summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/ABI/testing/sysfs-fs-f2fs80
-rw-r--r--Documentation/filesystems/f2fs.rst2
-rw-r--r--MAINTAINERS1
-rw-r--r--fs/f2fs/checkpoint.c37
-rw-r--r--fs/f2fs/compress.c24
-rw-r--r--fs/f2fs/data.c624
-rw-r--r--fs/f2fs/debug.c64
-rw-r--r--fs/f2fs/dir.c4
-rw-r--r--fs/f2fs/extent_cache.c60
-rw-r--r--fs/f2fs/f2fs.h128
-rw-r--r--fs/f2fs/file.c173
-rw-r--r--fs/f2fs/gc.c22
-rw-r--r--fs/f2fs/gc.h2
-rw-r--r--fs/f2fs/inline.c14
-rw-r--r--fs/f2fs/inode.c78
-rw-r--r--fs/f2fs/iostat.c186
-rw-r--r--fs/f2fs/iostat.h19
-rw-r--r--fs/f2fs/namei.c5
-rw-r--r--fs/f2fs/node.c9
-rw-r--r--fs/f2fs/segment.c225
-rw-r--r--fs/f2fs/segment.h41
-rw-r--r--fs/f2fs/super.c63
-rw-r--r--fs/f2fs/sysfs.c49
-rw-r--r--fs/f2fs/verity.c2
-rw-r--r--include/linux/f2fs_fs.h2
-rw-r--r--include/trace/events/f2fs.h104
26 files changed, 1090 insertions, 928 deletions
diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs
index 9e3756625a81..94132745ecbe 100644
--- a/Documentation/ABI/testing/sysfs-fs-f2fs
+++ b/Documentation/ABI/testing/sysfs-fs-f2fs
@@ -49,16 +49,23 @@ Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description: Controls the in-place-update policy.
updates in f2fs. User can set:
- ==== =================
- 0x01 F2FS_IPU_FORCE
- 0x02 F2FS_IPU_SSR
- 0x04 F2FS_IPU_UTIL
- 0x08 F2FS_IPU_SSR_UTIL
- 0x10 F2FS_IPU_FSYNC
- 0x20 F2FS_IPU_ASYNC
- 0x40 F2FS_IPU_NOCACHE
- 0x80 F2FS_IPU_HONOR_OPU_WRITE
- ==== =================
+ ===== =============== ===================================================
+ value policy description
+ 0x00 DISABLE disable IPU(=default option in LFS mode)
+ 0x01 FORCE all the time
+ 0x02 SSR if SSR mode is activated
+ 0x04 UTIL if FS utilization is over threashold
+ 0x08 SSR_UTIL if SSR mode is activated and FS utilization is over
+ threashold
+ 0x10 FSYNC activated in fsync path only for high performance
+ flash storages. IPU will be triggered only if the
+ # of dirty pages over min_fsync_blocks.
+ (=default option)
+ 0x20 ASYNC do IPU given by asynchronous write requests
+ 0x40 NOCACHE disable IPU bio cache
+ 0x80 HONOR_OPU_WRITE use OPU write prior to IPU write if inode has
+ FI_OPU_WRITE flag
+ ===== =============== ===================================================
Refer segment.h for details.
@@ -669,3 +676,56 @@ Contact: "Ping Xiong" <xiongping1@xiaomi.com>
Description: When DATA SEPARATION is on, it controls the age threshold to indicate
the data blocks as warm. By default it was initialized as 2621440 blocks
(equals to 10GB).
+
+What: /sys/fs/f2fs/<disk>/fault_rate
+Date: May 2016
+Contact: "Sheng Yong" <shengyong@oppo.com>
+Contact: "Chao Yu" <chao@kernel.org>
+Description: Enable fault injection in all supported types with
+ specified injection rate.
+
+What: /sys/fs/f2fs/<disk>/fault_type
+Date: May 2016
+Contact: "Sheng Yong" <shengyong@oppo.com>
+Contact: "Chao Yu" <chao@kernel.org>
+Description: Support configuring fault injection type, should be
+ enabled with fault_injection option, fault type value
+ is shown below, it supports single or combined type.
+
+ =================== ===========
+ Type_Name Type_Value
+ =================== ===========
+ FAULT_KMALLOC 0x000000001
+ FAULT_KVMALLOC 0x000000002
+ FAULT_PAGE_ALLOC 0x000000004
+ FAULT_PAGE_GET 0x000000008
+ FAULT_ALLOC_BIO 0x000000010 (obsolete)
+ FAULT_ALLOC_NID 0x000000020
+ FAULT_ORPHAN 0x000000040
+ FAULT_BLOCK 0x000000080
+ FAULT_DIR_DEPTH 0x000000100
+ FAULT_EVICT_INODE 0x000000200
+ FAULT_TRUNCATE 0x000000400
+ FAULT_READ_IO 0x000000800
+ FAULT_CHECKPOINT 0x000001000
+ FAULT_DISCARD 0x000002000
+ FAULT_WRITE_IO 0x000004000
+ FAULT_SLAB_ALLOC 0x000008000
+ FAULT_DQUOT_INIT 0x000010000
+ FAULT_LOCK_OP 0x000020000
+ FAULT_BLKADDR 0x000040000
+ =================== ===========
+
+What: /sys/fs/f2fs/<disk>/discard_io_aware_gran
+Date: January 2023
+Contact: "Yangtao Li" <frank.li@vivo.com>
+Description: Controls background discard granularity of inner discard thread
+ when is not in idle. Inner thread will not issue discards with size that
+ is smaller than granularity. The unit size is one block(4KB), now only
+ support configuring in range of [0, 512].
+ Default: 512
+
+What: /sys/fs/f2fs/<disk>/last_age_weight
+Date: January 2023
+Contact: "Ping Xiong" <xiongping1@xiaomi.com>
+Description: When DATA SEPARATION is on, it controls the weight of last data block age.
diff --git a/Documentation/filesystems/f2fs.rst b/Documentation/filesystems/f2fs.rst
index 220f3e0d3f55..2055e72871fe 100644
--- a/Documentation/filesystems/f2fs.rst
+++ b/Documentation/filesystems/f2fs.rst
@@ -158,7 +158,7 @@ nobarrier This option can be used if underlying storage guarantees
If this option is set, no cache_flush commands are issued
but f2fs still guarantees the write ordering of all the
data writes.
-barrier If this option is set, cache_flush commands are allowed to be
+barrier If this option is set, cache_flush commands are allowed to be
issued.
fastboot This option is used when a system wants to reduce mount
time as much as possible, even though normal performance
diff --git a/MAINTAINERS b/MAINTAINERS
index edd3d562beee..b0db911207ba 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7795,6 +7795,7 @@ M: Chao Yu <chao@kernel.org>
L: linux-f2fs-devel@lists.sourceforge.net
S: Maintained
W: https://f2fs.wiki.kernel.org/
+Q: https://patchwork.kernel.org/project/f2fs/list/
B: https://bugzilla.kernel.org/enter_bug.cgi?product=File%20System&component=f2fs
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
F: Documentation/ABI/testing/sysfs-fs-f2fs
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 5a5515d83a1b..c3e058e0a018 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -70,7 +70,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
.old_blkaddr = index,
.new_blkaddr = index,
.encrypted_page = NULL,
- .is_por = !is_meta,
+ .is_por = !is_meta ? 1 : 0,
};
int err;
@@ -171,10 +171,8 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type)
{
- if (time_to_inject(sbi, FAULT_BLKADDR)) {
- f2fs_show_injection_info(sbi, FAULT_BLKADDR);
+ if (time_to_inject(sbi, FAULT_BLKADDR))
return false;
- }
switch (type) {
case META_NAT:
@@ -239,8 +237,8 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
.op = REQ_OP_READ,
.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
.encrypted_page = NULL,
- .in_list = false,
- .is_por = (type == META_POR),
+ .in_list = 0,
+ .is_por = (type == META_POR) ? 1 : 0,
};
struct blk_plug plug;
int err;
@@ -625,7 +623,6 @@ int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
- f2fs_show_injection_info(sbi, FAULT_ORPHAN);
return -ENOSPC;
}
@@ -798,7 +795,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
*/
head = &im->ino_list;
- /* loop for each orphan inode entry and write them in Jornal block */
+ /* loop for each orphan inode entry and write them in journal block */
list_for_each_entry(orphan, head, list) {
if (!page) {
page = f2fs_grab_meta_page(sbi, start_blk++);
@@ -1128,7 +1125,7 @@ retry:
} else {
/*
* We should submit bio, since it exists several
- * wribacking dentry pages in the freeing inode.
+ * writebacking dentry pages in the freeing inode.
*/
f2fs_submit_merged_write(sbi, DATA);
cond_resched();
@@ -1476,20 +1473,18 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true));
ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
- ckpt->cur_node_segno[i] =
- cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE));
- ckpt->cur_node_blkoff[i] =
- cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE));
- ckpt->alloc_type[i + CURSEG_HOT_NODE] =
- curseg_alloc_type(sbi, i + CURSEG_HOT_NODE);
+ struct curseg_info *curseg = CURSEG_I(sbi, i + CURSEG_HOT_NODE);
+
+ ckpt->cur_node_segno[i] = cpu_to_le32(curseg->segno);
+ ckpt->cur_node_blkoff[i] = cpu_to_le16(curseg->next_blkoff);
+ ckpt->alloc_type[i + CURSEG_HOT_NODE] = curseg->alloc_type;
}
for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
- ckpt->cur_data_segno[i] =
- cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA));
- ckpt->cur_data_blkoff[i] =
- cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA));
- ckpt->alloc_type[i + CURSEG_HOT_DATA] =
- curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
+ struct curseg_info *curseg = CURSEG_I(sbi, i + CURSEG_HOT_DATA);
+
+ ckpt->cur_data_segno[i] = cpu_to_le32(curseg->segno);
+ ckpt->cur_data_blkoff[i] = cpu_to_le16(curseg->next_blkoff);
+ ckpt->alloc_type[i + CURSEG_HOT_DATA] = curseg->alloc_type;
}
/* 2 cp + n data seg summary + orphan inode blocks */
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 2532f369cb10..b40dec3d7f79 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -241,7 +241,7 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc)
unsigned int size = LZ4_MEM_COMPRESS;
#ifdef CONFIG_F2FS_FS_LZ4HC
- if (F2FS_I(cc->inode)->i_compress_flag >> COMPRESS_LEVEL_OFFSET)
+ if (F2FS_I(cc->inode)->i_compress_level)
size = LZ4HC_MEM_COMPRESS;
#endif
@@ -267,8 +267,7 @@ static void lz4_destroy_compress_ctx(struct compress_ctx *cc)
#ifdef CONFIG_F2FS_FS_LZ4HC
static int lz4hc_compress_pages(struct compress_ctx *cc)
{
- unsigned char level = F2FS_I(cc->inode)->i_compress_flag >>
- COMPRESS_LEVEL_OFFSET;
+ unsigned char level = F2FS_I(cc->inode)->i_compress_level;
int len;
if (level)
@@ -340,8 +339,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
zstd_cstream *stream;
void *workspace;
unsigned int workspace_size;
- unsigned char level = F2FS_I(cc->inode)->i_compress_flag >>
- COMPRESS_LEVEL_OFFSET;
+ unsigned char level = F2FS_I(cc->inode)->i_compress_level;
if (!level)
level = F2FS_ZSTD_DEFAULT_CLEVEL;
@@ -564,7 +562,7 @@ module_param(num_compress_pages, uint, 0444);
MODULE_PARM_DESC(num_compress_pages,
"Number of intermediate compress pages to preallocate");
-int f2fs_init_compress_mempool(void)
+int __init f2fs_init_compress_mempool(void)
{
compress_page_pool = mempool_create_page_pool(num_compress_pages, 0);
return compress_page_pool ? 0 : -ENOMEM;
@@ -690,9 +688,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
vm_unmap_ram(cc->cbuf, cc->nr_cpages);
vm_unmap_ram(cc->rbuf, cc->cluster_size);
- for (i = 0; i < cc->nr_cpages; i++) {
- if (i < new_nr_cpages)
- continue;
+ for (i = new_nr_cpages; i < cc->nr_cpages; i++) {
f2fs_compress_free_page(cc->cpages[i]);
cc->cpages[i] = NULL;
}
@@ -1070,7 +1066,7 @@ retry:
if (ret)
goto out;
if (bio)
- f2fs_submit_bio(sbi, bio, DATA);
+ f2fs_submit_read_bio(sbi, bio, DATA);
ret = f2fs_init_compress_ctx(cc);
if (ret)
@@ -1215,10 +1211,11 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
.page = NULL,
.encrypted_page = NULL,
.compressed_page = NULL,
- .submitted = false,
+ .submitted = 0,
.io_type = io_type,
.io_wbc = wbc,
- .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode),
+ .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ?
+ 1 : 0,
};
struct dnode_of_data dn;
struct node_info ni;
@@ -1228,7 +1225,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
loff_t psize;
int i, err;
- /* we should bypass data pages to proceed the kworkder jobs */
+ /* we should bypass data pages to proceed the kworker jobs */
if (unlikely(f2fs_cp_error(sbi))) {
mapping_set_error(cc->rpages[0]->mapping, -EIO);
goto out_free;
@@ -1813,6 +1810,7 @@ unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn)
const struct address_space_operations f2fs_compress_aops = {
.release_folio = f2fs_release_folio,
.invalidate_folio = f2fs_invalidate_folio,
+ .migrate_folio = filemap_migrate_folio,
};
struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 41addc605350..06b552a0aba2 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -292,13 +292,11 @@ static void f2fs_read_end_io(struct bio *bio)
struct bio_post_read_ctx *ctx;
bool intask = in_task();
- iostat_update_and_unbind_ctx(bio, 0);
+ iostat_update_and_unbind_ctx(bio);
ctx = bio->bi_private;
- if (time_to_inject(sbi, FAULT_READ_IO)) {
- f2fs_show_injection_info(sbi, FAULT_READ_IO);
+ if (time_to_inject(sbi, FAULT_READ_IO))
bio->bi_status = BLK_STS_IOERR;
- }
if (bio->bi_status) {
f2fs_finish_read_bio(bio, intask);
@@ -332,13 +330,11 @@ static void f2fs_write_end_io(struct bio *bio)
struct bio_vec *bvec;
struct bvec_iter_all iter_all;
- iostat_update_and_unbind_ctx(bio, 1);
+ iostat_update_and_unbind_ctx(bio);
sbi = bio->bi_private;
- if (time_to_inject(sbi, FAULT_WRITE_IO)) {
- f2fs_show_injection_info(sbi, FAULT_WRITE_IO);
+ if (time_to_inject(sbi, FAULT_WRITE_IO))
bio->bi_status = BLK_STS_IOERR;
- }
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
@@ -507,65 +503,66 @@ static bool f2fs_crypt_mergeable_bio(struct bio *bio, const struct inode *inode,
return fscrypt_mergeable_bio(bio, inode, next_idx);
}
-static inline void __submit_bio(struct f2fs_sb_info *sbi,
- struct bio *bio, enum page_type type)
+void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio,
+ enum page_type type)
{
- if (!is_read_io(bio_op(bio))) {
- unsigned int start;
+ WARN_ON_ONCE(!is_read_io(bio_op(bio)));
+ trace_f2fs_submit_read_bio(sbi->sb, type, bio);
- if (type != DATA && type != NODE)
- goto submit_io;
+ iostat_update_submit_ctx(bio, type);
+ submit_bio(bio);
+}
- if (f2fs_lfs_mode(sbi) && current->plug)
- blk_finish_plug(current->plug);
+static void f2fs_align_write_bio(struct f2fs_sb_info *sbi, struct bio *bio)
+{
+ unsigned int start =
+ (bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS) % F2FS_IO_SIZE(sbi);
- if (!F2FS_IO_ALIGNED(sbi))
- goto submit_io;
+ if (start == 0)
+ return;
- start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
- start %= F2FS_IO_SIZE(sbi);
+ /* fill dummy pages */
+ for (; start < F2FS_IO_SIZE(sbi); start++) {
+ struct page *page =
+ mempool_alloc(sbi->write_io_dummy,
+ GFP_NOIO | __GFP_NOFAIL);
+ f2fs_bug_on(sbi, !page);
- if (start == 0)
- goto submit_io;
+ lock_page(page);
- /* fill dummy pages */
- for (; start < F2FS_IO_SIZE(sbi); start++) {
- struct page *page =
- mempool_alloc(sbi->write_io_dummy,
- GFP_NOIO | __GFP_NOFAIL);
- f2fs_bug_on(sbi, !page);
+ zero_user_segment(page, 0, PAGE_SIZE);
+ set_page_private_dummy(page);
- lock_page(page);
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
+ f2fs_bug_on(sbi, 1);
+ }
+}
- zero_user_segment(page, 0, PAGE_SIZE);
- set_page_private_dummy(page);
+static void f2fs_submit_write_bio(struct f2fs_sb_info *sbi, struct bio *bio,
+ enum page_type type)
+{
+ WARN_ON_ONCE(is_read_io(bio_op(bio)));
+
+ if (type == DATA || type == NODE) {
+ if (f2fs_lfs_mode(sbi) && current->plug)
+ blk_finish_plug(current->plug);
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
- f2fs_bug_on(sbi, 1);
+ if (F2FS_IO_ALIGNED(sbi)) {
+ f2fs_align_write_bio(sbi, bio);
+ /*
+ * In the NODE case, we lose next block address chain.
+ * So, we need to do checkpoint in f2fs_sync_file.
+ */
+ if (type == NODE)
+ set_sbi_flag(sbi, SBI_NEED_CP);
}
- /*
- * In the NODE case, we lose next block address chain. So, we
- * need to do checkpoint in f2fs_sync_file.
- */
- if (type == NODE)
- set_sbi_flag(sbi, SBI_NEED_CP);
}
-submit_io:
- if (is_read_io(bio_op(bio)))
- trace_f2fs_submit_read_bio(sbi->sb, type, bio);
- else
- trace_f2fs_submit_write_bio(sbi->sb, type, bio);
+ trace_f2fs_submit_write_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
}
-void f2fs_submit_bio(struct f2fs_sb_info *sbi,
- struct bio *bio, enum page_type type)
-{
- __submit_bio(sbi, bio, type);
-}
-
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
@@ -573,12 +570,13 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
if (!io->bio)
return;
- if (is_read_io(fio->op))
+ if (is_read_io(fio->op)) {
trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
- else
+ f2fs_submit_read_bio(io->sbi, io->bio, fio->type);
+ } else {
trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
-
- __submit_bio(io->sbi, io->bio, fio->type);
+ f2fs_submit_write_bio(io->sbi, io->bio, fio->type);
+ }
io->bio = NULL;
}
@@ -655,6 +653,9 @@ static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
f2fs_down_write(&io->io_rwsem);
+ if (!io->bio)
+ goto unlock_out;
+
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
@@ -663,6 +664,7 @@ static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
io->bio->bi_opf |= REQ_PREFLUSH | REQ_FUA;
}
__submit_merged_bio(io);
+unlock_out:
f2fs_up_write(&io->io_rwsem);
}
@@ -741,12 +743,15 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
}
if (fio->io_wbc && !is_read_io(fio->op))
- wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
__read_io_type(page) : WB_DATA_TYPE(fio->page));
- __submit_bio(fio->sbi, bio, fio->type);
+ if (is_read_io(bio_op(bio)))
+ f2fs_submit_read_bio(fio->sbi, bio, fio->type);
+ else
+ f2fs_submit_write_bio(fio->sbi, bio, fio->type);
return 0;
}
@@ -848,7 +853,7 @@ static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio,
/* page can't be merged into bio; submit the bio */
del_bio_entry(be);
- __submit_bio(sbi, *bio, DATA);
+ f2fs_submit_write_bio(sbi, *bio, DATA);
break;
}
f2fs_up_write(&io->bio_list_lock);
@@ -911,7 +916,7 @@ void f2fs_submit_merged_ipu_write(struct f2fs_sb_info *sbi,
}
if (found)
- __submit_bio(sbi, target, DATA);
+ f2fs_submit_write_bio(sbi, target, DATA);
if (bio && *bio) {
bio_put(*bio);
*bio = NULL;
@@ -948,7 +953,7 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
inc_page_count(fio->sbi, WB_DATA_TYPE(page));
@@ -991,7 +996,7 @@ next:
bio_page = fio->page;
/* set submitted = true as a return value */
- fio->submitted = true;
+ fio->submitted = 1;
inc_page_count(sbi, WB_DATA_TYPE(bio_page));
@@ -1007,7 +1012,7 @@ alloc_new:
(fio->type == DATA || fio->type == NODE) &&
fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
dec_page_count(sbi, WB_DATA_TYPE(bio_page));
- fio->retry = true;
+ fio->retry = 1;
goto skip;
}
io->bio = __bio_alloc(fio, BIO_MAX_VECS);
@@ -1022,7 +1027,7 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, bio_page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
@@ -1107,7 +1112,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
}
inc_page_count(sbi, F2FS_RD_DATA);
f2fs_update_iostat(sbi, NULL, FS_DATA_READ_IO, F2FS_BLKSIZE);
- __submit_bio(sbi, bio, DATA);
+ f2fs_submit_read_bio(sbi, bio, DATA);
return 0;
}
@@ -1207,19 +1212,6 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
return err;
}
-int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
-{
- struct extent_info ei = {0, };
- struct inode *inode = dn->inode;
-
- if (f2fs_lookup_read_extent_cache(inode, index, &ei)) {
- dn->data_blkaddr = ei.blk + index - ei.fofs;
- return 0;
- }
-
- return f2fs_reserve_block(dn, index);
-}
-
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
blk_opf_t op_flags, bool for_write,
pgoff_t *next_pgofs)
@@ -1227,15 +1219,14 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
- struct extent_info ei = {0, };
int err;
page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
return ERR_PTR(-ENOMEM);
- if (f2fs_lookup_read_extent_cache(inode, index, &ei)) {
- dn.data_blkaddr = ei.blk + index - ei.fofs;
+ if (f2fs_lookup_read_extent_cache_block(inode, index,
+ &dn.data_blkaddr)) {
if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), dn.data_blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
@@ -1432,13 +1423,12 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
return err;
dn->data_blkaddr = f2fs_data_blkaddr(dn);
- if (dn->data_blkaddr != NULL_ADDR)
- goto alloc;
-
- if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
- return err;
+ if (dn->data_blkaddr == NULL_ADDR) {
+ err = inc_valid_block_count(sbi, dn->inode, &count);
+ if (unlikely(err))
+ return err;
+ }
-alloc:
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
old_blkaddr = dn->data_blkaddr;
f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
@@ -1452,19 +1442,91 @@ alloc:
return 0;
}
-void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
+static void f2fs_map_lock(struct f2fs_sb_info *sbi, int flag)
{
- if (flag == F2FS_GET_BLOCK_PRE_AIO) {
- if (lock)
- f2fs_down_read(&sbi->node_change);
- else
- f2fs_up_read(&sbi->node_change);
+ if (flag == F2FS_GET_BLOCK_PRE_AIO)
+ f2fs_down_read(&sbi->node_change);
+ else
+ f2fs_lock_op(sbi);
+}
+
+static void f2fs_map_unlock(struct f2fs_sb_info *sbi, int flag)
+{
+ if (flag == F2FS_GET_BLOCK_PRE_AIO)
+ f2fs_up_read(&sbi->node_change);
+ else
+ f2fs_unlock_op(sbi);
+}
+
+int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ int err = 0;
+
+ f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO);
+ if (!f2fs_lookup_read_extent_cache_block(dn->inode, index,
+ &dn->data_blkaddr))
+ err = f2fs_reserve_block(dn, index);
+ f2fs_map_unlock(sbi, F2FS_GET_BLOCK_PRE_AIO);
+
+ return err;
+}
+
+static int f2fs_map_no_dnode(struct inode *inode,
+ struct f2fs_map_blocks *map, struct dnode_of_data *dn,
+ pgoff_t pgoff)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ /*
+ * There is one exceptional case that read_node_page() may return
+ * -ENOENT due to filesystem has been shutdown or cp_error, return
+ * -EIO in that case.
+ */
+ if (map->m_may_create &&
+ (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || f2fs_cp_error(sbi)))
+ return -EIO;
+
+ if (map->m_next_pgofs)
+ *map->m_next_pgofs = f2fs_get_next_page_offset(dn, pgoff);
+ if (map->m_next_extent)
+ *map->m_next_extent = f2fs_get_next_page_offset(dn, pgoff);
+ return 0;
+}
+
+static bool f2fs_map_blocks_cached(struct inode *inode,
+ struct f2fs_map_blocks *map, int flag)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ unsigned int maxblocks = map->m_len;
+ pgoff_t pgoff = (pgoff_t)map->m_lblk;
+ struct extent_info ei = {};
+
+ if (!f2fs_lookup_read_extent_cache(inode, pgoff, &ei))
+ return false;
+
+ map->m_pblk = ei.blk + pgoff - ei.fofs;
+ map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgoff);
+ map->m_flags = F2FS_MAP_MAPPED;
+ if (map->m_next_extent)
+ *map->m_next_extent = pgoff + map->m_len;
+
+ /* for hardware encryption, but to avoid potential issue in future */
+ if (flag == F2FS_GET_BLOCK_DIO)
+ f2fs_wait_on_block_writeback_range(inode,
+ map->m_pblk, map->m_len);
+
+ if (f2fs_allow_multi_device_dio(sbi, flag)) {
+ int bidx = f2fs_target_device_index(sbi, map->m_pblk);
+ struct f2fs_dev_info *dev = &sbi->devs[bidx];
+
+ map->m_bdev = dev->bdev;
+ map->m_pblk -= dev->start_blk;
+ map->m_len = min(map->m_len, dev->end_blk + 1 - map->m_pblk);
} else {
- if (lock)
- f2fs_lock_op(sbi);
- else
- f2fs_unlock_op(sbi);
+ map->m_bdev = inode->i_sb->s_bdev;
}
+ return true;
}
/*
@@ -1472,8 +1534,7 @@ void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
* maps continuous logical blocks to physical blocks, and return such
* info via f2fs_map_blocks structure.
*/
-int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
- int create, int flag)
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int flag)
{
unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
@@ -1483,14 +1544,17 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int err = 0, ofs = 1;
unsigned int ofs_in_node, last_ofs_in_node;
blkcnt_t prealloc;
- struct extent_info ei = {0, };
block_t blkaddr;
unsigned int start_pgofs;
int bidx = 0;
+ bool is_hole;
if (!maxblocks)
return 0;
+ if (!map->m_may_create && f2fs_map_blocks_cached(inode, map, flag))
+ goto out;
+
map->m_bdev = inode->i_sb->s_bdev;
map->m_multidev_dio =
f2fs_allow_multi_device_dio(F2FS_I_SB(inode), flag);
@@ -1502,42 +1566,9 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
pgofs = (pgoff_t)map->m_lblk;
end = pgofs + maxblocks;
- if (!create && f2fs_lookup_read_extent_cache(inode, pgofs, &ei)) {
- if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO &&
- map->m_may_create)
- goto next_dnode;
-
- map->m_pblk = ei.blk + pgofs - ei.fofs;
- map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
- map->m_flags = F2FS_MAP_MAPPED;
- if (map->m_next_extent)
- *map->m_next_extent = pgofs + map->m_len;
-
- /* for hardware encryption, but to avoid potential issue in future */
- if (flag == F2FS_GET_BLOCK_DIO)
- f2fs_wait_on_block_writeback_range(inode,
- map->m_pblk, map->m_len);
-
- if (map->m_multidev_dio) {
- block_t blk_addr = map->m_pblk;
-
- bidx = f2fs_target_device_index(sbi, map->m_pblk);
-
- map->m_bdev = FDEV(bidx).bdev;
- map->m_pblk -= FDEV(bidx).start_blk;
- map->m_len = min(map->m_len,
- FDEV(bidx).end_blk + 1 - map->m_pblk);
-
- if (map->m_may_create)
- f2fs_update_device_state(sbi, inode->i_ino,
- blk_addr, map->m_len);
- }
- goto out;
- }
-
next_dnode:
if (map->m_may_create)
- f2fs_do_map_lock(sbi, flag, true);
+ f2fs_map_lock(sbi, flag);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -1545,29 +1576,8 @@ next_dnode:
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 =
- f2fs_get_next_page_offset(&dn, pgofs);
- if (map->m_next_extent)
- *map->m_next_extent =
- f2fs_get_next_page_offset(&dn, pgofs);
- }
+ if (err == -ENOENT)
+ err = f2fs_map_no_dnode(inode, map, &dn, pgofs);
goto unlock_out;
}
@@ -1578,78 +1588,76 @@ next_dnode:
next_block:
blkaddr = f2fs_data_blkaddr(&dn);
-
- if (__is_valid_data_blkaddr(blkaddr) &&
- !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
+ is_hole = !__is_valid_data_blkaddr(blkaddr);
+ if (!is_hole &&
+ !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto sync_out;
}
- if (__is_valid_data_blkaddr(blkaddr)) {
- /* use out-place-update for driect IO under LFS mode */
- if (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO &&
- map->m_may_create) {
+ /* use out-place-update for direct IO under LFS mod