Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index a0eef95..f7d27cb 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -108,7 +108,7 @@
return __get_meta_page(sbi, index, true);
}
-struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index)
+struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct page *page;
int count = 0;
@@ -243,6 +243,8 @@
blkno * NAT_ENTRY_PER_BLOCK);
break;
case META_SIT:
+ if (unlikely(blkno >= TOTAL_SEGS(sbi)))
+ goto out;
/* get sit block addr */
fio.new_blkaddr = current_sit_addr(sbi,
blkno * SIT_ENTRY_PER_BLOCK);
@@ -581,7 +583,7 @@
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
- f2fs_show_injection_info(FAULT_ORPHAN);
+ f2fs_show_injection_info(sbi, FAULT_ORPHAN);
return -ENOSPC;
}
@@ -892,8 +894,8 @@
int i;
int err;
- sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
- GFP_KERNEL);
+ sbi->ckpt = f2fs_kvzalloc(sbi, array_size(blk_size, cp_blks),
+ GFP_KERNEL);
if (!sbi->ckpt)
return -ENOMEM;
/*
@@ -1044,8 +1046,12 @@
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
retry:
- if (unlikely(f2fs_cp_error(sbi)))
+ if (unlikely(f2fs_cp_error(sbi))) {
+ trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
+ get_pages(sbi, is_dir ?
+ F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
return -EIO;
+ }
spin_lock(&sbi->inode_lock[type]);
@@ -1250,20 +1256,20 @@
f2fs_unlock_all(sbi);
}
-void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
+void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
{
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
- if (!get_pages(sbi, F2FS_WB_CP_DATA))
+ if (!get_pages(sbi, type))
break;
if (unlikely(f2fs_cp_error(sbi)))
break;
- io_schedule_timeout(5*HZ);
+ io_schedule_timeout(HZ/50);
}
finish_wait(&sbi->cp_wait, &wait);
}
@@ -1301,10 +1307,14 @@
else
__clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
- if (is_sbi_flag_set(sbi, SBI_NEED_FSCK) ||
- is_sbi_flag_set(sbi, SBI_IS_RESIZEFS))
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+ if (is_sbi_flag_set(sbi, SBI_IS_RESIZEFS))
+ __set_ckpt_flags(ckpt, CP_RESIZEFS_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_RESIZEFS_FLAG);
+
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
__set_ckpt_flags(ckpt, CP_DISABLED_FLAG);
else
@@ -1384,8 +1394,6 @@
/* Flush all the NAT/SIT pages */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
- f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
- !f2fs_cp_error(sbi));
/*
* modify checkpoint
@@ -1493,11 +1501,11 @@
/* Here, we have one bio having CP pack except cp pack 2 page */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
- f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
- !f2fs_cp_error(sbi));
+ /* Wait for all dirty meta pages to be submitted for IO */
+ f2fs_wait_on_all_pages(sbi, F2FS_DIRTY_META);
/* wait for previous submitted meta pages writeback */
- f2fs_wait_on_all_pages_writeback(sbi);
+ f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
/* flush all device cache */
err = f2fs_flush_device_cache(sbi);
@@ -1506,7 +1514,7 @@
/* barrier and flush checkpoint cp pack 2 page if it can */
commit_checkpoint(sbi, ckpt, start_blk);
- f2fs_wait_on_all_pages_writeback(sbi);
+ f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
/*
* invalidate intermediate page cache borrowed from meta inode
@@ -1588,7 +1596,7 @@
goto out;
}
- if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+ if (NM_I(sbi)->nat_cnt[DIRTY_NAT] == 0 &&
SIT_I(sbi)->dirty_sentries == 0 &&
prefree_segments(sbi) == 0) {
f2fs_flush_sit_entries(sbi, cpc);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5755e89..1679f9c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -167,9 +167,10 @@
static void f2fs_read_end_io(struct bio *bio)
{
- if (time_to_inject(F2FS_P_SB(bio_first_page_all(bio)),
- FAULT_READ_IO)) {
- f2fs_show_injection_info(FAULT_READ_IO);
+ struct f2fs_sb_info *sbi = F2FS_P_SB(bio_first_page_all(bio));
+
+ if (time_to_inject(sbi, FAULT_READ_IO)) {
+ f2fs_show_injection_info(sbi, FAULT_READ_IO);
bio->bi_status = BLK_STS_IOERR;
}
@@ -191,7 +192,7 @@
struct bvec_iter_all iter_all;
if (time_to_inject(sbi, FAULT_WRITE_IO)) {
- f2fs_show_injection_info(FAULT_WRITE_IO);
+ f2fs_show_injection_info(sbi, FAULT_WRITE_IO);
bio->bi_status = BLK_STS_IOERR;
}
@@ -318,7 +319,7 @@
if (test_opt(sbi, LFS) && current->plug)
blk_finish_plug(current->plug);
- if (F2FS_IO_ALIGNED(sbi))
+ if (!F2FS_IO_ALIGNED(sbi))
goto submit_io;
start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
@@ -1074,19 +1075,6 @@
int err = 0;
bool direct_io = iocb->ki_flags & IOCB_DIRECT;
- /* convert inline data for Direct I/O*/
- if (direct_io) {
- err = f2fs_convert_inline_inode(inode);
- if (err)
- return err;
- }
-
- if (direct_io && allow_outplace_dio(inode, iocb, from))
- return 0;
-
- if (is_inode_flag_set(inode, FI_NO_PREALLOC))
- return 0;
-
map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
if (map.m_len > map.m_lblk)
@@ -1203,7 +1191,21 @@
if (err) {
if (flag == F2FS_GET_BLOCK_BMAP)
map->m_pblk = 0;
+
if (err == -ENOENT) {
+ /*
+ * There is one exceptional case that read_node_page()
+ * may return -ENOENT due to filesystem has been
+ * shutdown or cp_error, so force to convert error
+ * number to EIO for such case.
+ */
+ if (map->m_may_create &&
+ (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
+ f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto unlock_out;
+ }
+
err = 0;
if (map->m_next_pgofs)
*map->m_next_pgofs =
@@ -2098,7 +2100,7 @@
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
>> PAGE_SHIFT;
- loff_t psize = (page->index + 1) << PAGE_SHIFT;
+ loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
int err = 0;
@@ -2766,6 +2768,9 @@
unsigned long align = offset | iov_iter_alignment(iter);
struct block_device *bdev = inode->i_sb->s_bdev;
+ if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode))
+ return 1;
+
if (align & blocksize_mask) {
if (bdev)
blkbits = blksize_bits(bdev_logical_block_size(bdev));
@@ -3043,7 +3048,8 @@
#ifdef CONFIG_SWAP
/* Copied from generic_swapfile_activate() to check any holes */
-static int check_swap_activate(struct file *swap_file, unsigned int max)
+static int check_swap_activate(struct swap_info_struct *sis,
+ struct file *swap_file, sector_t *span)
{
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
@@ -3054,6 +3060,8 @@
sector_t last_block;
sector_t lowest_block = -1;
sector_t highest_block = 0;
+ int nr_extents = 0;
+ int ret;
blkbits = inode->i_blkbits;
blocks_per_page = PAGE_SIZE >> blkbits;
@@ -3065,7 +3073,8 @@
probe_block = 0;
page_no = 0;
last_block = i_size_read(inode) >> blkbits;
- while ((probe_block + blocks_per_page) <= last_block && page_no < max) {
+ while ((probe_block + blocks_per_page) <= last_block &&
+ page_no < sis->max) {
unsigned block_in_page;
sector_t first_block;
@@ -3105,13 +3114,27 @@
highest_block = first_block;
}
+ /*
+ * We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
+ */
+ ret = add_swap_extent(sis, page_no, 1, first_block);
+ if (ret < 0)
+ goto out;
+ nr_extents += ret;
page_no++;
probe_block += blocks_per_page;
reprobe:
continue;
}
- return 0;
-
+ ret = nr_extents;
+ *span = 1 + highest_block - lowest_block;
+ if (page_no == 0)
+ page_no = 1; /* force Empty message */
+ sis->max = page_no;
+ sis->pages = page_no - 1;
+ sis->highest_bit = page_no - 1;
+out:
+ return ret;
bad_bmap:
pr_err("swapon: swapfile has holes\n");
return -EINVAL;
@@ -3133,14 +3156,14 @@
if (ret)
return ret;
- ret = check_swap_activate(file, sis->max);
- if (ret)
+ ret = check_swap_activate(sis, file, span);
+ if (ret < 0)
return ret;
set_inode_flag(inode, FI_PIN_FILE);
f2fs_precache_extents(inode);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- return 0;
+ return ret;
}
static void f2fs_swap_deactivate(struct file *file)
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 9b0bedd..d8d6444 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -107,8 +107,8 @@
si->node_pages = NODE_MAPPING(sbi)->nrpages;
if (sbi->meta_inode)
si->meta_pages = META_MAPPING(sbi)->nrpages;
- si->nats = NM_I(sbi)->nat_cnt;
- si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+ si->nats = NM_I(sbi)->nat_cnt[TOTAL_NAT];
+ si->dirty_nats = NM_I(sbi)->nat_cnt[DIRTY_NAT];
si->sits = MAIN_SEGS(sbi);
si->dirty_sits = SIT_I(sbi)->dirty_sentries;
si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID];
@@ -254,9 +254,10 @@
si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] +
NM_I(sbi)->nid_cnt[PREALLOC_NID]) *
sizeof(struct free_nid);
- si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
- si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
- sizeof(struct nat_entry_set);
+ si->cache_mem += NM_I(sbi)->nat_cnt[TOTAL_NAT] *
+ sizeof(struct nat_entry);
+ si->cache_mem += NM_I(sbi)->nat_cnt[DIRTY_NAT] *
+ sizeof(struct nat_entry_set);
si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
for (i = 0; i < MAX_INO_ENTRY; i++)
si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 4033778..99c4a86 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -107,36 +107,28 @@
/*
* Test whether a case-insensitive directory entry matches the filename
* being searched for.
- *
- * Returns: 0 if the directory entry matches, more than 0 if it
- * doesn't match or less than zero on error.
*/
-int f2fs_ci_compare(const struct inode *parent, const struct qstr *name,
- const struct qstr *entry, bool quick)
+static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
+ const struct qstr *entry, bool quick)
{
- const struct f2fs_sb_info *sbi = F2FS_SB(parent->i_sb);
+ const struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
const struct unicode_map *um = sbi->s_encoding;
- int ret;
+ int res;
if (quick)
- ret = utf8_strncasecmp_folded(um, name, entry);
+ res = utf8_strncasecmp_folded(um, name, entry);
else
- ret = utf8_strncasecmp(um, name, entry);
-
- if (ret < 0) {
- /* Handle invalid character sequence as either an error
- * or as an opaque byte sequence.
+ res = utf8_strncasecmp(um, name, entry);
+ if (res < 0) {
+ /*
+ * In strict mode, ignore invalid names. In non-strict mode,
+ * fall back to treating them as opaque byte sequences.
*/
- if (f2fs_has_strict_mode(sbi))
- return -EINVAL;
-
- if (name->len != entry->len)
- return 1;
-
- return !!memcmp(name->name, entry->name, name->len);
+ if (f2fs_has_strict_mode(sbi) || name->len != entry->len)
+ return false;
+ return !memcmp(name->name, entry->name, name->len);
}
-
- return ret;
+ return res == 0;
}
static void f2fs_fname_setup_ci_filename(struct inode *dir,
@@ -188,10 +180,10 @@
if (cf_str->name) {
struct qstr cf = {.name = cf_str->name,
.len = cf_str->len};
- return !f2fs_ci_compare(parent, &cf, &entry, true);
+ return f2fs_match_ci_name(parent, &cf, &entry, true);
}
- return !f2fs_ci_compare(parent, fname->usr_fname, &entry,
- false);
+ return f2fs_match_ci_name(parent, fname->usr_fname, &entry,
+ false);
}
#endif
if (fscrypt_match_name(fname, d->filename[bit_pos],
@@ -311,16 +303,15 @@
unsigned int max_depth;
unsigned int level;
+ *res_page = NULL;
+
if (f2fs_has_inline_dentry(dir)) {
- *res_page = NULL;
de = f2fs_find_in_inline_dir(dir, fname, res_page);
goto out;
}
- if (npages == 0) {
- *res_page = NULL;
+ if (npages == 0)
goto out;
- }
max_depth = F2FS_I(dir)->i_current_depth;
if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
@@ -331,7 +322,6 @@
}
for (level = 0; level < max_depth; level++) {
- *res_page = NULL;
de = find_in_level(dir, level, fname, res_page);
if (de || IS_ERR(*res_page))
break;
@@ -628,7 +618,7 @@
start:
if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
- f2fs_show_injection_info(FAULT_DIR_DEPTH);
+ f2fs_show_injection_info(F2FS_I_SB(dir), FAULT_DIR_DEPTH);
return -ENOSPC;
}
@@ -902,6 +892,7 @@
struct f2fs_sb_info *sbi = F2FS_I_SB(d->inode);
struct blk_plug plug;
bool readdir_ra = sbi->readdir_ra == 1;
+ bool found_valid_dirent = false;
int err = 0;
bit_pos = ((unsigned long)ctx->pos % d->max);
@@ -916,12 +907,15 @@
de = &d->dentry[bit_pos];
if (de->name_len == 0) {
+ if (found_valid_dirent || !bit_pos) {
+ printk_ratelimited(
+ "%sF2FS-fs (%s): invalid namelen(0), ino:%u, run fsck to fix.",
+ KERN_WARNING, sbi->sb->s_id,
+ le32_to_cpu(de->ino));
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ }
bit_pos++;
ctx->pos = start_pos + bit_pos;
- printk_ratelimited(
- "%s, invalid namelen(0), ino:%u, run fsck to fix.",
- KERN_WARNING, le32_to_cpu(de->ino));
- set_sbi_flag(sbi, SBI_NEED_FSCK);
continue;
}
@@ -964,6 +958,7 @@
f2fs_ra_node_page(sbi, le32_to_cpu(de->ino));
ctx->pos = start_pos + bit_pos;
+ found_valid_dirent = true;
}
out:
if (readdir_ra)
@@ -1067,25 +1062,52 @@
static int f2fs_d_compare(const struct dentry *dentry, unsigned int len,
const char *str, const struct qstr *name)
{
- struct qstr qstr = {.name = str, .len = len };
+ const struct dentry *parent = READ_ONCE(dentry->d_parent);
+ const struct inode *dir = READ_ONCE(parent->d_inode);
+ const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct qstr entry = QSTR_INIT(str, len);
+ char strbuf[DNAME_INLINE_LEN];
+ int res;
- if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) {
- if (len != name->len)
- return -1;
- return memcmp(str, name, len);
+ if (!dir || !IS_CASEFOLDED(dir))
+ goto fallback;
+
+ /*
+ * If the dentry name is stored in-line, then it may be concurrently
+ * modified by a rename. If this happens, the VFS will eventually retry
+ * the lookup, so it doesn't matter what ->d_compare() returns.
+ * However, it's unsafe to call utf8_strncasecmp() with an unstable
+ * string. Therefore, we have to copy the name into a temporary buffer.
+ */
+ if (len <= DNAME_INLINE_LEN - 1) {
+ memcpy(strbuf, str, len);
+ strbuf[len] = 0;
+ entry.name = strbuf;
+ /* prevent compiler from optimizing out the temporary buffer */
+ barrier();
}
- return f2fs_ci_compare(dentry->d_parent->d_inode, name, &qstr, false);
+ res = utf8_strncasecmp(sbi->s_encoding, name, &entry);
+ if (res >= 0)
+ return res;
+
+ if (f2fs_has_strict_mode(sbi))
+ return -EINVAL;
+fallback:
+ if (len != name->len)
+ return 1;
+ return !!memcmp(str, name->name, len);
}
static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
{
struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
const struct unicode_map *um = sbi->s_encoding;
+ const struct inode *inode = READ_ONCE(dentry->d_inode);
unsigned char *norm;
int len, ret = 0;
- if (!IS_CASEFOLDED(dentry->d_inode))
+ if (!inode || !IS_CASEFOLDED(inode))
return 0;
norm = f2fs_kmalloc(sbi, PATH_MAX, GFP_ATOMIC);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4024790..031a17b 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -100,6 +100,7 @@
#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000
#define F2FS_MOUNT_RESERVE_ROOT 0x01000000
#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000
+#define F2FS_MOUNT_NORECOVERY 0x04000000
#define F2FS_OPTION(sbi) ((sbi)->mount_opt)
#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -137,6 +138,7 @@
int alloc_mode; /* segment allocation policy */
int fsync_mode; /* fsync policy */
bool test_dummy_encryption; /* test dummy encryption */
+ block_t unusable_cap_perc; /* percentage for cap */
block_t unusable_cap; /* Amount of space allowed to be
* unusable when disabling checkpoint
*/
@@ -795,6 +797,13 @@
MAX_NID_STATE,
};
+enum nat_state {
+ TOTAL_NAT,
+ DIRTY_NAT,
+ RECLAIMABLE_NAT,
+ MAX_NAT_STATE,
+};
+
struct f2fs_nm_info {
block_t nat_blkaddr; /* base disk address of NAT */
nid_t max_nid; /* maximum possible node ids */
@@ -810,8 +819,7 @@
struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
spinlock_t nat_list_lock; /* protect clean nat entry list */
- unsigned int nat_cnt; /* the # of cached nat entries */
- unsigned int dirty_nat_cnt; /* total num of nat entries in set */
+ unsigned int nat_cnt[MAX_NAT_STATE]; /* the # of cached nat entries */
unsigned int nat_blocks; /* # of nat blocks */
/* free node ids management */
@@ -1289,6 +1297,7 @@
unsigned int gc_mode; /* current GC state */
unsigned int next_victim_seg[2]; /* next segment in victim section */
/* for skip statistic */
+ unsigned int atomic_files; /* # of opened atomic file */
unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
unsigned long long skipped_gc_rwsem; /* FG_GC only */
@@ -1365,9 +1374,10 @@
};
#ifdef CONFIG_F2FS_FAULT_INJECTION
-#define f2fs_show_injection_info(type) \
- printk_ratelimited("%sF2FS-fs : inject %s in %s of %pS\n", \
- KERN_INFO, f2fs_fault_name[type], \
+#define f2fs_show_injection_info(sbi, type) \
+ printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n", \
+ KERN_INFO, sbi->sb->s_id, \
+ f2fs_fault_name[type], \
__func__, __builtin_return_address(0))
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
@@ -1387,7 +1397,7 @@
return false;
}
#else
-#define f2fs_show_injection_info(type) do { } while (0)
+#define f2fs_show_injection_info(sbi, type) do { } while (0)
static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
{
return false;
@@ -1772,7 +1782,7 @@
return ret;
if (time_to_inject(sbi, FAULT_BLOCK)) {
- f2fs_show_injection_info(FAULT_BLOCK);
+ f2fs_show_injection_info(sbi, FAULT_BLOCK);
release = *count;
goto release_quota;
}
@@ -2024,7 +2034,7 @@
}
if (time_to_inject(sbi, FAULT_BLOCK)) {
- f2fs_show_injection_info(FAULT_BLOCK);
+ f2fs_show_injection_info(sbi, FAULT_BLOCK);
goto enospc;
}
@@ -2139,7 +2149,8 @@
return page;
if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
- f2fs_show_injection_info(FAULT_PAGE_ALLOC);
+ f2fs_show_injection_info(F2FS_M_SB(mapping),
+ FAULT_PAGE_ALLOC);
return NULL;
}
}
@@ -2154,7 +2165,7 @@
int fgp_flags, gfp_t gfp_mask)
{
if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) {
- f2fs_show_injection_info(FAULT_PAGE_GET);
+ f2fs_show_injection_info(F2FS_M_SB(mapping), FAULT_PAGE_GET);
return NULL;
}
@@ -2223,7 +2234,7 @@
return bio;
}
if (time_to_inject(sbi, FAULT_ALLOC_BIO)) {
- f2fs_show_injection_info(FAULT_ALLOC_BIO);
+ f2fs_show_injection_info(sbi, FAULT_ALLOC_BIO);
return NULL;
}
@@ -2704,6 +2715,20 @@
f2fs_mark_inode_dirty_sync(inode, true);
}
+static inline bool f2fs_is_time_consistent(struct inode *inode)
+{
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
+ return false;
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
+ return false;
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
+ return false;
+ if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
+ &F2FS_I(inode)->i_crtime))
+ return false;
+ return true;
+}
+
static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
{
bool ret;
@@ -2721,14 +2746,7 @@
i_size_read(inode) & ~PAGE_MASK)
return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime))
- return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime))
- return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime))
- return false;
- if (!timespec64_equal(F2FS_I(inode)->i_disk_time + 3,
- &F2FS_I(inode)->i_crtime))
+ if (!f2fs_is_time_consistent(inode))
return false;
down_read(&F2FS_I(inode)->i_sem);
@@ -2780,18 +2798,12 @@
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
size_t size, gfp_t flags)
{
- void *ret;
-
if (time_to_inject(sbi, FAULT_KMALLOC)) {
- f2fs_show_injection_info(FAULT_KMALLOC);
+ f2fs_show_injection_info(sbi, FAULT_KMALLOC);
return NULL;
}
- ret = kmalloc(size, flags);
- if (ret)
- return ret;
-
- return kvmalloc(size, flags);
+ return kmalloc(size, flags);
}
static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
@@ -2804,7 +2816,7 @@
size_t size, gfp_t flags)
{
if (time_to_inject(sbi, FAULT_KVMALLOC)) {
- f2fs_show_injection_info(FAULT_KVMALLOC);
+ f2fs_show_injection_info(sbi, FAULT_KVMALLOC);
return NULL;
}
@@ -2950,11 +2962,6 @@
bool hot, bool set);
struct dentry *f2fs_get_parent(struct dentry *child);
-extern int f2fs_ci_compare(const struct inode *parent,
- const struct qstr *name,
- const struct qstr *entry,
- bool quick);
-
/*
* dir.c
*/
@@ -2999,6 +3006,8 @@
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
+ if (fscrypt_is_nokey_name(dentry))
+ return -ENOKEY;
return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name,
inode, inode->i_ino, inode->i_mode);
}
@@ -3062,7 +3071,7 @@
void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
-void f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
+int f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
@@ -3150,7 +3159,7 @@
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
-struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type);
@@ -3177,7 +3186,7 @@
void f2fs_update_dirty_page(struct inode *inode, struct page *page);
void f2fs_remove_dirty_inode(struct inode *inode);
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
-void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi);
+void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init f2fs_create_checkpoint_caches(void);
@@ -3488,7 +3497,7 @@
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
int f2fs_write_inline_data(struct inode *inode, struct page *page);
-bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
+int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page);
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 29bc0a5..516007b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -50,7 +50,7 @@
struct page *page = vmf->page;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dnode_of_data dn = { .node_changed = false };
+ struct dnode_of_data dn;
int err;
if (unlikely(f2fs_cp_error(sbi))) {
@@ -63,6 +63,9 @@
goto err;
}
+ /* should do out of any locked page */
+ f2fs_balance_fs(sbi, true);
+
sb_start_pagefault(inode->i_sb);
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
@@ -120,8 +123,6 @@
out_sem:
up_read(&F2FS_I(inode)->i_mmap_sem);
- f2fs_balance_fs(sbi, dn.node_changed);
-
sb_end_pagefault(inode->i_sb);
err:
return block_page_mkwrite_return(err);
@@ -681,10 +682,14 @@
trace_f2fs_truncate(inode);
if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
- f2fs_show_injection_info(FAULT_TRUNCATE);
+ f2fs_show_injection_info(F2FS_I_SB(inode), FAULT_TRUNCATE);
return -EIO;
}
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+
/* we should check inline_data size */
if (!f2fs_may_inline_data(inode)) {
err = f2fs_convert_inline_inode(inode);
@@ -751,22 +756,17 @@
inode->i_uid = attr->ia_uid;
if (ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
- if (ia_valid & ATTR_ATIME) {
- inode->i_atime = timestamp_truncate(attr->ia_atime,
- inode);
- }
- if (ia_valid & ATTR_MTIME) {
- inode->i_mtime = timestamp_truncate(attr->ia_mtime,
- inode);
- }
- if (ia_valid & ATTR_CTIME) {
- inode->i_ctime = timestamp_truncate(attr->ia_ctime,
- inode);
- }
+ if (ia_valid & ATTR_ATIME)
+ inode->i_atime = attr->ia_atime;
+ if (ia_valid & ATTR_MTIME)
+ inode->i_mtime = attr->ia_mtime;
+ if (ia_valid & ATTR_CTIME)
+ inode->i_ctime = attr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
- if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
+ if (!in_group_p(inode->i_gid) &&
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID))
mode &= ~S_ISGID;
set_acl_inode(inode, mode);
}
@@ -981,7 +981,6 @@
}
if (pg_start < pg_end) {
- struct address_space *mapping = inode->i_mapping;
loff_t blk_start, blk_end;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -993,8 +992,7 @@
down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
down_write(&F2FS_I(inode)->i_mmap_sem);
- truncate_inode_pages_range(mapping, blk_start,
- blk_end - 1);
+ truncate_pagecache_range(inode, blk_start, blk_end - 1);
f2fs_lock_op(sbi);
ret = f2fs_truncate_hole(inode, pg_start, pg_end);
@@ -1139,7 +1137,7 @@
}
dn.ofs_in_node++;
i++;
- new_size = (dst + i) << PAGE_SHIFT;
+ new_size = (loff_t)(dst + i) << PAGE_SHIFT;
if (dst_inode->i_size < new_size)
f2fs_i_size_write(dst_inode, new_size);
} while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
@@ -1890,6 +1888,7 @@
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (list_empty(&fi->inmem_ilist))
list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]);
+ sbi->atomic_files++;
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
/* add inode in inmem_list first and set atomic_file */
@@ -2060,8 +2059,15 @@
if (in != F2FS_GOING_DOWN_FULLSYNC) {
ret = mnt_want_write_file(filp);
- if (ret)
+ if (ret) {
+ if (ret == -EROFS) {
+ ret = 0;
+ f2fs_stop_checkpoint(sbi, false);
+ set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+ trace_f2fs_shutdown(sbi, in, ret);
+ }
return ret;
+ }
}
switch (in) {
@@ -3353,18 +3359,41 @@
ret = -EAGAIN;
goto out;
}
- } else {
- preallocated = true;
- target_size = iocb->ki_pos + iov_iter_count(from);
-
- err = f2fs_preallocate_blocks(iocb, from);
- if (err) {
- clear_inode_flag(inode, FI_NO_PREALLOC);
- inode_unlock(inode);
- ret = err;
- goto out;
- }
+ goto write;
}
+
+ if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+ goto write;
+
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ /*
+ * Convert inline data for Direct I/O before entering
+ * f2fs_direct_IO().
+ */
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ goto out_err;
+ /*
+ * If force_buffere_io() is true, we have to allocate
+ * blocks all the time, since f2fs_direct_IO will fall
+ * back to buffered IO.
+ */
+ if (!f2fs_force_buffered_io(inode, iocb, from) &&
+ allow_outplace_dio(inode, iocb, from))
+ goto write;
+ }
+ preallocated = true;
+ target_size = iocb->ki_pos + iov_iter_count(from);
+
+ err = f2fs_preallocate_blocks(iocb, from);
+ if (err) {
+out_err:
+ clear_inode_flag(inode, FI_NO_PREALLOC);
+ inode_unlock(inode);
+ ret = err;
+ goto out;
+ }
+write:
ret = __generic_file_write_iter(iocb, from);
clear_inode_flag(inode, FI_NO_PREALLOC);
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 5877bd7..4b6c362 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -54,7 +54,7 @@
}
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
- f2fs_show_injection_info(FAULT_CHECKPOINT);
+ f2fs_show_injection_info(sbi, FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
}
@@ -1012,8 +1012,14 @@
block_t start_bidx;
nid_t nid = le32_to_cpu(entry->nid);
- /* stop BG_GC if there is not enough free sections. */
- if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
+ /*
+ * stop BG_GC if there is not enough free sections.
+ * Or, stop GC if the segment becomes fully valid caused by
+ * race condition along with SSR block allocation.
+ */
+ if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) ||
+ get_valid_blocks(sbi, segno, false) ==
+ sbi->blocks_per_seg)
return submitted;
if (check_valid_map(sbi, segno, off) == 0)
@@ -1089,8 +1095,10 @@
int err;
if (S_ISREG(inode->i_mode)) {
- if (!down_write_trylock(&fi->i_gc_rwsem[READ]))
+ if (!down_write_trylock(&fi->i_gc_rwsem[READ])) {
+ sbi->skipped_gc_rwsem++;
continue;
+ }
if (!down_write_trylock(
&fi->i_gc_rwsem[WRITE])) {
sbi->skipped_gc_rwsem++;
@@ -1532,11 +1540,17 @@
goto out;
}
+ mutex_lock(&sbi->cp_mutex);
update_fs_metadata(sbi, -secs);
clear_sbi_flag(sbi, SBI_IS_RESIZEFS);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ mutex_unlock(&sbi->cp_mutex);
+
err = f2fs_sync_fs(sbi->sb, 1);
if (err) {
+ mutex_lock(&sbi->cp_mutex);
update_fs_metadata(sbi, secs);
+ mutex_unlock(&sbi->cp_mutex);
update_sb_metadata(sbi, secs);
f2fs_commit_super(sbi, false);
}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 896db04..c6bd669 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -189,6 +189,10 @@
if (!f2fs_has_inline_data(inode))
return 0;
+ err = dquot_initialize(inode);
+ if (err)
+ return err;
+
page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
if (!page)
return -ENOMEM;
@@ -212,7 +216,8 @@
f2fs_put_page(page, 1);
- f2fs_balance_fs(sbi, dn.node_changed);
+ if (!err)
+ f2fs_balance_fs(sbi, dn.node_changed);
return err;
}
@@ -252,7 +257,7 @@
return 0;
}
-bool f2fs_recover_inline_data(struct inode *inode, struct page *npage)
+int f2fs_recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
@@ -274,7 +279,8 @@
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
ipage = f2fs_get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(sbi, IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true, true);
@@ -287,21 +293,25 @@
set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
- return true;
+ return 1;
}
if (f2fs_has_inline_data(inode)) {
ipage = f2fs_get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(sbi, IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
f2fs_truncate_inline_inode(inode, ipage, 0);
clear_inode_flag(inode, FI_INLINE_DATA);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
- if (f2fs_truncate_blocks(inode, 0, false))
- return false;
+ int ret;
+
+ ret = f2fs_truncate_blocks(inode, 0, false);
+ if (ret)
+ return ret;
goto process_inline;
}
- return false;
+ return 0;
}
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index db4fec3..502bd49 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -615,7 +615,11 @@
inode->i_ino == F2FS_META_INO(sbi))
return 0;
- if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
+ /*
+ * atime could be updated without dirtying f2fs inode in lazytime mode
+ */
+ if (f2fs_is_time_consistent(inode) &&
+ !is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;
if (!f2fs_is_checkpoint_ready(sbi))
@@ -677,7 +681,7 @@
err = f2fs_truncate(inode);
if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
- f2fs_show_injection_info(FAULT_EVICT_INODE);
+ f2fs_show_injection_info(sbi, FAULT_EVICT_INODE);
err = -EIO;
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 4faf06e..81a18ba 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -797,6 +797,11 @@
if (whiteout) {
f2fs_i_links_write(inode, false);
+
+ spin_lock(&inode->i_lock);
+ inode->i_state |= I_LINKABLE;
+ spin_unlock(&inode->i_lock);
+
*whiteout = inode;
} else {
d_tmpfile(dentry, inode);
@@ -867,6 +872,12 @@
F2FS_I(old_dentry->d_inode)->i_projid)))
return -EXDEV;
+ if (flags & RENAME_WHITEOUT) {
+ err = f2fs_create_whiteout(old_dir, &whiteout);
+ if (err)
+ return err;
+ }
+
err = dquot_initialize(old_dir);
if (err)
goto out;
@@ -898,17 +909,11 @@
}
}
- if (flags & RENAME_WHITEOUT) {
- err = f2fs_create_whiteout(old_dir, &whiteout);
- if (err)
- goto out_dir;
- }
-
if (new_inode) {
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
- goto out_whiteout;
+ goto out_dir;
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
@@ -916,7 +921,7 @@
if (!new_entry) {
if (IS_ERR(new_page))
err = PTR_ERR(new_page);
- goto out_whiteout;
+ goto out_dir;
}
f2fs_balance_fs(sbi, true);
@@ -948,7 +953,7 @@
err = f2fs_add_link(new_dentry, old_inode);
if (err) {
f2fs_unlock_op(sbi);
- goto out_whiteout;
+ goto out_dir;
}
if (old_dir_entry)
@@ -972,7 +977,7 @@
if (IS_ERR(old_page))
err = PTR_ERR(old_page);
f2fs_unlock_op(sbi);
- goto out_whiteout;
+ goto out_dir;
}
}
}
@@ -981,7 +986,8 @@
if (!old_dir_entry || whiteout)
file_lost_pino(old_inode);
else
- F2FS_I(old_inode)->i_pino = new_dir->i_ino;
+ /* adjust dir's i_pino to pass fsck check */
+ f2fs_i_pino_write(old_inode, new_dir->i_ino);
up_write(&F2FS_I(old_inode)->i_sem);
old_inode->i_ctime = current_time(old_inode);
@@ -990,12 +996,15 @@
f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
if (whiteout) {
- whiteout->i_state |= I_LINKABLE;
set_inode_flag(whiteout, FI_INC_LINK);
err = f2fs_add_link(old_dentry, whiteout);
if (err)
goto put_out_dir;
+
+ spin_lock(&whiteout->i_lock);
whiteout->i_state &= ~I_LINKABLE;
+ spin_unlock(&whiteout->i_lock);
+
iput(whiteout);
}
@@ -1026,15 +1035,14 @@
f2fs_unlock_op(sbi);
if (new_page)
f2fs_put_page(new_page, 0);
-out_whiteout:
- if (whiteout)
- iput(whiteout);
out_dir:
if (old_dir_entry)
f2fs_put_page(old_dir_page, 0);
out_old:
f2fs_put_page(old_page, 0);
out:
+ if (whiteout)
+ iput(whiteout);
return err;
}
@@ -1141,7 +1149,11 @@
f2fs_set_link(old_dir, old_entry, old_page, new_inode);
down_write(&F2FS_I(old_inode)->i_sem);
- file_lost_pino(old_inode);
+ if (!old_dir_entry)
+ file_lost_pino(old_inode);
+ else
+ /* adjust dir's i_pino to pass fsck check */
+ f2fs_i_pino_write(old_inode, new_dir->i_ino);
up_write(&F2FS_I(old_inode)->i_sem);
old_dir->i_ctime = current_time(old_dir);
@@ -1156,7 +1168,11 @@
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
down_write(&F2FS_I(new_inode)->i_sem);
- file_lost_pino(new_inode);
+ if (!new_dir_entry)
+ file_lost_pino(new_inode);
+ else
+ /* adjust dir's i_pino to pass fsck check */
+ f2fs_i_pino_write(new_inode, old_dir->i_ino);
up_write(&F2FS_I(new_inode)->i_sem);
new_dir->i_ctime = current_time(new_dir);
@@ -1240,9 +1256,18 @@
return target;
}
+static int f2fs_encrypted_symlink_getattr(const struct path *path,
+ struct kstat *stat, u32 request_mask,
+ unsigned int query_flags)
+{
+ f2fs_getattr(path, stat, request_mask, query_flags);
+
+ return fscrypt_symlink_getattr(path, stat);
+}
+
const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
.get_link = f2fs_encrypted_get_link,
- .getattr = f2fs_getattr,
+ .getattr = f2fs_encrypted_symlink_getattr,
.setattr = f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
.listxattr = f2fs_listxattr,
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 8b66bc4..4cb182c 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -62,8 +62,8 @@
sizeof(struct free_nid)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == NAT_ENTRIES) {
- mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
- PAGE_SHIFT;
+ mem_size = (nm_i->nat_cnt[TOTAL_NAT] *
+ sizeof(struct nat_entry)) >> PAGE_SHIFT;
res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
if (excess_cached_nats(sbi))
res = false;
@@ -109,7 +109,7 @@
static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
{
- return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid));
+ return f2fs_get_meta_page_retry(sbi, current_nat_addr(sbi, nid));
}
static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
@@ -177,7 +177,8 @@
list_add_tail(&ne->list, &nm_i->nat_entries);
spin_unlock(&nm_i->nat_list_lock);
- nm_i->nat_cnt++;
+ nm_i->nat_cnt[TOTAL_NAT]++;
+ nm_i->nat_cnt[RECLAIMABLE_NAT]++;
return ne;
}
@@ -207,7 +208,8 @@
static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
{
radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
- nm_i->nat_cnt--;
+ nm_i->nat_cnt[TOTAL_NAT]--;
+ nm_i->nat_cnt[RECLAIMABLE_NAT]--;
__free_nat_entry(e);
}
@@ -253,7 +255,8 @@
if (get_nat_flag(ne, IS_DIRTY))
goto refresh_list;
- nm_i->dirty_nat_cnt++;
+ nm_i->nat_cnt[DIRTY_NAT]++;
+ nm_i->nat_cnt[RECLAIMABLE_NAT]--;
set_nat_flag(ne, IS_DIRTY, true);
refresh_list:
spin_lock(&nm_i->nat_list_lock);
@@ -273,7 +276,8 @@
set_nat_flag(ne, IS_DIRTY, false);
set->entry_cnt--;
- nm_i->dirty_nat_cnt--;
+ nm_i->nat_cnt[DIRTY_NAT]--;
+ nm_i->nat_cnt[RECLAIMABLE_NAT]++;
}
static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
@@ -1562,15 +1566,16 @@
if (atomic && !test_opt(sbi, NOBARRIER))
fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
- set_page_writeback(page);
- ClearPageError(page);
-
+ /* should add to global list before clearing PAGECACHE status */
if (f2fs_in_warm_node_list(sbi, page)) {
seq = f2fs_add_fsync_node_entry(sbi, page);
if (seq_id)
*seq_id = seq;
}
+ set_page_writeback(page);
+ ClearPageError(page);
+
fio.old_blkaddr = ni.blk_addr;
f2fs_do_write_node_page(nid, &fio);
set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
@@ -2314,6 +2319,9 @@
if (unlikely(nid >= nm_i->max_nid))
nid = 0;
+ if (unlikely(nid % NAT_ENTRY_PER_BLOCK))
+ nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK;
+
/* Enough entries */
if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
return 0;
@@ -2349,7 +2357,6 @@
if (ret) {
up_read(&nm_i->nat_tree_lock);
- f2fs_bug_on(sbi, !mount);
f2fs_err(sbi, "NAT is corrupt, run fsck to fix it");
return ret;
}
@@ -2399,7 +2406,7 @@
struct free_nid *i = NULL;
retry:
if (time_to_inject(sbi, FAULT_ALLOC_NID)) {
- f2fs_show_injection_info(FAULT_ALLOC_NID);
+ f2fs_show_injection_info(sbi, FAULT_ALLOC_NID);
return false;
}
@@ -2511,7 +2518,7 @@
return nr - nr_shrink;
}
-void f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
+int f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
size_t inline_size;
@@ -2519,7 +2526,8 @@
struct f2fs_inode *ri;
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
- f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
ri = F2FS_INODE(page);
if (ri->i_inline & F2FS_INLINE_XATTR) {
@@ -2538,6 +2546,7 @@
update_inode:
f2fs_update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
+ return 0;
}
int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
@@ -2709,6 +2718,9 @@
struct f2fs_nat_entry raw_ne;
nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
+ if (f2fs_check_nid_range(sbi, nid))
+ continue;
+
raw_ne = nat_in_journal(journal, i);
ne = __lookup_nat_cache(nm_i, nid);
@@ -2876,14 +2888,17 @@
LIST_HEAD(sets);
int err = 0;
- /* during unmount, let's flush nat_bits before checking dirty_nat_cnt */
+ /*
+ * during unmount, let's flush nat_bits before checking
+ * nat_cnt[DIRTY_NAT].
+ */
if (enabled_nat_bits(sbi, cpc)) {
down_write(&nm_i->nat_tree_lock);
remove_nats_in_journal(sbi);
up_write(&nm_i->nat_tree_lock);
}
- if (!nm_i->dirty_nat_cnt)
+ if (!nm_i->nat_cnt[DIRTY_NAT])
return 0;
down_write(&nm_i->nat_tree_lock);
@@ -2894,7 +2909,8 @@
* into nat entry set.
*/
if (enabled_nat_bits(sbi, cpc) ||
- !__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+ !__has_cursum_space(journal,
+ nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL))
remove_nats_in_journal(sbi);
while ((found = __gang_lookup_nat_set(nm_i,
@@ -2932,7 +2948,7 @@
return 0;
nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8);
- nm_i->nat_bits = f2fs_kzalloc(sbi,
+ nm_i->nat_bits = f2fs_kvzalloc(sbi,
nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL);
if (!nm_i->nat_bits)
return -ENOMEM;
@@ -3018,7 +3034,6 @@
F2FS_RESERVED_NODE_NUM;
nm_i->nid_cnt[FREE_NID] = 0;
nm_i->nid_cnt[PREALLOC_NID] = 0;
- nm_i->nat_cnt = 0;
nm_i->ram_thresh = DEF_RAM_THRESHOLD;
nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
@@ -3065,9 +3080,9 @@
int i;
nm_i->free_nid_bitmap =
- f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *),
- nm_i->nat_blocks),
- GFP_KERNEL);
+ f2fs_kvzalloc(sbi, array_size(sizeof(unsigned char *),
+ nm_i->nat_blocks),
+ GFP_KERNEL);
if (!nm_i->free_nid_bitmap)
return -ENOMEM;
@@ -3155,7 +3170,7 @@
__del_from_nat_cache(nm_i, natvec[idx]);
}
}
- f2fs_bug_on(sbi, nm_i->nat_cnt);
+ f2fs_bug_on(sbi, nm_i->nat_cnt[TOTAL_NAT]);
/* destroy nat set cache */
nid = 0;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index e05af5d..4a2e7ea 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -123,13 +123,13 @@
static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
{
- return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
+ return NM_I(sbi)->nat_cnt[DIRTY_NAT] >= NM_I(sbi)->max_nid *
NM_I(sbi)->dirty_nats_ratio / 100;
}
static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
{
- return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
+ return NM_I(sbi)->nat_cnt[TOTAL_NAT] >= DEF_NAT_CACHE_THRESHOLD;
}
static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 783773e..5f230e9 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -514,7 +514,9 @@
/* step 1: recover xattr */
if (IS_INODE(page)) {
- f2fs_recover_inline_xattr(inode, page);
+ err = f2fs_recover_inline_xattr(inode, page);
+ if (err)
+ goto out;
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
err = f2fs_recover_xattr_data(inode, page);
if (!err)
@@ -523,8 +525,12 @@
}
/* step 2: recover inline data */
- if (f2fs_recover_inline_data(inode, page))
+ err = f2fs_recover_inline_data(inode, page);
+ if (err) {
+ if (err == 1)
+ err = 0;
goto out;
+ }
/* step 3: recover data indices */
start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 8087095..78c54bb 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -288,6 +288,8 @@
struct list_head *head = &sbi->inode_list[ATOMIC_FILE];
struct inode *inode;
struct f2fs_inode_info *fi;
+ unsigned int count = sbi->atomic_files;
+ unsigned int looped = 0;
next:
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (list_empty(head)) {
@@ -296,22 +298,26 @@
}
fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist);
inode = igrab(&fi->vfs_inode);
+ if (inode)
+ list_move_tail(&fi->inmem_ilist, head);
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
if (inode) {
if (gc_failure) {
- if (fi->i_gc_failures[GC_FAILURE_ATOMIC])
- goto drop;
- goto skip;
+ if (!fi->i_gc_failures[GC_FAILURE_ATOMIC])
+ goto skip;
}
-drop:
set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST);
f2fs_drop_inmem_pages(inode);
+skip:
iput(inode);
}
-skip:
congestion_wait(BLK_RW_ASYNC, HZ/50);
cond_resched();
+ if (gc_failure) {
+ if (++looped >= count)
+ return;
+ }
goto next;
}
@@ -327,13 +333,16 @@
mutex_unlock(&fi->inmem_lock);
}
- clear_inode_flag(inode, FI_ATOMIC_FILE);
fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0;
stat_dec_atomic_write(inode);
spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
if (!list_empty(&fi->inmem_ilist))
list_del_init(&fi->inmem_ilist);
+ if (f2fs_is_atomic_file(inode)) {
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ sbi->atomic_files--;
+ }
spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
}
@@ -480,7 +489,7 @@
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
- f2fs_show_injection_info(FAULT_CHECKPOINT);
+ f2fs_show_injection_info(sbi, FAULT_CHECKPOINT);
f2fs_stop_checkpoint(sbi, false);
}
@@ -1008,8 +1017,9 @@
if (dc->error)
printk_ratelimited(
- "%sF2FS-fs: Issue discard(%u, %u, %u) failed, ret: %d",
- KERN_INFO, dc->lstart, dc->start, dc->len, dc->error);
+ "%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d",
+ KERN_INFO, sbi->sb->s_id,
+ dc->lstart, dc->start, dc->len, dc->error);
__detach_discard_cmd(dcc, dc);
}
@@ -1149,7 +1159,7 @@
dc->len += len;
if (time_to_inject(sbi, FAULT_DISCARD)) {
- f2fs_show_injection_info(FAULT_DISCARD);
+ f2fs_show_injection_info(sbi, FAULT_DISCARD);
err = -EIO;
goto submit;
}
@@ -2301,7 +2311,9 @@
*/
struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno)
{
- return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno));
+ if (unlikely(f2fs_cp_error(sbi)))
+ return ERR_PTR(-EIO);
+ return f2fs_get_meta_page_retry(sbi, GET_SUM_BLOCK(sbi, segno));
}
void f2fs_update_meta_page(struct f2fs_sb_info *sbi,
@@ -2573,7 +2585,11 @@
__next_free_blkoff(sbi, curseg, 0);
sum_page = f2fs_get_sum_page(sbi, new_segno);
- f2fs_bug_on(sbi, IS_ERR(sum_page));
+ if (IS_ERR(sum_page)) {
+ /* GC won't be able to use stale summary pages by cp_error */
+ memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE);
+ return;
+ }
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
f2fs_put_page(sum_page, 1);
@@ -3704,7 +3720,7 @@
static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
unsigned int segno)
{
- return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno));
+ return f2fs_get_meta_page(sbi, current_sit_addr(sbi, segno));
}
static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 325781a..2034b9a 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -88,11 +88,11 @@
#define BLKS_PER_SEC(sbi) \
((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
#define GET_SEC_FROM_SEG(sbi, segno) \
- ((segno) / (sbi)->segs_per_sec)
+ (((segno) == -1) ? -1: (segno) / (sbi)->segs_per_sec)
#define GET_SEG_FROM_SEC(sbi, secno) \
((secno) * (sbi)->segs_per_sec)
#define GET_ZONE_FROM_SEC(sbi, secno) \
- ((secno) / (sbi)->secs_per_zone)
+ (((secno) == -1) ? -1: (secno) / (sbi)->secs_per_zone)
#define GET_ZONE_FROM_SEG(sbi, segno) \
GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno))
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
index a467aca..3ceebaa 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -18,9 +18,7 @@
static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
{
- long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
-
- return count > 0 ? count : 0;
+ return NM_I(sbi)->nat_cnt[RECLAIMABLE_NAT];
}
static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 1443cee..41bf656 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -277,6 +277,22 @@
F2FS_OPTION(sbi).s_resgid));
}
+static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
+{
+ if (!F2FS_OPTION(sbi).unusable_cap_perc)
+ return;
+
+ if (F2FS_OPTION(sbi).unusable_cap_perc == 100)
+ F2FS_OPTION(sbi).unusable_cap = sbi->user_block_count;
+ else
+ F2FS_OPTION(sbi).unusable_cap = (sbi->user_block_count / 100) *
+ F2FS_OPTION(sbi).unusable_cap_perc;
+
+ f2fs_info(sbi, "Adjust unusable cap for checkpoint=disable = %u / %u%%",
+ F2FS_OPTION(sbi).unusable_cap,
+ F2FS_OPTION(sbi).unusable_cap_perc);
+}
+
static void init_once(void *foo)
{
struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
@@ -439,7 +455,7 @@
break;
case Opt_norecovery:
/* this option mounts f2fs with ro */
- set_opt(sbi, DISABLE_ROLL_FORWARD);
+ set_opt(sbi, NORECOVERY);
if (!f2fs_readonly(sb))
return -EINVAL;
break;
@@ -790,12 +806,7 @@
return -EINVAL;
if (arg < 0 || arg > 100)
return -EINVAL;
- if (arg == 100)
- F2FS_OPTION(sbi).unusable_cap =
- sbi->user_block_count;
- else
- F2FS_OPTION(sbi).unusable_cap =
- (sbi->user_block_count / 100) * arg;
+ F2FS_OPTION(sbi).unusable_cap_perc = arg;
set_opt(sbi, DISABLE_CHECKPOINT);
break;
case Opt_checkpoint_disable_cap:
@@ -1064,6 +1075,9 @@
int i;
bool dropped;
+ /* unregister procfs/sysfs entries in advance to avoid race case */
+ f2fs_unregister_sysfs(sbi);
+
f2fs_quota_off_umount(sb);
/* prevent remaining shrinker jobs */
@@ -1105,7 +1119,7 @@
/* our cp_error case, we can wait for any writeback page */
f2fs_flush_merged_writes(sbi);
- f2fs_wait_on_all_pages_writeback(sbi);
+ f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA);
f2fs_bug_on(sbi, sbi->fsync_node_num);
@@ -1127,8 +1141,6 @@
kvfree(sbi->ckpt);
- f2fs_unregister_sysfs(sbi);
-
sb->s_fs_info = NULL;
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
@@ -1213,20 +1225,23 @@
return PTR_ERR(dquot);
spin_lock(&dquot->dq_dqb_lock);
- limit = (dquot->dq_dqb.dqb_bsoftlimit ?
- dquot->dq_dqb.dqb_bsoftlimit :
- dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+ limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit,
+ dquot->dq_dqb.dqb_bhardlimit);
+ if (limit)
+ limit >>= sb->s_blocksize_bits;
+
if (limit && buf->f_blocks > limit) {
- curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+ curblock = (dquot->dq_dqb.dqb_curspace +
+ dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
buf->f_blocks = limit;
buf->f_bfree = buf->f_bavail =
(buf->f_blocks > curblock) ?
(buf->f_blocks - curblock) : 0;
}
- limit = dquot->dq_dqb.dqb_isoftlimit ?
- dquot->dq_dqb.dqb_isoftlimit :
- dquot->dq_dqb.dqb_ihardlimit;
+ limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit,
+ dquot->dq_dqb.dqb_ihardlimit);
+
if (limit && buf->f_files > limit) {
buf->f_files = limit;
buf->f_ffree =
@@ -1346,6 +1361,8 @@
}
if (test_opt(sbi, DISABLE_ROLL_FORWARD))
seq_puts(seq, ",disable_roll_forward");
+ if (test_opt(sbi, NORECOVERY))
+ seq_puts(seq, ",norecovery");
if (test_opt(sbi, DISCARD))
seq_puts(seq, ",discard");
else
@@ -1731,6 +1748,7 @@
(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
limit_reserve_root(sbi);
+ adjust_unusable_cap_perc(sbi);
*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
return 0;
restore_gc:
@@ -1822,6 +1840,7 @@
int offset = off & (sb->s_blocksize - 1);
size_t towrite = len;
struct page *page;
+ void *fsdata = NULL;
char *kaddr;
int err = 0;
int tocopy;
@@ -1831,7 +1850,7 @@
towrite);
retry:
err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
- &page, NULL);
+ &page, &fsdata);
if (unlikely(err)) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
@@ -1847,7 +1866,7 @@
flush_dcache_page(page);
a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
- page, NULL);
+ page, fsdata);
offset = 0;
towrite -= tocopy;
off += tocopy;
@@ -1975,6 +1994,33 @@
return 0;
}
+static int f2fs_quota_sync_file(struct f2fs_sb_info *sbi, int type)
+{
+ struct quota_info *dqopt = sb_dqopt(sbi->sb);
+ struct address_space *mapping = dqopt->files[type]->i_mapping;
+ int ret = 0;
+
+ ret = dquot_writeback_dquots(sbi->sb, type);
+ if (ret)
+ goto out;
+
+ ret = filemap_fdatawrite(mapping);
+ if (ret)
+ goto out;
+
+ /* if we are using journalled quota */
+ if (is_journalled_quota(sbi))
+ goto out;
+
+ ret = filemap_fdatawait(mapping);
+
+ truncate_inode_pages(&dqopt->files[type]->i_data, 0);
+out:
+ if (ret)
+ set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+ return ret;
+}
+
int f2fs_quota_sync(struct super_block *sb, int type)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -1983,56 +2029,41 @@
int ret;
/*
- * do_quotactl
- * f2fs_quota_sync
- * down_read(quota_sem)
- * dquot_writeback_dquots()
- * f2fs_dquot_commit
- * block_operation
- * down_read(quota_sem)
- */
- f2fs_lock_op(sbi);
-
- down_read(&sbi->quota_sem);
- ret = dquot_writeback_dquots(sb, type);
- if (ret)
- goto out;
-
- /*
* Now when everything is written we can discard the pagecache so
* that userspace sees the changes.
*/
for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
- struct address_space *mapping;
if (type != -1 && cnt != type)
continue;
- if (!sb_has_quota_active(sb, cnt))
- continue;
- mapping = dqopt->files[cnt]->i_mapping;
-
- ret = filemap_fdatawrite(mapping);
- if (ret)
- goto out;
-
- /* if we are using journalled quota */
- if (is_journalled_quota(sbi))
- continue;
-
- ret = filemap_fdatawait(mapping);
- if (ret)
- set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
+ if (!sb_has_quota_active(sb, type))
+ return 0;
inode_lock(dqopt->files[cnt]);
- truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
+
+ /*
+ * do_quotactl
+ * f2fs_quota_sync
+ * down_read(quota_sem)
+ * dquot_writeback_dquots()
+ * f2fs_dquot_commit
+ * block_operation
+ * down_read(quota_sem)
+ */
+ f2fs_lock_op(sbi);
+ down_read(&sbi->quota_sem);
+
+ ret = f2fs_quota_sync_file(sbi, cnt);
+
+ up_read(&sbi->quota_sem);
+ f2fs_unlock_op(sbi);
+
inode_unlock(dqopt->files[cnt]);
+
+ if (ret)
+ break;
}
-out:
- if (ret)
- set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR);
- up_read(&sbi->quota_sem);
- f2fs_unlock_op(sbi);
return ret;
}
@@ -2504,7 +2535,6 @@
block_t total_sections, blocks_per_seg;
struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
(bh->b_data + F2FS_SUPER_OFFSET);
- unsigned int blocksize;
size_t crc_offset = 0;
__u32 crc = 0;
@@ -2538,10 +2568,10 @@
}
/* Currently, support only 4KB block size */
- blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
- if (blocksize != F2FS_BLKSIZE) {
- f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB",
- blocksize);
+ if (le32_to_cpu(raw_super->log_blocksize) != F2FS_BLKSIZE_BITS) {
+ f2fs_info(sbi, "Invalid log_blocksize (%u), supports only %u",
+ le32_to_cpu(raw_super->log_blocksize),
+ F2FS_BLKSIZE_BITS);
return -EFSCORRUPTED;
}
@@ -2883,7 +2913,7 @@
if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
FDEV(devi).nr_blkz++;
- FDEV(devi).blkz_seq = f2fs_kzalloc(sbi,
+ FDEV(devi).blkz_seq = f2fs_kvzalloc(sbi,
BITS_TO_LONGS(FDEV(devi).nr_blkz)
* sizeof(unsigned long),
GFP_KERNEL);
@@ -3392,6 +3422,7 @@
sbi->reserved_blocks = 0;
sbi->current_reserved_blocks = 0;
limit_reserve_root(sbi);
+ adjust_unusable_cap_perc(sbi);
for (i = 0; i < NR_INODE_TYPE; i++) {
INIT_LIST_HEAD(&sbi->inode_list[i]);
@@ -3486,7 +3517,8 @@
goto reset_checkpoint;
/* recover fsynced data */
- if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
+ if (!test_opt(sbi, DISABLE_ROLL_FORWARD) &&
+ !test_opt(sbi, NORECOVERY)) {
/*
* mount should be failed, when device has readonly mode, and
* previous checkpoint was not done by clean system shutdown.
@@ -3784,4 +3816,5 @@
MODULE_AUTHOR("Samsung Electronics's Praesto Team");
MODULE_DESCRIPTION("Flash Friendly File System");
MODULE_LICENSE("GPL");
+MODULE_SOFTDEP("pre: crc32");
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index b558b64..3a5360e 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -499,7 +499,9 @@
F2FS_FEATURE_RO_ATTR(verity, FEAT_VERITY);
#endif
F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
+#ifdef CONFIG_UNICODE
F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD);
+#endif
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
@@ -568,7 +570,9 @@
ATTR_LIST(verity),
#endif
ATTR_LIST(sb_checksum),
+#ifdef CONFIG_UNICODE
ATTR_LIST(casefold),
+#endif
NULL,
};
ATTRIBUTE_GROUPS(f2fs_feat);
@@ -729,10 +733,12 @@
ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype,
NULL, "features");
- if (ret)
+ if (ret) {
+ kobject_put(&f2fs_feat);
kset_unregister(&f2fs_kset);
- else
+ } else {
f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ }
return ret;
}
@@ -753,8 +759,11 @@
init_completion(&sbi->s_kobj_unregister);
err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL,
"%s", sb->s_id);
- if (err)
+ if (err) {
+ kobject_put(&sbi->s_kobj);
+ wait_for_completion(&sbi->s_kobj_unregister);
return err;
+ }
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
@@ -782,4 +791,6 @@
remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
}
kobject_del(&sbi->s_kobj);
+ kobject_put(&sbi->s_kobj);
+ wait_for_completion(&sbi->s_kobj_unregister);
}
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index a401ef7..7944a08 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -150,40 +150,73 @@
size_t desc_size, u64 merkle_tree_size)
{
struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
u64 desc_pos = f2fs_verity_metadata_pos(inode) + merkle_tree_size;
struct fsverity_descriptor_location dloc = {
.version = cpu_to_le32(1),
.size = cpu_to_le32(desc_size),
.pos = cpu_to_le64(desc_pos),
};
- int err = 0;
+ int err = 0, err2 = 0;
- if (desc != NULL) {
- /* Succeeded; write the verity descriptor. */
- err = pagecache_write(inode, desc, desc_size, desc_pos);
+ /*
+ * If an error already occurred (which fs/verity/ signals by passing
+ * desc == NULL), then only clean-up is needed.
+ */
+ if (desc == NULL)
+ goto cleanup;
- /* Write all pages before clearing FI_VERITY_IN_PROGRESS. */
- if (!err)
- err = filemap_write_and_wait(inode->i_mapping);
- }
+ /* Append the verity descriptor. */
+ err = pagecache_write(inode, desc, desc_size, desc_pos);
+ if (err)
+ goto cleanup;
- /* If we failed, truncate anything we wrote past i_size. */
- if (desc == NULL || err)
- f2fs_truncate(inode);
+ /*
+ * Write all pages (both data and verity metadata). Note that this must
+ * happen before clearing FI_VERITY_IN_PROGRESS; otherwise pages beyond
+ * i_size won't be written properly. For crash consistency, this also
+ * must happen before the verity inode flag gets persisted.
+ */
+ err = filemap_write_and_wait(inode->i_mapping);
+ if (err)
+ goto cleanup;
+
+ /* Set the verity xattr. */
+ err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_VERITY,
+ F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc),
+ NULL, XATTR_CREATE);
+ if (err)
+ goto cleanup;
+
+ /* Finally, set the verity inode flag. */
+ file_set_verity(inode);
+ f2fs_set_inode_flags(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
clear_inode_flag(inode, FI_VERITY_IN_PROGRESS);
+ return 0;
- if (desc != NULL && !err) {
- err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_VERITY,
- F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc),
- NULL, XATTR_CREATE);
- if (!err) {
- file_set_verity(inode);
- f2fs_set_inode_flags(inode);
- f2fs_mark_inode_dirty_sync(inode, true);
- }
+cleanup:
+ /*
+ * Verity failed to be enabled, so clean up by truncating any verity
+ * metadata that was written beyond i_size (both from cache and from
+ * disk) and clearing FI_VERITY_IN_PROGRESS.
+ *
+ * Taking i_gc_rwsem[WRITE] is needed to stop f2fs garbage collection
+ * from re-instantiating cached pages we are truncating (since unlike
+ * normal file accesses, garbage collection isn't limited by i_size).
+ */
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
+ err2 = f2fs_truncate(inode);
+ if (err2) {
+ f2fs_err(sbi, "Truncating verity metadata failed (errno=%d)",
+ err2);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
}
- return err;
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ clear_inode_flag(inode, FI_VERITY_IN_PROGRESS);
+ return err ?: err2;
}
static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 181900a..296b318 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -539,8 +539,9 @@
ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = d_inode(dentry);
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
struct f2fs_xattr_entry *entry;
- void *base_addr;
+ void *base_addr, *last_base_addr;
int error = 0;
size_t rest = buffer_size;
@@ -550,6 +551,8 @@
if (error)
return error;
+ last_base_addr = (void *)base_addr + XATTR_SIZE(xnid, inode);
+
list_for_each_xattr(entry, base_addr) {
const struct xattr_handler *handler =
f2fs_xattr_handler(entry->e_name_index);
@@ -557,6 +560,15 @@
size_t prefix_len;
size_t size;
+ if ((void *)(entry) + sizeof(__u32) > last_base_addr ||
+ (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) {
+ f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr",
+ inode->i_ino);
+ set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+ error = -EFSCORRUPTED;
+ goto cleanup;
+ }
+
if (!handler || (handler->list && !handler->list(dentry)))
continue;