summaryrefslogtreecommitdiff
path: root/fs/f2fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/f2fs')
-rw-r--r--fs/f2fs/Kconfig3
-rw-r--r--fs/f2fs/acl.c8
-rw-r--r--fs/f2fs/checkpoint.c107
-rw-r--r--fs/f2fs/compress.c252
-rw-r--r--fs/f2fs/data.c837
-rw-r--r--fs/f2fs/debug.c124
-rw-r--r--fs/f2fs/dir.c178
-rw-r--r--fs/f2fs/extent_cache.c176
-rw-r--r--fs/f2fs/f2fs.h617
-rw-r--r--fs/f2fs/file.c846
-rw-r--r--fs/f2fs/gc.c297
-rw-r--r--fs/f2fs/gc.h35
-rw-r--r--fs/f2fs/inline.c100
-rw-r--r--fs/f2fs/inode.c153
-rw-r--r--fs/f2fs/namei.c136
-rw-r--r--fs/f2fs/node.c128
-rw-r--r--fs/f2fs/node.h4
-rw-r--r--fs/f2fs/recovery.c76
-rw-r--r--fs/f2fs/segment.c984
-rw-r--r--fs/f2fs/segment.h144
-rw-r--r--fs/f2fs/super.c523
-rw-r--r--fs/f2fs/sysfs.c182
-rw-r--r--fs/f2fs/verity.c29
-rw-r--r--fs/f2fs/xattr.c14
24 files changed, 3618 insertions, 2335 deletions
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 68a1e23e1557..5916a02fb46d 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -4,8 +4,7 @@ config F2FS_FS
depends on BLOCK
select BUFFER_HEAD
select NLS
- select CRYPTO
- select CRYPTO_CRC32
+ select CRC32
select F2FS_FS_XATTR if FS_ENCRYPTION
select FS_ENCRYPTION_ALGS if FS_ENCRYPTION
select FS_IOMAP
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index ec2aeccb69a3..1fbc0607363b 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -219,8 +219,7 @@ static int f2fs_acl_update_mode(struct mnt_idmap *idmap,
return error;
if (error == 0)
*acl = NULL;
- if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) &&
- !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
+ if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
mode &= ~S_ISGID;
*mode_p = mode;
return 0;
@@ -297,9 +296,8 @@ static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl,
struct posix_acl *clone = NULL;
if (acl) {
- int size = sizeof(struct posix_acl) + acl->a_count *
- sizeof(struct posix_acl_entry);
- clone = kmemdup(acl, size, flags);
+ clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count),
+ flags);
if (clone)
refcount_set(&clone->a_refcount, 1);
}
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b0597a539fc5..efda9a022981 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -32,7 +32,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io,
f2fs_build_fault_attr(sbi, 0, 0);
if (!end_io)
f2fs_flush_merged_writes(sbi);
- f2fs_handle_critical_error(sbi, reason, end_io);
+ f2fs_handle_critical_error(sbi, reason);
}
/*
@@ -99,7 +99,7 @@ repeat:
}
if (unlikely(!PageUptodate(page))) {
- f2fs_handle_page_eio(sbi, page->index, META);
+ f2fs_handle_page_eio(sbi, page_folio(page), META);
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
@@ -154,49 +154,47 @@ static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
if (unlikely(f2fs_cp_error(sbi)))
return exist;
- 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_UPDATE) ||
+ (!exist && type == DATA_GENERIC_ENHANCE))
+ goto out_err;
+ if (!exist && type != DATA_GENERIC_ENHANCE_UPDATE)
+ goto out_handle;
+ return exist;
- if (!exist && type == DATA_GENERIC_ENHANCE) {
- f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
- blkaddr, exist);
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- dump_stack();
- }
+out_err:
+ f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d",
+ blkaddr, exist);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ dump_stack();
+out_handle:
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
return exist;
}
-bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+static bool __f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type)
{
- if (time_to_inject(sbi, FAULT_BLKADDR))
- return false;
-
switch (type) {
case META_NAT:
break;
case META_SIT:
if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
- return false;
+ goto check_only;
break;
case META_SSA:
if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
blkaddr < SM_I(sbi)->ssa_blkaddr))
- return false;
+ goto check_only;
break;
case META_CP:
if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
blkaddr < __start_cp_addr(sbi)))
- return false;
+ goto check_only;
break;
case META_POR:
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
blkaddr < MAIN_BLKADDR(sbi)))
- return false;
+ goto check_only;
break;
case DATA_GENERIC:
case DATA_GENERIC_ENHANCE:
@@ -213,7 +211,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
blkaddr);
set_sbi_flag(sbi, SBI_NEED_FSCK);
dump_stack();
- return false;
+ goto err;
} else {
return __is_bitmap_valid(sbi, blkaddr, type);
}
@@ -221,13 +219,31 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
case META_GENERIC:
if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
blkaddr >= MAIN_BLKADDR(sbi)))
- return false;
+ goto err;
break;
default:
BUG();
}
return true;
+err:
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+check_only:
+ return false;
+}
+
+bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
+{
+ if (time_to_inject(sbi, FAULT_BLKADDR_VALIDITY))
+ return false;
+ return __f2fs_is_valid_blkaddr(sbi, blkaddr, type);
+}
+
+bool f2fs_is_valid_blkaddr_raw(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type)
+{
+ return __f2fs_is_valid_blkaddr(sbi, blkaddr, type);
}
/*
@@ -329,30 +345,31 @@ static int __f2fs_write_meta_page(struct page *page,
enum iostat_type io_type)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+ struct folio *folio = page_folio(page);
- trace_f2fs_writepage(page, META);
+ trace_f2fs_writepage(folio, META);
if (unlikely(f2fs_cp_error(sbi))) {
if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) {
- ClearPageUptodate(page);
+ folio_clear_uptodate(folio);
dec_page_count(sbi, F2FS_DIRTY_META);
- unlock_page(page);
+ folio_unlock(folio);
return 0;
}
goto redirty_out;
}
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
- if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
+ if (wbc->for_reclaim && folio->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
- f2fs_do_write_meta_page(sbi, page, io_type);
+ f2fs_do_write_meta_page(sbi, folio, io_type);
dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim)
f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META);
- unlock_page(page);
+ folio_unlock(folio);
if (unlikely(f2fs_cp_error(sbi)))
f2fs_submit_merged_write(sbi, META);
@@ -477,7 +494,7 @@ stop:
static bool f2fs_dirty_meta_folio(struct address_space *mapping,
struct folio *folio)
{
- trace_f2fs_set_page_dirty(&folio->page, META);
+ trace_f2fs_set_page_dirty(folio, META);
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
@@ -889,7 +906,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
cp_blocks = le32_to_cpu(cp_block->cp_pack_total_block_count);
- if (cp_blocks > sbi->blocks_per_seg || cp_blocks <= F2FS_CP_PACKS) {
+ if (cp_blocks > BLKS_PER_SEG(sbi) || cp_blocks <= F2FS_CP_PACKS) {
f2fs_warn(sbi, "invalid cp_pack_total_block_count:%u",
le32_to_cpu(cp_block->cp_pack_total_block_count));
goto invalid_cp;
@@ -1170,6 +1187,11 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi)
ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
ckpt->next_free_nid = cpu_to_le32(last_nid);
+
+ /* update user_block_counts */
+ sbi->last_valid_block_count = sbi->total_valid_block_count;
+ percpu_counter_set(&sbi->alloc_valid_block_count, 0);
+ percpu_counter_set(&sbi->rf_node_block_count, 0);
}
static bool __need_flush_quota(struct f2fs_sb_info *sbi)
@@ -1324,7 +1346,7 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
if (cpc->reason & CP_UMOUNT) {
if (le32_to_cpu(ckpt->cp_pack_total_block_count) +
- NM_I(sbi)->nat_bits_blocks > sbi->blocks_per_seg) {
+ NM_I(sbi)->nat_bits_blocks > BLKS_PER_SEG(sbi)) {
clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
f2fs_notice(sbi, "Disable nat_bits due to no space");
} else if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG) &&
@@ -1527,10 +1549,10 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
cp_ver |= ((__u64)crc32 << 32);
*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
- blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
+ blk = start_blk + BLKS_PER_SEG(sbi) - nm_i->nat_bits_blocks;
for (i = 0; i < nm_i->nat_bits_blocks; i++)
f2fs_update_meta_page(sbi, nm_i->nat_bits +
- (i << F2FS_BLKSIZE_BITS), blk + i);
+ F2FS_BLK_TO_BYTES(i), blk + i);
}
/* write out checkpoint buffer at block 0 */
@@ -1559,11 +1581,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
start_blk += NR_CURSEG_NODE_TYPE;
}
- /* update user_block_counts */
- sbi->last_valid_block_count = sbi->total_valid_block_count;
- percpu_counter_set(&sbi->alloc_valid_block_count, 0);
- percpu_counter_set(&sbi->rf_node_block_count, 0);
-
/* Here, we have one bio having CP pack except cp pack 2 page */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
/* Wait for all dirty meta pages to be submitted for IO */
@@ -1587,8 +1604,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
*/
if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) ||
f2fs_sb_has_compression(sbi))
- invalidate_mapping_pages(META_MAPPING(sbi),
- MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
+ f2fs_bug_on(sbi,
+ invalidate_inode_pages2_range(META_MAPPING(sbi),
+ MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1));
f2fs_release_ino_entry(sbi, false);
@@ -1701,6 +1719,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
}
f2fs_restore_inmem_curseg(sbi);
+ f2fs_reinit_atgc_curseg(sbi);
stat_inc_cp_count(sbi);
stop:
unblock_operations(sbi);
@@ -1730,9 +1749,9 @@ void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
im->ino_num = 0;
}
- sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
+ sbi->max_orphans = (BLKS_PER_SEG(sbi) - F2FS_CP_PACKS -
NR_CURSEG_PERSIST_TYPE - __cp_payload(sbi)) *
- F2FS_ORPHANS_PER_BLOCK;
+ F2FS_ORPHANS_PER_BLOCK;
}
int __init f2fs_create_checkpoint_caches(void)
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 531517dac079..985690d81a82 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -90,11 +90,13 @@ bool f2fs_is_compressed_page(struct page *page)
static void f2fs_set_compressed_page(struct page *page,
struct inode *inode, pgoff_t index, void *data)
{
- attach_page_private(page, (void *)data);
+ struct folio *folio = page_folio(page);
+
+ folio_attach_private(folio, (void *)data);
/* i_crypto_info and iv index */
- page->index = index;
- page->mapping = inode->i_mapping;
+ folio->index = index;
+ folio->mapping = inode->i_mapping;
}
static void f2fs_drop_rpages(struct compress_ctx *cc, int len, bool unlock)
@@ -160,17 +162,17 @@ void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse)
cc->cluster_idx = NULL_CLUSTER;
}
-void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page)
+void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio)
{
unsigned int cluster_ofs;
- if (!f2fs_cluster_can_merge_page(cc, page->index))
+ if (!f2fs_cluster_can_merge_page(cc, folio->index))
f2fs_bug_on(F2FS_I_SB(cc->inode), 1);
- cluster_ofs = offset_in_cluster(cc, page->index);
- cc->rpages[cluster_ofs] = page;
+ cluster_ofs = offset_in_cluster(cc, folio->index);
+ cc->rpages[cluster_ofs] = folio_page(folio, 0);
cc->nr_rpages++;
- cc->cluster_idx = cluster_idx(cc, page->index);
+ cc->cluster_idx = cluster_idx(cc, folio->index);
}
#ifdef CONFIG_F2FS_FS_LZO
@@ -198,8 +200,8 @@ static int lzo_compress_pages(struct compress_ctx *cc)
ret = lzo1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata,
&cc->clen, cc->private);
if (ret != LZO_E_OK) {
- printk_ratelimited("%sF2FS-fs (%s): lzo compress failed, ret:%d\n",
- KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret);
+ f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+ "lzo compress failed, ret:%d", ret);
return -EIO;
}
return 0;
@@ -212,17 +214,15 @@ static int lzo_decompress_pages(struct decompress_io_ctx *dic)
ret = lzo1x_decompress_safe(dic->cbuf->cdata, dic->clen,
dic->rbuf, &dic->rlen);
if (ret != LZO_E_OK) {
- printk_ratelimited("%sF2FS-fs (%s): lzo decompress failed, ret:%d\n",
- KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+ f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+ "lzo decompress failed, ret:%d", ret);
return -EIO;
}
if (dic->rlen != PAGE_SIZE << dic->log_cluster_size) {
- printk_ratelimited("%sF2FS-fs (%s): lzo invalid rlen:%zu, "
- "expected:%lu\n", KERN_ERR,
- F2FS_I_SB(dic->inode)->sb->s_id,
- dic->rlen,
- PAGE_SIZE << dic->log_cluster_size);
+ f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+ "lzo invalid rlen:%zu, expected:%lu",
+ dic->rlen, PAGE_SIZE << dic->log_cluster_size);
return -EIO;
}
return 0;
@@ -294,16 +294,15 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic)
ret = LZ4_decompress_safe(dic->cbuf->cdata, dic->rbuf,
dic->clen, dic->rlen);
if (ret < 0) {
- printk_ratelimited("%sF2FS-fs (%s): lz4 decompress failed, ret:%d\n",
- KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, ret);
+ f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+ "lz4 decompress failed, ret:%d", ret);
return -EIO;
}
if (ret != PAGE_SIZE << dic->log_cluster_size) {
- printk_ratelimited("%sF2FS-fs (%s): lz4 invalid ret:%d, "
- "expected:%lu\n", KERN_ERR,
- F2FS_I_SB(dic->inode)->sb->s_id, ret,
- PAGE_SIZE << dic->log_cluster_size);
+ f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+ "lz4 invalid ret:%d, expected:%lu",
+ ret, PAGE_SIZE << dic->log_cluster_size);
return -EIO;
}
return 0;
@@ -350,9 +349,8 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
stream = zstd_init_cstream(&params, 0, workspace, workspace_size);
if (!stream) {
- printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_cstream failed\n",
- KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
- __func__);
+ f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+ "%s zstd_init_cstream failed", __func__);
kvfree(workspace);
return -EIO;
}
@@ -390,16 +388,16 @@ static int zstd_compress_pages(struct compress_ctx *cc)
ret = zstd_compress_stream(stream, &outbuf, &inbuf);
if (zstd_is_error(ret)) {
- printk_ratelimited("%sF2FS-fs (%s): %s zstd_compress_stream failed, ret: %d\n",
- KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
+ f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+ "%s zstd_compress_stream failed, ret: %d",
__func__, zstd_get_error_code(ret));
return -EIO;
}
ret = zstd_end_stream(stream, &outbuf);
if (zstd_is_error(ret)) {
- printk_ratelimited("%sF2FS-fs (%s): %s zstd_end_stream returned %d\n",
- KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id,
+ f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+ "%s zstd_end_stream returned %d",
__func__, zstd_get_error_code(ret));
return -EIO;
}
@@ -432,9 +430,8 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
stream = zstd_init_dstream(max_window_size, workspace, workspace_size);
if (!stream) {
- printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_dstream failed\n",
- KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
- __func__);
+ f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+ "%s zstd_init_dstream failed", __func__);
kvfree(workspace);
return -EIO;
}
@@ -469,16 +466,15 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic)
ret = zstd_decompress_stream(stream, &outbuf, &inbuf);
if (zstd_is_error(ret)) {
- printk_ratelimited("%sF2FS-fs (%s): %s zstd_decompress_stream failed, ret: %d\n",
- KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id,
+ f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+ "%s zstd_decompress_stream failed, ret: %d",
__func__, zstd_get_error_code(ret));
return -EIO;
}
if (dic->rlen != outbuf.pos) {
- printk_ratelimited("%sF2FS-fs (%s): %s ZSTD invalid rlen:%zu, "
- "expected:%lu\n", KERN_ERR,
- F2FS_I_SB(dic->inode)->sb->s_id,
+ f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
+ "%s ZSTD invalid rlen:%zu, expected:%lu",
__func__, dic->rlen,
PAGE_SIZE << dic->log_cluster_size);
return -EIO;
@@ -512,8 +508,8 @@ static int lzorle_compress_pages(struct compress_ctx *cc)
ret = lzorle1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata,
&cc->clen, cc->private);
if (ret != LZO_E_OK) {
- printk_ratelimited("%sF2FS-fs (%s): lzo-rle compress failed, ret:%d\n",
- KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret);
+ f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
+ "lzo-rle compress failed, ret:%d", ret);
return -EIO;
}
return 0;
@@ -780,9 +776,9 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task)
if (provided != calculated) {
if (!is_inode_flag_set(dic->inode, FI_COMPRESS_CORRUPT)) {
set_inode_flag(dic->inode, FI_COMPRESS_CORRUPT);
- printk_ratelimited(
- "%sF2FS-fs (%s): checksum invalid, nid = %lu, %x vs %x",
- KERN_INFO, sbi->sb->s_id, dic->inode->i_ino,
+ f2fs_info_ratelimited(sbi,
+ "checksum invalid, nid = %lu, %x vs %x",
+ dic->inode->i_ino,
provided, calculated);
}
set_sbi_flag(sbi, SBI_NEED_FSCK);
@@ -850,7 +846,7 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index)
bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages,
int index, int nr_pages, bool uptodate)
{
- unsigned long pgidx = pages[index]->index;
+ unsigned long pgidx = page_folio(pages[index])->index;
int i = uptodate ? 0 : 1;
/*
@@ -864,9 +860,11 @@ bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages,
return false;
for (; i < cc->cluster_size; i++) {
- if (pages[index + i]->index != pgidx + i)
+ struct folio *folio = page_folio(pages[index + i]);
+
+ if (folio->index != pgidx + i)
return false;
- if (uptodate && !PageUptodate(pages[index + i]))
+ if (uptodate && !folio_test_uptodate(folio))
return false;
}
@@ -885,7 +883,7 @@ static bool cluster_has_invalid_data(struct compress_ctx *cc)
f2fs_bug_on(F2FS_I_SB(cc->inode), !page);
/* beyond EOF */
- if (page->index >= nr_pages)
+ if (page_folio(page)->index >= nr_pages)
return true;
}
return false;
@@ -951,7 +949,7 @@ static int __f2fs_get_cluster_blocks(struct inode *inode,
unsigned int cluster_size = F2FS_I(inode)->i_cluster_size;
int count, i;
- for (i = 1, count = 1; i < cluster_size; i++) {
+ for (i = 0, count = 0; i < cluster_size; i++) {
block_t blkaddr = data_blkaddr(dn->inode, dn->node_page,
dn->ofs_in_node + i);
@@ -962,8 +960,8 @@ static int __f2fs_get_cluster_blocks(struct inode *inode,
return count;
}
-static int __f2fs_cluster_blocks(struct inode *inode,
- unsigned int cluster_idx, bool compr_blks)
+static int __f2fs_cluster_blocks(struct inode *inode, unsigned int cluster_idx,
+ enum cluster_check_type type)
{
struct dnode_of_data dn;
unsigned int start_idx = cluster_idx <<
@@ -984,10 +982,12 @@ static int __f2fs_cluster_blocks(struct inode *inode,
}
if (dn.data_blkaddr == COMPRESS_ADDR) {
- if (compr_blks)
- ret = __f2fs_get_cluster_blocks(inode, &dn);
- else
+ if (type == CLUSTER_COMPR_BLKS)
+ ret = 1 + __f2fs_get_cluster_blocks(inode, &dn);
+ else if (type == CLUSTER_IS_COMPR)
ret = 1;
+ } else if (type == CLUSTER_RAW_BLKS) {
+ ret = __f2fs_get_cluster_blocks(inode, &dn);
}
fail:
f2fs_put_dnode(&dn);
@@ -997,7 +997,16 @@ fail:
/* return # of compressed blocks in compressed cluster */
static int f2fs_compressed_blocks(struct compress_ctx *cc)
{
- return __f2fs_cluster_blocks(cc->inode, cc->cluster_idx, true);
+ return __f2fs_cluster_blocks(cc->inode, cc->cluster_idx,
+ CLUSTER_COMPR_BLKS);
+}
+
+/* return # of raw blocks in non-compressed cluster */
+static int f2fs_decompressed_blocks(struct inode *inode,
+ unsigned int cluster_idx)
+{
+ return __f2fs_cluster_blocks(inode, cluster_idx,
+ CLUSTER_RAW_BLKS);
}
/* return whether cluster is compressed one or not */
@@ -1005,7 +1014,16 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
{
return __f2fs_cluster_blocks(inode,
index >> F2FS_I(inode)->i_log_cluster_size,
- false);
+ CLUSTER_IS_COMPR);
+}
+
+/* return whether cluster contains non raw blocks or not */
+bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index)
+{
+ unsigned int cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size;
+
+ return f2fs_decompressed_blocks(inode, cluster_idx) !=
+ F2FS_I(inode)->i_cluster_size;
}
static bool cluster_may_compress(struct compress_ctx *cc)
@@ -1031,6 +1049,31 @@ static void set_cluster_writeback(struct compress_ctx *cc)
}
}
+static void cancel_cluster_writeback(struct compress_ctx *cc,
+ struct compress_io_ctx *cic, int submitted)
+{
+ int i;
+
+ /* Wait for submitted IOs. */
+ if (submitted > 1) {
+ f2fs_submit_merged_write(F2FS_I_SB(cc->inode), DATA);
+ while (atomic_read(&cic->pending_pages) !=
+ (cc->valid_nr_cpages - submitted + 1))
+ f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
+ }
+
+ /* Cancel writeback and stay locked. */
+ for (i = 0; i < cc->cluster_size; i++) {
+ if (i < submitted) {
+ inode_inc_dirty_pages(cc->inode);
+ lock_page(cc->rpages[i]);
+ }
+ clear_page_private_gcing(cc->rpages[i]);
+ if (folio_test_writeback(page_folio(cc->rpages[i])))
+ end_page_writeback(cc->rpages[i]);
+ }
+}
+
static void set_cluster_dirty(struct compress_ctx *cc)
{
int i;
@@ -1074,14 +1117,14 @@ retry:
if (PageUptodate(page))
f2fs_put_page(page, 1);
else
- f2fs_compress_ctx_add_page(cc, page);
+ f2fs_compress_ctx_add_page(cc, page_folio(page));
}
if (!f2fs_cluster_is_empty(cc)) {
struct bio *bio = NULL;
ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size,
- &last_block_in_bio, false, true);
+ &last_block_in_bio, NULL, true);
f2fs_put_rpages(cc);
f2fs_destroy_compress_ctx(cc, true);
if (ret)
@@ -1104,7 +1147,7 @@ retry:
}
f2fs_wait_on_page_writeback(page, DATA, true, true);
- f2fs_compress_ctx_add_page(cc, page);
+ f2fs_compress_ctx_add_page(cc, page_folio(page));
if (!PageUptodate(page)) {
release_and_retry:
@@ -1154,7 +1197,8 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
.cluster_size = F2FS_I(inode)->i_cluster_size,
.rpages = fsdata,
};
- bool first_index = (index == cc.rpages[0]->index);
+ struct folio *folio = page_folio(cc.rpages[0]);
+ bool first_index = (index == folio->index);
if (copied)
set_cluster_dirty(&cc);
@@ -1198,13 +1242,14 @@ int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock)
int i;
for (i = cluster_size - 1; i >= 0; i--) {
- loff_t start = rpages[i]->index << PAGE_SHIFT;
+ struct folio *folio = page_folio(rpages[i]);
+ loff_t start = folio->index << PAGE_SHIFT;
if (from <= start) {
- zero_user_segment(rpages[i], 0, PAGE_SIZE);
+ folio_zero_segment(folio, 0, folio_size(folio));
} else {
- zero_user_segment(rpages[i], from - start,
- PAGE_SIZE);
+ folio_zero_segment(folio, from - start,
+ folio_size(folio));
break;
}
}
@@ -1232,12 +1277,12 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
.page = NULL,
.encrypted_page = NULL,
.compressed_page = NULL,
- .submitted = 0,
.io_type = io_type,
.io_wbc = wbc,
.encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ?
1 : 0,
};
+ struct folio *folio;
struct dnode_of_data dn;
struct node_info ni;
struct compress_io_ctx *cic;
@@ -1249,7 +1294,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
/* we should bypass data pages to proceed the kworker jobs */
if (unlikely(f2fs_cp_error(sbi))) {
- mapping_set_error(cc->rpages[0]->mapping, -EIO);
+ mapping_set_error(inode->i_mapping, -EIO);
goto out_free;
}
@@ -1276,7 +1321,8 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
goto out_put_dnode;
}
- psize = (loff_t)(cc->rpages[last_index]->index + 1) << PAGE_SHIFT;
+ folio = page_folio(cc->rpages[last_index]);
+ psize = folio_pos(folio) + folio_size(folio);
err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false);
if (err)
@@ -1299,7 +1345,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
for (i = 0; i < cc->valid_nr_cpages; i++) {
f2fs_set_compressed_page(cc->cpages[i], inode,
- cc->rpages[i + 1]->index, cic);
+ page_folio(cc->rpages[i + 1])->index, cic);
fio.compressed_page = cc->cpages[i];
fio.old_blkaddr = data_blkaddr(dn.inode, dn.node_page,
@@ -1334,7 +1380,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
if (blkaddr == COMPRESS_ADDR)
fio.compr_blocks++;
if (__is_valid_data_blkaddr(blkaddr))
- f2fs_invalidate_blocks(sbi, blkaddr);
+ f2fs_invalidate_blocks(sbi, blkaddr, 1);
f2fs_update_data_blkaddr(&dn, COMPRESS_ADDR);
goto unlock_continue;
}
@@ -1344,7 +1390,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
if (i > cc->valid_nr_cpages) {
if (__is_valid_data_blkaddr(blkaddr)) {
- f2fs_invalidate_blocks(sbi, blkaddr);
+ f2fs_invalidate_blocks(sbi, blkaddr, 1);
f2fs_update_data_blkaddr(&dn, NEW_ADDR);
}
goto unlock_continue;
@@ -1358,7 +1404,16 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
fio.compressed_page = cc->cpages[i - 1];
cc->cpages[i - 1] = NULL;
+ fio.submitted = 0;
f2fs_outplace_write_data(&dn, &fio);
+ if (unlikely(!fio.submitted)) {
+ cancel_cluster_writeback(cc, cic, i);
+
+ /* To call fscrypt_finalize_bounce_page */
+ i = cc->valid_nr_cpages;
+ *submitted = 0;
+ goto out_destroy_crypt;
+ }
(*submitted)++;
unlock_continue:
inode_dec_dirty_pages(cc->inode);
@@ -1392,8 +1447,11 @@ unlock_continue:
out_destroy_crypt:
page_array_free(cc->inode, cic->rpages, cc->cluster_size);
- for (--i; i >= 0; i--)
+ for (--i; i >= 0; i--) {
+ if (!cc->cpages[i])
+ continue;
fscrypt_finalize_bounce_page(&cc->cpages[i]);
+ }
out_put_cic:
kmem_cache_free(cic_entry_slab, cic);
out_put_dnode:
@@ -1418,6 +1476,8 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page)
struct f2fs_sb_info *sbi = bio->bi_private;
struct compress_io_ctx *cic =
(struct compress_io_ctx *)page_private(page);
+ enum count_type type = WB_DATA_TYPE(page,
+ f2fs_is_compressed_page(page));
int i;
if (unlikely(bio->bi_status))
@@ -1425,7 +1485,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page)
f2fs_compress_free_page(page);
- dec_page_count(sbi, F2FS_WB_DATA);
+ dec_page_count(sbi, type);
if (atomic_dec_return(&cic->pending_pages))
return;
@@ -1441,12 +1501,14 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page)
}
static int f2fs_write_raw_pages(struct compress_ctx *cc,
- int *submitted,
+ int *submitted_p,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct address_space *mapping = cc->inode->i_mapping;
- int _submitted, compr_blocks, ret, i;
+ struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+ int submitted, compr_blocks, i;
+ int ret = 0;
compr_blocks = f2fs_compressed_blocks(cc);
@@ -1461,6 +1523,10 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc,
if (compr_blocks < 0)
return compr_blocks;
+ /* overwrite compressed cluster w/ normal cluster */
+ if (compr_blocks > 0)
+ f2fs_lock_op(sbi);
+
for (i = 0; i < cc->cluster_size; i++) {
if (!cc->rpages[i])
continue;
@@ -1476,7 +1542,7 @@ continue_unlock:
if (!PageDirty(cc->rpages[i]))
goto continue_unlock;
- if (PageWriteback(cc->rpages[i])) {
+ if (folio_test_writeback(page_folio(cc->rpages[i]))) {
if (wbc->sync_mode == WB_SYNC_NONE)
goto continue_unlock;
f2fs_wait_on_page_writeback(cc->rpages[i], DATA, true, true);
@@ -1485,7 +1551,9 @@ continue_unlock:
if (!clear_page_dirty_for_io(cc->rpages[i]))
goto continue_unlock;
- ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted,
+ submitted = 0;
+ ret = f2fs_write_single_data_page(page_folio(cc->rpages[i]),
+ &submitted,
NULL, NULL, wbc, io_type,
compr_blocks, false);
if (ret) {
@@ -1493,26 +1561,29 @@ continue_unlock:
unlock_page(cc->rpages[i]);
ret = 0;
} else if (ret == -EAGAIN) {
+ ret = 0;
/*
* for quota file, just redirty left pages to
* avoid deadlock caused by cluster update race
* from foreground operation.
*/
if (IS_NOQUOTA(cc->inode))
- return 0;
- ret = 0;
+ goto out;
f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
goto retry_write;
}
- return ret;
+ goto out;
}
- *submitted += _submitted;
+ *submitted_p += submitted;
}
- f2fs_balance_fs(F2FS_M_SB(mapping), true);
+out:
+ if (compr_blocks > 0)
+ f2fs_unlock_op(sbi);
- return 0;
+ f2fs_balance_fs(sbi, true);
+ return ret;
}
int f2fs_write_multi_pages(struct compress_ctx *cc,
@@ -1806,16 +1877,18 @@ void f2fs_put_page_dic(struct page *page, bool in_task)
* check whether cluster blocks are contiguous, and add extent cache entry
* only if cluster blocks are logically and physically contiguous.
*/
-unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn)
+unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn,
+ unsigned int ofs_in_node)
{
- bool compressed = f2fs_data_blkaddr(dn) == COMPRESS_ADDR;
+ bool compressed = data_blkaddr(dn->inode, dn->node_page,
+ ofs_in_node) == COMPRESS_ADDR;
int i = compressed ? 1 : 0;
block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page,
- dn->ofs_in_node + i);
+ ofs_in_node + i);
for (i += 1; i < F2FS_I(dn->inode)->i_cluster_size; i++) {
block_t blkaddr = data_blkaddr(dn->inode, dn->node_page,
- dn->ofs_in_node + i);
+ ofs_in_node + i);
if (!__is_valid_data_blkaddr(blkaddr))
break;
@@ -1837,11 +1910,12 @@ struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi)
return sbi->compress_inode->i_mapping;
}
-void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr)
+void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi,
+ block_t blkaddr, unsigned int len)
{
if (!sbi->compress_inode)
return;
- invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr);
+ invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr + len - 1);
}
void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
@@ -1878,12 +1952,8 @@ void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
set_page_private_data(cpage, ino);
- if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ))
- goto out;
-
memcpy(page_address(cpage), page_address(page), PAGE_SIZE);
SetPageUptodate(cpage);
-out:
f2fs_put_page(cpage, 1);
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 26e317696b33..de4da6d9cd93 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -7,7 +7,6 @@
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
-#include <linux/buffer_head.h>
#include <linux/sched/mm.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
@@ -48,7 +47,7 @@ void f2fs_destroy_bioset(void)
bioset_exit(&f2fs_bioset);
}
-static bool __is_cp_guaranteed(struct page *page)
+bool f2fs_is_cp_guaranteed(struct page *page)
{
struct address_space *mapping = page->mapping;
struct inode *inode;
@@ -65,17 +64,15 @@ static bool __is_cp_guaranteed(struct page *page)
S_ISDIR(inode->i_mode))
return true;
- if (f2fs_is_compressed_page(page))
- return false;
if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) ||
page_private_gcing(page))
return true;
return false;
}
-static enum count_type __read_io_type(struct page *page)
+static enum count_type __read_io_type(struct folio *folio)
{
- struct address_space *mapping = page_file_mapping(page);
+ struct address_space *mapping = folio->mapping;
if (mapping) {
struct inode *inode = mapping->host;
@@ -139,27 +136,22 @@ struct bio_post_read_ctx {
*/
static void f2fs_finish_read_bio(struct bio *bio, bool in_task)
{
- struct bio_vec *bv;
- struct bvec_iter_all iter_all;
+ struct folio_iter fi;
struct bio_post_read_ctx *ctx = bio->bi_private;
- bio_for_each_segment_all(bv, bio, iter_all) {
- struct page *page = bv->bv_page;
+ bio_for_each_folio_all(fi, bio) {
+ struct folio *folio = fi.folio;
- if (f2fs_is_compressed_page(page)) {
+ if (f2fs_is_compressed_page(&folio->page)) {
if (ctx && !ctx->decompression_attempted)
- f2fs_end_read_compressed_page(page, true, 0,
+ f2fs_end_read_compressed_page(&folio->page, true, 0,
in_task);
- f2fs_put_page_dic(page, in_task);
+ f2fs_put_page_dic(&folio->page, in_task);
continue;
}
- if (bio->bi_status)
- ClearPageUptodate(page);
- else
- SetPageUptodate(page);
- dec_page_count(F2FS_P_SB(page), __read_io_type(page));
- unlock_page(page);
+ dec_page_count(F2FS_F_SB(folio), __read_io_type(folio));
+ folio_end_read(folio, bio->bi_status == 0);
}
if (ctx)
@@ -338,18 +330,7 @@ static void f2fs_write_end_io(struct bio *bio)
bio_for_each_segment_all(bvec, bio, iter_all) {
struct page *page = bvec->bv_page;
- enum count_type type = WB_DATA_TYPE(page);
-
- if (page_private_dummy(page)) {
- clear_page_private_dummy(page);
- unlock_page(page);
- mempool_free(page, sbi->write_io_dummy);
-
- if (unlikely(bio->bi_status))
- f2fs_stop_checkpoint(sbi, true,
- STOP_CP_REASON_WRITE_FAIL);
- continue;
- }
+ enum count_type type = WB_DATA_TYPE(page, false);
fscrypt_finalize_bounce_page(&page);
@@ -368,7 +349,7 @@ static void f2fs_write_end_io(struct bio *bio)
}
f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
- page->index != nid_of_node(page));
+ page_folio(page)->index != nid_of_node(page));
dec_page_count(sbi, type);
if (f2fs_in_warm_node_list(sbi, page))
@@ -478,6 +459,8 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
} else {
bio->bi_end_io = f2fs_write_end_io;
bio->bi_private = sbi;
+ bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi,
+ fio->type, fio->temp);
}
iostat_alloc_and_bind_ctx(sbi, bio, NULL);
@@ -524,51 +507,10 @@ void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio,
submit_bio(bio);
}
-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 (start == 0)
- return;
-
- /* 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);
-
- lock_page(page);
-
- zero_user_segment(page, 0, PAGE_SIZE);
- set_page_private_dummy(page);
-
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
- f2fs_bug_on(sbi, 1);
- }
-}
-
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 (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);
- }
- }
-
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
@@ -643,17 +585,20 @@ int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi)
return -ENOMEM;
for (j = HOT; j < n; j++) {
- init_f2fs_rwsem(&sbi->write_io[i][j].io_rwsem);
- sbi->write_io[i][j].sbi = sbi;
- sbi->write_io[i][j].bio = NULL;
- spin_lock_init(&sbi->write_io[i][j].io_lock);
- INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
- INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list);
- init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock);
+ struct f2fs_bio_info *io = &sbi->write_io[i][j];
+
+ init_f2fs_rwsem(&io->io_rwsem);
+ io->sbi = sbi;
+ io->bio = NULL;
+ io->last_block_in_bio = 0;
+ spin_lock_init(&io->io_lock);
+ INIT_LIST_HEAD(&io->io_list);
+ INIT_LIST_HEAD(&io->bio_list);
+ init_f2fs_rwsem(&io->bio_list_lock);
#ifdef CONFIG_BLK_DEV_ZONED
- init_completion(&sbi->write_io[i][j].zone_wait);
- sbi->write_io[i][j].zone_pending_bio = NULL;
- sbi->write_io[i][j].bi_private = NULL;
+ init_completion(&io->zone_wait);
+ io->zone_pending_bio = NULL;
+ io->bi_private = NULL;
#endif
}
}
@@ -735,34 +680,29 @@ void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio;
- struct page *page = fio->encrypted_page ?
- fio->encrypted_page : fio->page;
+ struct folio *fio_folio = page_folio(fio->page);
+ struct folio *data_folio = fio->encrypted_page ?
+ page_folio(fio->encrypted_page) : fio_folio;
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_blkaddr,
fio->is_por ? META_POR : (__is_meta_io(fio) ?
- META_GENERIC : DATA_GENERIC_ENHANCE))) {
- f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR);
+ META_GENERIC : DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
- }
- trace_f2fs_submit_page_bio(page, fio);
+ trace_f2fs_submit_folio_bio(data_folio, fio);
/* Allocate a new bio */
bio = __bio_alloc(fio, 1);
- f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
- fio->page->index, fio, GFP_NOIO);
-
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
- bio_put(bio);
- return -EFAULT;
- }
+ f2fs_set_bio_crypt_ctx(bio, fio_folio->mapping->host,
+ fio_folio->index, fio, GFP_NOIO);
+ bio_add_folio_nofail(bio, data_folio, folio_size(data_folio), 0);
if (fio->io_wbc && !is_read_io(fio->op))
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, fio_folio, PAGE_SIZE);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
- __read_io_type(page) : WB_DATA_TYPE(fio->page));
+ __read_io_type(data_folio) : WB_DATA_TYPE(fio->page, false));
if (is_read_io(bio_op(bio)))
f2fs_submit_read_bio(fio->sbi, bio, fio->type);
@@ -796,16 +736,6 @@ static bool io_is_mergeable(struct f2fs_sb_info *sbi, struct bio *bio,
block_t last_blkaddr,
block_t cur_blkaddr)
{
- if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE)) {
- unsigned int filled_blocks =
- F2FS_BYTES_TO_BLK(bio->bi_iter.bi_size);
- unsigned int io_size = F2FS_IO_SIZE(sbi);
- unsigned int left_vecs = bio->bi_max_vecs - bio->bi_vcnt;
-
- /* IOs in bio is aligned and left space of vectors is not enough */
- if (!(filled_blocks % io_size) && left_vecs < io_size)
- return false;
- }
if (!page_is_mergeable(sbi, bio, last_blkaddr, cur_blkaddr))
return false;
return io_type_is_mergeable(io, fio);
@@ -860,7 +790,7 @@ static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio,
fio->new_blkaddr));
if (f2fs_crypt_mergeable_bio(*bio,
fio->page->mapping->host,
- fio->page->index, fio) &&
+ page_folio(fio->page)->index, fio) &&
bio_add_page(*bio, page, PAGE_SIZE, 0) ==
PAGE_SIZE) {
ret = 0;
@@ -948,12 +878,10 @@ 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)) {
- f2fs_handle_error(fio->sbi, ERROR_INVALID_BLKADDR);
+ __is_meta_io(fio) ? META_GENERIC : DATA_GENERIC))
return -EFSCORRUPTED;
- }
- trace_f2fs_submit_page_bio(page, fio);
+ trace_f2fs_submit_folio_bio(page_folio(page), fio);
if (bio && !page_is_mergeable(fio->sbi, bio, *fio->last_block,
fio->new_blkaddr))
@@ -962,7 +890,7 @@ alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
- fio->page->index, fio, GFP_NOIO);
+ page_folio(fio->page)->index, fio, GFP_NOIO);
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
@@ -971,9 +899,10 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
- inc_page_count(fio->sbi, WB_DATA_TYPE(page));
+ inc_page_count(fio->sbi, WB_DATA_TYPE(page, false));
*fio->last_block = fio->new_blkaddr;
*fio->bio = bio;
@@ -984,6 +913,7 @@ alloc_new:
#ifdef CONFIG_BLK_DEV_ZONED
static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
{
+ struct block_device *bdev = sbi->sb->s_bdev;
int devi = 0;
if (f2fs_is_multi_device(sbi)) {
@@ -994,8 +924,9 @@ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
return false;
}
blkaddr -= FDEV(devi).start_blk;
+ bdev = FDEV(devi).bdev;
}
- return bdev_is_zoned(FDEV(devi).bdev) &&
+ return bdev_is_zoned(bdev) &&
f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
(blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
}
@@ -1007,11 +938,12 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
struct page *bio_page;
+ enum count_type type;
f2fs_bug_on(sbi, is_read_io(fio->op));
f2fs_down_write(&io->io_rwsem);
-
+next:
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) {
wait_for_completion_io(&io->zone_wait);
@@ -1021,7 +953,6 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio)
}
#endif
-next:
if (fio->in_list) {
spin_lock(&io->io_lock);
if (list_empty(&io->io_list)) {
@@ -1046,26 +977,20 @@ next:
/* set submitted = true as a return value */
fio->submitted = 1;
- inc_page_count(sbi, WB_DATA_TYPE(bio_page));
+ type = WB_DATA_TYPE(bio_page, fio->compressed_page);
+ inc_page_count(sbi, type);
if (io->bio &&
(!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio,
fio->new_blkaddr) ||
!f2fs_crypt_mergeable_bio(io->bio, fio->page->mapping->host,
- bio_page->index, fio)))
+ page_folio(bio_page)->index, fio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
- if (F2FS_IO_ALIGNED(sbi) &&
- (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 = 1;
- goto skip;
- }
io->bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
- bio_page->index, fio, GFP_NOIO);
+ page_folio(bio_page)->index, fio, GFP_NOIO);
io->fio = *fio;
}
@@ -1075,15 +1000,12 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
+ PAGE_SIZE);
io->last_block_in_bio = fio->new_blkaddr;
- trace_f2fs_submit_page_write(fio->page, fio);
-skip:
- if (fio->in_list)
- goto next;
-out:
+ trace_f2fs_submit_folio_write(page_folio(fio->page), fio);
#ifdef CONFIG_BLK_DEV_ZONED
if (f2fs_sb_has_blkzoned(sbi) && btype < META &&
is_end_zone_blkaddr(sbi, fio->new_blkaddr)) {
@@ -1096,6 +1018,9 @@ out:
__submit_merged_bio(io);
}
#endif
+ if (fio->in_list)
+ goto next;
+out:
if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) ||
!f2fs_is_checkpoint_ready(sbi))
__submit_merged_bio(io);
@@ -1151,7 +1076,7 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
}
/* This can handle encryption stuffs */
-static int f2fs_submit_page_read(struct inode *inode, struct page *page,
+static int f2fs_submit_page_read(struct inode *inode, struct folio *folio,
block_t blkaddr, blk_opf_t op_flags,
bool for_write)
{
@@ -1159,14 +1084,14 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
struct bio *bio;
bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags,
- page->index, for_write);
+ folio->index, for_write);
if (IS_ERR(bio))
return PTR_ERR(bio);
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, blkaddr);
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+ if (!bio_add_folio(bio, folio, PAGE_SIZE, 0)) {
iostat_update_and_unbind_ctx(bio);
if (bio->bi_private)
mempool_free(bio->bi_private, bio_post_read_ctx_pool);
@@ -1218,7 +1143,8 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+ err = inc_valid_block_count(sbi, dn->inode, &count, true);
+ if (unlikely(err))
return err;
trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
@@ -1285,8 +1211,6 @@ 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;
@@ -1312,8 +1236,6 @@ 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:
@@ -1337,7 +1259,7 @@ got_it:
return page;
}
- err = f2fs_submit_page_read(inode, page, dn.data_blkaddr,
+ err = f2fs_submit_page_read(inode, page_folio(page), dn.data_blkaddr,
op_flags, for_write);
if (err)
goto put_err;
@@ -1354,7 +1276,7 @@ struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
struct address_space *mapping = inode->i_mapping;
struct page *page;
- page = find_get_page(mapping, index);
+ page = find_get_page_flags(mapping, index, FGP_ACCESSED);
if (page && PageUptodate(page))
return page;
f2fs_put_page(page, 0);
@@ -1475,17 +1397,20 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
dn->data_blkaddr = f2fs_data_blkaddr(dn);
if (dn->data_blkaddr == NULL_ADDR) {
- err = inc_valid_block_count(sbi, dn->inode, &count);
+ err = inc_valid_block_count(sbi, dn->inode, &count, true);
if (unlikely(err))
return err;
}
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,
- &sum, seg_type, NULL);
+ err = f2fs_allocate_data_block(sbi, NULL, old_blkaddr,
+ &dn->data_blkaddr, &sum, seg_type, NULL);
+ if (err)
+ return err;
+
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
- f2fs_invalidate_internal_cache(sbi, old_blkaddr);
+ f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1);
f2fs_update_data_blkaddr(dn, dn->data_blkaddr);
return 0;
@@ -1578,6 +1503,25 @@ static bool f2fs_map_blocks_cached(struct inode *inode,
return true;
}
+static bool map_is_mergeable(struct f2fs_sb_info *sbi,
+ struct f2fs_map_blocks *map,
+ block_t blkaddr, int flag, int bidx,
+ int ofs)
+{
+ if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
+ return false;
+ if (map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs))
+ return true;
+ if (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR)
+ return true;
+ if (flag == F2FS_GET_BLOCK_PRE_DIO)
+ return true;
+ if (flag == F2FS_GET_BLOCK_DIO &&
+ map->m_pblk == NULL_ADDR && blkaddr == NULL_ADDR)
+ return true;
+ return false;
+}
+
/*
* f2fs_map_blocks() tries to find or build mapping relationship which
* maps continuous logical blocks to physical blocks, and return such
@@ -1641,13 +1585,13 @@ next_block:
if (!is_hole &&
!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
err = -EFSCORRUPTED;
- f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
goto sync_out;
}
/* use out-place-update for direct IO under LFS mode */
- if (map->m_may_create &&
- (is_hole || (f2fs_lfs_mode(sbi) && flag == F2FS_GET_BLOCK_DIO))) {
+ if (map->m_may_create && (is_hole ||
+ (flag == F2FS_GET_BLOCK_DIO && f2fs_lfs_mode(sbi) &&
+ !f2fs_is_pinned_file(inode)))) {
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto sync_out;
@@ -1700,6 +1644,10 @@ next_block:
goto sync_out;
}
break;
+ case F2FS_GET_BLOCK_DIO:
+ if (map->m_next_pgofs)
+ *map->m_next_pgofs = pgofs + 1;
+ break;
default:
/* for defragment case */
if (map->m_next_pgofs)
@@ -1718,19 +1666,16 @@ next_block:
/* reserved delalloc block should be mapped for fiemap. */
if (blkaddr == NEW_ADDR)
map->m_flags |= F2FS_MAP_DELALLOC;
- map->m_flags |= F2FS_MAP_MAPPED;
+ /* DIO READ and hole case, should not map the blocks. */
+ if (!(flag == F2FS_GET_BLOCK_DIO && is_hole && !map->m_may_create))
+ map->m_flags |= F2FS_MAP_MAPPED;
map->m_pblk = blkaddr;
map->m_len = 1;
if (map->m_multidev_dio)
map->m_bdev = FDEV(bidx).bdev;
- } else if ((map->m_pblk != NEW_ADDR &&
- blkaddr == (map->m_pblk + ofs)) ||
- (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
- flag == F2FS_GET_BLOCK_PRE_DIO) {
- if (map->m_multidev_dio && map->m_bdev != FDEV(bidx).bdev)
- goto sync_out;
+ } else if (map_is_mergeable(sbi, map, blkaddr, flag, bidx, ofs)) {
ofs++;
map->m_len++;
} else {
@@ -1758,6 +1703,14 @@ skip:
dn.ofs_in_node = end_offset;
}
+ if (flag == F2FS_GET_BLOCK_DIO && f2fs_lfs_mode(sbi) &&
+ map->m_may_create) {
+ /* the next block to be allocated may not be contiguous. */
+ if (GET_SEGOFF_FROM_SEG0(sbi, blkaddr) % BLKS_PER_SEC(sbi) ==
+ CAP_BLKS_PER_SEC(sbi) - 1)
+ goto sync_out;
+ }
+
if (pgofs >= end)
goto sync_out;
else if (dn.ofs_in_node < end_offset)
@@ -1856,16 +1809,6 @@ bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len)
return true;
}
-static inline u64 bytes_to_blks(struct inode *inode, u64 bytes)
-{
- return (bytes >> inode->i_blkbits);
-}
-
-static inline u64 blks_to_bytes(struct inode *inode, u64 blks)
-{
- return (blks << inode->i_blkbits);
-}
-
static int f2fs_xattr_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo)
{
@@ -1891,7 +1834,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
return err;
}
- phys = blks_to_bytes(inode, ni.blk_addr);
+ phys = F2FS_BLK_TO_BYTES(ni.blk_addr);
offset = offsetof(struct f2fs_inode, i_addr) +
sizeof(__le32) * (DEF_ADDRS_PER_INODE -
get_inline_xattr_addrs(inode));
@@ -1923,7 +1866,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
return err;
}
- phys = blks_to_bytes(inode, ni.blk_addr);
+ phys = F2FS_BLK_TO_BYTES(ni.blk_addr);
len = inode->i_sb->s_blocksize;
f2fs_put_page(page, 1);
@@ -1939,30 +1882,11 @@ static int f2fs_xattr_fiemap(struct inode *inode,
return (err < 0 ? err : 0);
}
-static loff_t max_inode_blocks(struct inode *inode)
-{
- loff_t result = ADDRS_PER_INODE(inode);
- loff_t leaf_count = ADDRS_PER_BLOCK(inode);
-
- /* two direct node blocks */
- result += (leaf_count * 2);
-
- /* two indirect node blocks */
- leaf_count *= NIDS_PER_BLOCK;
- result += (leaf_count * 2);
-
- /* one double indirect node block */
- leaf_count *= NIDS_PER_BLOCK;
- result += leaf_count;
-
- return result;
-}
-
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
struct f2fs_map_blocks map;
- sector_t start_blk, last_blk;
+ sector_t start_blk, last_blk, blk_len, max_len;
pgoff_t next_pgofs;
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
@@ -1984,7 +1908,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
inode_lock_shared(inode);
- maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
+ maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode));
if (start > maxbytes) {
ret = -EFBIG;
goto out;
@@ -2004,16 +1928,15 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
goto out;
}
- if (bytes_to_blks(inode, len) == 0)
- len = blks_to_bytes(inode, 1);
-
- start_blk = bytes_to_blks(inode, start);
- last_blk = bytes_to_blks(inode, start + len - 1);
+ start_blk = F2FS_BYTES_TO_BLK(start);
+ last_blk = F2FS_BYTES_TO_BLK(start + len - 1);
+ blk_len = last_blk - start_blk + 1;
+ max_len = F2FS_BYTES_TO_BLK(maxbytes) - start_blk;
next:
memset(&map, 0, sizeof(map));
map.m_lblk = start_blk;
- map.m_len = bytes_to_blks(inode, len);
+ map.m_len = blk_len;
map.m_next_pgofs = &next_pgofs;
map.m_seg_type = NO_CHECK_TYPE;
@@ -2030,13 +1953,23 @@ next:
if (!compr_cluster && !(map.m_flags & F2FS_MAP_FLAGS)) {
start_blk = next_pgofs;
- if (blks_to_bytes(inode, start_blk) < blks_to_bytes(inode,
- max_inode_blocks(inode)))
+ if (F2FS_BLK_TO_BYTES(start_blk) < maxbytes)
goto prep_next;
flags |= FIEMAP_EXTENT_LAST;
}
+ /*
+ * current extent may cross boundary of inquiry, increase len to
+ * requery.
+ */
+ if (!compr_cluster && (map.m_flags & F2FS_MAP_MAPPED) &&
+ map.m_lblk + map.m_len - 1 == last_blk &&
+ blk_len != max_len) {
+ blk_len = max_len;
+ goto next;
+ }
+
compr_appended = false;
/* In a case of compressed cluster, append this to the last extent */
if (compr_cluster && ((map.m_flags & F2FS_MAP_DELALLOC) ||
@@ -2068,14 +2001,14 @@ skip_fill:
} else if (compr_appended) {
unsigned int appended_blks = cluster_size -
count_in_cluster + 1;
- size += blks_to_bytes(inode, appended_blks);
+ size += F2FS_BLK_TO_BYTES(appended_blks);
start_blk += appended_blks;
compr_cluster = false;
} else {
- logical = blks_to_bytes(inode, start_blk);
+ logical = F2FS_BLK_TO_BYTES(start_blk);
phys = __is_valid_data_blkaddr(map.m_pblk) ?
- blks_to_bytes(inode, map.m_pblk) : 0;
- size = blks_to_bytes(inode, map.m_len);
+ F2FS_BLK_TO_BYTES(map.m_pblk) : 0;
+ size = F2FS_BLK_TO_BYTES(map.m_len);
flags = 0;
if (compr_cluster) {
@@ -2083,13 +2016,13 @@ skip_fill:
count_in_cluster += map.m_len;
if (count_in_cluster == cluster_size) {
compr_cluster = false;
- size += blks_to_bytes(inode, 1);
+ size += F2FS_BLKSIZE;
}
} else if (map.m_flags & F2FS_MAP_DELALLOC) {
flags = FIEMAP_EXTENT_UNWRITTEN;
}
- start_blk += bytes_to_blks(inode, size);
+ start_blk += F2FS_BYTES_TO_BLK(size);
}
prep_next:
@@ -2109,30 +2042,36 @@ out:
static inline loff_t f2fs_readpage_limit(struct inode *inode)
{
if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode))
- return inode->i_sb->s_maxbytes;
+ return F2FS_BLK_TO_BYTES(max_file_blocks(inode));
return i_size_read(inode);
}
-static int f2fs_read_single_page(struct inode *inode, struct page *page,
+static inline blk_opf_t f2fs_ra_op_flags(struct readahead_control *rac)
+{
+ return rac ? REQ_RAHEAD : 0;
+}
+
+static int f2fs_read_single_page(struct inode *inode, struct folio *folio,
unsigned nr_pages,
struct f2fs_map_blocks *map,
struct bio **bio_ret,
sector_t *last_block_in_bio,
- bool is_readahead)
+ struct readahead_control *rac)
{
struct bio *bio = *bio_ret;
- const unsigned blocksize = blks_to_bytes(inode, 1);
+ const unsigned int blocksize = F2FS_BLKSIZE;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
+ pgoff_t index = folio_index(folio);
int ret = 0;
- block_in_file = (sector_t)page_index(page);
+ block_in_file = (sector_t)index;
last_block = block_in_file + nr_pages;
- last_block_in_file = bytes_to_blks(inode,
- f2fs_readpage_limit(inode) + blocksize - 1);
+ last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) +
+ blocksize - 1);
if (last_block > last_block_in_file)
last_block = last_block_in_file;
@@ -2160,26 +2099,24 @@ static int f2fs_read_single_page(struct inode *inode, struct page *page,
got_it:
if ((map->m_flags & F2FS_MAP_MAPPED)) {
block_nr = map->m_pblk + block_in_file - map->m_lblk;
- SetPageMappedToDisk(page);
+ folio_set_mappedtodisk(folio);
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 {
zero_out:
- zero_user_segment(page, 0, PAGE_SIZE);
- if (f2fs_need_verity(inode, page->index) &&
- !fsverity_verify_page(page)) {
+ folio_zero_segment(folio, 0, folio_size(folio));
+ if (f2fs_need_verity(inode, index) &&
+ !fsverity_verify_folio(folio)) {
ret = -EIO;
goto out;
}
- if (!PageUptodate(page))
- SetPageUptodate(page);
- unlock_page(page);
+ if (!folio_test_uptodate(folio))
+ folio_mark_uptodate(folio);
+ folio_unlock(folio);
goto out;
}
@@ -2189,14 +2126,14 @@ zero_out:
*/
if (bio && (!page_is_mergeable(F2FS_I_SB(inode), bio,
*last_block_in_bio, block_nr) ||
- !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
+ !f2fs_crypt_mergeable_bio(bio, inode, index, NULL))) {
submit_and_realloc:
f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
}
if (bio == NULL) {
bio = f2fs_grab_read_bio(inode, block_nr, nr_pages,
- is_readahead ? REQ_RAHEAD : 0, page->index,
+ f2fs_ra_op_flags(rac), index,
false);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
@@ -2211,7 +2148,7 @@ submit_and_realloc:
*/
f2fs_wait_on_block_writeback(inode, block_nr);
- if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+ if (!bio_add_folio(bio, folio, blocksize, 0))
goto submit_and_realloc;
inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
@@ -2226,7 +2163,7 @@ out:
#ifdef CONFIG_F2FS_FS_COMPRESSION
int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
unsigned nr_pages, sector_t *last_block_in_bio,
- bool is_readahead, bool for_write)
+ struct readahead_control *rac, bool for_write)
{
struct dnode_of_data dn;
struct inode *inode = cc->inode;
@@ -2234,7 +2171,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
struct bio *bio = *bio_ret;
unsigned int start_idx = cc->cluster_idx << cc->log_cluster_size;
sector_t last_block_in_file;
- const unsigned blocksize = blks_to_bytes(inode, 1);
+ const unsigned int blocksize = F2FS_BLKSIZE;
struct decompress_io_ctx *dic = NULL;
struct extent_info ei = {};
bool from_dnode = true;
@@ -2243,25 +2180,28 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
- last_block_in_file = bytes_to_blks(inode,
- f2fs_readpage_limit(inode) + blocksize - 1);
+ last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) +
+ blocksize - 1);
/* get rid of pages beyond EOF */
for (i = 0; i < cc->cluster_size; i++) {
struct page *page = cc->rpages[i];
+ struct folio *folio;
if (!page)
continue;
- if ((sector_t)page->index >= last_block_in_file) {
- zero_user_segment(page, 0, PAGE_SIZE);
- if (!PageUptodate(page))
- SetPageUptodate(page);
- } else if (!PageUptodate(page)) {
+
+ folio = page_folio(page);
+ if ((sector_t)folio->index >= last_block_in_file) {
+ folio_zero_segment(folio, 0, folio_size(folio));
+ if (!folio_test_uptodate(folio))
+ folio_mark_uptodate(folio);
+ } else if (!folio_test_uptodate(folio)) {
continue;
}
- unlock_page(page);
+ folio_unlock(folio);
if (for_write)
- put_page(page);
+ folio_put(folio);
cc->rpages[i] = NULL;
cc->nr_rpages--;
}
@@ -2321,7 +2261,7 @@ skip_reading_dnode:
}
for (i = 0; i < cc->nr_cpages; i++) {
- struct page *page = dic->cpages[i];
+ struct folio *folio = page_folio(dic->cpages[i]);
block_t blkaddr;
struct bio_post_read_ctx *ctx;
@@ -2331,7 +2271,8 @@ skip_reading_dnode:
f2fs_wait_on_block_writeback(inode, blkaddr);
- if (f2fs_load_compressed_page(sbi, page, blkaddr)) {
+ if (f2fs_load_compressed_page(sbi, folio_page(folio, 0),
+ blkaddr)) {
if (atomic_dec_and_test(&dic->remaining_pages)) {
f2fs_decompress_cluster(dic, true);
break;
@@ -2341,7 +2282,7 @@ skip_reading_dnode:
if (bio && (!page_is_mergeable(sbi, bio,
*last_block_in_bio, blkaddr) ||
- !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
+ !f2fs_crypt_mergeable_bio(bio, inode, folio->index, NULL))) {
submit_and_realloc:
f2fs_submit_read_bio(sbi, bio, DATA);
bio = NULL;
@@ -2349,8 +2290,8 @@ submit_and_realloc:
if (!bio) {
bio = f2fs_grab_read_bio(inode, blkaddr, nr_pages,
- is_readahead ? REQ_RAHEAD : 0,
- page->index, for_write);
+ f2fs_ra_op_flags(rac),
+ folio->index, for_write);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
f2fs_decompress_end_io(dic, ret, true);
@@ -2360,7 +2301,7 @@ submit_and_realloc:
}
}
- if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+ if (!bio_add_folio(bio, folio, blocksize, 0))
goto submit_and_realloc;
ctx = get_post_read_ctx(bio);
@@ -2398,7 +2339,7 @@ out:
* Major change was from block_size == page_size in f2fs by default.
*/
static int f2fs_mpage_readpages(struct inode *inode,
- struct readahead_control *rac, struct page *page)
+ struct readahead_control *rac, struct folio *folio)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
@@ -2415,6 +2356,7 @@ static int f2fs_mpage_readpages(struct inode *inode,
.nr_cpages = 0,
};
pgoff_t nc_cluster_idx = NULL_CLUSTER;
+ pgoff_t index;
#endif
unsigned nr_pages = rac ? readahead_count(rac) : 1;
unsigned max_nr_pages = nr_pages;
@@ -2431,64 +2373,63 @@ static int f2fs_mpage_readpages(struct inode *inode,
for (; nr_pages; nr_pages--) {
if (rac) {
- page = readahead_page(rac);
- prefetchw(&page->flags);
+ folio = readahead_folio(rac);
+ prefetchw(&folio->flags);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
- if (f2fs_compressed_file(inode)) {
- /* there are remained compressed pages, submit them */
- if (!f2fs_cluster_can_merge_page(&cc, page->index)) {
- ret = f2fs_read_multi_pages(&cc, &bio,
- max_nr_pages,
- &last_block_in_bio,
- rac != NULL, false);
- f2fs_destroy_compress_ctx(&cc, false);
- if (ret)
- goto set_error_page;
- }
- if (cc.cluster_idx == NULL_CLUSTER) {
- if (nc_cluster_idx ==
- page->index >> cc.log_cluster_size) {
- goto read_single_page;
- }
-
- ret = f2fs_is_compressed_cluster(inode, page->index);
- if (ret < 0)
- goto set_error_page;
- else if (!ret) {
- nc_cluster_idx =
- page->index >> cc.log_cluster_size;
- goto read_single_page;
- }
-
- nc_cluster_idx = NULL_CLUSTER;
- }
- ret = f2fs_init_compress_ctx(&cc);
+ index = folio_index(folio);
+
+ if (!f2fs_compressed_file(inode))
+ goto read_single_page;
+
+ /* there are remained compressed pages, submit them */
+ if (!f2fs_cluster_can_merge_page(&cc, index)) {
+ ret = f2fs_read_multi_pages(&cc, &bio,
+ max_nr_pages,
+ &last_block_in_bio,
+ rac, false);
+ f2fs_destroy_compress_ctx(&cc, false);
if (ret)
goto set_error_page;
+ }
+ if (cc.cluster_idx == NULL_CLUSTER) {
+ if (nc_cluster_idx == index >> cc.log_cluster_size)
+ goto read_single_page;
- f2fs_compress_ctx_add_page(&cc, page);
+ ret = f2fs_is_compressed_cluster(inode, index);
+ if (ret < 0)
+ goto set_error_page;
+ else if (!ret) {
+ nc_cluster_idx =
+ index >> cc.log_cluster_size;
+ goto read_single_page;
+ }
- goto next_page;
+ nc_cluster_idx = NULL_CLUSTER;
}
+ ret = f2fs_init_compress_ctx(&cc);
+ if (ret)
+ goto set_error_page;
+
+ f2fs_compress_ctx_add_page(&cc, folio);
+
+ goto next_page;
read_single_page:
#endif
- ret = f2fs_read_single_page(inode, page, max_nr_pages, &map,
+ ret = f2fs_read_single_page(inode, folio, max_nr_pages, &map,
&bio, &last_block_in_bio, rac);
if (ret) {
#ifdef CONFIG_F2FS_FS_COMPRESSION
set_error_page:
#endif
- zero_user_segment(page, 0, PAGE_SIZE);
- unlock_page(page);
+ folio_zero_segment(folio, 0, folio_size(folio));
+ folio_unlock(folio);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
next_page:
#endif
- if (rac)
- put_page(page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
@@ -2497,7 +2438,7 @@ next_page:
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
- rac != NULL, false);
+ rac, false);
f2fs_destroy_compress_ctx(&cc, false);
}
}
@@ -2510,22 +2451,21 @@ next_page:
static int f2fs_read_data_folio(struct file *file, struct folio *folio)
{
- struct page *page = &folio->page;
- struct inode *inode = page_file_mapping(page)->host;
+ struct inode *inode = folio->mapping->host;
int ret = -EAGAIN;
- trace_f2fs_readpage(page, DATA);
+ trace_f2fs_readpage(folio, DATA);
if (!f2fs_is_compress_backend_ready(inode)) {
- unlock_page(page);
+ folio_unlock(folio);
return -EOPNOTSUPP;
}
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
- ret = f2fs_read_inline_data(inode, page);
+ ret = f2fs_read_inline_data(inode, folio);
if (ret == -EAGAIN)
- ret = f2fs_mpage_readpages(inode, NULL, page);
+ ret = f2fs_mpage_readpages(inode, NULL, folio);
return ret;
}
@@ -2650,7 +2590,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
return true;
if (IS_NOQUOTA(inode))
return true;
- if (f2fs_is_atomic_file(inode))
+ if (f2fs_used_in_atomic_write(inode))
return true;
/* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */
if (f2fs_compressed_file(inode) &&
@@ -2668,8 +2608,6 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
if (fio) {
if (page_private_gcing(fio->page))
return true;
- if (page_private_dummy(fio->page))
- return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
f2fs_is_checkpointed_data(sbi, fio->old_blkaddr)))
return true;
@@ -2689,28 +2627,28 @@ static inline bool need_inplace_update(struct f2fs_io_info *fio)
int f2fs_do_write_data_page(struct f2fs_io_info *fio)
{
- struct page *page = fio->page;
- struct inode *inode = page->mapping->host;
+ struct folio *folio = page_folio(fio->page);
+ struct inode *inode = folio->mapping->host;
struct dnode_of_data dn;
struct node_info ni;
bool ipu_force = false;
+ bool atomic_commit;
int err = 0;
/* Use COW inode to make dnode_of_data for atomic write */
- if (f2fs_is_atomic_file(inode))
+ atomic_commit = f2fs_is_atomic_file(inode) &&
+ page_private_atomic(folio_page(folio, 0));
+ if (atomic_commit)
set_new_dnode(&dn, F2FS_I(inode)->cow_inode, NULL, NULL, 0);
else
set_new_dnode(&dn, inode, NULL, NULL, 0);
if (need_inplace_update(fio) &&
- f2fs_lookup_read_extent_cache_block(inode, page->index,
+ f2fs_lookup_read_extent_cache_block(inode, folio->index,
&fio->old_blkaddr)) {
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->old_blkaddr,
- DATA_GENERIC_ENHANCE)) {
- f2fs_handle_error(fio->sbi,
- ERROR_INVALID_BLKADDR);
+ DATA_GENERIC_ENHANCE))
return -EFSCORRUPTED;
- }
ipu_force = true;
fio->need_lock = LOCK_DONE;
@@ -2721,7 +2659,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
return -EAGAIN;
- err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+ err = f2fs_get_dnode_of_data(&dn, folio->index, LOOKUP_NODE);
if (err)
goto out;
@@ -2729,8 +2667,8 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
/* This page is already truncated */
if (fio->old_blkaddr == NULL_ADDR) {
- ClearPageUptodate(page);
- clear_page_private_gcing(page);
+ folio_clear_uptodate(folio);
+ clear_page_private_gcing(folio_page(folio, 0));
goto out_writepage;
}
got_it:
@@ -2738,12 +2676,11 @@ 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;
}
/* wait for GCed page writeback via META_MAPPING */
- if (fio->post_read)
+ if (fio->meta_gc)
f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
/*
@@ -2757,7 +2694,7 @@ got_it:
if (err)
goto out_writepage;
- set_page_writeback(page);
+ folio_start_writeback(folio);
f2fs_put_dnode(&dn);
if (fio->need_lock == LOCK_REQ)
f2fs_unlock_op(fio->sbi);
@@ -2765,12 +2702,11 @@ got_it:
if (err) {
if (fscrypt_inode_uses_fs_layer_crypto(inode))
fscrypt_finalize_bounce_page(&fio->encrypted_page);
- if (PageWriteback(page))
- end_page_writeback(page);
+ folio_end_writeback(folio);
} else {
set_inode_flag(inode, FI_UPDATE_WRITE);
}
- trace_f2fs_do_write_data_page(fio->page, IPU);
+ trace_f2fs_do_write_data_page(folio, IPU);
return err;
}
@@ -2792,15 +2728,17 @@ got_it:
if (err)
goto out_writepage;
- set_page_writeback(page);
+ folio_start_writeback(folio);
if (fio->compr_blocks && fio->old_blkaddr == COMPRESS_ADDR)
f2fs_i_compr_blocks_update(inode, fio->compr_blocks - 1, false);
/* LFS mode write path */
f2fs_outplace_write_data(&dn, fio);
- trace_f2fs_do_write_data_page(page, OPU);
+ trace_f2fs_do_write_data_page(folio, OPU);
set_inode_flag(inode, FI_APPEND_WRITE);
+ if (atomic_commit)
+ clear_page_private_atomic(folio_page(folio, 0));
out_writepage:
f2fs_put_dnode(&dn);
out:
@@ -2809,7 +2747,7 @@ out:
return err;
}
-int f2fs_write_single_data_page(struct page *page, int *submitted,
+int f2fs_write_single_data_page(struct folio *folio, int *submitted,
struct bio **bio,
sector_t *last_block,
struct writeback_control *wbc,
@@ -2817,12 +2755,13 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
int compr_blocks,
bool allow_balance)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
+ struct page *page = folio_page(folio, 0);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long)i_size)
>> PAGE_SHIFT;
- loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT;
+ loff_t psize = (loff_t)(folio->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
bool quota_inode = IS_NOQUOTA(inode);
@@ -2838,19 +2777,19 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
.encrypted_page = NULL,
.submitted = 0,
.compr_blocks = compr_blocks,
- .need_lock = LOCK_RETRY,
- .post_read = f2fs_post_read_required(inode) ? 1 : 0,
+ .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY,
+ .meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0,
.io_type = io_type,
.io_wbc = wbc,
.bio = bio,
.last_block = last_block,
};
- trace_f2fs_writepage(page, DATA);
+ trace_f2fs_writepage(folio, DATA);
/* we should bypass data pages to proceed the kworker jobs */
if (unlikely(f2fs_cp_error(sbi))) {
- mapping_set_error(page->mapping, -EIO);
+ mapping_set_error(folio->mapping, -EIO);
/*
* don't drop any dirty dentry pages for keeping lastest
* directory structure.
@@ -2868,7 +2807,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
- if (page->index < end_index ||
+ if (folio->index < end_index ||
f2fs_verity_in_progress(inode) ||
compr_blocks)
goto write;
@@ -2878,10 +2817,10 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
* this page does not have to be written to disk.
*/
offset = i_size & (PAGE_SIZE - 1);
- if ((page->index >= end_index + 1) || !offset)
+ if ((folio->index >= end_index + 1) || !offset)
goto out;
- zero_user_segment(page, offset, PAGE_SIZE);
+ folio_zero_segment(folio, offset, folio_size(folio));
write:
/* Dentry/quota blocks are controlled by checkpoint */
if (S_ISDIR(inode->i_mode) || quota_inode) {
@@ -2911,7 +2850,7 @@ write:
err = -EAGAIN;
if (f2fs_has_inline_data(inode)) {
- err = f2fs_write_inline_data(inode, page);
+ err = f2fs_write_inline_data(inode, folio);
if (!err)
goto out;
}
@@ -2919,6 +2858,7 @@ write:
if (err == -EAGAIN) {
err = f2fs_do_write_data_page(&fio);
if (err == -EAGAIN) {
+ f2fs_bug_on(sbi, compr_blocks);
fio.need_lock = LOCK_REQ;
err = f2fs_do_write_data_page(&fio);
}
@@ -2940,7 +2880,7 @@ done:
out:
inode_dec_dirty_pages(inode);
if (err) {
- ClearPageUptodate(page);
+ folio_clear_uptodate(folio);
clear_page_private_gcing(page);
}
@@ -2950,7 +2890,7 @@ out:
f2fs_remove_dirty_inode(inode);
submitted = NULL;
}
- unlock_page(page);
+ folio_unlock(folio);
if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode) &&
!F2FS_I(inode)->wb_task && allow_balance)
f2fs_balance_fs(sbi, need_balance_fs);
@@ -2968,7 +2908,7 @@ out:
return 0;
redirty_out:
- redirty_page_for_writepage(wbc, page);
+ folio_redirty_for_writepage(wbc, folio);
/*
* pageout() in MM translates EAGAIN, so calls handle_write_error()
* -> mapping_set_error() -> set_bit(AS_EIO, ...).
@@ -2977,29 +2917,30 @@ redirty_out:
*/
if (!err || wbc->for_reclaim)
return AOP_WRITEPAGE_ACTIVATE;
- unlock_page(page);
+ folio_unlock(folio);
return err;
}
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
+ struct folio *folio = page_folio(page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
goto out;
if (f2fs_compressed_file(inode)) {
- if (f2fs_is_compressed_cluster(inode, page->index)) {
- redirty_page_for_writepage(wbc, page);
+ if (f2fs_is_compressed_cluster(inode, folio->index)) {
+ folio_redirty_for_writepage(wbc, folio);
return AOP_WRITEPAGE_ACTIVATE;
}
}
out:
#endif
- return f2fs_write_single_data_page(page, NULL, NULL, NULL,
+ return f2fs_write_single_data_page(folio, NULL, NULL, NULL,
wbc, FS_DATA_IO, 0, true);
}
@@ -3205,11 +3146,12 @@ continue_unlock:
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
folio_get(folio);
- f2fs_compress_ctx_add_page(&cc, &folio->page);
+ f2fs_compress_ctx_add_page(&cc, folio);
continue;
}
#endif
- ret = f2fs_write_single_data_page(&folio->page,
+ submitted = 0;
+ ret = f2fs_write_single_data_page(folio,
&submitted, &bio, &last_block,
wbc, io_type, 0, true);
if (ret == AOP_WRITEPAGE_ACTIVATE)
@@ -3417,11 +3359,11 @@ void f2fs_write_failed(struct inode *inode, loff_t to)
}
static int prepare_write_begin(struct f2fs_sb_info *sbi,
- struct page *page, loff_t pos, unsigned len,
+ struct folio *folio, loff_t pos, unsigned int len,
block_t *blk_addr, bool *node_changed)
{
- struct inode *inode = page->mapping->host;
- pgoff_t index = page->index;
+ struct inode *inode = folio->mapping->host;
+ pgoff_t index = folio->index;
struct dnode_of_data dn;
struct page *ipage;
bool locked = false;
@@ -3458,19 +3400,24 @@ restart:
if (f2fs_has_inline_data(inode)) {
if (pos + len <= MAX_INLINE_DATA(inode)) {
- f2fs_do_read_inline_data(page, ipage);
+ f2fs_do_read_inline_data(folio, ipage);
set_inode_flag(inode, FI_DATA_EXIST);
if (inode->i_nlink)
set_page_private_inline(ipage);
goto out;
}
- err = f2fs_convert_inline_page(&dn, page);
+ err = f2fs_convert_inline_page(&dn, folio_page(folio, 0));
if (err || dn.data_blkaddr != NULL_ADDR)
goto out;
}
if (!f2fs_lookup_read_extent_cache_block(inode, index,
&dn.data_blkaddr)) {
+ if (IS_DEVICE_ALIASING(inode)) {
+ err = -ENODATA;
+ goto out;
+ }
+
if (locked) {
err = f2fs_reserve_block(&dn, index);
goto out;
@@ -3557,12 +3504,12 @@ unlock_out:
}
static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi,
- struct page *page, loff_t pos, unsigned int len,
+ struct folio *folio, loff_t pos, unsigned int len,
block_t *blk_addr, bool *node_changed, bool *use_cow)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
struct inode *cow_inode = F2FS_I(inode)->cow_inode;
- pgoff_t index = page->index;
+ pgoff_t index = folio->index;
int err = 0;
block_t ori_blk_addr = NULL_ADDR;
@@ -3600,12 +3547,12 @@ reserve_block:
}
static int f2fs_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+ loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct page *page = NULL;
- pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
+ struct folio *folio;
+ pgoff_t index = pos >> PAGE_SHIFT;
bool need_balance = false;
bool use_cow = false;
block_t blkaddr = NULL_ADDR;
@@ -3621,7 +3568,7 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
/*
* We should check this at this moment to avoid deadlock on inode page
* and #0 page. The locking rule for inline_data conversion should be:
- * lock_page(page #0) -> lock_page(inode_page)
+ * folio_lock(folio #0) -> folio_lock(inode_page)
*/
if (index != 0) {
err = f2fs_convert_inline_inode(inode);
@@ -3632,18 +3579,20 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
int ret;
+ struct page *page;
*fsdata = NULL;
if (len == PAGE_SIZE && !(f2fs_is_atomic_file(inode)))
goto repeat;
- ret = f2fs_prepare_compress_overwrite(inode, pagep,
+ ret = f2fs_prepare_compress_overwrite(inode, &page,
index, fsdata);
if (ret < 0) {
err = ret;
goto fail;
} else if (ret) {
+ *foliop = page_folio(page);
return 0;
}
}
@@ -3651,82 +3600,85 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
repeat:
/*
- * Do not use grab_cache_page_write_begin() to avoid deadlock due to
- * wait_for_stable_page. Will wait that below with our IO control.
+ * Do not use FGP_STABLE to avoid deadlock.
+ * Will wait that below with our IO control.
*/
- page = f2fs_pagecache_get_page(mapping, index,
+ folio = __filemap_get_folio(mapping, index,
FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
- if (!page) {
- err = -ENOMEM;
+ if (IS_ERR(folio)) {
+ err = PTR_ERR(folio);
goto fail;
}
/* TODO: cluster can be compressed due to race with .writepage */
- *pagep = page;
+ *foliop = folio;
if (f2fs_is_atomic_file(inode))
- err = prepare_atomic_write_begin(sbi, page, pos, len,
+ err = prepare_atomic_write_begin(sbi, folio, pos, len,
&blkaddr, &need_balance, &use_cow);
else
- err = prepare_write_begin(sbi, page, pos, len,
+ err = prepare_write_begin(sbi, folio, pos, len,
&blkaddr, &need_balance);
if (err)
- goto fail;
+ goto put_folio;
if (need_balance && !IS_NOQUOTA(inode) &&
has_not_enough_free_secs(sbi, 0, 0)) {
- unlock_page(page);
+ folio_unlock(folio);
f2fs_balance_fs(sbi, true);
- lock_page(page);
- if (page->mapping != mapping) {
- /* The page got truncated from under us */
- f2fs_put_page(page, 1);
+ folio_lock(folio);
+ if (folio->mapping != mapping) {
+ /* The folio got truncated from under us */
+ folio_unlock(folio);
+ folio_put(folio);
goto repeat;
}
}
- f2fs_wait_on_page_writeback(page, DATA, false, true);
+ f2fs_wait_on_page_writeback(&folio->page, DATA, false, true);
- if (len == PAGE_SIZE || PageUptodate(page))
+ if (len == folio_size(folio) || folio_test_uptodate(folio))
return 0;
if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode) &&
!f2fs_verity_in_progress(inode)) {
- zero_user_segment(page, len, PAGE_SIZE);
+ folio_zero_segment(folio, len, folio_size(folio));
return 0;
}
if (blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_SIZE);
- SetPageUptodate(page);
+ folio_zero_segment(folio, 0, folio_size(folio));
+ folio_mark_uptodate(folio);
} else {
if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
DATA_GENERIC_ENHANCE_READ)) {
err = -EFSCORRUPTED;
- f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
- goto fail;
+ goto put_folio;
}
err = f2fs_submit_page_read(use_cow ?
- F2FS_I(inode)->cow_inode : inode, page,
- blkaddr, 0, true);
+ F2FS_I(inode)->cow_inode : inode,
+ folio, blkaddr, 0, true);
if (err)
- goto fail;
+ goto put_folio;
- lock_page(page);
- if (unlikely(page->mapping != mapping)) {
- f2fs_put_page(page, 1);
+ folio_lock(folio);
+ if (unlikely(folio->mapping != mapping)) {
+ folio_unlock(folio);
+ folio_put(folio);
goto repeat;
}
- if (unlikely(!PageUptodate(page))) {
+ if (unlikely(!folio_test_uptodate(folio))) {
err = -EIO;
- goto fail;
+ goto put_folio;
}
}
return 0;
+put_folio:
+ folio_unlock(folio);
+ folio_put(folio);
fail:
- f2fs_put_page(page, 1);
f2fs_write_failed(inode, pos + len);
return err;
}
@@ -3734,9 +3686,9 @@ fail:
static int f2fs_write_end(struct file *file,
struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
+ struct folio *folio, void *fsdata)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
trace_f2fs_write_end(inode, pos, len, copied);
@@ -3745,17 +3697,17 @@ static int f2fs_write_end(struct file *file,
* should be PAGE_SIZE. Otherwise, we treat it with zero copied and
* let generic_perform_write() try to copy data again through copied=0.
*/
- if (!PageUptodate(page)) {
+ if (!folio_test_uptodate(folio)) {
if (unlikely(copied != len))
copied = 0;
else
- SetPageUptodate(page);
+ folio_mark_uptodate(folio);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
/* overwrite compressed file */
if (f2fs_compressed_file(inode) && fsdata) {
- f2fs_compress_write_end(inode, fsdata, page->index, copied);
+ f2fs_compress_write_end(inode, fsdata, folio->index, copied);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
if (pos + copied > i_size_read(inode) &&
@@ -3768,7 +3720,10 @@ static int f2fs_write_end(struct file *file,
if (!copied)
goto unlock_out;
- set_page_dirty(page);
+ folio_mark_dirty(folio);
+
+ if (f2fs_is_atomic_file(inode))
+ set_page_private_atomic(folio_page(folio, 0));
if (pos + copied > i_size_read(inode) &&
!f2fs_verity_in_progress(inode)) {
@@ -3778,7 +3733,8 @@ static int f2fs_write_end(struct file *file,
pos + copied);
}
unlock_out:
- f2fs_put_page(page, 1);
+ folio_unlock(folio);
+ folio_put(folio);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
@@ -3820,7 +3776,7 @@ static bool f2fs_dirty_data_folio(struct address_space *mapping,
{
struct inode *inode = mapping->host;
- trace_f2fs_set_page_dirty(&folio->page, DATA);
+ trace_f2fs_set_page_dirty(folio, DATA);
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
@@ -3905,26 +3861,36 @@ static int f2fs_migrate_blocks(struct inode *inode, block_t start_blk,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int blkofs;
unsigned int blk_per_sec = BLKS_PER_SEC(sbi);
+ unsigned int end_blk = start_blk + blkcnt - 1;
unsigned int secidx = start_blk / blk_per_sec;
- unsigned int end_sec = secidx + blkcnt / blk_per_sec;
+ unsigned int end_sec;
int ret = 0;
+ if (!blkcnt)
+ return 0;
+ end_sec = end_blk / blk_per_sec;
+
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
set_inode_flag(inode, FI_ALIGNED_WRITE);
set_inode_flag(inode, FI_OPU_WRITE);
- for (; secidx < end_sec; secidx++) {
+ for (; secidx <= end_sec; secidx++) {
+ unsigned int blkofs_end = secidx == end_sec ?
+ end_blk % blk_per_sec : blk_per_sec - 1;
+
f2fs_down_write(&sbi->pin_sem);
- f2fs_lock_op(sbi);
- f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false);
- f2fs_unlock_op(sbi);
+ ret = f2fs_allocate_pinning_section(sbi);
+ if (ret) {
+ f2fs_up_write(&sbi->pin_sem);
+ break;
+ }
set_inode_flag(inode, FI_SKIP_WRITES);
- for (blkofs = 0; blkofs < blk_per_sec; blkofs++) {
+ for (blkofs = 0; blkofs <= blkofs_end; blkofs++) {
struct page *page;
unsigned int blkidx = secidx * blk_per_sec + blkofs;
@@ -3966,15 +3932,14 @@ static int check_swap_activate(struct swap_info_struct *sis,
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- sector_t cur_lblock;
- sector_t last_lblock;
- sector_t pblock;
- sector_t lowest_pblock = -1;
- sector_t highest_pblock = 0;
+ block_t cur_lblock;
+ block_t last_lblock;
+ block_t pblock;
+ block_t lowest_pblock = -1;
+ block_t highest_pblock = 0;
int nr_extents = 0;
- unsigned long nr_pblocks;
+ unsigned int nr_pblocks;
unsigned int blks_per_sec = BLKS_PER_SEC(sbi);
- unsigned int sec_blks_mask = BLKS_PER_SEC(sbi) - 1;
unsigned int not_aligned = 0;
int ret = 0;
@@ -3983,7 +3948,7 @@ static int check_swap_activate(struct swap_info_struct *sis,
* to be very smart.
*/
cur_lblock = 0;
- last_lblock = bytes_to_blks(inode, i_size_read(inode));
+ last_lblock = F2FS_BYTES_TO_BLK(i_size_read(inode));
while (cur_lblock < last_lblock && cur_lblock < sis->max) {
struct f2fs_map_blocks map;
@@ -4012,28 +3977,35 @@ retry:
pblock = map.m_pblk;
nr_pblocks = map.m_len;
- if ((pblock - SM_I(sbi)->main_blkaddr) & sec_blks_mask ||
- nr_pblocks & sec_blks_mask) {
+ if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec ||
+ nr_pblocks % blks_per_sec ||
+ !f2fs_valid_pinned_area(sbi, pblock)) {
+ bool last_extent = false;
+
not_aligned++;
nr_pblocks = roundup(nr_pblocks, blks_per_sec);
if (cur_lblock + nr_pblocks > sis->max)
nr_pblocks -= blks_per_sec;
+ /* this extent is last one */
if (!nr_pblocks) {
- /* this extent is last one */
- nr_pblocks = map.m_len;
- f2fs_warn(sbi, "Swapfile: last extent is not aligned to section");
- goto next;
+ nr_pblocks = last_lblock - cur_lblock;
+ last_extent = true;
}
ret = f2fs_migrate_blocks(inode, cur_lblock,
nr_pblocks);
- if (ret)
+ if (ret) {
+ if (ret == -ENOENT)
+ ret = -EINVAL;
goto out;
- goto retry;
+ }
+
+ if (!last_extent)
+ goto retry;
}
-next:
+
if (cur_lblock + nr_pblocks >= sis->max)
nr_pblocks = sis->max - cur_lblock;
@@ -4059,7 +4031,6 @@ next:
cur_lblock = 1; /* force Empty message */
sis->max = cur_lblock;
sis->pages = cur_lblock - 1;
- sis->highest_bit = cur_lblock - 1;
out:
if (not_aligned)
f2fs_warn(sbi, "Swapfile (%u) is not align to section: 1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate(%lu * N)",
@@ -4071,17 +4042,17 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
sector_t *span)
{
struct inode *inode = file_inode(file);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int ret;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
- if (f2fs_readonly(F2FS_I_SB(inode)->sb))
+ if (f2fs_readonly(sbi->sb))
return -EROFS;
- if (f2fs_lfs_mode(F2FS_I_SB(inode))) {
- f2fs_err(F2FS_I_SB(inode),
- "Swapfile not supported in LFS mode");
+ if (f2fs_lfs_mode(sbi) && !f2fs_sb_has_blkzoned(sbi)) {
+ f2fs_err(sbi, "Swapfile not supported in LFS mode");
return -EINVAL;
}
@@ -4092,6 +4063,10 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
if (!f2fs_disable_compressed_file(inode))
return -EINVAL;
+ ret = filemap_fdatawrite(inode->i_mapping);
+ if (ret < 0)
+ return ret;
+
f2fs_precache_extents(inode);
ret = check_swap_activate(sis, file, span);
@@ -4100,7 +4075,7 @@ static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file,
stat_inc_swapfile_inode(inode);
set_inode_flag(inode, FI_PIN_FILE);
- f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+ f2fs_update_time(sbi, REQ_TIME);
return ret;
}
@@ -4139,13 +4114,13 @@ const struct address_space_operations f2fs_dblock_aops = {
.swap_deactivate = f2fs_swap_deactivate,
};
-void f2fs_clear_page_cache_dirty_tag(struct page *page)
+void f2fs_clear_page_cache_dirty_tag(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
+ struct address_space *mapping = folio->mapping;
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
- __xa_clear_mark(&mapping->i_pages, page_index(page),
+ __xa_clear_mark(&mapping->i_pages, folio->index,
PAGECACHE_TAG_DIRTY);
xa_unlock_irqrestore(&mapping->i_pages, flags);
}
@@ -4215,10 +4190,11 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
pgoff_t next_pgofs = 0;
int err;
- map.m_lblk = bytes_to_blks(inode, offset);
- map.m_len = bytes_to_blks(inode, offset + length - 1) - map.m_lblk + 1;
+ map.m_lblk = F2FS_BYTES_TO_BLK(offset);
+ map.m_len = F2FS_BYTES_TO_BLK(offset + length - 1) - map.m_lblk + 1;
map.m_next_pgofs = &next_pgofs;
- map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint);
+ map.m_seg_type = f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode),
+ inode->i_write_hint);
if (flags & IOMAP_WRITE)
map.m_may_create = true;
@@ -4226,7 +4202,7 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
if (err)
return err;
- iomap->offset = blks_to_bytes(inode, map.m_lblk);
+ iomap->offset = F2FS_BLK_TO_BYTES(map.m_lblk);
/*
* When inline encryption is enabled, sometimes I/O to an encrypted file
@@ -4239,23 +4215,32 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
* We should never see delalloc or compressed extents here based on
* prior flushing and checks.
*/
- if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR))
- return -EINVAL;
if (WARN_ON_ONCE(map.m_pblk == COMPRESS_ADDR))
return -EINVAL;
- if (map.m_pblk != NULL_ADDR) {
- iomap->length = blks_to_bytes(inode, map.m_len);
+ if (map.m_flags & F2FS_MAP_MAPPED) {
+ if (WARN_ON_ONCE(map.m_pblk == NEW_ADDR))
+ return -EINVAL;
+
+ iomap->length = F2FS_BLK_TO_BYTES(map.m_len);
iomap->type = IOMAP_MAPPED;
iomap->flags |= IOMAP_F_MERGED;
iomap->bdev = map.m_bdev;
- iomap->addr = blks_to_bytes(inode, map.m_pblk);
+ iomap->addr = F2FS_BLK_TO_BYTES(map.m_pblk);
} else {
if (flags & IOMAP_WRITE)
return -ENOTBLK;
- iomap->length = blks_to_bytes(inode, next_pgofs) -
- iomap->offset;
- iomap->type = IOMAP_HOLE;
+
+ if (map.m_pblk == NULL_ADDR) {
+ iomap->length = F2FS_BLK_TO_BYTES(next_pgofs) -
+ iomap->offset;
+ iomap->type = IOMAP_HOLE;
+ } else if (map.m_pblk == NEW_ADDR) {
+ iomap->length = F2FS_BLK_TO_BYTES(map.m_len);
+ iomap->type = IOMAP_UNWRITTEN;
+ } else {
+ f2fs_bug_on(F2FS_I_SB(inode), 1);
+ }
iomap->addr = IOMAP_NULL_ADDR;
}
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index fdbf994f1271..468828288a4a 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -41,7 +41,7 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi)
total_vblocks = 0;
blks_per_sec = CAP_BLKS_PER_SEC(sbi);
hblks_per_sec = blks_per_sec / 2;
- for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) {
vblocks = get_valid_blocks(sbi, segno, true);
dist = abs(vblocks - hblks_per_sec);
bimodal += dist * dist;
@@ -60,6 +60,70 @@ void f2fs_update_sit_info(struct f2fs_sb_info *sbi)
}
#ifdef CONFIG_DEBUG_FS
+static void update_multidevice_stats(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
+ struct f2fs_dev_stats *dev_stats = si->dev_stats;
+ int i, j;
+
+ if (!f2fs_is_multi_device(sbi))
+ return;
+
+ memset(dev_stats, 0, sizeof(struct f2fs_dev_stats) * sbi->s_ndevs);
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ unsigned int start_segno, end_segno;
+ block_t start_blk, end_blk;
+
+ if (i == 0) {
+ start_blk = MAIN_BLKADDR(sbi);
+ end_blk = FDEV(i).end_blk + 1 - SEG0_BLKADDR(sbi);
+ } else {
+ start_blk = FDEV(i).start_blk;
+ end_blk = FDEV(i).end_blk + 1;
+ }
+
+ start_segno = GET_SEGNO(sbi, start_blk);
+ end_segno = GET_SEGNO(sbi, end_blk);
+
+ for (j = start_segno; j < end_segno; j++) {
+ unsigned int seg_blks, sec_blks;
+
+ seg_blks = get_seg_entry(sbi, j)->valid_blocks;
+
+ /* update segment stats */
+ if (IS_CURSEG(sbi, j))
+ dev_stats[i].devstats[0][DEVSTAT_INUSE]++;
+ else if (seg_blks == BLKS_PER_SEG(sbi))
+ dev_stats[i].devstats[0][DEVSTAT_FULL]++;
+ else if (seg_blks != 0)
+ dev_stats[i].devstats[0][DEVSTAT_DIRTY]++;
+ else if (!test_bit(j, FREE_I(sbi)->free_segmap))
+ dev_stats[i].devstats[0][DEVSTAT_FREE]++;
+ else
+ dev_stats[i].devstats[0][DEVSTAT_PREFREE]++;
+
+ if (!__is_large_section(sbi) ||
+ (j % SEGS_PER_SEC(sbi)) != 0)
+ continue;
+
+ sec_blks = get_sec_entry(sbi, j)->valid_blocks;
+
+ /* update section stats */
+ if (IS_CURSEC(sbi, GET_SEC_FROM_SEG(sbi, j)))
+ dev_stats[i].devstats[1][DEVSTAT_INUSE]++;
+ else if (sec_blks == BLKS_PER_SEC(sbi))
+ dev_stats[i].devstats[1][DEVSTAT_FULL]++;
+ else if (sec_blks != 0)
+ dev_stats[i].devstats[1][DEVSTAT_DIRTY]++;
+ else if (!test_bit(GET_SEC_FROM_SEG(sbi, j),
+ FREE_I(sbi)->free_secmap))
+ dev_stats[i].devstats[1][DEVSTAT_FREE]++;
+ else
+ dev_stats[i].devstats[1][DEVSTAT_PREFREE]++;
+ }
+ }
+}
+
static void update_general_status(struct f2fs_sb_info *sbi)
{
struct f2fs_stat_info *si = F2FS_STAT(sbi);
@@ -135,7 +199,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->cur_ckpt_time = sbi->cprc_info.cur_time;
si->peak_ckpt_time = sbi->cprc_info.peak_time;
spin_unlock(&sbi->cprc_info.stat_lock);
- si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
+ si->total_count = BLKS_TO_SEGS(sbi, (int)sbi->user_block_count);
si->rsvd_segs = reserved_segments(sbi);
si->overp_segs = overprovision_segments(sbi);
si->valid_count = valid_user_blocks(sbi);
@@ -176,11 +240,10 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID];
si->io_skip_bggc = sbi->io_skip_bggc;
si->other_skip_bggc = sbi->other_skip_bggc;
- si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
+ si->util_free = (int)(BLKS_TO_SEGS(sbi, free_user_blocks(sbi)))
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
/ 2;
- si->util_valid = (int)(written_block_count(sbi) >>
- sbi->log_blocks_per_seg)
+ si->util_valid = (int)(BLKS_TO_SEGS(sbi, written_block_count(sbi)))
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
/ 2;
si->util_invalid = 50 - si->util_free - si->util_valid;
@@ -208,13 +271,15 @@ static void update_general_status(struct f2fs_sb_info *sbi)
if (!blks)
continue;
- if (blks == sbi->blocks_per_seg)
+ if (blks == BLKS_PER_SEG(sbi))
si->full_seg[type]++;
else
si->dirty_seg[type]++;
si->valid_blks[type] += blks;
}
+ update_multidevice_stats(sbi);
+
for (i = 0; i < MAX_CALL_TYPE; i++)
si->cp_call_count[i] = atomic_read(&sbi->cp_call_count[i]);
@@ -276,7 +341,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
/* build nm */
si->base_mem += sizeof(struct f2fs_nm_info);
si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
- si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
+ si->base_mem += F2FS_BLK_TO_BYTES(NM_I(sbi)->nat_bits_blocks);
si->base_mem += NM_I(sbi)->nat_blocks *
f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK);
si->base_mem += NM_I(sbi)->nat_blocks / 8;
@@ -499,6 +564,36 @@ static int stat_show(struct seq_file *s, void *v)
si->dirty_count);
seq_printf(s, " - Prefree: %d\n - Free: %d (%d)\n\n",
si->prefree_count, si->free_segs, si->free_secs);
+ if (f2fs_is_multi_device(sbi)) {
+ seq_puts(s, "Multidevice stats:\n");
+ seq_printf(s, " [seg: %8s %8s %8s %8s %8s]",
+ "inuse", "dirty", "full", "free", "prefree");
+ if (__is_large_section(sbi))
+ seq_printf(s, " [sec: %8s %8s %8s %8s %8s]\n",
+ "inuse", "dirty", "full", "free", "prefree");
+ else
+ seq_puts(s, "\n");
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ seq_printf(s, " #%-2d %8u %8u %8u %8u %8u", i,
+ si->dev_stats[i].devstats[0][DEVSTAT_INUSE],
+ si->dev_stats[i].devstats[0][DEVSTAT_DIRTY],
+ si->dev_stats[i].devstats[0][DEVSTAT_FULL],
+ si->dev_stats[i].devstats[0][DEVSTAT_FREE],
+ si->dev_stats[i].devstats[0][DEVSTAT_PREFREE]);
+ if (!__is_large_section(sbi)) {
+ seq_puts(s, "\n");
+ continue;
+ }
+ seq_printf(s, " %8u %8u %8u %8u %8u\n",
+ si->dev_stats[i].devstats[1][DEVSTAT_INUSE],
+ si->dev_stats[i].devstats[1][DEVSTAT_DIRTY],
+ si->dev_stats[i].devstats[1][DEVSTAT_FULL],
+ si->dev_stats[i].devstats[1][DEVSTAT_FREE],
+ si->dev_stats[i].devstats[1][DEVSTAT_PREFREE]);
+ }
+ seq_puts(s, "\n");
+ }
seq_printf(s, "CP calls: %d (BG: %d)\n",
si->cp_call_count[TOTAL_CALL],
si->cp_call_count[BACKGROUND]);
@@ -599,9 +694,9 @@ static int stat_show(struct seq_file *s, void *v)
si->ndirty_node, si->node_pages);
seq_printf(s, " - dents: %4d in dirs:%4d (%4d)\n",
si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
- seq_printf(s, " - datas: %4d in files:%4d\n",
+ seq_printf(s, " - data: %4d in files:%4d\n",
si->ndirty_data, si->ndirty_files);
- seq_printf(s, " - quota datas: %4d in quota files:%4d\n",
+ seq_printf(s, " - quota data: %4d in quota files:%4d\n",
si->ndirty_qdata, si->nquota_files);
seq_printf(s, " - meta: %4d in %4d\n",
si->ndirty_meta, si->meta_pages);
@@ -666,6 +761,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_stat_info *si;
+ struct f2fs_dev_stats *dev_stats;
unsigned long flags;
int i;
@@ -673,6 +769,15 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
if (!si)
return -ENOMEM;
+ dev_stats = f2fs_kzalloc(sbi, sizeof(struct f2fs_dev_stats) *
+ sbi->s_ndevs, GFP_KERNEL);
+ if (!dev_stats) {
+ kfree(si);
+ return -ENOMEM;
+ }
+
+ si->dev_stats = dev_stats;
+
si->all_area_segs = le32_to_cpu(raw_super->segment_count);
si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
@@ -725,6 +830,7 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
list_del(&si->stat_list);
raw_spin_unlock_irqrestore(&f2fs_stat_lock, flags);
+ kfree(si->dev_stats);
kfree(si);
}
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 042593aed1ec..54dd52de7269 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -5,7 +5,7 @@
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/sched/signal.h>
@@ -42,35 +42,49 @@ static unsigned int bucket_blocks(unsigned int level)
return 4;
}
+#if IS_ENABLED(CONFIG_UNICODE)
/* If @dir is casefolded, initialize @fname->cf_name from @fname->usr_fname. */
int f2fs_init_casefolded_name(const struct inode *dir,
struct f2fs_filename *fname)
{
-#if IS_ENABLED(CONFIG_UNICODE)
struct super_block *sb = dir->i_sb;
+ unsigned char *buf;
+ int len;
if (IS_CASEFOLDED(dir) &&
!is_dot_dotdot(fname->usr_fname->name, fname->usr_fname->len)) {
- fname->cf_name.name = f2fs_kmem_cache_alloc(f2fs_cf_name_slab,
- GFP_NOFS, false, F2FS_SB(sb));
- if (!fname->cf_name.name)
+ buf = f2fs_kmem_cache_alloc(f2fs_cf_name_slab,
+ GFP_NOFS, false, F2FS_SB(sb));
+ if (!buf)
return -ENOMEM;
- fname->cf_name.len = utf8_casefold(sb->s_encoding,
- fname->usr_fname,
- fname->cf_name.name,
- F2FS_NAME_LEN);
- if ((int)fname->cf_name.len <= 0) {
- kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
- fname->cf_name.name = NULL;
+
+ len = utf8_casefold(sb->s_encoding, fname->usr_fname,
+ buf, F2FS_NAME_LEN);
+ if (len <= 0) {
+ kmem_cache_free(f2fs_cf_name_slab, buf);
if (sb_has_strict_encoding(sb))
return -EINVAL;
/* fall back to treating name as opaque byte sequence */
+ return 0;
}
+ fname->cf_name.name = buf;
+ fname->cf_name.len = len;
}
-#endif
+
return 0;
}
+void f2fs_free_casefolded_name(struct f2fs_filename *fname)
+{
+ unsigned char *buf = (unsigned char *)fname->cf_name.name;
+
+ if (buf) {
+ kmem_cache_free(f2fs_cf_name_slab, buf);
+ fname->cf_name.name = NULL;
+ }
+}
+#endif /* CONFIG_UNICODE */
+
static int __f2fs_setup_filename(const struct inode *dir,
const struct fscrypt_name *crypt_name,
struct f2fs_filename *fname)
@@ -142,12 +156,7 @@ void f2fs_free_filename(struct f2fs_filename *fname)
kfree(fname->crypto_buf.name);
fname->crypto_buf.name = NULL;
#endif
-#if IS_ENABLED(CONFIG_UNICODE)
- if (fname->cf_name.name) {
- kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
- fname->cf_name.name = NULL;
- }
-#endif
+ f2fs_free_casefolded_name(fname);
}
static unsigned long dir_block_index(unsigned int level,
@@ -157,7 +166,8 @@ static unsigned long dir_block_index(unsigned int level,
unsigned long bidx = 0;
for (i = 0; i < level; i++)
- bidx += dir_buckets(i, dir_level) * bucket_blocks(i);
+ bidx += mul_u32_u32(dir_buckets(i, dir_level),
+ bucket_blocks(i));
bidx += idx * bucket_blocks(level);
return bidx;
}
@@ -165,7 +175,8 @@ static unsigned long dir_block_index(unsigned int level,
static struct f2fs_dir_entry *find_in_block(struct inode *dir,
struct page *dentry_page,
const struct f2fs_filename *fname,
- int *max_slots)
+ int *max_slots,
+ bool use_hash)
{
struct f2fs_dentry_block *dentry_blk;
struct f2fs_dentry_ptr d;
@@ -173,60 +184,8 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
make_dentry_ptr_block(dir, &d, dentry_blk);
- return f2fs_find_target_dentry(&d, fname, max_slots);
-}
-
-#if IS_ENABLED(CONFIG_UNICODE)
-/*
- * Test whether a case-insensitive directory entry matches the filename
- * being searched for.
- *
- * Returns 1 for a match, 0 for no match, and -errno on an error.
- */
-static int f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
- const u8 *de_name, u32 de_name_len)
-{
- const struct super_block *sb = dir->i_sb;
- const struct unicode_map *um = sb->s_encoding;
- struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
- struct qstr entry = QSTR_INIT(de_name, de_name_len);
- int res;
-
- if (IS_ENCRYPTED(dir)) {
- const struct fscrypt_str encrypted_name =
- FSTR_INIT((u8 *)de_name, de_name_len);
-
- if (WARN_ON_ONCE(!fscrypt_has_encryption_key(dir)))
- return -EINVAL;
-
- decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
- if (!decrypted_name.name)
- return -ENOMEM;
- res = fscrypt_fname_disk_to_usr(dir, 0, 0, &encrypted_name,
- &decrypted_name);
- if (res < 0)
- goto out;
- entry.name = decrypted_name.name;
- entry.len = decrypted_name.len;
- }
-
- res = utf8_strncasecmp_folded(um, name, &entry);
- /*
- * In strict mode, ignore invalid names. In non-strict mode,
- * fall back to treating them as opaque byte sequences.
- */
- if (res < 0 && !sb_has_strict_encoding(sb)) {
- res = name->len == entry.len &&
- memcmp(name->name, entry.name, name->len) == 0;
- } else {
- /* utf8_strncasecmp_folded returns 0 on match */
- res = (res == 0);
- }
-out:
- kfree(decrypted_name.name);
- return res;
+ return f2fs_find_target_dentry(&d, fname, max_slots, use_hash);
}
-#endif /* CONFIG_UNICODE */
static inline int f2fs_match_name(const struct inode *dir,
const struct f2fs_filename *fname,
@@ -235,11 +194,11 @@ static inline int f2fs_match_name(const struct inode *dir,
struct fscrypt_name f;
#if IS_ENABLED(CONFIG_UNICODE)
- if (fname->cf_name.name) {
- struct qstr cf = FSTR_TO_QSTR(&fname->cf_name);
+ if (fname->cf_name.name)
+ return generic_ci_match(dir, fname->usr_fname,
+ &fname->cf_name,
+ de_name, de_name_len);
- return f2fs_match_ci_name(dir, &cf, de_name, de_name_len);
- }
#endif
f.usr_fname = fname->usr_fname;
f.disk_name = fname->disk_name;
@@ -250,7 +209,8 @@ static inline int f2fs_match_name(const struct inode *dir,
}
struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
- const struct f2fs_filename *fname, int *max_slots)
+ const struct f2fs_filename *fname, int *max_slots,
+ bool use_hash)
{
struct f2fs_dir_entry *de;
unsigned long bit_pos = 0;
@@ -273,7 +233,7 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
continue;
}
- if (de->hash_code == fname->hash) {
+ if (!use_hash || de->hash_code == fname->hash) {
res = f2fs_match_name(d->inode, fname,
d->filename[bit_pos],
le16_to_cpu(de->name_len));
@@ -300,11 +260,12 @@ found:
static struct f2fs_dir_entry *find_in_level(struct inode *dir,
unsigned int level,
const struct f2fs_filename *fname,
- struct page **res_page)
+ struct page **res_page,
+ bool use_hash)
{
int s = GET_DENTRY_SLOTS(fname->disk_name.len);
unsigned int nbucket, nblock;
- unsigned int bidx, end_block;
+ unsigned int bidx, end_block, bucket_no;
struct page *dentry_page;
struct f2fs_dir_entry *de = NULL;
pgoff_t next_pgofs;
@@ -314,8 +275,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
+ bucket_no = use_hash ? le32_to_cpu(fname->hash) % nbucket : 0;
+
+start_find_bucket:
bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
- le32_to_cpu(fname->hash) % nbucket);
+ bucket_no);
end_block = bidx + nblock;
while (bidx < end_block) {
@@ -332,7 +296,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
}
}
- de = find_in_block(dir, dentry_page, fname, &max_slots);
+ de = find_in_block(dir, dentry_page, fname, &max_slots, use_hash);
if (IS_ERR(de)) {
*res_page = ERR_CAST(de);
de = NULL;
@@ -349,12 +313,18 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
bidx++;
}
- if (!de && room && F2FS_I(dir)->chash != fname->hash) {
- F2FS_I(dir)->chash = fname->hash;
- F2FS_I(dir)->clevel = level;
- }
+ if (de)
+ return de;
- return de;
+ if (likely(use_hash)) {
+ if (room && F2FS_I(dir)->chash != fname->hash) {
+ F2FS_I(dir)->chash = fname->hash;
+ F2FS_I(dir)->clevel = level;
+ }
+ } else if (++bucket_no < nbucket) {
+ goto start_find_bucket;
+ }
+ return NULL;
}
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
@@ -365,11 +335,15 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
struct f2fs_dir_entry *de = NULL;
unsigned int max_depth;
unsigned int level;
+ bool use_hash = true;
*res_page = NULL;
+#if IS_ENABLED(CONFIG_UNICODE)
+start_find_entry:
+#endif
if (f2fs_has_inline_dentry(dir)) {
- de = f2fs_find_in_inline_dir(dir, fname, res_page);
+ de = f2fs_find_in_inline_dir(dir, fname, res_page, use_hash);
goto out;
}
@@ -385,11 +359,18 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
}
for (level = 0; level < max_depth; level++) {
- de = find_in_level(dir, level, fname, res_page);
+ de = find_in_level(dir, level, fname, res_page, use_hash);
if (de || IS_ERR(*res_page))
break;
}
+
out:
+#if IS_ENABLED(CONFIG_UNICODE)
+ if (IS_CASEFOLDED(dir) && !de && use_hash) {
+ use_hash = false;
+ goto start_find_entry;
+ }
+#endif
/* This is to increase the speed of f2fs_create */
if (!de)
F2FS_I(dir)->task = current;
@@ -830,13 +811,14 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
return err;
}
-int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
+int f2fs_do_tmpfile(struct inode *inode, struct inode *dir,
+ struct f2fs_filename *fname)
{
struct page *page;
int err = 0;
f2fs_down_write(&F2FS_I(inode)->i_sem);
- page = f2fs_init_inode_metadata(inode, dir, NULL, NULL);
+ page = f2fs_init_inode_metadata(inode, dir, fname, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -883,6 +865,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
+ pgoff_t index = page_folio(page)->index;
int i;
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
@@ -908,8 +891,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
set_page_dirty(page);
if (bit_pos == NR_DENTRY_IN_BLOCK &&
- !f2fs_truncate_hole(dir, page->index, page->index + 1)) {
- f2fs_clear_page_cache_dirty_tag(page);
+ !f2fs_truncate_hole(dir, index, index + 1)) {
+ f2fs_clear_page_cache_dirty_tag(page_folio(page));
clear_page_dirty_for_io(page);
ClearPageUptodate(page);
clear_page_private_all(page);
@@ -995,9 +978,8 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
de = &d->dentry[bit_pos];
if (de->name_len == 0) {
if (found_valid_dirent || !bit_pos) {
- printk_ratelimited(
- "%sF2FS-fs (%s): invalid namelen(0), ino:%u, run fsck to fix.",
- KERN_WARNING, sbi->sb->s_id,
+ f2fs_warn_ratelimited(sbi,
+ "invalid namelen(0), ino:%u, run fsck to fix.",
le32_to_cpu(de->ino));
set_sbi_flag(sbi, SBI_NEED_FSCK);
}
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index ad8dfac73bd4..347b3b647834 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -19,37 +19,56 @@
#include "node.h"
#include <trace/events/f2fs.h>
-bool sanity_check_extent_cache(struct inode *inode)
+bool sanity_check_extent_cache(struct inode *inode, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_inode_info *fi = F2FS_I(inode);
- struct extent_tree *et = fi->extent_tree[EX_READ];
- struct extent_info *ei;
-
- if (!et)
- return true;
+ struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext;
+ struct extent_info ei;
+ int devi;
- ei = &et->largest;
- if (!ei->len)
- return true;
+ get_read_extent_info(&ei, i_ext);
- /* Let's drop, if checkpoint got corrupted. */
- if (is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) {
- ei->len = 0;
- et->largest_updated = true;
+ if (!ei.len)
return true;
- }
- if (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE) ||
- !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
+ if (!f2fs_is_valid_blkaddr(sbi, ei.blk, DATA_GENERIC_ENHANCE) ||
+ !f2fs_is_valid_blkaddr(sbi, ei.blk + ei.len - 1,
DATA_GENERIC_ENHANCE)) {
- set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix",
__func__, inode->i_ino,
- ei->blk, ei->fofs, ei->len);
+ ei.blk, ei.fofs, ei.len);
return false;
}
- return true;
+
+ if (!IS_DEVICE_ALIASING(inode))
+ return true;
+
+ for (devi = 0; devi < sbi->s_ndevs; devi++) {
+ if (FDEV(devi).start_blk != ei.blk ||
+ FDEV(devi).end_blk != ei.blk + ei.len - 1)
+ continue;
+
+ if (devi == 0) {
+ f2fs_warn(sbi,
+ "%s: inode (ino=%lx) is an alias of meta device",
+ __func__, inode->i_ino);
+ return false;
+ }
+
+ if (bdev_is_zoned(FDEV(devi).bdev)) {
+ f2fs_warn(sbi,
+ "%s: device alias inode (ino=%lx)'s extent info "
+ "[%u, %u, %u] maps to zoned block device",
+ __func__, inode->i_ino, ei.blk, ei.fofs, ei.len);
+ return false;
+ }
+ return true;
+ }
+
+ f2fs_warn(sbi, "%s: device alias inode (ino=%lx)'s extent info "
+ "[%u, %u, %u] is inconsistent w/ any devices",
+ __func__, inode->i_ino, ei.blk, ei.fofs, ei.len);
+ return false;
}
static void __set_extent_info(struct extent_info *ei,
@@ -87,6 +106,9 @@ static bool __init_may_extent_tree(struct inode *inode, enum extent_type type)
static bool __may_extent_tree(struct inode *inode, enum extent_type type)
{
+ if (IS_DEVICE_ALIASING(inode) && type == EX_READ)
+ return true;
+
/*
* for recovered files during mount do not create extents
* if shrinker is not registered.
@@ -357,27 +379,28 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode,
}
static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
- struct extent_tree *et)
+ struct extent_tree *et, unsigned int nr_shrink)
{
struct rb_node *node, *next;
struct extent_node *en;
- unsigned int count = atomic_read(&et->node_cnt);
+ unsigned int count;
node = rb_first_cached(&et->root);
- while (node) {
+
+ for (count = 0; node && count < nr_shrink; count++) {
next = rb_next(node);
en = rb_entry(node, struct extent_node, rb_node);
__release_extent_node(sbi, et, en);
node = next;
}
- return count - atomic_read(&et->node_cnt);
+ return count;
}
static void __drop_largest_extent(struct extent_tree *et,
pgoff_t fofs, unsigned int len)
{
- if (fofs < et->largest.fofs + et->largest.len &&
+ if (fofs < (pgoff_t)et->largest.fofs + et->largest.len &&
fofs + len > et->largest.fofs) {
et->largest.len = 0;
et->largest_updated = true;
@@ -395,24 +418,27 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
if (!__may_extent_tree(inode, EX_READ)) {
/* drop largest read extent */
- if (i_ext && i_ext->len) {
+ if (i_ext->len) {
f2fs_wait_on_page_writeback(ipage, NODE, true, true);
i_ext->len = 0;
set_page_dirty(ipage);
}
- goto out;
+ set_inode_flag(inode, FI_NO_EXTENT);
+ return;
}
et = __grab_extent_tree(inode, EX_READ);
- if (!i_ext || !i_ext->len)
- goto out;
-
get_read_extent_info(&ei, i_ext);
write_lock(&et->lock);
- if (atomic_read(&et->node_cnt))
- goto unlock_out;
+ if (atomic_read(&et->node_cnt) || !ei.len)
+ goto skip;
+
+ if (IS_DEVICE_ALIASING(inode)) {
+ et->largest = ei;
+ goto skip;
+ }
en = __attach_extent_node(sbi, et, &ei, NULL,
&et->root.rb_root.rb_node, true);
@@ -424,11 +450,13 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
list_add_tail(&en->list, &eti->extent_list);
spin_unlock(&eti->extent_lock);
}
-unlock_out:
+skip:
+ /* Let's drop, if checkpoint got corrupted. */
+ if (f2fs_cp_error(sbi)) {
+ et->largest.len = 0;
+ et->largest_updated = true;
+ }
write_unlock(&et->lock);
-out:
- if (!F2FS_I(inode)->extent_tree[EX_READ])
- set_inode_flag(inode, FI_NO_EXTENT);
}
void f2fs_init_age_extent_tree(struct inode *inode)
@@ -467,13 +495,18 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
if (type == EX_READ &&
et->largest.fofs <= pgofs &&
- et->largest.fofs + et->largest.len > pgofs) {
+ (pgoff_t)et->largest.fofs + et->largest.len > pgofs) {
*ei = et->largest;
ret = true;
stat_inc_largest_node_hit(sbi);
goto out;
}
+ if (IS_DEVICE_ALIASING(inode)) {
+ ret = false;
+ goto out;
+ }
+
en = __lookup_extent_node(&et->root, et->cached_en, pgofs);
if (!en)
goto out;
@@ -590,6 +623,30 @@ do_insert:
return en;
}
+static unsigned int __destroy_extent_node(struct inode *inode,
+ enum extent_type type)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
+ unsigned int nr_shrink = type == EX_READ ?
+ READ_EXTENT_CACHE_SHRINK_NUMBER :
+ AGE_EXTENT_CACHE_SHRINK_NUMBER;
+ unsigned int node_cnt = 0;
+
+ if (!et || !atomic_read(&et->node_cnt))
+ return 0;
+
+ while (atomic_read(&et->node_cnt)) {
+ write_lock(&et->lock);
+ node_cnt += __free_extent_tree(sbi, et, nr_shrink);
+ write_unlock(&et->lock);
+ }
+
+ f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
+
+ return node_cnt;
+}
+
static void __update_extent_tree_range(struct inode *inode,
struct extent_info *tei, enum extent_type type)
{
@@ -660,7 +717,9 @@ static void __update_extent_tree_range(struct inode *inode,
}
if (end < org_end && (type != EX_READ ||
- org_end - end >= F2FS_MIN_EXTENT_LEN)) {
+ (org_end - end >= F2FS_MIN_EXTENT_LEN &&
+ atomic_read(&et->node_cnt) <
+ sbi->max_read_extent_count))) {
if (parts) {
__set_extent_info(&ei,
end, org_end - end,
@@ -728,9 +787,6 @@ static void __update_extent_tree_range(struct inode *inode,
}
}
- if (is_inode_flag_set(inode, FI_NO_EXTENT))
- __free_extent_tree(sbi, et);
-
if (et->largest_updated) {
et->largest_updated = false;
updated = true;
@@ -748,6 +804,9 @@ update_age_extent_cache:
out_read_extent_cache:
write_unlock(&et->lock);
+ if (is_inode_flag_set(inode, FI_NO_EXTENT))
+ __destroy_extent_node(inode, EX_READ);
+
if (updated)
f2fs_mark_inode_dirty_sync(inode, true);
}
@@ -856,10 +915,8 @@ static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
goto out;
if (__is_valid_data_blkaddr(blkaddr) &&
- !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
- f2fs_bug_on(sbi, 1);
+ !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE))
return -EINVAL;
- }
out:
/*
* init block age with zero, this can happen when the block age extent
@@ -912,10 +969,14 @@ static unsigned int __shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink
list_for_each_entry_safe(et, next, &eti->zombie_list, list) {
if (atomic_read(&et->node_cnt)) {
write_lock(&et->lock);
- node_cnt += __free_extent_tree(sbi, et);
+ node_cnt += __free_extent_tree(sbi, et,
+ nr_shrink - node_cnt - tree_cnt);
write_unlock(&et->lock);
}
- f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
+
+ if (atomic_read(&et->node_cnt))
+ goto unlock_out;
+
list_del_init(&et->list);
radix_tree_delete(&eti->extent_tree_root, et->ino);
kmem_cache_free(extent_tree_slab, et);
@@ -1054,23 +1115,6 @@ unsigned int f2fs_shrink_age_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink
return __shrink_extent_tree(sbi, nr_shrink, EX_BLOCK_AGE);
}
-static unsigned int __destroy_extent_node(struct inode *inode,
- enum extent_type type)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
- unsigned int node_cnt = 0;
-
- if (!et || !atomic_read(&et->node_cnt))
- return 0;
-
- write_lock(&et->lock);
- node_cnt = __free_extent_tree(sbi, et);
- write_unlock(&et->lock);
-
- return node_cnt;
-}
-
void f2fs_destroy_extent_node(struct inode *inode)
{
__destroy_extent_node(inode, EX_READ);
@@ -1079,7 +1123,6 @@ void f2fs_destroy_extent_node(struct inode *inode)
static void __drop_extent_tree(struct inode *inode, enum extent_type type)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct extent_tree *et = F2FS_I(inode)->extent_tree[type];
bool updated = false;
@@ -1087,7 +1130,6 @@ static void __drop_extent_tree(struct inode *inode, enum extent_type type)
return;
write_lock(&et->lock);
- __free_extent_tree(sbi, et);
if (type == EX_READ) {
set_inode_flag(inode, FI_NO_EXTENT);
if (et->largest.len) {
@@ -1096,6 +1138,9 @@ static void __drop_extent_tree(struct inode *inode, enum extent_type type)
}
}
write_unlock(&et->lock);
+
+ __destroy_extent_node(inode, type);
+
if (updated)
f2fs_mark_inode_dirty_sync(inode, true);
}
@@ -1169,6 +1214,7 @@ void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi)
sbi->hot_data_age_threshold = DEF_HOT_DATA_AGE_THRESHOLD;
sbi->warm_data_age_threshold = DEF_WARM_DATA_AGE_THRESHOLD;
sbi->last_age_weight = LAST_AGE_WEIGHT;
+ sbi->max_read_extent_count = DEF_MAX_READ_EXTENT_COUNT;
}
int __init f2fs_create_extent_cache(void)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 65294e3b0bef..1afa7be16e7d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -11,7 +11,6 @@
#include <linux/uio.h>
#include <linux/types.h>
#include <linux/page-flags.h>
-#include <linux/buffer_head.h>
#include <linux/slab.h>
#include <linux/crc32.h>
#include <linux/magic.h>
@@ -24,7 +23,7 @@
#include <linux/blkdev.h>
#include <linux/quotaops.h>
#include <linux/part_stat.h>
-#include <crypto/hash.h>
+#include <linux/rw_hint.h>
#include <linux/fscrypt.h>
#include <linux/fsverity.h>
@@ -60,7 +59,9 @@ enum {
FAULT_SLAB_ALLOC,
FAULT_DQUOT_INIT,
FAULT_LOCK_OP,
- FAULT_BLKADDR,
+ FAULT_BLKADDR_VALIDITY,
+ FAULT_BLKADDR_CONSISTENCE,
+ FAULT_NO_SEGMENT,
FAULT_MAX,
};
@@ -69,12 +70,17 @@ enum {
struct f2fs_fault_info {
atomic_t inject_ops;
- unsigned int inject_rate;
+ int inject_rate;
unsigned int inject_type;
};
extern const char *f2fs_fault_name[FAULT_MAX];
#define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type))
+
+/* maximum retry count for injected failure */
+#define DEFAULT_FAILURE_RETRY_COUNT 8
+#else
+#define DEFAULT_FAILURE_RETRY_COUNT 1
#endif
/*
@@ -126,6 +132,12 @@ typedef u32 nid_t;
#define COMPRESS_EXT_NUM 16
+enum blkzone_allocation_policy {
+ BLKZONE_ALLOC_PRIOR_SEQ, /* Prioritize writing to sequential zones */
+ BLKZONE_ALLOC_ONLY_SEQ, /* Only allow writing to sequential zones */
+ BLKZONE_ALLOC_PRIOR_CONV, /* Prioritize writing to conventional zones */
+};
+
/*
* An implementation of an rwsem that is explicitly unfair to readers. This
* prevents priority inversion when a low-priority reader acquires the read lock
@@ -142,7 +154,6 @@ struct f2fs_rwsem {
struct f2fs_mount_info {
unsigned int opt;
- int write_io_size_bits; /* Write IO size bits */
block_t root_reserved_blocks; /* root reserved blocks */
kuid_t s_resuid; /* reserved blocks for uid */
kgid_t s_resgid; /* reserved blocks for gid */
@@ -201,6 +212,7 @@ struct f2fs_mount_info {
#define F2FS_FEATURE_CASEFOLD 0x00001000
#define F2FS_FEATURE_COMPRESSION 0x00002000
#define F2FS_FEATURE_RO 0x00004000
+#define F2FS_FEATURE_DEVICE_ALIAS 0x00008000
#define __F2FS_HAS_FEATURE(raw_super, mask) \
((raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -278,6 +290,7 @@ enum {
APPEND_INO, /* for append ino list */
UPDATE_INO, /* for update ino list */
TRANS_DIR_INO, /* for transactions dir ino list */
+ XATTR_DIR_INO, /* for xattr updated dir ino list */
FLUSH_INO, /* for multiple device flushing */
MAX_INO_ENTRY, /* max. list */
};
@@ -524,7 +537,7 @@ struct f2fs_filename {
* internal operation where usr_fname is also NULL. In all these cases
* we fall back to treating the name as an opaque byte sequence.
*/
- struct fscrypt_str cf_name;
+ struct qstr cf_name;
#endif
};
@@ -621,6 +634,9 @@ enum {
#define DEF_HOT_DATA_AGE_THRESHOLD 262144
#define DEF_WARM_DATA_AGE_THRESHOLD 2621440
+/* default max read extent count per inode */
+#define DEF_MAX_READ_EXTENT_COUNT 10240
+
/* extent cache type */
enum extent_type {
EX_READ,
@@ -758,11 +774,6 @@ enum {
#define DEF_DIR_LEVEL 0
-enum {
- GC_FAILURE_PIN,
- MAX_GC_FAILURE
-};
-
/* used for f2fs_inode_info->flags */
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
@@ -782,7 +793,6 @@ enum {
FI_NEED_IPU, /* used for ipu per file */
FI_ATOMIC_FILE, /* indicate atomic file */
FI_DATA_EXIST, /* indicate data exists */
- FI_INLINE_DOTS, /* indicate inline dot dentries */
FI_SKIP_WRITES, /* should skip data page writeback */
FI_OPU_WRITE, /* used for opu per file */
FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
@@ -800,7 +810,9 @@ enum {
FI_ALIGNED_WRITE, /* enable aligned write */
FI_COW_FILE, /* indicate COW file */
FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */
+ FI_ATOMIC_DIRTIED, /* indicate atomic file is dirtied */
FI_ATOMIC_REPLACE, /* indicate atomic replace */
+ FI_OPENED_FILE, /* indicate file has been opened */
FI_MAX, /* max flag, never be used */
};
@@ -809,9 +821,10 @@ struct f2fs_inode_info {
unsigned long i_flags; /* keep an inode flags for ioctl */
unsigned char i_advise; /* use to give file attribute hints */
unsigned char i_dir_level; /* use for dentry level for large dir */
- unsigned int i_current_depth; /* only for directory depth */
- /* for gc failure statistic */
- unsigned int i_gc_failures[MAX_GC_FAILURE];
+ union {
+ unsigned int i_current_depth; /* only for directory depth */
+ unsigned short i_gc_failures; /* for gc failure statistic */
+ };
unsigned int i_pino; /* parent inode number */
umode_t i_acl_mode; /* keep file acl mode temporarily */
@@ -829,7 +842,7 @@ struct f2fs_inode_info {
spinlock_t i_size_lock; /* protect last_disk_size */
#ifdef CONFIG_QUOTA
- struct dquot *i_dquot[MAXQUOTAS];
+ struct dquot __rcu *i_dquot[MAXQUOTAS];
/* quota space reservation, managed internally by quota code */
qsize_t i_reserved_quota;
@@ -839,7 +852,11 @@ struct f2fs_inode_info {
struct task_struct *atomic_write_task; /* store atomic write task */
struct extent_tree *extent_tree[NR_EXTENT_CACHES];
/* cached extent_tree entry */
- struct inode *cow_inode; /* copy-on-write inode for atomic write */
+ union {
+ struct inode *cow_inode; /* copy-on-write inode for atomic write */
+ struct inode *atomic_inode;
+ /* point to atomic_inode, available only for cow_inode */
+ };
/* avoid racing between foreground op and gc */
struct f2fs_rwsem i_gc_rwsem[2];
@@ -1004,7 +1021,7 @@ static inline void set_new_dnode(struct dnode_of_data *dn, struct inode *inode,
#define NR_CURSEG_PERSIST_TYPE (NR_CURSEG_DATA_TYPE + NR_CURSEG_NODE_TYPE)
#define NR_CURSEG_TYPE (NR_CURSEG_INMEM_TYPE + NR_CURSEG_PERSIST_TYPE)
-enum {
+enum log_type {
CURSEG_HOT_DATA = 0, /* directory entry blocks */
CURSEG_WARM_DATA, /* data blocks */
CURSEG_COLD_DATA, /* multimedia or GCed data blocks */
@@ -1049,7 +1066,6 @@ struct f2fs_sm_info {
unsigned int segment_count; /* total # of segments */
unsigned int main_segments; /* # of segments in main area */
unsigned int reserved_segments; /* # of reserved segments */
- unsigned int additional_reserved_segments;/* reserved segs for IO align feature */
unsigned int ovp_segments; /* # of overprovision segments */
/* a threshold to reclaim prefree segments */
@@ -1080,7 +1096,8 @@ struct f2fs_sm_info {
* f2fs monitors the number of several block types such as on-writeback,
* dirty dentry blocks, dirty node blocks, and dirty meta blocks.
*/
-#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
+#define WB_DATA_TYPE(p, f) \
+ (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
enum count_type {
F2FS_DIRTY_DENTS,
F2FS_DIRTY_DATA,
@@ -1110,6 +1127,7 @@ enum count_type {
* ... Only can be used with META.
*/
#define PAGE_TYPE_OF_BIO(type) ((type) > META ? META : (type))
+#define PAGE_TYPE_ON_MAIN(type) ((type) == DATA || (type) == NODE)
enum page_type {
DATA = 0,
NODE = 1, /* should not change this */
@@ -1145,6 +1163,7 @@ enum cp_reason_type {
CP_FASTBOOT_MODE,
CP_SPEC_LOG_NUM,
CP_RECOVER_DIR,
+ CP_XATTR_DIR,
};
enum iostat_type {
@@ -1204,9 +1223,8 @@ struct f2fs_io_info {
unsigned int submitted:1; /* indicate IO submission */
unsigned int in_list:1; /* indicate fio is in io_list */
unsigned int is_por:1; /* indicate IO is from recovery or not */
- unsigned int retry:1; /* need to reallocate block address */
unsigned int encrypted:1; /* indicate file is encrypted */
- unsigned int post_read:1; /* require post read */
+ unsigned int meta_gc:1; /* require meta inode GC */
enum iostat_type io_type; /* io type */
struct writeback_control *io_wbc; /* writeback control */
struct bio **bio; /* bio for ipu */
@@ -1239,7 +1257,7 @@ struct f2fs_bio_info {
#define FDEV(i) (sbi->devs[i])
#define RDEV(i) (raw_super->devs[i])
struct f2fs_dev_info {
- struct bdev_handle *bdev_handle;
+ struct file *bdev_file;
struct block_device *bdev;
char path[MAX_PATH_LEN];
unsigned int total_segments;
@@ -1284,6 +1302,7 @@ struct f2fs_gc_control {
bool no_bg_gc; /* check the space and stop bg_gc */
bool should_migrate_blocks; /* should migrate blocks */
bool err_gc_skipped; /* return EAGAIN if GC skipped */
+ bool one_time; /* require one time GC in one migration unit */
unsigned int nr_free_secs; /* # of free sections to do GC */
};
@@ -1406,10 +1425,10 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr);
* Layout A: lowest bit should be 1
* | bit0 = 1 | bit1 | bit2 | ... | bit MAX | private data .... |
* bit 0 PAGE_PRIVATE_NOT_POINTER
- * bit 1 PAGE_PRIVATE_DUMMY_WRITE
- * bit 2 PAGE_PRIVATE_ONGOING_MIGRATION
- * bit 3 PAGE_PRIVATE_INLINE_INODE
- * bit 4 PAGE_PRIVATE_REF_RESOURCE
+ * bit 1 PAGE_PRIVATE_ONGOING_MIGRATION
+ * bit 2 PAGE_PRIVATE_INLINE_INODE
+ * bit 3 PAGE_PRIVATE_REF_RESOURCE
+ * bit 4 PAGE_PRIVATE_ATOMIC_WRITE
* bit 5- f2fs private data
*
* Layout B: lowest bit should be 0
@@ -1417,10 +1436,10 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr);
*/
enum {
PAGE_PRIVATE_NOT_POINTER, /* private contains non-pointer data */
- PAGE_PRIVATE_DUMMY_WRITE, /* data page for padding aligned IO */
PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */
PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */
PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */
+ PAGE_PRIVATE_ATOMIC_WRITE, /* data page from atomic write path */
PAGE_PRIVATE_MAX
};
@@ -1551,6 +1570,9 @@ struct f2fs_sb_info {
#ifdef CONFIG_BLK_DEV_ZONED
unsigned int blocks_per_blkz; /* F2FS blocks per zone */
+ unsigned int max_open_zones; /* max open zone resources of the zoned device */
+ /* For adjust the priority writing position of data in zone UFS */
+ unsigned int blkzone_alloc_policy;
#endif
/* for node-related operations */
@@ -1564,7 +1586,6 @@ struct f2fs_sb_info {
struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */
/* keep migration IO order for LFS mode */
struct f2fs_rwsem io_order_lock;
- mempool_t *write_io_dummy; /* Dummy pages */
pgoff_t page_eio_ofs[NR_PAGE_TYPE]; /* EIO page offset */
int page_eio_cnt[NR_PAGE_TYPE]; /* EIO count */
@@ -1600,6 +1621,7 @@ struct f2fs_sb_info {
/* for extent tree cache */
struct extent_tree_info extent_tree[NR_EXTENT_CACHES];
atomic64_t allocated_data_blocks; /* for block age extent_cache */
+ unsigned int max_read_extent_count; /* max read extent count per inode */
/* The threshold used for hot and warm data seperation*/
unsigned int hot_data_age_threshold;
@@ -1671,13 +1693,15 @@ struct f2fs_sb_info {
unsigned long long skipped_gc_rwsem; /* FG_GC only */
/* threshold for gc trials on pinned files */
- u64 gc_pin_file_threshold;
+ unsigned short gc_pin_file_threshold;
struct f2fs_rwsem pin_sem;
/* maximum # of trials to find a victim segment for SSR and GC */
unsigned int max_victim_search;
/* migration granularity of garbage collection, unit: segment */
unsigned int migration_granularity;
+ /* migration window granularity of garbage collection, unit: segment */
+ unsigned int migration_window_granularity;
/*
* for stat information.
@@ -1737,14 +1761,12 @@ struct f2fs_sb_info {
unsigned int dirty_device; /* for checkpoint data flush */
spinlock_t dev_lock; /* protect dirty_device */
bool aligned_blksize; /* all devices has the same logical blksize */
+ unsigned int first_zoned_segno; /* first zoned segno */
/* For write statistics */
u64 sectors_written_start;
u64 kbytes_written;
- /* Reference to checksum algorithm driver via cryptoapi */
- struct crypto_shash *s_chksum_driver;
-
/* Precomputed FS UUID checksum for seeding other checksums */
__u32 s_chksum_seed;
@@ -1810,6 +1832,37 @@ struct f2fs_sb_info {
#endif
};
+/* Definitions to access f2fs_sb_info */
+#define SEGS_TO_BLKS(sbi, segs) \
+ ((segs) << (sbi)->log_blocks_per_seg)
+#define BLKS_TO_SEGS(sbi, blks) \
+ ((blks) >> (sbi)->log_blocks_per_seg)
+
+#define BLKS_PER_SEG(sbi) ((sbi)->blocks_per_seg)
+#define BLKS_PER_SEC(sbi) (SEGS_TO_BLKS(sbi, (sbi)->segs_per_sec))
+#define SEGS_PER_SEC(sbi) ((sbi)->segs_per_sec)
+
+__printf(3, 4)
+void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate, const char *fmt, ...);
+
+#define f2fs_err(sbi, fmt, ...) \
+ f2fs_printk(sbi, false, KERN_ERR fmt, ##__VA_ARGS__)
+#define f2fs_warn(sbi, fmt, ...) \
+ f2fs_printk(sbi, false, KERN_WARNING fmt, ##__VA_ARGS__)
+#define f2fs_notice(sbi, fmt, ...) \
+ f2fs_printk(sbi, false, KERN_NOTICE fmt, ##__VA_ARGS__)
+#define f2fs_info(sbi, fmt, ...) \
+ f2fs_printk(sbi, false, KERN_INFO fmt, ##__VA_ARGS__)
+#define f2fs_debug(sbi, fmt, ...) \
+ f2fs_printk(sbi, false, KERN_DEBUG fmt, ##__VA_ARGS__)
+
+#define f2fs_err_ratelimited(sbi, fmt, ...) \
+ f2fs_printk(sbi, true, KERN_ERR fmt, ##__VA_ARGS__)
+#define f2fs_warn_ratelimited(sbi, fmt, ...) \
+ f2fs_printk(sbi, true, KERN_WARNING fmt, ##__VA_ARGS__)
+#define f2fs_info_ratelimited(sbi, fmt, ...) \
+ f2fs_printk(sbi, true, KERN_INFO fmt, ##__VA_ARGS__)
+
#ifdef CONFIG_F2FS_FAULT_INJECTION
#define time_to_inject(sbi, type) __time_to_inject(sbi, type, __func__, \
__builtin_return_address(0))
@@ -1827,9 +1880,8 @@ static inline bool __time_to_inject(struct f2fs_sb_info *sbi, int type,
atomic_inc(&ffi->inject_ops);
if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
atomic_set(&ffi->inject_ops, 0);
- printk_ratelimited("%sF2FS-fs (%s) : inject %s in %s of %pS\n",
- KERN_INFO, sbi->sb->s_id, f2fs_fault_name[type],
- func, parent_func);
+ f2fs_info_ratelimited(sbi, "inject %s in %s of %pS",
+ f2fs_fault_name[type], func, parent_func);
return true;
}
return false;
@@ -1892,21 +1944,7 @@ static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi,
static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
const void *address, unsigned int length)
{
- struct {
- struct shash_desc shash;
- char ctx[4];
- } desc;
- int err;
-
- BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));
-
- desc.shash.tfm = sbi->s_chksum_driver;
- *(u32 *)desc.ctx = crc;
-
- err = crypto_shash_update(&desc.shash, address, length);
- BUG_ON(err);
-
- return *(u32 *)desc.ctx;
+ return crc32(crc, address, length);
}
static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
@@ -1947,9 +1985,14 @@ static inline struct f2fs_sb_info *F2FS_M_SB(struct address_space *mapping)
return F2FS_I_SB(mapping->host);
}
+static inline struct f2fs_sb_info *F2FS_F_SB(struct folio *folio)
+{
+ return F2FS_M_SB(folio->mapping);
+}
+
static inline struct f2fs_sb_info *F2FS_P_SB(struct page *page)
{
- return F2FS_M_SB(page_file_mapping(page));
+ return F2FS_F_SB(page_folio(page));
}
static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
@@ -1957,6 +2000,16 @@ static inline struct f2fs_super_block *F2FS_RAW_SUPER(struct f2fs_sb_info *sbi)
return (struct f2fs_super_block *)(sbi->raw_super);
}
+static inline struct f2fs_super_block *F2FS_SUPER_BLOCK(struct folio *folio,
+ pgoff_t index)
+{
+ pgoff_t idx_in_folio = index % (1 << folio_order(folio));
+
+ return (struct f2fs_super_block *)
+ (page_address(folio_page(folio, idx_in_folio)) +
+ F2FS_SUPER_OFFSET);
+}
+
static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
{
return (struct f2fs_checkpoint *)(sbi->ckpt);
@@ -2249,11 +2302,32 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi,
return false;
}
+static inline unsigned int get_available_block_count(struct f2fs_sb_info *sbi,
+ struct inode *inode, bool cap)
+{
+ block_t avail_user_block_count;
+
+ avail_user_block_count = sbi->user_block_count -
+ sbi->current_reserved_blocks;
+
+ if (!__allow_reserved_blocks(sbi, inode, cap))
+ avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ if (avail_user_block_count > sbi->unusable_block_count)
+ avail_user_block_count -= sbi->unusable_block_count;
+ else
+ avail_user_block_count = 0;
+ }
+
+ return avail_user_block_count;
+}
+
static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
- struct inode *inode, blkcnt_t *count)
+ struct inode *inode, blkcnt_t *count, bool partial)
{
- blkcnt_t diff = 0, release = 0;
+ long long diff = 0, release = 0;
block_t avail_user_block_count;
int ret;
@@ -2273,35 +2347,27 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
percpu_counter_add(&sbi->alloc_valid_block_count, (*count));
spin_lock(&sbi->stat_lock);
- sbi->total_valid_block_count += (block_t)(*count);
- avail_user_block_count = sbi->user_block_count -
- sbi->current_reserved_blocks;
- if (!__allow_reserved_blocks(sbi, inode, true))
- avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks;
-
- if (F2FS_IO_ALIGNED(sbi))
- avail_user_block_count -= sbi->blocks_per_seg *
- SM_I(sbi)->additional_reserved_segments;
-
- if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
- if (avail_user_block_count > sbi->unusable_block_count)
- avail_user_block_count -= sbi->unusable_block_count;
- else
- avail_user_block_count = 0;
- }
- if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
- diff = sbi->total_valid_block_count - avail_user_block_count;
+ avail_user_block_count = get_available_block_count(sbi, inode, true);
+ diff = (long long)sbi->total_valid_block_count + *count -
+ avail_user_block_count;
+ if (unlikely(diff > 0)) {
+ if (!partial) {
+ spin_unlock(&sbi->stat_lock);
+ release = *count;
+ goto enospc;
+ }
if (diff > *count)
diff = *count;
*count -= diff;
release = diff;
- sbi->total_valid_block_count -= diff;
if (!*count) {
spin_unlock(&sbi->stat_lock);
goto enospc;
}
}
+ sbi->total_valid_block_count += (block_t)(*count);
+
spin_unlock(&sbi->stat_lock);
if (unlikely(release)) {
@@ -2318,20 +2384,6 @@ release_quota:
return -ENOSPC;
}
-__printf(2, 3)
-void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...);
-
-#define f2fs_err(sbi, fmt, ...) \
- f2fs_printk(sbi, KERN_ERR fmt, ##__VA_ARGS__)
-#define f2fs_warn(sbi, fmt, ...) \
- f2fs_printk(sbi, KERN_WARNING fmt, ##__VA_ARGS__)
-#define f2fs_notice(sbi, fmt, ...) \
- f2fs_printk(sbi, KERN_NOTICE fmt, ##__VA_ARGS__)
-#define f2fs_info(sbi, fmt, ...) \
- f2fs_printk(sbi, KERN_INFO fmt, ##__VA_ARGS__)
-#define f2fs_debug(sbi, fmt, ...) \
- f2fs_printk(sbi, KERN_DEBUG fmt, ##__VA_ARGS__)
-
#define PAGE_PRIVATE_GET_FUNC(name, flagname) \
static inline bool page_private_##name(struct page *page) \
{ \
@@ -2360,17 +2412,17 @@ static inline void clear_page_private_##name(struct page *page) \
PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER);
PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION);
-PAGE_PRIVATE_GET_FUNC(dummy, DUMMY_WRITE);
+PAGE_PRIVATE_GET_FUNC(atomic, ATOMIC_WRITE);
PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE);
PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION);
-PAGE_PRIVATE_SET_FUNC(dummy, DUMMY_WRITE);
+PAGE_PRIVATE_SET_FUNC(atomic, ATOMIC_WRITE);
PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE);
PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE);
PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION);
-PAGE_PRIVATE_CLEAR_FUNC(dummy, DUMMY_WRITE);
+PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
static inline unsigned long get_page_private_data(struct page *page)
{
@@ -2402,6 +2454,7 @@ static inline void clear_page_private_all(struct page *page)
clear_page_private_reference(page);
clear_page_private_gcing(page);
clear_page_private_inline(page);
+ clear_page_private_atomic(page);
f2fs_bug_on(F2FS_P_SB(page), page_private(page));
}
@@ -2504,11 +2557,8 @@ static inline int get_dirty_pages(struct inode *inode)
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
- unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
- unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
- sbi->log_blocks_per_seg;
-
- return segs / sbi->segs_per_sec;
+ return div_u64(get_pages(sbi, block_type) + BLKS_PER_SEC(sbi) - 1,
+ BLKS_PER_SEC(sbi));
}
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
@@ -2572,7 +2622,7 @@ static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
if (sbi->cur_cp_pack == 2)
- start_addr += sbi->blocks_per_seg;
+ start_addr += BLKS_PER_SEG(sbi);
return start_addr;
}
@@ -2581,7 +2631,7 @@ static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
if (sbi->cur_cp_pack == 1)
- start_addr += sbi->blocks_per_seg;
+ start_addr += BLKS_PER_SEG(sbi);
return start_addr;
}
@@ -2600,7 +2650,8 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
struct inode *inode, bool is_inode)
{
block_t valid_block_count;
- unsigned int valid_node_count, user_block_count;
+ unsigned int valid_node_count;
+ unsigned int avail_user_block_count;
int err;
if (is_inode) {
@@ -2620,21 +2671,10 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
spin_lock(&sbi->stat_lock);
- valid_block_count = sbi->total_valid_block_count +
- sbi->current_reserved_blocks + 1;
-
- if (!__allow_reserved_blocks(sbi, inode, false))
- valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks;
+ valid_block_count = sbi->total_valid_block_count + 1;
+ avail_user_block_count = get_available_block_count(sbi, inode, false);
- if (F2FS_IO_ALIGNED(sbi))
- valid_block_count += sbi->blocks_per_seg *
- SM_I(sbi)->additional_reserved_segments;
-
- user_block_count = sbi->user_block_count;
- if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
- user_block_count -= sbi->unusable_block_count;
-
- if (unlikely(valid_block_count > user_block_count)) {
+ if (unlikely(valid_block_count > avail_user_block_count)) {
spin_unlock(&sbi->stat_lock);
goto enospc;
}
@@ -2834,13 +2874,26 @@ static inline bool is_inflight_io(struct f2fs_sb_info *sbi, int type)
return false;
}
+static inline bool is_inflight_read_io(struct f2fs_sb_info *sbi)
+{
+ return get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_DIO_READ);
+}
+
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
+ bool zoned_gc = (type == GC_TIME &&
+ F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_BLKZONED));
+
if (sbi->gc_mode == GC_URGENT_HIGH)
return true;
- if (is_inflight_io(sbi, type))
- return false;
+ if (zoned_gc) {
+ if (is_inflight_read_io(sbi))
+ return false;
+ } else {
+ if (is_inflight_io(sbi, type))
+ return false;
+ }
if (sbi->gc_mode == GC_URGENT_MID)
return true;
@@ -2849,6 +2902,9 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
(type == DISCARD_TIME || type == GC_TIME))
return true;
+ if (zoned_gc)
+ return true;
+
return f2fs_time_over(sbi, type);
}
@@ -2880,26 +2936,27 @@ static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
}
static inline int f2fs_has_extra_attr(struct inode *inode);
-static inline block_t data_blkaddr(struct inode *inode,
- struct page *node_page, unsigned int offset)
+static inline unsigned int get_dnode_base(struct inode *inode,
+ struct page *node_page)
{
- struct f2fs_node *raw_node;
- __le32 *addr_array;
- int base = 0;
- bool is_inode = IS_INODE(node_page);
+ if (!IS_INODE(node_page))
+ return 0;
- raw_node = F2FS_NODE(node_page);
+ return inode ? get_extra_isize(inode) :
+ offset_in_addr(&F2FS_NODE(node_page)->i);
+}
- if (is_inode) {
- if (!inode)
- /* from GC path only */
- base = offset_in_addr(&raw_node->i);
- else if (f2fs_has_extra_attr(inode))
- base = get_extra_isize(inode);
- }
+static inline __le32 *get_dnode_addr(struct inode *inode,
+ struct page *node_page)
+{
+ return blkaddr_in_node(F2FS_NODE(node_page)) +
+ get_dnode_base(inode, node_page);
+}
- addr_array = blkaddr_in_node(raw_node);
- return le32_to_cpu(addr_array[base + offset]);
+static inline block_t data_blkaddr(struct inode *inode,
+ struct page *node_page, unsigned int offset)
+{
+ return le32_to_cpu(*(get_dnode_addr(inode, node_page) + offset));
}
static inline block_t f2fs_data_blkaddr(struct dnode_of_data *dn)
@@ -2981,6 +3038,7 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
#define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
#define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
#define F2FS_CASEFOLD_FL 0x40000000 /* Casefolded file */
+#define F2FS_DEVICE_ALIAS_FL 0x80000000 /* File for aliasing a device */
#define F2FS_QUOTA_DEFAULT_FL (F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL)
@@ -2996,6 +3054,8 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
/* Flags that are appropriate for non-directories/regular files. */
#define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL)
+#define IS_DEVICE_ALIASING(inode) (F2FS_I(inode)->i_flags & F2FS_DEVICE_ALIAS_FL)
+
static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
{
if (S_ISDIR(mode))
@@ -3018,7 +3078,6 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
return;
fallthrough;
case FI_DATA_EXIST:
- case FI_INLINE_DOTS:
case FI_PIN_FILE:
case FI_COMPRESS_RELEASED:
f2fs_mark_inode_dirty_sync(inode, true);
@@ -3114,7 +3173,7 @@ static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
static inline void f2fs_i_gc_failures_write(struct inode *inode,
unsigned int count)
{
- F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count;
+ F2FS_I(inode)->i_gc_failures = count;
f2fs_mark_inode_dirty_sync(inode, true);
}
@@ -3142,8 +3201,6 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
set_bit(FI_INLINE_DENTRY, fi->flags);
if (ri->i_inline & F2FS_DATA_EXIST)
set_bit(FI_DATA_EXIST, fi->flags);
- if (ri->i_inline & F2FS_INLINE_DOTS)
- set_bit(FI_INLINE_DOTS, fi->flags);
if (ri->i_inline & F2FS_EXTRA_ATTR)
set_bit(FI_EXTRA_ATTR, fi->flags);
if (ri->i_inline & F2FS_PIN_FILE)
@@ -3164,8 +3221,6 @@ static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
ri->i_inline |= F2FS_INLINE_DENTRY;
if (is_inode_flag_set(inode, FI_DATA_EXIST))
ri->i_inline |= F2FS_DATA_EXIST;
- if (is_inode_flag_set(inode, FI_INLINE_DOTS))
- ri->i_inline |= F2FS_INLINE_DOTS;
if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
ri->i_inline |= F2FS_EXTRA_ATTR;
if (is_inode_flag_set(inode, FI_PIN_FILE))
@@ -3206,21 +3261,15 @@ static inline bool f2fs_need_compress_data(struct inode *inode)
return false;
}
-static inline unsigned int addrs_per_inode(struct inode *inode)
+static inline unsigned int addrs_per_page(struct inode *inode,
+ bool is_inode)
{
- unsigned int addrs = CUR_ADDRS_PER_INODE(inode) -
- get_inline_xattr_addrs(inode);
+ unsigned int addrs = is_inode ? (CUR_ADDRS_PER_INODE(inode) -
+ get_inline_xattr_addrs(inode)) : DEF_ADDRS_PER_BLOCK;
- if (!f2fs_compressed_file(inode))
- return addrs;
- return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
-}
-
-static inline unsigned int addrs_per_block(struct inode *inode)
-{
- if (!f2fs_compressed_file(inode))
- return DEF_ADDRS_PER_BLOCK;
- return ALIGN_DOWN(DEF_ADDRS_PER_BLOCK, F2FS_I(inode)->i_cluster_size);
+ if (f2fs_compressed_file(inode))
+ return ALIGN_DOWN(addrs, F2FS_I(inode)->i_cluster_size);
+ return addrs;
}
static inline void *inline_xattr_addr(struct inode *inode, struct page *page)
@@ -3252,11 +3301,6 @@ static inline int f2fs_exist_data(struct inode *inode)
return is_inode_flag_set(inode, FI_DATA_EXIST);
}
-static inline int f2fs_has_inline_dots(struct inode *inode)
-{
- return is_inode_flag_set(inode, FI_INLINE_DOTS);
-}
-
static inline int f2fs_is_mmap_file(struct inode *inode)
{
return is_inode_flag_set(inode, FI_MMAP_FILE);
@@ -3277,8 +3321,6 @@ static inline bool f2fs_is_cow_file(struct inode *inode)
return is_inode_flag_set(inode, FI_COW_FILE);
}
-static inline __le32 *get_dnode_addr(struct inode *inode,
- struct page *node_page);
static inline void *inline_data_addr(struct inode *inode, struct page *page)
{
__le32 *addr = get_dnode_addr(inode, page);
@@ -3364,17 +3406,6 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
}
-static inline bool is_dot_dotdot(const u8 *name, size_t len)
-{
- if (len == 1 && name[0] == '.')
- return true;
-
- if (len == 2 && name[0] == '.' && name[1] == '.')
- return true;
-
- return false;
-}
-
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
size_t size, gfp_t flags)
{
@@ -3428,17 +3459,6 @@ static inline int get_inline_xattr_addrs(struct inode *inode)
return F2FS_I(inode)->i_inline_xattr_size;
}
-static inline __le32 *get_dnode_addr(struct inode *inode,
- struct page *node_page)
-{
- int base = 0;
-
- if (IS_INODE(node_page) && f2fs_has_extra_attr(inode))
- base = get_extra_isize(inode);
-
- return blkaddr_in_node(F2FS_NODE(node_page)) + base;
-}
-
#define f2fs_get_inode_mode(i) \
((is_inode_flag_set(i, FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
@@ -3455,7 +3475,7 @@ static inline __le32 *get_dnode_addr(struct inode *inode,
sizeof((f2fs_inode)->field)) \
<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \
-#define __is_large_section(sbi) ((sbi)->segs_per_sec > 1)
+#define __is_large_section(sbi) (SEGS_PER_SEC(sbi) > 1)
#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META)
@@ -3464,11 +3484,9 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
static inline void verify_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type)
{
- if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) {
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type))
f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.",
blkaddr, type);
- f2fs_bug_on(sbi, 1);
- }
}
static inline bool __is_valid_data_blkaddr(block_t blkaddr)
@@ -3492,6 +3510,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr);
int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
+int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
+ bool readonly, bool need_lock);
int f2fs_precache_extents(struct inode *inode);
int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
int f2fs_fileattr_set(struct mnt_idmap *idmap,
@@ -3528,15 +3548,30 @@ int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
/*
* dir.c
*/
+#if IS_ENABLED(CONFIG_UNICODE)
int f2fs_init_casefolded_name(const struct inode *dir,
struct f2fs_filename *fname);
+void f2fs_free_casefolded_name(struct f2fs_filename *fname);
+#else
+static inline int f2fs_init_casefolded_name(const struct inode *dir,
+ struct f2fs_filename *fname)
+{
+ return 0;
+}
+
+static inline void f2fs_free_casefolded_name(struct f2fs_filename *fname)
+{
+}
+#endif /* CONFIG_UNICODE */
+
int f2fs_setup_filename(struct inode *dir, const struct qstr *iname,
int lookup, struct f2fs_filename *fname);
int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
struct f2fs_filename *fname);
void f2fs_free_filename(struct f2fs_filename *fname);
struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
- const struct f2fs_filename *fname, int *max_slots);
+ const struct f2fs_filename *fname, int *max_slots,
+ bool use_hash);
int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
unsigned int start_pos, struct fscrypt_str *fstr);
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
@@ -3570,7 +3605,8 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode);
-int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
+int f2fs_do_tmpfile(struct inode *inode, struct inode *dir,
+ struct f2fs_filename *fname);
bool f2fs_empty_dir(struct inode *dir);
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
@@ -3592,8 +3628,7 @@ 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_save_errors(struct f2fs_sb_info *sbi, unsigned char flag);
-void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
- bool irq_context);
+void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason);
void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error);
void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error);
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
@@ -3671,7 +3706,8 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino);
int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi);
int f2fs_flush_device_cache(struct f2fs_sb_info *sbi);
void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
-void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
+void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr,
+ unsigned int len);
bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
int f2fs_start_discard_thread(struct f2fs_sb_info *sbi);
void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
@@ -3685,22 +3721,22 @@ int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno);
-void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
+int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi);
+int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi);
void f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi);
void f2fs_restore_inmem_curseg(struct f2fs_sb_info *sbi);
-void f2fs_get_new_segment(struct f2fs_sb_info *sbi,
- unsigned int *newseg, bool new_sec, int dir);
-void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
+int f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end);
-void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force);
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
+int f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force);
+int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi);
+int f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src,
block_t blk_addr);
-void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct folio *folio,
enum iostat_type io_type);
void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio);
void f2fs_outplace_write_data(struct dnode_of_data *dn,
@@ -3714,7 +3750,9 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
block_t old_addr, block_t new_addr,
unsigned char version, bool recover_curseg,
bool recover_newaddr);
-void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+enum temp_type f2fs_get_segment_temp(struct f2fs_sb_info *sbi,
+ enum log_type seg_type);
+int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
struct f2fs_io_info *fio);
@@ -3730,17 +3768,19 @@ void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc);
void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
-int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi);
-int f2fs_check_write_pointer(struct f2fs_sb_info *sbi);
+int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi);
int f2fs_build_segment_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init f2fs_create_segment_manager_caches(void);
void f2fs_destroy_segment_manager_caches(void);
-int f2fs_rw_hint_to_seg_type(enum rw_hint hint);
-unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
- unsigned int segno);
+int f2fs_rw_hint_to_seg_type(struct f2fs_sb_info *sbi, enum rw_hint hint);
+enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
+ enum page_type type, enum temp_type temp);
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi);
unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
unsigned int segno);
+unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
+ unsigned int segno);
#define DEF_FRAGMENT_SIZE 4
#define MIN_FRAGMENT_SIZE 1
@@ -3764,6 +3804,8 @@ struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index);
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
block_t blkaddr, int type);
+bool f2fs_is_valid_blkaddr_raw(struct f2fs_sb_info *sbi,
+ block_t blkaddr, int type);
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync);
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index,
@@ -3804,6 +3846,7 @@ void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi);
*/
int __init f2fs_init_bioset(void);
void f2fs_destroy_bioset(void);
+bool f2fs_is_cp_guaranteed(struct page *page);
int f2fs_init_bio_entry_cache(void);
void f2fs_destroy_bio_entry_cache(void);
void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio,
@@ -3843,7 +3886,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
int f2fs_encrypt_one_page(struct f2fs_io_info *fio);
bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio);
bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio);
-int f2fs_write_single_data_page(struct page *page, int *submitted,
+int f2fs_write_single_data_page(struct folio *folio, int *submitted,
struct bio **bio, sector_t *last_block,
struct writeback_control *wbc,
enum iostat_type io_type,
@@ -3852,7 +3895,7 @@ void f2fs_write_failed(struct inode *inode, loff_t to);
void f2fs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
bool f2fs_release_folio(struct folio *folio, gfp_t wait);
bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len);
-void f2fs_clear_page_cache_dirty_tag(struct page *page);
+void f2fs_clear_page_cache_dirty_tag(struct folio *folio);
int f2fs_init_post_read_processing(void);
void f2fs_destroy_post_read_processing(void);
int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
@@ -3867,13 +3910,16 @@ void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi);
block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control);
void f2fs_build_gc_manager(struct f2fs_sb_info *sbi);
+int f2fs_gc_range(struct f2fs_sb_info *sbi,
+ unsigned int start_seg, unsigned int end_seg,
+ bool dry_run, unsigned int dry_run_sections);
int f2fs_resize_fs(struct file *filp, __u64 block_count);
int __init f2fs_create_garbage_collection_cache(void);
void f2fs_destroy_garbage_collection_cache(void);
/* victim selection function for cleaning and SSR */
int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result,
int gc_type, int type, char alloc_mode,
- unsigned long long age);
+ unsigned long long age, bool one_time);
/*
* recovery.c
@@ -3887,6 +3933,19 @@ void f2fs_destroy_recovery_cache(void);
* debug.c
*/
#ifdef CONFIG_F2FS_STAT_FS
+enum {
+ DEVSTAT_INUSE,
+ DEVSTAT_DIRTY,
+ DEVSTAT_FULL,
+ DEVSTAT_FREE,
+ DEVSTAT_PREFREE,
+ DEVSTAT_MAX,
+};
+
+struct f2fs_dev_stats {
+ unsigned int devstats[2][DEVSTAT_MAX]; /* 0: segs, 1: secs */
+};
+
struct f2fs_stat_info {
struct list_head stat_list;
struct f2fs_sb_info *sbi;
@@ -3950,6 +4009,7 @@ struct f2fs_stat_info {
unsigned int block_count[2];
unsigned int inplace_count;
unsigned long long base_mem, cache_mem, page_mem;
+ struct f2fs_dev_stats *dev_stats;
};
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
@@ -3959,7 +4019,7 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
#define stat_inc_cp_call_count(sbi, foreground) \
atomic_inc(&sbi->cp_call_count[(foreground)])
-#define stat_inc_cp_count(si) (F2FS_STAT(sbi)->cp_count++)
+#define stat_inc_cp_count(sbi) (F2FS_STAT(sbi)->cp_count++)
#define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++)
#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++)
#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++)
@@ -4135,20 +4195,21 @@ extern struct kmem_cache *f2fs_inode_entry_slab;
* inline.c
*/
bool f2fs_may_inline_data(struct inode *inode);
-bool f2fs_sanity_check_inline_data(struct inode *inode);
+bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage);
bool f2fs_may_inline_dentry(struct inode *inode);
-void f2fs_do_read_inline_data(struct page *page, struct page *ipage);
+void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage);
void f2fs_truncate_inline_inode(struct inode *inode,
struct page *ipage, u64 from);
-int f2fs_read_inline_data(struct inode *inode, struct page *page);
+int f2fs_read_inline_data(struct inode *inode, struct folio *folio);
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
-int f2fs_write_inline_data(struct inode *inode, struct page *page);
+int f2fs_write_inline_data(struct inode *inode, struct folio *folio);
int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
const struct f2fs_filename *fname,
- struct page **res_page);
+ struct page **res_page,
+ bool use_hash);
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage);
int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
@@ -4176,7 +4237,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
/*
* extent_cache.c
*/
-bool sanity_check_extent_cache(struct inode *inode);
+bool sanity_check_extent_cache(struct inode *inode, struct page *ipage);
void f2fs_init_extent_tree(struct inode *inode);
void f2fs_drop_extent_tree(struct inode *inode);
void f2fs_destroy_extent_node(struct inode *inode);
@@ -4247,10 +4308,25 @@ static inline bool f2fs_post_read_required(struct inode *inode)
f2fs_compressed_file(inode);
}
+static inline bool f2fs_used_in_atomic_write(struct inode *inode)
+{
+ return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode);
+}
+
+static inline bool f2fs_meta_inode_gc_required(struct inode *inode)
+{
+ return f2fs_post_read_required(inode) || f2fs_used_in_atomic_write(inode);
+}
+
/*
* compress.c
*/
#ifdef CONFIG_F2FS_FS_COMPRESSION
+enum cluster_check_type {
+ CLUSTER_IS_COMPR, /* check only if compressed cluster */
+ CLUSTER_COMPR_BLKS, /* return # of compressed blocks in a cluster */
+ CLUSTER_RAW_BLKS /* return # of raw blocks in a cluster */
+};
bool f2fs_is_compressed_page(struct page *page);
struct page *f2fs_compress_control_page(struct page *page);
int f2fs_prepare_compress_overwrite(struct inode *inode,
@@ -4271,23 +4347,25 @@ bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages,
int index, int nr_pages, bool uptodate);
bool f2fs_sanity_check_cluster(struct dnode_of_data *dn);
-void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page);
+void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio);
int f2fs_write_multi_pages(struct compress_ctx *cc,
int *submitted,
struct writeback_control *wbc,
enum iostat_type io_type);
int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
+bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index);
void f2fs_update_read_extent_tree_range_compressed(struct inode *inode,
pgoff_t fofs, block_t blkaddr,
unsigned int llen, unsigned int c_len);
int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
unsigned nr_pages, sector_t *last_block_in_bio,
- bool is_readahead, bool for_write);
+ struct readahead_control *rac, bool for_write);
struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc);
void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed,
bool in_task);
void f2fs_put_page_dic(struct page *page, bool in_task);
-unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn);
+unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn,
+ unsigned int ofs_in_node);
int f2fs_init_compress_ctx(struct compress_ctx *cc);
void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse);
void f2fs_init_compress_info(struct f2fs_sb_info *sbi);
@@ -4298,7 +4376,8 @@ void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi);
int __init f2fs_init_compress_cache(void);
void f2fs_destroy_compress_cache(void);
struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi);
-void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi, block_t blkaddr);
+void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi,
+ block_t blkaddr, unsigned int len);
void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
nid_t ino, block_t blkaddr);
bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi, struct page *page,
@@ -4344,7 +4423,8 @@ static inline void f2fs_put_page_dic(struct page *page, bool in_task)
{
WARN_ON_ONCE(1);
}
-static inline unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) { return 0; }
+static inline unsigned int f2fs_cluster_blocks_are_contiguous(
+ struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; }
static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; }
static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { }
@@ -4352,8 +4432,8 @@ static inline int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { return
static inline void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { }
static inline int __init f2fs_init_compress_cache(void) { return 0; }
static inline void f2fs_destroy_compress_cache(void) { }
-static inline void f2fs_invalidate_compress_page(struct f2fs_sb_info *sbi,
- block_t blkaddr) { }
+static inline void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi,
+ block_t blkaddr, unsigned int len) { }
static inline void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi,
struct page *page, nid_t ino, block_t blkaddr) { }
static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
@@ -4361,6 +4441,12 @@ static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi,
nid_t ino) { }
#define inc_compr_inode_stat(inode) do { } while (0)
+static inline int f2fs_is_compressed_cluster(
+ struct inode *inode,
+ pgoff_t index) { return 0; }
+static inline bool f2fs_is_sparse_cluster(
+ struct inode *inode,
+ pgoff_t index) { return true; }
static inline void f2fs_update_read_extent_tree_range_compressed(
struct inode *inode,
pgoff_t fofs, block_t blkaddr,
@@ -4371,22 +4457,18 @@ static inline int set_compress_context(struct inode *inode)
{
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
- F2FS_I(inode)->i_compress_algorithm =
- F2FS_OPTION(sbi).compress_algorithm;
- F2FS_I(inode)->i_log_cluster_size =
- F2FS_OPTION(sbi).compress_log_size;
- F2FS_I(inode)->i_compress_flag =
- F2FS_OPTION(sbi).compress_chksum ?
- BIT(COMPRESS_CHKSUM) : 0;
- F2FS_I(inode)->i_cluster_size =
- BIT(F2FS_I(inode)->i_log_cluster_size);
- if ((F2FS_I(inode)->i_compress_algorithm == COMPRESS_LZ4 ||
- F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) &&
+ fi->i_compress_algorithm = F2FS_OPTION(sbi).compress_algorithm;
+ fi->i_log_cluster_size = F2FS_OPTION(sbi).compress_log_size;
+ fi->i_compress_flag = F2FS_OPTION(sbi).compress_chksum ?
+ BIT(COMPRESS_CHKSUM) : 0;
+ fi->i_cluster_size = BIT(fi->i_log_cluster_size);
+ if ((fi->i_compress_algorithm == COMPRESS_LZ4 ||
+ fi->i_compress_algorithm == COMPRESS_ZSTD) &&
F2FS_OPTION(sbi).compress_level)
- F2FS_I(inode)->i_compress_level =
- F2FS_OPTION(sbi).compress_level;
- F2FS_I(inode)->i_flags |= F2FS_COMPR_FL;
+ fi->i_compress_level = F2FS_OPTION(sbi).compress_level;
+ fi->i_flags |= F2FS_COMPR_FL;
set_inode_flag(inode, FI_COMPRESSED_FILE);
stat_inc_compr_inode(inode);
inc_compr_inode_stat(inode);
@@ -4401,15 +4483,24 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
- if (!f2fs_compressed_file(inode))
+ f2fs_down_write(&fi->i_sem);
+
+ if (!f2fs_compressed_file(inode)) {
+ f2fs_up_write(&fi->i_sem);
return true;
- if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))
+ }
+ if (f2fs_is_mmap_file(inode) ||
+ (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) {
+ f2fs_up_write(&fi->i_sem);
return false;
+ }
fi->i_flags &= ~F2FS_COMPR_FL;
stat_dec_compr_inode(inode);
clear_inode_flag(inode, FI_COMPRESSED_FILE);
f2fs_mark_inode_dirty_sync(inode, true);
+
+ f2fs_up_write(&fi->i_sem);
return true;
}
@@ -4433,6 +4524,7 @@ F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
F2FS_FEATURE_FUNCS(compression, COMPRESSION);
F2FS_FEATURE_FUNCS(readonly, RO);
+F2FS_FEATURE_FUNCS(device_alias, DEVICE_ALIAS);
#ifdef CONFIG_BLK_DEV_ZONED
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
@@ -4512,6 +4604,17 @@ static inline bool f2fs_lfs_mode(struct f2fs_sb_info *sbi)
return F2FS_OPTION(sbi).fs_mode == FS_MODE_LFS;
}
+static inline bool f2fs_valid_pinned_area(struct f2fs_sb_info *sbi,
+ block_t blkaddr)
+{
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ int devi = f2fs_target_device_index(sbi, blkaddr);
+
+ return !bdev_is_zoned(FDEV(devi).bdev);
+ }
+ return true;
+}
+
static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi)
{
return F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW;
@@ -4563,10 +4666,14 @@ static inline bool f2fs_need_verity(const struct inode *inode, pgoff_t idx)
}
#ifdef CONFIG_F2FS_FAULT_INJECTION
-extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
- unsigned int type);
+extern int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
+ unsigned long type);
#else
-#define f2fs_build_fault_attr(sbi, rate, type) do { } while (0)
+static inline int f2fs_build_fault_attr(struct f2fs_sb_info *sbi,
+ unsigned long rate, unsigned long type)
+{
+ return 0;
+}
#endif
static inline bool is_journalled_quota(struct f2fs_sb_info *sbi)
@@ -4593,9 +4700,11 @@ static inline void f2fs_io_schedule_timeout(long timeout)
io_schedule_timeout(timeout);
}
-static inline void f2fs_handle_page_eio(struct f2fs_sb_info *sbi, pgoff_t ofs,
- enum page_type type)
+static inline void f2fs_handle_page_eio(struct f2fs_sb_info *sbi,
+ struct folio *folio, enum page_type type)
{
+ pgoff_t ofs = folio->index;
+
if (unlikely(f2fs_cp_error(sbi)))
return;
@@ -4613,11 +4722,37 @@ static inline bool f2fs_is_readonly(struct f2fs_sb_info *sbi)
return f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb);
}
+static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi,
+ block_t blkaddr, unsigned int cnt)
+{
+ bool need_submit = false;
+ int i = 0;
+
+ do {
+ struct page *page;
+
+ page = find_get_page(META_MAPPING(sbi), blkaddr + i);
+ if (page) {
+ if (folio_test_writeback(page_folio(page)))
+ need_submit = true;
+ f2fs_put_page(page, 0);
+ }
+ } while (++i < cnt && !need_submit);
+
+ if (need_submit)
+ f2fs_submit_merged_write_cond(sbi, sbi->meta_inode,
+ NULL, 0, DATA);
+
+ truncate_inode_pages_range(META_MAPPING(sbi),
+ F2FS_BLK_TO_BYTES((loff_t)blkaddr),
+ F2FS_BLK_END_BYTES((loff_t)(blkaddr + cnt - 1)));
+}
+
static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi,
- block_t blkaddr)
+ block_t blkaddr, unsigned int len)
{
- invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr);
- f2fs_invalidate_compress_page(sbi, blkaddr);
+ f2fs_truncate_meta_inode_pages(sbi, blkaddr, len);
+ f2fs_invalidate_compress_pages_range(sbi, blkaddr, len);
}
#define EFSBADCRC EBADMSG /* Bad CRC detected */
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index b58ab1157b7e..f92a9fba9991 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -8,7 +8,6 @@
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/stat.h>
-#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/falloc.h>
@@ -39,6 +38,7 @@
static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
+ vm_flags_t flags = vmf->vma->vm_flags;
vm_fault_t ret;
ret = filemap_fault(vmf);
@@ -46,18 +46,18 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
f2fs_update_iostat(F2FS_I_SB(inode), inode,
APP_MAPPED_READ_IO, F2FS_BLKSIZE);
- trace_f2fs_filemap_fault(inode, vmf->pgoff, vmf->vma->vm_flags, ret);
+ trace_f2fs_filemap_fault(inode, vmf->pgoff, flags, ret);
return ret;
}
static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
{
- struct page *page = vmf->page;
+ struct folio *folio = page_folio(vmf->page);
struct inode *inode = file_inode(vmf->vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
- bool need_alloc = true;
+ bool need_alloc = !f2fs_is_pinned_file(inode);
int err = 0;
vm_fault_t ret;
@@ -85,7 +85,7 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (f2fs_compressed_file(inode)) {
- int ret = f2fs_is_compressed_cluster(inode, page->index);
+ int ret = f2fs_is_compressed_cluster(inode, folio->index);
if (ret < 0) {
err = ret;
@@ -105,34 +105,33 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
file_update_time(vmf->vma->vm_file);
filemap_invalidate_lock_shared(inode->i_mapping);
- lock_page(page);
- if (unlikely(page->mapping != inode->i_mapping ||
- page_offset(page) > i_size_read(inode) ||
- !PageUptodate(page))) {
- unlock_page(page);
+ folio_lock(folio);
+ if (unlikely(folio->mapping != inode->i_mapping ||
+ folio_pos(folio) > i_size_read(inode) ||
+ !folio_test_uptodate(folio))) {
+ folio_unlock(folio);
err = -EFAULT;
goto out_sem;
}
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
if (need_alloc) {
/* block allocation */
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_get_block_locked(&dn, page->index);
- }
-
-#ifdef CONFIG_F2FS_FS_COMPRESSION
- if (!need_alloc) {
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+ err = f2fs_get_block_locked(&dn, folio->index);
+ } else {
+ err = f2fs_get_dnode_of_data(&dn, folio->index, LOOKUP_NODE);
f2fs_put_dnode(&dn);
+ if (f2fs_is_pinned_file(inode) &&
+ !__is_valid_data_blkaddr(dn.data_blkaddr))
+ err = -EIO;
}
-#endif
+
if (err) {
- unlock_page(page);
+ folio_unlock(folio);
goto out_sem;
}
- f2fs_wait_on_page_writeback(page, DATA, false, true);
+ f2fs_wait_on_page_writeback(folio_page(folio, 0), DATA, false, true);
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, dn.data_blkaddr);
@@ -140,18 +139,18 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
/*
* check to see if the page is mapped already (no holes)
*/
- if (PageMappedToDisk(page))
+ if (folio_test_mappedtodisk(folio))
goto out_sem;
/* page is wholly or partially inside EOF */
- if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
+ if (((loff_t)(folio->index + 1) << PAGE_SHIFT) >
i_size_read(inode)) {
loff_t offset;
offset = i_size_read(inode) & ~PAGE_MASK;
- zero_user_segment(page, offset, PAGE_SIZE);
+ folio_zero_segment(folio, offset, folio_size(folio));
}
- set_page_dirty(page);
+ folio_mark_dirty(folio);
f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE);
f2fs_update_time(sbi, REQ_TIME);
@@ -163,7 +162,7 @@ out_sem:
out:
ret = vmf_fs_error(err);
- trace_f2fs_vm_page_mkwrite(inode, page->index, vmf->vma->vm_flags, ret);
+ trace_f2fs_vm_page_mkwrite(inode, folio->index, vmf->vma->vm_flags, ret);
return ret;
}
@@ -185,7 +184,7 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
if (!dentry)
return 0;
- *pino = parent_ino(dentry);
+ *pino = d_parent_ino(dentry);
dput(dentry);
return 1;
}
@@ -218,6 +217,9 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
TRANS_DIR_INO))
cp_reason = CP_RECOVER_DIR;
+ else if (f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
+ XATTR_DIR_INO))
+ cp_reason = CP_XATTR_DIR;
return cp_reason;
}
@@ -373,8 +375,7 @@ sync_nodes:
f2fs_remove_ino_entry(sbi, ino, APPEND_INO);
clear_inode_flag(inode, FI_APPEND_WRITE);
flush_out:
- if ((!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) ||
- (atomic && !test_opt(sbi, NOBARRIER) && f2fs_sb_has_blkzoned(sbi)))
+ if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER)
ret = f2fs_issue_flush(sbi, inode->i_ino);
if (!ret) {
f2fs_remove_ino_entry(sbi, ino, UPDATE_INO);
@@ -394,9 +395,20 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
return f2fs_do_sync_file(file, start, end, datasync, false);
}
-static bool __found_offset(struct address_space *mapping, block_t blkaddr,
- pgoff_t index, int whence)
+static bool __found_offset(struct address_space *mapping,
+ struct dnode_of_data *dn, pgoff_t index, int whence)
{
+ block_t blkaddr = f2fs_data_blkaddr(dn);
+ struct inode *inode = mapping->host;
+ bool compressed_cluster = false;
+
+ if (f2fs_compressed_file(inode)) {
+ block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ ALIGN_DOWN(dn->ofs_in_node, F2FS_I(inode)->i_cluster_size));
+
+ compressed_cluster = first_blkaddr == COMPRESS_ADDR;
+ }
+
switch (whence) {
case SEEK_DATA:
if (__is_valid_data_blkaddr(blkaddr))
@@ -404,8 +416,12 @@ static bool __found_offset(struct address_space *mapping, block_t blkaddr,
if (blkaddr == NEW_ADDR &&
xa_get_mark(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY))
return true;
+ if (compressed_cluster)
+ return true;
break;
case SEEK_HOLE:
+ if (compressed_cluster)
+ return false;
if (blkaddr == NULL_ADDR)
return true;
break;
@@ -416,7 +432,7 @@ static bool __found_offset(struct address_space *mapping, block_t blkaddr,
static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
- loff_t maxbytes = inode->i_sb->s_maxbytes;
+ loff_t maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode));
struct dnode_of_data dn;
pgoff_t pgofs, end_offset;
loff_t data_ofs = offset;
@@ -474,7 +490,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
goto fail;
}
- if (__found_offset(file->f_mapping, blkaddr,
+ if (__found_offset(file->f_mapping, &dn,
pgofs, whence)) {
f2fs_put_dnode(&dn);
goto found;
@@ -498,10 +514,7 @@ fail:
static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
- loff_t maxbytes = inode->i_sb->s_maxbytes;
-
- if (f2fs_compressed_file(inode))
- maxbytes = max_file_blocks(inode) << F2FS_BLKSIZE_BITS;
+ loff_t maxbytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode));
switch (whence) {
case SEEK_SET:
@@ -539,6 +552,42 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}
+static int finish_preallocate_blocks(struct inode *inode)
+{
+ int ret;
+
+ inode_lock(inode);
+ if (is_inode_flag_set(inode, FI_OPENED_FILE)) {
+ inode_unlock(inode);
+ return 0;
+ }
+
+ if (!file_should_truncate(inode)) {
+ set_inode_flag(inode, FI_OPENED_FILE);
+ inode_unlock(inode);
+ return 0;
+ }
+
+ f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ filemap_invalidate_lock(inode->i_mapping);
+
+ truncate_setsize(inode, i_size_read(inode));
+ ret = f2fs_truncate(inode);
+
+ filemap_invalidate_unlock(inode->i_mapping);
+ f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+
+ if (!ret)
+ set_inode_flag(inode, FI_OPENED_FILE);
+
+ inode_unlock(inode);
+ if (ret)
+ return ret;
+
+ file_dont_truncate(inode);
+ return 0;
+}
+
static int f2fs_file_open(struct inode *inode, struct file *filp)
{
int err = fscrypt_file_open(inode, filp);
@@ -553,10 +602,14 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
if (err)
return err;
- filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
+ filp->f_mode |= FMODE_NOWAIT;
filp->f_mode |= FMODE_CAN_ODIRECT;
- return dquot_file_open(inode, filp);
+ err = dquot_file_open(inode, filp);
+ if (err)
+ return err;
+
+ return finish_preallocate_blocks(inode);
}
void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -568,8 +621,11 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
int cluster_index = 0, valid_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks);
+ block_t blkstart;
+ int blklen = 0;
addr = get_dnode_addr(dn->inode, dn->node_page) + ofs;
+ blkstart = le32_to_cpu(*addr);
/* Assumption: truncation starts with cluster */
for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) {
@@ -585,24 +641,44 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
}
if (blkaddr == NULL_ADDR)
- continue;
+ goto next;
f2fs_set_data_blkaddr(dn, NULL_ADDR);
if (__is_valid_data_blkaddr(blkaddr)) {
- if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
- DATA_GENERIC_ENHANCE))
- continue;
+ if (time_to_inject(sbi, FAULT_BLKADDR_CONSISTENCE))
+ goto next;
+ if (!f2fs_is_valid_blkaddr_raw(sbi, blkaddr,
+ DATA_GENERIC_ENHANCE))
+ goto next;
if (compressed_cluster)
valid_blocks++;
}
- f2fs_invalidate_blocks(sbi, blkaddr);
+ if (blkstart + blklen == blkaddr) {
+ blklen++;
+ } else {
+ f2fs_invalidate_blocks(sbi, blkstart, blklen);
+ blkstart = blkaddr;
+ blklen = 1;
+ }
if (!released || blkaddr != COMPRESS_ADDR)
nr_free++;
+
+ continue;
+
+next:
+ if (blklen)
+ f2fs_invalidate_blocks(sbi, blkstart, blklen);
+
+ blkstart = le32_to_cpu(*(addr + 1));
+ blklen = 0;
}
+ if (blklen)
+ f2fs_invalidate_blocks(sbi, blkstart, blklen);
+
if (compressed_cluster)
f2fs_i_compr_blocks_update(dn->inode, valid_blocks, false);
@@ -670,6 +746,11 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
trace_f2fs_truncate_blocks_enter(inode, from);
+ if (IS_DEVICE_ALIASING(inode) && from) {
+ err = -EINVAL;
+ goto out_err;
+ }
+
free_from = (pgoff_t)F2FS_BLK_ALIGN(from);
if (free_from >= max_file_blocks(inode))
@@ -684,6 +765,19 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
goto out;
}
+ if (IS_DEVICE_ALIASING(inode)) {
+ struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ];
+ struct extent_info ei = et->largest;
+
+ f2fs_invalidate_blocks(sbi, ei.blk, ei.len);
+
+ dec_valid_block_count(sbi, inode, ei.len);
+ f2fs_update_time(sbi, REQ_TIME);
+
+ f2fs_put_page(ipage, 1);
+ goto out;
+ }
+
if (f2fs_has_inline_data(inode)) {
f2fs_truncate_inline_inode(inode, ipage, from);
f2fs_put_page(ipage, 1);
@@ -719,7 +813,7 @@ free_partial:
/* lastly zero out the first data page */
if (!err)
err = truncate_partial_data_page(inode, from, truncate_page);
-
+out_err:
trace_f2fs_truncate_blocks_exit(inode, err);
return err;
}
@@ -808,6 +902,12 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw)
return true;
if (f2fs_compressed_file(inode))
return true;
+ /*
+ * only force direct read to use buffered IO, for direct write,
+ * it expects inline data conversion before committing IO.
+ */
+ if (f2fs_has_inline_data(inode) && rw == READ)
+ return true;
/* disallow direct IO if any of devices has unaligned blksize */
if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
@@ -816,9 +916,8 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw)
* 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))
+ if (f2fs_sb_has_blkzoned(sbi) && (rw == WRITE) &&
+ !f2fs_is_pinned_file(inode))
return true;
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
return true;
@@ -907,10 +1006,8 @@ static void __setattr_copy(struct mnt_idmap *idmap,
inode_set_ctime_to_ts(inode, attr->ia_ctime);
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
- vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode);
- if (!vfsgid_in_group_p(vfsgid) &&
- !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
+ if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
mode &= ~S_ISGID;
set_acl_inode(inode, mode);
}
@@ -923,6 +1020,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
int err;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode))))
@@ -936,9 +1034,15 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
ATTR_GID | ATTR_TIMES_SET))))
return -EPERM;
- if ((attr->ia_valid & ATTR_SIZE) &&
- !f2fs_is_compress_backend_ready(inode))
- return -EOPNOTSUPP;
+ if ((attr->ia_valid & ATTR_SIZE)) {
+ if (!f2fs_is_compress_backend_ready(inode) ||
+ IS_DEVICE_ALIASING(inode))
+ return -EOPNOTSUPP;
+ if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) &&
+ !IS_ALIGNED(attr->ia_size,
+ F2FS_BLK_TO_BYTES(fi->i_cluster_size)))
+ return -EINVAL;
+ }
err = setattr_prepare(idmap, dentry, attr);
if (err)
@@ -990,7 +1094,14 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
return err;
}
- f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ /*
+ * wait for inflight dio, blocks should be removed after
+ * IO completion.
+ */
+ if (attr->ia_size < old_size)
+ inode_dio_wait(inode);
+
+ f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
truncate_setsize(inode, attr->ia_size);
@@ -1002,14 +1113,14 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
* larger than i_size.
*/
filemap_invalidate_unlock(inode->i_mapping);
- f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
if (err)
return err;
- spin_lock(&F2FS_I(inode)->i_size_lock);
+ spin_lock(&fi->i_size_lock);
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
- F2FS_I(inode)->last_disk_size = i_size_read(inode);
- spin_unlock(&F2FS_I(inode)->i_size_lock);
+ fi->last_disk_size = i_size_read(inode);
+ spin_unlock(&fi->i_size_lock);
}
__setattr_copy(idmap, inode, attr);
@@ -1019,7 +1130,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
if (is_inode_flag_set(inode, FI_ACL_MODE)) {
if (!err)
- inode->i_mode = F2FS_I(inode)->i_acl_mode;
+ inode->i_mode = fi->i_acl_mode;
clear_inode_flag(inode, FI_ACL_MODE);
}
}
@@ -1192,7 +1303,6 @@ next_dnode:
!f2fs_is_valid_blkaddr(sbi, *blkaddr,
DATA_GENERIC_ENHANCE)) {
f2fs_put_dnode(&dn);
- f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
return -EFSCORRUPTED;
}
@@ -1232,7 +1342,7 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
if (ret) {
dec_valid_block_count(sbi, inode, 1);
- f2fs_invalidate_blocks(sbi, *blkaddr);
+ f2fs_invalidate_blocks(sbi, *blkaddr, 1);
} else {
f2fs_update_data_blkaddr(&dn, *blkaddr);
}
@@ -1310,6 +1420,9 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
f2fs_put_page(psrc, 1);
return PTR_ERR(pdst);
}
+
+ f2fs_wait_on_page_writeback(pdst, DATA, true, true);
+
memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE);
set_page_dirty(pdst);
set_page_private_gcing(pdst);
@@ -1478,11 +1591,10 @@ 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;
}
- f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
+ f2fs_invalidate_blocks(sbi, dn->data_blkaddr, 1);
f2fs_set_data_blkaddr(dn, NEW_ADDR);
}
@@ -1662,10 +1774,12 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
}
filemap_invalidate_unlock(mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ if (ret)
+ return ret;
/* write out all moved pages, if possible */
filemap_invalidate_lock(mapping);
- filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
+ ret = filemap_write_and_wait_range(mapping, offset, LLONG_MAX);
truncate_pagecache(inode, offset);
filemap_invalidate_unlock(mapping);
@@ -1720,7 +1834,8 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
map.m_len = sec_blks;
next_alloc:
- if (has_not_enough_free_secs(sbi, 0,
+ if (has_not_enough_free_secs(sbi, 0, f2fs_sb_has_blkzoned(sbi) ?
+ ZONED_PIN_SEC_REQUIRED_COUNT :
GET_SEC_FROM_SEG(sbi, overprovision_segments(sbi)))) {
f2fs_down_write(&sbi->gc_lock);
stat_inc_gc_call_count(sbi, FOREGROUND);
@@ -1731,9 +1846,11 @@ next_alloc:
f2fs_down_write(&sbi->pin_sem);
- f2fs_lock_op(sbi);
- f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false);
- f2fs_unlock_op(sbi);
+ err = f2fs_allocate_pinning_section(sbi);
+ if (err) {
+ f2fs_up_write(&sbi->pin_sem);
+ goto out_err;
+ }
map.m_seg_type = CURSEG_COLD_DATA_PINNED;
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_PRE_DIO);
@@ -1788,7 +1905,7 @@ static long f2fs_fallocate(struct file *file, int mode,
return -EIO;
if (!f2fs_is_checkpoint_ready(F2FS_I_SB(inode)))
return -ENOSPC;
- if (!f2fs_is_compress_backend_ready(inode))
+ if (!f2fs_is_compress_backend_ready(inode) || IS_DEVICE_ALIASING(inode))
return -EOPNOTSUPP;
/* f2fs only support ->fallocate for regular file */
@@ -1799,15 +1916,6 @@ static long f2fs_fallocate(struct file *file, int mode,
(mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
- /*
- * Pinned file should not support partial truncation since the block
- * can be used by applications.
- */
- if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) &&
- (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
- FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)))
- return -EOPNOTSUPP;
-
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
FALLOC_FL_INSERT_RANGE))
@@ -1815,10 +1923,27 @@ static long f2fs_fallocate(struct file *file, int mode,
inode_lock(inode);
+ /*
+ * Pinned file should not support partial truncation since the block
+ * can be used by applications.
+ */
+ if ((f2fs_compressed_file(inode) || f2fs_is_pinned_file(inode)) &&
+ (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE |
+ FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE))) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
ret = file_modified(file);
if (ret)
goto out;
+ /*
+ * wait for inflight dio, blocks should be removed after IO
+ * completion.
+ */
+ inode_dio_wait(inode);
+
if (mode & FALLOC_FL_PUNCH_HOLE) {
if (offset >= inode->i_size)
goto out;
@@ -1920,15 +2045,15 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
if (err)
return err;
- f2fs_down_write(&F2FS_I(inode)->i_sem);
+ f2fs_down_write(&fi->i_sem);
if (!f2fs_may_compress(inode) ||
(S_ISREG(inode->i_mode) &&
F2FS_HAS_BLOCKS(inode))) {
- f2fs_up_write(&F2FS_I(inode)->i_sem);
+ f2fs_up_write(&fi->i_sem);
return -EINVAL;
}
err = set_compress_context(inode);
- f2fs_up_write(&F2FS_I(inode)->i_sem);
+ f2fs_up_write(&fi->i_sem);
if (err)
return err;
@@ -2047,10 +2172,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
struct mnt_idmap *idmap = file_mnt_idmap(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct inode *pinode;
loff_t isize;
int ret;
+ if (!(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
@@ -2066,7 +2193,8 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
inode_lock(inode);
- if (!f2fs_disable_compressed_file(inode)) {
+ if (!f2fs_disable_compressed_file(inode) ||
+ f2fs_is_pinned_file(inode)) {
ret = -EINVAL;
goto out;
}
@@ -2079,6 +2207,7 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
goto out;
f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
+ f2fs_down_write(&fi->i_gc_rwsem[READ]);
/*
* Should wait end_io to count F2FS_WB_CP_DATA correctly by
@@ -2088,37 +2217,33 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
f2fs_warn(sbi, "Unexpected flush for atomic writes: ino=%lu, npages=%u",
inode->i_ino, get_dirty_pages(inode));
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
- if (ret) {
- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- goto out;
- }
+ if (ret)
+ goto out_unlock;
/* Check if the inode already has a COW inode */
if (fi->cow_inode == NULL) {
/* Create a COW inode for atomic write */
- pinode = f2fs_iget(inode->i_sb, fi->i_pino);
- if (IS_ERR(pinode)) {
- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- ret = PTR_ERR(pinode);
- goto out;
- }
+ struct dentry *dentry = file_dentry(filp);
+ struct inode *dir = d_inode(dentry->d_parent);
- ret = f2fs_get_tmpfile(idmap, pinode, &fi->cow_inode);
- iput(pinode);
- if (ret) {
- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- goto out;
- }
+ ret = f2fs_get_tmpfile(idmap, dir, &fi->cow_inode);
+ if (ret)
+ goto out_unlock;
set_inode_flag(fi->cow_inode, FI_COW_FILE);
clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
+
+ /* Set the COW inode's atomic_inode to the atomic inode */
+ F2FS_I(fi->cow_inode)->atomic_inode = inode;
} else {
/* Reuse the already created COW inode */
+ f2fs_bug_on(sbi, get_dirty_pages(fi->cow_inode));
+
+ invalidate_mapping_pages(fi->cow_inode->i_mapping, 0, -1);
+
ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
- if (ret) {
- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- goto out;
- }
+ if (ret)
+ goto out_unlock;
}
f2fs_write_inode(inode, NULL);
@@ -2137,7 +2262,11 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
}
f2fs_i_size_write(fi->cow_inode, isize);
+out_unlock:
+ f2fs_up_write(&fi->i_gc_rwsem[READ]);
f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+ if (ret)
+ goto out;
f2fs_update_time(sbi, REQ_TIME);
fi->atomic_write_task = current;
@@ -2155,6 +2284,9 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
struct mnt_idmap *idmap = file_mnt_idmap(filp);
int ret;
+ if (!(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
@@ -2187,6 +2319,9 @@ static int f2fs_ioc_abort_atomic_write(struct file *filp)
struct mnt_idmap *idmap = file_mnt_idmap(filp);
int ret;
+ if (!(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
if (!inode_owner_or_capable(idmap, inode))
return -EACCES;
@@ -2205,34 +2340,13 @@ static int f2fs_ioc_abort_atomic_write(struct file *filp)
return ret;
}
-static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
+int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
+ bool readonly, bool need_lock)
{
- struct inode *inode = file_inode(filp);
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct super_block *sb = sbi->sb;
- __u32 in;
int ret = 0;
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if (get_user(in, (__u32 __user *)arg))
- return -EFAULT;
-
- if (in != F2FS_GOING_DOWN_FULLSYNC) {
- ret = mnt_want_write_file(filp);
- if (ret) {
- if (ret == -EROFS) {
- ret = 0;
- f2fs_stop_checkpoint(sbi, false,
- STOP_CP_REASON_SHUTDOWN);
- trace_f2fs_shutdown(sbi, in, ret);
- }
- return ret;
- }
- }
-
- switch (in) {
+ switch (flag) {
case F2FS_GOING_DOWN_FULLSYNC:
ret = bdev_freeze(sb->s_bdev);
if (ret)
@@ -2243,8 +2357,11 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
case F2FS_GOING_DOWN_METASYNC:
/* do checkpoint only */
ret = f2fs_sync_fs(sb, 1);
- if (ret)
+ if (ret) {
+ if (ret == -EIO)
+ ret = 0;
goto out;
+ }
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN);
break;
case F2FS_GOING_DOWN_NOSYNC:
@@ -2260,24 +2377,73 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
set_sbi_flag(sbi, SBI_IS_DIRTY);
/* do checkpoint only */
ret = f2fs_sync_fs(sb, 1);
+ if (ret == -EIO)
+ ret = 0;
goto out;
default:
ret = -EINVAL;
goto out;
}
+ if (readonly)
+ goto out;
+
+ /*
+ * grab sb->s_umount to avoid racing w/ remount() and other shutdown
+ * paths.
+ */
+ if (need_lock)
+ down_write(&sbi->sb->s_umount);
+
f2fs_stop_gc_thread(sbi);
f2fs_stop_discard_thread(sbi);
f2fs_drop_discard_cmd(sbi);
clear_opt(sbi, DISCARD);
+ if (need_lock)
+ up_write(&sbi->sb->s_umount);
+
f2fs_update_time(sbi, REQ_TIME);
out:
- if (in != F2FS_GOING_DOWN_FULLSYNC)
- mnt_drop_write_file(filp);
- trace_f2fs_shutdown(sbi, in, ret);
+ trace_f2fs_shutdown(sbi, flag, ret);
+
+ return ret;
+}
+
+static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ __u32 in;
+ int ret;
+ bool need_drop = false, readonly = false;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(in, (__u32 __user *)arg))
+ return -EFAULT;
+
+ if (in != F2FS_GOING_DOWN_FULLSYNC) {
+ ret = mnt_want_write_file(filp);
+ if (ret) {
+ if (ret != -EROFS)
+ return ret;
+
+ /* fallback to nosync shutdown for readonly fs */
+ in = F2FS_GOING_DOWN_NOSYNC;
+ readonly = true;
+ } else {
+ need_drop = true;
+ }
+ }
+
+ ret = f2fs_do_shutdown(sbi, in, readonly, true);
+
+ if (need_drop)
+ mnt_drop_write_file(filp);
return ret;
}
@@ -2330,13 +2496,14 @@ static bool uuid_is_nonzero(__u8 u[16])
static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
+ int ret;
if (!f2fs_sb_has_encrypt(F2FS_I_SB(inode)))
return -EOPNOTSUPP;
+ ret = fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
-
- return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
+ return ret;
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
@@ -2578,20 +2745,21 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
.m_may_create = false };
struct extent_info ei = {};
pgoff_t pg_start, pg_end, next_pgofs;
- unsigned int blk_per_seg = sbi->blocks_per_seg;
unsigned int total = 0, sec_num;
block_t blk_end = 0;
bool fragmented = false;
int err;
- pg_start = range->start >> PAGE_SHIFT;
- pg_end = (range->start + range->len) >> PAGE_SHIFT;
-
f2fs_balance_fs(sbi, true);
inode_lock(inode);
+ pg_start = range->start >> PAGE_SHIFT;
+ pg_end = min_t(pgoff_t,
+ (range->start + range->len) >> PAGE_SHIFT,
+ DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE));
- if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+ if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) ||
+ f2fs_is_atomic_file(inode)) {
err = -EINVAL;
goto unlock_out;
}
@@ -2604,8 +2772,9 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
}
/* writeback all dirty pages in the range */
- err = filemap_write_and_wait_range(inode->i_mapping, range->start,
- range->start + range->len - 1);
+ err = filemap_write_and_wait_range(inode->i_mapping,
+ pg_start << PAGE_SHIFT,
+ (pg_end << PAGE_SHIFT) - 1);
if (err)
goto out;
@@ -2614,7 +2783,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
* block addresses are continuous.
*/
if (f2fs_lookup_read_extent_cache(inode, pg_start, &ei)) {
- if (ei.fofs + ei.len >= pg_end)
+ if ((pgoff_t)ei.fofs + ei.len >= pg_end)
goto out;
}
@@ -2687,7 +2856,8 @@ do_map:
set_inode_flag(inode, FI_SKIP_WRITES);
idx = map.m_lblk;
- while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
+ while (idx < map.m_lblk + map.m_len &&
+ cnt < BLKS_PER_SEG(sbi)) {
struct page *page;
page = f2fs_get_lock_data_page(inode, idx, true);
@@ -2696,6 +2866,8 @@ do_map:
goto clear_out;
}
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
+
set_page_dirty(page);
set_page_private_gcing(page);
f2fs_put_page(page, 1);
@@ -2707,7 +2879,7 @@ do_map:
map.m_lblk = idx;
check:
- if (map.m_lblk < pg_end && cnt < blk_per_seg)
+ if (map.m_lblk < pg_end && cnt < BLKS_PER_SEG(sbi))
goto do_map;
clear_inode_flag(inode, FI_SKIP_WRITES);
@@ -2737,7 +2909,7 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
+ if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (f2fs_readonly(sbi->sb))
@@ -2762,7 +2934,8 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
err = f2fs_defragment_range(sbi, filp, &range);
mnt_drop_write_file(filp);
- f2fs_update_time(sbi, REQ_TIME);
+ if (range.len)
+ f2fs_update_time(sbi, REQ_TIME);
if (err < 0)
return err;
@@ -2813,11 +2986,17 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
goto out;
}
- if (f2fs_compressed_file(src) || f2fs_compressed_file(dst)) {
+ if (f2fs_compressed_file(src) || f2fs_compressed_file(dst) ||
+ f2fs_is_pinned_file(src) || f2fs_is_pinned_file(dst)) {
ret = -EOPNOTSUPP;
goto out_unlock;
}
+ if (f2fs_is_atomic_file(src) || f2fs_is_atomic_file(dst)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
ret = -EINVAL;
if (pos_in + len > src->i_size || pos_in + len < pos_in)
goto out_unlock;
@@ -2869,9 +3048,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
}
f2fs_lock_op(sbi);
- ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
- pos_out >> F2FS_BLKSIZE_BITS,
- len >> F2FS_BLKSIZE_BITS, false);
+ ret = __exchange_data_block(src, dst, F2FS_BYTES_TO_BLK(pos_in),
+ F2FS_BYTES_TO_BLK(pos_out),
+ F2FS_BYTES_TO_BLK(len), false);
if (!ret) {
if (dst_max_i_size)
@@ -2907,32 +3086,27 @@ out:
static int __f2fs_ioc_move_range(struct file *filp,
struct f2fs_move_range *range)
{
- struct fd dst;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
- dst = fdget(range->dst_fd);
- if (!dst.file)
+ CLASS(fd, dst)(range->dst_fd);
+ if (fd_empty(dst))
return -EBADF;
- if (!(dst.file->f_mode & FMODE_WRITE)) {
- err = -EBADF;
- goto err_out;
- }
+ if (!(fd_file(dst)->f_mode & FMODE_WRITE))
+ return -EBADF;
err = mnt_want_write_file(filp);
if (err)
- goto err_out;
+ return err;
- err = f2fs_move_file_range(filp, range->pos_in, dst.file,
+ err = f2fs_move_file_range(filp, range->pos_in, fd_file(dst),
range->pos_out, range->len);
mnt_drop_write_file(filp);
-err_out:
- fdput(dst);
return err;
}
@@ -2976,8 +3150,8 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num ||
__is_large_section(sbi)) {
- f2fs_warn(sbi, "Can't flush %u in %d for segs_per_sec %u != 1",
- range.dev_num, sbi->s_ndevs, sbi->segs_per_sec);
+ f2fs_warn(sbi, "Can't flush %u in %d for SEGS_PER_SEC %u != 1",
+ range.dev_num, sbi->s_ndevs, SEGS_PER_SEC(sbi));
return -EINVAL;
}
@@ -3165,24 +3339,27 @@ int f2fs_pin_file_control(struct inode *inode, bool inc)
struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- /* Use i_gc_failures for normal file as a risk signal. */
- if (inc)
- f2fs_i_gc_failures_write(inode,
- fi->i_gc_failures[GC_FAILURE_PIN] + 1);
+ if (IS_DEVICE_ALIASING(inode))
+ return -EINVAL;
- if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) {
+ if (fi->i_gc_failures >= sbi->gc_pin_file_threshold) {
f2fs_warn(sbi, "%s: Enable GC = ino %lx after %x GC trials",
- __func__, inode->i_ino,
- fi->i_gc_failures[GC_FAILURE_PIN]);
+ __func__, inode->i_ino, fi->i_gc_failures);
clear_inode_flag(inode, FI_PIN_FILE);
return -EAGAIN;
}
+
+ /* Use i_gc_failures for normal file as a risk signal. */
+ if (inc)
+ f2fs_i_gc_failures_write(inode, fi->i_gc_failures + 1);
+
return 0;
}
static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
__u32 pin;
int ret = 0;
@@ -3192,22 +3369,39 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
if (!S_ISREG(inode->i_mode))
return -EINVAL;
- if (f2fs_readonly(F2FS_I_SB(inode)->sb))
+ if (f2fs_readonly(sbi->sb))
return -EROFS;
+ if (!pin && IS_DEVICE_ALIASING(inode))
+ return -EOPNOTSUPP;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
+ if (f2fs_is_atomic_file(inode)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (!pin) {
clear_inode_flag(inode, FI_PIN_FILE);
f2fs_i_gc_failures_write(inode, 0);
goto done;
+ } else if (f2fs_is_pinned_file(inode)) {
+ goto done;
}
- if (f2fs_should_update_outplace(inode, NULL)) {
+ if (F2FS_HAS_BLOCKS(inode)) {
+ ret = -EFBIG;
+ goto out;
+ }
+
+ /* Let's allow file pinning on zoned device. */
+ if (!f2fs_sb_has_blkzoned(sbi) &&
+ f2fs_should_update_outplace(inode, NULL)) {
ret = -EINVAL;
goto out;
}
@@ -3227,9 +3421,9 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
}
set_inode_flag(inode, FI_PIN_FILE);
- ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
+ ret = F2FS_I(inode)->i_gc_failures;
done:
- f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+ f2fs_update_time(sbi, REQ_TIME);
out:
inode_unlock(inode);
mnt_drop_write_file(filp);
@@ -3242,10 +3436,16 @@ static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg)
__u32 pin = 0;
if (is_inode_flag_set(inode, FI_PIN_FILE))
- pin = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN];
+ pin = F2FS_I(inode)->i_gc_failures;
return put_user(pin, (u32 __user *)arg);
}
+static int f2fs_ioc_get_dev_alias_file(struct file *filp, unsigned long arg)
+{
+ return put_user(IS_DEVICE_ALIASING(file_inode(filp)) ? 1 : 0,
+ (u32 __user *)arg);
+}
+
int f2fs_precache_extents(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -3438,10 +3638,8 @@ 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))) {
- f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+ DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
- }
}
while (count) {
@@ -3481,6 +3679,7 @@ next:
static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t page_idx = 0, last_idx;
unsigned int released_blocks = 0;
@@ -3490,9 +3689,6 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
if (!f2fs_sb_has_compression(sbi))
return -EOPNOTSUPP;
- if (!f2fs_compressed_file(inode))
- return -EINVAL;
-
if (f2fs_readonly(sbi->sb))
return -EROFS;
@@ -3511,7 +3707,8 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
goto out;
}
- if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+ if (!f2fs_compressed_file(inode) ||
+ is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
ret = -EINVAL;
goto out;
}
@@ -3520,7 +3717,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
if (ret)
goto out;
- if (!atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
+ if (!atomic_read(&fi->i_compr_blocks)) {
ret = -EPERM;
goto out;
}
@@ -3529,7 +3726,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
inode_set_ctime_current(inode);
f2fs_mark_inode_dirty_sync(inode, true);
- f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
@@ -3538,9 +3735,12 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
struct dnode_of_data dn;
pgoff_t end_offset, count;
+ f2fs_lock_op(sbi);
+
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
if (ret) {
+ f2fs_unlock_op(sbi);
if (ret == -ENOENT) {
page_idx = f2fs_get_next_page_offset(&dn,
page_idx);
@@ -3552,12 +3752,14 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
- count = round_up(count, F2FS_I(inode)->i_cluster_size);
+ count = round_up(count, fi->i_cluster_size);
ret = release_compress_blocks(&dn, count);
f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+
if (ret < 0)
break;
@@ -3566,8 +3768,10 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
}
filemap_invalidate_unlock(inode->i_mapping);
- f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
out:
+ if (released_blocks)
+ f2fs_update_time(sbi, REQ_TIME);
inode_unlock(inode);
mnt_drop_write_file(filp);
@@ -3575,23 +3779,23 @@ out:
if (ret >= 0) {
ret = put_user(released_blocks, (u64 __user *)arg);
} else if (released_blocks &&
- atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
+ atomic_read(&fi->i_compr_blocks)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
"iblocks=%llu, released=%u, compr_blocks=%u, "
"run fsck to fix.",
__func__, inode->i_ino, inode->i_blocks,
released_blocks,
- atomic_read(&F2FS_I(inode)->i_compr_blocks));
+ atomic_read(&fi->i_compr_blocks));
}
return ret;
}
-static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
+static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count,
+ unsigned int *reserved_blocks)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- unsigned int reserved_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
block_t blkaddr;
int i;
@@ -3603,56 +3807,75 @@ 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))) {
- f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+ DATA_GENERIC_ENHANCE)))
return -EFSCORRUPTED;
- }
}
while (count) {
int compr_blocks = 0;
- blkcnt_t reserved;
+ blkcnt_t reserved = 0;
+ blkcnt_t to_reserved;
int ret;
- for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
- blkaddr = f2fs_data_blkaddr(dn);
+ for (i = 0; i < cluster_size; i++) {
+ blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ dn->ofs_in_node + i);
if (i == 0) {
- if (blkaddr == COMPRESS_ADDR)
- continue;
- dn->ofs_in_node += cluster_size;
- goto next;
+ if (blkaddr != COMPRESS_ADDR) {
+ dn->ofs_in_node += cluster_size;
+ goto next;
+ }
+ continue;
}
+ /*
+ * compressed cluster was not released due to it
+ * fails in release_compress_blocks(), so NEW_ADDR
+ * is a possible case.
+ */
+ if (blkaddr == NEW_ADDR) {
+ reserved++;
+ continue;
+ }
if (__is_valid_data_blkaddr(blkaddr)) {
compr_blocks++;
continue;
}
+ }
- f2fs_set_data_blkaddr(dn, NEW_ADDR);
+ to_reserved = cluster_size - compr_blocks - reserved;
+
+ /* for the case all blocks in cluster were reserved */
+ if (reserved && to_reserved == 1) {
+ dn->ofs_in_node += cluster_size;
+ goto next;
}
- reserved = cluster_size - compr_blocks;
- ret = inc_valid_block_count(sbi, dn->inode, &reserved);
- if (ret)
+ ret = inc_valid_block_count(sbi, dn->inode,
+ &to_reserved, false);
+ if (unlikely(ret))
return ret;
- if (reserved != cluster_size - compr_blocks)
- return -ENOSPC;
+ for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
+ if (f2fs_data_blkaddr(dn) == NULL_ADDR)
+ f2fs_set_data_blkaddr(dn, NEW_ADDR);
+ }
f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true);
- reserved_blocks += reserved;
+ *reserved_blocks += to_reserved;
next:
count -= cluster_size;
}
- return reserved_blocks;
+ return 0;
}
static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
pgoff_t page_idx = 0, last_idx;
unsigned int reserved_blocks = 0;
@@ -3661,9 +3884,6 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
if (!f2fs_sb_has_compression(sbi))
return -EOPNOTSUPP;
- if (!f2fs_compressed_file(inode))
- return -EINVAL;
-
if (f2fs_readonly(sbi->sb))
return -EROFS;
@@ -3671,19 +3891,20 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
if (ret)
return ret;
- if (atomic_read(&F2FS_I(inode)->i_compr_blocks))
- goto out;
-
f2fs_balance_fs(sbi, true);
inode_lock(inode);
- if (!is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+ if (!f2fs_compressed_file(inode) ||
+ !is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
ret = -EINVAL;
goto unlock_inode;
}
- f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ if (atomic_read(&fi->i_compr_blocks))
+ goto unlock_inode;
+
+ f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
@@ -3692,9 +3913,12 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
struct dnode_of_data dn;
pgoff_t end_offset, count;
+ f2fs_lock_op(sbi);
+
set_new_dnode(&dn, inode, NULL, NULL, 0);
ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
if (ret) {
+ f2fs_unlock_op(sbi);
if (ret == -ENOENT) {
page_idx = f2fs_get_next_page_offset(&dn,
page_idx);
@@ -3706,43 +3930,45 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
- count = round_up(count, F2FS_I(inode)->i_cluster_size);
+ count = round_up(count, fi->i_cluster_size);
- ret = reserve_compress_blocks(&dn, count);
+ ret = reserve_compress_blocks(&dn, count, &reserved_blocks);
f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+
if (ret < 0)
break;
page_idx += count;
- reserved_blocks += ret;
}
filemap_invalidate_unlock(inode->i_mapping);
- f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
- if (ret >= 0) {
+ if (!ret) {
clear_inode_flag(inode, FI_COMPRESS_RELEASED);
inode_set_ctime_current(inode);
f2fs_mark_inode_dirty_sync(inode, true);
}
unlock_inode:
+ if (reserved_blocks)
+ f2fs_update_time(sbi, REQ_TIME);
inode_unlock(inode);
-out:
mnt_drop_write_file(filp);
- if (ret >= 0) {
+ if (!ret) {
ret = put_user(reserved_blocks, (u64 __user *)arg);
} else if (reserved_blocks &&
- atomic_read(&F2FS_I(inode)->i_compr_blocks)) {
+ atomic_read(&fi->i_compr_blocks)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
+ f2fs_warn(sbi, "%s: partial blocks were reserved i_ino=%lx "
"iblocks=%llu, reserved=%u, compr_blocks=%u, "
"run fsck to fix.",
__func__, inode->i_ino, inode->i_blocks,
reserved_blocks,
- atomic_read(&F2FS_I(inode)->i_compr_blocks));
+ atomic_read(&fi->i_compr_blocks));
}
return ret;
@@ -3805,7 +4031,9 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi)))
return -EOPNOTSUPP;
- file_start_write(filp);
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
inode_lock(inode);
if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) ||
@@ -3877,8 +4105,6 @@ 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;
}
@@ -3927,12 +4153,13 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
if (len)
ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
prev_block, len, range.flags);
+ f2fs_update_time(sbi, REQ_TIME);
out:
filemap_invalidate_unlock(mapping);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
err:
inode_unlock(inode);
- file_end_write(filp);
+ mnt_drop_write_file(filp);
return ret;
}
@@ -3967,6 +4194,7 @@ static int f2fs_ioc_get_compress_option(struct file *filp, unsigned long arg)
static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_comp_option option;
int ret = 0;
@@ -3981,16 +4209,22 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
sizeof(option)))
return -EFAULT;
- if (!f2fs_compressed_file(inode) ||
- option.log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
- option.log_cluster_size > MAX_COMPRESS_LOG_SIZE ||
- option.algorithm >= COMPRESS_MAX)
+ if (option.log_cluster_size < MIN_COMPRESS_LOG_SIZE ||
+ option.log_cluster_size > MAX_COMPRESS_LOG_SIZE ||
+ option.algorithm >= COMPRESS_MAX)
return -EINVAL;
- file_start_write(filp);
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
inode_lock(inode);
f2fs_down_write(&F2FS_I(inode)->i_sem);
+ if (!f2fs_compressed_file(inode)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) {
ret = -EBUSY;
goto out;
@@ -4001,27 +4235,27 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg)
goto out;
}
- F2FS_I(inode)->i_compress_algorithm = option.algorithm;
- F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size;
- F2FS_I(inode)->i_cluster_size = BIT(option.log_cluster_size);
+ fi->i_compress_algorithm = option.algorithm;
+ fi->i_log_cluster_size = option.log_cluster_size;
+ fi->i_cluster_size = BIT(option.log_cluster_size);
/* Set default level */
- if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD)
- F2FS_I(inode)->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL;
+ if (fi->i_compress_algorithm == COMPRESS_ZSTD)
+ fi->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL;
else
- F2FS_I(inode)->i_compress_level = 0;
+ fi->i_compress_level = 0;
/* Adjust mount option level */
if (option.algorithm == F2FS_OPTION(sbi).compress_algorithm &&
F2FS_OPTION(sbi).compress_level)
- F2FS_I(inode)->i_compress_level = F2FS_OPTION(sbi).compress_level;
+ fi->i_compress_level = F2FS_OPTION(sbi).compress_level;
f2fs_mark_inode_dirty_sync(inode, true);
if (!f2fs_is_compress_backend_ready(inode))
f2fs_warn(sbi, "compression algorithm is successfully set, "
"but current kernel doesn't support this algorithm.");
out:
- f2fs_up_write(&F2FS_I(inode)->i_sem);
+ f2fs_up_write(&fi->i_sem);
inode_unlock(inode);
- file_end_write(filp);
+ mnt_drop_write_file(filp);
return ret;
}
@@ -4051,6 +4285,8 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len)
/* It will never fail, when page has pinned above */
f2fs_bug_on(F2FS_I_SB(inode), !page);
+ f2fs_wait_on_page_writeback(page, DATA, true, true);
+
set_page_dirty(page);
set_page_private_gcing(page);
f2fs_put_page(page, 1);
@@ -4065,10 +4301,8 @@ static int f2fs_ioc_decompress_file(struct file *filp)
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
- pgoff_t page_idx = 0, last_idx;
- unsigned int blk_per_seg = sbi->blocks_per_seg;
- int cluster_size = fi->i_cluster_size;
- int count, ret;
+ pgoff_t page_idx = 0, last_idx, cluster_idx;
+ int ret;
if (!f2fs_sb_has_compression(sbi) ||
F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
@@ -4077,12 +4311,11 @@ static int f2fs_ioc_decompress_file(struct file *filp)
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
- if (!f2fs_compressed_file(inode))
- return -EINVAL;
-
f2fs_balance_fs(sbi, true);
- file_start_write(filp);
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
inode_lock(inode);
if (!f2fs_is_compress_backend_ready(inode)) {
@@ -4090,7 +4323,8 @@ static int f2fs_ioc_decompress_file(struct file *filp)
goto out;
}
- if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+ if (!f2fs_compressed_file(inode) ||
+ is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
ret = -EINVAL;
goto out;
}
@@ -4103,22 +4337,24 @@ static int f2fs_ioc_decompress_file(struct file *filp)
goto out;
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+ last_idx >>= fi->i_log_cluster_size;
- count = last_idx - page_idx;
- while (count && count >= cluster_size) {
- ret = redirty_blocks(inode, page_idx, cluster_size);
+ for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) {
+ page_idx = cluster_idx << fi->i_log_cluster_size;
+
+ if (!f2fs_is_compressed_cluster(inode, page_idx))
+ continue;
+
+ ret = redirty_blocks(inode, page_idx, fi->i_cluster_size);
if (ret < 0)
break;
- if (get_dirty_pages(inode) >= blk_per_seg) {
+ if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) {
ret = filemap_fdatawrite(inode->i_mapping);
if (ret < 0)
break;
}
- count -= cluster_size;
- page_idx += cluster_size;
-
cond_resched();
if (fatal_signal_pending(current)) {
ret = -EINTR;
@@ -4133,9 +4369,10 @@ static int f2fs_ioc_decompress_file(struct file *filp)
if (ret)
f2fs_warn(sbi, "%s: The file might be partially decompressed (errno=%d). Please delete the file.",
__func__, ret);
+ f2fs_update_time(sbi, REQ_TIME);
out:
inode_unlock(inode);
- file_end_write(filp);
+ mnt_drop_write_file(filp);
return ret;
}
@@ -4144,10 +4381,9 @@ static int f2fs_ioc_compress_file(struct file *filp)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- pgoff_t page_idx = 0, last_idx;
- unsigned int blk_per_seg = sbi->blocks_per_seg;
- int cluster_size = F2FS_I(inode)->i_cluster_size;
- int count, ret;
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ pgoff_t page_idx = 0, last_idx, cluster_idx;
+ int ret;
if (!f2fs_sb_has_compression(sbi) ||
F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
@@ -4156,12 +4392,11 @@ static int f2fs_ioc_compress_file(struct file *filp)
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
- if (!f2fs_compressed_file(inode))
- return -EINVAL;
-
f2fs_balance_fs(sbi, true);
- file_start_write(filp);
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
inode_lock(inode);
if (!f2fs_is_compress_backend_ready(inode)) {
@@ -4169,7 +4404,8 @@ static int f2fs_ioc_compress_file(struct file *filp)
goto out;
}
- if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
+ if (!f2fs_compressed_file(inode) ||
+ is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
ret = -EINVAL;
goto out;
}
@@ -4181,22 +4417,24 @@ static int f2fs_ioc_compress_file(struct file *filp)
set_inode_flag(inode, FI_ENABLE_COMPRESS);
last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+ last_idx >>= fi->i_log_cluster_size;
+
+ for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) {
+ page_idx = cluster_idx << fi->i_log_cluster_size;
+
+ if (f2fs_is_sparse_cluster(inode, page_idx))
+ continue;
- count = last_idx - page_idx;
- while (count && count >= cluster_size) {
- ret = redirty_blocks(inode, page_idx, cluster_size);
+ ret = redirty_blocks(inode, page_idx, fi->i_cluster_size);
if (ret < 0)
break;
- if (get_dirty_pages(inode) >= blk_per_seg) {
+ if (get_dirty_pages(inode) >= BLKS_PER_SEG(sbi)) {
ret = filemap_fdatawrite(inode->i_mapping);
if (ret < 0)
break;
}
- count -= cluster_size;
- page_idx += cluster_size;
-
cond_resched();
if (fatal_signal_pending(current)) {
ret = -EINTR;
@@ -4213,9 +4451,10 @@ static int f2fs_ioc_compress_file(struct file *filp)
if (ret)
f2fs_warn(sbi, "%s: The file might be partially compressed (errno=%d). Please delete the file.",
__func__, ret);
+ f2fs_update_time(sbi, REQ_TIME);
out:
inode_unlock(inode);
- file_end_write(filp);
+ mnt_drop_write_file(filp);
return ret;
}
@@ -4306,6 +4545,8 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_decompress_file(filp);
case F2FS_IOC_COMPRESS_FILE:
return f2fs_ioc_compress_file(filp);
+ case F2FS_IOC_GET_DEV_ALIAS_FILE:
+ return f2fs_ioc_get_dev_alias_file(filp, arg);
default:
return -ENOTTY;
}
@@ -4396,6 +4637,13 @@ static ssize_t f2fs_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
f2fs_down_read(&fi->i_gc_rwsem[READ]);
}
+ /* dio is not compatible w/ atomic file */
+ if (f2fs_is_atomic_file(inode)) {
+ f2fs_up_read(&fi->i_gc_rwsem[READ]);
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
/*
* We have to use __iomap_dio_rw() and iomap_dio_complete() instead of
* the higher-level function iomap_dio_rw() in order to ensure that the
@@ -4455,6 +4703,11 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos,
iov_iter_count(to), READ);
+ /* In LFS mode, if there is inflight dio, wait for its completion */
+ if (f2fs_lfs_mode(F2FS_I_SB(inode)) &&
+ get_pages(F2FS_I_SB(inode), F2FS_DIO_WRITE))
+ inode_dio_wait(inode);
+
if (f2fs_should_use_dio(inode, iocb, to)) {
ret = f2fs_dio_read_iter(iocb, to);
} else {
@@ -4569,9 +4822,11 @@ static int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *iter,
else
return 0;
- map.m_may_create = true;
+ if (!IS_DEVICE_ALIASING(inode))
+ map.m_may_create = true;
if (dio) {
- map.m_seg_type = f2fs_rw_hint_to_seg_type(inode->i_write_hint);
+ map.m_seg_type = f2fs_rw_hint_to_seg_type(sbi,
+ inode->i_write_hint);
flag = F2FS_GET_BLOCK_PRE_DIO;
} else {
map.m_seg_type = NO_CHECK_TYPE;
@@ -4619,8 +4874,21 @@ static int f2fs_dio_write_end_io(struct kiocb *iocb, ssize_t size, int error,
return 0;
}
+static void f2fs_dio_write_submit_io(const struct iomap_iter *iter,
+ struct bio *bio, loff_t file_offset)
+{
+ struct inode *inode = iter->inode;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ enum log_type type = f2fs_rw_hint_to_seg_type(sbi, inode->i_write_hint);
+ enum temp_type temp = f2fs_get_segment_temp(sbi, type);
+
+ bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, DATA, temp);
+ submit_bio(bio);
+}
+
static const struct iomap_dio_ops f2fs_iomap_dio_write_ops = {
- .end_io = f2fs_dio_write_end_io,
+ .end_io = f2fs_dio_write_end_io,
+ .submit_io = f2fs_dio_write_submit_io,
};
static void f2fs_flush_buffered_write(struct address_space *mapping,
@@ -4757,6 +5025,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
bool dio;
bool may_need_sync = true;
int preallocated;
+ const loff_t pos = iocb->ki_pos;
+ const ssize_t count = iov_iter_count(from);
ssize_t ret;
if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) {
@@ -4778,6 +5048,12 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
inode_lock(inode);
}
+ if (f2fs_is_pinned_file(inode) &&
+ !f2fs_overwrite_io(inode, pos, count)) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
ret = f2fs_write_checks(iocb, from);
if (ret <= 0)
goto out_unlock;
@@ -4785,6 +5061,12 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
/* Determine whether we will do a direct write or a buffered write. */
dio = f2fs_should_use_dio(inode, iocb, from);
+ /* dio is not compatible w/ atomic write */
+ if (dio && f2fs_is_atomic_file(inode)) {
+ ret = -EOPNOTSUPP;
+ goto out_unlock;
+ }
+
/* Possibly preallocate the blocks for the write. */
target_size = iocb->ki_pos + iov_iter_count(from);
preallocated = f2fs_preallocate_blocks(iocb, from, dio);
@@ -4978,6 +5260,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_SET_COMPRESS_OPTION:
case F2FS_IOC_DECOMPRESS_FILE:
case F2FS_IOC_COMPRESS_FILE:
+ case F2FS_IOC_GET_DEV_ALIAS_FILE:
break;
default:
return -ENOIOCTLCMD;
@@ -5004,4 +5287,5 @@ const struct file_operations f2fs_file_operations = {
.splice_read = f2fs_file_splice_read,
.splice_write = iter_file_splice_write,
.fadvise = f2fs_file_fadvise,
+ .fop_flags = FOP_BUFFER_RASYNC,
};
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index a079eebfb080..faf9fa1c804d 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -81,6 +81,8 @@ static int gc_thread_func(void *data)
continue;
}
+ gc_control.one_time = false;
+
/*
* [GC triggering condition]
* 0. GC is not conducted currently.
@@ -116,15 +118,30 @@ static int gc_thread_func(void *data)
goto next;
}
- if (has_enough_invalid_blocks(sbi))
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ if (has_enough_free_blocks(sbi,
+ gc_th->no_zoned_gc_percent)) {
+ wait_ms = gc_th->no_gc_sleep_time;
+ f2fs_up_write(&sbi->gc_lock);
+ goto next;
+ }
+ if (wait_ms == gc_th->no_gc_sleep_time)
+ wait_ms = gc_th->max_sleep_time;
+ }
+
+ if (need_to_boost_gc(sbi)) {
decrease_sleep_time(gc_th, &wait_ms);
- else
+ if (f2fs_sb_has_blkzoned(sbi))
+ gc_control.one_time = true;
+ } else {
increase_sleep_time(gc_th, &wait_ms);
+ }
do_gc:
stat_inc_gc_call_count(sbi, foreground ?
FOREGROUND : BACKGROUND);
- sync_mode = F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC;
+ sync_mode = (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC) ||
+ gc_control.one_time;
/* foreground GC was been triggered via f2fs_balance_fs() */
if (foreground)
@@ -179,9 +196,21 @@ int f2fs_start_gc_thread(struct f2fs_sb_info *sbi)
return -ENOMEM;
gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME;
- gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
- gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
- gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
+ gc_th->valid_thresh_ratio = DEF_GC_THREAD_VALID_THRESH_RATIO;
+
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME_ZONED;
+ gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME_ZONED;
+ gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME_ZONED;
+ gc_th->no_zoned_gc_percent = LIMIT_NO_ZONED_GC;
+ gc_th->boost_zoned_gc_percent = LIMIT_BOOST_ZONED_GC;
+ } else {
+ gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
+ gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
+ gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
+ gc_th->no_zoned_gc_percent = 0;
+ gc_th->boost_zoned_gc_percent = 0;
+ }
gc_th->gc_wake = false;
@@ -228,6 +257,8 @@ static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
switch (sbi->gc_mode) {
case GC_IDLE_CB:
+ case GC_URGENT_LOW:
+ case GC_URGENT_MID:
gc_mode = GC_CB;
break;
case GC_IDLE_GREEDY:
@@ -259,7 +290,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
p->ofs_unit = 1;
} else {
p->gc_mode = select_gc_type(sbi, gc_type);
- p->ofs_unit = sbi->segs_per_sec;
+ p->ofs_unit = SEGS_PER_SEC(sbi);
if (__is_large_section(sbi)) {
p->dirty_bitmap = dirty_i->dirty_secmap;
p->max_search = count_bits(p->dirty_bitmap,
@@ -280,11 +311,11 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
p->max_search > sbi->max_victim_search)
p->max_search = sbi->max_victim_search;
- /* let's select beginning hot/small space first in no_heap mode*/
+ /* let's select beginning hot/small space first. */
if (f2fs_need_rand_seg(sbi))
- p->offset = get_random_u32_below(MAIN_SECS(sbi) * sbi->segs_per_sec);
- else if (test_opt(sbi, NOHEAP) &&
- (type == CURSEG_HOT_DATA || IS_NODESEG(type)))
+ p->offset = get_random_u32_below(MAIN_SECS(sbi) *
+ SEGS_PER_SEC(sbi));
+ else if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
p->offset = 0;
else
p->offset = SIT_I(sbi)->last_victim[p->gc_mode];
@@ -295,13 +326,13 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
{
/* SSR allocates in a segment unit */
if (p->alloc_mode == SSR)
- return sbi->blocks_per_seg;
+ return BLKS_PER_SEG(sbi);
else if (p->alloc_mode == AT_SSR)
return UINT_MAX;
/* LFS */
if (p->gc_mode == GC_GREEDY)
- return 2 * sbi->blocks_per_seg * p->ofs_unit;
+ return SEGS_TO_BLKS(sbi, 2 * p->ofs_unit);
else if (p->gc_mode == GC_CB)
return UINT_MAX;
else if (p->gc_mode == GC_AT)
@@ -332,23 +363,18 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
- unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
unsigned long long mtime = 0;
unsigned int vblocks;
unsigned char age = 0;
unsigned char u;
- unsigned int i;
- unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi, segno);
+ unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi);
- for (i = 0; i < usable_segs_per_sec; i++)
- mtime += get_seg_entry(sbi, start + i)->mtime;
+ mtime = f2fs_get_section_mtime(sbi, segno);
+ f2fs_bug_on(sbi, mtime == INVALID_MTIME);
vblocks = get_valid_blocks(sbi, segno, true);
-
- mtime = div_u64(mtime, usable_segs_per_sec);
vblocks = div_u64(vblocks, usable_segs_per_sec);
- u = (vblocks * 100) >> sbi->log_blocks_per_seg;
+ u = BLKS_TO_SEGS(sbi, vblocks * 100);
/* Handle if the system time has changed by the user */
if (mtime < sit_i->min_mtime)
@@ -368,6 +394,11 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
if (p->alloc_mode == SSR)
return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+ if (p->one_time_gc && (get_valid_blocks(sbi, segno, true) >=
+ CAP_BLKS_PER_SEC(sbi) * sbi->gc_thread->valid_thresh_ratio /
+ 100))
+ return UINT_MAX;
+
/* alloc_mode == LFS */
if (p->gc_mode == GC_GREEDY)
return get_valid_blocks(sbi, segno, true);
@@ -485,10 +516,7 @@ static void add_victim_entry(struct f2fs_sb_info *sbi,
struct victim_sel_policy *p, unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
- unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
unsigned long long mtime = 0;
- unsigned int i;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
if (p->gc_mode == GC_AT &&
@@ -496,9 +524,8 @@ static void add_victim_entry(struct f2fs_sb_info *sbi,
return;
}
- for (i = 0; i < sbi->segs_per_sec; i++)
- mtime += get_seg_entry(sbi, start + i)->mtime;
- mtime = div_u64(mtime, sbi->segs_per_sec);
+ mtime = f2fs_get_section_mtime(sbi, segno);
+ f2fs_bug_on(sbi, mtime == INVALID_MTIME);
/* Handle if the system time has changed by the user */
if (mtime < sit_i->min_mtime)
@@ -599,7 +626,6 @@ static void atssr_lookup_victim(struct f2fs_sb_info *sbi,
unsigned long long age;
unsigned long long max_mtime = sit_i->dirty_max_mtime;
unsigned long long min_mtime = sit_i->dirty_min_mtime;
- unsigned int seg_blocks = sbi->blocks_per_seg;
unsigned int vblocks;
unsigned int dirty_threshold = max(am->max_candidate_count,
am->candidate_ratio *
@@ -629,7 +655,7 @@ next_node:
f2fs_bug_on(sbi, !vblocks);
/* rare case */
- if (vblocks == seg_blocks)
+ if (vblocks == BLKS_PER_SEG(sbi))
goto skip_node;
iter++;
@@ -743,7 +769,7 @@ static int f2fs_gc_pinned_control(struct inode *inode, int gc_type,
*/
int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result,
int gc_type, int type, char alloc_mode,
- unsigned long long age)
+ unsigned long long age, bool one_time)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct sit_info *sm = SIT_I(sbi);
@@ -755,11 +781,12 @@ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result,
int ret = 0;
mutex_lock(&dirty_i->seglist_lock);
- last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec;
+ last_segment = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi);
p.alloc_mode = alloc_mode;
p.age = age;
p.age_threshold = sbi->am.age_threshold;
+ p.one_time_gc = one_time;
retry:
select_policy(sbi, gc_type, type, &p);
@@ -779,11 +806,14 @@ retry:
goto out;
}
- if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+ if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result))) {
ret = -EBUSY;
- else
- p.min_segno = *result;
- goto out;
+ goto out;
+ }
+ if (gc_type == FG_GC)
+ clear_bit(GET_SEC_FROM_SEG(sbi, *result), dirty_i->victim_secmap);
+ p.min_segno = *result;
+ goto got_result;
}
ret = -ENODATA;
@@ -896,7 +926,7 @@ next:
else
sm->last_victim[p.gc_mode] = segno + p.ofs_unit;
sm->last_victim[p.gc_mode] %=
- (MAIN_SECS(sbi) * sbi->segs_per_sec);
+ (MAIN_SECS(sbi) * SEGS_PER_SEC(sbi));
break;
}
}
@@ -1172,7 +1202,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
static int ra_data_block(struct inode *inode, pgoff_t index)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct address_space *mapping = inode->i_mapping;
+ struct address_space *mapping = f2fs_is_cow_file(inode) ?
+ F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
struct f2fs_io_info fio = {
@@ -1184,7 +1215,6 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
.op_flags = 0,
.encrypted_page = NULL,
.in_list = 0,
- .retry = 0,
};
int err;
@@ -1197,7 +1227,6 @@ 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;
@@ -1216,7 +1245,6 @@ 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:
@@ -1264,6 +1292,8 @@ put_page:
static int move_data_block(struct inode *inode, block_t bidx,
int gc_type, unsigned int segno, int off)
{
+ struct address_space *mapping = f2fs_is_cow_file(inode) ?
+ F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping;
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
.ino = inode->i_ino,
@@ -1273,7 +1303,6 @@ static int move_data_block(struct inode *inode, block_t bidx,
.op_flags = 0,
.encrypted_page = NULL,
.in_list = 0,
- .retry = 0,
};
struct dnode_of_data dn;
struct f2fs_summary sum;
@@ -1287,7 +1316,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA;
/* do not read out */
- page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
+ page = f2fs_grab_cache_page(mapping, bidx, false);
if (!page)
return -ENOMEM;
@@ -1364,8 +1393,13 @@ static int move_data_block(struct inode *inode, block_t bidx,
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
/* allocate block address */
- f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
+ err = f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
&sum, type, NULL);
+ if (err) {
+ f2fs_put_page(mpage, 1);
+ /* filesystem should shutdown, no need to recovery block */
+ goto up_out;
+ }
fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS);
@@ -1381,7 +1415,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
page_address(mpage), PAGE_SIZE);
f2fs_put_page(mpage, 1);
- f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr);
+ f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr, 1);
set_page_dirty(fio.encrypted_page);
if (clear_page_dirty_for_io(fio.encrypted_page))
@@ -1393,18 +1427,12 @@ static int move_data_block(struct inode *inode, block_t bidx,
fio.op_flags = REQ_SYNC;
fio.new_blkaddr = newaddr;
f2fs_submit_page_write(&fio);
- if (fio.retry) {
- err = -EAGAIN;
- if (PageWriteback(fio.encrypted_page))
- end_page_writeback(fio.encrypted_page);
- goto put_page_out;
- }
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);
-put_page_out:
+
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
if (err)
@@ -1440,7 +1468,7 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
goto out;
if (gc_type == BG_GC) {
- if (PageWriteback(page)) {
+ if (folio_test_writeback(page_folio(page))) {
err = -EAGAIN;
goto out;
}
@@ -1560,9 +1588,24 @@ next_step:
int err;
inode = f2fs_iget(sb, dni.ino);
- if (IS_ERR(inode) || is_bad_inode(inode) ||
- special_file(inode->i_mode))
+ if (IS_ERR(inode))
+ continue;
+
+ if (is_bad_inode(inode) ||
+ special_file(inode->i_mode)) {
+ iput(inode);
+ continue;
+ }
+
+ if (f2fs_has_inline_data(inode)) {
+ iput(inode);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_err_ratelimited(sbi,
+ "inode %lx has both inline_data flag and "
+ "data block, nid=%u, ofs_in_node=%u",
+ inode->i_ino, dni.nid, ofs_in_node);
continue;
+ }
err = f2fs_gc_pinned_control(inode, gc_type, segno);
if (err == -EAGAIN) {
@@ -1580,7 +1623,7 @@ next_step:
start_bidx = f2fs_start_bidx_of_node(nofs, inode) +
ofs_in_node;
- if (f2fs_post_read_required(inode)) {
+ if (f2fs_meta_inode_gc_required(inode)) {
int err = ra_data_block(inode, start_bidx);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
@@ -1631,7 +1674,7 @@ next_step:
start_bidx = f2fs_start_bidx_of_node(nofs, inode)
+ ofs_in_node;
- if (f2fs_post_read_required(inode))
+ if (f2fs_meta_inode_gc_required(inode))
err = move_data_block(inode, start_bidx,
gc_type, segno, off);
else
@@ -1639,7 +1682,7 @@ next_step:
segno, off);
if (!err && (gc_type == FG_GC ||
- f2fs_post_read_required(inode)))
+ f2fs_meta_inode_gc_required(inode)))
submitted++;
if (locked) {
@@ -1658,13 +1701,14 @@ next_step:
}
static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
- int gc_type)
+ int gc_type, bool one_time)
{
struct sit_info *sit_i = SIT_I(sbi);
int ret;
down_write(&sit_i->sentry_lock);
- ret = f2fs_get_victim(sbi, victim, gc_type, NO_CHECK_TYPE, LFS, 0);
+ ret = f2fs_get_victim(sbi, victim, gc_type, NO_CHECK_TYPE,
+ LFS, 0, one_time);
up_write(&sit_i->sentry_lock);
return ret;
}
@@ -1672,30 +1716,49 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
static int do_garbage_collect(struct f2fs_sb_info *sbi,
unsigned int start_segno,
struct gc_inode_list *gc_list, int gc_type,
- bool force_migrate)
+ bool force_migrate, bool one_time)
{
struct page *sum_page;
struct f2fs_summary_block *sum;
struct blk_plug plug;
unsigned int segno = start_segno;
- unsigned int end_segno = start_segno + sbi->segs_per_sec;
+ unsigned int end_segno = start_segno + SEGS_PER_SEC(sbi);
+ unsigned int sec_end_segno;
int seg_freed = 0, migrated = 0;
unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
SUM_TYPE_DATA : SUM_TYPE_NODE;
unsigned char data_type = (type == SUM_TYPE_DATA) ? DATA : NODE;
int submitted = 0;
- if (__is_large_section(sbi))
- end_segno = rounddown(end_segno, sbi->segs_per_sec);
+ if (__is_large_section(sbi)) {
+ sec_end_segno = rounddown(end_segno, SEGS_PER_SEC(sbi));
- /*
- * zone-capacity can be less than zone-size in zoned devices,
- * resulting in less than expected usable segments in the zone,
- * calculate the end segno in the zone which can be garbage collected
- */
- if (f2fs_sb_has_blkzoned(sbi))
- end_segno -= sbi->segs_per_sec -
- f2fs_usable_segs_in_sec(sbi, segno);
+ /*
+ * zone-capacity can be less than zone-size in zoned devices,
+ * resulting in less than expected usable segments in the zone,
+ * calculate the end segno in the zone which can be garbage
+ * collected
+ */
+ if (f2fs_sb_has_blkzoned(sbi))
+ sec_end_segno -= SEGS_PER_SEC(sbi) -
+ f2fs_usable_segs_in_sec(sbi);
+
+ if (gc_type == BG_GC || one_time) {
+ unsigned int window_granularity =
+ sbi->migration_window_granularity;
+
+ if (f2fs_sb_has_blkzoned(sbi) &&
+ !has_enough_free_blocks(sbi,
+ sbi->gc_thread->boost_zoned_gc_percent))
+ window_granularity *=
+ BOOST_GC_MULTIPLE;
+
+ end_segno = start_segno + window_granularity;
+ }
+
+ if (end_segno > sec_end_segno)
+ end_segno = sec_end_segno;
+ }
sanity_check_seg_type(sbi, get_seg_entry(sbi, segno)->type);
@@ -1743,7 +1806,6 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
if (type != GET_SUM_TYPE((&sum->footer))) {
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,
STOP_CP_REASON_CORRUPTED_SUMMARY);
goto skip;
@@ -1775,7 +1837,8 @@ freed:
if (__is_large_section(sbi))
sbi->next_victim_seg[gc_type] =
- (segno + 1 < end_segno) ? segno + 1 : NULL_SEGNO;
+ (segno + 1 < sec_end_segno) ?
+ segno + 1 : NULL_SEGNO;
skip:
f2fs_put_page(sum_page, 0);
}
@@ -1852,7 +1915,7 @@ gc_more:
goto stop;
}
retry:
- ret = __get_victim(sbi, &segno, gc_type);
+ ret = __get_victim(sbi, &segno, gc_type, gc_control->one_time);
if (ret) {
/* allow to search victim from sections has pinned data */
if (ret == -ENODATA && gc_type == FG_GC &&
@@ -1864,17 +1927,21 @@ retry:
}
seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type,
- gc_control->should_migrate_blocks);
+ gc_control->should_migrate_blocks,
+ gc_control->one_time);
if (seg_freed < 0)
goto stop;
total_freed += seg_freed;
- if (seg_freed == f2fs_usable_segs_in_sec(sbi, segno)) {
+ if (seg_freed == f2fs_usable_segs_in_sec(sbi)) {
sec_freed++;
total_sec_freed++;
}
+ if (gc_control->one_time)
+ goto stop;
+
if (gc_type == FG_GC) {
sbi->cur_victim_sec = NULL_SEGNO;
@@ -1983,10 +2050,42 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi)
init_atgc_management(sbi);
}
+int f2fs_gc_range(struct f2fs_sb_info *sbi,
+ unsigned int start_seg, unsigned int end_seg,
+ bool dry_run, unsigned int dry_run_sections)
+{
+ unsigned int segno;
+ unsigned int gc_secs = dry_run_sections;
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
+ for (segno = start_seg; segno <= end_seg; segno += SEGS_PER_SEC(sbi)) {
+ struct gc_inode_list gc_list = {
+ .ilist = LIST_HEAD_INIT(gc_list.ilist),
+ .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
+ };
+
+ do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false);
+ put_gc_inode(&gc_list);
+
+ if (!dry_run && get_valid_blocks(sbi, segno, true))
+ return -EAGAIN;
+ if (dry_run && dry_run_sections &&
+ !get_valid_blocks(sbi, segno, true) && --gc_secs == 0)
+ break;
+
+ if (fatal_signal_pending(current))
+ return -ERESTARTSYS;
+ }
+
+ return 0;
+}
+
static int free_segment_range(struct f2fs_sb_info *sbi,
- unsigned int secs, bool gc_only)
+ unsigned int secs, bool dry_run)
{
- unsigned int segno, next_inuse, start, end;
+ unsigned int next_inuse, start, end;
struct cp_control cpc = { CP_RESIZE, 0, 0, 0 };
int gc_mode, gc_type;
int err = 0;
@@ -1994,7 +2093,7 @@ static int free_segment_range(struct f2fs_sb_info *sbi,
/* Force block allocation for GC */
MAIN_SECS(sbi) -= secs;
- start = MAIN_SECS(sbi) * sbi->segs_per_sec;
+ start = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi);
end = MAIN_SEGS(sbi) - 1;
mutex_lock(&DIRTY_I(sbi)->seglist_lock);
@@ -2008,29 +2107,15 @@ static int free_segment_range(struct f2fs_sb_info *sbi,
mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
/* Move out cursegs from the target range */
- for (type = CURSEG_HOT_DATA; type < NR_CURSEG_PERSIST_TYPE; type++)
- f2fs_allocate_segment_for_resize(sbi, type, start, end);
-
- /* do GC to move out valid blocks in the range */
- for (segno = start; segno <= end; segno += sbi->segs_per_sec) {
- struct gc_inode_list gc_list = {
- .ilist = LIST_HEAD_INIT(gc_list.ilist),
- .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
- };
-
- do_garbage_collect(sbi, segno, &gc_list, FG_GC, true);
- put_gc_inode(&gc_list);
-
- if (!gc_only && get_valid_blocks(sbi, segno, true)) {
- err = -EAGAIN;
- goto out;
- }
- if (fatal_signal_pending(current)) {
- err = -ERESTARTSYS;
+ for (type = CURSEG_HOT_DATA; type < NR_CURSEG_PERSIST_TYPE; type++) {
+ err = f2fs_allocate_segment_for_resize(sbi, type, start, end);
+ if (err)
goto out;
- }
}
- if (gc_only)
+
+ /* do GC to move out valid blocks in the range */
+ err = f2fs_gc_range(sbi, start, end, dry_run, 0);
+ if (err || dry_run)
goto out;
stat_inc_cp_call_count(sbi, TOTAL_CALL);
@@ -2056,7 +2141,7 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs)
int segment_count;
int segment_count_main;
long long block_count;
- int segs = secs * sbi->segs_per_sec;
+ int segs = secs * SEGS_PER_SEC(sbi);
f2fs_down_write(&sbi->sb_lock);
@@ -2069,7 +2154,7 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs)
raw_sb->segment_count = cpu_to_le32(segment_count + segs);
raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs);
raw_sb->block_count = cpu_to_le64(block_count +
- (long long)segs * sbi->blocks_per_seg);
+ (long long)SEGS_TO_BLKS(sbi, segs));
if (f2fs_is_multi_device(sbi)) {
int last_dev = sbi->s_ndevs - 1;
int dev_segs =
@@ -2084,8 +2169,8 @@ static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs)
static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs)
{
- int segs = secs * sbi->segs_per_sec;
- long long blks = (long long)segs * sbi->blocks_per_seg;
+ int segs = secs * SEGS_PER_SEC(sbi);
+ long long blks = SEGS_TO_BLKS(sbi, segs);
long long user_block_count =
le64_to_cpu(F2FS_CKPT(sbi)->user_block_count);
@@ -2127,7 +2212,7 @@ int f2fs_resize_fs(struct file *filp, __u64 block_count)
int last_dev = sbi->s_ndevs - 1;
__u64 last_segs = FDEV(last_dev).total_segments;
- if (block_count + last_segs * sbi->blocks_per_seg <=
+ if (block_count + SEGS_TO_BLKS(sbi, last_segs) <=
old_block_count)
return -EINVAL;
}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 28a00942802c..5c1eaf55e127 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -15,17 +15,30 @@
#define DEF_GC_THREAD_MAX_SLEEP_TIME 60000
#define DEF_GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */
+/* GC sleep parameters for zoned deivces */
+#define DEF_GC_THREAD_MIN_SLEEP_TIME_ZONED 10
+#define DEF_GC_THREAD_MAX_SLEEP_TIME_ZONED 20
+#define DEF_GC_THREAD_NOGC_SLEEP_TIME_ZONED 60000
+
/* choose candidates from sections which has age of more than 7 days */
#define DEF_GC_THREAD_AGE_THRESHOLD (60 * 60 * 24 * 7)
#define DEF_GC_THREAD_CANDIDATE_RATIO 20 /* select 20% oldest sections as candidates */
#define DEF_GC_THREAD_MAX_CANDIDATE_COUNT 10 /* select at most 10 sections as candidates */
#define DEF_GC_THREAD_AGE_WEIGHT 60 /* age weight */
+#define DEF_GC_THREAD_VALID_THRESH_RATIO 95 /* do not GC over 95% valid block ratio for one time GC */
#define DEFAULT_ACCURACY_CLASS 10000 /* accuracy class */
#define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */
#define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */
+#define LIMIT_NO_ZONED_GC 60 /* percentage over total user space of no gc for zoned devices */
+#define LIMIT_BOOST_ZONED_GC 25 /* percentage over total user space of boosted gc for zoned devices */
+#define DEF_MIGRATION_WINDOW_GRANULARITY_ZONED 3
+#define BOOST_GC_MULTIPLE 5
+#define ZONED_PIN_SEC_REQUIRED_COUNT 1
+
#define DEF_GC_FAILED_PINNED_FILES 2048
+#define MAX_GC_FAILED_PINNED_FILES USHRT_MAX
/* Search max. number of dirty segments to select a victim segment */
#define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */
@@ -50,6 +63,11 @@ struct f2fs_gc_kthread {
* caller of f2fs_balance_fs()
* will wait on this wait queue.
*/
+
+ /* for gc control for zoned devices */
+ unsigned int no_zoned_gc_percent;
+ unsigned int boost_zoned_gc_percent;
+ unsigned int valid_thresh_ratio;
};
struct gc_inode_list {
@@ -96,7 +114,7 @@ static inline block_t free_segs_blk_count(struct f2fs_sb_info *sbi)
if (f2fs_sb_has_blkzoned(sbi))
return free_segs_blk_count_zoned(sbi);
- return free_segments(sbi) << sbi->log_blocks_per_seg;
+ return SEGS_TO_BLKS(sbi, free_segments(sbi));
}
static inline block_t free_user_blocks(struct f2fs_sb_info *sbi)
@@ -104,7 +122,7 @@ static inline block_t free_user_blocks(struct f2fs_sb_info *sbi)
block_t free_blks, ovp_blks;
free_blks = free_segs_blk_count(sbi);
- ovp_blks = overprovision_segments(sbi) << sbi->log_blocks_per_seg;
+ ovp_blks = SEGS_TO_BLKS(sbi, overprovision_segments(sbi));
if (free_blks < ovp_blks)
return 0;
@@ -151,6 +169,12 @@ static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
*wait -= min_time;
}
+static inline bool has_enough_free_blocks(struct f2fs_sb_info *sbi,
+ unsigned int limit_perc)
+{
+ return free_sections(sbi) > ((sbi->total_sections * limit_perc) / 100);
+}
+
static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
{
block_t user_block_count = sbi->user_block_count;
@@ -166,3 +190,10 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
free_user_blocks(sbi) <
limit_free_user_blocks(invalid_user_blocks));
}
+
+static inline bool need_to_boost_gc(struct f2fs_sb_info *sbi)
+{
+ if (f2fs_sb_has_blkzoned(sbi))
+ return !has_enough_free_blocks(sbi, LIMIT_BOOST_ZONED_GC);
+ return has_enough_invalid_blocks(sbi);
+}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index ac00423f117b..3e3c35d4c98b 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -16,7 +16,7 @@
static bool support_inline_data(struct inode *inode)
{
- if (f2fs_is_atomic_file(inode))
+ if (f2fs_used_in_atomic_write(inode))
return false;
if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
return false;
@@ -33,11 +33,29 @@ bool f2fs_may_inline_data(struct inode *inode)
return !f2fs_post_read_required(inode);
}
-bool f2fs_sanity_check_inline_data(struct inode *inode)
+static bool inode_has_blocks(struct inode *inode, struct page *ipage)
+{
+ struct f2fs_inode *ri = F2FS_INODE(ipage);
+ int i;
+
+ if (F2FS_HAS_BLOCKS(inode))
+ return true;
+
+ for (i = 0; i < DEF_NIDS_PER_INODE; i++) {
+ if (ri->i_nid[i])
+ return true;
+ }
+ return false;
+}
+
+bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage)
{
if (!f2fs_has_inline_data(inode))
return false;
+ if (inode_has_blocks(inode, ipage))
+ return false;
+
if (!support_inline_data(inode))
return true;
@@ -61,22 +79,22 @@ bool f2fs_may_inline_dentry(struct inode *inode)
return true;
}
-void f2fs_do_read_inline_data(struct page *page, struct page *ipage)
+void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = folio->mapping->host;
- if (PageUptodate(page))
+ if (folio_test_uptodate(folio))
return;
- f2fs_bug_on(F2FS_P_SB(page), page->index);
+ f2fs_bug_on(F2FS_I_SB(inode), folio_index(folio));
- zero_user_segment(page, MAX_INLINE_DATA(inode), PAGE_SIZE);
+ folio_zero_segment(folio, MAX_INLINE_DATA(inode), folio_size(folio));
/* Copy the whole inline data block */
- memcpy_to_page(page, 0, inline_data_addr(inode, ipage),
+ memcpy_to_folio(folio, 0, inline_data_addr(inode, ipage),
MAX_INLINE_DATA(inode));
- if (!PageUptodate(page))
- SetPageUptodate(page);
+ if (!folio_test_uptodate(folio))
+ folio_mark_uptodate(folio);
}
void f2fs_truncate_inline_inode(struct inode *inode,
@@ -97,13 +115,13 @@ void f2fs_truncate_inline_inode(struct inode *inode,
clear_inode_flag(inode, FI_DATA_EXIST);
}
-int f2fs_read_inline_data(struct inode *inode, struct page *page)
+int f2fs_read_inline_data(struct inode *inode, struct folio *folio)
{
struct page *ipage;
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
- unlock_page(page);
+ folio_unlock(folio);
return PTR_ERR(ipage);
}
@@ -112,15 +130,15 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
return -EAGAIN;
}
- if (page->index)
- zero_user_segment(page, 0, PAGE_SIZE);
+ if (folio_index(folio))
+ folio_zero_segment(folio, 0, folio_size(folio));
else
- f2fs_do_read_inline_data(page, ipage);
+ f2fs_do_read_inline_data(folio, ipage);
- if (!PageUptodate(page))
- SetPageUptodate(page);
+ if (!folio_test_uptodate(folio))
+ folio_mark_uptodate(folio);
f2fs_put_page(ipage, 1);
- unlock_page(page);
+ folio_unlock(folio);
return 0;
}
@@ -164,9 +182,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
return -EFSCORRUPTED;
}
- f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
+ f2fs_bug_on(F2FS_P_SB(page), folio_test_writeback(page_folio(page)));
- f2fs_do_read_inline_data(page, dn->inode_page);
+ f2fs_do_read_inline_data(page_folio(page), dn->inode_page);
set_page_dirty(page);
/* clear dirty state */
@@ -203,8 +221,10 @@ int f2fs_convert_inline_inode(struct inode *inode)
struct page *ipage, *page;
int err = 0;
- if (!f2fs_has_inline_data(inode) ||
- f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
+ if (f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ if (!f2fs_has_inline_data(inode))
return 0;
err = f2fs_dquot_initialize(inode);
@@ -240,35 +260,34 @@ out:
return err;
}
-int f2fs_write_inline_data(struct inode *inode, struct page *page)
+int f2fs_write_inline_data(struct inode *inode, struct folio *folio)
{
- struct dnode_of_data dn;
- int err;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct page *ipage;
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE);
- if (err)
- return err;
+ ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
if (!f2fs_has_inline_data(inode)) {
- f2fs_put_dnode(&dn);
+ f2fs_put_page(ipage, 1);
return -EAGAIN;
}
- f2fs_bug_on(F2FS_I_SB(inode), page->index);
+ f2fs_bug_on(F2FS_I_SB(inode), folio->index);
- f2fs_wait_on_page_writeback(dn.inode_page, NODE, true, true);
- memcpy_from_page(inline_data_addr(inode, dn.inode_page),
- page, 0, MAX_INLINE_DATA(inode));
- set_page_dirty(dn.inode_page);
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
+ memcpy_from_folio(inline_data_addr(inode, ipage),
+ folio, 0, MAX_INLINE_DATA(inode));
+ set_page_dirty(ipage);
- f2fs_clear_page_cache_dirty_tag(page);
+ f2fs_clear_page_cache_dirty_tag(folio);
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
- clear_page_private_inline(dn.inode_page);
- f2fs_put_dnode(&dn);
+ clear_page_private_inline(ipage);
+ f2fs_put_page(ipage, 1);
return 0;
}
@@ -333,7 +352,8 @@ process_inline:
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
const struct f2fs_filename *fname,
- struct page **res_page)
+ struct page **res_page,
+ bool use_hash)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct f2fs_dir_entry *de;
@@ -350,7 +370,7 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
inline_dentry = inline_data_addr(dir, ipage);
make_dentry_ptr_inline(dir, &d, inline_dentry);
- de = f2fs_find_target_dentry(&d, fname, NULL);
+ de = f2fs_find_target_dentry(&d, fname, NULL, use_hash);
unlock_page(ipage);
if (IS_ERR(de)) {
*res_page = ERR_CAST(de);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index c26effdce9aa..3dd25f64d6f1 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -7,7 +7,6 @@
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
-#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/sched/mm.h>
#include <linux/lz4.h>
@@ -29,9 +28,17 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
if (is_inode_flag_set(inode, FI_NEW_INODE))
return;
+ if (f2fs_readonly(F2FS_I_SB(inode)->sb))
+ return;
+
if (f2fs_inode_dirtied(inode, sync))
return;
+ if (f2fs_is_atomic_file(inode)) {
+ set_inode_flag(inode, FI_ATOMIC_DIRTIED);
+ return;
+ }
+
mark_inode_dirty_sync(inode);
}
@@ -161,7 +168,8 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
if (!f2fs_enable_inode_chksum(sbi, page))
#else
if (!f2fs_enable_inode_chksum(sbi, page) ||
- PageDirty(page) || PageWriteback(page))
+ PageDirty(page) ||
+ folio_test_writeback(page_folio(page)))
#endif
return true;
@@ -171,7 +179,8 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
if (provided != calculated)
f2fs_warn(sbi, "checksum invalid, nid = %lu, ino_of_node = %x, %x vs. %x",
- page->index, ino_of_node(page), provided, calculated);
+ page_folio(page)->index, ino_of_node(page),
+ provided, calculated);
return provided == calculated;
}
@@ -293,15 +302,6 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
F2FS_TOTAL_EXTRA_ATTR_SIZE);
return false;
}
- if (f2fs_sb_has_flexible_inline_xattr(sbi) &&
- f2fs_has_inline_xattr(inode) &&
- (!fi->i_inline_xattr_size ||
- fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) {
- f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, max: %lu",
- __func__, inode->i_ino, fi->i_inline_xattr_size,
- MAX_INLINE_XATTR_SIZE);
- return false;
- }
if (f2fs_sb_has_compression(sbi) &&
fi->i_flags & F2FS_COMPR_FL &&
F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
@@ -309,9 +309,15 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
if (!sanity_check_compress_inode(inode, ri))
return false;
}
- } else if (f2fs_sb_has_flexible_inline_xattr(sbi)) {
- f2fs_warn(sbi, "%s: corrupted inode ino=%lx, run fsck to fix.",
- __func__, inode->i_ino);
+ }
+
+ if (f2fs_sb_has_flexible_inline_xattr(sbi) &&
+ f2fs_has_inline_xattr(inode) &&
+ (fi->i_inline_xattr_size < MIN_INLINE_XATTR_SIZE ||
+ fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) {
+ f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, min: %zu, max: %lu",
+ __func__, inode->i_ino, fi->i_inline_xattr_size,
+ MIN_INLINE_XATTR_SIZE, MAX_INLINE_XATTR_SIZE);
return false;
}
@@ -343,7 +349,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
}
}
- if (f2fs_sanity_check_inline_data(inode)) {
+ if (f2fs_sanity_check_inline_data(inode, node_page)) {
f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix",
__func__, inode->i_ino, inode->i_mode);
return false;
@@ -361,6 +367,25 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return false;
}
+ if (fi->i_xattr_nid && f2fs_check_nid_range(sbi, fi->i_xattr_nid)) {
+ f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_xattr_nid: %u, run fsck to fix.",
+ __func__, inode->i_ino, fi->i_xattr_nid);
+ return false;
+ }
+
+ if (IS_DEVICE_ALIASING(inode)) {
+ if (!f2fs_sb_has_device_alias(sbi)) {
+ f2fs_warn(sbi, "%s: inode (ino=%lx) has device alias flag, but the feature is off",
+ __func__, inode->i_ino);
+ return false;
+ }
+ if (!f2fs_is_pinned_file(inode)) {
+ f2fs_warn(sbi, "%s: inode (ino=%lx) has device alias flag, but is not pinned",
+ __func__, inode->i_ino);
+ return false;
+ }
+ }
+
return true;
}
@@ -408,8 +433,7 @@ static int do_read_inode(struct inode *inode)
if (S_ISDIR(inode->i_mode))
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
else if (S_ISREG(inode->i_mode))
- fi->i_gc_failures[GC_FAILURE_PIN] =
- le16_to_cpu(ri->i_gc_failures);
+ fi->i_gc_failures = le16_to_cpu(ri->i_gc_failures);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
fi->i_flags = le32_to_cpu(ri->i_flags);
if (S_ISREG(inode->i_mode))
@@ -502,16 +526,16 @@ static int do_read_inode(struct inode *inode)
init_idisk_time(inode);
- /* Need all the flag bits */
- f2fs_init_read_extent_tree(inode, node_page);
- f2fs_init_age_extent_tree(inode);
-
- if (!sanity_check_extent_cache(inode)) {
+ if (!sanity_check_extent_cache(inode, node_page)) {
f2fs_put_page(node_page, 1);
f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
return -EFSCORRUPTED;
}
+ /* Need all the flag bits */
+ f2fs_init_read_extent_tree(inode, node_page);
+ f2fs_init_age_extent_tree(inode);
+
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
@@ -604,14 +628,6 @@ make_now:
}
f2fs_set_inode_flags(inode);
- if (file_should_truncate(inode) &&
- !is_sbi_flag_set(sbi, SBI_POR_DOING)) {
- ret = f2fs_truncate(inode);
- if (ret)
- goto bad_inode;
- file_dont_truncate(inode);
- }
-
unlock_new_inode(inode);
trace_f2fs_iget(inode);
return inode;
@@ -639,8 +655,9 @@ retry:
void f2fs_update_inode(struct inode *inode, struct page *node_page)
{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_inode *ri;
- struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ];
+ struct extent_tree *et = fi->extent_tree[EX_READ];
f2fs_wait_on_page_writeback(node_page, NODE, true, true);
set_page_dirty(node_page);
@@ -650,7 +667,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
ri = F2FS_INODE(node_page);
ri->i_mode = cpu_to_le16(inode->i_mode);
- ri->i_advise = F2FS_I(inode)->i_advise;
+ ri->i_advise = fi->i_advise;
ri->i_uid = cpu_to_le32(i_uid_read(inode));
ri->i_gid = cpu_to_le32(i_gid_read(inode));
ri->i_links = cpu_to_le32(inode->i_nlink);
@@ -676,59 +693,49 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page)
ri->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
ri->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode));
if (S_ISDIR(inode->i_mode))
- ri->i_current_depth =
- cpu_to_le32(F2FS_I(inode)->i_current_depth);
+ ri->i_current_depth = cpu_to_le32(fi->i_current_depth);
else if (S_ISREG(inode->i_mode))
- ri->i_gc_failures =
- cpu_to_le16(F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]);
- ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
- ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
- ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
+ ri->i_gc_failures = cpu_to_le16(fi->i_gc_failures);
+ ri->i_xattr_nid = cpu_to_le32(fi->i_xattr_nid);
+ ri->i_flags = cpu_to_le32(fi->i_flags);
+ ri->i_pino = cpu_to_le32(fi->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
- ri->i_dir_level = F2FS_I(inode)->i_dir_level;
+ ri->i_dir_level = fi->i_dir_level;
if (f2fs_has_extra_attr(inode)) {
- ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize);
+ ri->i_extra_isize = cpu_to_le16(fi->i_extra_isize);
if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode)))
ri->i_inline_xattr_size =
- cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size);
+ cpu_to_le16(fi->i_inline_xattr_size);
if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) &&
- F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
- i_projid)) {
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid)) {
projid_t i_projid;
- i_projid = from_kprojid(&init_user_ns,
- F2FS_I(inode)->i_projid);
+ i_projid = from_kprojid(&init_user_ns, fi->i_projid);
ri->i_projid = cpu_to_le32(i_projid);
}
if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) &&
- F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
- i_crtime)) {
- ri->i_crtime =
- cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec);
- ri->i_crtime_nsec =
- cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
+ ri->i_crtime = cpu_to_le64(fi->i_crtime.tv_sec);
+ ri->i_crtime_nsec = cpu_to_le32(fi->i_crtime.tv_nsec);
}
if (f2fs_sb_has_compression(F2FS_I_SB(inode)) &&
- F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize,
i_compress_flag)) {
unsigned short compress_flag;
- ri->i_compr_blocks =
- cpu_to_le64(atomic_read(
- &F2FS_I(inode)->i_compr_blocks));
- ri->i_compress_algorithm =
- F2FS_I(inode)->i_compress_algorithm;
- compress_flag = F2FS_I(inode)->i_compress_flag |
- F2FS_I(inode)->i_compress_level <<
+ ri->i_compr_blocks = cpu_to_le64(
+ atomic_read(&fi->i_compr_blocks));
+ ri->i_compress_algorithm = fi->i_compress_algorithm;
+ compress_flag = fi->i_compress_flag |
+ fi->i_compress_level <<
COMPRESS_LEVEL_OFFSET;
ri->i_compress_flag = cpu_to_le16(compress_flag);
- ri->i_log_cluster_size =
- F2FS_I(inode)->i_log_cluster_size;
+ ri->i_log_cluster_size = fi->i_log_cluster_size;
}
}
@@ -782,8 +789,10 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
!is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;
- if (!f2fs_is_checkpoint_ready(sbi))
+ if (!f2fs_is_checkpoint_ready(sbi)) {
+ f2fs_mark_inode_dirty_sync(inode, true);
return -ENOSPC;
+ }
/*
* We need to balance fs here to prevent from producing dirty node pages
@@ -804,11 +813,13 @@ void f2fs_evict_inode(struct inode *inode)
struct f2fs_inode_info *fi = F2FS_I(inode);
nid_t xnid = fi->i_xattr_nid;
int err = 0;
+ bool freeze_protected = false;
f2fs_abort_atomic_write(inode, true);
- if (fi->cow_inode) {
+ if (fi->cow_inode && f2fs_is_cow_file(fi->cow_inode)) {
clear_inode_flag(fi->cow_inode, FI_COW_FILE);
+ F2FS_I(fi->cow_inode)->atomic_inode = NULL;
iput(fi->cow_inode);
fi->cow_inode = NULL;
}
@@ -828,7 +839,8 @@ void f2fs_evict_inode(struct inode *inode)
f2fs_bug_on(sbi, get_dirty_pages(inode));
f2fs_remove_dirty_inode(inode);
- f2fs_destroy_extent_tree(inode);
+ if (!IS_DEVICE_ALIASING(inode))
+ f2fs_destroy_extent_tree(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
@@ -843,8 +855,10 @@ void f2fs_evict_inode(struct inode *inode)
f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
- if (!is_sbi_flag_set(sbi, SBI_IS_FREEZING))
+ if (!is_sbi_flag_set(sbi, SBI_IS_FREEZING)) {
sb_start_intwrite(inode->i_sb);
+ freeze_protected = true;
+ }
set_inode_flag(inode, FI_NO_ALLOC);
i_size_write(inode, 0);
retry:
@@ -882,12 +896,15 @@ retry:
goto retry;
}
+ if (IS_DEVICE_ALIASING(inode))
+ f2fs_destroy_extent_tree(inode);
+
if (err) {
f2fs_update_inode_page(inode);
if (dquot_initialize_needed(inode))
set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
}
- if (!is_sbi_flag_set(sbi, SBI_IS_FREEZING))
+ if (freeze_protected)
sb_end_intwrite(inode->i_sb);
no_delete:
dquot_drop(inode);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index b3bb815fc6aa..a278c7da8177 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -221,6 +221,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
const char *name)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct f2fs_inode_info *fi;
nid_t ino;
struct inode *inode;
bool nid_free = false;
@@ -241,14 +242,15 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
inode_init_owner(idmap, inode, dir, mode);
+ fi = F2FS_I(inode);
inode->i_ino = ino;
inode->i_blocks = 0;
simple_inode_init_ts(inode);
- F2FS_I(inode)->i_crtime = inode_get_mtime(inode);
+ fi->i_crtime = inode_get_mtime(inode);
inode->i_generation = get_random_u32();
if (S_ISDIR(inode->i_mode))
- F2FS_I(inode)->i_current_depth = 1;
+ fi->i_current_depth = 1;
err = insert_inode_locked(inode);
if (err) {
@@ -258,9 +260,9 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
if (f2fs_sb_has_project_quota(sbi) &&
(F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL))
- F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid;
+ fi->i_projid = F2FS_I(dir)->i_projid;
else
- F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns,
+ fi->i_projid = make_kprojid(&init_user_ns,
F2FS_DEF_PROJID);
err = fscrypt_prepare_new_inode(dir, inode, &encrypt);
@@ -278,7 +280,7 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
if (f2fs_sb_has_extra_attr(sbi)) {
set_inode_flag(inode, FI_EXTRA_ATTR);
- F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
+ fi->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
}
if (test_opt(sbi, INLINE_XATTR))
@@ -296,15 +298,15 @@ static struct inode *f2fs_new_inode(struct mnt_idmap *idmap,
f2fs_has_inline_dentry(inode)) {
xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
}
- F2FS_I(inode)->i_inline_xattr_size = xattr_size;
+ fi->i_inline_xattr_size = xattr_size;
- F2FS_I(inode)->i_flags =
+ fi->i_flags =
f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED);
if (S_ISDIR(inode->i_mode))
- F2FS_I(inode)->i_flags |= F2FS_INDEX_FL;
+ fi->i_flags |= F2FS_INDEX_FL;
- if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL)
+ if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
/* Check compression first. */
@@ -339,6 +341,7 @@ fail_drop:
trace_f2fs_new_inode(inode, err);
dquot_drop(inode);
inode->i_flags |= S_NOQUOTA;
+ make_bad_inode(inode);
if (nid_free)
set_inode_flag(inode, FI_FREE_NID);
clear_nlink(inode);
@@ -455,62 +458,6 @@ struct dentry *f2fs_get_parent(struct dentry *child)
return d_obtain_alias(f2fs_iget(child->d_sb, ino));
}
-static int __recover_dot_dentries(struct inode *dir, nid_t pino)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
- struct qstr dot = QSTR_INIT(".", 1);
- struct f2fs_dir_entry *de;
- struct page *page;
- int err = 0;
-
- if (f2fs_readonly(sbi->sb)) {
- f2fs_info(sbi, "skip recovering inline_dots inode (ino:%lu, pino:%u) in readonly mountpoint",
- dir->i_ino, pino);
- return 0;
- }
-
- if (!S_ISDIR(dir->i_mode)) {
- f2fs_err(sbi, "inconsistent inode status, skip recovering inline_dots inode (ino:%lu, i_mode:%u, pino:%u)",
- dir->i_ino, dir->i_mode, pino);
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- return -ENOTDIR;
- }
-
- err = f2fs_dquot_initialize(dir);
- if (err)
- return err;
-
- f2fs_balance_fs(sbi, true);
-
- f2fs_lock_op(sbi);
-
- de = f2fs_find_entry(dir, &dot, &page);
- if (de) {
- f2fs_put_page(page, 0);
- } else if (IS_ERR(page)) {
- err = PTR_ERR(page);
- goto out;
- } else {
- err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
- if (err)
- goto out;
- }
-
- de = f2fs_find_entry(dir, &dotdot_name, &page);
- if (de)
- f2fs_put_page(page, 0);
- else if (IS_ERR(page))
- err = PTR_ERR(page);
- else
- err = f2fs_do_add_link(dir, &dotdot_name, NULL, pino, S_IFDIR);
-out:
- if (!err)
- clear_inode_flag(dir, FI_INLINE_DOTS);
-
- f2fs_unlock_op(sbi);
- return err;
-}
-
static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
@@ -520,7 +467,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
struct dentry *new;
nid_t ino = -1;
int err = 0;
- unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
struct f2fs_filename fname;
trace_f2fs_lookup_start(dir, dentry, flags);
@@ -531,7 +477,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
}
err = f2fs_prepare_lookup(dir, dentry, &fname);
- generic_set_encrypted_ci_d_ops(dentry);
if (err == -ENOENT)
goto out_splice;
if (err)
@@ -557,17 +502,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
- err = __recover_dot_dentries(dir, root_ino);
- if (err)
- goto out_iput;
- }
-
- if (f2fs_has_inline_dots(inode)) {
- err = __recover_dot_dentries(inode, dir->i_ino);
- if (err)
- goto out_iput;
- }
if (IS_ENCRYPTED(dir) &&
(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
!fscrypt_has_permitted_context(dir, inode)) {
@@ -577,8 +511,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
goto out_iput;
}
out_splice:
-#if IS_ENABLED(CONFIG_UNICODE)
- if (!inode && IS_CASEFOLDED(dir)) {
+ if (IS_ENABLED(CONFIG_UNICODE) && !inode && IS_CASEFOLDED(dir)) {
/* Eventually we want to call d_add_ci(dentry, NULL)
* for negative dentries in the encoding case as
* well. For now, prevent the negative dentry
@@ -587,7 +520,7 @@ out_splice:
trace_f2fs_lookup_end(dir, dentry, ino, err);
return NULL;
}
-#endif
+
new = d_splice_alias(inode, dentry);
trace_f2fs_lookup_end(dir, !IS_ERR_OR_NULL(new) ? new : dentry,
ino, IS_ERR(new) ? PTR_ERR(new) : err);
@@ -640,16 +573,15 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
f2fs_delete_entry(de, page, dir, inode);
f2fs_unlock_op(sbi);
-#if IS_ENABLED(CONFIG_UNICODE)
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
* negative dentries at f2fs_lookup(), when it is better
* supported by the VFS for the CI case.
*/
- if (IS_CASEFOLDED(dir))
+ if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
d_invalidate(dentry);
-#endif
+
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
fail:
@@ -852,7 +784,7 @@ out:
static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
struct file *file, umode_t mode, bool is_whiteout,
- struct inode **new_inode)
+ struct inode **new_inode, struct f2fs_filename *fname)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
@@ -880,7 +812,7 @@ static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
if (err)
goto out;
- err = f2fs_do_tmpfile(inode, dir);
+ err = f2fs_do_tmpfile(inode, dir, fname);
if (err)
goto release_out;
@@ -931,22 +863,24 @@ static int f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
if (!f2fs_is_checkpoint_ready(sbi))
return -ENOSPC;
- err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL);
+ err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL, NULL);
return finish_open_simple(file, err);
}
static int f2fs_create_whiteout(struct mnt_idmap *idmap,
- struct inode *dir, struct inode **whiteout)
+ struct inode *dir, struct inode **whiteout,
+ struct f2fs_filename *fname)
{
- return __f2fs_tmpfile(idmap, dir, NULL,
- S_IFCHR | WHITEOUT_MODE, true, whiteout);
+ return __f2fs_tmpfile(idmap, dir, NULL, S_IFCHR | WHITEOUT_MODE,
+ true, whiteout, fname);
}
int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
struct inode **new_inode)
{
- return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG, false, new_inode);
+ return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG,
+ false, new_inode, NULL);
}
static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
@@ -990,7 +924,14 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
}
if (flags & RENAME_WHITEOUT) {
- err = f2fs_create_whiteout(idmap, old_dir, &whiteout);
+ struct f2fs_filename fname;
+
+ err = f2fs_setup_filename(old_dir, &old_dentry->d_name,
+ 0, &fname);
+ if (err)
+ return err;
+
+ err = f2fs_create_whiteout(idmap, old_dir, &whiteout, &fname);
if (err)
return err;
}
@@ -1105,14 +1046,11 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
iput(whiteout);
}
- if (old_is_dir) {
- if (old_dir_entry)
- f2fs_set_link(old_inode, old_dir_entry,
- old_dir_page, new_dir);
- else
- f2fs_put_page(old_dir_page, 0);
+ if (old_dir_entry)
+ f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir);
+ if (old_is_dir)
f2fs_i_links_write(old_dir, false);
- }
+
if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) {
f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO);
if (S_ISDIR(old_inode->i_mode))
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 9b546fd21010..f88392fc4ba9 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -20,7 +20,7 @@
#include "iostat.h"
#include <trace/events/f2fs.h>
-#define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
+#define on_f2fs_build_free_nids(nm_i) mutex_is_locked(&(nm_i)->build_lock)
static struct kmem_cache *nat_entry_slab;
static struct kmem_cache *free_nid_slab;
@@ -123,7 +123,7 @@ bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type)
static void clear_node_page_dirty(struct page *page)
{
if (PageDirty(page)) {
- f2fs_clear_page_cache_dirty_tag(page);
+ f2fs_clear_page_cache_dirty_tag(page_folio(page));
clear_page_dirty_for_io(page);
dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
}
@@ -558,6 +558,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
block_t blkaddr;
int i;
+ ni->flag = 0;
ni->nid = nid;
retry:
/* Check nat cache */
@@ -852,21 +853,29 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
if (is_inode_flag_set(dn->inode, FI_COMPRESSED_FILE) &&
f2fs_sb_has_readonly(sbi)) {
- unsigned int c_len = f2fs_cluster_blocks_are_contiguous(dn);
+ unsigned int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+ unsigned int ofs_in_node = dn->ofs_in_node;
+ pgoff_t fofs = index;
+ unsigned int c_len;
block_t blkaddr;
+ /* should align fofs and ofs_in_node to cluster_size */
+ if (fofs % cluster_size) {
+ fofs = round_down(fofs, cluster_size);
+ ofs_in_node = round_down(ofs_in_node, cluster_size);
+ }
+
+ c_len = f2fs_cluster_blocks_are_contiguous(dn, ofs_in_node);
if (!c_len)
goto out;
- blkaddr = f2fs_data_blkaddr(dn);
+ blkaddr = data_blkaddr(dn->inode, dn->node_page, ofs_in_node);
if (blkaddr == COMPRESS_ADDR)
blkaddr = data_blkaddr(dn->inode, dn->node_page,
- dn->ofs_in_node + 1);
+ ofs_in_node + 1);
f2fs_update_read_extent_tree_range_compressed(dn->inode,
- index, blkaddr,
- F2FS_I(dn->inode)->i_cluster_size,
- c_len);
+ fofs, blkaddr, cluster_size, c_len);
}
out:
return 0;
@@ -897,8 +906,18 @@ static int truncate_node(struct dnode_of_data *dn)
if (err)
return err;
+ if (ni.blk_addr != NEW_ADDR &&
+ !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC_ENHANCE)) {
+ f2fs_err_ratelimited(sbi,
+ "nat entry is corrupted, run fsck to fix it, ino:%u, "
+ "nid:%u, blkaddr:%u", ni.ino, ni.nid, ni.blk_addr);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_NAT);
+ return -EFSCORRUPTED;
+ }
+
/* Deallocate node address */
- f2fs_invalidate_blocks(sbi, ni.blk_addr);
+ f2fs_invalidate_blocks(sbi, ni.blk_addr, 1);
dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);
set_node_addr(sbi, &ni, NULL_ADDR, false);
@@ -911,7 +930,7 @@ static int truncate_node(struct dnode_of_data *dn)
clear_node_page_dirty(dn->node_page);
set_sbi_flag(sbi, SBI_IS_DIRTY);
- index = dn->node_page->index;
+ index = page_folio(dn->node_page)->index;
f2fs_put_page(dn->node_page, 1);
invalidate_mapping_pages(NODE_MAPPING(sbi),
@@ -1048,7 +1067,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn,
int i;
int idx = depth - 2;
- nid[0] = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]);
+ nid[0] = get_nid(dn->inode_page, offset[0], true);
if (!nid[0])
return 0;
@@ -1159,7 +1178,7 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
skip_partial:
while (cont) {
- dn.nid = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]);
+ dn.nid = get_nid(page, offset[0], true);
switch (offset[0]) {
case NODE_DIR1_BLOCK:
case NODE_DIR2_BLOCK:
@@ -1179,15 +1198,22 @@ skip_partial:
default:
BUG();
}
- if (err < 0 && err != -ENOENT)
+ if (err == -ENOENT) {
+ set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
+ f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+ f2fs_err_ratelimited(sbi,
+ "truncate node fail, ino:%lu, nid:%u, "
+ "offset[0]:%d, offset[1]:%d, nofs:%d",
+ inode->i_ino, dn.nid, offset[0],
+ offset[1], nofs);
+ err = 0;
+ }
+ if (err < 0)
goto fail;
- if (offset[1] == 0 &&
- ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
+ if (offset[1] == 0 && get_nid(page, offset[0], true)) {
lock_page(page);
BUG_ON(page->mapping != NODE_MAPPING(sbi));
- f2fs_wait_on_page_writeback(page, NODE, true, true);
- ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
- set_page_dirty(page);
+ set_nid(page, offset[0], 0, true);
unlock_page(page);
}
offset[1] = 0;
@@ -1249,8 +1275,9 @@ int f2fs_remove_inode_page(struct inode *inode)
}
/* remove potential inline_data blocks */
- if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- S_ISLNK(inode->i_mode))
+ if (!IS_DEVICE_ALIASING(inode) &&
+ (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ S_ISLNK(inode->i_mode)))
f2fs_truncate_data_blocks_range(&dn, 1);
/* 0 is possible, after f2fs_new_inode() has failed */
@@ -1311,8 +1338,14 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
}
if (unlikely(new_ni.blk_addr != NULL_ADDR)) {
err = -EFSCORRUPTED;
+ dec_valid_node_count(sbi, dn->inode, !ofs);
set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
+ f2fs_warn_ratelimited(sbi,
+ "f2fs_new_node_page: inconsistent nat entry, "
+ "ino:%u, nid:%u, blkaddr:%u, ver:%u, flag:%u",
+ new_ni.ino, new_ni.nid, new_ni.blk_addr,
+ new_ni.version, new_ni.flag);
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_NAT);
goto fail;
}
#endif
@@ -1337,7 +1370,6 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs)
if (ofs == 0)
inc_valid_inode_count(sbi);
return page;
-
fail:
clear_node_page_dirty(page);
f2fs_put_page(page, 1);
@@ -1351,6 +1383,7 @@ fail:
*/
static int read_node_page(struct page *page, blk_opf_t op_flags)
{
+ struct folio *folio = page_folio(page);
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct node_info ni;
struct f2fs_io_info fio = {
@@ -1363,21 +1396,21 @@ static int read_node_page(struct page *page, blk_opf_t op_flags)
};
int err;
- if (PageUptodate(page)) {
+ if (folio_test_uptodate(folio)) {
if (!f2fs_inode_chksum_verify(sbi, page)) {
- ClearPageUptodate(page);
+ folio_clear_uptodate(folio);
return -EFSBADCRC;
}
return LOCKED_PAGE;
}
- err = f2fs_get_node_info(sbi, page->index, &ni, false);
+ err = f2fs_get_node_info(sbi, folio->index, &ni, false);
if (err)
return err;
/* NEW_ADDR can be seen, after cp_error drops some dirty node pages */
if (unlikely(ni.blk_addr == NULL_ADDR || ni.blk_addr == NEW_ADDR)) {
- ClearPageUptodate(page);
+ folio_clear_uptodate(folio);
return -ENOENT;
}
@@ -1474,7 +1507,7 @@ out_err:
out_put_err:
/* ENOENT comes from read_node_page which is not an error. */
if (err != -ENOENT)
- f2fs_handle_page_eio(sbi, page->index, NODE);
+ f2fs_handle_page_eio(sbi, page_folio(page), NODE);
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
@@ -1517,7 +1550,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
if (!clear_page_dirty_for_io(page))
goto page_out;
- ret = f2fs_write_inline_data(inode, page);
+ ret = f2fs_write_inline_data(inode, page_folio(page));
inode_dec_dirty_pages(inode);
f2fs_remove_dirty_inode(inode);
if (ret)
@@ -1590,6 +1623,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
enum iostat_type io_type, unsigned int *seq_id)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+ struct folio *folio = page_folio(page);
nid_t nid;
struct node_info ni;
struct f2fs_io_info fio = {
@@ -1606,15 +1640,15 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
};
unsigned int seq;
- trace_f2fs_writepage(page, NODE);
+ trace_f2fs_writepage(folio, NODE);
if (unlikely(f2fs_cp_error(sbi))) {
/* keep node pages in remount-ro mode */
if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY)
goto redirty_out;
- ClearPageUptodate(page);
+ folio_clear_uptodate(folio);
dec_page_count(sbi, F2FS_DIRTY_NODES);
- unlock_page(page);
+ folio_unlock(folio);
return 0;
}
@@ -1628,7 +1662,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
/* get old block addr of this node page */
nid = nid_of_node(page);
- f2fs_bug_on(sbi, page->index != nid);
+ f2fs_bug_on(sbi, folio->index != nid);
if (f2fs_get_node_info(sbi, nid, &ni, !do_balance))
goto redirty_out;
@@ -1642,10 +1676,10 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
/* This page is already truncated */
if (unlikely(ni.blk_addr == NULL_ADDR)) {
- ClearPageUptodate(page);
+ folio_clear_uptodate(folio);
dec_page_count(sbi, F2FS_DIRTY_NODES);
f2fs_up_read(&sbi->node_write);
- unlock_page(page);
+ folio_unlock(folio);
return 0;
}
@@ -1656,7 +1690,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
goto redirty_out;
}
- if (atomic && !test_opt(sbi, NOBARRIER) && !f2fs_sb_has_blkzoned(sbi))
+ if (atomic && !test_opt(sbi, NOBARRIER))
fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
/* should add to global list before clearing PAGECACHE status */
@@ -1666,7 +1700,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
*seq_id = seq;
}
- set_page_writeback(page);
+ folio_start_writeback(folio);
fio.old_blkaddr = ni.blk_addr;
f2fs_do_write_node_page(nid, &fio);
@@ -1679,7 +1713,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
submitted = NULL;
}
- unlock_page(page);
+ folio_unlock(folio);
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_submit_merged_write(sbi, NODE);
@@ -1693,7 +1727,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
return 0;
redirty_out:
- redirty_page_for_writepage(wbc, page);
+ folio_redirty_for_writepage(wbc, folio);
return AOP_WRITEPAGE_ACTIVATE;
}
@@ -1725,7 +1759,7 @@ int f2fs_move_node_page(struct page *node_page, int gc_type)
goto release_page;
} else {
/* set page dirty and write it */
- if (!PageWriteback(node_page))
+ if (!folio_test_writeback(page_folio(node_page)))
set_page_dirty(node_page);
}
out_page:
@@ -1849,7 +1883,7 @@ continue_unlock:
}
if (!ret && atomic && !marked) {
f2fs_debug(sbi, "Retry to write fsync mark: ino=%u, idx=%lx",
- ino, last_page->index);
+ ino, page_folio(last_page)->index);
lock_page(last_page);
f2fs_wait_on_page_writeback(last_page, NODE, true, true);
set_page_dirty(last_page);
@@ -1919,7 +1953,7 @@ void f2fs_flush_inline_data(struct f2fs_sb_info *sbi)
for (i = 0; i < nr_folios; i++) {
struct page *page = &fbatch.folios[i]->page;
- if (!IS_DNODE(page))
+ if (!IS_INODE(page))
continue;
lock_page(page);
@@ -2153,7 +2187,7 @@ skip_write:
static bool f2fs_dirty_node_folio(struct address_space *mapping,
struct folio *folio)
{
- trace_f2fs_set_page_dirty(&folio->page, NODE);
+ trace_f2fs_set_page_dirty(folio, NODE);
if (!folio_test_uptodate(folio))
folio_mark_uptodate(folio);
@@ -2731,7 +2765,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
if (err)
return err;
- f2fs_invalidate_blocks(sbi, ni.blk_addr);
+ f2fs_invalidate_blocks(sbi, ni.blk_addr, 1);
dec_valid_node_count(sbi, inode, false);
set_node_addr(sbi, &ni, NULL_ADDR, false);
@@ -2841,7 +2875,7 @@ int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
int i, idx, last_offset, nrpages;
/* scan the node segment */
- last_offset = sbi->blocks_per_seg;
+ last_offset = BLKS_PER_SEG(sbi);
addr = START_BLOCK(sbi, segno);
sum_entry = &sum->entries[0];
@@ -3148,7 +3182,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8);
nm_i->nat_bits = f2fs_kvzalloc(sbi,
- nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL);
+ F2FS_BLK_TO_BYTES(nm_i->nat_bits_blocks), GFP_KERNEL);
if (!nm_i->nat_bits)
return -ENOMEM;
@@ -3158,7 +3192,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
return 0;
- nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg -
+ nat_bits_addr = __start_cp_addr(sbi) + BLKS_PER_SEG(sbi) -
nm_i->nat_bits_blocks;
for (i = 0; i < nm_i->nat_bits_blocks; i++) {
struct page *page;
@@ -3167,7 +3201,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
if (IS_ERR(page))
return PTR_ERR(page);
- memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS),
+ memcpy(nm_i->nat_bits + F2FS_BLK_TO_BYTES(i),
page_address(page), F2FS_BLKSIZE);
f2fs_put_page(page, 1);
}
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 5bd16a95eef8..6aea13024ac1 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -208,10 +208,10 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
block_addr = (pgoff_t)(nm_i->nat_blkaddr +
(block_off << 1) -
- (block_off & (sbi->blocks_per_seg - 1)));
+ (block_off & (BLKS_PER_SEG(sbi) - 1)));
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
- block_addr += sbi->blocks_per_seg;
+ block_addr += BLKS_PER_SEG(sbi);
return block_addr;
}
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index d0f24ccbd1ac..69a2027e3ebc 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -5,7 +5,7 @@
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/sched/mm.h>
@@ -46,10 +46,6 @@
static struct kmem_cache *fsync_entry_slab;
-#if IS_ENABLED(CONFIG_UNICODE)
-extern struct kmem_cache *f2fs_cf_name_slab;
-#endif
-
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
{
s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
@@ -153,11 +149,8 @@ static int init_recovered_filename(const struct inode *dir,
if (err)
return err;
f2fs_hash_filename(dir, fname);
-#if IS_ENABLED(CONFIG_UNICODE)
/* Case-sensitive match is fine for recovery */
- kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
- fname->cf_name.name = NULL;
-#endif
+ f2fs_free_casefolded_name(fname);
} else {
f2fs_hash_filename(dir, fname);
}
@@ -287,6 +280,7 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri)
static int recover_inode(struct inode *inode, struct page *page)
{
struct f2fs_inode *raw = F2FS_INODE(page);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
char *name;
int err;
@@ -309,12 +303,12 @@ static int recover_inode(struct inode *inode, struct page *page)
i_projid = (projid_t)le32_to_cpu(raw->i_projid);
kprojid = make_kprojid(&init_user_ns, i_projid);
- if (!projid_eq(kprojid, F2FS_I(inode)->i_projid)) {
+ if (!projid_eq(kprojid, fi->i_projid)) {
err = f2fs_transfer_project_quota(inode,
kprojid);
if (err)
return err;
- F2FS_I(inode)->i_projid = kprojid;
+ fi->i_projid = kprojid;
}
}
}
@@ -327,11 +321,10 @@ static int recover_inode(struct inode *inode, struct page *page)
inode_set_mtime(inode, le64_to_cpu(raw->i_mtime),
le32_to_cpu(raw->i_mtime_nsec));
- F2FS_I(inode)->i_advise = raw->i_advise;
- F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags);
+ fi->i_advise = raw->i_advise;
+ fi->i_flags = le32_to_cpu(raw->i_flags);
f2fs_set_inode_flags(inode);
- F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] =
- le16_to_cpu(raw->i_gc_failures);
+ fi->i_gc_failures = le16_to_cpu(raw->i_gc_failures);
recover_inline_flags(inode, raw);
@@ -354,7 +347,7 @@ static unsigned int adjust_por_ra_blocks(struct f2fs_sb_info *sbi,
if (blkaddr + 1 == next_blkaddr)
ra_blocks = min_t(unsigned int, RECOVERY_MAX_RA_BLOCKS,
ra_blocks * 2);
- else if (next_blkaddr % sbi->blocks_per_seg)
+ else if (next_blkaddr % BLKS_PER_SEG(sbi))
ra_blocks = max_t(unsigned int, RECOVERY_MIN_RA_BLOCKS,
ra_blocks / 2);
return ra_blocks;
@@ -611,6 +604,19 @@ truncate_out:
return 0;
}
+static int f2fs_reserve_new_block_retry(struct dnode_of_data *dn)
+{
+ int i, err = 0;
+
+ for (i = DEFAULT_FAILURE_RETRY_COUNT; i > 0; i--) {
+ err = f2fs_reserve_new_block(dn);
+ if (!err)
+ break;
+ }
+
+ return err;
+}
+
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page)
{
@@ -680,14 +686,12 @@ 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;
}
@@ -712,14 +716,8 @@ retry_dn:
*/
if (dest == NEW_ADDR) {
f2fs_truncate_data_blocks_range(&dn, 1);
- do {
- err = f2fs_reserve_new_block(&dn);
- if (err == -ENOSPC) {
- f2fs_bug_on(sbi, 1);
- break;
- }
- } while (err &&
- IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION));
+
+ err = f2fs_reserve_new_block_retry(&dn);
if (err)
goto err;
continue;
@@ -727,16 +725,8 @@ retry_dn:
/* dest is valid block, try to recover from src to dest */
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
-
if (src == NULL_ADDR) {
- do {
- err = f2fs_reserve_new_block(&dn);
- if (err == -ENOSPC) {
- f2fs_bug_on(sbi, 1);
- break;
- }
- } while (err &&
- IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION));
+ err = f2fs_reserve_new_block_retry(&dn);
if (err)
goto err;
}
@@ -756,8 +746,6 @@ retry_prev:
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;
}
@@ -852,7 +840,7 @@ next:
f2fs_ra_meta_pages_cond(sbi, blkaddr, ra_blocks);
}
if (!err)
- f2fs_allocate_new_segments(sbi);
+ err = f2fs_allocate_new_segments(sbi);
return err;
}
@@ -864,7 +852,6 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
int ret = 0;
unsigned long s_flags = sbi->sb->s_flags;
bool need_writecp = false;
- bool fix_curseg_write_pointer = false;
if (is_sbi_flag_set(sbi, SBI_IS_WRITABLE))
f2fs_info(sbi, "recover fsync data on readonly fs");
@@ -895,8 +882,6 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
else
f2fs_bug_on(sbi, sbi->sb->s_flags & SB_ACTIVE);
skip:
- fix_curseg_write_pointer = !check_only || list_empty(&inode_list);
-
destroy_fsync_dnodes(&inode_list, err);
destroy_fsync_dnodes(&tmp_inode_list, err);
@@ -914,13 +899,8 @@ skip:
* and the f2fs is not read only, check and fix zoned block devices'
* write pointer consistency.
*/
- if (!err && fix_curseg_write_pointer && !f2fs_readonly(sbi->sb) &&
- f2fs_sb_has_blkzoned(sbi)) {
- err = f2fs_fix_curseg_write_pointer(sbi);
- if (!err)
- err = f2fs_check_write_pointer(sbi);
- ret = err;
- }
+ if (!err)
+ err = f2fs_check_and_fix_write_pointer(sbi);
if (!err)
clear_sbi_flag(sbi, SBI_POR_DOING);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 4c8836ded90f..c282e8a0a2ec 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -192,16 +192,28 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
if (!f2fs_is_atomic_file(inode))
return;
+ if (clean)
+ truncate_inode_pages_final(inode->i_mapping);
+
release_atomic_write_cnt(inode);
clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
clear_inode_flag(inode, FI_ATOMIC_REPLACE);
clear_inode_flag(inode, FI_ATOMIC_FILE);
+ if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
+ clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
+ /*
+ * The vfs inode keeps clean during commit, but the f2fs inode
+ * doesn't. So clear the dirty state after commit and let
+ * f2fs_mark_inode_dirty_sync ensure a consistent dirty state.
+ */
+ f2fs_inode_synced(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
+ }
stat_dec_atomic_inode(inode);
F2FS_I(inode)->atomic_write_task = NULL;
if (clean) {
- truncate_inode_pages_final(inode->i_mapping);
f2fs_i_size_write(inode, fi->original_i_size);
fi->original_i_size = 0;
}
@@ -239,7 +251,7 @@ retry:
if (!__is_valid_data_blkaddr(new_addr)) {
if (new_addr == NULL_ADDR)
dec_valid_block_count(sbi, inode, 1);
- f2fs_invalidate_blocks(sbi, dn.data_blkaddr);
+ f2fs_invalidate_blocks(sbi, dn.data_blkaddr, 1);
f2fs_update_data_blkaddr(&dn, new_addr);
} else {
f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
@@ -248,7 +260,7 @@ retry:
} else {
blkcnt_t count = 1;
- err = inc_valid_block_count(sbi, inode, &count);
+ err = inc_valid_block_count(sbi, inode, &count, true);
if (err) {
f2fs_put_dnode(&dn);
return err;
@@ -334,8 +346,6 @@ 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;
}
@@ -366,6 +376,10 @@ out:
} else {
sbi->committed_atomic_block += fi->atomic_write_cnt;
set_inode_flag(inode, FI_ATOMIC_COMMITTED);
+ if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
+ clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
+ f2fs_mark_inode_dirty_sync(inode, true);
+ }
}
__complete_revoke_list(inode, &revoke_list, ret ? true : false);
@@ -400,6 +414,9 @@ int f2fs_commit_atomic_write(struct inode *inode)
*/
void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
+ if (f2fs_cp_error(sbi))
+ return;
+
if (time_to_inject(sbi, FAULT_CHECKPOINT))
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_FAULT_INJECT);
@@ -448,8 +465,8 @@ static inline bool excess_dirty_threshold(struct f2fs_sb_info *sbi)
unsigned int nodes = get_pages(sbi, F2FS_DIRTY_NODES);
unsigned int meta = get_pages(sbi, F2FS_DIRTY_META);
unsigned int imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
- unsigned int threshold = sbi->blocks_per_seg * factor *
- DEFAULT_DIRTY_THRESHOLD;
+ unsigned int threshold =
+ SEGS_TO_BLKS(sbi, (factor * DEFAULT_DIRTY_THRESHOLD));
unsigned int global_threshold = threshold * 3 / 2;
if (dents >= threshold || qdata >= threshold ||
@@ -768,8 +785,10 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
block_t valid_blocks =
get_valid_blocks(sbi, segno, true);
- f2fs_bug_on(sbi, unlikely(!valid_blocks ||
- valid_blocks == CAP_BLKS_PER_SEC(sbi)));
+ f2fs_bug_on(sbi,
+ (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) &&
+ !valid_blocks) ||
+ valid_blocks == CAP_BLKS_PER_SEC(sbi));
if (!IS_CURSEC(sbi, secno))
set_bit(secno, dirty_i->dirty_secmap);
@@ -872,7 +891,7 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi)
{
int ovp_hole_segs =
(overprovision_segments(sbi) - reserved_segments(sbi));
- block_t ovp_holes = ovp_hole_segs << sbi->log_blocks_per_seg;
+ block_t ovp_holes = SEGS_TO_BLKS(sbi, ovp_hole_segs);
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
block_t holes[2] = {0, 0}; /* DATA and NODE */
block_t unusable;
@@ -901,11 +920,16 @@ int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable)
{
int ovp_hole_segs =
(overprovision_segments(sbi) - reserved_segments(sbi));
+
+ if (F2FS_OPTION(sbi).unusable_cap_perc == 100)
+ return 0;
if (unusable > F2FS_OPTION(sbi).unusable_cap)
return -EAGAIN;
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) &&
dirty_segments(sbi) > ovp_hole_segs)
return -EAGAIN;
+ if (has_not_enough_free_secs(sbi, 0, 0))
+ return -EAGAIN;
return 0;
}
@@ -1101,9 +1125,8 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
dc->error = 0;
if (dc->error)
- printk_ratelimited(
- "%sF2FS-fs (%s): Issue discard(%u, %u, %u) failed, ret: %d",
- KERN_INFO, sbi->sb->s_id,
+ f2fs_info_ratelimited(sbi,
+ "Issue discard(%u, %u, %u) failed, ret: %d",
dc->di.lstart, dc->di.start, dc->di.len, dc->error);
__detach_discard_cmd(dcc, dc);
}
@@ -1132,8 +1155,7 @@ static void __check_sit_bitmap(struct f2fs_sb_info *sbi,
struct seg_entry *sentry;
unsigned int segno;
block_t blk = start;
- unsigned long offset, size, max_blocks = sbi->blocks_per_seg;
- unsigned long *map;
+ unsigned long offset, size, *map;
while (blk < end) {
segno = GET_SEGNO(sbi, blk);
@@ -1143,7 +1165,7 @@ static void __check_sit_bitmap(struct f2fs_sb_info *sbi,
if (end < START_BLOCK(sbi, segno + 1))
size = GET_BLKOFF_FROM_SEG0(sbi, end);
else
- size = max_blocks;
+ size = BLKS_PER_SEG(sbi);
map = (unsigned long *)(sentry->cur_valid_map);
offset = __find_rev_next_bit(map, size, offset);
f2fs_bug_on(sbi, offset != size);
@@ -1277,6 +1299,15 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
}
#endif
+ /*
+ * stop issuing discard for any of below cases:
+ * 1. device is conventional zone, but it doesn't support discard.
+ * 2. device is regulare device, after snapshot it doesn't support
+ * discard.
+ */
+ if (!bdev_max_discard_sectors(bdev))
+ return -EOPNOTSUPP;
+
trace_f2fs_issue_discard(bdev, dc->di.start, dc->di.len);
lstart = dc->di.lstart;
@@ -1971,9 +2002,15 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
}
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) {
+ unsigned int nofs_flags;
+ int ret;
+
trace_f2fs_issue_reset_zone(bdev, blkstart);
- return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
- sector, nr_sects, GFP_NOFS);
+ nofs_flags = memalloc_nofs_save();
+ ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+ sector, nr_sects);
+ memalloc_nofs_restore(nofs_flags);
+ return ret;
}
__queue_zone_reset_cmd(sbi, bdev, blkstart, lblkstart, blklen);
@@ -2042,7 +2079,6 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
bool check_only)
{
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
- int max_blocks = sbi->blocks_per_seg;
struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
@@ -2054,8 +2090,9 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
struct list_head *head = &SM_I(sbi)->dcc_info->entry_list;
int i;
- if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi) ||
- !f2fs_block_unit_discard(sbi))
+ if (se->valid_blocks == BLKS_PER_SEG(sbi) ||
+ !f2fs_hw_support_discard(sbi) ||
+ !f2fs_block_unit_discard(sbi))
return false;
if (!force) {
@@ -2072,13 +2109,14 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
while (force || SM_I(sbi)->dcc_info->nr_discards <=
SM_I(sbi)->dcc_info->max_discards) {
- start = __find_rev_next_bit(dmap, max_blocks, end + 1);
- if (start >= max_blocks)
+ start = __find_rev_next_bit(dmap, BLKS_PER_SEG(sbi), end + 1);
+ if (start >= BLKS_PER_SEG(sbi))
break;
- end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
- if (force && start && end != max_blocks
- && (end - start) < cpc->trim_minlen)
+ end = __find_rev_next_zero_bit(dmap,
+ BLKS_PER_SEG(sbi), start + 1);
+ if (force && start && end != BLKS_PER_SEG(sbi) &&
+ (end - start) < cpc->trim_minlen)
continue;
if (check_only)
@@ -2160,8 +2198,8 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
start + 1);
if (section_alignment) {
- start = rounddown(start, sbi->segs_per_sec);
- end = roundup(end, sbi->segs_per_sec);
+ start = rounddown(start, SEGS_PER_SEC(sbi));
+ end = roundup(end, SEGS_PER_SEC(sbi));
}
for (i = start; i < end; i++) {
@@ -2180,7 +2218,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
if (!f2fs_sb_has_blkzoned(sbi) &&
(!f2fs_lfs_mode(sbi) || !__is_large_section(sbi))) {
f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
- (end - start) << sbi->log_blocks_per_seg);
+ SEGS_TO_BLKS(sbi, end - start));
continue;
}
next:
@@ -2189,9 +2227,9 @@ next:
if (!IS_CURSEC(sbi, secno) &&
!get_valid_blocks(sbi, start, true))
f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
- sbi->segs_per_sec << sbi->log_blocks_per_seg);
+ BLKS_PER_SEC(sbi));
- start = start_segno + sbi->segs_per_sec;
+ start = start_segno + SEGS_PER_SEC(sbi);
if (start < end)
goto next;
else
@@ -2210,7 +2248,7 @@ next:
find_next:
if (is_valid) {
next_pos = find_next_zero_bit_le(entry->discard_map,
- sbi->blocks_per_seg, cur_pos);
+ BLKS_PER_SEG(sbi), cur_pos);
len = next_pos - cur_pos;
if (f2fs_sb_has_blkzoned(sbi) ||
@@ -2222,13 +2260,13 @@ find_next:
total_len += len;
} else {
next_pos = find_next_bit_le(entry->discard_map,
- sbi->blocks_per_seg, cur_pos);
+ BLKS_PER_SEG(sbi), cur_pos);
}
skip:
cur_pos = next_pos;
is_valid = !is_valid;
- if (cur_pos < sbi->blocks_per_seg)
+ if (cur_pos < BLKS_PER_SEG(sbi))
goto find_next;
release_discard_addr(entry);
@@ -2245,6 +2283,12 @@ int f2fs_start_discard_thread(struct f2fs_sb_info *sbi)
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
int err = 0;
+ if (f2fs_sb_has_readonly(sbi)) {
+ f2fs_info(sbi,
+ "Skip to start discard thread for readonly image");
+ return 0;
+ }
+
if (!f2fs_realtime_discard_enable(sbi))
return 0;
@@ -2277,7 +2321,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
dcc->max_ordered_discard = DEFAULT_MAX_ORDERED_DISCARD_GRANULARITY;
dcc->discard_io_aware = DPOLICY_IO_AWARE_ENABLE;
if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT)
- dcc->discard_granularity = sbi->blocks_per_seg;
+ dcc->discard_granularity = BLKS_PER_SEG(sbi);
else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
dcc->discard_granularity = BLKS_PER_SEC(sbi);
@@ -2291,7 +2335,7 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
atomic_set(&dcc->queued_discard, 0);
atomic_set(&dcc->discard_cmd_cnt, 0);
dcc->nr_discards = 0;
- dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
+ dcc->max_discards = SEGS_TO_BLKS(sbi, MAIN_SEGS(sbi));
dcc->max_discard_request = DEF_MAX_DISCARD_REQUEST;
dcc->min_discard_issue_time = DEF_MIN_DISCARD_ISSUE_TIME;
dcc->mid_discard_issue_time = DEF_MID_DISCARD_ISSUE_TIME;
@@ -2388,76 +2432,38 @@ static void update_segment_mtime(struct f2fs_sb_info *sbi, block_t blkaddr,
SIT_I(sbi)->max_mtime = ctime;
}
-static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
+/*
+ * NOTE: when updating multiple blocks at the same time, please ensure
+ * that the consecutive input blocks belong to the same segment.
+ */
+static int update_sit_entry_for_release(struct f2fs_sb_info *sbi, struct seg_entry *se,
+ block_t blkaddr, unsigned int offset, int del)
{
- struct seg_entry *se;
- unsigned int segno, offset;
- long int new_vblocks;
bool exist;
#ifdef CONFIG_F2FS_CHECK_FS
bool mir_exist;
#endif
+ int i;
+ int del_count = -del;
- segno = GET_SEGNO(sbi, blkaddr);
-
- se = get_seg_entry(sbi, segno);
- new_vblocks = se->valid_blocks + del;
- offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
-
- f2fs_bug_on(sbi, (new_vblocks < 0 ||
- (new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
-
- se->valid_blocks = new_vblocks;
-
- /* Update valid block bitmap */
- if (del > 0) {
- exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
-#ifdef CONFIG_F2FS_CHECK_FS
- mir_exist = f2fs_test_and_set_bit(offset,
- se->cur_valid_map_mir);
- if (unlikely(exist != mir_exist)) {
- f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
- blkaddr, exist);
- f2fs_bug_on(sbi, 1);
- }
-#endif
- if (unlikely(exist)) {
- f2fs_err(sbi, "Bitmap was wrongly set, blk:%u",
- blkaddr);
- f2fs_bug_on(sbi, 1);
- se->valid_blocks--;
- del = 0;
- }
-
- if (f2fs_block_unit_discard(sbi) &&
- !f2fs_test_and_set_bit(offset, se->discard_map))
- sbi->discard_blks--;
+ f2fs_bug_on(sbi, GET_SEGNO(sbi, blkaddr) != GET_SEGNO(sbi, blkaddr + del_count - 1));
- /*
- * SSR should never reuse block which is checkpointed
- * or newly invalidated.
- */
- if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
- if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
- se->ckpt_valid_blocks++;
- }
- } else {
- exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
+ for (i = 0; i < del_count; i++) {
+ exist = f2fs_test_and_clear_bit(offset + i, se->cur_valid_map);
#ifdef CONFIG_F2FS_CHECK_FS
- mir_exist = f2fs_test_and_clear_bit(offset,
+ mir_exist = f2fs_test_and_clear_bit(offset + i,
se->cur_valid_map_mir);
if (unlikely(exist != mir_exist)) {
f2fs_err(sbi, "Inconsistent error when clearing bitmap, blk:%u, old bit:%d",
- blkaddr, exist);
+ blkaddr + i, exist);
f2fs_bug_on(sbi, 1);
}
#endif
if (unlikely(!exist)) {
- f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u",
- blkaddr);
+ f2fs_err(sbi, "Bitmap was wrongly cleared, blk:%u", blkaddr + i);
f2fs_bug_on(sbi, 1);
se->valid_blocks++;
- del = 0;
+ del += 1;
} else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
/*
* If checkpoints are off, we must not reuse data that
@@ -2465,7 +2471,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
* before, we must track that to know how much space we
* really have.
*/
- if (f2fs_test_bit(offset, se->ckpt_valid_map)) {
+ if (f2fs_test_bit(offset + i, se->ckpt_valid_map)) {
spin_lock(&sbi->stat_lock);
sbi->unusable_block_count++;
spin_unlock(&sbi->stat_lock);
@@ -2473,12 +2479,91 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
}
if (f2fs_block_unit_discard(sbi) &&
- f2fs_test_and_clear_bit(offset, se->discard_map))
+ f2fs_test_and_clear_bit(offset + i, se->discard_map))
sbi->discard_blks++;
+
+ if (!f2fs_test_bit(offset + i, se->ckpt_valid_map))
+ se->ckpt_valid_blocks -= 1;
}
+
+ return del;
+}
+
+static int update_sit_entry_for_alloc(struct f2fs_sb_info *sbi, struct seg_entry *se,
+ block_t blkaddr, unsigned int offset, int del)
+{
+ bool exist;
+#ifdef CONFIG_F2FS_CHECK_FS
+ bool mir_exist;
+#endif
+
+ exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+ mir_exist = f2fs_test_and_set_bit(offset,
+ se->cur_valid_map_mir);
+ if (unlikely(exist != mir_exist)) {
+ f2fs_err(sbi, "Inconsistent error when setting bitmap, blk:%u, old bit:%d",
+ blkaddr, exist);
+ f2fs_bug_on(sbi, 1);
+ }
+#endif
+ if (unlikely(exist)) {
+ f2fs_err(sbi, "Bitmap was wrongly set, blk:%u", blkaddr);
+ f2fs_bug_on(sbi, 1);
+ se->valid_blocks--;
+ del = 0;
+ }
+
+ if (f2fs_block_unit_discard(sbi) &&
+ !f2fs_test_and_set_bit(offset, se->discard_map))
+ sbi->discard_blks--;
+
+ /*
+ * SSR should never reuse block which is checkpointed
+ * or newly invalidated.
+ */
+ if (!is_sbi_flag_set(sbi, SBI_CP_DISABLED)) {
+ if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+ se->ckpt_valid_blocks++;
+ }
+
if (!f2fs_test_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks += del;
+ return del;
+}
+
+/*
+ * If releasing blocks, this function supports updating multiple consecutive blocks
+ * at one time, but please note that these consecutive blocks need to belong to the
+ * same segment.
+ */
+static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
+{
+ struct seg_entry *se;
+ unsigned int segno, offset;
+ long int new_vblocks;
+
+ segno = GET_SEGNO(sbi, blkaddr);
+ if (segno == NULL_SEGNO)
+ return;
+
+ se = get_seg_entry(sbi, segno);
+ new_vblocks = se->valid_blocks + del;
+ offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+ f2fs_bug_on(sbi, (new_vblocks < 0 ||
+ (new_vblocks > f2fs_usable_blks_in_seg(sbi, segno))));
+
+ se->valid_blocks = new_vblocks;
+
+ /* Update valid block bitmap */
+ if (del > 0) {
+ del = update_sit_entry_for_alloc(sbi, se, blkaddr, offset, del);
+ } else {
+ del = update_sit_entry_for_release(sbi, se, blkaddr, offset, del);
+ }
+
__mark_sit_entry_dirty(sbi, segno);
/* update total number of valid blocks to be written in ckpt area */
@@ -2488,25 +2573,43 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
get_sec_entry(sbi, segno)->valid_blocks += del;
}
-void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
+void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr,
+ unsigned int len)
{
unsigned int segno = GET_SEGNO(sbi, addr);
struct sit_info *sit_i = SIT_I(sbi);
+ block_t addr_start = addr, addr_end = addr + len - 1;
+ unsigned int seg_num = GET_SEGNO(sbi, addr_end) - segno + 1;
+ unsigned int i = 1, max_blocks = sbi->blocks_per_seg, cnt;
f2fs_bug_on(sbi, addr == NULL_ADDR);
if (addr == NEW_ADDR || addr == COMPRESS_ADDR)
return;
- f2fs_invalidate_internal_cache(sbi, addr);
+ f2fs_invalidate_internal_cache(sbi, addr, len);
/* add it into sit main buffer */
down_write(&sit_i->sentry_lock);
- update_segment_mtime(sbi, addr, 0);
- update_sit_entry(sbi, addr, -1);
+ if (seg_num == 1)
+ cnt = len;
+ else
+ cnt = max_blocks - GET_BLKOFF_FROM_SEG0(sbi, addr);
- /* add it into dirty seglist */
- locate_dirty_segment(sbi, segno);
+ do {
+ update_segment_mtime(sbi, addr_start, 0);
+ update_sit_entry(sbi, addr_start, -cnt);
+
+ /* add it into dirty seglist */
+ locate_dirty_segment(sbi, segno);
+
+ /* update @addr_start and @cnt and @segno */
+ addr_start = START_BLOCK(sbi, ++segno);
+ if (++i == seg_num)
+ cnt = GET_BLKOFF_FROM_SEG0(sbi, addr_end) + 1;
+ else
+ cnt = max_blocks;
+ } while (i <= seg_num);
up_write(&sit_i->sentry_lock);
}
@@ -2540,7 +2643,7 @@ static unsigned short f2fs_curseg_valid_blocks(struct f2fs_sb_info *sbi, int typ
struct curseg_info *curseg = CURSEG_I(sbi, type);
if (sbi->ckpt->alloc_type[type] == SSR)
- return sbi->blocks_per_seg;
+ return BLKS_PER_SEG(sbi);
return curseg->next_blkoff;
}
@@ -2623,12 +2726,12 @@ static void write_current_sum_page(struct f2fs_sb_info *sbi,
}
static int is_next_segment_free(struct f2fs_sb_info *sbi,
- struct curseg_info *curseg, int type)
+ struct curseg_info *curseg)
{
unsigned int segno = curseg->segno + 1;
struct free_segmap_info *free_i = FREE_I(sbi);
- if (segno < MAIN_SEGS(sbi) && segno % sbi->segs_per_sec)
+ if (segno < MAIN_SEGS(sbi) && segno % SEGS_PER_SEC(sbi))
return !test_bit(segno, free_i->free_segmap);
return 0;
}
@@ -2637,54 +2740,76 @@ static int is_next_segment_free(struct f2fs_sb_info *sbi,
* Find a new segment from the free segments bitmap to right order
* This function should be returned with success, otherwise BUG
*/
-static void get_new_segment(struct f2fs_sb_info *sbi,
- unsigned int *newseg, bool new_sec, int dir)
+static int get_new_segment(struct f2fs_sb_info *sbi,
+ unsigned int *newseg, bool new_sec, bool pinning)
{
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int segno, secno, zoneno;
unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg);
unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg);
- unsigned int left_start = hint;
bool init = true;
- int go_left = 0;
int i;
+ int ret = 0;
spin_lock(&free_i->segmap_lock);
- if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
+ if (time_to_inject(sbi, FAULT_NO_SEGMENT)) {
+ ret = -ENOSPC;
+ goto out_unlock;
+ }
+
+ if (!new_sec && ((*newseg + 1) % SEGS_PER_SEC(sbi))) {
segno = find_next_zero_bit(free_i->free_segmap,
GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1);
if (segno < GET_SEG_FROM_SEC(sbi, hint + 1))
goto got_it;
}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+ /*
+ * If we format f2fs on zoned storage, let's try to get pinned sections
+ * from beginning of the storage, which should be a conventional one.
+ */
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ /* Prioritize writing to conventional zones */
+ if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV || pinning)
+ segno = 0;
+ else
+ segno = max(sbi->first_zoned_segno, *newseg);
+ hint = GET_SEC_FROM_SEG(sbi, segno);
+ }
+#endif
+
find_other_zone:
secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
- if (secno >= MAIN_SECS(sbi)) {
- if (dir == ALLOC_RIGHT) {
+
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (secno >= MAIN_SECS(sbi) && f2fs_sb_has_blkzoned(sbi)) {
+ /* Write only to sequential zones */
+ if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_ONLY_SEQ) {
+ hint = GET_SEC_FROM_SEG(sbi, sbi->first_zoned_segno);
+ secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
+ } else
secno = find_first_zero_bit(free_i->free_secmap,
- MAIN_SECS(sbi));
- f2fs_bug_on(sbi, secno >= MAIN_SECS(sbi));
- } else {
- go_left = 1;
- left_start = hint - 1;
+ MAIN_SECS(sbi));
+ if (secno >= MAIN_SECS(sbi)) {
+ ret = -ENOSPC;
+ f2fs_bug_on(sbi, 1);
+ goto out_unlock;
}
}
- if (go_left == 0)
- goto skip_left;
+#endif
- while (test_bit(left_start, free_i->free_secmap)) {
- if (left_start > 0) {
- left_start--;
- continue;
- }
- left_start = find_first_zero_bit(free_i->free_secmap,
+ if (secno >= MAIN_SECS(sbi)) {
+ secno = find_first_zero_bit(free_i->free_secmap,
MAIN_SECS(sbi));
- f2fs_bug_on(sbi, left_start >= MAIN_SECS(sbi));
- break;
+ if (secno >= MAIN_SECS(sbi)) {
+ ret = -ENOSPC;
+ f2fs_bug_on(sbi, 1);
+ goto out_unlock;
+ }
}
- secno = left_start;
-skip_left:
segno = GET_SEG_FROM_SEC(sbi, secno);
zoneno = GET_ZONE_FROM_SEC(sbi, secno);
@@ -2695,21 +2820,13 @@ skip_left:
goto got_it;
if (zoneno == old_zoneno)
goto got_it;
- if (dir == ALLOC_LEFT) {
- if (!go_left && zoneno + 1 >= total_zones)
- goto got_it;
- if (go_left && zoneno == 0)
- goto got_it;
- }
for (i = 0; i < NR_CURSEG_TYPE; i++)
if (CURSEG_I(sbi, i)->zone == zoneno)
break;
if (i < NR_CURSEG_TYPE) {
/* zone is in user, try another */
- if (go_left)
- hint = zoneno * sbi->secs_per_zone - 1;
- else if (zoneno + 1 >= total_zones)
+ if (zoneno + 1 >= total_zones)
hint = 0;
else
hint = (zoneno + 1) * sbi->secs_per_zone;
@@ -2719,9 +2836,21 @@ skip_left:
got_it:
/* set it as dirty segment in free segmap */
f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
+
+ /* no free section in conventional zone */
+ if (new_sec && pinning &&
+ !f2fs_valid_pinned_area(sbi, START_BLOCK(sbi, segno))) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
__set_inuse(sbi, segno);
*newseg = segno;
+out_unlock:
spin_unlock(&free_i->segmap_lock);
+
+ if (ret == -ENOSPC)
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT);
+ return ret;
}
static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
@@ -2730,6 +2859,10 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
struct summary_footer *sum_footer;
unsigned short seg_type = curseg->seg_type;
+ /* only happen when get_new_segment() fails */
+ if (curseg->next_segno == NULL_SEGNO)
+ return;
+
curseg->inited = true;
curseg->segno = curseg->next_segno;
curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno);
@@ -2754,12 +2887,19 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
unsigned short seg_type = curseg->seg_type;
sanity_check_seg_type(sbi, seg_type);
- if (f2fs_need_rand_seg(sbi))
- return get_random_u32_below(MAIN_SECS(sbi) * sbi->segs_per_sec);
+ if (__is_large_section(sbi)) {
+ if (f2fs_need_rand_seg(sbi)) {
+ unsigned int hint = GET_SEC_FROM_SEG(sbi, curseg->segno);
- /* if segs_per_sec is large than 1, we need to keep original policy. */
- if (__is_large_section(sbi))
+ if (GET_SEC_FROM_SEG(sbi, curseg->segno + 1) != hint)
+ return curseg->segno;
+ return get_random_u32_inclusive(curseg->segno + 1,
+ GET_SEG_FROM_SEC(sbi, hint + 1) - 1);
+ }
return curseg->segno;
+ } else if (f2fs_need_rand_seg(sbi)) {
+ return get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi));
+ }
/* inmem log may not locate on any segment after mount */
if (!curseg->inited)
@@ -2768,8 +2908,7 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return 0;
- if (test_opt(sbi, NOHEAP) &&
- (seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type)))
+ if (seg_type == CURSEG_HOT_DATA || IS_NODESEG(seg_type))
return 0;
if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
@@ -2786,30 +2925,31 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
* Allocate a current working segment.
* This function always allocates a free segment in LFS manner.
*/
-static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
+static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned short seg_type = curseg->seg_type;
unsigned int segno = curseg->segno;
- int dir = ALLOC_LEFT;
+ bool pinning = type == CURSEG_COLD_DATA_PINNED;
+ int ret;
if (curseg->inited)
- write_sum_page(sbi, curseg->sum_blk,
- GET_SUM_BLOCK(sbi, segno));
- if (seg_type == CURSEG_WARM_DATA || seg_type == CURSEG_COLD_DATA)
- dir = ALLOC_RIGHT;
-
- if (test_opt(sbi, NOHEAP))
- dir = ALLOC_RIGHT;
+ write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, segno));
segno = __get_next_segno(sbi, type);
- get_new_segment(sbi, &segno, new_sec, dir);
+ ret = get_new_segment(sbi, &segno, new_sec, pinning);
+ if (ret) {
+ if (ret == -ENOSPC)
+ curseg->segno = NULL_SEGNO;
+ return ret;
+ }
+
curseg->next_segno = segno;
reset_curseg(sbi, type, 1);
curseg->alloc_type = LFS;
if (F2FS_OPTION(sbi).fs_mode == FS_MODE_FRAGMENT_BLK)
curseg->fragment_remained_chunk =
get_random_u32_inclusive(1, sbi->max_fragment_chunk);
+ return 0;
}
static int __next_free_blkoff(struct f2fs_sb_info *sbi,
@@ -2825,7 +2965,7 @@ static int __next_free_blkoff(struct f2fs_sb_info *sbi,
for (i = 0; i < entries; i++)
target_map[i] = ckpt_map[i] | cur_map[i];
- return __find_rev_next_zero_bit(target_map, sbi->blocks_per_seg, start);
+ return __find_rev_next_zero_bit(target_map, BLKS_PER_SEG(sbi), start);
}
static int f2fs_find_next_ssr_block(struct f2fs_sb_info *sbi,
@@ -2836,14 +2976,14 @@ static int f2fs_find_next_ssr_block(struct f2fs_sb_info *sbi,
bool f2fs_segment_has_free_slot(struct f2fs_sb_info *sbi, int segno)
{
- return __next_free_blkoff(sbi, segno, 0) < sbi->blocks_per_seg;
+ return __next_free_blkoff(sbi, segno, 0) < BLKS_PER_SEG(sbi);
}
/*
* This function always allocates a used segment(from dirty seglist) by SSR
* manner, so it should recover the existing segment information of valid blocks
*/
-static void change_curseg(struct f2fs_sb_info *sbi, int type)
+static int change_curseg(struct f2fs_sb_info *sbi, int type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -2851,7 +2991,8 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type)
struct f2fs_summary_block *sum_node;
struct page *sum_page;
- write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno));
+ if (curseg->inited)
+ write_sum_page(sbi, curseg->sum_blk, GET_SUM_BLOCK(sbi, curseg->segno));
__set_test_and_inuse(sbi, new_segno);
@@ -2868,21 +3009,23 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type)
if (IS_ERR(sum_page)) {
/* GC won't be able to use stale summary pages by cp_error */
memset(curseg->sum_blk, 0, SUM_ENTRY_SIZE);
- return;
+ return PTR_ERR(sum_page);
}
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
f2fs_put_page(sum_page, 1);
+ return 0;
}
static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
int alloc_mode, unsigned long long age);
-static void get_atssr_segment(struct f2fs_sb_info *sbi, int type,
+static int get_atssr_segment(struct f2fs_sb_info *sbi, int type,
int target_type, int alloc_mode,
unsigned long long age)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
+ int ret = 0;
curseg->seg_type = target_type;
@@ -2890,38 +3033,62 @@ static void get_atssr_segment(struct f2fs_sb_info *sbi, int type,
struct seg_entry *se = get_seg_entry(sbi, curseg->next_segno);
curseg->seg_type = se->type;
- change_curseg(sbi, type);
+ ret = change_curseg(sbi, type);
} else {
/* allocate cold segment by default */
curseg->seg_type = CURSEG_COLD_DATA;
- new_curseg(sbi, type, true);
+ ret = new_curseg(sbi, type, true);
}
stat_inc_seg_type(sbi, curseg);
+ return ret;
}
-static void __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi)
+static int __f2fs_init_atgc_curseg(struct f2fs_sb_info *sbi, bool force)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC);
+ int ret = 0;
- if (!sbi->am.atgc_enabled)
- return;
+ if (!sbi->am.atgc_enabled && !force)
+ return 0;
f2fs_down_read(&SM_I(sbi)->curseg_lock);
mutex_lock(&curseg->curseg_mutex);
down_write(&SIT_I(sbi)->sentry_lock);
- get_atssr_segment(sbi, CURSEG_ALL_DATA_ATGC, CURSEG_COLD_DATA, SSR, 0);
+ ret = get_atssr_segment(sbi, CURSEG_ALL_DATA_ATGC,
+ CURSEG_COLD_DATA, SSR, 0);
up_write(&SIT_I(sbi)->sentry_lock);
mutex_unlock(&curseg->curseg_mutex);
f2fs_up_read(&SM_I(sbi)->curseg_lock);
+ return ret;
+}
+int f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi)
+{
+ return __f2fs_init_atgc_curseg(sbi, false);
}
-void f2fs_init_inmem_curseg(struct f2fs_sb_info *sbi)
+
+int f2fs_reinit_atgc_curseg(struct f2fs_sb_info *sbi)
{
- __f2fs_init_atgc_curseg(sbi);
+ int ret;
+
+ if (!test_opt(sbi, ATGC))
+ return 0;
+ if (sbi->am.atgc_enabled)
+ return 0;
+ if (le64_to_cpu(F2FS_CKPT(sbi)->elapsed_time) <
+ sbi->am.age_threshold)
+ return 0;
+
+ ret = __f2fs_init_atgc_curseg(sbi, true);
+ if (!ret) {
+ sbi->am.atgc_enabled = true;
+ f2fs_info(sbi, "reenabled age threshold GC");
+ }
+ return ret;
}
static void __f2fs_save_inmem_curseg(struct f2fs_sb_info *sbi, int type)
@@ -2989,7 +3156,8 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
sanity_check_seg_type(sbi, seg_type);
/* f2fs_need_SSR() already forces to do this */
- if (!f2fs_get_victim(sbi, &segno, BG_GC, seg_type, alloc_mode, age)) {
+ if (!f2fs_get_victim(sbi, &segno, BG_GC, seg_type,
+ alloc_mode, age, false)) {
curseg->next_segno = segno;
return 1;
}
@@ -3016,7 +3184,8 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type,
for (; cnt-- > 0; reversed ? i-- : i++) {
if (i == seg_type)
continue;
- if (!f2fs_get_victim(sbi, &segno, BG_GC, i, alloc_mode, age)) {
+ if (!f2fs_get_victim(sbi, &segno, BG_GC, i,
+ alloc_mode, age, false)) {
curseg->next_segno = segno;
return 1;
}
@@ -3040,8 +3209,7 @@ static bool need_new_seg(struct f2fs_sb_info *sbi, int type)
if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
curseg->seg_type == CURSEG_WARM_NODE)
return true;
- if (curseg->alloc_type == LFS &&
- is_next_segment_free(sbi, curseg, type) &&
+ if (curseg->alloc_type == LFS && is_next_segment_free(sbi, curseg) &&
likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return true;
if (!f2fs_need_SSR(sbi) || !get_ssr_segment(sbi, type, SSR, 0))
@@ -3049,11 +3217,12 @@ static bool need_new_seg(struct f2fs_sb_info *sbi, int type)
return false;
}
-void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
+int f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
unsigned int segno;
+ int ret = 0;
f2fs_down_read(&SM_I(sbi)->curseg_lock);
mutex_lock(&curseg->curseg_mutex);
@@ -3064,9 +3233,9 @@ void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
goto unlock;
if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type, SSR, 0))
- change_curseg(sbi, type);
+ ret = change_curseg(sbi, type);
else
- new_curseg(sbi, type, true);
+ ret = new_curseg(sbi, type, true);
stat_inc_seg_type(sbi, curseg);
@@ -3080,45 +3249,85 @@ unlock:
mutex_unlock(&curseg->curseg_mutex);
f2fs_up_read(&SM_I(sbi)->curseg_lock);
+ return ret;
}
-static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type,
+static int __allocate_new_segment(struct f2fs_sb_info *sbi, int type,
bool new_sec, bool force)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
unsigned int old_segno;
+ int err = 0;
+
+ if (type == CURSEG_COLD_DATA_PINNED && !curseg->inited)
+ goto allocate;
if (!force && curseg->inited &&
!curseg->next_blkoff &&
!get_valid_blocks(sbi, curseg->segno, new_sec) &&
!get_ckpt_valid_blocks(sbi, curseg->segno, new_sec))
- return;
+ return 0;
+allocate:
old_segno = curseg->segno;
- new_curseg(sbi, type, true);
+ err = new_curseg(sbi, type, true);
+ if (err)
+ return err;
stat_inc_seg_type(sbi, curseg);
locate_dirty_segment(sbi, old_segno);
+ return 0;
}
-void f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force)
+int f2fs_allocate_new_section(struct f2fs_sb_info *sbi, int type, bool force)
{
+ int ret;
+
f2fs_down_read(&SM_I(sbi)->curseg_lock);
down_write(&SIT_I(sbi)->sentry_lock);
- __allocate_new_segment(sbi, type, true, force);
+ ret = __allocate_new_segment(sbi, type, true, force);
up_write(&SIT_I(sbi)->sentry_lock);
f2fs_up_read(&SM_I(sbi)->curseg_lock);
+
+ return ret;
}
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
+int f2fs_allocate_pinning_section(struct f2fs_sb_info *sbi)
+{
+ int err;
+ bool gc_required = true;
+
+retry:
+ f2fs_lock_op(sbi);
+ err = f2fs_allocate_new_section(sbi, CURSEG_COLD_DATA_PINNED, false);
+ f2fs_unlock_op(sbi);
+
+ if (f2fs_sb_has_blkzoned(sbi) && err == -EAGAIN && gc_required) {
+ f2fs_down_write(&sbi->gc_lock);
+ err = f2fs_gc_range(sbi, 0, GET_SEGNO(sbi, FDEV(0).end_blk),
+ true, ZONED_PIN_SEC_REQUIRED_COUNT);
+ f2fs_up_write(&sbi->gc_lock);
+
+ gc_required = false;
+ if (!err)
+ goto retry;
+ }
+
+ return err;
+}
+
+int f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
{
int i;
+ int err = 0;
f2fs_down_read(&SM_I(sbi)->curseg_lock);
down_write(&SIT_I(sbi)->sentry_lock);
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
- __allocate_new_segment(sbi, i, false, false);
+ err += __allocate_new_segment(sbi, i, false, false);
up_write(&SIT_I(sbi)->sentry_lock);
f2fs_up_read(&SM_I(sbi)->curseg_lock);
+
+ return err;
}
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
@@ -3236,8 +3445,8 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
GET_SEGNO(sbi, end);
if (need_align) {
- start_segno = rounddown(start_segno, sbi->segs_per_sec);
- end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1;
+ start_segno = rounddown(start_segno, SEGS_PER_SEC(sbi));
+ end_segno = roundup(end_segno + 1, SEGS_PER_SEC(sbi)) - 1;
}
cpc.reason = CP_DISCARD;
@@ -3279,8 +3488,14 @@ out:
return err;
}
-int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
+int f2fs_rw_hint_to_seg_type(struct f2fs_sb_info *sbi, enum rw_hint hint)
{
+ if (F2FS_OPTION(sbi).active_logs == 2)
+ return CURSEG_HOT_DATA;
+ else if (F2FS_OPTION(sbi).active_logs == 4)
+ return CURSEG_COLD_DATA;
+
+ /* active_log == 6 */
switch (hint) {
case WRITE_LIFE_SHORT:
return CURSEG_HOT_DATA;
@@ -3291,6 +3506,65 @@ int f2fs_rw_hint_to_seg_type(enum rw_hint hint)
}
}
+/*
+ * This returns write hints for each segment type. This hints will be
+ * passed down to block layer as below by default.
+ *
+ * User F2FS Block
+ * ---- ---- -----
+ * META WRITE_LIFE_NONE|REQ_META
+ * HOT_NODE WRITE_LIFE_NONE
+ * WARM_NODE WRITE_LIFE_MEDIUM
+ * COLD_NODE WRITE_LIFE_LONG
+ * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME
+ * extension list " "
+ *
+ * -- buffered io
+ * COLD_DATA WRITE_LIFE_EXTREME
+ * HOT_DATA WRITE_LIFE_SHORT
+ * WARM_DATA WRITE_LIFE_NOT_SET
+ *
+ * -- direct io
+ * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME
+ * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT
+ * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET
+ * WRITE_LIFE_NONE " WRITE_LIFE_NONE
+ * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM
+ * WRITE_LIFE_LONG " WRITE_LIFE_LONG
+ */
+enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi,
+ enum page_type type, enum temp_type temp)
+{
+ switch (type) {
+ case DATA:
+ switch (temp) {
+ case WARM:
+ return WRITE_LIFE_NOT_SET;
+ case HOT:
+ return WRITE_LIFE_SHORT;
+ case COLD:
+ return WRITE_LIFE_EXTREME;
+ default:
+ return WRITE_LIFE_NONE;
+ }
+ case NODE:
+ switch (temp) {
+ case WARM:
+ return WRITE_LIFE_MEDIUM;
+ case HOT:
+ return WRITE_LIFE_NONE;
+ case COLD:
+ return WRITE_LIFE_LONG;
+ default:
+ return WRITE_LIFE_NONE;
+ }
+ case META:
+ return WRITE_LIFE_NONE;
+ default:
+ return WRITE_LIFE_NONE;
+ }
+}
+
static int __get_segment_type_2(struct f2fs_io_info *fio)
{
if (fio->type == DATA)
@@ -3345,7 +3619,9 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
if (page_private_gcing(fio->page)) {
if (fio->sbi->am.atgc_enabled &&
(fio->io_type == FS_DATA_IO) &&
- (fio->sbi->gc_mode != GC_URGENT_HIGH))
+ (fio->sbi->gc_mode != GC_URGENT_HIGH) &&
+ __is_valid_data_blkaddr(fio->old_blkaddr) &&
+ !is_inode_flag_set(inode, FI_OPU_WRITE))
return CURSEG_ALL_DATA_ATGC;
else
return CURSEG_COLD_DATA;
@@ -3353,7 +3629,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
if (file_is_cold(inode) || f2fs_need_compress_data(inode))
return CURSEG_COLD_DATA;
- type = __get_age_segment_type(inode, fio->page->index);
+ type = __get_age_segment_type(inode,
+ page_folio(fio->page)->index);
if (type != NO_CHECK_TYPE)
return type;
@@ -3361,7 +3638,8 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
is_inode_flag_set(inode, FI_HOT_DATA) ||
f2fs_is_cow_file(inode))
return CURSEG_HOT_DATA;
- return f2fs_rw_hint_to_seg_type(inode->i_write_hint);
+ return f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode),
+ inode->i_write_hint);
} else {
if (IS_DNODE(fio->page))
return is_cold_node(fio->page) ? CURSEG_WARM_NODE :
@@ -3370,9 +3648,35 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
}
}
+enum temp_type f2fs_get_segment_temp(struct f2fs_sb_info *sbi,
+ enum log_type type)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
+ enum temp_type temp = COLD;
+
+ switch (curseg->seg_type) {
+ case CURSEG_HOT_NODE:
+ case CURSEG_HOT_DATA:
+ temp = HOT;
+ break;
+ case CURSEG_WARM_NODE:
+ case CURSEG_WARM_DATA:
+ temp = WARM;
+ break;
+ case CURSEG_COLD_NODE:
+ case CURSEG_COLD_DATA:
+ temp = COLD;
+ break;
+ default:
+ f2fs_bug_on(sbi, 1);
+ }
+
+ return temp;
+}
+
static int __get_segment_type(struct f2fs_io_info *fio)
{
- int type = 0;
+ enum log_type type = CURSEG_HOT_DATA;
switch (F2FS_OPTION(fio->sbi).active_logs) {
case 2:
@@ -3388,12 +3692,8 @@ static int __get_segment_type(struct f2fs_io_info *fio)
f2fs_bug_on(fio->sbi, true);
}
- if (IS_HOT(type))
- fio->temp = HOT;
- else if (IS_WARM(type))
- fio->temp = WARM;
- else
- fio->temp = COLD;
+ fio->temp = f2fs_get_segment_temp(fio->sbi, type);
+
return type;
}
@@ -3410,7 +3710,14 @@ static void f2fs_randomize_chunk(struct f2fs_sb_info *sbi,
get_random_u32_inclusive(1, sbi->max_fragment_hole);
}
-void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+static void reset_curseg_fields(struct curseg_info *curseg)
+{
+ curseg->inited = false;
+ curseg->segno = NULL_SEGNO;
+ curseg->next_segno = 0;
+}
+
+int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
struct f2fs_io_info *fio)
@@ -3421,12 +3728,18 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
bool from_gc = (type == CURSEG_ALL_DATA_ATGC);
struct seg_entry *se = NULL;
bool segment_full = false;
+ int ret = 0;
f2fs_down_read(&SM_I(sbi)->curseg_lock);
mutex_lock(&curseg->curseg_mutex);
down_write(&sit_i->sentry_lock);
+ if (curseg->segno == NULL_SEGNO) {
+ ret = -ENOSPC;
+ goto out_err;
+ }
+
if (from_gc) {
f2fs_bug_on(sbi, GET_SEGNO(sbi, old_blkaddr) == NULL_SEGNO);
se = get_seg_entry(sbi, GET_SEGNO(sbi, old_blkaddr));
@@ -3435,7 +3748,7 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
}
*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
- f2fs_bug_on(sbi, curseg->next_blkoff >= sbi->blocks_per_seg);
+ f2fs_bug_on(sbi, curseg->next_blkoff >= BLKS_PER_SEG(sbi));
f2fs_wait_discard_bio(sbi, *new_blkaddr);
@@ -3464,25 +3777,37 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
* since SSR needs latest valid block information.
*/
update_sit_entry(sbi, *new_blkaddr, 1);
- if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
- update_sit_entry(sbi, old_blkaddr, -1);
+ update_sit_entry(sbi, old_blkaddr, -1);
/*
* If the current segment is full, flush it out and replace it with a
* new segment.
*/
if (segment_full) {
+ if (type == CURSEG_COLD_DATA_PINNED &&
+ !((curseg->segno + 1) % sbi->segs_per_sec)) {
+ write_sum_page(sbi, curseg->sum_blk,
+ GET_SUM_BLOCK(sbi, curseg->segno));
+ reset_curseg_fields(curseg);
+ goto skip_new_segment;
+ }
+
if (from_gc) {
- get_atssr_segment(sbi, type, se->type,
+ ret = get_atssr_segment(sbi, type, se->type,
AT_SSR, se->mtime);
} else {
if (need_new_seg(sbi, type))
- new_curseg(sbi, type, false);
+ ret = new_curseg(sbi, type, false);
else
- change_curseg(sbi, type);
+ ret = change_curseg(sbi, type);
stat_inc_seg_type(sbi, curseg);
}
+
+ if (ret)
+ goto out_err;
}
+
+skip_new_segment:
/*
* segment dirty status should be updated after segment allocation,
* so we just need to update status only one time after previous
@@ -3491,12 +3816,12 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr));
- if (IS_DATASEG(type))
+ if (IS_DATASEG(curseg->seg_type))
atomic64_inc(&sbi->allocated_data_blocks);
up_write(&sit_i->sentry_lock);
- if (page && IS_NODESEG(type)) {
+ if (page && IS_NODESEG(curseg->seg_type)) {
fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
f2fs_inode_chksum_set(sbi, page);
@@ -3505,9 +3830,6 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
if (fio) {
struct f2fs_bio_info *io;
- if (F2FS_IO_ALIGNED(sbi))
- fio->retry = 0;
-
INIT_LIST_HEAD(&fio->list);
fio->in_list = 1;
io = sbi->write_io[fio->type] + fio->temp;
@@ -3517,8 +3839,15 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
}
mutex_unlock(&curseg->curseg_mutex);
+ f2fs_up_read(&SM_I(sbi)->curseg_lock);
+ return 0;
+out_err:
+ *new_blkaddr = NULL_ADDR;
+ up_write(&sit_i->sentry_lock);
+ mutex_unlock(&curseg->curseg_mutex);
f2fs_up_read(&SM_I(sbi)->curseg_lock);
+ return ret;
}
void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
@@ -3548,33 +3877,61 @@ void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
}
}
+static int log_type_to_seg_type(enum log_type type)
+{
+ int seg_type = CURSEG_COLD_DATA;
+
+ switch (type) {
+ case CURSEG_HOT_DATA:
+ case CURSEG_WARM_DATA:
+ case CURSEG_COLD_DATA:
+ case CURSEG_HOT_NODE:
+ case CURSEG_WARM_NODE:
+ case CURSEG_COLD_NODE:
+ seg_type = (int)type;
+ break;
+ case CURSEG_COLD_DATA_PINNED:
+ case CURSEG_ALL_DATA_ATGC:
+ seg_type = CURSEG_COLD_DATA;
+ break;
+ default:
+ break;
+ }
+ return seg_type;
+}
+
static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
- int type = __get_segment_type(fio);
- bool keep_order = (f2fs_lfs_mode(fio->sbi) && type == CURSEG_COLD_DATA);
+ enum log_type type = __get_segment_type(fio);
+ int seg_type = log_type_to_seg_type(type);
+ bool keep_order = (f2fs_lfs_mode(fio->sbi) &&
+ seg_type == CURSEG_COLD_DATA);
if (keep_order)
f2fs_down_read(&fio->sbi->io_order_lock);
-reallocate:
- f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
- &fio->new_blkaddr, sum, type, fio);
+
+ if (f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
+ &fio->new_blkaddr, sum, type, fio)) {
+ if (fscrypt_inode_uses_fs_layer_crypto(fio->page->mapping->host))
+ fscrypt_finalize_bounce_page(&fio->encrypted_page);
+ end_page_writeback(fio->page);
+ if (f2fs_in_warm_node_list(fio->sbi, fio->page))
+ f2fs_del_fsync_node_entry(fio->sbi, fio->page);
+ goto out;
+ }
if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
- f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr);
+ f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr, 1);
/* writeout dirty page into bdev */
f2fs_submit_page_write(fio);
- if (fio->retry) {
- fio->old_blkaddr = fio->new_blkaddr;
- goto reallocate;
- }
f2fs_update_device_state(fio->sbi, fio->ino, fio->new_blkaddr, 1);
-
+out:
if (keep_order)
f2fs_up_read(&fio->sbi->io_order_lock);
}
-void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct folio *folio,
enum iostat_type io_type)
{
struct f2fs_io_info fio = {
@@ -3583,20 +3940,20 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
.temp = HOT,
.op = REQ_OP_WRITE,
.op_flags = REQ_SYNC | REQ_META | REQ_PRIO,
- .old_blkaddr = page->index,
- .new_blkaddr = page->index,
- .page = page,
+ .old_blkaddr = folio->index,
+ .new_blkaddr = folio->index,
+ .page = folio_page(folio, 0),
.encrypted_page = NULL,
.in_list = 0,
};
- if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
+ if (unlikely(folio->index >= MAIN_BLKADDR(sbi)))
fio.op_flags &= ~REQ_META;
- set_page_writeback(page);
+ folio_start_writeback(folio);
f2fs_submit_page_write(&fio);
- stat_inc_meta_count(sbi, page->index);
+ stat_inc_meta_count(sbi, folio->index);
f2fs_update_iostat(sbi, NULL, io_type, F2FS_BLKSIZE);
}
@@ -3652,9 +4009,8 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
goto drop_bio;
}
- if (fio->post_read)
- invalidate_mapping_pages(META_MAPPING(sbi),
- fio->new_blkaddr, fio->new_blkaddr);
+ if (fio->meta_gc)
+ f2fs_truncate_meta_inode_pages(sbi, fio->new_blkaddr, 1);
stat_inc_inplace_blocks(fio->sbi);
@@ -3730,8 +4086,8 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
}
}
- f2fs_bug_on(sbi, !IS_DATASEG(type));
curseg = CURSEG_I(sbi, type);
+ f2fs_bug_on(sbi, !IS_DATASEG(curseg->seg_type));
mutex_lock(&curseg->curseg_mutex);
down_write(&sit_i->sentry_lock);
@@ -3743,7 +4099,8 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
/* change the current segment */
if (segno != curseg->segno) {
curseg->next_segno = segno;
- change_curseg(sbi, type);
+ if (change_curseg(sbi, type))
+ goto out_unlock;
}
curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
@@ -3755,7 +4112,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
update_sit_entry(sbi, new_blkaddr, 1);
}
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) {
- f2fs_invalidate_internal_cache(sbi, old_blkaddr);
+ f2fs_invalidate_internal_cache(sbi, old_blkaddr, 1);
if (!from_gc)
update_segment_mtime(sbi, old_blkaddr, 0);
update_sit_entry(sbi, old_blkaddr, -1);
@@ -3769,12 +4126,14 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (recover_curseg) {
if (old_cursegno != curseg->segno) {
curseg->next_segno = old_cursegno;
- change_curseg(sbi, type);
+ if (change_curseg(sbi, type))
+ goto out_unlock;
}
curseg->next_blkoff = old_blkoff;
curseg->alloc_type = old_alloc_type;
}
+out_unlock:
up_write(&sit_i->sentry_lock);
mutex_unlock(&curseg->curseg_mutex);
f2fs_up_write(&SM_I(sbi)->curseg_lock);
@@ -3798,7 +4157,7 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered, bool locked)
{
- if (PageWriteback(page)) {
+ if (folio_test_writeback(page_folio(page))) {
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
/* submit cached LFS IO */
@@ -3807,7 +4166,8 @@ void f2fs_wait_on_page_writeback(struct page *page,
f2fs_submit_merged_ipu_write(sbi, NULL, page);
if (ordered) {
wait_on_page_writeback(page);
- f2fs_bug_on(sbi, locked && PageWriteback(page));
+ f2fs_bug_on(sbi, locked &&
+ folio_test_writeback(page_folio(page)));
} else {
wait_for_stable_page(page);
}
@@ -3819,7 +4179,7 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *cpage;
- if (!f2fs_post_read_required(inode))
+ if (!f2fs_meta_inode_gc_required(inode))
return;
if (!__is_valid_data_blkaddr(blkaddr))
@@ -3838,13 +4198,13 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
block_t i;
- if (!f2fs_post_read_required(inode))
+ if (!f2fs_meta_inode_gc_required(inode))
return;
for (i = 0; i < len; i++)
f2fs_wait_on_block_writeback(inode, blkaddr + i);
- invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr + len - 1);
+ f2fs_truncate_meta_inode_pages(sbi, blkaddr, len);
}
static int read_compacted_summaries(struct f2fs_sb_info *sbi)
@@ -3886,7 +4246,7 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
seg_i->next_blkoff = blk_off;
if (seg_i->alloc_type == SSR)
- blk_off = sbi->blocks_per_seg;
+ blk_off = BLKS_PER_SEG(sbi);
for (j = 0; j < blk_off; j++) {
struct f2fs_summary *s;
@@ -3954,7 +4314,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
struct f2fs_summary *ns = &sum->entries[0];
int i;
- for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
+ for (i = 0; i < BLKS_PER_SEG(sbi); i++, ns++) {
ns->version = 0;
ns->ofs_in_node = 0;
}
@@ -4460,7 +4820,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
#endif
sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
- sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
+ sit_i->sit_blocks = SEGS_TO_BLKS(sbi, sit_segs);
sit_i->written_valid_blocks = 0;
sit_i->bitmap_size = sit_bitmap_size;
sit_i->dirty_sentries = 0;
@@ -4527,15 +4887,8 @@ static int build_curseg(struct f2fs_sb_info *sbi)
sizeof(struct f2fs_journal), GFP_KERNEL);
if (!array[i].journal)
return -ENOMEM;
- if (i < NR_PERSISTENT_LOG)
- array[i].seg_type = CURSEG_HOT_DATA + i;
- else if (i == CURSEG_COLD_DATA_PINNED)
- array[i].seg_type = CURSEG_COLD_DATA;
- else if (i == CURSEG_ALL_DATA_ATGC)
- array[i].seg_type = CURSEG_COLD_DATA;
- array[i].segno = NULL_SEGNO;
- array[i].next_blkoff = 0;
- array[i].inited = false;
+ array[i].seg_type = log_type_to_seg_type(i);
+ reset_curseg_fields(&array[i]);
}
return restore_curseg_summaries(sbi);
}
@@ -4587,21 +4940,20 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
sit_valid_blocks[SE_PAGETYPE(se)] += se->valid_blocks;
- if (f2fs_block_unit_discard(sbi)) {
- /* build discard map only one time */
- if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
- memset(se->discard_map, 0xff,
+ if (!f2fs_block_unit_discard(sbi))
+ goto init_discard_map_done;
+
+ /* build discard map only one time */
+ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+ memset(se->discard_map, 0xff,
SIT_VBLOCK_MAP_SIZE);
- } else {
- memcpy(se->discard_map,
- se->cur_valid_map,
+ goto init_discard_map_done;
+ }
+ memcpy(se->discard_map, se->cur_valid_map,
SIT_VBLOCK_MAP_SIZE);
- sbi->discard_blks +=
- sbi->blocks_per_seg -
+ sbi->discard_blks += BLKS_PER_SEG(sbi) -
se->valid_blocks;
- }
- }
-
+init_discard_map_done:
if (__is_large_section(sbi))
get_sec_entry(sbi, start)->valid_blocks +=
se->valid_blocks;
@@ -4741,7 +5093,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
return;
mutex_lock(&dirty_i->seglist_lock);
- for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) {
valid_blocks = get_valid_blocks(sbi, segno, true);
secno = GET_SEC_FROM_SEG(sbi, segno);
@@ -4840,7 +5192,7 @@ static int sanity_check_curseg(struct f2fs_sb_info *sbi)
if (curseg->alloc_type == SSR)
continue;
- for (blkofs += 1; blkofs < sbi->blocks_per_seg; blkofs++) {
+ for (blkofs += 1; blkofs < BLKS_PER_SEG(sbi); blkofs++) {
if (!f2fs_test_bit(blkofs, se->cur_valid_map))
continue;
out:
@@ -4856,7 +5208,6 @@ out:
}
#ifdef CONFIG_BLK_DEV_ZONED
-
static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
struct f2fs_dev_info *fdev,
struct blk_zone *zone)
@@ -4865,6 +5216,7 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
block_t zone_block, valid_block_cnt;
unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT;
int ret;
+ unsigned int nofs_flags;
if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ)
return 0;
@@ -4876,14 +5228,19 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
* Skip check of zones cursegs point to, since
* fix_curseg_write_pointer() checks them.
*/
- if (zone_segno >= MAIN_SEGS(sbi) ||
- IS_CURSEC(sbi, GET_SEC_FROM_SEG(sbi, zone_segno)))
+ if (zone_segno >= MAIN_SEGS(sbi))
return 0;
/*
* Get # of valid block of the zone.
*/
valid_block_cnt = get_valid_blocks(sbi, zone_segno, true);
+ if (IS_CURSEC(sbi, GET_SEC_FROM_SEG(sbi, zone_segno))) {
+ f2fs_notice(sbi, "Open zones: valid block[0x%x,0x%x] cond[%s]",
+ zone_segno, valid_block_cnt,
+ blk_zone_cond_str(zone->cond));
+ return 0;
+ }
if ((!valid_block_cnt && zone->cond == BLK_ZONE_COND_EMPTY) ||
(valid_block_cnt && zone->cond == BLK_ZONE_COND_FULL))
@@ -4891,8 +5248,8 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
if (!valid_block_cnt) {
f2fs_notice(sbi, "Zone without valid block has non-zero write "
- "pointer. Reset the write pointer: cond[0x%x]",
- zone->cond);
+ "pointer. Reset the write pointer: cond[%s]",
+ blk_zone_cond_str(zone->cond));
ret = __f2fs_issue_discard_zone(sbi, fdev->bdev, zone_block,
zone->len >> log_sectors_per_block);
if (ret)
@@ -4909,11 +5266,13 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi,
* selected for write operation until it get discarded.
*/
f2fs_notice(sbi, "Valid blocks are not aligned with write "
- "pointer: valid block[0x%x,0x%x] cond[0x%x]",
- zone_segno, valid_block_cnt, zone->cond);
+ "pointer: valid block[0x%x,0x%x] cond[%s]",
+ zone_segno, valid_block_cnt, blk_zone_cond_str(zone->cond));
+ nofs_flags = memalloc_nofs_save();
ret = blkdev_zone_mgmt(fdev->bdev, REQ_OP_ZONE_FINISH,
- zone->start, zone->len, GFP_NOFS);
+ zone->start, zone->len);
+ memalloc_nofs_restore(nofs_flags);
if (ret == -EOPNOTSUPP) {
ret = blkdev_issue_zeroout(fdev->bdev, zone->wp,
zone->len - (zone->wp - zone->start),
@@ -4952,7 +5311,7 @@ static int report_one_zone_cb(struct blk_zone *zone, unsigned int idx,
return 0;
}
-static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
+static int do_fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *cs = CURSEG_I(sbi, type);
struct f2fs_dev_info *zbd;
@@ -5004,7 +5363,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
}
/* Allocate a new section if it's not new. */
- if (cs->next_blkoff) {
+ if (cs->next_blkoff ||
+ cs->segno != GET_SEG_FROM_SEC(sbi, GET_ZONE_FROM_SEC(sbi, cs_section))) {
unsigned int old_segno = cs->segno, old_blkoff = cs->next_blkoff;
f2fs_allocate_new_section(sbi, type, true);
@@ -5056,12 +5416,12 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type)
return 0;
}
-int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
+static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
{
int i, ret;
for (i = 0; i < NR_PERSISTENT_LOG; i++) {
- ret = fix_curseg_write_pointer(sbi, i);
+ ret = do_fix_curseg_write_pointer(sbi, i);
if (ret)
return ret;
}
@@ -5084,7 +5444,7 @@ static int check_zone_write_pointer_cb(struct blk_zone *zone, unsigned int idx,
return check_zone_write_pointer(args->sbi, args->fdev, zone);
}
-int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+static int check_write_pointer(struct f2fs_sb_info *sbi)
{
int i, ret;
struct check_zone_write_pointer_args args;
@@ -5104,6 +5464,21 @@ int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
return 0;
}
+int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi)
+{
+ int ret;
+
+ if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb) ||
+ f2fs_hw_is_readonly(sbi))
+ return 0;
+
+ f2fs_notice(sbi, "Checking entire write pointers");
+ ret = fix_curseg_write_pointer(sbi);
+ if (!ret)
+ ret = check_write_pointer(sbi);
+ return ret;
+}
+
/*
* Return the number of usable blocks in a segment. The number of blocks
* returned is always equal to the number of blocks in a segment for
@@ -5119,7 +5494,7 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg(
unsigned int secno;
if (!sbi->unusable_blocks_per_sec)
- return sbi->blocks_per_seg;
+ return BLKS_PER_SEG(sbi);
secno = GET_SEC_FROM_SEG(sbi, segno);
seg_start = START_BLOCK(sbi, segno);
@@ -5134,18 +5509,13 @@ static inline unsigned int f2fs_usable_zone_blks_in_seg(
*/
if (seg_start >= sec_cap_blkaddr)
return 0;
- if (seg_start + sbi->blocks_per_seg > sec_cap_blkaddr)
+ if (seg_start + BLKS_PER_SEG(sbi) > sec_cap_blkaddr)
return sec_cap_blkaddr - seg_start;
- return sbi->blocks_per_seg;
+ return BLKS_PER_SEG(sbi);
}
#else
-int f2fs_fix_curseg_write_pointer(struct f2fs_sb_info *sbi)
-{
- return 0;
-}
-
-int f2fs_check_write_pointer(struct f2fs_sb_info *sbi)
+int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi)
{
return 0;
}
@@ -5163,16 +5533,50 @@ unsigned int f2fs_usable_blks_in_seg(struct f2fs_sb_info *sbi,
if (f2fs_sb_has_blkzoned(sbi))
return f2fs_usable_zone_blks_in_seg(sbi, segno);
- return sbi->blocks_per_seg;
+ return BLKS_PER_SEG(sbi);
}
-unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi,
- unsigned int segno)
+unsigned int f2fs_usable_segs_in_sec(struct f2fs_sb_info *sbi)
{
if (f2fs_sb_has_blkzoned(sbi))
return CAP_SEGS_PER_SEC(sbi);
- return sbi->segs_per_sec;
+ return SEGS_PER_SEC(sbi);
+}
+
+unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
+ unsigned int segno)
+{
+ unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi);
+ unsigned int secno = 0, start = 0;
+ unsigned int total_valid_blocks = 0;
+ unsigned long long mtime = 0;
+ unsigned int i = 0;
+
+ secno = GET_SEC_FROM_SEG(sbi, segno);
+ start = GET_SEG_FROM_SEC(sbi, secno);
+
+ if (!__is_large_section(sbi)) {
+ mtime = get_seg_entry(sbi, start + i)->mtime;
+ goto out;
+ }
+
+ for (i = 0; i < usable_segs_per_sec; i++) {
+ /* for large section, only check the mtime of valid segments */
+ struct seg_entry *se = get_seg_entry(sbi, start+i);
+
+ mtime += se->mtime * se->valid_blocks;
+ total_valid_blocks += se->valid_blocks;
+ }
+
+ if (total_valid_blocks == 0)
+ return INVALID_MTIME;
+
+ mtime = div_u64(mtime, total_valid_blocks);
+out:
+ if (unlikely(mtime == INVALID_MTIME))
+ mtime -= 1;
+ return mtime;
}
/*
@@ -5187,14 +5591,10 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi)
sit_i->min_mtime = ULLONG_MAX;
- for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
- unsigned int i;
+ for (segno = 0; segno < MAIN_SEGS(sbi); segno += SEGS_PER_SEC(sbi)) {
unsigned long long mtime = 0;
- for (i = 0; i < sbi->segs_per_sec; i++)
- mtime += get_seg_entry(sbi, segno + i)->mtime;
-
- mtime = div_u64(mtime, sbi->segs_per_sec);
+ mtime = f2fs_get_section_mtime(sbi, segno);
if (sit_i->min_mtime > mtime)
sit_i->min_mtime = mtime;
@@ -5233,7 +5633,7 @@ int f2fs_build_segment_manager(struct f2fs_sb_info *sbi)
sm_info->ipu_policy = BIT(F2FS_IPU_FSYNC);
sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
- sm_info->min_seq_blocks = sbi->blocks_per_seg;
+ sm_info->min_seq_blocks = BLKS_PER_SEG(sbi);
sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
sm_info->min_ssr_sections = reserved_sections(sbi);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 8129be788bd5..943be4f1d6d2 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -18,6 +18,8 @@
#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
#define F2FS_MIN_META_SEGMENTS 8 /* SB + 2 (CP + SIT + NAT) + SSA */
+#define INVALID_MTIME ULLONG_MAX /* no valid blocks in a segment/section */
+
/* L: Logical segment # in volume, R: Relative segment # in main area */
#define GET_L2R_SEGNO(free_i, segno) ((segno) - (free_i)->start_segno)
#define GET_R2L_SEGNO(free_i, segno) ((segno) + (free_i)->start_segno)
@@ -32,10 +34,6 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
f2fs_bug_on(sbi, seg_type >= NR_PERSISTENT_LOG);
}
-#define IS_HOT(t) ((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
-#define IS_WARM(t) ((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
-#define IS_COLD(t) ((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
-
#define IS_CURSEG(sbi, seg) \
(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \
((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \
@@ -48,21 +46,21 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
#define IS_CURSEC(sbi, secno) \
(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \
- (sbi)->segs_per_sec) || \
+ SEGS_PER_SEC(sbi)) || \
((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \
- (sbi)->segs_per_sec) || \
+ SEGS_PER_SEC(sbi)) || \
((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \
- (sbi)->segs_per_sec) || \
+ SEGS_PER_SEC(sbi)) || \
((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \
- (sbi)->segs_per_sec) || \
+ SEGS_PER_SEC(sbi)) || \
((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \
- (sbi)->segs_per_sec) || \
+ SEGS_PER_SEC(sbi)) || \
((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
- (sbi)->segs_per_sec) || \
+ SEGS_PER_SEC(sbi)) || \
((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA_PINNED)->segno / \
- (sbi)->segs_per_sec) || \
+ SEGS_PER_SEC(sbi)) || \
((secno) == CURSEG_I(sbi, CURSEG_ALL_DATA_ATGC)->segno / \
- (sbi)->segs_per_sec))
+ SEGS_PER_SEC(sbi)))
#define MAIN_BLKADDR(sbi) \
(SM_I(sbi) ? SM_I(sbi)->main_blkaddr : \
@@ -77,40 +75,37 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
#define TOTAL_SEGS(sbi) \
(SM_I(sbi) ? SM_I(sbi)->segment_count : \
le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count))
-#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
+#define TOTAL_BLKS(sbi) (SEGS_TO_BLKS(sbi, TOTAL_SEGS(sbi)))
#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
#define SEGMENT_SIZE(sbi) (1ULL << ((sbi)->log_blocksize + \
(sbi)->log_blocks_per_seg))
#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \
- (GET_R2L_SEGNO(FREE_I(sbi), segno) << (sbi)->log_blocks_per_seg))
+ (SEGS_TO_BLKS(sbi, GET_R2L_SEGNO(FREE_I(sbi), segno))))
#define NEXT_FREE_BLKADDR(sbi, curseg) \
(START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff)
#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi))
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \
- (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg)
+ (BLKS_TO_SEGS(sbi, GET_SEGOFF_FROM_SEG0(sbi, blk_addr)))
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \
- (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))
+ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (BLKS_PER_SEG(sbi) - 1))
#define GET_SEGNO(sbi, blk_addr) \
((!__is_valid_data_blkaddr(blk_addr)) ? \
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
-#define BLKS_PER_SEC(sbi) \
- ((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
#define CAP_BLKS_PER_SEC(sbi) \
- ((sbi)->segs_per_sec * (sbi)->blocks_per_seg - \
- (sbi)->unusable_blocks_per_sec)
+ (BLKS_PER_SEC(sbi) - (sbi)->unusable_blocks_per_sec)
#define CAP_SEGS_PER_SEC(sbi) \
- ((sbi)->segs_per_sec - ((sbi)->unusable_blocks_per_sec >>\
- (sbi)->log_blocks_per_seg))
+ (SEGS_PER_SEC(sbi) - \
+ BLKS_TO_SEGS(sbi, (sbi)->unusable_blocks_per_sec))
#define GET_SEC_FROM_SEG(sbi, segno) \
- (((segno) == -1) ? -1 : (segno) / (sbi)->segs_per_sec)
+ (((segno) == -1) ? -1 : (segno) / SEGS_PER_SEC(sbi))
#define GET_SEG_FROM_SEC(sbi, secno) \
- ((secno) * (sbi)->segs_per_sec)
+ ((secno) * SEGS_PER_SEC(sbi))
#define GET_ZONE_FROM_SEC(sbi, secno) \
(((secno) == -1) ? -1 : (secno) / (sbi)->secs_per_zone)
#define GET_ZONE_FROM_SEG(sbi, segno) \
@@ -139,16 +134,6 @@ static inline void sanity_check_seg_type(struct f2fs_sb_info *sbi,
((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK)
/*
- * indicate a block allocation direction: RIGHT and LEFT.
- * RIGHT means allocating new sections towards the end of volume.
- * LEFT means the opposite direction.
- */
-enum {
- ALLOC_RIGHT = 0,
- ALLOC_LEFT
-};
-
-/*
* In the victim_sel_policy->alloc_mode, there are three block allocation modes.
* LFS writes data sequentially with cleaning operations.
* SSR (Slack Space Recycle) reuses obsolete space without cleaning operations.
@@ -201,6 +186,7 @@ struct victim_sel_policy {
unsigned int min_segno; /* segment # having min. cost */
unsigned long long age; /* mtime of GCed section*/
unsigned long long age_threshold;/* age threshold */
+ bool one_time_gc; /* one time GC */
};
struct seg_entry {
@@ -360,11 +346,12 @@ static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
unsigned int segno, bool use_section)
{
if (use_section && __is_large_section(sbi)) {
- unsigned int start_segno = START_SEGNO(segno);
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
unsigned int blocks = 0;
int i;
- for (i = 0; i < sbi->segs_per_sec; i++, start_segno++) {
+ for (i = 0; i < SEGS_PER_SEC(sbi); i++, start_segno++) {
struct seg_entry *se = get_seg_entry(sbi, start_segno);
blocks += se->ckpt_valid_blocks;
@@ -442,14 +429,14 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
unsigned int next;
- unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
+ unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi);
spin_lock(&free_i->segmap_lock);
clear_bit(segno, free_i->free_segmap);
free_i->free_segments++;
next = find_next_bit(free_i->free_segmap,
- start_segno + sbi->segs_per_sec, start_segno);
+ start_segno + SEGS_PER_SEC(sbi), start_segno);
if (next >= start_segno + usable_segs) {
clear_bit(secno, free_i->free_secmap);
free_i->free_sections++;
@@ -476,7 +463,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
unsigned int next;
- unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi, segno);
+ unsigned int usable_segs = f2fs_usable_segs_in_sec(sbi);
spin_lock(&free_i->segmap_lock);
if (test_and_clear_bit(segno, free_i->free_segmap)) {
@@ -485,7 +472,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
if (!inmem && IS_CURSEC(sbi, secno))
goto skip_free;
next = find_next_bit(free_i->free_segmap,
- start_segno + sbi->segs_per_sec, start_segno);
+ start_segno + SEGS_PER_SEC(sbi), start_segno);
if (next >= start_segno + usable_segs) {
if (test_and_clear_bit(secno, free_i->free_secmap))
free_i->free_sections++;
@@ -535,8 +522,7 @@ static inline unsigned int free_segments(struct f2fs_sb_info *sbi)
static inline unsigned int reserved_segments(struct f2fs_sb_info *sbi)
{
- return SM_I(sbi)->reserved_segments +
- SM_I(sbi)->additional_reserved_segments;
+ return SM_I(sbi)->reserved_segments;
}
static inline unsigned int free_sections(struct f2fs_sb_info *sbi)
@@ -570,34 +556,37 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi)
}
static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
- unsigned int node_blocks, unsigned int dent_blocks)
+ unsigned int node_blocks, unsigned int data_blocks,
+ unsigned int dent_blocks)
{
- unsigned int segno, left_blocks;
+ unsigned int segno, left_blocks, blocks;
int i;
- /* check current node segment */
- for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) {
+ /* check current data/node sections in the worst case. */
+ for (i = CURSEG_HOT_DATA; i < NR_PERSISTENT_LOG; i++) {
segno = CURSEG_I(sbi, i)->segno;
- left_blocks = f2fs_usable_blks_in_seg(sbi, segno) -
- get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+ left_blocks = CAP_BLKS_PER_SEC(sbi) -
+ get_ckpt_valid_blocks(sbi, segno, true);
- if (node_blocks > left_blocks)
+ blocks = i <= CURSEG_COLD_DATA ? data_blocks : node_blocks;
+ if (blocks > left_blocks)
return false;
}
- /* check current data segment */
+ /* check current data section for dentry blocks. */
segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
- left_blocks = f2fs_usable_blks_in_seg(sbi, segno) -
- get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+ left_blocks = CAP_BLKS_PER_SEC(sbi) -
+ get_ckpt_valid_blocks(sbi, segno, true);
if (dent_blocks > left_blocks)
return false;
return true;
}
/*
- * calculate needed sections for dirty node/dentry
- * and call has_curseg_enough_space
+ * calculate needed sections for dirty node/dentry and call
+ * has_curseg_enough_space, please note that, it needs to account
+ * dirty data as well in lfs mode when checkpoint is disabled.
*/
static inline void __get_secs_required(struct f2fs_sb_info *sbi,
unsigned int *lower_p, unsigned int *upper_p, bool *curseg_p)
@@ -606,19 +595,30 @@ static inline void __get_secs_required(struct f2fs_sb_info *sbi,
get_pages(sbi, F2FS_DIRTY_DENTS) +
get_pages(sbi, F2FS_DIRTY_IMETA);
unsigned int total_dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS);
+ unsigned int total_data_blocks = 0;
unsigned int node_secs = total_node_blocks / CAP_BLKS_PER_SEC(sbi);
unsigned int dent_secs = total_dent_blocks / CAP_BLKS_PER_SEC(sbi);
+ unsigned int data_secs = 0;
unsigned int node_blocks = total_node_blocks % CAP_BLKS_PER_SEC(sbi);
unsigned int dent_blocks = total_dent_blocks % CAP_BLKS_PER_SEC(sbi);
+ unsigned int data_blocks = 0;
+
+ if (f2fs_lfs_mode(sbi) &&
+ unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ total_data_blocks = get_pages(sbi, F2FS_DIRTY_DATA);
+ data_secs = total_data_blocks / CAP_BLKS_PER_SEC(sbi);
+ data_blocks = total_data_blocks % CAP_BLKS_PER_SEC(sbi);
+ }
if (lower_p)
- *lower_p = node_secs + dent_secs;
+ *lower_p = node_secs + dent_secs + data_secs;
if (upper_p)
*upper_p = node_secs + dent_secs +
- (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0);
+ (node_blocks ? 1 : 0) + (dent_blocks ? 1 : 0) +
+ (data_blocks ? 1 : 0);
if (curseg_p)
*curseg_p = has_curseg_enough_space(sbi,
- node_blocks, dent_blocks);
+ node_blocks, data_blocks, dent_blocks);
}
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
@@ -638,7 +638,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
if (free_secs > upper_secs)
return false;
- else if (free_secs <= lower_secs)
+ if (free_secs <= lower_secs)
return true;
return !curseg_space;
}
@@ -649,12 +649,30 @@ static inline bool has_enough_free_secs(struct f2fs_sb_info *sbi,
return !has_not_enough_free_secs(sbi, freed, needed);
}
+static inline bool has_enough_free_blks(struct f2fs_sb_info *sbi)
+{
+ unsigned int total_free_blocks = 0;
+ unsigned int avail_user_block_count;
+
+ spin_lock(&sbi->stat_lock);
+
+ avail_user_block_count = get_available_block_count(sbi, NULL, true);
+ total_free_blocks = avail_user_block_count - (unsigned int)valid_user_blocks(sbi);
+
+ spin_unlock(&sbi->stat_lock);
+
+ return total_free_blocks > 0;
+}
+
static inline bool f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi)
{
if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return true;
if (likely(has_enough_free_secs(sbi, 0, 0)))
return true;
+ if (!f2fs_lfs_mode(sbi) &&
+ likely(has_enough_free_blks(sbi)))
+ return true;
return false;
}
@@ -793,10 +811,10 @@ static inline int check_block_count(struct f2fs_sb_info *sbi,
return -EFSCORRUPTED;
}
- if (usable_blks_per_seg < sbi->blocks_per_seg)
+ if (usable_blks_per_seg < BLKS_PER_SEG(sbi))
f2fs_bug_on(sbi, find_next_bit_le(&raw_sit->valid_map,
- sbi->blocks_per_seg,
- usable_blks_per_seg) != sbi->blocks_per_seg);
+ BLKS_PER_SEG(sbi),
+ usable_blks_per_seg) != BLKS_PER_SEG(sbi));
/* check segment usage, and check boundary of a given segment number */
if (unlikely(GET_SIT_VBLOCKS(raw_sit) > usable_blks_per_seg
@@ -915,9 +933,9 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
return 0;
if (type == DATA)
- return sbi->blocks_per_seg;
+ return BLKS_PER_SEG(sbi);
else if (type == NODE)
- return 8 * sbi->blocks_per_seg;
+ return SEGS_TO_BLKS(sbi, 8);
else if (type == META)
return 8 * BIO_MAX_VECS;
else
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d45ab0992ae5..19b67828ae32 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -11,7 +11,6 @@
#include <linux/fs_context.h>
#include <linux/sched/mm.h>
#include <linux/statfs.h>
-#include <linux/buffer_head.h>
#include <linux/kthread.h>
#include <linux/parser.h>
#include <linux/mount.h>
@@ -44,41 +43,53 @@ static struct kmem_cache *f2fs_inode_cachep;
#ifdef CONFIG_F2FS_FAULT_INJECTION
const char *f2fs_fault_name[FAULT_MAX] = {
- [FAULT_KMALLOC] = "kmalloc",
- [FAULT_KVMALLOC] = "kvmalloc",
- [FAULT_PAGE_ALLOC] = "page alloc",
- [FAULT_PAGE_GET] = "page get",
- [FAULT_ALLOC_NID] = "alloc nid",
- [FAULT_ORPHAN] = "orphan",
- [FAULT_BLOCK] = "no more block",
- [FAULT_DIR_DEPTH] = "too big dir depth",
- [FAULT_EVICT_INODE] = "evict_inode fail",
- [FAULT_TRUNCATE] = "truncate fail",
- [FAULT_READ_IO] = "read IO error",
- [FAULT_CHECKPOINT] = "checkpoint error",
- [FAULT_DISCARD] = "discard error",
- [FAULT_WRITE_IO] = "write IO error",
- [FAULT_SLAB_ALLOC] = "slab alloc",
- [FAULT_DQUOT_INIT] = "dquot initialize",
- [FAULT_LOCK_OP] = "lock_op",
- [FAULT_BLKADDR] = "invalid blkaddr",
+ [FAULT_KMALLOC] = "kmalloc",
+ [FAULT_KVMALLOC] = "kvmalloc",
+ [FAULT_PAGE_ALLOC] = "page alloc",
+ [FAULT_PAGE_GET] = "page get",
+ [FAULT_ALLOC_NID] = "alloc nid",
+ [FAULT_ORPHAN] = "orphan",
+ [FAULT_BLOCK] = "no more block",
+ [FAULT_DIR_DEPTH] = "too big dir depth",
+ [FAULT_EVICT_INODE] = "evict_inode fail",
+ [FAULT_TRUNCATE] = "truncate fail",
+ [FAULT_READ_IO] = "read IO error",
+ [FAULT_CHECKPOINT] = "checkpoint error",
+ [FAULT_DISCARD] = "discard error",
+ [FAULT_WRITE_IO] = "write IO error",
+ [FAULT_SLAB_ALLOC] = "slab alloc",
+ [FAULT_DQUOT_INIT] = "dquot initialize",
+ [FAULT_LOCK_OP] = "lock_op",
+ [FAULT_BLKADDR_VALIDITY] = "invalid blkaddr",
+ [FAULT_BLKADDR_CONSISTENCE] = "inconsistent blkaddr",
+ [FAULT_NO_SEGMENT] = "no free segment",
};
-void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
- unsigned int type)
+int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
+ unsigned long type)
{
struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info;
if (rate) {
+ if (rate > INT_MAX)
+ return -EINVAL;
atomic_set(&ffi->inject_ops, 0);
- ffi->inject_rate = rate;
+ ffi->inject_rate = (int)rate;
}
- if (type)
- ffi->inject_type = type;
+ if (type) {
+ if (type >= BIT(FAULT_MAX))
+ return -EINVAL;
+ ffi->inject_type = (unsigned int)type;
+ }
if (!rate && !type)
memset(ffi, 0, sizeof(struct f2fs_fault_info));
+ else
+ f2fs_info(sbi,
+ "build fault injection attr: rate: %lu, type: 0x%lx",
+ rate, type);
+ return 0;
}
#endif
@@ -137,7 +148,6 @@ enum {
Opt_resgid,
Opt_resuid,
Opt_mode,
- Opt_io_size_bits,
Opt_fault_injection,
Opt_fault_type,
Opt_lazytime,
@@ -216,7 +226,6 @@ static match_table_t f2fs_tokens = {
{Opt_resgid, "resgid=%u"},
{Opt_resuid, "resuid=%u"},
{Opt_mode, "mode=%s"},
- {Opt_io_size_bits, "io_bits=%u"},
{Opt_fault_injection, "fault_injection=%u"},
{Opt_fault_type, "fault_type=%u"},
{Opt_lazytime, "lazytime"},
@@ -263,7 +272,8 @@ static match_table_t f2fs_tokens = {
{Opt_err, NULL},
};
-void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
+void f2fs_printk(struct f2fs_sb_info *sbi, bool limit_rate,
+ const char *fmt, ...)
{
struct va_format vaf;
va_list args;
@@ -274,8 +284,12 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
level = printk_get_level(fmt);
vaf.fmt = printk_skip_level(fmt);
vaf.va = &args;
- printk("%c%cF2FS-fs (%s): %pV\n",
- KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf);
+ if (limit_rate)
+ printk_ratelimited("%c%cF2FS-fs (%s): %pV\n",
+ KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf);
+ else
+ printk("%c%cF2FS-fs (%s): %pV\n",
+ KERN_SOH_ASCII, level, sbi->sb->s_id, &vaf);
va_end(args);
}
@@ -306,7 +320,7 @@ struct kmem_cache *f2fs_cf_name_slab;
static int __init f2fs_create_casefold_cache(void)
{
f2fs_cf_name_slab = f2fs_kmem_cache_create("f2fs_casefolded_name",
- F2FS_NAME_LEN);
+ F2FS_NAME_LEN);
return f2fs_cf_name_slab ? 0 : -ENOMEM;
}
@@ -343,46 +357,6 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).s_resgid));
}
-static inline int adjust_reserved_segment(struct f2fs_sb_info *sbi)
-{
- unsigned int sec_blks = sbi->blocks_per_seg * sbi->segs_per_sec;
- unsigned int avg_vblocks;
- unsigned int wanted_reserved_segments;
- block_t avail_user_block_count;
-
- if (!F2FS_IO_ALIGNED(sbi))
- return 0;
-
- /* average valid block count in section in worst case */
- avg_vblocks = sec_blks / F2FS_IO_SIZE(sbi);
-
- /*
- * we need enough free space when migrating one section in worst case
- */
- wanted_reserved_segments = (F2FS_IO_SIZE(sbi) / avg_vblocks) *
- reserved_segments(sbi);
- wanted_reserved_segments -= reserved_segments(sbi);
-
- avail_user_block_count = sbi->user_block_count -
- sbi->current_reserved_blocks -
- F2FS_OPTION(sbi).root_reserved_blocks;
-
- if (wanted_reserved_segments * sbi->blocks_per_seg >
- avail_user_block_count) {
- f2fs_err(sbi, "IO align feature can't grab additional reserved segment: %u, available segments: %u",
- wanted_reserved_segments,
- avail_user_block_count >> sbi->log_blocks_per_seg);
- return -ENOSPC;
- }
-
- SM_I(sbi)->additional_reserved_segments = wanted_reserved_segments;
-
- f2fs_info(sbi, "IO align feature needs additional reserved segment: %u",
- wanted_reserved_segments);
-
- return 0;
-}
-
static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
{
if (!F2FS_OPTION(sbi).unusable_cap_perc)
@@ -663,7 +637,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str)
#ifdef CONFIG_F2FS_FS_ZSTD
static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
{
- unsigned int level;
+ int level;
int len = 4;
if (strlen(str) == len) {
@@ -677,9 +651,15 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
f2fs_info(sbi, "wrong format, e.g. <alg_name>:<compr_level>");
return -EINVAL;
}
- if (kstrtouint(str + 1, 10, &level))
+ if (kstrtoint(str + 1, 10, &level))
return -EINVAL;
+ /* f2fs does not support negative compress level now */
+ if (level < 0) {
+ f2fs_info(sbi, "do not support negative compress level: %d", level);
+ return -ERANGE;
+ }
+
if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) {
f2fs_info(sbi, "invalid zstd compress level: %d", level);
return -EINVAL;
@@ -730,6 +710,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
if (!strcmp(name, "on")) {
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
} else if (!strcmp(name, "off")) {
+ if (f2fs_sb_has_blkzoned(sbi)) {
+ f2fs_warn(sbi, "zoned devices need bggc");
+ kfree(name);
+ return -EINVAL;
+ }
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_OFF;
} else if (!strcmp(name, "sync")) {
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_SYNC;
@@ -763,10 +748,8 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
clear_opt(sbi, DISCARD);
break;
case Opt_noheap:
- set_opt(sbi, NOHEAP);
- break;
case Opt_heap:
- clear_opt(sbi, NOHEAP);
+ f2fs_warn(sbi, "heap/no_heap options were deprecated");
break;
#ifdef CONFIG_F2FS_FS_XATTR
case Opt_user_xattr:
@@ -855,6 +838,10 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
set_opt(sbi, READ_EXTENT_CACHE);
break;
case Opt_noextent_cache:
+ if (F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_DEVICE_ALIAS)) {
+ f2fs_err(sbi, "device aliasing requires extent cache");
+ return -EINVAL;
+ }
clear_opt(sbi, READ_EXTENT_CACHE);
break;
case Opt_noinline_data:
@@ -913,28 +900,21 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
}
kfree(name);
break;
- case Opt_io_size_bits:
- if (args->from && match_int(args, &arg))
- return -EINVAL;
- if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) {
- f2fs_warn(sbi, "Not support %ld, larger than %d",
- BIT(arg), BIO_MAX_VECS);
- return -EINVAL;
- }
- F2FS_OPTION(sbi).write_io_size_bits = arg;
- break;
#ifdef CONFIG_F2FS_FAULT_INJECTION
case Opt_fault_injection:
if (args->from && match_int(args, &arg))
return -EINVAL;
- f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE);
+ if (f2fs_build_fault_attr(sbi, arg,
+ F2FS_ALL_FAULT_TYPE))
+ return -EINVAL;
set_opt(sbi, FAULT_INJECTION);
break;
case Opt_fault_type:
if (args->from && match_int(args, &arg))
return -EINVAL;
- f2fs_build_fault_attr(sbi, 0, arg);
+ if (f2fs_build_fault_attr(sbi, 0, arg))
+ return -EINVAL;
set_opt(sbi, FAULT_INJECTION);
break;
#else
@@ -1192,7 +1172,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
break;
}
- strcpy(ext[ext_cnt], name);
+ ret = strscpy(ext[ext_cnt], name);
+ if (ret < 0) {
+ kfree(name);
+ return ret;
+ }
F2FS_OPTION(sbi).compress_ext_cnt++;
kfree(name);
break;
@@ -1221,7 +1205,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
break;
}
- strcpy(noext[noext_cnt], name);
+ ret = strscpy(noext[noext_cnt], name);
+ if (ret < 0) {
+ kfree(name);
+ return ret;
+ }
F2FS_OPTION(sbi).nocompress_ext_cnt++;
kfree(name);
break;
@@ -1354,13 +1342,13 @@ default_check:
return -EINVAL;
}
#endif
-#if !IS_ENABLED(CONFIG_UNICODE)
- if (f2fs_sb_has_casefold(sbi)) {
+
+ if (!IS_ENABLED(CONFIG_UNICODE) && f2fs_sb_has_casefold(sbi)) {
f2fs_err(sbi,
"Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE");
return -EINVAL;
}
-#endif
+
/*
* The BLKZONED feature indicates that the drive was formatted with
* zone alignment optimization. This is optional for host-aware
@@ -1392,12 +1380,6 @@ default_check:
}
#endif
- if (F2FS_IO_SIZE_BITS(sbi) && !f2fs_lfs_mode(sbi)) {
- f2fs_err(sbi, "Should set mode=lfs with %luKB-sized IO",
- F2FS_IO_SIZE_KB(sbi));
- return -EINVAL;
- }
-
if (test_opt(sbi, INLINE_XATTR_SIZE)) {
int min_size, max_size;
@@ -1605,7 +1587,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
for (i = 0; i < sbi->s_ndevs; i++) {
if (i > 0)
- bdev_release(FDEV(i).bdev_handle);
+ bdev_fput(FDEV(i).bdev_file);
#ifdef CONFIG_BLK_DEV_ZONED
kvfree(FDEV(i).blkz_seq);
#endif
@@ -1712,13 +1694,10 @@ static void f2fs_put_super(struct super_block *sb)
kvfree(sbi->ckpt);
- if (sbi->s_chksum_driver)
- crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi->raw_super);
f2fs_destroy_page_array_cache(sbi);
f2fs_destroy_xattr_caches(sbi);
- mempool_destroy(sbi->write_io_dummy);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
kfree(F2FS_OPTION(sbi).s_qf_names[i]);
@@ -1779,6 +1758,18 @@ static int f2fs_freeze(struct super_block *sb)
static int f2fs_unfreeze(struct super_block *sb)
{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+ /*
+ * It will update discard_max_bytes of mounted lvm device to zero
+ * after creating snapshot on this lvm device, let's drop all
+ * remained discards.
+ * We don't need to disable real-time discard because discard_max_bytes
+ * will recover after removal of snapshot.
+ */
+ if (test_opt(sbi, DISCARD) && !f2fs_hw_support_discard(sbi))
+ f2fs_issue_discard_timeout(sbi);
+
clear_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING);
return 0;
}
@@ -2009,10 +2000,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
} else {
seq_puts(seq, ",nodiscard");
}
- if (test_opt(sbi, NOHEAP))
- seq_puts(seq, ",no_heap");
- else
- seq_puts(seq, ",heap");
#ifdef CONFIG_F2FS_FS_XATTR
if (test_opt(sbi, XATTR_USER))
seq_puts(seq, ",user_xattr");
@@ -2078,9 +2065,6 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
F2FS_OPTION(sbi).s_resuid),
from_kgid_munged(&init_user_ns,
F2FS_OPTION(sbi).s_resgid));
- if (F2FS_IO_SIZE_BITS(sbi))
- seq_printf(seq, ",io_bits=%u",
- F2FS_OPTION(sbi).write_io_size_bits);
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (test_opt(sbi, FAULT_INJECTION)) {
seq_printf(seq, ",fault_injection=%u",
@@ -2187,12 +2171,9 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount)
F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL;
F2FS_OPTION(sbi).errors = MOUNT_ERRORS_CONTINUE;
- sbi->sb->s_flags &= ~SB_INLINECRYPT;
-
set_opt(sbi, INLINE_XATTR);
set_opt(sbi, INLINE_DATA);
set_opt(sbi, INLINE_DENTRY);
- set_opt(sbi, NOHEAP);
set_opt(sbi, MERGE_CHECKPOINT);
F2FS_OPTION(sbi).unusable_cap = 0;
sbi->sb->s_flags |= SB_LAZYTIME;
@@ -2247,6 +2228,7 @@ static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi)
.init_gc_type = FG_GC,
.should_migrate_blocks = false,
.err_gc_skipped = true,
+ .no_bg_gc = true,
.nr_free_secs = 1 };
f2fs_down_write(&sbi->gc_lock);
@@ -2332,7 +2314,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
bool no_read_extent_cache = !test_opt(sbi, READ_EXTENT_CACHE);
bool no_age_extent_cache = !test_opt(sbi, AGE_EXTENT_CACHE);
bool enable_checkpoint = !test_opt(sbi, DISABLE_CHECKPOINT);
- bool no_io_align = !F2FS_IO_ALIGNED(sbi);
bool no_atgc = !test_opt(sbi, ATGC);
bool no_discard = !test_opt(sbi, DISCARD);
bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE);
@@ -2382,6 +2363,17 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
if (err)
goto restore_opts;
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (f2fs_sb_has_blkzoned(sbi) &&
+ sbi->max_open_zones < F2FS_OPTION(sbi).active_logs) {
+ f2fs_err(sbi,
+ "zoned: max open zones %u is too small, need at least %u open zones",
+ sbi->max_open_zones, F2FS_OPTION(sbi).active_logs);
+ err = -EINVAL;
+ goto restore_opts;
+ }
+#endif
+
/* flush outstanding errors before changing fs state */
flush_work(&sbi->s_error_work);
@@ -2440,12 +2432,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
- if (no_io_align == !!F2FS_IO_ALIGNED(sbi)) {
- err = -EINVAL;
- f2fs_warn(sbi, "switch io_bits option is not allowed");
- goto restore_opts;
- }
-
if (no_compress_cache == !!test_opt(sbi, COMPRESS_CACHE)) {
err = -EINVAL;
f2fs_warn(sbi, "switch compress_cache option is not allowed");
@@ -2520,6 +2506,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
}
}
+ adjust_unusable_cap_perc(sbi);
if (enable_checkpoint == !!test_opt(sbi, DISABLE_CHECKPOINT)) {
if (test_opt(sbi, DISABLE_CHECKPOINT)) {
err = f2fs_disable_checkpoint(sbi);
@@ -2564,7 +2551,6 @@ skip:
(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
limit_reserve_root(sbi);
- adjust_unusable_cap_perc(sbi);
*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
return 0;
restore_checkpoint:
@@ -2609,6 +2595,11 @@ restore_opts:
return err;
}
+static void f2fs_shutdown(struct super_block *sb)
+{
+ f2fs_do_shutdown(F2FS_SB(sb), F2FS_GOING_DOWN_NOSYNC, false, false);
+}
+
#ifdef CONFIG_QUOTA
static bool f2fs_need_recovery(struct f2fs_sb_info *sbi)
{
@@ -2722,7 +2713,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
const struct address_space_operations *a_ops = mapping->a_ops;
int offset = off & (sb->s_blocksize - 1);
size_t towrite = len;
- struct page *page;
+ struct folio *folio;
void *fsdata = NULL;
int err = 0;
int tocopy;
@@ -2732,7 +2723,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
towrite);
retry:
err = a_ops->write_begin(NULL, mapping, off, tocopy,
- &page, &fsdata);
+ &folio, &fsdata);
if (unlikely(err)) {
if (err == -ENOMEM) {
f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT);
@@ -2742,10 +2733,10 @@ retry:
break;
}
- memcpy_to_page(page, offset, data, tocopy);
+ memcpy_to_folio(folio, offset_in_folio(folio, off), data, tocopy);
a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
- page, fsdata);
+ folio, fsdata);
offset = 0;
towrite -= tocopy;
off += tocopy;
@@ -2768,7 +2759,7 @@ int f2fs_dquot_initialize(struct inode *inode)
return dquot_initialize(inode);
}
-static struct dquot **f2fs_get_dquots(struct inode *inode)
+static struct dquot __rcu **f2fs_get_dquots(struct inode *inode)
{
return F2FS_I(inode)->i_dquot;
}
@@ -3208,6 +3199,7 @@ static const struct super_operations f2fs_sops = {
.unfreeze_fs = f2fs_unfreeze,
.statfs = f2fs_statfs,
.remount_fs = f2fs_remount,
+ .shutdown = f2fs_shutdown,
};
#ifdef CONFIG_FS_ENCRYPTION
@@ -3362,29 +3354,47 @@ loff_t max_file_blocks(struct inode *inode)
* fit within U32_MAX + 1 data units.
*/
- result = min(result, (((loff_t)U32_MAX + 1) * 4096) >> F2FS_BLKSIZE_BITS);
+ result = umin(result, F2FS_BYTES_TO_BLK(((loff_t)U32_MAX + 1) * 4096));
return result;
}
-static int __f2fs_commit_super(struct buffer_head *bh,
- struct f2fs_super_block *super)
+static int __f2fs_commit_super(struct f2fs_sb_info *sbi, struct folio *folio,
+ pgoff_t index, bool update)
{
- lock_buffer(bh);
- if (super)
- memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
- set_buffer_dirty(bh);
- unlock_buffer(bh);
-
+ struct bio *bio;
/* it's rare case, we can do fua all the time */
- return __sync_dirty_buffer(bh, REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
+ blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH | REQ_FUA;
+ int ret;
+
+ folio_lock(folio);
+ folio_wait_writeback(folio);
+ if (update)
+ memcpy(F2FS_SUPER_BLOCK(folio, index), F2FS_RAW_SUPER(sbi),
+ sizeof(struct f2fs_super_block));
+ folio_mark_dirty(folio);
+ folio_clear_dirty_for_io(folio);
+ folio_start_writeback(folio);
+ folio_unlock(folio);
+
+ bio = bio_alloc(sbi->sb->s_bdev, 1, opf, GFP_NOFS);
+
+ /* it doesn't need to set crypto context for superblock update */
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(folio_index(folio));
+
+ if (!bio_add_folio(bio, folio, folio_size(folio), 0))
+ f2fs_bug_on(sbi, 1);
+
+ ret = submit_bio_wait(bio);
+ folio_end_writeback(folio);
+
+ return ret;
}
static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
- struct buffer_head *bh)
+ struct folio *folio, pgoff_t index)
{
- struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
- (bh->b_data + F2FS_SUPER_OFFSET);
+ struct f2fs_super_block *raw_super = F2FS_SUPER_BLOCK(folio, index);
struct super_block *sb = sbi->sb;
u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
@@ -3400,9 +3410,9 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
u32 segment_count = le32_to_cpu(raw_super->segment_count);
u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
u64 main_end_blkaddr = main_blkaddr +
- (segment_count_main << log_blocks_per_seg);
+ ((u64)segment_count_main << log_blocks_per_seg);
u64 seg_end_blkaddr = segment0_blkaddr +
- (segment_count << log_blocks_per_seg);
+ ((u64)segment_count << log_blocks_per_seg);
if (segment0_blkaddr != cp_blkaddr) {
f2fs_info(sbi, "Mismatch start address, segment0(%u) cp_blkaddr(%u)",
@@ -3459,7 +3469,7 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
res = "internally";
} else {
- err = __f2fs_commit_super(bh, NULL);
+ err = __f2fs_commit_super(sbi, folio, index, false);
res = err ? "failed" : "done";
}
f2fs_info(sbi, "Fix alignment : %s, start(%u) end(%llu) block(%u)",
@@ -3472,12 +3482,11 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
}
static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
- struct buffer_head *bh)
+ struct folio *folio, pgoff_t index)
{
block_t segment_count, segs_per_sec, secs_per_zone, segment_count_main;
block_t total_sections, blocks_per_seg;
- struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
- (bh->b_data + F2FS_SUPER_OFFSET);
+ struct f2fs_super_block *raw_super = F2FS_SUPER_BLOCK(folio, index);
size_t crc_offset = 0;
__u32 crc = 0;
@@ -3503,7 +3512,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
}
}
- /* Currently, support only 4KB block size */
+ /* only support block_size equals to PAGE_SIZE */
if (le32_to_cpu(raw_super->log_blocksize) != F2FS_BLKSIZE_BITS) {
f2fs_info(sbi, "Invalid log_blocksize (%u), supports only %u",
le32_to_cpu(raw_super->log_blocksize),
@@ -3635,7 +3644,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
}
/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
- if (sanity_check_area_boundary(sbi, bh))
+ if (sanity_check_area_boundary(sbi, folio, index))
return -EFSCORRUPTED;
return 0;
@@ -3706,7 +3715,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
}
main_segs = le32_to_cpu(raw_super->segment_count_main);
- blocks_per_seg = sbi->blocks_per_seg;
+ blocks_per_seg = BLKS_PER_SEG(sbi);
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
@@ -3818,9 +3827,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
sbi->total_sections = le32_to_cpu(raw_super->section_count);
- sbi->total_node_count =
- (le32_to_cpu(raw_super->segment_count_nat) / 2)
- * sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
+ sbi->total_node_count = SEGS_TO_BLKS(sbi,
+ ((le32_to_cpu(raw_super->segment_count_nat) / 2) *
+ NAT_ENTRY_PER_BLOCK));
F2FS_ROOT_INO(sbi) = le32_to_cpu(raw_super->root_ino);
F2FS_NODE_INO(sbi) = le32_to_cpu(raw_super->node_ino);
F2FS_META_INO(sbi) = le32_to_cpu(raw_super->meta_ino);
@@ -3829,7 +3838,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
- sbi->migration_granularity = sbi->segs_per_sec;
+ sbi->migration_granularity = SEGS_PER_SEC(sbi);
+ sbi->migration_window_granularity = f2fs_sb_has_blkzoned(sbi) ?
+ DEF_MIGRATION_WINDOW_GRANULARITY_ZONED : SEGS_PER_SEC(sbi);
sbi->seq_file_ra_mul = MIN_RA_MUL;
sbi->max_fragment_chunk = DEF_FRAGMENT_SIZE;
sbi->max_fragment_hole = DEF_FRAGMENT_SIZE;
@@ -3924,17 +3935,25 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
sector_t nr_sectors = bdev_nr_sectors(bdev);
struct f2fs_report_zones_args rep_zone_arg;
u64 zone_sectors;
+ unsigned int max_open_zones;
int ret;
if (!f2fs_sb_has_blkzoned(sbi))
return 0;
- zone_sectors = bdev_zone_sectors(bdev);
- if (!is_power_of_2(zone_sectors)) {
- f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n");
- return -EINVAL;
+ if (bdev_is_zoned(FDEV(devi).bdev)) {
+ max_open_zones = bdev_max_open_zones(bdev);
+ if (max_open_zones && (max_open_zones < sbi->max_open_zones))
+ sbi->max_open_zones = max_open_zones;
+ if (sbi->max_open_zones < F2FS_OPTION(sbi).active_logs) {
+ f2fs_err(sbi,
+ "zoned: max open zones %u is too small, need at least %u open zones",
+ sbi->max_open_zones, F2FS_OPTION(sbi).active_logs);
+ return -EINVAL;
+ }
}
+ zone_sectors = bdev_zone_sectors(bdev);
if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
SECTOR_TO_BLOCK(zone_sectors))
return -EINVAL;
@@ -3974,7 +3993,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
{
struct super_block *sb = sbi->sb;
int block;
- struct buffer_head *bh;
+ struct folio *folio;
struct f2fs_super_block *super;
int err = 0;
@@ -3983,32 +4002,32 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
return -ENOMEM;
for (block = 0; block < 2; block++) {
- bh = sb_bread(sb, block);
- if (!bh) {
+ folio = read_mapping_folio(sb->s_bdev->bd_mapping, block, NULL);
+ if (IS_ERR(folio)) {
f2fs_err(sbi, "Unable to read %dth superblock",
block + 1);
- err = -EIO;
+ err = PTR_ERR(folio);
*recovery = 1;
continue;
}
/* sanity checking of raw super */
- err = sanity_check_raw_super(sbi, bh);
+ err = sanity_check_raw_super(sbi, folio, block);
if (err) {
f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock",
block + 1);
- brelse(bh);
+ folio_put(folio);
*recovery = 1;
continue;
}
if (!*raw_super) {
- memcpy(super, bh->b_data + F2FS_SUPER_OFFSET,
+ memcpy(super, F2FS_SUPER_BLOCK(folio, block),
sizeof(*super));
*valid_super_block = block;
*raw_super = super;
}
- brelse(bh);
+ folio_put(folio);
}
/* No valid superblock */
@@ -4022,7 +4041,8 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
{
- struct buffer_head *bh;
+ struct folio *folio;
+ pgoff_t index;
__u32 crc = 0;
int err;
@@ -4040,22 +4060,24 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
}
/* write back-up superblock first */
- bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1);
- if (!bh)
- return -EIO;
- err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
- brelse(bh);
+ index = sbi->valid_super_block ? 0 : 1;
+ folio = read_mapping_folio(sbi->sb->s_bdev->bd_mapping, index, NULL);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
+ err = __f2fs_commit_super(sbi, folio, index, true);
+ folio_put(folio);
/* if we are in recovery path, skip writing valid superblock */
if (recover || err)
return err;
/* write current valid superblock */
- bh = sb_bread(sbi->sb, sbi->valid_super_block);
- if (!bh)
- return -EIO;
- err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
- brelse(bh);
+ index = sbi->valid_super_block;
+ folio = read_mapping_folio(sbi->sb->s_bdev->bd_mapping, index, NULL);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
+ err = __f2fs_commit_super(sbi, folio, index, true);
+ folio_put(folio);
return err;
}
@@ -4090,7 +4112,9 @@ static void f2fs_record_stop_reason(struct f2fs_sb_info *sbi)
f2fs_up_write(&sbi->sb_lock);
if (err)
- f2fs_err(sbi, "f2fs_commit_super fails to record err:%d", err);
+ f2fs_err_ratelimited(sbi,
+ "f2fs_commit_super fails to record stop_reason, err:%d",
+ err);
}
void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag)
@@ -4133,8 +4157,9 @@ static void f2fs_record_errors(struct f2fs_sb_info *sbi, unsigned char error)
err = f2fs_commit_super(sbi, false);
if (err)
- f2fs_err(sbi, "f2fs_commit_super fails to record errors:%u, err:%d",
- error, err);
+ f2fs_err_ratelimited(sbi,
+ "f2fs_commit_super fails to record errors:%u, err:%d",
+ error, err);
out_unlock:
f2fs_up_write(&sbi->sb_lock);
}
@@ -4162,8 +4187,7 @@ static bool system_going_down(void)
|| system_state == SYSTEM_RESTART;
}
-void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
- bool irq_context)
+void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason)
{
struct super_block *sb = sbi->sb;
bool shutdown = reason == STOP_CP_REASON_SHUTDOWN;
@@ -4175,10 +4199,12 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
if (!f2fs_hw_is_readonly(sbi)) {
save_stop_reason(sbi, reason);
- if (irq_context && !shutdown)
- schedule_work(&sbi->s_error_work);
- else
- f2fs_record_stop_reason(sbi);
+ /*
+ * always create an asynchronous task to record stop_reason
+ * in order to avoid potential deadlock when running into
+ * f2fs_record_stop_reason() synchronously.
+ */
+ schedule_work(&sbi->s_error_work);
}
/*
@@ -4195,17 +4221,25 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
if (shutdown)
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
- /* continue filesystem operators if errors=continue */
- if (continue_fs || f2fs_readonly(sb))
+ /*
+ * Continue filesystem operators if errors=continue. Should not set
+ * RO by shutdown, since RO bypasses thaw_super which can hang the
+ * system.
+ */
+ if (continue_fs || f2fs_readonly(sb) || shutdown) {
+ f2fs_warn(sbi, "Stopped filesystem due to reason: %d", reason);
return;
+ }
f2fs_warn(sbi, "Remounting filesystem read-only");
+
/*
- * Make sure updated value of ->s_mount_flags will be visible before
- * ->s_flags update
+ * We have already set CP_ERROR_FLAG flag to stop all updates
+ * to filesystem, so it doesn't need to set SB_RDONLY flag here
+ * because the flag should be set covered w/ sb->s_umount semaphore
+ * via remount procedure, otherwise, it will confuse code like
+ * freeze_super() which will lead to deadlocks and other problems.
*/
- smp_wmb();
- sb->s_flags |= SB_RDONLY;
}
static void f2fs_record_error_work(struct work_struct *work)
@@ -4216,6 +4250,16 @@ static void f2fs_record_error_work(struct work_struct *work)
f2fs_record_stop_reason(sbi);
}
+static inline unsigned int get_first_zoned_segno(struct f2fs_sb_info *sbi)
+{
+ int devi;
+
+ for (devi = 0; devi < sbi->s_ndevs; devi++)
+ if (bdev_is_zoned(FDEV(devi).bdev))
+ return GET_SEGNO(sbi, FDEV(devi).start_blk);
+ return 0;
+}
+
static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -4244,10 +4288,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
logical_blksize = bdev_logical_block_size(sbi->sb->s_bdev);
sbi->aligned_blksize = true;
+#ifdef CONFIG_BLK_DEV_ZONED
+ sbi->max_open_zones = UINT_MAX;
+ sbi->blkzone_alloc_policy = BLKZONE_ALLOC_PRIOR_SEQ;
+#endif
for (i = 0; i < max_devices; i++) {
if (i == 0)
- FDEV(0).bdev_handle = sbi->sb->s_bdev_handle;
+ FDEV(0).bdev_file = sbi->sb->s_bdev_file;
else if (!RDEV(i).path[0])
break;
@@ -4259,22 +4307,22 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
if (i == 0) {
FDEV(i).start_blk = 0;
FDEV(i).end_blk = FDEV(i).start_blk +
- (FDEV(i).total_segments <<
- sbi->log_blocks_per_seg) - 1 +
- le32_to_cpu(raw_super->segment0_blkaddr);
+ SEGS_TO_BLKS(sbi,
+ FDEV(i).total_segments) - 1 +
+ le32_to_cpu(raw_super->segment0_blkaddr);
} else {
FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
FDEV(i).end_blk = FDEV(i).start_blk +
- (FDEV(i).total_segments <<
- sbi->log_blocks_per_seg) - 1;
- FDEV(i).bdev_handle = bdev_open_by_path(
+ SEGS_TO_BLKS(sbi,
+ FDEV(i).total_segments) - 1;
+ FDEV(i).bdev_file = bdev_file_open_by_path(
FDEV(i).path, mode, sbi->sb, NULL);
}
}
- if (IS_ERR(FDEV(i).bdev_handle))
- return PTR_ERR(FDEV(i).bdev_handle);
+ if (IS_ERR(FDEV(i).bdev_file))
+ return PTR_ERR(FDEV(i).bdev_file);
- FDEV(i).bdev = FDEV(i).bdev_handle->bdev;
+ FDEV(i).bdev = file_bdev(FDEV(i).bdev_file);
/* to release errored devices */
sbi->s_ndevs = i + 1;
@@ -4305,8 +4353,6 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
FDEV(i).total_segments,
FDEV(i).start_blk, FDEV(i).end_blk);
}
- f2fs_info(sbi,
- "IO Block Size: %8ld KB", F2FS_IO_SIZE_KB(sbi));
return 0;
}
@@ -4418,15 +4464,6 @@ try_onemore:
}
mutex_init(&sbi->flush_lock);
- /* Load the checksum driver */
- sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
- if (IS_ERR(sbi->s_chksum_driver)) {
- f2fs_err(sbi, "Cannot load crc32 driver.");
- err = PTR_ERR(sbi->s_chksum_driver);
- sbi->s_chksum_driver = NULL;
- goto free_sbi;
- }
-
/* set a block size */
if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
f2fs_err(sbi, "unable to set blocksize");
@@ -4496,7 +4533,8 @@ try_onemore:
sb->s_time_gran = 1;
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
- memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+ super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid));
+ super_set_sysfs_name_bdev(sb);
sb->s_iflags |= SB_I_CGROUPWB;
/* init f2fs-specific super block info */
@@ -4519,19 +4557,10 @@ try_onemore:
if (err)
goto free_iostat;
- if (F2FS_IO_ALIGNED(sbi)) {
- sbi->write_io_dummy =
- mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
- if (!sbi->write_io_dummy) {
- err = -ENOMEM;
- goto free_percpu;
- }
- }
-
/* init per sbi slab cache */
err = f2fs_init_xattr_caches(sbi);
if (err)
- goto free_io_dummy;
+ goto free_percpu;
err = f2fs_init_page_array_cache(sbi);
if (err)
goto free_xattr_cache;
@@ -4619,13 +4648,12 @@ try_onemore:
goto free_nm;
}
- err = adjust_reserved_segment(sbi);
- if (err)
- goto free_nm;
-
/* For write statistics */
sbi->sectors_written_start = f2fs_get_sectors_written(sbi);
+ /* get segno of first zoned block device */
+ sbi->first_zoned_segno = get_first_zoned_segno(sbi);
+
/* Read accumulated write IO statistics if exists */
seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
if (__exist_node_summaries(sbi))
@@ -4660,6 +4688,7 @@ try_onemore:
goto free_node_inode;
}
+ generic_set_sb_d_ops(sb);
sb->s_root = d_make_root(root); /* allocate root dentry */
if (!sb->s_root) {
err = -ENOMEM;
@@ -4746,19 +4775,23 @@ try_onemore:
reset_checkpoint:
/*
* If the f2fs is not readonly and fsync data recovery succeeds,
- * check zoned block devices' write pointer consistency.
+ * write pointer consistency of cursegs and other zones are already
+ * checked and fixed during recovery. However, if recovery fails,
+ * write pointers are left untouched, and retry-mount should check
+ * them here.
*/
- if (!err && !f2fs_readonly(sb) && f2fs_sb_has_blkzoned(sbi)) {
- err = f2fs_check_write_pointer(sbi);
- if (err)
- goto free_meta;
- }
-
- f2fs_init_inmem_curseg(sbi);
+ if (skip_recovery)
+ err = f2fs_check_and_fix_write_pointer(sbi);
+ if (err)
+ goto free_meta;
/* f2fs_recover_fsync_data() cleared this already */
clear_sbi_flag(sbi, SBI_POR_DOING);
+ err = f2fs_init_inmem_curseg(sbi);
+ if (err)
+ goto sync_free_meta;
+
if (test_opt(sbi, DISABLE_CHECKPOINT)) {
err = f2fs_disable_checkpoint(sbi);
if (err)
@@ -4853,8 +4886,6 @@ free_page_array_cache:
f2fs_destroy_page_array_cache(sbi);
free_xattr_cache:
f2fs_destroy_xattr_caches(sbi);
-free_io_dummy:
- mempool_destroy(sbi->write_io_dummy);
free_percpu:
destroy_percpu_info(sbi);
free_iostat:
@@ -4877,8 +4908,6 @@ free_options:
free_sb_buf:
kfree(raw_super);
free_sbi:
- if (sbi->s_chksum_driver)
- crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi);
sb->s_fs_info = NULL;
@@ -4967,12 +4996,6 @@ static int __init init_f2fs_fs(void)
{
int err;
- if (PAGE_SIZE != F2FS_BLKSIZE) {
- printk("F2FS not supported on PAGE_SIZE(%lu) != BLOCK_SIZE(%lu)\n",
- PAGE_SIZE, F2FS_BLKSIZE);
- return -EINVAL;
- }
-
err = init_inodecache();
if (err)
goto fail;
@@ -5000,9 +5023,6 @@ static int __init init_f2fs_fs(void)
err = f2fs_init_shrinker();
if (err)
goto free_sysfs;
- err = register_filesystem(&f2fs_fs_type);
- if (err)
- goto free_shrinker;
f2fs_create_root_stats();
err = f2fs_init_post_read_processing();
if (err)
@@ -5025,7 +5045,12 @@ static int __init init_f2fs_fs(void)
err = f2fs_create_casefold_cache();
if (err)
goto free_compress_cache;
+ err = register_filesystem(&f2fs_fs_type);
+ if (err)
+ goto free_casefold_cache;
return 0;
+free_casefold_cache:
+ f2fs_destroy_casefold_cache();
free_compress_cache:
f2fs_destroy_compress_cache();
free_compress_mempool:
@@ -5040,8 +5065,6 @@ free_post_read:
f2fs_destroy_post_read_processing();
free_root_stats:
f2fs_destroy_root_stats();
- unregister_filesystem(&f2fs_fs_type);
-free_shrinker:
f2fs_exit_shrinker();
free_sysfs:
f2fs_exit_sysfs();
@@ -5065,6 +5088,7 @@ fail:
static void __exit exit_f2fs_fs(void)
{
+ unregister_filesystem(&f2fs_fs_type);
f2fs_destroy_casefold_cache();
f2fs_destroy_compress_cache();
f2fs_destroy_compress_mempool();
@@ -5073,7 +5097,6 @@ static void __exit exit_f2fs_fs(void)
f2fs_destroy_iostat_processing();
f2fs_destroy_post_read_processing();
f2fs_destroy_root_stats();
- unregister_filesystem(&f2fs_fs_type);
f2fs_exit_shrinker();
f2fs_exit_sysfs();
f2fs_destroy_garbage_collection_cache();
@@ -5091,5 +5114,3 @@ module_exit(exit_f2fs_fs)
MODULE_AUTHOR("Samsung Electronics's Praesto Team");
MODULE_DESCRIPTION("Flash Friendly File System");
MODULE_LICENSE("GPL");
-MODULE_SOFTDEP("pre: crc32");
-
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index a7ec55c7bb20..d15c68b28952 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -170,6 +170,12 @@ static ssize_t undiscard_blks_show(struct f2fs_attr *a,
SM_I(sbi)->dcc_info->undiscard_blks);
}
+static ssize_t atgc_enabled_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", sbi->am.atgc_enabled ? 1 : 0);
+}
+
static ssize_t gc_mode_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -182,50 +188,50 @@ static ssize_t features_show(struct f2fs_attr *a,
int len = 0;
if (f2fs_sb_has_encrypt(sbi))
- len += scnprintf(buf, PAGE_SIZE - len, "%s",
+ len += sysfs_emit_at(buf, len, "%s",
"encryption");
if (f2fs_sb_has_blkzoned(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "blkzoned");
if (f2fs_sb_has_extra_attr(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "extra_attr");
if (f2fs_sb_has_project_quota(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "projquota");
if (f2fs_sb_has_inode_chksum(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "inode_checksum");
if (f2fs_sb_has_flexible_inline_xattr(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "flexible_inline_xattr");
if (f2fs_sb_has_quota_ino(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "quota_ino");
if (f2fs_sb_has_inode_crtime(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "inode_crtime");
if (f2fs_sb_has_lost_found(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "lost_found");
if (f2fs_sb_has_verity(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "verity");
if (f2fs_sb_has_sb_chksum(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "sb_checksum");
if (f2fs_sb_has_casefold(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "casefold");
if (f2fs_sb_has_readonly(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "readonly");
if (f2fs_sb_has_compression(sbi))
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "compression");
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len += sysfs_emit_at(buf, len, "%s%s",
len ? ", " : "", "pin_file");
- len += scnprintf(buf + len, PAGE_SIZE - len, "\n");
+ len += sysfs_emit_at(buf, len, "\n");
return len;
}
@@ -323,30 +329,27 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
int hot_count = sbi->raw_super->hot_ext_count;
int len = 0, i;
- len += scnprintf(buf + len, PAGE_SIZE - len,
- "cold file extension:\n");
+ len += sysfs_emit_at(buf, len, "cold file extension:\n");
for (i = 0; i < cold_count; i++)
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n",
- extlist[i]);
+ len += sysfs_emit_at(buf, len, "%s\n", extlist[i]);
- len += scnprintf(buf + len, PAGE_SIZE - len,
- "hot file extension:\n");
+ len += sysfs_emit_at(buf, len, "hot file extension:\n");
for (i = cold_count; i < cold_count + hot_count; i++)
- len += scnprintf(buf + len, PAGE_SIZE - len, "%s\n",
- extlist[i]);
+ len += sysfs_emit_at(buf, len, "%s\n", extlist[i]);
+
return len;
}
if (!strcmp(a->attr.name, "ckpt_thread_ioprio")) {
struct ckpt_req_control *cprc = &sbi->cprc_info;
int class = IOPRIO_PRIO_CLASS(cprc->ckpt_thread_ioprio);
- int data = IOPRIO_PRIO_DATA(cprc->ckpt_thread_ioprio);
+ int level = IOPRIO_PRIO_LEVEL(cprc->ckpt_thread_ioprio);
if (class != IOPRIO_CLASS_RT && class != IOPRIO_CLASS_BE)
return -EINVAL;
return sysfs_emit(buf, "%s,%d\n",
- class == IOPRIO_CLASS_RT ? "rt" : "be", data);
+ class == IOPRIO_CLASS_RT ? "rt" : "be", level);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -450,7 +453,7 @@ out:
const char *name = strim((char *)buf);
struct ckpt_req_control *cprc = &sbi->cprc_info;
int class;
- long data;
+ long level;
int ret;
if (!strncmp(name, "rt,", 3))
@@ -461,13 +464,13 @@ out:
return -EINVAL;
name += 3;
- ret = kstrtol(name, 10, &data);
+ ret = kstrtol(name, 10, &level);
if (ret)
return ret;
- if (data >= IOPRIO_NR_LEVELS || data < 0)
+ if (level >= IOPRIO_NR_LEVELS || level < 0)
return -EINVAL;
- cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, data);
+ cprc->ckpt_thread_ioprio = IOPRIO_PRIO_VALUE(class, level);
if (test_opt(sbi, MERGE_CHECKPOINT)) {
ret = set_task_ioprio(cprc->f2fs_issue_ckpt,
cprc->ckpt_thread_ioprio);
@@ -484,17 +487,21 @@ out:
if (ret < 0)
return ret;
#ifdef CONFIG_F2FS_FAULT_INJECTION
- if (a->struct_type == FAULT_INFO_TYPE && t >= BIT(FAULT_MAX))
- return -EINVAL;
- if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX)
- return -EINVAL;
+ if (a->struct_type == FAULT_INFO_TYPE) {
+ if (f2fs_build_fault_attr(sbi, 0, t))
+ return -EINVAL;
+ return count;
+ }
+ if (a->struct_type == FAULT_INFO_RATE) {
+ if (f2fs_build_fault_attr(sbi, t, 0))
+ return -EINVAL;
+ return count;
+ }
#endif
if (a->struct_type == RESERVED_BLOCKS) {
spin_lock(&sbi->stat_lock);
if (t > (unsigned long)(sbi->user_block_count -
- F2FS_OPTION(sbi).root_reserved_blocks -
- sbi->blocks_per_seg *
- SM_I(sbi)->additional_reserved_segments)) {
+ F2FS_OPTION(sbi).root_reserved_blocks)) {
spin_unlock(&sbi->stat_lock);
return -EINVAL;
}
@@ -551,7 +558,12 @@ out:
}
if (!strcmp(a->attr.name, "migration_granularity")) {
- if (t == 0 || t > sbi->segs_per_sec)
+ if (t == 0 || t > SEGS_PER_SEC(sbi))
+ return -EINVAL;
+ }
+
+ if (!strcmp(a->attr.name, "migration_window_granularity")) {
+ if (t == 0 || t > SEGS_PER_SEC(sbi))
return -EINVAL;
}
@@ -621,6 +633,15 @@ out:
}
#endif
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (!strcmp(a->attr.name, "blkzone_alloc_policy")) {
+ if (t < BLKZONE_ALLOC_PRIOR_SEQ || t > BLKZONE_ALLOC_PRIOR_CONV)
+ return -EINVAL;
+ sbi->blkzone_alloc_policy = t;
+ return count;
+ }
+#endif
+
#ifdef CONFIG_F2FS_FS_COMPRESSION
if (!strcmp(a->attr.name, "compr_written_block") ||
!strcmp(a->attr.name, "compr_saved_block")) {
@@ -675,6 +696,13 @@ out:
return count;
}
+ if (!strcmp(a->attr.name, "gc_pin_file_threshold")) {
+ if (t > MAX_GC_FAILED_PINNED_FILES)
+ return -EINVAL;
+ sbi->gc_pin_file_threshold = t;
+ return count;
+ }
+
if (!strcmp(a->attr.name, "gc_reclaimed_segments")) {
if (t != 0)
return -EINVAL;
@@ -759,10 +787,18 @@ out:
return count;
}
+ if (!strcmp(a->attr.name, "max_read_extent_count")) {
+ if (t > UINT_MAX)
+ return -EINVAL;
+ *ui = (unsigned int)t;
+ return count;
+ }
+
if (!strcmp(a->attr.name, "ipu_policy")) {
if (t >= BIT(F2FS_IPU_MAX))
return -EINVAL;
- if (t && f2fs_lfs_mode(sbi))
+ /* allow F2FS_IPU_NOCACHE only for IPU in the pinned file */
+ if (f2fs_lfs_mode(sbi) && (t & ~BIT(F2FS_IPU_NOCACHE)))
return -EINVAL;
SM_I(sbi)->ipu_policy = (unsigned int)t;
return count;
@@ -947,6 +983,9 @@ GC_THREAD_RW_ATTR(gc_urgent_sleep_time, urgent_sleep_time);
GC_THREAD_RW_ATTR(gc_min_sleep_time, min_sleep_time);
GC_THREAD_RW_ATTR(gc_max_sleep_time, max_sleep_time);
GC_THREAD_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time);
+GC_THREAD_RW_ATTR(gc_no_zoned_gc_percent, no_zoned_gc_percent);
+GC_THREAD_RW_ATTR(gc_boost_zoned_gc_percent, boost_zoned_gc_percent);
+GC_THREAD_RW_ATTR(gc_valid_thresh_ratio, valid_thresh_ratio);
/* SM_INFO ATTR */
SM_INFO_RW_ATTR(reclaim_segments, rec_prefree_segments);
@@ -956,6 +995,7 @@ SM_INFO_GENERAL_RW_ATTR(min_fsync_blocks);
SM_INFO_GENERAL_RW_ATTR(min_seq_blocks);
SM_INFO_GENERAL_RW_ATTR(min_hot_blocks);
SM_INFO_GENERAL_RW_ATTR(min_ssr_sections);
+SM_INFO_GENERAL_RW_ATTR(reserved_segments);
/* DCC_INFO ATTR */
DCC_INFO_RW_ATTR(max_small_discards, max_discards);
@@ -988,6 +1028,7 @@ F2FS_SBI_RW_ATTR(gc_pin_file_thresh, gc_pin_file_threshold);
F2FS_SBI_RW_ATTR(gc_reclaimed_segments, gc_reclaimed_segs);
F2FS_SBI_GENERAL_RW_ATTR(max_victim_search);
F2FS_SBI_GENERAL_RW_ATTR(migration_granularity);
+F2FS_SBI_GENERAL_RW_ATTR(migration_window_granularity);
F2FS_SBI_GENERAL_RW_ATTR(dir_level);
#ifdef CONFIG_F2FS_IOSTAT
F2FS_SBI_GENERAL_RW_ATTR(iostat_enable);
@@ -1018,8 +1059,11 @@ F2FS_SBI_GENERAL_RW_ATTR(revoked_atomic_block);
F2FS_SBI_GENERAL_RW_ATTR(hot_data_age_threshold);
F2FS_SBI_GENERAL_RW_ATTR(warm_data_age_threshold);
F2FS_SBI_GENERAL_RW_ATTR(last_age_weight);
+/* read extent cache */
+F2FS_SBI_GENERAL_RW_ATTR(max_read_extent_count);
#ifdef CONFIG_BLK_DEV_ZONED
F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec);
+F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy);
#endif
/* STAT_INFO ATTR */
@@ -1059,6 +1103,7 @@ F2FS_GENERAL_RO_ATTR(encoding);
F2FS_GENERAL_RO_ATTR(mounted_time_sec);
F2FS_GENERAL_RO_ATTR(main_blkaddr);
F2FS_GENERAL_RO_ATTR(pending_discard);
+F2FS_GENERAL_RO_ATTR(atgc_enabled);
F2FS_GENERAL_RO_ATTR(gc_mode);
#ifdef CONFIG_F2FS_STAT_FS
F2FS_GENERAL_RO_ATTR(moved_blocks_background);
@@ -1103,6 +1148,9 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(gc_min_sleep_time),
ATTR_LIST(gc_max_sleep_time),
ATTR_LIST(gc_no_gc_sleep_time),
+ ATTR_LIST(gc_no_zoned_gc_percent),
+ ATTR_LIST(gc_boost_zoned_gc_percent),
+ ATTR_LIST(gc_valid_thresh_ratio),
ATTR_LIST(gc_idle),
ATTR_LIST(gc_urgent),
ATTR_LIST(reclaim_segments),
@@ -1125,8 +1173,10 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(min_seq_blocks),
ATTR_LIST(min_hot_blocks),
ATTR_LIST(min_ssr_sections),
+ ATTR_LIST(reserved_segments),
ATTR_LIST(max_victim_search),
ATTR_LIST(migration_granularity),
+ ATTR_LIST(migration_window_granularity),
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
ATTR_LIST(ra_nid_pages),
@@ -1174,6 +1224,7 @@ static struct attribute *f2fs_attrs[] = {
#endif
#ifdef CONFIG_BLK_DEV_ZONED
ATTR_LIST(unusable_blocks_per_sec),
+ ATTR_LIST(blkzone_alloc_policy),
#endif
#ifdef CONFIG_F2FS_FS_COMPRESSION
ATTR_LIST(compr_written_block),
@@ -1187,6 +1238,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(atgc_candidate_count),
ATTR_LIST(atgc_age_weight),
ATTR_LIST(atgc_age_threshold),
+ ATTR_LIST(atgc_enabled),
ATTR_LIST(seq_file_ra_mul),
ATTR_LIST(gc_segment_mode),
ATTR_LIST(gc_reclaimed_segments),
@@ -1199,6 +1251,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(hot_data_age_threshold),
ATTR_LIST(warm_data_age_threshold),
ATTR_LIST(last_age_weight),
+ ATTR_LIST(max_read_extent_count),
NULL,
};
ATTRIBUTE_GROUPS(f2fs);
@@ -1268,6 +1321,7 @@ F2FS_SB_FEATURE_RO_ATTR(sb_checksum, SB_CHKSUM);
F2FS_SB_FEATURE_RO_ATTR(casefold, CASEFOLD);
F2FS_SB_FEATURE_RO_ATTR(compression, COMPRESSION);
F2FS_SB_FEATURE_RO_ATTR(readonly, RO);
+F2FS_SB_FEATURE_RO_ATTR(device_alias, DEVICE_ALIAS);
static struct attribute *f2fs_sb_feat_attrs[] = {
ATTR_LIST(sb_encryption),
@@ -1284,6 +1338,7 @@ static struct attribute *f2fs_sb_feat_attrs[] = {
ATTR_LIST(sb_casefold),
ATTR_LIST(sb_compression),
ATTR_LIST(sb_readonly),
+ ATTR_LIST(sb_device_alias),
NULL,
};
ATTRIBUTE_GROUPS(f2fs_sb_feat);
@@ -1417,7 +1472,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
le32_to_cpu(sbi->raw_super->segment_count_main);
int i, j;
- seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+ seq_puts(seq, "format: segment_type|valid_blocks|bitmaps|mtime\n"
"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
for (i = 0; i < total_segs; i++) {
@@ -1427,6 +1482,7 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
seq_printf(seq, "%d|%-3u|", se->type, se->valid_blocks);
for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
seq_printf(seq, " %.2x", se->cur_valid_map[j]);
+ seq_printf(seq, "| %llx", se->mtime);
seq_putc(seq, '\n');
}
return 0;
@@ -1492,6 +1548,50 @@ static int __maybe_unused discard_plist_seq_show(struct seq_file *seq,
return 0;
}
+static int __maybe_unused disk_map_seq_show(struct seq_file *seq,
+ void *offset)
+{
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ int i;
+
+ seq_printf(seq, "Address Layout : %5luB Block address (# of Segments)\n",
+ F2FS_BLKSIZE);
+ seq_printf(seq, " SB : %12s\n", "0/1024B");
+ seq_printf(seq, " seg0_blkaddr : 0x%010x\n", SEG0_BLKADDR(sbi));
+ seq_printf(seq, " Checkpoint : 0x%010x (%10d)\n",
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr), 2);
+ seq_printf(seq, " SIT : 0x%010x (%10d)\n",
+ SIT_I(sbi)->sit_base_addr,
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_sit));
+ seq_printf(seq, " NAT : 0x%010x (%10d)\n",
+ NM_I(sbi)->nat_blkaddr,
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_nat));
+ seq_printf(seq, " SSA : 0x%010x (%10d)\n",
+ SM_I(sbi)->ssa_blkaddr,
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_ssa));
+ seq_printf(seq, " Main : 0x%010x (%10d)\n",
+ SM_I(sbi)->main_blkaddr,
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->segment_count_main));
+ seq_printf(seq, " # of Sections : %12d\n",
+ le32_to_cpu(F2FS_RAW_SUPER(sbi)->section_count));
+ seq_printf(seq, " Segs/Sections : %12d\n",
+ SEGS_PER_SEC(sbi));
+ seq_printf(seq, " Section size : %12d MB\n",
+ SEGS_PER_SEC(sbi) << 1);
+
+ if (!f2fs_is_multi_device(sbi))
+ return 0;
+
+ seq_puts(seq, "\nDisk Map for multi devices:\n");
+ for (i = 0; i < sbi->s_ndevs; i++)
+ seq_printf(seq, "Disk:%2d (zoned=%d): 0x%010x - 0x%010x on %s\n",
+ i, bdev_is_zoned(FDEV(i).bdev),
+ FDEV(i).start_blk, FDEV(i).end_blk,
+ FDEV(i).path);
+ return 0;
+}
+
int __init f2fs_init_sysfs(void)
{
int ret;
@@ -1573,6 +1673,8 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
victim_bits_seq_show, sb);
proc_create_single_data("discard_plist_info", 0444, sbi->s_proc,
discard_plist_seq_show, sb);
+ proc_create_single_data("disk_map", 0444, sbi->s_proc,
+ disk_map_seq_show, sb);
return 0;
put_feature_list_kobj:
kobject_put(&sbi->s_feature_list_kobj);
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index 4fc95f353a7a..2287f238ae09 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -74,23 +74,23 @@ static int pagecache_write(struct inode *inode, const void *buf, size_t count,
struct address_space *mapping = inode->i_mapping;
const struct address_space_operations *aops = mapping->a_ops;
- if (pos + count > inode->i_sb->s_maxbytes)
+ if (pos + count > F2FS_BLK_TO_BYTES(max_file_blocks(inode)))
return -EFBIG;
while (count) {
size_t n = min_t(size_t, count,
PAGE_SIZE - offset_in_page(pos));
- struct page *page;
+ struct folio *folio;
void *fsdata = NULL;
int res;
- res = aops->write_begin(NULL, mapping, pos, n, &page, &fsdata);
+ res = aops->write_begin(NULL, mapping, pos, n, &folio, &fsdata);
if (res)
return res;
- memcpy_to_page(page, offset_in_page(pos), buf, n);
+ memcpy_to_folio(folio, offset_in_folio(folio, pos), buf, n);
- res = aops->write_end(NULL, mapping, pos, n, n, page, fsdata);
+ res = aops->write_end(NULL, mapping, pos, n, n, folio, fsdata);
if (res < 0)
return res;
if (res != n)
@@ -237,7 +237,8 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
pos = le64_to_cpu(dloc.pos);
/* Get the descriptor */
- if (pos + size < pos || pos + size > inode->i_sb->s_maxbytes ||
+ if (pos + size < pos ||
+ pos + size > F2FS_BLK_TO_BYTES(max_file_blocks(inode)) ||
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),
@@ -258,21 +259,23 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
{
- struct page *page;
+ struct folio *folio;
index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;
- page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED);
- if (!page || !PageUptodate(page)) {
+ folio = __filemap_get_folio(inode->i_mapping, index, FGP_ACCESSED, 0);
+ if (IS_ERR(folio) || !folio_test_uptodate(folio)) {
DEFINE_READAHEAD(ractl, NULL, NULL, inode->i_mapping, index);
- if (page)
- put_page(page);
+ if (!IS_ERR(folio))
+ folio_put(folio);
else if (num_ra_pages > 1)
page_cache_ra_unbounded(&ractl, num_ra_pages, 0);
- page = read_mapping_page(inode->i_mapping, index, NULL);
+ folio = read_mapping_folio(inode->i_mapping, index, NULL);
+ if (IS_ERR(folio))
+ return ERR_CAST(folio);
}
- return page;
+ return folio_file_page(folio, index);
}
static int f2fs_write_merkle_tree_block(struct inode *inode, const void *buf,
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index f290fe9327c4..3f3874943679 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -629,6 +629,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
const char *name, const void *value, size_t size,
struct page *ipage, int flags)
{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_xattr_entry *here, *last;
void *base_addr, *last_base_addr;
int found, newsize;
@@ -772,9 +773,18 @@ retry:
if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
f2fs_set_encrypted_inode(inode);
- if (S_ISDIR(inode->i_mode))
- set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
+ if (!S_ISDIR(inode->i_mode))
+ goto same;
+ /*
+ * In restrict mode, fsync() always try to trigger checkpoint for all
+ * metadata consistency, in other mode, it triggers checkpoint when
+ * parent's xattr metadata was updated.
+ */
+ if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
+ set_sbi_flag(sbi, SBI_NEED_CP);
+ else
+ f2fs_add_ino_entry(sbi, inode->i_ino, XATTR_DIR_INO);
same:
if (is_inode_flag_set(inode, FI_ACL_MODE)) {
inode->i_mode = F2FS_I(inode)->i_acl_mode;
generated by cgit (git 2.34.1) at 2025-07-31 04:20:12 +0000