f2fs: updates on v4.16-rc1
Pull f2fs updates from Jaegeuk Kim:
"In this round, we've followed up to support some generic features such
as cgroup, block reservation, linking fscrypt_ops, delivering
write_hints, and some ioctls. And, we could fix some corner cases in
terms of power-cut recovery and subtle deadlocks.
Enhancements:
- bitmap operations to handle NAT blocks
- readahead to improve readdir speed
- switch to use fscrypt_*
- apply write hints for direct IO
- add reserve_root=%u,resuid=%u,resgid=%u to reserve blocks for root/uid/gid
- modify b_avail and b_free to consider root reserved blocks
- support cgroup writeback
- support FIEMAP_FLAG_XATTR for fibmap
- add F2FS_IOC_PRECACHE_EXTENTS to pre-cache extents
- add F2FS_IOC_{GET/SET}_PIN_FILE to pin LBAs for data blocks
- support inode creation time
Bug fixs:
- sysfile-based quota operations
- memory footprint accounting
- allow to write data on partial preallocation case
- fix deadlock case on fallocate
- fix to handle fill_super errors
- fix missing inode updates of fsync'ed file
- recover renamed file which was fsycn'ed before
- drop inmemory pages in corner error case
- keep last_disk_size correctly
- recover missing i_inline flags during roll-forward
Various clean-up patches were added as well"
Cherry-pick from origin/upstream-f2fs-stable-linux-4.9.y:
71f8f0499e8b f2fs: support inode creation time
58dc6f6fcef7 f2fs: rebuild sit page from sit info in mem
6393cef3f112 f2fs: stop issuing discard if fs is readonly
742bc90e88fa f2fs: clean up duplicated assignment in init_discard_policy
cfabb6edfbc2 f2fs: use GFP_F2FS_ZERO for cleanup
111e8456a697 f2fs: allow to recover node blocks given updated checkpoint
36e041a57ccf f2fs: recover some i_inline flags
3127a7b67ca8 f2fs: correct removexattr behavior for null valued extended attribute
86f78c1e5523 f2fs: drop page cache after fs shutdown
1a3b0047597c f2fs: stop gc/discard thread after fs shutdown
62a91a5a489f f2fs: hanlde error case in f2fs_ioc_shutdown
66356ee5f94c f2fs: split need_inplace_update
5912fbae9da5 f2fs: fix to update last_disk_size correctly
3aa46e2c2187 f2fs: kill F2FS_INLINE_XATTR_ADDRS for cleanup
acdaca27aacb f2fs: clean up error path of fill_super
cf8821115c54 f2fs: avoid hungtask when GC encrypted block if io_bits is set
4be98c9805e4 f2fs: allow quota to use reserved blocks
2a6489c87ee0 f2fs: fix to drop all inmem pages correctly
fd214422395f f2fs: speed up defragment on sparse file
6bce96329c85 f2fs: support F2FS_IOC_PRECACHE_EXTENTS
9ce3d6bb6883 f2fs: add an ioctl to disable GC for specific file
9ef5e6568449 f2fs: prevent newly created inode from being dirtied incorrectly
08ddb1917e04 f2fs: support FIEMAP_FLAG_XATTR
aa9c1c1046e0 f2fs: fix to cover f2fs_inline_data_fiemap with inode_lock
92b8f9c726ef f2fs: check node page again in write end io
4992a3ca15b3 f2fs: fix to caclulate required free section correctly
d1a6b4f6c958 f2fs: handle newly created page when revoking inmem pages
462d762b205a f2fs: add resgid and resuid to reserve root blocks
cbd5e5af8cac f2fs: implement cgroup writeback support
5a5847421d31 f2fs: remove unused pend_list_tag
37d4ca7cd1c1 f2fs: avoid high cpu usage in discard thread
02cfdab8344f f2fs: make local functions static
5fee54098565 f2fs: add reserved blocks for root user
265974636ae0 f2fs: check segment type in __f2fs_replace_block
4f76d6acc6ff f2fs: update inode info to inode page for new file
52b452817452 f2fs: show precise # of blocks that user/root can use
ae0e1fa5a816 f2fs: clean up unneeded declaration
8fc74466298f f2fs: continue to do direct IO if we only preallocate partial blocks
162464df894e f2fs: enable quota at remount from r to w
e270976ff848 f2fs: skip stop_checkpoint for user data writes
d04736926fa7 f2fs: fix missing error number for xattr operation
211cb7bb2428 f2fs: recover directory operations by fsync
2648e735ffe5 f2fs: return error during fill_super
e2a0518d8c24 f2fs: fix an error case of missing update inode page
bf1750bafe86 f2fs: fix potential hangtask in f2fs_trace_pid
c804fcf3df1f f2fs: no need return value in restore summary process
fdd41a8793ad f2fs: use unlikely for release case
a74690b03e24 f2fs: don't return value in truncate_data_blocks_range
987892cc67aa f2fs: clean up f2fs_map_blocks
d7714cb2319a f2fs: clean up hash codes
e3d2a1e946df f2fs: fix error handling in fill_super
b02e72d2942c f2fs: spread f2fs_k{m,z}alloc
ead5259de34d f2fs: inject fault to kvmalloc
e585ca29dd7e f2fs: inject fault to kzalloc
8234ed56e748 f2fs: remove a redundant conditional expression
1a9d6a9c0046 f2fs: apply write hints to select the type of segment for direct write
955e7f58f67b f2fs: switch to fscrypt_prepare_setattr()
268c7f607cb8 f2fs: switch to fscrypt_prepare_lookup()
8dfa646f972c f2fs: switch to fscrypt_prepare_rename()
d5382ccb020a f2fs: switch to fscrypt_prepare_link()
3ccc177c9b8b f2fs: switch to fscrypt_file_open()
8b5674efdc35 f2fs: remove repeated f2fs_bug_on
ba4556cdf10c f2fs: remove an excess variable
46accc925145 f2fs: fix lock dependency in between dio_rwsem & i_mmap_sem
8933908c4f93 f2fs: remove unused parameter
76b6e8ed2058 f2fs: still write data if preallocate only partial blocks
1ed753392fe7 f2fs: introduce sysfs readdir_ra to readahead inode block in readdir
4e68a15eeebc f2fs: fix concurrent problem for updating free bitmap
9be6e7596232 f2fs: remove unneeded memory footprint accounting
923df752db37 f2fs: no need to read nat block if nat_block_bitmap is set
09234be262cb f2fs: reserve nid resource for quota sysfile
Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 0abe694..cc34d88 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -248,7 +248,11 @@
goto next;
}
get_node_info(sbi, dn.nid, &ni);
- f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+ if (cur->old_addr == NEW_ADDR) {
+ invalidate_blocks(sbi, dn.data_blkaddr);
+ f2fs_update_data_blkaddr(&dn, NEW_ADDR);
+ } else
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
cur->old_addr, ni.version, true, true);
f2fs_put_dnode(&dn);
}
@@ -657,7 +661,7 @@
goto init_thread;
}
- fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
+ fcc = f2fs_kzalloc(sbi, sizeof(struct flush_cmd_control), GFP_KERNEL);
if (!fcc)
return -ENOMEM;
atomic_set(&fcc->issued_flush, 0);
@@ -884,7 +888,7 @@
bio_put(bio);
}
-void __check_sit_bitmap(struct f2fs_sb_info *sbi,
+static void __check_sit_bitmap(struct f2fs_sb_info *sbi,
block_t start, block_t end)
{
#ifdef CONFIG_F2FS_CHECK_FS
@@ -1204,6 +1208,8 @@
pend_list = &dcc->pend_list[i];
mutex_lock(&dcc->cmd_lock);
+ if (list_empty(pend_list))
+ goto next;
f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
blk_start_plug(&plug);
list_for_each_entry_safe(dc, tmp, pend_list, list) {
@@ -1222,6 +1228,7 @@
break;
}
blk_finish_plug(&plug);
+next:
mutex_unlock(&dcc->cmd_lock);
if (iter >= dpolicy->max_requests)
@@ -1256,6 +1263,11 @@
return dropped;
}
+void drop_discard_cmd(struct f2fs_sb_info *sbi)
+{
+ __drop_discard_cmd(sbi);
+}
+
static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi,
struct discard_cmd *dc)
{
@@ -1324,7 +1336,7 @@
}
/* This should be covered by global mutex, &sit_i->sentry_lock */
-void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
+static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct discard_cmd *dc;
@@ -1394,6 +1406,8 @@
msecs_to_jiffies(wait_ms));
if (try_to_freeze())
continue;
+ if (f2fs_readonly(sbi->sb))
+ continue;
if (kthread_should_stop())
return 0;
@@ -1703,25 +1717,20 @@
dpolicy->sync = true;
dpolicy->granularity = granularity;
+ dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
+ dpolicy->io_aware_gran = MAX_PLIST_NUM;
+
if (discard_type == DPOLICY_BG) {
dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
- dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
- dpolicy->io_aware_gran = MAX_PLIST_NUM;
dpolicy->io_aware = true;
} else if (discard_type == DPOLICY_FORCE) {
dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME;
dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME;
- dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
- dpolicy->io_aware_gran = MAX_PLIST_NUM;
dpolicy->io_aware = true;
} else if (discard_type == DPOLICY_FSTRIM) {
- dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
- dpolicy->io_aware_gran = MAX_PLIST_NUM;
dpolicy->io_aware = false;
} else if (discard_type == DPOLICY_UMOUNT) {
- dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST;
- dpolicy->io_aware_gran = MAX_PLIST_NUM;
dpolicy->io_aware = false;
}
}
@@ -1737,7 +1746,7 @@
goto init_thread;
}
- dcc = kzalloc(sizeof(struct discard_cmd_control), GFP_KERNEL);
+ dcc = f2fs_kzalloc(sbi, sizeof(struct discard_cmd_control), GFP_KERNEL);
if (!dcc)
return -ENOMEM;
@@ -2434,7 +2443,6 @@
return false;
}
-#if 0
int rw_hint_to_seg_type(enum rw_hint hint)
{
switch (hint) {
@@ -2446,7 +2454,6 @@
return CURSEG_WARM_DATA;
}
}
-#endif
static int __get_segment_type_2(struct f2fs_io_info *fio)
{
@@ -2742,6 +2749,7 @@
}
}
+ f2fs_bug_on(sbi, !IS_DATASEG(type));
curseg = CURSEG_I(sbi, type);
mutex_lock(&curseg->curseg_mutex);
@@ -2826,7 +2834,7 @@
}
}
-static int read_compacted_summaries(struct f2fs_sb_info *sbi)
+static void read_compacted_summaries(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct curseg_info *seg_i;
@@ -2883,7 +2891,6 @@
}
}
f2fs_put_page(page, 1);
- return 0;
}
static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
@@ -2929,13 +2936,7 @@
ns->ofs_in_node = 0;
}
} else {
- int err;
-
- err = restore_node_summary(sbi, segno, sum);
- if (err) {
- f2fs_put_page(new, 1);
- return err;
- }
+ restore_node_summary(sbi, segno, sum);
}
}
@@ -2974,8 +2975,7 @@
META_CP, true);
/* restore for compacted data summary */
- if (read_compacted_summaries(sbi))
- return -EINVAL;
+ read_compacted_summaries(sbi);
type = CURSEG_HOT_NODE;
}
@@ -3111,28 +3111,19 @@
unsigned int start)
{
struct sit_info *sit_i = SIT_I(sbi);
- struct page *src_page, *dst_page;
+ struct page *page;
pgoff_t src_off, dst_off;
- void *src_addr, *dst_addr;
src_off = current_sit_addr(sbi, start);
dst_off = next_sit_addr(sbi, src_off);
- /* get current sit block page without lock */
- src_page = get_meta_page(sbi, src_off);
- dst_page = grab_meta_page(sbi, dst_off);
- f2fs_bug_on(sbi, PageDirty(src_page));
+ page = grab_meta_page(sbi, dst_off);
+ seg_info_to_sit_page(sbi, page, start);
- src_addr = page_address(src_page);
- dst_addr = page_address(dst_page);
- memcpy(dst_addr, src_addr, PAGE_SIZE);
-
- set_page_dirty(dst_page);
- f2fs_put_page(src_page, 1);
-
+ set_page_dirty(page);
set_to_next_sit(sit_i, start);
- return dst_page;
+ return page;
}
static struct sit_entry_set *grab_sit_entry_set(void)
@@ -3341,52 +3332,54 @@
unsigned int bitmap_size;
/* allocate memory for SIT information */
- sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL);
+ sit_i = f2fs_kzalloc(sbi, sizeof(struct sit_info), GFP_KERNEL);
if (!sit_i)
return -ENOMEM;
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = kvzalloc(MAIN_SEGS(sbi) *
+ sit_i->sentries = f2fs_kvzalloc(sbi, MAIN_SEGS(sbi) *
sizeof(struct seg_entry), GFP_KERNEL);
if (!sit_i->sentries)
return -ENOMEM;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- sit_i->dirty_sentries_bitmap = kvzalloc(bitmap_size, GFP_KERNEL);
+ sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, bitmap_size,
+ GFP_KERNEL);
if (!sit_i->dirty_sentries_bitmap)
return -ENOMEM;
for (start = 0; start < MAIN_SEGS(sbi); start++) {
sit_i->sentries[start].cur_valid_map
- = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
sit_i->sentries[start].ckpt_valid_map
- = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
if (!sit_i->sentries[start].cur_valid_map ||
!sit_i->sentries[start].ckpt_valid_map)
return -ENOMEM;
#ifdef CONFIG_F2FS_CHECK_FS
sit_i->sentries[start].cur_valid_map_mir
- = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
if (!sit_i->sentries[start].cur_valid_map_mir)
return -ENOMEM;
#endif
if (f2fs_discard_en(sbi)) {
sit_i->sentries[start].discard_map
- = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE,
+ GFP_KERNEL);
if (!sit_i->sentries[start].discard_map)
return -ENOMEM;
}
}
- sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
if (!sit_i->tmp_map)
return -ENOMEM;
if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = kvzalloc(MAIN_SECS(sbi) *
+ sit_i->sec_entries = f2fs_kvzalloc(sbi, MAIN_SECS(sbi) *
sizeof(struct sec_entry), GFP_KERNEL);
if (!sit_i->sec_entries)
return -ENOMEM;
@@ -3430,19 +3423,19 @@
unsigned int bitmap_size, sec_bitmap_size;
/* allocate memory for free segmap information */
- free_i = kzalloc(sizeof(struct free_segmap_info), GFP_KERNEL);
+ free_i = f2fs_kzalloc(sbi, sizeof(struct free_segmap_info), GFP_KERNEL);
if (!free_i)
return -ENOMEM;
SM_I(sbi)->free_info = free_i;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- free_i->free_segmap = kvmalloc(bitmap_size, GFP_KERNEL);
+ free_i->free_segmap = f2fs_kvmalloc(sbi, bitmap_size, GFP_KERNEL);
if (!free_i->free_segmap)
return -ENOMEM;
sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- free_i->free_secmap = kvmalloc(sec_bitmap_size, GFP_KERNEL);
+ free_i->free_secmap = f2fs_kvmalloc(sbi, sec_bitmap_size, GFP_KERNEL);
if (!free_i->free_secmap)
return -ENOMEM;
@@ -3463,7 +3456,7 @@
struct curseg_info *array;
int i;
- array = kcalloc(NR_CURSEG_TYPE, sizeof(*array), GFP_KERNEL);
+ array = f2fs_kzalloc(sbi, sizeof(*array) * NR_CURSEG_TYPE, GFP_KERNEL);
if (!array)
return -ENOMEM;
@@ -3471,12 +3464,12 @@
for (i = 0; i < NR_CURSEG_TYPE; i++) {
mutex_init(&array[i].curseg_mutex);
- array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL);
if (!array[i].sum_blk)
return -ENOMEM;
init_rwsem(&array[i].journal_rwsem);
- array[i].journal = kzalloc(sizeof(struct f2fs_journal),
- GFP_KERNEL);
+ array[i].journal = f2fs_kzalloc(sbi,
+ sizeof(struct f2fs_journal), GFP_KERNEL);
if (!array[i].journal)
return -ENOMEM;
array[i].segno = NULL_SEGNO;
@@ -3485,7 +3478,7 @@
return restore_curseg_summaries(sbi);
}
-static void build_sit_entries(struct f2fs_sb_info *sbi)
+static int build_sit_entries(struct f2fs_sb_info *sbi)
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
@@ -3495,6 +3488,7 @@
int sit_blk_cnt = SIT_BLK_CNT(sbi);
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
+ int err = 0;
do {
readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
@@ -3513,7 +3507,9 @@
sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
f2fs_put_page(page, 1);
- check_block_count(sbi, start, &sit);
+ err = check_block_count(sbi, start, &sit);
+ if (err)
+ return err;
seg_info_from_raw_sit(se, &sit);
/* build discard map only one time */
@@ -3548,7 +3544,9 @@
old_valid_blocks = se->valid_blocks;
- check_block_count(sbi, start, &sit);
+ err = check_block_count(sbi, start, &sit);
+ if (err)
+ break;
seg_info_from_raw_sit(se, &sit);
if (f2fs_discard_en(sbi)) {
@@ -3568,6 +3566,7 @@
se->valid_blocks - old_valid_blocks;
}
up_read(&curseg->journal_rwsem);
+ return err;
}
static void init_free_segmap(struct f2fs_sb_info *sbi)
@@ -3622,7 +3621,7 @@
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- dirty_i->victim_secmap = kvzalloc(bitmap_size, GFP_KERNEL);
+ dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
return -ENOMEM;
return 0;
@@ -3634,7 +3633,8 @@
unsigned int bitmap_size, i;
/* allocate memory for dirty segments list information */
- dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL);
+ dirty_i = f2fs_kzalloc(sbi, sizeof(struct dirty_seglist_info),
+ GFP_KERNEL);
if (!dirty_i)
return -ENOMEM;
@@ -3644,7 +3644,8 @@
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
for (i = 0; i < NR_DIRTY_TYPE; i++) {
- dirty_i->dirty_segmap[i] = kvzalloc(bitmap_size, GFP_KERNEL);
+ dirty_i->dirty_segmap[i] = f2fs_kvzalloc(sbi, bitmap_size,
+ GFP_KERNEL);
if (!dirty_i->dirty_segmap[i])
return -ENOMEM;
}
@@ -3688,7 +3689,7 @@
struct f2fs_sm_info *sm_info;
int err;
- sm_info = kzalloc(sizeof(struct f2fs_sm_info), GFP_KERNEL);
+ sm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_sm_info), GFP_KERNEL);
if (!sm_info)
return -ENOMEM;
@@ -3740,7 +3741,9 @@
return err;
/* reinit free segmap based on SIT */
- build_sit_entries(sbi);
+ err = build_sit_entries(sbi);
+ if (err)
+ return err;
init_free_segmap(sbi);
err = build_dirty_segmap(sbi);