summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/f2fs/acl.c2
-rw-r--r--fs/f2fs/checkpoint.c65
-rw-r--r--fs/f2fs/compress.c32
-rw-r--r--fs/f2fs/data.c53
-rw-r--r--fs/f2fs/debug.c9
-rw-r--r--fs/f2fs/dir.c1
-rw-r--r--fs/f2fs/extent_cache.c9
-rw-r--r--fs/f2fs/f2fs.h48
-rw-r--r--fs/f2fs/file.c57
-rw-r--r--fs/f2fs/gc.c40
-rw-r--r--fs/f2fs/inline.c17
-rw-r--r--fs/f2fs/inode.c51
-rw-r--r--fs/f2fs/iostat.c74
-rw-r--r--fs/f2fs/iostat.h4
-rw-r--r--fs/f2fs/node.c9
-rw-r--r--fs/f2fs/recovery.c29
-rw-r--r--fs/f2fs/segment.c37
-rw-r--r--fs/f2fs/segment.h2
-rw-r--r--fs/f2fs/super.c96
-rw-r--r--fs/f2fs/sysfs.c9
-rw-r--r--fs/f2fs/verity.c12
-rw-r--r--fs/f2fs/xattr.c8
22 files changed, 465 insertions, 199 deletions
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index eaa240b21f07..5bbc44a5216e 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -219,7 +219,7 @@ static int f2fs_acl_update_mode(struct user_namespace *mnt_userns,
return error;
if (error == 0)
*acl = NULL;
- if (!in_group_p(i_gid_into_mnt(mnt_userns, inode)) &&
+ if (!vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)) &&
!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
*mode_p = mode;
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 8259e0fa97e1..0c82dae082aa 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -26,12 +26,16 @@
static struct kmem_cache *ino_entry_slab;
struct kmem_cache *f2fs_inode_entry_slab;
-void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
+ unsigned char reason)
{
f2fs_build_fault_attr(sbi, 0, 0);
set_ckpt_flags(sbi, CP_ERROR_FLAG);
- if (!end_io)
+ if (!end_io) {
f2fs_flush_merged_writes(sbi);
+
+ f2fs_handle_stop(sbi, reason);
+ }
}
/*
@@ -89,7 +93,7 @@ repeat:
return ERR_PTR(err);
}
- f2fs_update_iostat(sbi, FS_META_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, NULL, FS_META_READ_IO, F2FS_BLKSIZE);
lock_page(page);
if (unlikely(page->mapping != mapping)) {
@@ -122,7 +126,7 @@ retry:
if (PTR_ERR(page) == -EIO &&
++count <= DEFAULT_RETRY_IO_COUNT)
goto retry;
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_META_PAGE);
}
return page;
}
@@ -140,7 +144,7 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
unsigned int segno, offset;
bool exist;
- if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ)
+ if (type == DATA_GENERIC)
return true;
segno = GET_SEGNO(sbi, blkaddr);
@@ -148,6 +152,13 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
se = get_seg_entry(sbi, segno);
exist = f2fs_test_bit(offset, se->cur_valid_map);
+ if (exist && type == DATA_GENERIC_ENHANCE_UPDATE) {
+ f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
+ blkaddr, exist);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ return exist;
+ }
+
if (!exist && type == DATA_GENERIC_ENHANCE) {
f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
blkaddr, exist);
@@ -185,6 +196,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
case DATA_GENERIC:
case DATA_GENERIC_ENHANCE:
case DATA_GENERIC_ENHANCE_READ:
+ case DATA_GENERIC_ENHANCE_UPDATE:
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
blkaddr < MAIN_BLKADDR(sbi))) {
f2fs_warn(sbi, "access invalid blkaddr:%u",
@@ -276,7 +288,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
f2fs_put_page(page, err ? 1 : 0);
if (!err)
- f2fs_update_iostat(sbi, FS_META_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, NULL, FS_META_READ_IO,
+ F2FS_BLKSIZE);
}
out:
blk_finish_plug(&plug);
@@ -448,8 +461,7 @@ static bool f2fs_dirty_meta_folio(struct address_space *mapping,
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
- if (!folio_test_dirty(folio)) {
- filemap_dirty_folio(mapping, folio);
+ if (filemap_dirty_folio(mapping, folio)) {
inc_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_META);
set_page_private_reference(&folio->page);
return true;
@@ -1053,7 +1065,8 @@ void f2fs_remove_dirty_inode(struct inode *inode)
spin_unlock(&sbi->inode_lock[type]);
}
-int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
+int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
+ bool from_cp)
{
struct list_head *head;
struct inode *inode;
@@ -1088,11 +1101,15 @@ retry:
if (inode) {
unsigned long cur_ino = inode->i_ino;
- F2FS_I(inode)->cp_task = current;
+ if (from_cp)
+ F2FS_I(inode)->cp_task = current;
+ F2FS_I(inode)->wb_task = current;
filemap_fdatawrite(inode->i_mapping);
- F2FS_I(inode)->cp_task = NULL;
+ F2FS_I(inode)->wb_task = NULL;
+ if (from_cp)
+ F2FS_I(inode)->cp_task = NULL;
iput(inode);
/* We need to give cpu to another writers. */
@@ -1221,7 +1238,7 @@ retry_flush_dents:
/* write all the dirty dentry pages */
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
f2fs_unlock_all(sbi);
- err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
+ err = f2fs_sync_dirty_inodes(sbi, DIR_INODE, true);
if (err)
return err;
cond_resched();
@@ -1892,15 +1909,27 @@ int f2fs_start_ckpt_thread(struct f2fs_sb_info *sbi)
void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi)
{
struct ckpt_req_control *cprc = &sbi->cprc_info;
+ struct task_struct *ckpt_task;
+
+ if (!cprc->f2fs_issue_ckpt)
+ return;
- if (cprc->f2fs_issue_ckpt) {
- struct task_struct *ckpt_task = cprc->f2fs_issue_ckpt;
+ ckpt_task = cprc->f2fs_issue_ckpt;
+ cprc->f2fs_issue_ckpt = NULL;
+ kthread_stop(ckpt_task);
- cprc->f2fs_issue_ckpt = NULL;
- kthread_stop(ckpt_task);
+ f2fs_flush_ckpt_thread(sbi);
+}
- flush_remained_ckpt_reqs(sbi, NULL);
- }
+void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi)
+{
+ struct ckpt_req_control *cprc = &sbi->cprc_info;
+
+ flush_remained_ckpt_reqs(sbi, NULL);
+
+ /* Let's wait for the previous dispatched checkpoint. */
+ while (atomic_read(&cprc->queued_ckpt))
+ io_schedule_timeout(DEFAULT_IO_TIMEOUT);
}
void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 70e97075e535..d315c2de136f 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -762,6 +762,7 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task)
if (dic->clen > PAGE_SIZE * dic->nr_cpages - COMPRESS_HEADER_SIZE) {
ret = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION);
goto out_release;
}
@@ -912,17 +913,15 @@ bool f2fs_sanity_check_cluster(struct dnode_of_data *dn)
reason = "[C|*|C|*]";
goto out;
}
- if (compressed) {
- if (!__is_valid_data_blkaddr(blkaddr)) {
- if (!cluster_end)
- cluster_end = i;
- continue;
- }
- /* [COMPR_ADDR, NULL_ADDR or NEW_ADDR, valid_blkaddr] */
- if (cluster_end) {
- reason = "[C|N|N|V]";
- goto out;
- }
+ if (!__is_valid_data_blkaddr(blkaddr)) {
+ if (!cluster_end)
+ cluster_end = i;
+ continue;
+ }
+ /* [COMPR_ADDR, NULL_ADDR or NEW_ADDR, valid_blkaddr] */
+ if (cluster_end) {
+ reason = "[C|N|N|V]";
+ goto out;
}
}
return false;
@@ -952,6 +951,7 @@ static int __f2fs_cluster_blocks(struct inode *inode,
if (f2fs_sanity_check_cluster(&dn)) {
ret = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode), ERROR_CORRUPTED_CLUSTER);
goto fail;
}
@@ -1568,12 +1568,8 @@ static int f2fs_prepare_decomp_mem(struct decompress_io_ctx *dic,
if (!dic->cbuf)
return -ENOMEM;
- if (cops->init_decompress_ctx) {
- int ret = cops->init_decompress_ctx(dic);
-
- if (ret)
- return ret;
- }
+ if (cops->init_decompress_ctx)
+ return cops->init_decompress_ctx(dic);
return 0;
}
@@ -1905,7 +1901,7 @@ bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino)
{
- struct address_space *mapping = sbi->compress_inode->i_mapping;
+ struct address_space *mapping = COMPRESS_MAPPING(sbi);
struct folio_batch fbatch;
pgoff_t index = 0;
pgoff_t end = MAX_BLKADDR(sbi);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 93cc2ec51c2a..a71e818cd67b 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -335,7 +335,8 @@ static void f2fs_write_end_io(struct bio *bio)
mempool_free(page, sbi->write_io_dummy);
if (unlikely(bio->bi_status))
- f2fs_stop_checkpoint(sbi, true);
+ f2fs_stop_checkpoint(sbi, true,
+ STOP_CP_REASON_WRITE_FAIL);
continue;
}
@@ -351,7 +352,8 @@ static void f2fs_write_end_io(struct bio *bio)
if (unlikely(bio->bi_status)) {
mapping_set_error(page->mapping, -EIO);
if (type == F2FS_WB_CP_DATA)
- f2fs_stop_checkpoint(sbi, true);
+ f2fs_stop_checkpoint(sbi, true,
+ STOP_CP_REASON_WRITE_FAIL);
}
f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
@@ -705,8 +707,10 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
fio->is_por ? META_POR : (__is_meta_io(fio) ?
- META_GENERIC : DATA_GENERIC_ENHANCE)))
+ META_GENERIC : DATA_GENERIC_ENHANCE))) {
+ f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
+ }
trace_f2fs_submit_page_bio(page, fio);
@@ -725,7 +729,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
- __read_io_type(page): WB_DATA_TYPE(fio->page));
+ __read_io_type(page) : WB_DATA_TYPE(fio->page));
__submit_bio(fio->sbi, bio, fio->type);
return 0;
@@ -906,8 +910,10 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
fio->encrypted_page : fio->page;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
- __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
+ __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC)) {
+ f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
+ }
trace_f2fs_submit_page_bio(page, fio);
@@ -1085,7 +1091,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
}
ClearPageError(page);
inc_page_count(sbi, F2FS_RD_DATA);
- f2fs_update_iostat(sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, NULL, FS_DATA_READ_IO, F2FS_BLKSIZE);
__submit_bio(sbi, bio, DATA);
return 0;
}
@@ -1217,6 +1223,8 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_INVALID_BLKADDR);
goto put_err;
}
goto got_it;
@@ -1237,6 +1245,8 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
dn.data_blkaddr,
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_INVALID_BLKADDR);
goto put_err;
}
got_it:
@@ -1550,6 +1560,7 @@ next_block:
if (__is_valid_data_blkaddr(blkaddr) &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto sync_out;
}
@@ -1595,6 +1606,8 @@ next_block:
(flag != F2FS_GET_BLOCK_FIEMAP ||
IS_ENABLED(CONFIG_F2FS_CHECK_FS))) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi,
+ ERROR_CORRUPTED_CLUSTER);
goto sync_out;
}
if (flag == F2FS_GET_BLOCK_BMAP) {
@@ -1818,7 +1831,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
- if (err || err == 1)
+ if (err)
return err;
}
@@ -2076,6 +2089,8 @@ got_it:
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr,
DATA_GENERIC_ENHANCE_READ)) {
ret = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_INVALID_BLKADDR);
goto out;
}
} else {
@@ -2124,7 +2139,8 @@ submit_and_realloc:
goto submit_and_realloc;
inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
- f2fs_update_iostat(F2FS_I_SB(inode), FS_DATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO,
+ F2FS_BLKSIZE);
ClearPageError(page);
*last_block_in_bio = block_nr;
goto out;
@@ -2272,8 +2288,7 @@ submit_and_realloc:
refcount_inc(&dic->refcnt);
inc_page_count(sbi, F2FS_RD_DATA);
- f2fs_update_iostat(sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
- f2fs_update_iostat(sbi, FS_CDATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE);
ClearPageError(page);
*last_block_in_bio = blkaddr;
}
@@ -2545,7 +2560,7 @@ bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio)
return true;
/* if this is cold file, we should overwrite to avoid fragmentation */
- if (file_is_cold(inode))
+ if (file_is_cold(inode) && !is_inode_flag_set(inode, FI_OPU_WRITE))
return true;
return check_inplace_update_policy(inode, fio);
@@ -2619,8 +2634,11 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
fio->old_blkaddr = ei.blk + page->index - ei.fofs;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
- DATA_GENERIC_ENHANCE))
+ DATA_GENERIC_ENHANCE)) {
+ f2fs_handle_error(fio->sbi,
+ ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
+ }
ipu_force = true;
fio->need_lock = LOCK_DONE;
@@ -2648,6 +2666,7 @@ got_it:
!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR);
goto out_writepage;
}
@@ -2858,7 +2877,7 @@ out:
}
unlock_page(page);
if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
- !F2FS_I(inode)->cp_task && allow_balance)
+ !F2FS_I(inode)->wb_task && allow_balance)
f2fs_balance_fs(sbi, need_balance_fs);
if (unlikely(f2fs_cp_error(sbi))) {
@@ -3158,7 +3177,7 @@ static inline bool __should_serialize_io(struct inode *inode,
struct writeback_control *wbc)
{
/* to avoid deadlock in path of data flush */
- if (F2FS_I(inode)->cp_task)
+ if (F2FS_I(inode)->wb_task)
return false;
if (!S_ISREG(inode->i_mode))
@@ -3561,6 +3580,7 @@ repeat:
if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto fail;
}
err = f2fs_submit_page_read(inode, page, blkaddr, 0, true);
@@ -3699,8 +3719,7 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping,
folio_mark_uptodate(folio);
BUG_ON(folio_test_swapcache(folio));
- if (!folio_test_dirty(folio)) {
- filemap_dirty_folio(mapping, folio);
+ if (filemap_dirty_folio(mapping, folio)) {
f2fs_update_dirty_folio(inode, folio);
return true;
}
@@ -3972,6 +3991,7 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
if (ret < 0)
return ret;
+ stat_inc_swapfile_inode(inode);
set_inode_flag(inode, FI_PIN_FILE);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return ret;
@@ -3981,6 +4001,7 @@ static void f2fs_swap_deactivate(struct file *file)
{
struct inode *inode = file_inode(file);
+ stat_dec_swapfile_inode(inode);
clear_inode_flag(inode, FI_PIN_FILE);
}
#else
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index c01471573977..a216dcdf6941 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -91,7 +91,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
si->nquota_files = sbi->nquota_files;
si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
- si->aw_cnt = sbi->atomic_files;
+ si->aw_cnt = atomic_read(&sbi->atomic_files);
si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
si->nr_dio_read = get_pages(sbi, F2FS_DIO_READ);
si->nr_dio_write = get_pages(sbi, F2FS_DIO_WRITE);
@@ -135,6 +135,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->inline_inode = atomic_read(&sbi->inline_inode);
si->inline_dir = atomic_read(&sbi->inline_dir);
si->compr_inode = atomic_read(&sbi->compr_inode);
+ si->swapfile_inode = atomic_read(&sbi->swapfile_inode);
si->compr_blocks = atomic64_read(&sbi->compr_blocks);
si->append = sbi->im[APPEND_INO].ino_num;
si->update = sbi->im[UPDATE_INO].ino_num;
@@ -347,7 +348,7 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n",
si->sbi->sb->s_bdev, i++,
- f2fs_readonly(si->sbi->sb) ? "RO": "RW",
+ f2fs_readonly(si->sbi->sb) ? "RO" : "RW",
is_set_ckpt_flags(si->sbi, CP_DISABLED_FLAG) ?
"Disabled" : (f2fs_cp_error(si->sbi) ? "Error" : "Good"));
if (si->sbi->s_flag) {
@@ -385,6 +386,8 @@ static int stat_show(struct seq_file *s, void *v)
si->inline_dir);
seq_printf(s, " - Compressed Inode: %u, Blocks: %llu\n",
si->compr_inode, si->compr_blocks);
+ seq_printf(s, " - Swapfile Inode: %u\n",
+ si->swapfile_inode);
seq_printf(s, " - Orphan/Append/Update Inode: %u, %u, %u\n",
si->orphans, si->append, si->update);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
@@ -607,6 +610,8 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
atomic_set(&sbi->inline_dir, 0);
atomic_set(&sbi->compr_inode, 0);
atomic64_set(&sbi->compr_blocks, 0);
+ atomic_set(&sbi->swapfile_inode, 0);
+ atomic_set(&sbi->atomic_files, 0);
atomic_set(&sbi->inplace_count, 0);
for (i = META_CP; i < META_MAX; i++)
atomic_set(&sbi->meta_count[i], 0);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index d5bd7932fb64..21960a899b6a 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -1041,6 +1041,7 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
__func__, le16_to_cpu(de->name_len));
set_sbi_flag(sbi, SBI_NEED_FSCK);
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_CORRUPTED_DIRENT);
goto out;
}
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 866e72b29bd5..932c070173b9 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -544,7 +544,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode,
if (!et)
return;
- trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
+ trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len, 0);
write_lock(&et->lock);
@@ -583,7 +583,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode,
org_end = dei.fofs + dei.len;
f2fs_bug_on(sbi, pos >= org_end);
- if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
+ if (pos > dei.fofs && pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
en->ei.len = pos - en->ei.fofs;
prev_en = en;
parts = 1;
@@ -675,7 +675,7 @@ void f2fs_update_extent_tree_range_compressed(struct inode *inode,
struct rb_node **insert_p = NULL, *insert_parent = NULL;
bool leftmost = false;
- trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, llen);
+ trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, llen, c_len);
/* it is safe here to check FI_NO_EXTENT w/o et->lock in ro image */
if (is_inode_flag_set(inode, FI_NO_EXTENT))
@@ -804,9 +804,8 @@ void f2fs_drop_extent_tree(struct inode *inode)
if (!f2fs_may_extent_tree(inode))
return;
- set_inode_flag(inode, FI_NO_EXTENT);
-
write_lock(&et->lock);
+ set_inode_flag(inode, FI_NO_EXTENT);
__free_extent_tree(sbi, et);
if (et->largest.len) {
et->largest.len = 0;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index aea816a133a8..e6355a5683b7 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -266,6 +266,10 @@ enum {
* condition of read on truncated area
* by extent_cache
*/
+ DATA_GENERIC_ENHANCE_UPDATE, /*
+ * strong check on range and segment
+ * bitmap for update case
+ */
META_GENERIC,
};
@@ -274,7 +278,7 @@ enum {
ORPHAN_INO, /* for orphan ino list */
APPEND_INO, /* for append ino list */
UPDATE_INO, /* for update ino list */
- TRANS_DIR_INO, /* for trasactions dir ino list */
+ TRANS_DIR_INO, /* for transactions dir ino list */
FLUSH_INO, /* for multiple device flushing */
MAX_INO_ENTRY, /* max. list */
};
@@ -782,6 +786,7 @@ struct f2fs_inode_info {
unsigned int clevel; /* maximum level of given file name */
struct task_struct *task; /* lookup and create consistency */
struct task_struct *cp_task; /* separate cp/wb IO stats*/
+ struct task_struct *wb_task; /* indicate inode is in context of writeback */
nid_t i_xattr_nid; /* node id that contains xattrs */
loff_t last_disk_size; /* lastly written file size */
spinlock_t i_size_lock; /* protect last_disk_size */
@@ -1158,7 +1163,10 @@ enum iostat_type {
APP_BUFFERED_IO, /* app buffered write IOs */
APP_WRITE_IO, /* app write IOs */
APP_MAPPED_IO, /* app mapped IOs */
+ APP_BUFFERED_CDATA_IO, /* app buffered write IOs on compressed file */
+ APP_MAPPED_CDATA_IO, /* app mapped write IOs on compressed file */
FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */
+ FS_CDATA_IO, /* data IOs from kworker/fsync/reclaimer on compressed file */
FS_NODE_IO, /* node IOs from kworker/fsync/reclaimer */
FS_META_IO, /* meta IOs from kworker/reclaimer */
FS_GC_DATA_IO, /* data IOs from forground gc */
@@ -1172,6 +1180,8 @@ enum iostat_type {
APP_BUFFERED_READ_IO, /* app buffered read IOs */
APP_READ_IO, /* app read IOs */
APP_MAPPED_READ_IO, /* app mapped read IOs */
+ APP_BUFFERED_CDATA_READ_IO, /* app buffered read IOs on compressed file */
+ APP_MAPPED_CDATA_READ_IO, /* app mapped read IOs on compressed file */
FS_DATA_READ_IO, /* data read IOs */
FS_GDATA_READ_IO, /* data read IOs from background gc */
FS_CDATA_READ_IO, /* compressed data read IOs */
@@ -1247,7 +1257,6 @@ enum inode_type {
DIR_INODE, /* for dirty dir inode */
FILE_INODE, /* for dirty regular/symlink inode */
DIRTY_META, /* for all dirtied inode metadata */
- ATOMIC_FILE, /* for all atomic files */
NR_INODE_TYPE,
};
@@ -1726,11 +1735,9 @@ struct f2fs_sb_info {
unsigned int gc_mode; /* current GC state */
unsigned int next_victim_seg[2]; /* next segment in victim section */
spinlock_t gc_urgent_high_lock;
- bool gc_urgent_high_limited; /* indicates having limited trial count */
unsigned int gc_urgent_high_remaining; /* remaining trial count for GC_URGENT_HIGH */
/* for skip statistic */
- unsigned int atomic_files; /* # of opened atomic file */
unsigned long long skipped_gc_rwsem; /* FG_GC only */
/* threshold for gc trials on pinned files */
@@ -1761,6 +1768,8 @@ struct f2fs_sb_info {
atomic_t inline_dir; /* # of inline_dentry inodes */
atomic_t compr_inode; /* # of compressed inodes */
atomic64_t compr_blocks; /* # of compressed blocks */
+ atomic_t swapfile_inode; /* # of swapfile inodes */
+ atomic_t atomic_files; /* # of opened atomic file */
atomic_t max_aw_cnt; /* max # of atomic writes */
unsigned int io_skip_bggc; /* skip background gc for in-flight IO */
unsigned int other_skip_bggc; /* skip background gc for other reasons */
@@ -1806,6 +1815,10 @@ struct f2fs_sb_info {
struct workqueue_struct *post_read_wq; /* post read workqueue */
+ unsigned char errors[MAX_F2FS_ERRORS]; /* error flags */
+ spinlock_t error_lock; /* protect errors array */
+ bool error_dirty; /* errors of sb is dirty */
+
struct kmem_cache *inline_xattr_slab; /* inline xattr entry */
unsigned int inline_xattr_slab_size; /* default inline xattr slab size */
@@ -2525,7 +2538,7 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
if (__cp_payload(sbi) > 0) {
if (flag == NAT_BITMAP)
- return &ckpt->sit_nat_version_bitmap;
+ return tmp_ptr;
else
return (unsigned char *)ckpt + F2FS_BLKSIZE;
} else {
@@ -3547,6 +3560,8 @@ int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
int f2fs_quota_sync(struct super_block *sb, int type);
loff_t max_file_blocks(struct inode *inode);
void f2fs_quota_off_umount(struct super_block *sb);
+void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason);
+void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error);
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
int f2fs_sync_fs(struct super_block *sb, int sync);
int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
@@ -3706,7 +3721,9 @@ static inline bool f2fs_need_rand_seg(struct f2fs_sb_info *sbi)
/*
* checkpoint.c
*/
-void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
+ unsigned char reason);
+void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi);
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_retry(struct f2fs_sb_info *sbi, pgoff_t index);
@@ -3736,7 +3753,8 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi);
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi);
void f2fs_update_dirty_folio(struct inode *inode, struct folio *folio);
void f2fs_remove_dirty_inode(struct inode *inode);
-int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type,
+ bool from_cp);
void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type);
u64 f2fs_get_sectors_written(struct f2fs_sb_info *sbi);
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
@@ -3858,7 +3876,7 @@ struct f2fs_stat_info {
int nr_issued_ckpt, nr_total_ckpt, nr_queued_ckpt;
unsigned int cur_ckpt_time, peak_ckpt_time;
int inline_xattr, inline_inode, inline_dir, append, update, orphans;
- int compr_inode;
+ int compr_inode, swapfile_inode;
unsigned long long compr_blocks;
int aw_cnt, max_aw_cnt;
unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
@@ -3947,6 +3965,14 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
(atomic64_add(blocks, &F2FS_I_SB(inode)->compr_blocks))
#define stat_sub_compr_blocks(inode, blocks) \
(atomic64_sub(blocks, &F2FS_I_SB(inode)->compr_blocks))
+#define stat_inc_swapfile_inode(inode) \
+ (atomic_inc(&F2FS_I_SB(inode)->swapfile_inode))
+#define stat_dec_swapfile_inode(inode) \
+ (atomic_dec(&F2FS_I_SB(inode)->swapfile_inode))
+#define stat_inc_atomic_inode(inode) \
+ (atomic_inc(&F2FS_I_SB(inode)->atomic_files))
+#define stat_dec_atomic_inode(inode) \
+ (atomic_dec(&F2FS_I_SB(inode)->atomic_files))
#define stat_inc_meta_count(sbi, blkaddr) \
do { \
if (blkaddr < SIT_I(sbi)->sit_base_addr) \
@@ -3966,7 +3992,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
(atomic_inc(&(sbi)->inplace_count))
#define stat_update_max_atomic_write(inode) \
do { \
- int cur = F2FS_I_SB(inode)->atomic_files; \
+ int cur = atomic_read(&F2FS_I_SB(inode)->atomic_files); \
int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt); \
if (cur > max) \
atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \
@@ -4031,6 +4057,10 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi);
#define stat_dec_compr_inode(inode) do { } while (0)
#define stat_add_compr_blocks(inode, blocks) do { } while (0)
#define stat_sub_compr_blocks(inode, blocks) do { } while (0)
+#define stat_inc_swapfile_inode(inode) do { } while (0)
+#define stat_dec_swapfile_inode(inode) do { } while (0)
+#define stat_inc_atomic_inode(inode) do { } while (0)
+#define stat_dec_atomic_inode(inode) do { } while (0)
#define stat_update_max_atomic_write(inode) do { } while (0)
#define stat_inc_meta_count(sbi, blkaddr) do { } while (0)
#define stat_inc_seg_type(sbi, curseg) do { } while (0)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 791770507328..82cda1258227 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -43,8 +43,8 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
ret = filemap_fault(vmf);
if (!ret)
- f2fs_update_iostat(F2FS_I_SB(inode), APP_MAPPED_READ_IO,
- F2FS_BLKSIZE);
+ f2fs_update_iostat(F2FS_I_SB(inode), inode,
+ APP_MAPPED_READ_IO, F2FS_BLKSIZE);
trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)ret);
@@ -154,7 +154,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
if (!PageUptodate(page))
SetPageUptodate(page);
- f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE);
f2fs_update_time(sbi, REQ_TIME);
trace_f2fs_vm_page_mkwrite(page, DATA);
@@ -822,7 +822,12 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw)
/* disallow direct IO if any of devices has unaligned blksize */
if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
return true;
-
+ /*
+ * for blkzoned device, fallback direct IO to buffered IO, so
+ * all IOs can be serialized by log-structured write.
+ */
+ if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE))
+ return true;
if (f2fs_lfs_mode(sbi) && rw == WRITE && F2FS_IO_ALIGNED(sbi))
return true;
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
@@ -912,9 +917,10 @@ static void __setattr_copy(struct user_namespace *mnt_userns,
inode->i_ctime = attr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
- kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
+ vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
- if (!in_group_p(kgid) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
+ if (!vfsgid_in_group_p(vfsgid) &&
+ !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
mode &= ~S_ISGID;
set_acl_inode(inode, mode);
}
@@ -1196,6 +1202,7 @@ next_dnode:
!f2fs_is_valid_blkaddr(sbi, *blkaddr,
DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
}
@@ -1480,6 +1487,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
if (!f2fs_is_valid_blkaddr(sbi, dn->data_blkaddr,
DATA_GENERIC_ENHANCE)) {
ret = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
break;
}
@@ -2089,9 +2097,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
}
f2fs_i_size_write(fi->cow_inode, i_size_read(inode));
- spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- sbi->atomic_files++;
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+ stat_inc_atomic_inode(inode);
set_inode_flag(inode, FI_ATOMIC_FILE);
set_inode_flag(fi->cow_inode, FI_COW_FILE);
@@ -2185,7 +2191,8 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
if (ret) {
if (ret == -EROFS) {
ret = 0;
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false,
+ STOP_CP_REASON_SHUTDOWN);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
trace_f2fs_shutdown(sbi, in, ret);
}
@@ -2198,7 +2205,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
ret = freeze_bdev(sb->s_bdev);
if (ret)
goto out;
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
thaw_bdev(sb->s_bdev);
break;
@@ -2207,16 +2214,16 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
ret = f2fs_sync_fs(sb, 1);
if (ret)
goto out;
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NOSYNC:
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_METAFLUSH:
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NEED_FSCK:
@@ -3362,8 +3369,10 @@ static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
if (!__is_valid_data_blkaddr(blkaddr))
continue;
if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
- DATA_GENERIC_ENHANCE)))
+ DATA_GENERIC_ENHANCE))) {
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
+ }
}
while (count) {
@@ -3524,8 +3533,10 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
if (!__is_valid_data_blkaddr(blkaddr))
continue;
if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
- DATA_GENERIC_ENHANCE)))
+ DATA_GENERIC_ENHANCE))) {
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
+ }
}
while (count) {
@@ -3797,6 +3808,8 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
DATA_GENERIC_ENHANCE)) {
ret = -EFSCORRUPTED;
f2fs_put_dnode(&dn);
+ f2fs_handle_error(sbi,
+ ERROR_INVALID_BLKADDR);
goto out;
}
@@ -4253,7 +4266,7 @@ static int f2fs_dio_read_end_io(struct kiocb *iocb, ssize_t size, int error,
dec_page_count(sbi, F2FS_DIO_READ);
if (error)
return error;
- f2fs_update_iostat(sbi, APP_DIRECT_READ_IO, size);
+ f2fs_update_iostat(sbi, NULL, APP_DIRECT_READ_IO, size);
return 0;
}
@@ -4342,7 +4355,8 @@ skip_read_trace:
} else {
ret = filemap_read(iocb, to, 0);
if (ret > 0)
- f2fs_update_iostat(F2FS_I_SB(inode), APP_BUFFERED_READ_IO, ret);
+ f2fs_update_iostat(F2FS_I_SB(inode), inode,
+ APP_BUFFERED_READ_IO, ret);
}
if (trace_f2fs_dataread_end_enabled())
trace_f2fs_dataread_end(inode, pos, ret);
@@ -4459,7 +4473,8 @@ static ssize_t f2fs_buffered_write_iter(struct kiocb *iocb,
if (ret > 0) {
iocb->ki_pos += ret;
- f2fs_update_iostat(F2FS_I_SB(inode), APP_BUFFERED_IO, ret);
+ f2fs_update_iostat(F2FS_I_SB(inode), inode,
+ APP_BUFFERED_IO, ret);
}
return ret;
}
@@ -4472,7 +4487,7 @@ static int f2fs_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error,
dec_page_count(sbi, F2FS_DIO_WRITE);
if (error)
return error;
- f2fs_update_iostat(sbi, APP_DIRECT_IO, size);
+ f2fs_update_iostat(sbi, NULL, APP_DIRECT_IO, size);
return 0;
}
@@ -4660,7 +4675,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
skip_write_trace:
/* Do the actual write. */
ret = dio ?
- f2fs_dio_write_iter(iocb, from, &may_need_sync):
+ f2fs_dio_write_iter(iocb, from, &may_need_sync) :
f2fs_buffered_write_iter(iocb, from);
if (trace_f2fs_datawrite_end_enabled())
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 6da21d405ce1..d36bcb23ccfe 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -74,7 +74,8 @@ static int gc_thread_func(void *data)
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
f2fs_show_injection_info(sbi, FAULT_CHECKPOINT);
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false,
+ STOP_CP_REASON_FAULT_INJECT);
}
if (!sb_start_write_trylock(sbi->sb)) {
@@ -97,14 +98,10 @@ static int gc_thread_func(void *data)
*/
if (sbi->gc_mode == GC_URGENT_HIGH) {
spin_lock(&sbi->gc_urgent_high_lock);
- if (sbi->gc_urgent_high_limited) {
- if (!sbi->gc_urgent_high_remaining) {
- sbi->gc_urgent_high_limited = false;
- spin_unlock(&sbi->gc_urgent_high_lock);
- sbi->gc_mode = GC_NORMAL;
- continue;
- }
+ if (sbi->gc_urgent_high_remaining) {
sbi->gc_urgent_high_remaining--;
+ if (!sbi->gc_urgent_high_remaining)
+ sbi->gc_mode = GC_NORMAL;
}
spin_unlock(&sbi->gc_urgent_high_lock);
}
@@ -1082,7 +1079,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
{
struct page *node_page;
nid_t nid;
- unsigned int ofs_in_node;
+ unsigned int ofs_in_node, max_addrs;
block_t source_blkaddr;
nid = le32_to_cpu(sum->nid);
@@ -1108,6 +1105,14 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
return false;
}
+ max_addrs = IS_INODE(node_page) ? DEF_ADDRS_PER_INODE :
+ DEF_ADDRS_PER_BLOCK;
+ if (ofs_in_node >= max_addrs) {
+ f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%u, nid:%u, max:%u",
+ ofs_in_node, dni->ino, dni->nid, max_addrs);
+ return false;
+ }
+
*nofs = ofs_of_node(node_page);
source_blkaddr = data_blkaddr(NULL, node_page, ofs_in_node);
f2fs_put_page(node_page, 1);
@@ -1159,6 +1164,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr,
DATA_GENERIC_ENHANCE_READ))) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto put_page;
}
goto got_it;
@@ -1177,6 +1183,7 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr,
DATA_GENERIC_ENHANCE))) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto put_page;
}
got_it:
@@ -1206,8 +1213,8 @@ got_it:
f2fs_put_page(fio.encrypted_page, 0);
f2fs_put_page(page, 1);
- f2fs_update_iostat(sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
- f2fs_update_iostat(sbi, FS_GDATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, NULL, FS_GDATA_READ_IO, F2FS_BLKSIZE);
return 0;
put_encrypted_page:
@@ -1307,8 +1314,10 @@ static int move_data_block(struct inode *inode, block_t bidx,
goto up_out;
}
- f2fs_update_iostat(fio.sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
- f2fs_update_iostat(fio.sbi, FS_GDATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(fio.sbi, inode, FS_DATA_READ_IO,
+ F2FS_BLKSIZE);
+ f2fs_update_iostat(fio.sbi, NULL, FS_GDATA_READ_IO,
+ F2FS_BLKSIZE);
lock_page(mpage);
if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) ||
@@ -1360,7 +1369,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
goto put_page_out;
}
- f2fs_update_iostat(fio.sbi, FS_GC_DATA_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(fio.sbi, NULL, FS_GC_DATA_IO, F2FS_BLKSIZE);
f2fs_update_data_blkaddr(&dn, newaddr);
set_inode_flag(inode, FI_APPEND_WRITE);
@@ -1706,7 +1715,8 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
f2fs_err(sbi, "Inconsistent segment (%u) type [%d, %d] in SSA and SIT",
segno, type, GET_SUM_TYPE((&sum->footer)));
set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false,
+ STOP_CP_REASON_CORRUPTED_SUMMARY);
goto skip;
}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index bf46a7dfbea2..21a495234ffd 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -64,7 +64,6 @@ bool f2fs_may_inline_dentry(struct inode *inode)
void f2fs_do_read_inline_data(struct page *page, struct page *ipage)
{
struct inode *inode = page->mapping->host;
- void *src_addr, *dst_addr;
if (PageUptodate(page))
return;
@@ -74,11 +73,8 @@ void f2fs_do_read_inline_data(struct page *page, struct page *ipage)
zero_user_segment(page, MAX_INLINE_DATA(inode), PAGE_SIZE);
/* Copy the whole inline data block */
- src_addr = inline_data_addr(inode, ipage);
- dst_addr = kmap_atomic(page);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
- flush_dcache_page(page);
- kunmap_atomic(dst_addr);
+ memcpy_to_page(page, 0, inline_data_addr(inode, ipage),
+ MAX_INLINE_DATA(inode));
if (!PageUptodate(page))
SetPageUptodate(page);
}
@@ -164,6 +160,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
set_sbi_flag(fio.sbi, SBI_NEED_FSCK);
f2fs_warn(fio.sbi, "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.",
__func__, dn->inode->i_ino, dn->data_blkaddr);
+ f2fs_handle_error(fio.sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
}
@@ -246,7 +243,6 @@ out:
int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
- void *src_addr, *dst_addr;
struct dnode_of_data dn;
int err;
@@ -263,10 +259,8 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
f2fs_bug_on(F2FS_I_SB(inode), page->index);
f2fs_wait_on_page_writeback(dn.inode_page, NODE, true, true);
- src_addr = kmap_atomic(page);
- dst_addr = inline_data_addr(inode, dn.inode_page);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
- kunmap_atomic(src_addr);
+ memcpy_from_page(inline_data_addr(inode, dn.inode_page),
+ page, 0, MAX_INLINE_DATA(inode));
set_page_dirty(dn.inode_page);
f2fs_clear_page_cache_dirty_tag(page);
@@ -419,6 +413,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
f2fs_warn(F2FS_P_SB(page), "%s: corrupted inline inode ino=%lx, i_addr[0]:0x%x, run fsck to fix.",
__func__, dir->i_ino, dn.data_blkaddr);
+ f2fs_handle_error(F2FS_P_SB(page), ERROR_INVALID_BLKADDR);
err = -EFSCORRUPTED;
goto out;
}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 6d11c365d7b4..9f0d3864d9f1 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -81,8 +81,10 @@ static int __written_first_block(struct f2fs_sb_info *sbi,
if (!__is_valid_data_blkaddr(addr))
return 1;
- if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE))
+ if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) {
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
+ }
return 0;
}
@@ -333,6 +335,16 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return true;
}
+static void init_idisk_time(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+
+ fi->i_disk_time[0] = inode->i_atime;
+ fi->i_disk_time[1] = inode->i_ctime;
+ fi->i_disk_time[2] = inode->i_mtime;
+ fi->i_disk_time[3] = fi->i_crtime;
+}
+
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -405,6 +417,7 @@ static int do_read_inode(struct inode *inode)
if (!sanity_check_inode(inode, node_page)) {
f2fs_put_page(node_page, 1);
+ f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
return -EFSCORRUPTED;
}
@@ -465,10 +478,7 @@ static int do_read_inode(struct inode *inode)
}
}
- fi->i_disk_time[0] = inode->i_atime;
- fi->i_disk_time[1] = inode->i_ctime;
- fi->i_disk_time[2] = inode->i_mtime;
- fi->i_disk_time[3] = fi->i_crtime;
+ init_idisk_time(inode);
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
@@ -480,6 +490,12 @@ static int do_read_inode(struct inode *inode)
return 0;
}
+static bool is_meta_ino(struct f2fs_sb_info *sbi, unsigned int ino)
+{
+ return ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi) ||
+ ino == F2FS_COMPRESS_INO(sbi);
+}
+
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -491,16 +507,22 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW)) {
+ if (is_meta_ino(sbi, ino)) {
+ f2fs_err(sbi, "inaccessible inode: %lu, run fsck to repair", ino);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ ret = -EFSCORRUPTED;
+ trace_f2fs_iget_exit(inode, ret);
+ iput(inode);
+ f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
+ return ERR_PTR(ret);
+ }
+
trace_f2fs_iget(inode);
return inode;
}
- if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
- goto make_now;
-#ifdef CONFIG_F2FS_FS_COMPRESSION
- if (ino == F2FS_COMPRESS_INO(sbi))
+ if (is_meta_ino(sbi, ino))
goto make_now;
-#endif
ret = do_read_inode(inode);
if (ret)
@@ -676,11 +698,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
if (inode->i_nlink == 0)
clear_page_private_inline(node_page);
- F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
- F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
- F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
- F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
-
+ init_idisk_time(inode);
#ifdef CONFIG_F2FS_CHECK_FS
f2fs_inode_chksum_set(F2FS_I_SB(inode), node_page);
#endif
@@ -699,7 +717,8 @@ retry:
cond_resched();
goto retry;
} else if (err != -ENOENT) {
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false,
+ STOP_CP_REASON_UPDATE_INODE);
}
return;
}
diff --git a/fs/f2fs/iostat.c b/fs/f2fs/iostat.c
index d84c5f6cc09d..3166a8939ed4 100644
--- a/fs/f2fs/iostat.c
+++ b/fs/f2fs/iostat.c
@@ -31,55 +31,65 @@ int __maybe_unused iostat_info_seq_show(struct seq_file *seq, void *offset)
/* print app write IOs */
seq_puts(seq, "[WRITE]\n");
- seq_printf(seq, "app buffered: %-16llu\n",
+ seq_printf(seq, "app buffered data: %-16llu\n",
sbi->rw_iostat[APP_BUFFERED_IO]);
- seq_printf(seq, "app direct: %-16llu\n",
+ seq_printf(seq, "app direct data: %-16llu\n",
sbi->rw_iostat[APP_DIRECT_IO]);
- seq_printf(seq, "app mapped: %-16llu\n",
+ seq_printf(seq, "app mapped data: %-16llu\n",
sbi->rw_iostat[APP_MAPPED_IO]);
+ seq_printf(seq, "app buffered cdata: %-16llu\n",
+ sbi->rw_iostat[APP_BUFFERED_CDATA_IO]);
+ seq_printf(seq, "app mapped cdata: %-16llu\n",
+ sbi->rw_iostat[APP_MAPPED_CDATA_IO]);
/* print fs write IOs */
- seq_printf(seq, "fs data: %-16llu\n",
+ seq_printf(seq, "fs data: %-16llu\n",
sbi->rw_iostat[FS_DATA_IO]);
- seq_printf(seq, "fs node: %-16llu\n",
+ seq_printf(seq, "fs cdata: %-16llu\n",
+ sbi->rw_iostat[FS_CDATA_IO]);
+ seq_printf(seq, "fs node: %-16llu\n",
sbi->rw_iostat[FS_NODE_IO]);
- seq_printf(seq, "fs meta: %-16llu\n",
+ seq_printf(seq, "fs meta: %-16llu\n",
sbi->rw_iostat[FS_META_IO]);
- seq_printf(seq, "fs gc data: %-16llu\n",
+ seq_printf(seq, "fs gc data: %-16llu\n",
sbi->rw_iostat[FS_GC_DATA_IO]);
- seq_printf(seq, "fs gc node: %-16llu\n",
+ seq_printf(seq, "fs gc node: %-16llu\n",
sbi->rw_iostat[FS_GC_NODE_IO]);
- seq_printf(seq, "fs cp data: %-16llu\n",
+ seq_printf(seq, "fs cp data: %-16llu\n",
sbi->rw_iostat[FS_CP_DATA_IO]);
- seq_printf(seq, "fs cp node: %-16llu\n",
+ seq_printf(seq, "fs cp node: %-16llu\n",
sbi->rw_iostat[FS_CP_NODE_IO]);
- seq_printf(seq, "fs cp meta: %-16llu\n",
+ seq_printf(seq, "fs cp meta: %-16llu\n",
sbi->rw_iostat[FS_CP_META_IO]);
/* print app read IOs */
seq_puts(seq, "[READ]\n");
- seq_printf(seq, "app buffered: %-16llu\n",
+ seq_printf(seq, "app buffered data: %-16llu\n",
sbi->rw_iostat[APP_BUFFERED_READ_IO]);
- seq_printf(seq, "app direct: %-16llu\n",
+ seq_printf(seq, "app direct data: %-16llu\n",
sbi->rw_iostat[APP_DIRECT_READ_IO]);
- seq_printf(seq, "app mapped: %-16llu\n",
+ seq_printf(seq, "app mapped data: %-16llu\n",
sbi->rw_iostat[APP_MAPPED_READ_IO]);
+ seq_printf(seq, "app buffered cdata: %-16llu\n",
+ sbi->rw_iostat[APP_BUFFERED_CDATA_READ_IO]);
+ seq_printf(seq, "app mapped cdata: %-16llu\n",
+ sbi->rw_iostat[APP_MAPPED_CDATA_READ_IO]);
/* print fs read IOs */
- seq_printf(seq, "fs data: %-16llu\n",
+ seq_printf(seq, "fs data: %-16llu\n",
sbi->rw_iostat[FS_DATA_READ_IO]);
- seq_printf(seq, "fs gc data: %-16llu\n",
+ seq_printf(seq, "fs gc data: %-16llu\n",
sbi->rw_iostat[FS_GDATA_READ_IO]);
- seq_printf(seq, "fs compr_data: %-16llu\n",
+ seq_printf(seq, "fs cdata: %-16llu\n",
sbi->rw_iostat[FS_CDATA_READ_IO]);
- seq_printf(seq, "fs node: %-16llu\n",
+ seq_printf(seq, "fs node: %-16llu\n",
sbi->rw_iostat[FS_NODE_READ_IO]);
- seq_printf(seq, "fs meta: %-16llu\n",
+ seq_printf(seq, "fs meta: %-16llu\n",
sbi->rw_iostat[FS_META_READ_IO]);
/* print other IOs */
seq_puts(seq, "[OTHER]\n");
- seq_printf(seq, "fs discard: %-16llu\n",
+ seq_printf(seq, "fs discard: %-16llu\n",
sbi->rw_iostat[FS_DISCARD]);
return 0;
@@ -159,7 +169,7 @@ void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
spin_unlock_irq(&sbi->iostat_lat_lock);
}
-void f2fs_update_iostat(struct f2fs_sb_info *sbi,
+void f2fs_update_iostat(struct f2fs_sb_info *sbi, struct inode *inode,
enum iostat_type type, unsigned long long io_bytes)
{
unsigned long flags;
@@ -176,6 +186,28 @@ void f2fs_update_iostat(struct f2fs_sb_info *sbi,
if (type == APP_BUFFERED_READ_IO || type == APP_DIRECT_READ_IO)
sbi->rw_iostat[APP_READ_IO] += io_bytes;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (inode && f2fs_compressed_file(inode)) {
+ if (type == APP_BUFFERED_IO)
+ sbi->rw_iostat[APP_BUFFERED_CDATA_IO] += io_bytes;
+
+ if (type == APP_BUFFERED_READ_IO)
+ sbi->rw_iostat[APP_BUFFERED_CDATA_READ_IO] += io_bytes;
+
+ if (type == APP_MAPPED_READ_IO)
+ sbi->rw_iostat[APP_MAPPED_CDATA_READ_IO] += io_bytes;
+
+ if (type == APP_MAPPED_IO)
+ sbi->rw_iostat[APP_MAPPED_CDATA_IO] += io_bytes;
+
+ if (type == FS_DATA_READ_IO)
+ sbi->rw_iostat[FS_CDATA_READ_IO] += io_bytes;
+
+ if (type == FS_DATA_IO)
+ sbi->rw_iostat[FS_CDATA_IO] += io_bytes;
+ }
+#endif
+
spin_unlock_irqrestore(&sbi->iostat_lock, flags);
f2fs_record_iostat(sbi);
diff --git a/fs/f2fs/iostat.h b/fs/f2fs/iostat.h
index 22a2d01f57ef..2c048307b6e0 100644
--- a/fs/f2fs/iostat.h
+++ b/fs/f2fs/iostat.h
@@ -31,7 +31,7 @@ struct iostat_lat_info {
extern int __maybe_unused iostat_info_seq_show(struct seq_file *seq,
void *offset);
extern void f2fs_reset_iostat(struct f2fs_sb_info *sbi);
-extern void f2fs_update_iostat(struct f2fs_sb_info *sbi,
+extern void f2fs_update_iostat(struct f2fs_sb_info *sbi, struct inode *inode,
enum iostat_type type, unsigned long long io_bytes);
struct bio_iostat_ctx {
@@ -65,7 +65,7 @@ extern void f2fs_destroy_iostat_processing(void);
extern int f2fs_init_iostat(struct f2fs_sb_info *sbi);
extern void f2fs_destroy_iostat(struct f2fs_sb_info *sbi);
#else
-static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
+static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, struct inode *inode,
enum iostat_type type, unsigned long long io_bytes) {}
static inline void iostat_update_and_unbind_ctx(struct bio *bio, int rw) {}
static inline void iostat_alloc_and_bind_ctx(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index e06a0c478b39..983572f23896 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -36,6 +36,7 @@ int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: out-of-range nid=%x, run fsck to fix.",
__func__, nid);
+ f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
return -EFSCORRUPTED;
}
return 0;
@@ -585,7 +586,7 @@ retry:
ne = nat_in_journal(journal, i);
node_info_from_raw_nat(ni, &ne);
}
- up_read(&curseg->journal_rwsem);
+ up_read(&curseg->journal_rwsem);
if (i >= 0) {
f2fs_up_read(&nm_i->nat_tree_lock);
goto cache;
@@ -1295,6 +1296,7 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
if (unlikely(new_ni.blk_addr != NULL_ADDR)) {
err = -EFSCORRUPTED;
set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto fail;
}
#endif
@@ -1369,7 +1371,7 @@ static int read_node_page(struct page *page, blk_opf_t op_flags)
err = f2fs_submit_page_bio(&fio);
if (!err)
- f2fs_update_iostat(sbi, FS_NODE_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, NULL, FS_NODE_READ_IO, F2FS_BLKSIZE);
return err;
}
@@ -2147,8 +2149,7 @@ static bool f2fs_dirty_node_folio(struct address_space *mapping,
if (IS_INODE(&folio->page))
f2fs_inode_chksum_set(F2FS_M_SB(mapping), &folio->page);
#endif
- if (!folio_test_dirty(folio)) {
- filemap_dirty_folio(mapping, folio);
+ if (filemap_dirty_folio(mapping, folio)) {
inc_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES);
set_page_private_reference(&folio->page);
return true;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index dcd0a1e35095..dea95b48b647 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -474,7 +474,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
struct dnode_of_data tdn = *dn;
nid_t ino, nid;
struct inode *inode;
- unsigned int offset;
+ unsigned int offset, ofs_in_node, max_addrs;
block_t bidx;
int i;
@@ -501,15 +501,25 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
got_it:
/* Use the locked dnode page and inode */
nid = le32_to_cpu(sum.nid);
+ ofs_in_node = le16_to_cpu(sum.ofs_in_node);
+
+ max_addrs = ADDRS_PER_PAGE(dn->node_page, dn->inode);
+ if (ofs_in_node >= max_addrs) {
+ f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%lu, nid:%u, max:%u",
+ ofs_in_node, dn->inode->i_ino, nid, max_addrs);
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_SUMMARY);
+ return -EFSCORRUPTED;
+ }
+
if (dn->inode->i_ino == nid) {
tdn.nid = nid;
if (!dn->inode_page_locked)
lock_page(dn->inode_page);
tdn.node_page = dn->inode_page;
- tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
+ tdn.ofs_in_node = ofs_in_node;
goto truncate_out;
} else if (dn->nid == nid) {
- tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
+ tdn.ofs_in_node = ofs_in_node;
goto truncate_out;
}
@@ -628,6 +638,7 @@ retry_dn:
inode->i_ino, ofs_of_node(dn.node_page),
ofs_of_node(page));
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER);
goto err;
}
@@ -640,12 +651,14 @@ retry_dn:
if (__is_valid_data_blkaddr(src) &&
!f2fs_is_valid_blkaddr(sbi, src, META_POR)) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto err;
}
if (__is_valid_data_blkaddr(dest) &&
!f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto err;
}
@@ -698,6 +711,16 @@ retry_prev:
goto err;
}
+ if (f2fs_is_valid_blkaddr(sbi, dest,
+ DATA_GENERIC_ENHANCE_UPDATE)) {
+ f2fs_err(sbi, "Inconsistent dest blkaddr:%u, ino:%lu, ofs:%u",
+ dest, inode->i_ino, dn.ofs_in_node);
+ err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi,
+ ERROR_INVALID_BLKADDR);
+ goto err;
+ }
+
/* write dummy data page */
f2fs_replace_block(sbi, &dn, src, dest,
ni.version, false, false);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 0de21f82d7bc..289bcb7ca300 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -187,7 +187,6 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
void f2fs_abort_atomic_write(struct inode *inode, bool clean)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
if (!f2fs_is_atomic_file(inode))
@@ -200,10 +199,7 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
fi->cow_inode = NULL;
release_atomic_write_cnt(inode);
clear_inode_flag(inode, FI_ATOMIC_FILE);
-
- spin_lock(&sbi->inode_lock[ATOMIC_FILE]);
- sbi->atomic_files--;
- spin_unlock(&sbi->inode_lock[ATOMIC_FILE]);
+ stat_dec_atomic_inode(inode);
}
static int __replace_atomic_write_block(struct inode *inode, pgoff_t index,
@@ -312,6 +308,8 @@ static int __f2fs_commit_atomic_write(struct inode *inode)
DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
ret = -EFSCORRUPTED;
+ f2fs_handle_error(sbi,
+ ERROR_INVALID_BLKADDR);
goto out;
}
@@ -376,7 +374,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
f2fs_show_injection_info(sbi, FAULT_CHECKPOINT);
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_FAULT_INJECT);
}
/* balance_fs_bg is able to be pending */
@@ -476,12 +474,12 @@ do_sync:
mutex_lock(&sbi->flush_lock);
blk_start_plug(&plug);
- f2fs_sync_dirty_inodes(sbi, FILE_INODE);
+ f2fs_sync_dirty_inodes(sbi, FILE_INODE, false);
blk_finish_plug(&plug);
mutex_unlock(&sbi->flush_lock);
}
- f2fs_sync_fs(sbi->sb, true);
+ f2fs_sync_fs(sbi->sb, 1);
stat_inc_bg_cp_count(sbi->stat_info);
}
@@ -694,7 +692,8 @@ int f2fs_flush_device_cache(struct f2fs_sb_info *sbi)
} while (ret && --count);
if (ret) {
- f2fs_stop_checkpoint(sbi, false);
+ f2fs_stop_checkpoint(sbi, false,
+ STOP_CP_REASON_FLUSH_FAIL);
break;
}
@@ -1171,7 +1170,7 @@ submit:
atomic_inc(&dcc->issued_discard);
- f2fs_update_iostat(sbi, FS_DISCARD, 1);
+ f2fs_update_iostat(sbi, NULL, FS_DISCARD, 1);
lstart += len;
start += len;
@@ -3388,7 +3387,7 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
f2fs_submit_page_write(&fio);
stat_inc_meta_count(sbi, page->index);
- f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, NULL, io_type, F2FS_BLKSIZE);
}
void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio)
@@ -3398,7 +3397,7 @@ void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio)
set_summary(&sum, nid, 0, 0);
do_write_page(&sum, fio);
- f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
+ f2fs_update_iostat(fio->sbi, NULL, fio->io_type, F2FS_BLKSIZE);
}
void f2fs_outplace_write_data(struct dnode_of_data *dn,
@@ -3412,7 +3411,7 @@ void f2fs_outplace_write_data(struct dnode_of_data *dn,
do_write_page(&sum, fio);
f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
- f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, dn->inode, fio->io_type, F2FS_BLKSIZE);
}
int f2fs_inplace_write_data(struct f2fs_io_info *fio)
@@ -3432,6 +3431,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
f2fs_warn(sbi, "%s: incorrect segment(%u) type, run fsck to fix.",
__func__, segno);
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_SUM_TYPE);
goto drop_bio;
}
@@ -3453,7 +3453,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
if (!err) {
f2fs_update_device_state(fio->sbi, fio->ino,
fio->new_blkaddr, 1);
- f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
+ f2fs_update_iostat(fio->sbi, fio->page->mapping->host,
+ fio->io_type, F2FS_BLKSIZE);
}
return err;
@@ -4379,6 +4380,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
if (se->type >= NR_PERSISTENT_LOG) {
f2fs_err(sbi, "Invalid segment type: %u, segno: %u",
se->type, start);
+ f2fs_handle_error(sbi,
+ ERROR_INCONSISTENT_SUM_TYPE);
return -EFSCORRUPTED;
}
@@ -4415,6 +4418,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
f2fs_err(sbi, "Wrong journal entry on segno %u",
start);
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_CORRUPTED_JOURNAL);
break;
}
@@ -4434,6 +4438,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
f2fs_err(sbi, "Invalid segment type: %u, segno: %u",
se->type, start);
err = -EFSCORRUPTED;
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_SUM_TYPE);
break;
}
@@ -4465,6 +4470,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
if (sit_valid_blocks[NODE] != valid_node_count(sbi)) {
f2fs_err(sbi, "SIT is corrupted node# %u vs %u",
sit_valid_blocks[NODE], valid_node_count(sbi));
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_NODE_COUNT);
return -EFSCORRUPTED;
}
@@ -4473,6 +4479,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
f2fs_err(sbi, "SIT is corrupted data# %u %u vs %u",
sit_valid_blocks[DATA], sit_valid_blocks[NODE],
valid_user_blocks(sbi));
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_BLOCK_COUNT);
return -EFSCORRUPTED;
}
@@ -4623,6 +4630,7 @@ static int sanity_check_curseg(struct f2fs_sb_info *sbi)
f2fs_err(sbi,
"Current segment has invalid alloc_type:%d",
curseg->alloc_type);
+ f2fs_handle_error(sbi, ERROR_INVALID_CURSEG);
return -EFSCORRUPTED;
}
@@ -4640,6 +4648,7 @@ out:
"Current segment's next free block offset is inconsistent with bitmap, logtype:%u, segno:%u, type:%u, next_blkoff:%u, blkofs:%u",
i, curseg->segno, curseg->alloc_type,
curseg->next_blkoff, blkofs);
+ f2fs_handle_error(sbi, ERROR_INVALID_CURSEG);
return -EFSCORRUPTED;
}
}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index d1d63766f2c7..be8f2d7d007b 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -753,6 +753,7 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
f2fs_err(sbi, "Mismatch valid blocks %d vs. %d",
GET_SIT_VBLOCKS(raw_sit), valid_blocks);
set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_SIT);
return -EFSCORRUPTED;
}
@@ -767,6 +768,7 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
f2fs_err(sbi, "Wrong valid blocks %d or segno %u",
GET_SIT_VBLOCKS(raw_sit), segno);
set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_SIT);
return -EFSCORRUPTED;
}
return 0;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 26817b5aeac7..3834ead04620 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -301,10 +301,10 @@ static void f2fs_destroy_casefold_cache(void) { }
static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
{
- block_t limit = min((sbi->user_block_count << 1) / 1000,
+ block_t limit = min((sbi->user_block_count >> 3),
sbi->user_block_count - sbi->reserved_blocks);
- /* limit is 0.2% */
+ /* limit is 12.5% */
if (test_opt(sbi, RESERVE_ROOT) &&
F2FS_OPTION(sbi).root_reserved_blocks > limit) {
F2FS_OPTION(sbi).root_reserved_blocks = limit;
@@ -1342,6 +1342,11 @@ default_check:
return -EINVAL;
}
+ if (test_opt(sbi, ATGC) && f2fs_lfs_mode(sbi)) {
+ f2fs_err(sbi, "LFS not compatible with ATGC");
+ return -EINVAL;
+ }
+
if (f2fs_sb_has_readonly(sbi) && !f2fs_readonly(sbi->sb)) {
f2fs_err(sbi, "Allow to mount readonly mode only");
return -EROFS;
@@ -1666,9 +1671,8 @@ static int f2fs_freeze(struct super_block *sb)
if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY))
return -EINVAL;
- /* ensure no checkpoint required */
- if (!llist_empty(&F2FS_SB(sb)->cprc_info.issue_list))
- return -EINVAL;
+ /* Let's flush checkpoints and stop the thread. */
+ f2fs_flush_ckpt_thread(F2FS_SB(sb));
/* to avoid deadlock on f2fs_evict_inode->SB_FREEZE_FS */
set_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING);
@@ -2181,6 +2185,9 @@ static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi)
f2fs_up_write(&sbi->gc_lock);
f2fs_sync_fs(sbi->sb, 1);
+
+ /* Let's ensure there's no pending checkpoint anymore */
+ f2fs_flush_ckpt_thread(sbi);
}
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
@@ -2346,6 +2353,9 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
f2fs_stop_ckpt_thread(sbi);
need_restart_ckpt = true;
} else {
+ /* Flush if the prevous checkpoint, if exists. */
+ f2fs_flush_ckpt_thread(sbi);
+
err = f2fs_start_ckpt_thread(sbi);
if (err) {
f2fs_err(sbi,
@@ -2465,7 +2475,6 @@ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data,
size_t toread;
loff_t i_size = i_size_read(inode);
struct page *page;
- char *kaddr;
if (off > i_size)
return 0;
@@ -2498,9 +2507,7 @@ repeat:
return -EIO;
}
- kaddr = kmap_atomic(page);
- memcpy(data, kaddr + offset, tocopy);
- kunmap_atomic(kaddr);
+ memcpy_from_page(data, page, offset, tocopy);
f2fs_put_page(page, 1);
offset = 0;
@@ -2522,7 +2529,6 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
size_t towrite = len;
struct page *page;
void *fsdata = NULL;
- char *kaddr;
int err = 0;
int tocopy;
@@ -2541,10 +2547,7 @@ retry:
break;
}
- kaddr = kmap_atomic(page);
- memcpy(kaddr + offset, data, tocopy);
- kunmap_atomic(kaddr);
- flush_dcache_page(page);
+ memcpy_to_page(page, offset, data, tocopy);
a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
page, fsdata);
@@ -3843,6 +3846,68 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
return err;
}
+void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason)
+{
+ struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+ int err;
+
+ f2fs_down_write(&sbi->sb_lock);
+
+ if (raw_super->s_stop_reason[reason] < ((1 << BITS_PER_BYTE) - 1))
+ raw_super->s_stop_reason[reason]++;
+
+ err = f2fs_commit_super(sbi, false);
+ if (err)
+ f2fs_err(sbi, "f2fs_commit_super fails to record reason:%u err:%d",
+ reason, err);
+ f2fs_up_write(&sbi->sb_lock);
+}
+
+static void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag)
+{
+ spin_lock(&sbi->error_lock);
+ if (!test_bit(flag, (unsigned long *)sbi->errors)) {
+ set_bit(flag, (unsigned long *)sbi->errors);
+ sbi->error_dirty = true;
+ }
+ spin_unlock(&sbi->error_lock);
+}
+
+static bool f2fs_update_errors(struct f2fs_sb_info *sbi)
+{
+ bool need_update = false;
+
+ spin_lock(&sbi->error_lock);
+ if (sbi->error_dirty) {
+ memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors,
+ MAX_F2FS_ERRORS);
+ sbi->error_dirty = false;
+ need_update = true;
+ }
+ spin_unlock(&sbi->error_lock);
+
+ return need_update;
+}
+
+void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error)
+{
+ int err;
+
+ f2fs_save_errors(sbi, error);
+
+ f2fs_down_write(&sbi->sb_lock);
+
+ if (!f2fs_update_errors(sbi))
+ goto out_unlock;
+
+ err = f2fs_commit_super(sbi, false);
+ if (err)
+ f2fs_err(sbi, "f2fs_commit_super fails to record errors:%u, err:%d",
+ error, err);
+out_unlock:
+ f2fs_up_write(&sbi->sb_lock);
+}
+
static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -4190,6 +4255,9 @@ try_onemore:
goto free_devices;
}
+ spin_lock_init(&sbi->error_lock);
+ memcpy(sbi->errors, raw_super->s_errors, MAX_F2FS_ERRORS);
+
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
percpu_counter_set(&sbi->total_valid_inode_count,
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index eba5fb1629d7..df27afd71ef4 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -128,6 +128,12 @@ static ssize_t sb_status_show(struct f2fs_attr *a,
return sprintf(buf, "%lx\n", sbi->s_flag);
}
+static ssize_t cp_status_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ return sprintf(buf, "%x\n", le32_to_cpu(F2FS_CKPT(sbi)->ckpt_flags));
+}
+
static ssize_t pending_discard_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -527,7 +533,6 @@ out:
if (!strcmp(a->attr.name, "gc_urgent_high_remaining")) {
spin_lock(&sbi->gc_urgent_high_lock);
- sbi->gc_urgent_high_limited = t != 0;
sbi->gc_urgent_high_remaining = t;
spin_unlock(&sbi->gc_urgent_high_lock);
@@ -1030,8 +1035,10 @@ static struct attribute *f2fs_feat_attrs[] = {
ATTRIBUTE_GROUPS(f2fs_feat);
F2FS_GENERAL_RO_ATTR(sb_status);
+F2FS_GENERAL_RO_ATTR(cp_status);
static struct attribute *f2fs_stat_attrs[] = {
ATTR_LIST(sb_status),
+ ATTR_LIST(cp_status),
NULL,
};
ATTRIBUTE_GROUPS(f2fs_stat);
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 7b8f2b41c29b..f0805e51b3fe 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -47,16 +47,13 @@ static int pagecache_read(struct inode *inode, void *buf, size_t count,
size_t n = min_t(size_t, count,
PAGE_SIZE - offset_in_page(pos));
struct page *page;
- void *addr;
page = read_mapping_page(inode->i_mapping, pos >> PAGE_SHIFT,
NULL);
if (IS_ERR(page))
return PTR_ERR(page);
- addr = kmap_atomic(page);
- memcpy(buf, addr + offset_in_page(pos), n);
- kunmap_atomic(addr);
+ memcpy_from_page(buf, page, offset_in_page(pos), n);
put_page(page);
@@ -85,16 +82,13 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count,
PAGE_SIZE - offset_in_page(pos));
struct page *page;
void *fsdata;
- void *addr;
int res;
res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata);
if (res)
return res;
- addr = kmap_atomic(page);
- memcpy(addr + offset_in_page(pos), buf, n);
- kunmap_atomic(addr);
+ memcpy_to_page(page, offset_in_page(pos), buf, n);
res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata);
if (res < 0)
@@ -246,6 +240,8 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
if (pos + size < pos || pos + size > inode->i_sb->s_maxbytes ||
pos < f2fs_verity_metadata_pos(inode) || size > INT_MAX) {
f2fs_warn(F2FS_I_SB(inode), "invalid verity xattr");
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_CORRUPTED_VERITY_XATTR);
return -EFSCORRUPTED;
}
if (buf_size) {
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index c76c15086e5f..dc2e8637189e 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -367,6 +367,8 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
inode->i_ino);
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
err = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_CORRUPTED_XATTR);
goto out;
}
check:
@@ -583,6 +585,8 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
inode->i_ino);
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
error = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_CORRUPTED_XATTR);
goto cleanup;
}
@@ -658,6 +662,8 @@ static int __f2fs_setxattr(struct inode *inode, int index,
inode->i_ino);
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
error = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_CORRUPTED_XATTR);
goto exit;
}
@@ -684,6 +690,8 @@ static int __f2fs_setxattr(struct inode *inode, int index,
inode->i_ino, ENTRY_SIZE(last));
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
error = -EFSCORRUPTED;
+ f2fs_handle_error(F2FS_I_SB(inode),
+ ERROR_CORRUPTED_XATTR);
goto exit;
}
last = XATTR_NEXT_ENTRY(last);