+ entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+ if (!entry)
+ return NULL;
+
+ entry->inode = inode;
+ list_add_tail(&entry->list, head);
+
+ return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+ iput(entry->inode);
+ list_del(&entry->list);
+ kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+ struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
@@ -75,18 +98,29 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
struct qstr name;
struct page *page;
struct inode *dir, *einode;
+ struct fsync_inode_entry *entry;
int err = 0;
- dir = f2fs_iget(inode->i_sb, pino);
- if (IS_ERR(dir)) {
- err = PTR_ERR(dir);
- goto out;
+ entry = get_fsync_inode(dir_list, pino);
+ if (!entry) {
+ dir = f2fs_iget(inode->i_sb, pino);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto out;
+ }
+
+ entry = add_fsync_inode(dir_list, dir);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(dir);
+ goto out;
+ }
}
- if (file_enc_name(inode)) {
- iput(dir);
+ dir = entry->inode;
+
+ if (file_enc_name(inode))
return 0;
- }
name.len = le32_to_cpu(raw_inode->i_namelen);
name.name = raw_inode->i_name;
@@ -94,7 +128,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
if (unlikely(name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
- goto out_err;
+ goto out;
}
retry:
de = f2fs_find_entry(dir, &name, &page);
@@ -120,23 +154,12 @@ retry:
goto retry;
}
err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
- if (err)
- goto out_err;
-
- if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
- iput(dir);
- } else {
- add_dirty_dir_inode(dir);
- set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
- }
goto out;
out_unmap_put:
f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
-out_err:
- iput(dir);
out:
f2fs_msg(inode->i_sb, KERN_NOTICE,
"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -170,8 +193,8 @@ static void recover_inode(struct inode *inode, struct page *page)
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
- unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
+ struct inode *inode;
struct page *page = NULL;
block_t blkaddr;
int err = 0;
@@ -185,12 +208,12 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
while (1) {
struct fsync_inode_entry *entry;
- if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
page = get_tmp_page(sbi, blkaddr);
- if (cp_ver != cpver_of_node(page))
+ if (!is_recoverable_dnode(page))
break;
if (!is_fsync_dnode(page))
@@ -204,27 +227,27 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
break;
}
- /* add this fsync inode to the list */
- entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
- if (!entry) {
- err = -ENOMEM;
- break;
- }
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
- entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
- if (IS_ERR(entry->inode)) {
- err = PTR_ERR(entry->inode);
- kmem_cache_free(fsync_entry_slab, entry);
+ inode = f2fs_iget(sbi->sb, ino_of_node(page));
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
if (err == -ENOENT) {
err = 0;
goto next;
}
break;
}
- list_add_tail(&entry->list, head);
+
+ /* add this fsync inode to the list */
+ entry = add_fsync_inode(head, inode);
+ if (!entry) {
+ err = -ENOMEM;
+ iput(inode);
+ break;
+ }
}
entry->blkaddr = blkaddr;
@@ -248,11 +271,8 @@ static void destroy_fsync_dnodes(struct list_head *head)
{
struct fsync_inode_entry *entry, *tmp;
- list_for_each_entry_safe(entry, tmp, head, list) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ list_for_each_entry_safe(entry, tmp, head, list)
+ del_fsync_inode(entry);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -423,7 +443,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
}
/* dest is valid block, try to recover from src to dest */
- if (is_valid_blkaddr(sbi, dest, META_POR)) {
+ if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
err = reserve_new_block(&dn);
@@ -459,35 +479,34 @@ out:
return err;
}
-static int recover_data(struct f2fs_sb_info *sbi,
- struct list_head *head, int type)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+ struct list_head *dir_list)
{
- unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page = NULL;
int err = 0;
block_t blkaddr;
/* get node pages in the current segment */
- curseg = CURSEG_I(sbi, type);
+ curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
- if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
ra_meta_pages_cond(sbi, blkaddr);
page = get_tmp_page(sbi, blkaddr);
- if (cp_ver != cpver_of_node(page)) {
+ if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
- entry = get_fsync_inode(head, ino_of_node(page));
+ entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
@@ -498,7 +517,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
if (entry->last_inode == blkaddr)
recover_inode(entry->inode, page);
if (entry->last_dentry == blkaddr) {
- err = recover_dentry(entry->inode, page);
+ err = recover_dentry(entry->inode, page, dir_list);
if (err) {
f2fs_put_page(page, 1);
break;
@@ -510,11 +529,8 @@ static int recover_data(struct f2fs_sb_info *sbi,
break;
}
- if (entry->blkaddr == blkaddr) {
- iput(entry->inode);
- list_del(&entry->list);
- kmem_cache_free(fsync_entry_slab, entry);
- }
+ if (entry->blkaddr == blkaddr)
+ del_fsync_inode(entry);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
@@ -525,12 +541,14 @@ next:
return err;
}
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct list_head inode_list;
+ struct list_head dir_list;
block_t blkaddr;
int err;
+ int ret = 0;
bool need_writecp = false;
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -539,6 +557,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
return -ENOMEM;
INIT_LIST_HEAD(&inode_list);
+ INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
@@ -547,21 +566,22 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list);
- if (err)
+ if (err || list_empty(&inode_list))
goto out;
- if (list_empty(&inode_list))
+ if (check_only) {
+ ret = 1;
goto out;
+ }
need_writecp = true;
/* step #2: recover data */
- err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+ err = recover_data(sbi, &inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
out:
destroy_fsync_dnodes(&inode_list);
- kmem_cache_destroy(fsync_entry_slab);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
@@ -573,31 +593,20 @@ out:
}
clear_sbi_flag(sbi, SBI_POR_DOING);
- if (err) {
- bool invalidate = false;
-
- if (discard_next_dnode(sbi, blkaddr))
- invalidate = true;
-
- /* Flush all the NAT/SIT pages */
- while (get_pages(sbi, F2FS_DIRTY_META))
- sync_meta_pages(sbi, META, LONG_MAX);
+ if (err)
+ set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
+ mutex_unlock(&sbi->cp_mutex);
- /* invalidate temporary meta page */
- if (invalidate)
- invalidate_mapping_pages(META_MAPPING(sbi),
- blkaddr, blkaddr);
+ /* let's drop all the directory inodes for clean checkpoint */
+ destroy_fsync_dnodes(&dir_list);
- set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
- mutex_unlock(&sbi->cp_mutex);
- } else if (need_writecp) {
+ if (!err && need_writecp) {
struct cp_control cpc = {
.reason = CP_RECOVERY,
};
- mutex_unlock(&sbi->cp_mutex);
write_checkpoint(sbi, &cpc);
- } else {
- mutex_unlock(&sbi->cp_mutex);
}
- return err;
+
+ kmem_cache_destroy(fsync_entry_slab);
+ return ret ? ret: err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 2bba0c4ef4b7..6802cd754eda 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -398,6 +398,9 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
init_waitqueue_head(&fcc->flush_wait_queue);
init_llist_head(&fcc->issue_list);
SM_I(sbi)->cmd_control_info = fcc;
+ if (!test_opt(sbi, FLUSH_MERGE))
+ return err;
+
fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(fcc->f2fs_issue_flush)) {
@@ -516,28 +519,6 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
}
-bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
-{
- int err = -ENOTSUPP;
-
- if (test_opt(sbi, DISCARD)) {
- struct seg_entry *se = get_seg_entry(sbi,
- GET_SEGNO(sbi, blkaddr));
- unsigned int offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
-
- if (f2fs_test_bit(offset, se->discard_map))
- return false;
-
- err = f2fs_issue_discard(sbi, blkaddr, 1);
- }
-
- if (err) {
- update_meta_page(sbi, NULL, blkaddr);
- return true;
- }
- return false;
-}
-
static void __add_discard_entry(struct f2fs_sb_info *sbi,
struct cp_control *cpc, struct seg_entry *se,
unsigned int start, unsigned int end)
@@ -771,7 +752,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
struct seg_entry *se;
bool is_cp = false;
- if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ if (!is_valid_data_blkaddr(sbi, blkaddr))
return true;
mutex_lock(&sit_i->sentry_lock);
@@ -1485,7 +1466,7 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
{
struct page *cpage;
- if (blkaddr == NEW_ADDR)
+ if (!is_valid_data_blkaddr(sbi, blkaddr))
return;
f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
@@ -2120,7 +2101,7 @@ static int build_curseg(struct f2fs_sb_info *sbi)
return restore_curseg_summaries(sbi);
}
-static void build_sit_entries(struct f2fs_sb_info *sbi)
+static int build_sit_entries(struct f2fs_sb_info *sbi)
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
@@ -2129,6 +2110,7 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
int nrpages = MAX_BIO_BLOCKS(sbi);
+ int err = 0;
do {
readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
@@ -2142,36 +2124,62 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
struct f2fs_sit_entry sit;
struct page *page;
- mutex_lock(&curseg->curseg_mutex);
- for (i = 0; i < sits_in_cursum(sum); i++) {
- if (le32_to_cpu(segno_in_journal(sum, i))
- == start) {
- sit = sit_in_journal(sum, i);
- mutex_unlock(&curseg->curseg_mutex);
- goto got_it;
- }
- }
- mutex_unlock(&curseg->curseg_mutex);
-
page = get_current_sit_page(sbi, start);
sit_blk = (struct f2fs_sit_block *)page_address(page);
sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
f2fs_put_page(page, 1);
-got_it:
- check_block_count(sbi, start, &sit);
+
+ err = check_block_count(sbi, start, &sit);
+ if (err)
+ return err;
seg_info_from_raw_sit(se, &sit);
/* build discard map only one time */
memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks;
- if (sbi->segs_per_sec > 1) {
- struct sec_entry *e = get_sec_entry(sbi, start);
- e->valid_blocks += se->valid_blocks;
- }
+ if (sbi->segs_per_sec > 1)
+ get_sec_entry(sbi, start)->valid_blocks +=
+ se->valid_blocks;
}
start_blk += readed;
} while (start_blk < sit_blk_cnt);
+
+ mutex_lock(&curseg->curseg_mutex);
+ for (i = 0; i < sits_in_cursum(sum); i++) {
+ struct f2fs_sit_entry sit;
+ struct seg_entry *se;
+ unsigned int old_valid_blocks;
+
+ start = le32_to_cpu(segno_in_journal(sum, i));
+ if (start >= MAIN_SEGS(sbi)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong journal entry on segno %u",
+ start);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ err = -EINVAL;
+ break;
+ }
+
+ se = &sit_i->sentries[start];
+ sit = sit_in_journal(sum, i);
+
+ old_valid_blocks = se->valid_blocks;
+
+ err = check_block_count(sbi, start, &sit);
+ if (err)
+ break;
+ seg_info_from_raw_sit(se, &sit);
+
+ memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks += old_valid_blocks - se->valid_blocks;
+
+ if (sbi->segs_per_sec > 1)
+ get_sec_entry(sbi, start)->valid_blocks +=
+ se->valid_blocks - old_valid_blocks;
+ }
+ mutex_unlock(&curseg->curseg_mutex);
+ return err;
}
static void init_free_segmap(struct f2fs_sb_info *sbi)
@@ -2316,7 +2324,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
INIT_LIST_HEAD(&sm_info->sit_entry_set);
- if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+ if (!f2fs_readonly(sbi->sb)) {
err = create_flush_cmd_control(sbi);
if (err)
return err;
@@ -2333,7 +2341,9 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
return err;
/* reinit free segmap based on SIT */
- build_sit_entries(sbi);
+ err = build_sit_entries(sbi);
+ if (err)
+ return err;
init_free_segmap(sbi);
err = build_dirty_segmap(sbi);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index bfa1d31f79aa..08b08ae6ba9d 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -17,6 +17,8 @@
#define DEF_RECLAIM_PREFREE_SEGMENTS 5 /* 5% over total segments */
+#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
+
/* L: Logical segment # in volume, R: Relative segment # in main area */
#define GET_L2R_SEGNO(free_i, segno) (segno - free_i->start_segno)
#define GET_R2L_SEGNO(free_i, segno) (segno + free_i->start_segno)
@@ -46,13 +48,19 @@
(secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
sbi->segs_per_sec)) \
-#define MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr)
-#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr)
+#define MAIN_BLKADDR(sbi) \
+ (SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->main_blkaddr))
+#define SEG0_BLKADDR(sbi) \
+ (SM_I(sbi) ? SM_I(sbi)->seg0_blkaddr : \
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment0_blkaddr))
#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
#define MAIN_SECS(sbi) (sbi->total_sections)
-#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count)
+#define TOTAL_SEGS(sbi) \
+ (SM_I(sbi) ? SM_I(sbi)->segment_count : \
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
@@ -72,7 +80,7 @@
(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))
#define GET_SEGNO(sbi, blk_addr) \
- (((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ? \
+ ((!is_valid_data_blkaddr(sbi, blk_addr)) ? \
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
#define GET_SECNO(sbi, segno) \
@@ -574,16 +582,20 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
}
-static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
+static inline void verify_block_addr(struct f2fs_io_info *fio, block_t blk_addr)
{
- f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi)
- || blk_addr >= MAX_BLKADDR(sbi));
+ struct f2fs_sb_info *sbi = fio->sbi;
+
+ if (__is_meta_io(fio))
+ verify_blkaddr(sbi, blk_addr, META_GENERIC);
+ else
+ verify_blkaddr(sbi, blk_addr, DATA_GENERIC);
}
/*
* Summary block is always treated as an invalid block
*/
-static inline void check_block_count(struct f2fs_sb_info *sbi,
+static inline int check_block_count(struct f2fs_sb_info *sbi,
int segno, struct f2fs_sit_entry *raw_sit)
{
#ifdef CONFIG_F2FS_CHECK_FS
@@ -605,11 +617,25 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
cur_pos = next_pos;
is_valid = !is_valid;
} while (cur_pos < sbi->blocks_per_seg);
- BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
+
+ if (unlikely(GET_SIT_VBLOCKS(raw_sit) != valid_blocks)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Mismatch valid blocks %d vs. %d",
+ GET_SIT_VBLOCKS(raw_sit), valid_blocks);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ return -EINVAL;
+ }
#endif
/* check segment usage, and check boundary of a given segment number */
- f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
- || segno > TOTAL_SEGS(sbi) - 1);
+ if (unlikely(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+ || segno > TOTAL_SEGS(sbi) - 1)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong valid blocks %d or segno %u",
+ GET_SIT_VBLOCKS(raw_sit), segno);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ return -EINVAL;
+ }
+ return 0;
}
static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 2ffc53d0c9c7..dbd7adff8b5a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -994,6 +994,8 @@ static inline bool sanity_check_area_boundary(struct super_block *sb,
static int sanity_check_raw_super(struct super_block *sb,
struct f2fs_super_block *raw_super)
{
+ block_t segment_count, segs_per_sec, secs_per_zone;
+ block_t total_sections, blocks_per_seg;
unsigned int blocksize;
if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -1047,6 +1049,68 @@ static int sanity_check_raw_super(struct super_block *sb,
return 1;
}
+ segment_count = le32_to_cpu(raw_super->segment_count);
+ segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
+ secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
+ total_sections = le32_to_cpu(raw_super->section_count);
+
+ /* blocks_per_seg should be 512, given the above check */
+ blocks_per_seg = 1 << le32_to_cpu(raw_super->log_blocks_per_seg);
+
+ if (segment_count > F2FS_MAX_SEGMENT ||
+ segment_count < F2FS_MIN_SEGMENTS) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid segment count (%u)",
+ segment_count);
+ return 1;
+ }
+
+ if (total_sections > segment_count ||
+ total_sections < F2FS_MIN_SEGMENTS ||
+ segs_per_sec > segment_count || !segs_per_sec) {
+ f2fs_msg(sb, KERN_INFO,
+ "Invalid segment/section count (%u, %u x %u)",
+ segment_count, total_sections, segs_per_sec);
+ return 1;
+ }
+
+ if ((segment_count / segs_per_sec) < total_sections) {
+ f2fs_msg(sb, KERN_INFO,
+ "Small segment_count (%u < %u * %u)",
+ segment_count, segs_per_sec, total_sections);
+ return 1;
+ }
+
+ if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong segment_count / block_count (%u > %llu)",
+ segment_count, le64_to_cpu(raw_super->block_count));
+ return 1;
+ }
+
+ if (secs_per_zone > total_sections || !secs_per_zone) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong secs_per_zone / total_sections (%u, %u)",
+ secs_per_zone, total_sections);
+ return 1;
+ }
+ if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) {
+ f2fs_msg(sb, KERN_INFO,
+ "Corrupted extension count (%u > %u)",
+ le32_to_cpu(raw_super->extension_count),
+ F2FS_MAX_EXTENSION);
+ return 1;
+ }
+
+ if (le32_to_cpu(raw_super->cp_payload) >
+ (blocks_per_seg - F2FS_CP_PACKS)) {
+ f2fs_msg(sb, KERN_INFO,
+ "Insane cp_payload (%u > %u)",
+ le32_to_cpu(raw_super->cp_payload),
+ blocks_per_seg - F2FS_CP_PACKS);
+ return 1;
+ }
+
/* check reserved ino info */
if (le32_to_cpu(raw_super->node_ino) != 1 ||
le32_to_cpu(raw_super->meta_ino) != 2 ||
@@ -1059,13 +1123,6 @@ static int sanity_check_raw_super(struct super_block *sb,
return 1;
}
- if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
- f2fs_msg(sb, KERN_INFO,
- "Invalid segment count (%u)",
- le32_to_cpu(raw_super->segment_count));
- return 1;
- }
-
/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
if (sanity_check_area_boundary(sb, raw_super))
return 1;
@@ -1073,15 +1130,19 @@ static int sanity_check_raw_super(struct super_block *sb,
return 0;
}
-static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(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);
@@ -1096,6 +1157,26 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
if (unlikely(fsmeta >= total))
return 1;
+ ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+ reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+
+ if (unlikely(fsmeta < F2FS_MIN_SEGMENTS ||
+ ovp_segments == 0 || reserved_segments == 0)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong layout: check mkfs.f2fs version");
+ 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;
@@ -1112,7 +1193,6 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize);
nat_bitmap_size = le32_to_cpu(ckpt->nat_ver_bitmap_bytesize);
- log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
if (sit_bitmap_size != ((sit_segs / 2) << log_blocks_per_seg) / 8 ||
nat_bitmap_size != ((nat_segs / 2) << log_blocks_per_seg) / 8) {
@@ -1122,6 +1202,17 @@ static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
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;
@@ -1358,13 +1449,6 @@ try_onemore:
goto free_meta_inode;
}
- /* sanity checking of checkpoint */
- err = -EINVAL;
- if (sanity_check_ckpt(sbi)) {
- f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
- goto free_cp;
- }
-
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
sbi->total_valid_inode_count =
@@ -1464,14 +1548,27 @@ try_onemore:
if (need_fsck)
set_sbi_flag(sbi, SBI_NEED_FSCK);
- err = recover_fsync_data(sbi);
- if (err) {
+ if (!retry)
+ goto skip_recovery;
+
+ err = recover_fsync_data(sbi, false);
+ if (err < 0) {
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%ld", err);
goto free_kobj;
}
+ } else {
+ err = recover_fsync_data(sbi, true);
+
+ if (!f2fs_readonly(sb) && err > 0) {
+ err = -EINVAL;
+ f2fs_msg(sb, KERN_ERR,
+ "Need to recover fsync data");
+ goto free_kobj;
+ }
}
+skip_recovery:
/* recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
@@ -1517,7 +1614,6 @@ free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
-free_cp:
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-13 20:03:40 +0000