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/checkpoint.c71
-rw-r--r--fs/f2fs/compress.c62
-rw-r--r--fs/f2fs/data.c259
-rw-r--r--fs/f2fs/debug.c3
-rw-r--r--fs/f2fs/dir.c2
-rw-r--r--fs/f2fs/f2fs.h249
-rw-r--r--fs/f2fs/file.c201
-rw-r--r--fs/f2fs/gc.c58
-rw-r--r--fs/f2fs/inline.c24
-rw-r--r--fs/f2fs/inode.c60
-rw-r--r--fs/f2fs/namei.c42
-rw-r--r--fs/f2fs/node.c468
-rw-r--r--fs/f2fs/node.h13
-rw-r--r--fs/f2fs/recovery.c4
-rw-r--r--fs/f2fs/segment.c289
-rw-r--r--fs/f2fs/segment.h54
-rw-r--r--fs/f2fs/shrinker.c92
-rw-r--r--fs/f2fs/super.c291
-rw-r--r--fs/f2fs/sysfs.c142
-rw-r--r--fs/f2fs/xattr.c8
21 files changed, 1533 insertions, 862 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/checkpoint.c b/fs/f2fs/checkpoint.c
index efda9a022981..cf77987d0698 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -21,7 +21,7 @@
#include "iostat.h"
#include <trace/events/f2fs.h>
-#define DEFAULT_CHECKPOINT_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+#define DEFAULT_CHECKPOINT_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 3))
static struct kmem_cache *ino_entry_slab;
struct kmem_cache *f2fs_inode_entry_slab;
@@ -58,7 +58,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
bool is_meta)
{
struct address_space *mapping = META_MAPPING(sbi);
- struct page *page;
+ struct folio *folio;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
@@ -74,37 +74,37 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
if (unlikely(!is_meta))
fio.op_flags &= ~REQ_META;
repeat:
- page = f2fs_grab_cache_page(mapping, index, false);
- if (!page) {
+ folio = f2fs_grab_cache_folio(mapping, index, false);
+ if (IS_ERR(folio)) {
cond_resched();
goto repeat;
}
- if (PageUptodate(page))
+ if (folio_test_uptodate(folio))
goto out;
- fio.page = page;
+ fio.page = &folio->page;
err = f2fs_submit_page_bio(&fio);
if (err) {
- f2fs_put_page(page, 1);
+ f2fs_folio_put(folio, true);
return ERR_PTR(err);
}
f2fs_update_iostat(sbi, NULL, FS_META_READ_IO, F2FS_BLKSIZE);
- lock_page(page);
- if (unlikely(page->mapping != mapping)) {
- f2fs_put_page(page, 1);
+ folio_lock(folio);
+ if (unlikely(folio->mapping != mapping)) {
+ f2fs_folio_put(folio, true);
goto repeat;
}
- if (unlikely(!PageUptodate(page))) {
- f2fs_handle_page_eio(sbi, page_folio(page), META);
- f2fs_put_page(page, 1);
+ if (unlikely(!folio_test_uptodate(folio))) {
+ f2fs_handle_page_eio(sbi, folio, META);
+ f2fs_folio_put(folio, true);
return ERR_PTR(-EIO);
}
out:
- return page;
+ return &folio->page;
}
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
@@ -381,12 +381,6 @@ redirty_out:
return AOP_WRITEPAGE_ACTIVATE;
}
-static int f2fs_write_meta_page(struct page *page,
- struct writeback_control *wbc)
-{
- return __f2fs_write_meta_page(page, wbc, FS_META_IO);
-}
-
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -507,7 +501,6 @@ static bool f2fs_dirty_meta_folio(struct address_space *mapping,
}
const struct address_space_operations f2fs_meta_aops = {
- .writepage = f2fs_write_meta_page,
.writepages = f2fs_write_meta_pages,
.dirty_folio = f2fs_dirty_meta_folio,
.invalidate_folio = f2fs_invalidate_folio,
@@ -1237,7 +1230,7 @@ static int block_operations(struct f2fs_sb_info *sbi)
retry_flush_quotas:
f2fs_lock_all(sbi);
if (__need_flush_quota(sbi)) {
- int locked;
+ bool need_lock = sbi->umount_lock_holder != current;
if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) {
set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
@@ -1246,11 +1239,13 @@ retry_flush_quotas:
}
f2fs_unlock_all(sbi);
- /* only failed during mount/umount/freeze/quotactl */
- locked = down_read_trylock(&sbi->sb->s_umount);
- f2fs_quota_sync(sbi->sb, -1);
- if (locked)
+ /* don't grab s_umount lock during mount/umount/remount/freeze/quotactl */
+ if (!need_lock) {
+ f2fs_do_quota_sync(sbi->sb, -1);
+ } else if (down_read_trylock(&sbi->sb->s_umount)) {
+ f2fs_do_quota_sync(sbi->sb, -1);
up_read(&sbi->sb->s_umount);
+ }
cond_resched();
goto retry_flush_quotas;
}
@@ -1344,21 +1339,13 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long flags;
- if (cpc->reason & CP_UMOUNT) {
- if (le32_to_cpu(ckpt->cp_pack_total_block_count) +
- 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) &&
- f2fs_nat_bitmap_enabled(sbi)) {
- f2fs_enable_nat_bits(sbi);
- set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
- f2fs_notice(sbi, "Rebuild and enable nat_bits");
- }
- }
-
spin_lock_irqsave(&sbi->cp_lock, flags);
+ if ((cpc->reason & CP_UMOUNT) &&
+ le32_to_cpu(ckpt->cp_pack_total_block_count) >
+ sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
+ disable_nat_bits(sbi, false);
+
if (cpc->reason & CP_TRIMMED)
__set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
else
@@ -1541,8 +1528,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
start_blk = __start_cp_next_addr(sbi);
/* write nat bits */
- if ((cpc->reason & CP_UMOUNT) &&
- is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG)) {
+ if (enabled_nat_bits(sbi, cpc)) {
__u64 cp_ver = cur_cp_version(ckpt);
block_t blk;
@@ -1867,7 +1853,8 @@ int f2fs_issue_checkpoint(struct f2fs_sb_info *sbi)
struct cp_control cpc;
cpc.reason = __get_cp_reason(sbi);
- if (!test_opt(sbi, MERGE_CHECKPOINT) || cpc.reason != CP_SYNC) {
+ if (!test_opt(sbi, MERGE_CHECKPOINT) || cpc.reason != CP_SYNC ||
+ sbi->umount_lock_holder == current) {
int ret;
f2fs_down_write(&sbi->gc_lock);
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index 7f26440e8595..5a9b6d5f3ae0 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -178,8 +178,7 @@ void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio)
#ifdef CONFIG_F2FS_FS_LZO
static int lzo_init_compress_ctx(struct compress_ctx *cc)
{
- cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
- LZO1X_MEM_COMPRESS, GFP_NOFS);
+ cc->private = f2fs_vmalloc(LZO1X_MEM_COMPRESS);
if (!cc->private)
return -ENOMEM;
@@ -189,7 +188,7 @@ static int lzo_init_compress_ctx(struct compress_ctx *cc)
static void lzo_destroy_compress_ctx(struct compress_ctx *cc)
{
- kvfree(cc->private);
+ vfree(cc->private);
cc->private = NULL;
}
@@ -246,7 +245,7 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc)
size = LZ4HC_MEM_COMPRESS;
#endif
- cc->private = f2fs_kvmalloc(F2FS_I_SB(cc->inode), size, GFP_NOFS);
+ cc->private = f2fs_vmalloc(size);
if (!cc->private)
return -ENOMEM;
@@ -261,7 +260,7 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc)
static void lz4_destroy_compress_ctx(struct compress_ctx *cc)
{
- kvfree(cc->private);
+ vfree(cc->private);
cc->private = NULL;
}
@@ -342,8 +341,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
params = zstd_get_params(level, cc->rlen);
workspace_size = zstd_cstream_workspace_bound(&params.cParams);
- workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode),
- workspace_size, GFP_NOFS);
+ workspace = f2fs_vmalloc(workspace_size);
if (!workspace)
return -ENOMEM;
@@ -351,7 +349,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
if (!stream) {
f2fs_err_ratelimited(F2FS_I_SB(cc->inode),
"%s zstd_init_cstream failed", __func__);
- kvfree(workspace);
+ vfree(workspace);
return -EIO;
}
@@ -364,7 +362,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc)
static void zstd_destroy_compress_ctx(struct compress_ctx *cc)
{
- kvfree(cc->private);
+ vfree(cc->private);
cc->private = NULL;
cc->private2 = NULL;
}
@@ -423,8 +421,7 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
workspace_size = zstd_dstream_workspace_bound(max_window_size);
- workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode),
- workspace_size, GFP_NOFS);
+ workspace = f2fs_vmalloc(workspace_size);
if (!workspace)
return -ENOMEM;
@@ -432,7 +429,7 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
if (!stream) {
f2fs_err_ratelimited(F2FS_I_SB(dic->inode),
"%s zstd_init_dstream failed", __func__);
- kvfree(workspace);
+ vfree(workspace);
return -EIO;
}
@@ -444,7 +441,7 @@ static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic)
static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic)
{
- kvfree(dic->private);
+ vfree(dic->private);
dic->private = NULL;
dic->private2 = NULL;
}
@@ -846,7 +843,7 @@ 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;
/*
@@ -860,9 +857,11 @@ 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;
}
@@ -1148,6 +1147,7 @@ retry:
f2fs_compress_ctx_add_page(cc, page_folio(page));
if (!PageUptodate(page)) {
+ f2fs_handle_page_eio(sbi, page_folio(page), DATA);
release_and_retry:
f2fs_put_rpages(cc);
f2fs_unlock_rpages(cc, i + 1);
@@ -1195,7 +1195,8 @@ 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);
@@ -1239,13 +1240,14 @@ 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;
}
}
@@ -1278,6 +1280,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
.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;
@@ -1289,7 +1292,7 @@ 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;
}
@@ -1316,7 +1319,8 @@ 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)
@@ -1339,7 +1343,7 @@ 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,
@@ -1374,7 +1378,7 @@ 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;
}
@@ -1384,7 +1388,7 @@ 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;
@@ -1545,6 +1549,7 @@ continue_unlock:
if (!clear_page_dirty_for_io(cc->rpages[i]))
goto continue_unlock;
+ submitted = 0;
ret = f2fs_write_single_data_page(page_folio(cc->rpages[i]),
&submitted,
NULL, NULL, wbc, io_type,
@@ -1903,11 +1908,12 @@ 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,
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index a2478c2afb3a..b0b8748ae287 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -53,8 +53,8 @@ bool f2fs_is_cp_guaranteed(struct page *page)
struct inode *inode;
struct f2fs_sb_info *sbi;
- if (!mapping)
- return false;
+ if (fscrypt_is_bounce_page(page))
+ return page_private_gcing(fscrypt_pagecache_page(page));
inode = mapping->host;
sbi = F2FS_I_SB(inode);
@@ -70,9 +70,9 @@ bool f2fs_is_cp_guaranteed(struct page *page)
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;
@@ -136,27 +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)
@@ -324,8 +319,7 @@ static void f2fs_read_end_io(struct bio *bio)
static void f2fs_write_end_io(struct bio *bio)
{
struct f2fs_sb_info *sbi;
- struct bio_vec *bvec;
- struct bvec_iter_all iter_all;
+ struct folio_iter fi;
iostat_update_and_unbind_ctx(bio);
sbi = bio->bi_private;
@@ -333,34 +327,41 @@ static void f2fs_write_end_io(struct bio *bio)
if (time_to_inject(sbi, FAULT_WRITE_IO))
bio->bi_status = BLK_STS_IOERR;
- bio_for_each_segment_all(bvec, bio, iter_all) {
- struct page *page = bvec->bv_page;
- enum count_type type = WB_DATA_TYPE(page, false);
+ bio_for_each_folio_all(fi, bio) {
+ struct folio *folio = fi.folio;
+ enum count_type type;
- fscrypt_finalize_bounce_page(&page);
+ if (fscrypt_is_bounce_folio(folio)) {
+ struct folio *io_folio = folio;
+
+ folio = fscrypt_pagecache_folio(io_folio);
+ fscrypt_free_bounce_page(&io_folio->page);
+ }
#ifdef CONFIG_F2FS_FS_COMPRESSION
- if (f2fs_is_compressed_page(page)) {
- f2fs_compress_write_end_io(bio, page);
+ if (f2fs_is_compressed_page(&folio->page)) {
+ f2fs_compress_write_end_io(bio, &folio->page);
continue;
}
#endif
+ type = WB_DATA_TYPE(&folio->page, false);
+
if (unlikely(bio->bi_status)) {
- mapping_set_error(page->mapping, -EIO);
+ mapping_set_error(folio->mapping, -EIO);
if (type == F2FS_WB_CP_DATA)
f2fs_stop_checkpoint(sbi, true,
STOP_CP_REASON_WRITE_FAIL);
}
- f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) &&
- page_folio(page)->index != nid_of_node(page));
+ f2fs_bug_on(sbi, folio->mapping == NODE_MAPPING(sbi) &&
+ folio->index != nid_of_node(&folio->page));
dec_page_count(sbi, type);
- if (f2fs_in_warm_node_list(sbi, page))
- f2fs_del_fsync_node_entry(sbi, page);
- clear_page_private_gcing(page);
- end_page_writeback(page);
+ if (f2fs_in_warm_node_list(sbi, folio))
+ f2fs_del_fsync_node_entry(sbi, &folio->page);
+ clear_page_private_gcing(&folio->page);
+ folio_end_writeback(folio);
}
if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
wq_has_sleeper(&sbi->cp_wait))
@@ -418,6 +419,7 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
{
unsigned int temp_mask = GENMASK(NR_TEMP_TYPE - 1, 0);
+ struct folio *fio_folio = page_folio(fio->page);
unsigned int fua_flag, meta_flag, io_flag;
blk_opf_t op_flags = 0;
@@ -443,6 +445,11 @@ static blk_opf_t f2fs_io_flags(struct f2fs_io_info *fio)
op_flags |= REQ_META;
if (BIT(fio->temp) & fua_flag)
op_flags |= REQ_FUA;
+
+ if (fio->type == DATA &&
+ F2FS_I(fio_folio->mapping->host)->ioprio_hint == F2FS_IOPRIO_WRITE)
+ op_flags |= REQ_PRIO;
+
return op_flags;
}
@@ -516,10 +523,6 @@ 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 (f2fs_lfs_mode(sbi) && current->plug && PAGE_TYPE_ON_MAIN(type))
- blk_finish_plug(current->plug);
-
trace_f2fs_submit_write_bio(sbi->sb, type, bio);
iostat_update_submit_ctx(bio, type);
submit_bio(bio);
@@ -689,33 +692,29 @@ 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)))
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,
- page_folio(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, page_folio(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, false));
+ __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);
@@ -889,12 +888,13 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
struct bio *bio = *fio->bio;
struct page *page = fio->encrypted_page ?
fio->encrypted_page : fio->page;
+ struct folio *folio = page_folio(fio->page);
if (!f2fs_is_valid_blkaddr(fio->sbi, fio->new_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))
@@ -902,8 +902,8 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_VECS);
- f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
- page_folio(fio->page)->index, fio, GFP_NOIO);
+ f2fs_set_bio_crypt_ctx(bio, folio->mapping->host,
+ folio->index, fio, GFP_NOIO);
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
@@ -912,8 +912,7 @@ alloc_new:
}
if (fio->io_wbc)
- wbc_account_cgroup_owner(fio->io_wbc, page_folio(fio->page),
- PAGE_SIZE);
+ wbc_account_cgroup_owner(fio->io_wbc, folio, folio_size(folio));
inc_page_count(fio->sbi, WB_DATA_TYPE(page, false));
@@ -1018,7 +1017,7 @@ alloc_new:
io->last_block_in_bio = fio->new_blkaddr;
- trace_f2fs_submit_page_write(fio->page, fio);
+ 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)) {
@@ -1054,8 +1053,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
bio = bio_alloc_bioset(bdev, bio_max_segs(nr_pages),
REQ_OP_READ | op_flag,
for_write ? GFP_NOIO : GFP_KERNEL, &f2fs_bioset);
- if (!bio)
- return ERR_PTR(-ENOMEM);
bio->bi_iter.bi_sector = sector;
f2fs_set_bio_crypt_ctx(bio, inode, first_idx, NULL, GFP_NOFS);
bio->bi_end_io = f2fs_read_end_io;
@@ -1206,18 +1203,17 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
return err;
}
-struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
- blk_opf_t op_flags, bool for_write,
- pgoff_t *next_pgofs)
+struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
+ blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
- struct page *page;
+ struct folio *folio;
int err;
- page = f2fs_grab_cache_page(mapping, index, for_write);
- if (!page)
- return ERR_PTR(-ENOMEM);
+ folio = f2fs_grab_cache_folio(mapping, index, for_write);
+ if (IS_ERR(folio))
+ return folio;
if (f2fs_lookup_read_extent_cache_block(inode, index,
&dn.data_blkaddr)) {
@@ -1252,9 +1248,9 @@ struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
goto put_err;
}
got_it:
- if (PageUptodate(page)) {
- unlock_page(page);
- return page;
+ if (folio_test_uptodate(folio)) {
+ folio_unlock(folio);
+ return folio;
}
/*
@@ -1265,48 +1261,51 @@ got_it:
* f2fs_init_inode_metadata.
*/
if (dn.data_blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_SIZE);
- if (!PageUptodate(page))
- SetPageUptodate(page);
- unlock_page(page);
- return page;
+ folio_zero_segment(folio, 0, folio_size(folio));
+ if (!folio_test_uptodate(folio))
+ folio_mark_uptodate(folio);
+ folio_unlock(folio);
+ return folio;
}
- err = f2fs_submit_page_read(inode, page_folio(page), dn.data_blkaddr,
+ err = f2fs_submit_page_read(inode, folio, dn.data_blkaddr,
op_flags, for_write);
if (err)
goto put_err;
- return page;
+ return folio;
put_err:
- f2fs_put_page(page, 1);
+ f2fs_folio_put(folio, true);
return ERR_PTR(err);
}
-struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
+struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
pgoff_t *next_pgofs)
{
struct address_space *mapping = inode->i_mapping;
- struct page *page;
+ struct folio *folio;
- page = find_get_page(mapping, index);
- if (page && PageUptodate(page))
- return page;
- f2fs_put_page(page, 0);
+ folio = __filemap_get_folio(mapping, index, FGP_ACCESSED, 0);
+ if (IS_ERR(folio))
+ goto read;
+ if (folio_test_uptodate(folio))
+ return folio;
+ f2fs_folio_put(folio, false);
- page = f2fs_get_read_data_page(inode, index, 0, false, next_pgofs);
- if (IS_ERR(page))
- return page;
+read:
+ folio = f2fs_get_read_data_folio(inode, index, 0, false, next_pgofs);
+ if (IS_ERR(folio))
+ return folio;
- if (PageUptodate(page))
- return page;
+ if (folio_test_uptodate(folio))
+ return folio;
- wait_on_page_locked(page);
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 0);
+ folio_wait_locked(folio);
+ if (unlikely(!folio_test_uptodate(folio))) {
+ f2fs_folio_put(folio, false);
return ERR_PTR(-EIO);
}
- return page;
+ return folio;
}
/*
@@ -1314,23 +1313,23 @@ struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
-struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
+struct folio *f2fs_get_lock_data_folio(struct inode *inode, pgoff_t index,
bool for_write)
{
struct address_space *mapping = inode->i_mapping;
- struct page *page;
+ struct folio *folio;
- page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL);
- if (IS_ERR(page))
- return page;
+ folio = f2fs_get_read_data_folio(inode, index, 0, for_write, NULL);
+ if (IS_ERR(folio))
+ return folio;
/* wait for read completion */
- lock_page(page);
- if (unlikely(page->mapping != mapping || !PageUptodate(page))) {
- f2fs_put_page(page, 1);
+ folio_lock(folio);
+ if (unlikely(folio->mapping != mapping || !folio_test_uptodate(folio))) {
+ f2fs_folio_put(folio, true);
return ERR_PTR(-EIO);
}
- return page;
+ return folio;
}
/*
@@ -1423,7 +1422,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
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;
@@ -2191,6 +2190,12 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
int i;
int ret = 0;
+ if (unlikely(f2fs_cp_error(sbi))) {
+ ret = -EIO;
+ from_dnode = false;
+ goto out_put_dnode;
+ }
+
f2fs_bug_on(sbi, f2fs_cluster_is_empty(cc));
last_block_in_file = F2FS_BYTES_TO_BLK(f2fs_readpage_limit(inode) +
@@ -2234,10 +2239,6 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
if (ret)
goto out;
- if (unlikely(f2fs_cp_error(sbi))) {
- ret = -EIO;
- goto out_put_dnode;
- }
f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
skip_reading_dnode:
@@ -2464,7 +2465,7 @@ next_page:
static int f2fs_read_data_folio(struct file *file, struct folio *folio)
{
- struct inode *inode = folio_file_mapping(folio)->host;
+ struct inode *inode = folio->mapping->host;
int ret = -EAGAIN;
trace_f2fs_readpage(folio, DATA);
@@ -2513,7 +2514,7 @@ int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
return 0;
retry_encrypt:
- fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page,
+ fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page_folio(page),
PAGE_SIZE, 0, gfp_flags);
if (IS_ERR(fio->encrypted_page)) {
/* flush pending IOs and wait for a while in the ENOMEM case */
@@ -2934,29 +2935,6 @@ redirty_out:
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 = 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, folio->index)) {
- folio_redirty_for_writepage(wbc, folio);
- return AOP_WRITEPAGE_ACTIVATE;
- }
- }
-out:
-#endif
-
- return f2fs_write_single_data_page(folio, NULL, NULL, NULL,
- wbc, FS_DATA_IO, 0, true);
-}
-
/*
* This function was copied from write_cache_pages from mm/page-writeback.c.
* The major change is making write step of cold data page separately from
@@ -3163,6 +3141,7 @@ continue_unlock:
continue;
}
#endif
+ submitted = 0;
ret = f2fs_write_single_data_page(folio,
&submitted, &bio, &last_block,
wbc, io_type, 0, true);
@@ -3278,10 +3257,6 @@ static int __f2fs_write_data_pages(struct address_space *mapping,
int ret;
bool locked = false;
- /* deal with chardevs and other special file */
- if (!mapping->a_ops->writepage)
- return 0;
-
/* skip writing if there is no dirty page in this inode */
if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
return 0;
@@ -3402,7 +3377,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
restart:
/* check inline_data */
- ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
@@ -3465,7 +3440,7 @@ static int __find_data_block(struct inode *inode, pgoff_t index,
struct page *ipage;
int err = 0;
- ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@@ -3495,7 +3470,7 @@ static int __reserve_data_block(struct inode *inode, pgoff_t index,
f2fs_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO);
- ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto unlock_out;
@@ -3991,7 +3966,7 @@ retry:
if ((pblock - SM_I(sbi)->main_blkaddr) % blks_per_sec ||
nr_pblocks % blks_per_sec ||
- !f2fs_valid_pinned_area(sbi, pblock)) {
+ f2fs_is_sequential_zone_area(sbi, pblock)) {
bool last_extent = false;
not_aligned++;
@@ -4043,7 +4018,6 @@ retry:
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)",
@@ -4114,7 +4088,6 @@ static void f2fs_swap_deactivate(struct file *file)
const struct address_space_operations f2fs_dblock_aops = {
.read_folio = f2fs_read_data_folio,
.readahead = f2fs_readahead,
- .writepage = f2fs_write_data_page,
.writepages = f2fs_write_data_pages,
.write_begin = f2fs_write_begin,
.write_end = f2fs_write_end,
@@ -4208,7 +4181,13 @@ static int f2fs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
map.m_next_pgofs = &next_pgofs;
map.m_seg_type = f2fs_rw_hint_to_seg_type(F2FS_I_SB(inode),
inode->i_write_hint);
- if (flags & IOMAP_WRITE)
+
+ /*
+ * If the blocks being overwritten are already allocated,
+ * f2fs_map_lock and f2fs_balance_fs are not necessary.
+ */
+ if ((flags & IOMAP_WRITE) &&
+ !f2fs_overwrite_io(inode, offset, length))
map.m_may_create = true;
err = f2fs_map_blocks(inode, &map, F2FS_GET_BLOCK_DIO);
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 468828288a4a..16c2dfb4f595 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -164,6 +164,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+ si->ndonate_files = sbi->donate_files;
si->nquota_files = sbi->nquota_files;
si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
si->aw_cnt = atomic_read(&sbi->atomic_files);
@@ -501,6 +502,8 @@ static int stat_show(struct seq_file *s, void *v)
si->compr_inode, si->compr_blocks);
seq_printf(s, " - Swapfile Inode: %u\n",
si->swapfile_inode);
+ seq_printf(s, " - Donate Inode: %u\n",
+ si->ndonate_files);
seq_printf(s, " - Orphan/Append/Update Inode: %u, %u, %u\n",
si->orphans, si->append, si->update);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 54dd52de7269..5a63ff0df03b 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -551,7 +551,7 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
goto put_error;
}
} else {
- page = f2fs_get_node_page(F2FS_I_SB(dir), inode->i_ino);
+ page = f2fs_get_inode_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
return page;
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index da199fdfebfc..34e4ae2a5f5b 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -24,7 +24,6 @@
#include <linux/quotaops.h>
#include <linux/part_stat.h>
#include <linux/rw_hint.h>
-#include <crypto/hash.h>
#include <linux/fscrypt.h>
#include <linux/fsverity.h>
@@ -63,6 +62,7 @@ enum {
FAULT_BLKADDR_VALIDITY,
FAULT_BLKADDR_CONSISTENCE,
FAULT_NO_SEGMENT,
+ FAULT_INCONSISTENT_FOOTER,
FAULT_MAX,
};
@@ -115,6 +115,13 @@ extern const char *f2fs_fault_name[FAULT_MAX];
#define F2FS_MOUNT_GC_MERGE 0x02000000
#define F2FS_MOUNT_COMPRESS_CACHE 0x04000000
#define F2FS_MOUNT_AGE_EXTENT_CACHE 0x08000000
+#define F2FS_MOUNT_NAT_BITS 0x10000000
+#define F2FS_MOUNT_INLINECRYPT 0x20000000
+/*
+ * Some f2fs environments expect to be able to pass the "lazytime" option
+ * string rather than using the MS_LAZYTIME flag, so this must remain.
+ */
+#define F2FS_MOUNT_LAZYTIME 0x40000000
#define F2FS_OPTION(sbi) ((sbi)->mount_opt)
#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option)
@@ -831,6 +838,7 @@ struct f2fs_inode_info {
/* Use below internally in f2fs*/
unsigned long flags[BITS_TO_LONGS(FI_MAX)]; /* use to pass per-file flags */
+ unsigned int ioprio_hint; /* hint for IO priority */
struct f2fs_rwsem i_sem; /* protect fi info */
atomic_t dirty_pages; /* # of dirty pages */
f2fs_hash_t chash; /* hash value of given file name */
@@ -850,6 +858,11 @@ struct f2fs_inode_info {
#endif
struct list_head dirty_list; /* dirty list for dirs and files */
struct list_head gdirty_list; /* linked in global dirty list */
+
+ /* linked in global inode list for cache donation */
+ struct list_head gdonate_list;
+ pgoff_t donate_start, donate_end; /* inclusive */
+
struct task_struct *atomic_write_task; /* store atomic write task */
struct extent_tree *extent_tree[NR_EXTENT_CACHES];
/* cached extent_tree entry */
@@ -1274,6 +1287,7 @@ enum inode_type {
DIR_INODE, /* for dirty dir inode */
FILE_INODE, /* for dirty regular/symlink inode */
DIRTY_META, /* for all dirtied inode metadata */
+ DONATE_INODE, /* for all inode to donate pages */
NR_INODE_TYPE,
};
@@ -1629,6 +1643,9 @@ struct f2fs_sb_info {
unsigned int warm_data_age_threshold;
unsigned int last_age_weight;
+ /* control donate caches */
+ unsigned int donate_files;
+
/* basic filesystem units */
unsigned int log_sectors_per_block; /* log2 sectors per block */
unsigned int log_blocksize; /* log2 block size */
@@ -1660,6 +1677,7 @@ struct f2fs_sb_info {
unsigned int nquota_files; /* # of quota sysfile */
struct f2fs_rwsem quota_sem; /* blocking cp for flags */
+ struct task_struct *umount_lock_holder; /* s_umount lock holder */
/* # of pages, see count_type */
atomic_t nr_pages[NR_COUNT_TYPE];
@@ -1762,15 +1780,12 @@ 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 */
+ unsigned int first_seq_zone_segno; /* first segno in sequential zone */
/* 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;
@@ -1804,6 +1819,9 @@ struct f2fs_sb_info {
u64 committed_atomic_block;
u64 revoked_atomic_block;
+ /* carve out reserved_blocks from total blocks */
+ bool carve_out;
+
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct kmem_cache *page_array_slab; /* page array entry */
unsigned int page_array_slab_size; /* default page array slab size */
@@ -1948,21 +1966,7 @@ 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,
@@ -2003,9 +2007,14 @@ 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)
@@ -2028,7 +2037,7 @@ static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
return (struct f2fs_checkpoint *)(sbi->ckpt);
}
-static inline struct f2fs_node *F2FS_NODE(struct page *page)
+static inline struct f2fs_node *F2FS_NODE(const struct page *page)
{
return (struct f2fs_node *)page_address(page);
}
@@ -2232,6 +2241,36 @@ static inline void f2fs_up_write(struct f2fs_rwsem *sem)
#endif
}
+static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
+{
+ unsigned long flags;
+ unsigned char *nat_bits;
+
+ /*
+ * In order to re-enable nat_bits we need to call fsck.f2fs by
+ * set_sbi_flag(sbi, SBI_NEED_FSCK). But it may give huge cost,
+ * so let's rely on regular fsck or unclean shutdown.
+ */
+
+ if (lock)
+ spin_lock_irqsave(&sbi->cp_lock, flags);
+ __clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
+ nat_bits = NM_I(sbi)->nat_bits;
+ NM_I(sbi)->nat_bits = NULL;
+ if (lock)
+ spin_unlock_irqrestore(&sbi->cp_lock, flags);
+
+ kvfree(nat_bits);
+}
+
+static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc)
+{
+ bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
+
+ return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
+}
+
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
f2fs_down_read(&sbi->cp_rwsem);
@@ -2479,8 +2518,14 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;
spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
- sbi->total_valid_block_count -= (block_t)count;
+ if (unlikely(sbi->total_valid_block_count < count)) {
+ f2fs_warn(sbi, "Inconsistent total_valid_block_count:%u, ino:%lu, count:%u",
+ sbi->total_valid_block_count, inode->i_ino, count);
+ sbi->total_valid_block_count = 0;
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ } else {
+ sbi->total_valid_block_count -= count;
+ }
if (sbi->reserved_blocks &&
sbi->current_reserved_blocks < sbi->reserved_blocks)
sbi->current_reserved_blocks = min(sbi->reserved_blocks,
@@ -2778,33 +2823,46 @@ static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
}
-static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
- pgoff_t index, bool for_write)
+static inline struct folio *f2fs_grab_cache_folio(struct address_space *mapping,
+ pgoff_t index, bool for_write)
{
- struct page *page;
+ struct folio *folio;
unsigned int flags;
if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) {
+ fgf_t fgf_flags;
+
if (!for_write)
- page = find_get_page_flags(mapping, index,
- FGP_LOCK | FGP_ACCESSED);
+ fgf_flags = FGP_LOCK | FGP_ACCESSED;
else
- page = find_lock_page(mapping, index);
- if (page)
- return page;
+ fgf_flags = FGP_LOCK;
+ folio = __filemap_get_folio(mapping, index, fgf_flags, 0);
+ if (!IS_ERR(folio))
+ return folio;
if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC))
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
if (!for_write)
- return grab_cache_page(mapping, index);
+ return filemap_grab_folio(mapping, index);
flags = memalloc_nofs_save();
- page = grab_cache_page_write_begin(mapping, index);
+ folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
+ mapping_gfp_mask(mapping));
memalloc_nofs_restore(flags);
- return page;
+ return folio;
+}
+
+static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
+ pgoff_t index, bool for_write)
+{
+ struct folio *folio = f2fs_grab_cache_folio(mapping, index, for_write);
+
+ if (IS_ERR(folio))
+ return NULL;
+ return &folio->page;
}
static inline struct page *f2fs_pagecache_get_page(
@@ -2817,16 +2875,23 @@ static inline struct page *f2fs_pagecache_get_page(
return pagecache_get_page(mapping, index, fgp_flags, gfp_mask);
}
-static inline void f2fs_put_page(struct page *page, int unlock)
+static inline void f2fs_folio_put(struct folio *folio, bool unlock)
{
- if (!page)
+ if (!folio)
return;
if (unlock) {
- f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
- unlock_page(page);
+ f2fs_bug_on(F2FS_F_SB(folio), !folio_test_locked(folio));
+ folio_unlock(folio);
}
- put_page(page);
+ folio_put(folio);
+}
+
+static inline void f2fs_put_page(struct page *page, int unlock)
+{
+ if (!page)
+ return;
+ f2fs_folio_put(page_folio(page), unlock);
}
static inline void f2fs_put_dnode(struct dnode_of_data *dn)
@@ -3462,6 +3527,11 @@ static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi,
return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO);
}
+static inline void *f2fs_vmalloc(size_t size)
+{
+ return vmalloc(size);
+}
+
static inline int get_extra_isize(struct inode *inode)
{
return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
@@ -3637,7 +3707,7 @@ int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
int f2fs_dquot_initialize(struct inode *inode);
int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly);
-int f2fs_quota_sync(struct super_block *sb, int type);
+int f2fs_do_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);
@@ -3660,7 +3730,8 @@ struct node_info;
int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type);
-bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page);
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi,
+ const struct folio *folio);
void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi);
void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page);
void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi);
@@ -3675,12 +3746,14 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from);
int f2fs_truncate_xattr_node(struct inode *inode);
int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi,
unsigned int seq_id);
-bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi);
int f2fs_remove_inode_page(struct inode *inode);
struct page *f2fs_new_inode_page(struct inode *inode);
struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs);
void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
+struct folio *f2fs_get_inode_folio(struct f2fs_sb_info *sbi, pgoff_t ino);
+struct page *f2fs_get_inode_page(struct f2fs_sb_info *sbi, pgoff_t ino);
+struct page *f2fs_get_xnode_page(struct f2fs_sb_info *sbi, pgoff_t xnid);
struct page *f2fs_get_node_page_ra(struct page *parent, int start);
int f2fs_move_node_page(struct page *node_page, int gc_type);
void f2fs_flush_inline_data(struct f2fs_sb_info *sbi);
@@ -3700,7 +3773,6 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page);
int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
int f2fs_restore_node_summary(struct f2fs_sb_info *sbi,
unsigned int segno, struct f2fs_summary_block *sum);
-void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi);
int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
int f2fs_build_node_manager(struct f2fs_sb_info *sbi);
void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi);
@@ -3719,7 +3791,8 @@ 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);
@@ -3770,8 +3843,10 @@ int f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
struct f2fs_io_info *fio);
void f2fs_update_device_state(struct f2fs_sb_info *sbi, nid_t ino,
block_t blkaddr, unsigned int blkcnt);
-void f2fs_wait_on_page_writeback(struct page *page,
- enum page_type type, bool ordered, bool locked);
+void f2fs_folio_wait_writeback(struct folio *folio, enum page_type type,
+ bool ordered, bool locked);
+#define f2fs_wait_on_page_writeback(page, type, ordered, locked) \
+ f2fs_folio_wait_writeback(page_folio(page), type, ordered, locked)
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
block_t len);
@@ -3883,11 +3958,11 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block_locked(struct dnode_of_data *dn, pgoff_t index);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
-struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
- blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs);
-struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index,
- pgoff_t *next_pgofs);
-struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
+struct folio *f2fs_get_read_data_folio(struct inode *inode, pgoff_t index,
+ blk_opf_t op_flags, bool for_write, pgoff_t *next_pgofs);
+struct folio *f2fs_find_data_folio(struct inode *inode, pgoff_t index,
+ pgoff_t *next_pgofs);
+struct folio *f2fs_get_lock_data_folio(struct inode *inode, pgoff_t index,
bool for_write);
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size);
@@ -3914,6 +3989,22 @@ int f2fs_init_post_read_wq(struct f2fs_sb_info *sbi);
void f2fs_destroy_post_read_wq(struct f2fs_sb_info *sbi);
extern const struct iomap_ops f2fs_iomap_ops;
+static inline struct page *f2fs_find_data_page(struct inode *inode,
+ pgoff_t index, pgoff_t *next_pgofs)
+{
+ struct folio *folio = f2fs_find_data_folio(inode, index, next_pgofs);
+
+ return &folio->page;
+}
+
+static inline struct page *f2fs_get_lock_data_page(struct inode *inode,
+ pgoff_t index, bool for_write)
+{
+ struct folio *folio = f2fs_get_lock_data_folio(inode, index, for_write);
+
+ return &folio->page;
+}
+
/*
* gc.c
*/
@@ -3978,7 +4069,8 @@ struct f2fs_stat_info {
unsigned long long allocated_data_blocks;
int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta;
int ndirty_data, ndirty_qdata;
- unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all;
+ unsigned int ndirty_dirs, ndirty_files, ndirty_all;
+ unsigned int nquota_files, ndonate_files;
int nats, dirty_nats, sits, dirty_sits;
int free_nids, avail_nids, alloc_nids;
int total_count, utilization;
@@ -4243,6 +4335,8 @@ unsigned long f2fs_shrink_count(struct shrinker *shrink,
struct shrink_control *sc);
unsigned long f2fs_shrink_scan(struct shrinker *shrink,
struct shrink_control *sc);
+unsigned int f2fs_donate_files(void);
+void f2fs_reclaim_caches(unsigned int reclaim_caches_kb);
void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
@@ -4388,7 +4482,8 @@ 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,
@@ -4443,8 +4538,8 @@ 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,
@@ -4538,12 +4633,16 @@ 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,
- block_t blkaddr)
+static inline bool f2fs_zone_is_seq(struct f2fs_sb_info *sbi, int devi,
+ unsigned int zone)
{
- unsigned int zno = blkaddr / sbi->blocks_per_blkz;
+ return test_bit(zone, FDEV(devi).blkz_seq);
+}
- return test_bit(zno, FDEV(devi).blkz_seq);
+static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,
+ block_t blkaddr)
+{
+ return f2fs_zone_is_seq(sbi, devi, blkaddr / sbi->blocks_per_blkz);
}
#endif
@@ -4615,15 +4714,31 @@ 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,
+static inline bool f2fs_is_sequential_zone_area(struct f2fs_sb_info *sbi,
block_t blkaddr)
{
if (f2fs_sb_has_blkzoned(sbi)) {
+#ifdef CONFIG_BLK_DEV_ZONED
int devi = f2fs_target_device_index(sbi, blkaddr);
- return !bdev_is_zoned(FDEV(devi).bdev);
+ if (!bdev_is_zoned(FDEV(devi).bdev))
+ return false;
+
+ if (f2fs_is_multi_device(sbi)) {
+ if (blkaddr < FDEV(devi).start_blk ||
+ blkaddr > FDEV(devi).end_blk) {
+ f2fs_err(sbi, "Invalid block %x", blkaddr);
+ return false;
+ }
+ blkaddr -= FDEV(devi).start_blk;
+ }
+
+ return f2fs_blkz_is_seq(sbi, devi, blkaddr);
+#else
+ return false;
+#endif
}
- return true;
+ return false;
}
static inline bool f2fs_low_mem_mode(struct f2fs_sb_info *sbi)
@@ -4760,10 +4875,10 @@ static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi,
}
static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi,
- block_t blkaddr)
+ block_t blkaddr, unsigned int len)
{
- f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1);
- 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 aa9679b3d8e4..f2de3c886c08 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -35,6 +35,17 @@
#include <trace/events/f2fs.h>
#include <uapi/linux/f2fs.h>
+static void f2fs_zero_post_eof_page(struct inode *inode, loff_t new_size)
+{
+ loff_t old_size = i_size_read(inode);
+
+ if (old_size >= new_size)
+ return;
+
+ /* zero or drop pages only in range of [old_size, new_size] */
+ truncate_pagecache(inode, old_size);
+}
+
static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -103,8 +114,13 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT);
+ filemap_invalidate_unlock(inode->i_mapping);
+
file_update_time(vmf->vma->vm_file);
filemap_invalidate_lock_shared(inode->i_mapping);
+
folio_lock(folio);
if (unlikely(folio->mapping != inode->i_mapping ||
folio_pos(folio) > i_size_read(inode) ||
@@ -621,8 +637,11 @@ 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++) {
@@ -638,26 +657,44 @@ 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 (time_to_inject(sbi, FAULT_BLKADDR_CONSISTENCE))
- continue;
+ goto next;
if (!f2fs_is_valid_blkaddr_raw(sbi, blkaddr,
DATA_GENERIC_ENHANCE))
- continue;
+ 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);
@@ -686,31 +723,33 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
loff_t offset = from & (PAGE_SIZE - 1);
pgoff_t index = from >> PAGE_SHIFT;
struct address_space *mapping = inode->i_mapping;
- struct page *page;
+ struct folio *folio;
if (!offset && !cache_only)
return 0;
if (cache_only) {
- page = find_lock_page(mapping, index);
- if (page && PageUptodate(page))
+ folio = filemap_lock_folio(mapping, index);
+ if (IS_ERR(folio))
+ return 0;
+ if (folio_test_uptodate(folio))
goto truncate_out;
- f2fs_put_page(page, 1);
+ f2fs_folio_put(folio, true);
return 0;
}
- page = f2fs_get_lock_data_page(inode, index, true);
- if (IS_ERR(page))
- return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
+ folio = f2fs_get_lock_data_folio(inode, index, true);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio) == -ENOENT ? 0 : PTR_ERR(folio);
truncate_out:
- f2fs_wait_on_page_writeback(page, DATA, true, true);
- zero_user(page, offset, PAGE_SIZE - offset);
+ f2fs_folio_wait_writeback(folio, DATA, true, true);
+ folio_zero_segment(folio, offset, folio_size(folio));
/* An encrypted inode should have a key and truncate the last page. */
f2fs_bug_on(F2FS_I_SB(inode), cache_only && IS_ENCRYPTED(inode));
if (!cache_only)
- set_page_dirty(page);
- f2fs_put_page(page, 1);
+ folio_mark_dirty(folio);
+ f2fs_folio_put(folio, true);
return 0;
}
@@ -738,7 +777,7 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
if (lock)
f2fs_lock_op(sbi);
- ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
@@ -747,10 +786,8 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
if (IS_DEVICE_ALIASING(inode)) {
struct extent_tree *et = F2FS_I(inode)->extent_tree[EX_READ];
struct extent_info ei = et->largest;
- unsigned int i;
- for (i = 0; i < ei.len; i++)
- f2fs_invalidate_blocks(sbi, ei.blk + i);
+ f2fs_invalidate_blocks(sbi, ei.blk, ei.len);
dec_valid_block_count(sbi, inode, ei.len);
f2fs_update_time(sbi, REQ_TIME);
@@ -1085,6 +1122,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
+ if (attr->ia_size > old_size)
+ f2fs_zero_post_eof_page(inode, attr->ia_size);
truncate_setsize(inode, attr->ia_size);
if (attr->ia_size <= old_size)
@@ -1203,6 +1242,10 @@ static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+ filemap_invalidate_unlock(inode->i_mapping);
+
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
@@ -1323,7 +1366,7 @@ 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);
}
@@ -1486,6 +1529,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+
f2fs_lock_op(sbi);
f2fs_drop_extent_tree(inode);
truncate_pagecache(inode, offset);
@@ -1575,7 +1620,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
break;
}
- f2fs_invalidate_blocks(sbi, dn->data_blkaddr);
+ f2fs_invalidate_blocks(sbi, dn->data_blkaddr, 1);
f2fs_set_data_blkaddr(dn, NEW_ADDR);
}
@@ -1607,6 +1652,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
if (ret)
return ret;
+ filemap_invalidate_lock(mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+ filemap_invalidate_unlock(mapping);
+
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
@@ -1738,6 +1787,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
/* avoid gc operation during block exchange */
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(mapping);
+
+ f2fs_zero_post_eof_page(inode, offset + len);
truncate_pagecache(inode, offset);
while (!ret && idx > pg_start) {
@@ -1795,6 +1846,10 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
if (err)
return err;
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+ filemap_invalidate_unlock(inode->i_mapping);
+
f2fs_balance_fs(sbi, true);
pg_start = ((unsigned long long)offset) >> PAGE_SHIFT;
@@ -1815,18 +1870,32 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
map.m_len = sec_blks;
next_alloc:
+ f2fs_down_write(&sbi->pin_sem);
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
+ if (has_not_enough_free_secs(sbi, 0, 0)) {
+ f2fs_up_write(&sbi->pin_sem);
+ err = -ENOSPC;
+ f2fs_warn_ratelimited(sbi,
+ "ino:%lu, start:%lu, end:%lu, need to trigger GC to "
+ "reclaim enough free segment when checkpoint is enabled",
+ inode->i_ino, pg_start, pg_end);
+ goto out_err;
+ }
+ }
+
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);
err = f2fs_gc(sbi, &gc_control);
- if (err && err != -ENODATA)
+ if (err && err != -ENODATA) {
+ f2fs_up_write(&sbi->pin_sem);
goto out_err;
+ }
}
- f2fs_down_write(&sbi->pin_sem);
-
err = f2fs_allocate_pinning_section(sbi);
if (err) {
f2fs_up_write(&sbi->pin_sem);
@@ -2429,6 +2498,52 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
return ret;
}
+static void f2fs_keep_noreuse_range(struct inode *inode,
+ loff_t offset, loff_t len)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ u64 max_bytes = F2FS_BLK_TO_BYTES(max_file_blocks(inode));
+ u64 start, end;
+
+ if (!S_ISREG(inode->i_mode))
+ return;
+
+ if (offset >= max_bytes || len > max_bytes ||
+ (offset + len) > max_bytes)
+ return;
+
+ start = offset >> PAGE_SHIFT;
+ end = DIV_ROUND_UP(offset + len, PAGE_SIZE);
+
+ inode_lock(inode);
+ if (f2fs_is_atomic_file(inode)) {
+ inode_unlock(inode);
+ return;
+ }
+
+ spin_lock(&sbi->inode_lock[DONATE_INODE]);
+ /* let's remove the range, if len = 0 */
+ if (!len) {
+ if (!list_empty(&F2FS_I(inode)->gdonate_list)) {
+ list_del_init(&F2FS_I(inode)->gdonate_list);
+ sbi->donate_files--;
+ }
+ } else {
+ if (list_empty(&F2FS_I(inode)->gdonate_list)) {
+ list_add_tail(&F2FS_I(inode)->gdonate_list,
+ &sbi->inode_list[DONATE_INODE]);
+ sbi->donate_files++;
+ } else {
+ list_move_tail(&F2FS_I(inode)->gdonate_list,
+ &sbi->inode_list[DONATE_INODE]);
+ }
+ F2FS_I(inode)->donate_start = start;
+ F2FS_I(inode)->donate_end = end - 1;
+ }
+ spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+ inode_unlock(inode);
+}
+
static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -3427,6 +3542,23 @@ static int f2fs_ioc_get_dev_alias_file(struct file *filp, unsigned long arg)
(u32 __user *)arg);
}
+static int f2fs_ioc_io_prio(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ __u32 level;
+
+ if (get_user(level, (__u32 __user *)arg))
+ return -EFAULT;
+
+ if (!S_ISREG(inode->i_mode) || level >= F2FS_IOPRIO_MAX)
+ return -EINVAL;
+
+ inode_lock(inode);
+ F2FS_I(inode)->ioprio_hint = level;
+ inode_unlock(inode);
+ return 0;
+}
+
int f2fs_precache_extents(struct inode *inode)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -4528,6 +4660,8 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_compress_file(filp);
case F2FS_IOC_GET_DEV_ALIAS_FILE:
return f2fs_ioc_get_dev_alias_file(filp, arg);
+ case F2FS_IOC_IO_PRIO:
+ return f2fs_ioc_io_prio(filp, arg);
default:
return -ENOTTY;
}
@@ -4746,6 +4880,10 @@ static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from)
err = file_modified(file);
if (err)
return err;
+
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, iocb->ki_pos + iov_iter_count(from));
+ filemap_invalidate_unlock(inode->i_mapping);
return count;
}
@@ -5128,12 +5266,16 @@ static int f2fs_file_fadvise(struct file *filp, loff_t offset, loff_t len,
}
err = generic_fadvise(filp, offset, len, advice);
- if (!err && advice == POSIX_FADV_DONTNEED &&
- test_opt(F2FS_I_SB(inode), COMPRESS_CACHE) &&
- f2fs_compressed_file(inode))
- f2fs_invalidate_compress_pages(F2FS_I_SB(inode), inode->i_ino);
+ if (err)
+ return err;
- return err;
+ if (advice == POSIX_FADV_DONTNEED &&
+ (test_opt(F2FS_I_SB(inode), COMPRESS_CACHE) &&
+ f2fs_compressed_file(inode)))
+ f2fs_invalidate_compress_pages(F2FS_I_SB(inode), inode->i_ino);
+ else if (advice == POSIX_FADV_NOREUSE)
+ f2fs_keep_noreuse_range(inode, offset, len);
+ return 0;
}
#ifdef CONFIG_COMPAT
@@ -5242,6 +5384,7 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_DECOMPRESS_FILE:
case F2FS_IOC_COMPRESS_FILE:
case F2FS_IOC_GET_DEV_ALIAS_FILE:
+ case F2FS_IOC_IO_PRIO:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 3e1b6d2ff3a7..8b5a55b72264 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -806,11 +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;
@@ -1412,7 +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))
@@ -1446,14 +1449,14 @@ out:
}
static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
- unsigned int segno, int off)
+ unsigned int segno, int off)
{
- struct page *page;
+ struct folio *folio;
int err = 0;
- page = f2fs_get_lock_data_page(inode, bidx, true);
- if (IS_ERR(page))
- return PTR_ERR(page);
+ folio = f2fs_get_lock_data_folio(inode, bidx, true);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
if (!check_valid_map(F2FS_I_SB(inode), segno, off)) {
err = -ENOENT;
@@ -1465,12 +1468,12 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
goto out;
if (gc_type == BG_GC) {
- if (folio_test_writeback(page_folio(page))) {
+ if (folio_test_writeback(folio)) {
err = -EAGAIN;
goto out;
}
- set_page_dirty(page);
- set_page_private_gcing(page);
+ folio_mark_dirty(folio);
+ set_page_private_gcing(&folio->page);
} else {
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
@@ -1480,37 +1483,37 @@ static int move_data_page(struct inode *inode, block_t bidx, int gc_type,
.op = REQ_OP_WRITE,
.op_flags = REQ_SYNC,
.old_blkaddr = NULL_ADDR,
- .page = page,
+ .page = &folio->page,
.encrypted_page = NULL,
.need_lock = LOCK_REQ,
.io_type = FS_GC_DATA_IO,
};
- bool is_dirty = PageDirty(page);
+ bool is_dirty = folio_test_dirty(folio);
retry:
- f2fs_wait_on_page_writeback(page, DATA, true, true);
+ f2fs_folio_wait_writeback(folio, DATA, true, true);
- set_page_dirty(page);
- if (clear_page_dirty_for_io(page)) {
+ folio_mark_dirty(folio);
+ if (folio_clear_dirty_for_io(folio)) {
inode_dec_dirty_pages(inode);
f2fs_remove_dirty_inode(inode);
}
- set_page_private_gcing(page);
+ set_page_private_gcing(&folio->page);
err = f2fs_do_write_data_page(&fio);
if (err) {
- clear_page_private_gcing(page);
+ clear_page_private_gcing(&folio->page);
if (err == -ENOMEM) {
memalloc_retry_wait(GFP_NOFS);
goto retry;
}
if (is_dirty)
- set_page_dirty(page);
+ folio_mark_dirty(folio);
}
}
out:
- f2fs_put_page(page, 1);
+ f2fs_folio_put(folio, true);
return err;
}
@@ -1539,7 +1542,6 @@ next_step:
entry = sum;
for (off = 0; off < usable_blks_in_seg; off++, entry++) {
- struct page *data_page;
struct inode *inode;
struct node_info dni; /* dnode info for the data */
unsigned int ofs_in_node, nofs;
@@ -1582,6 +1584,7 @@ next_step:
ofs_in_node = le16_to_cpu(entry->ofs_in_node);
if (phase == 3) {
+ struct folio *data_folio;
int err;
inode = f2fs_iget(sb, dni.ino);
@@ -1632,15 +1635,15 @@ next_step:
continue;
}
- data_page = f2fs_get_read_data_page(inode, start_bidx,
+ data_folio = f2fs_get_read_data_folio(inode, start_bidx,
REQ_RAHEAD, true, NULL);
f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
- if (IS_ERR(data_page)) {
+ if (IS_ERR(data_folio)) {
iput(inode);
continue;
}
- f2fs_put_page(data_page, 0);
+ f2fs_folio_put(data_folio, false);
add_gc_inode(gc_list, inode);
continue;
}
@@ -2063,6 +2066,9 @@ int f2fs_gc_range(struct f2fs_sb_info *sbi,
.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
};
+ if (IS_CURSEC(sbi, GET_SEC_FROM_SEG(sbi, segno)))
+ continue;
+
do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false);
put_gc_inode(&gc_list);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 3b91a95d4276..ad92e9008781 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -81,7 +81,7 @@ bool f2fs_may_inline_dentry(struct inode *inode)
void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage)
{
- struct inode *inode = folio_file_mapping(folio)->host;
+ struct inode *inode = folio->mapping->host;
if (folio_test_uptodate(folio))
return;
@@ -119,7 +119,7 @@ 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);
+ ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
folio_unlock(folio);
return PTR_ERR(ipage);
@@ -237,7 +237,7 @@ int f2fs_convert_inline_inode(struct inode *inode)
f2fs_lock_op(sbi);
- ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
@@ -265,7 +265,7 @@ int f2fs_write_inline_data(struct inode *inode, struct folio *folio)
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *ipage;
- ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@@ -312,7 +312,7 @@ int f2fs_recover_inline_data(struct inode *inode, struct page *npage)
if (f2fs_has_inline_data(inode) &&
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
- ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@@ -331,7 +331,7 @@ process_inline:
}
if (f2fs_has_inline_data(inode)) {
- ipage = f2fs_get_node_page(sbi, inode->i_ino);
+ ipage = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
f2fs_truncate_inline_inode(inode, ipage, 0);
@@ -361,7 +361,7 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
struct page *ipage;
void *inline_dentry;
- ipage = f2fs_get_node_page(sbi, dir->i_ino);
+ ipage = f2fs_get_inode_page(sbi, dir->i_ino);
if (IS_ERR(ipage)) {
*res_page = ipage;
return NULL;
@@ -609,7 +609,7 @@ int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry)
if (err)
goto out;
- ipage = f2fs_get_node_page(sbi, dir->i_ino);
+ ipage = f2fs_get_inode_page(sbi, dir->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out_fname;
@@ -644,7 +644,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
struct page *page = NULL;
int err = 0;
- ipage = f2fs_get_node_page(sbi, dir->i_ino);
+ ipage = f2fs_get_inode_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@@ -734,7 +734,7 @@ bool f2fs_empty_inline_dir(struct inode *dir)
void *inline_dentry;
struct f2fs_dentry_ptr d;
- ipage = f2fs_get_node_page(sbi, dir->i_ino);
+ ipage = f2fs_get_inode_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return false;
@@ -765,7 +765,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
if (ctx->pos == d.max)
return 0;
- ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@@ -797,7 +797,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
struct page *ipage;
int err = 0;
- ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 282fd320bdb3..f5991e8751b9 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -34,10 +34,10 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
if (f2fs_inode_dirtied(inode, sync))
return;
- if (f2fs_is_atomic_file(inode)) {
- set_inode_flag(inode, FI_ATOMIC_DIRTIED);
+ /* only atomic file w/ FI_ATOMIC_COMMITTED can be set vfs dirty */
+ if (f2fs_is_atomic_file(inode) &&
+ !is_inode_flag_set(inode, FI_ATOMIC_COMMITTED))
return;
- }
mark_inode_dirty_sync(inode);
}
@@ -288,6 +288,12 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
return false;
}
+ if (ino_of_node(node_page) == fi->i_xattr_nid) {
+ f2fs_warn(sbi, "%s: corrupted inode i_ino=%lx, xnid=%x, run fsck to fix.",
+ __func__, inode->i_ino, fi->i_xattr_nid);
+ return false;
+ }
+
if (f2fs_has_extra_attr(inode)) {
if (!f2fs_sb_has_extra_attr(sbi)) {
f2fs_warn(sbi, "%s: inode (ino=%lx) is with extra_attr, but extra_attr feature is off",
@@ -302,15 +308,6 @@ 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,
@@ -320,6 +317,16 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
}
}
+ 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;
+ }
+
if (!f2fs_sb_has_extra_attr(sbi)) {
if (f2fs_sb_has_project_quota(sbi)) {
f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.",
@@ -409,7 +416,7 @@ static int do_read_inode(struct inode *inode)
if (f2fs_check_nid_range(sbi, inode->i_ino))
return -EINVAL;
- node_page = f2fs_get_node_page(sbi, inode->i_ino);
+ node_page = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
@@ -756,7 +763,7 @@ void f2fs_update_inode_page(struct inode *inode)
struct page *node_page;
int count = 0;
retry:
- node_page = f2fs_get_node_page(sbi, inode->i_ino);
+ node_page = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
int err = PTR_ERR(node_page);
@@ -764,8 +771,12 @@ retry:
if (err == -ENOENT)
return;
+ if (err == -EFSCORRUPTED)
+ goto stop_checkpoint;
+
if (err == -ENOMEM || ++count <= DEFAULT_RETRY_IO_COUNT)
goto retry;
+stop_checkpoint:
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_UPDATE_INODE);
return;
}
@@ -788,6 +799,13 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
!is_inode_flag_set(inode, FI_DIRTY_INODE))
return 0;
+ /*
+ * no need to update inode page, ultimately f2fs_evict_inode() will
+ * clear dirty status of inode.
+ */
+ if (f2fs_cp_error(sbi))
+ return -EIO;
+
if (!f2fs_is_checkpoint_ready(sbi)) {
f2fs_mark_inode_dirty_sync(inode, true);
return -ENOSPC;
@@ -803,6 +821,19 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
return 0;
}
+static void f2fs_remove_donate_inode(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ if (list_empty(&F2FS_I(inode)->gdonate_list))
+ return;
+
+ spin_lock(&sbi->inode_lock[DONATE_INODE]);
+ list_del_init(&F2FS_I(inode)->gdonate_list);
+ sbi->donate_files--;
+ spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+}
+
/*
* Called at the last iput() if i_nlink is zero
*/
@@ -837,6 +868,7 @@ void f2fs_evict_inode(struct inode *inode)
f2fs_bug_on(sbi, get_dirty_pages(inode));
f2fs_remove_dirty_inode(inode);
+ f2fs_remove_donate_inode(inode);
if (!IS_DEVICE_ALIASING(inode))
f2fs_destroy_extent_tree(inode);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 57d46e1439de..f775dc62511c 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -341,6 +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);
@@ -413,7 +414,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
if (is_inode_flag_set(dir, FI_PROJ_INHERIT) &&
(!projid_eq(F2FS_I(dir)->i_projid,
- F2FS_I(old_dentry->d_inode)->i_projid)))
+ F2FS_I(inode)->i_projid)))
return -EXDEV;
err = f2fs_dquot_initialize(dir);
@@ -501,6 +502,14 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
+ if (inode->i_nlink == 0) {
+ f2fs_warn(F2FS_I_SB(inode), "%s: inode (ino=%lx) has zero i_nlink",
+ __func__, inode->i_ino);
+ err = -EFSCORRUPTED;
+ set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+ goto out_iput;
+ }
+
if (IS_ENCRYPTED(dir) &&
(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
!fscrypt_has_permitted_context(dir, inode)) {
@@ -560,6 +569,15 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
goto fail;
}
+ if (unlikely(inode->i_nlink == 0)) {
+ f2fs_warn(F2FS_I_SB(inode), "%s: inode (ino=%lx) has zero i_nlink",
+ __func__, inode->i_ino);
+ err = -EFSCORRUPTED;
+ set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK);
+ f2fs_put_page(page, 0);
+ goto fail;
+ }
+
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
@@ -683,23 +701,23 @@ out_free_encrypted_link:
return err;
}
-static int f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
- struct dentry *dentry, umode_t mode)
+static struct dentry *f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
int err;
if (unlikely(f2fs_cp_error(sbi)))
- return -EIO;
+ return ERR_PTR(-EIO);
err = f2fs_dquot_initialize(dir);
if (err)
- return err;
+ return ERR_PTR(err);
inode = f2fs_new_inode(idmap, dir, S_IFDIR | mode, NULL);
if (IS_ERR(inode))
- return PTR_ERR(inode);
+ return ERR_CAST(inode);
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
@@ -721,12 +739,12 @@ static int f2fs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
f2fs_sync_fs(sbi->sb, 1);
f2fs_balance_fs(sbi, true);
- return 0;
+ return NULL;
out_fail:
clear_inode_flag(inode, FI_INC_LINK);
f2fs_handle_failed_inode(inode);
- return err;
+ return ERR_PTR(err);
}
static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
@@ -905,7 +923,7 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
(!projid_eq(F2FS_I(new_dir)->i_projid,
- F2FS_I(old_dentry->d_inode)->i_projid)))
+ F2FS_I(old_inode)->i_projid)))
return -EXDEV;
/*
@@ -1098,10 +1116,10 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
!projid_eq(F2FS_I(new_dir)->i_projid,
- F2FS_I(old_dentry->d_inode)->i_projid)) ||
- (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+ F2FS_I(old_inode)->i_projid)) ||
+ (is_inode_flag_set(old_dir, FI_PROJ_INHERIT) &&
!projid_eq(F2FS_I(old_dir)->i_projid,
- F2FS_I(new_dentry->d_inode)->i_projid)))
+ F2FS_I(new_inode)->i_projid)))
return -EXDEV;
err = f2fs_dquot_initialize(old_dir);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 0b900a7a48e5..f476c2e7b096 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -310,10 +310,10 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
start, nr);
}
-bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page)
+bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, const struct folio *folio)
{
- return NODE_MAPPING(sbi) == page->mapping &&
- IS_DNODE(page) && is_cold_node(page);
+ return NODE_MAPPING(sbi) == folio->mapping &&
+ IS_DNODE(&folio->page) && is_cold_node(&folio->page);
}
void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi)
@@ -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 */
@@ -777,7 +778,7 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
npage[0] = dn->inode_page;
if (!npage[0]) {
- npage[0] = f2fs_get_node_page(sbi, nids[0]);
+ npage[0] = f2fs_get_inode_page(sbi, nids[0]);
if (IS_ERR(npage[0]))
return PTR_ERR(npage[0]);
}
@@ -916,7 +917,7 @@ static int truncate_node(struct dnode_of_data *dn)
}
/* 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);
@@ -1129,26 +1130,33 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
unsigned int nofs = 0;
struct f2fs_inode *ri;
struct dnode_of_data dn;
- struct page *page;
+ struct folio *folio;
trace_f2fs_truncate_inode_blocks_enter(inode, from);
level = get_node_path(inode, from, offset, noffset);
- if (level < 0) {
+ if (level <= 0) {
+ if (!level) {
+ level = -EFSCORRUPTED;
+ f2fs_err(sbi, "%s: inode ino=%lx has corrupted node block, from:%lu addrs:%u",
+ __func__, inode->i_ino,
+ from, ADDRS_PER_INODE(inode));
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ }
trace_f2fs_truncate_inode_blocks_exit(inode, level);
return level;
}
- page = f2fs_get_node_page(sbi, inode->i_ino);
- if (IS_ERR(page)) {
- trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
- return PTR_ERR(page);
+ folio = f2fs_get_inode_folio(sbi, inode->i_ino);
+ if (IS_ERR(folio)) {
+ trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(folio));
+ return PTR_ERR(folio);
}
- set_new_dnode(&dn, inode, page, NULL, 0);
- unlock_page(page);
+ set_new_dnode(&dn, inode, &folio->page, NULL, 0);
+ folio_unlock(folio);
- ri = F2FS_INODE(page);
+ ri = F2FS_INODE(&folio->page);
switch (level) {
case 0:
case 1:
@@ -1177,7 +1185,7 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
skip_partial:
while (cont) {
- dn.nid = get_nid(page, offset[0], true);
+ dn.nid = get_nid(&folio->page, offset[0], true);
switch (offset[0]) {
case NODE_DIR1_BLOCK:
case NODE_DIR2_BLOCK:
@@ -1198,7 +1206,7 @@ skip_partial:
BUG();
}
if (err == -ENOENT) {
- set_sbi_flag(F2FS_P_SB(page), SBI_NEED_FSCK);
+ set_sbi_flag(F2FS_F_SB(folio), SBI_NEED_FSCK);
f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR);
f2fs_err_ratelimited(sbi,
"truncate node fail, ino:%lu, nid:%u, "
@@ -1209,18 +1217,18 @@ skip_partial:
}
if (err < 0)
goto fail;
- if (offset[1] == 0 && get_nid(page, offset[0], true)) {
- lock_page(page);
- BUG_ON(page->mapping != NODE_MAPPING(sbi));
- set_nid(page, offset[0], 0, true);
- unlock_page(page);
+ if (offset[1] == 0 && get_nid(&folio->page, offset[0], true)) {
+ folio_lock(folio);
+ BUG_ON(folio->mapping != NODE_MAPPING(sbi));
+ set_nid(&folio->page, offset[0], 0, true);
+ folio_unlock(folio);
}
offset[1] = 0;
offset[0]++;
nofs += err;
}
fail:
- f2fs_put_page(page, 0);
+ f2fs_folio_put(folio, false);
trace_f2fs_truncate_inode_blocks_exit(inode, err);
return err > 0 ? 0 : err;
}
@@ -1237,7 +1245,7 @@ int f2fs_truncate_xattr_node(struct inode *inode)
if (!nid)
return 0;
- npage = f2fs_get_node_page(sbi, nid);
+ npage = f2fs_get_xnode_page(sbi, nid);
if (IS_ERR(npage))
return PTR_ERR(npage);
@@ -1274,8 +1282,9 @@ 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 */
@@ -1447,10 +1456,32 @@ void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
f2fs_put_page(apage, err ? 1 : 0);
}
-static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
- struct page *parent, int start)
+static int sanity_check_node_footer(struct f2fs_sb_info *sbi,
+ struct page *page, pgoff_t nid,
+ enum node_type ntype)
{
- struct page *page;
+ if (unlikely(nid != nid_of_node(page) ||
+ (ntype == NODE_TYPE_INODE && !IS_INODE(page)) ||
+ (ntype == NODE_TYPE_XATTR &&
+ !f2fs_has_xattr_block(ofs_of_node(page))) ||
+ time_to_inject(sbi, FAULT_INCONSISTENT_FOOTER))) {
+ f2fs_warn(sbi, "inconsistent node block, node_type:%d, nid:%lu, "
+ "node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
+ ntype, nid, nid_of_node(page), ino_of_node(page),
+ ofs_of_node(page), cpver_of_node(page),
+ next_blkaddr_of_node(page));
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER);
+ return -EFSCORRUPTED;
+ }
+ return 0;
+}
+
+static struct folio *__get_node_folio(struct f2fs_sb_info *sbi, pgoff_t nid,
+ struct page *parent, int start,
+ enum node_type ntype)
+{
+ struct folio *folio;
int err;
if (!nid)
@@ -1458,11 +1489,11 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
if (f2fs_check_nid_range(sbi, nid))
return ERR_PTR(-EINVAL);
repeat:
- page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
- if (!page)
- return ERR_PTR(-ENOMEM);
+ folio = f2fs_grab_cache_folio(NODE_MAPPING(sbi), nid, false);
+ if (IS_ERR(folio))
+ return folio;
- err = read_node_page(page, 0);
+ err = read_node_page(&folio->page, 0);
if (err < 0) {
goto out_put_err;
} else if (err == LOCKED_PAGE) {
@@ -1473,54 +1504,72 @@ repeat:
if (parent)
f2fs_ra_node_pages(parent, start + 1, MAX_RA_NODE);
- lock_page(page);
+ folio_lock(folio);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
- f2fs_put_page(page, 1);
+ if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
+ f2fs_folio_put(folio, true);
goto repeat;
}
- if (unlikely(!PageUptodate(page))) {
+ if (unlikely(!folio_test_uptodate(folio))) {
err = -EIO;
goto out_err;
}
- if (!f2fs_inode_chksum_verify(sbi, page)) {
+ if (!f2fs_inode_chksum_verify(sbi, &folio->page)) {
err = -EFSBADCRC;
goto out_err;
}
page_hit:
- if (likely(nid == nid_of_node(page)))
- return page;
-
- f2fs_warn(sbi, "inconsistent node block, nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
- nid, nid_of_node(page), ino_of_node(page),
- ofs_of_node(page), cpver_of_node(page),
- next_blkaddr_of_node(page));
- set_sbi_flag(sbi, SBI_NEED_FSCK);
- f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER);
- err = -EFSCORRUPTED;
+ err = sanity_check_node_footer(sbi, &folio->page, nid, ntype);
+ if (!err)
+ return folio;
out_err:
- ClearPageUptodate(page);
+ folio_clear_uptodate(folio);
out_put_err:
/* ENOENT comes from read_node_page which is not an error. */
if (err != -ENOENT)
- f2fs_handle_page_eio(sbi, page_folio(page), NODE);
- f2fs_put_page(page, 1);
+ f2fs_handle_page_eio(sbi, folio, NODE);
+ f2fs_folio_put(folio, true);
return ERR_PTR(err);
}
struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
{
- return __get_node_page(sbi, nid, NULL, 0);
+ struct folio *folio = __get_node_folio(sbi, nid, NULL, 0,
+ NODE_TYPE_REGULAR);
+
+ return &folio->page;
+}
+
+struct folio *f2fs_get_inode_folio(struct f2fs_sb_info *sbi, pgoff_t ino)
+{
+ return __get_node_folio(sbi, ino, NULL, 0, NODE_TYPE_INODE);
+}
+
+struct page *f2fs_get_inode_page(struct f2fs_sb_info *sbi, pgoff_t ino)
+{
+ struct folio *folio = f2fs_get_inode_folio(sbi, ino);
+
+ return &folio->page;
+}
+
+struct page *f2fs_get_xnode_page(struct f2fs_sb_info *sbi, pgoff_t xnid)
+{
+ struct folio *folio = __get_node_folio(sbi, xnid, NULL, 0,
+ NODE_TYPE_XATTR);
+
+ return &folio->page;
}
struct page *f2fs_get_node_page_ra(struct page *parent, int start)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
nid_t nid = get_nid(parent, start, false);
+ struct folio *folio = __get_node_folio(sbi, nid, parent, start,
+ NODE_TYPE_REGULAR);
- return __get_node_page(sbi, nid, parent, start);
+ return &folio->page;
}
static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
@@ -1559,11 +1608,11 @@ iput_out:
iput(inode);
}
-static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
+static struct folio *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
{
pgoff_t index;
struct folio_batch fbatch;
- struct page *last_page = NULL;
+ struct folio *last_folio = NULL;
int nr_folios;
folio_batch_init(&fbatch);
@@ -1575,45 +1624,45 @@ static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
int i;
for (i = 0; i < nr_folios; i++) {
- struct page *page = &fbatch.folios[i]->page;
+ struct folio *folio = fbatch.folios[i];
if (unlikely(f2fs_cp_error(sbi))) {
- f2fs_put_page(last_page, 0);
+ f2fs_folio_put(last_folio, false);
folio_batch_release(&fbatch);
return ERR_PTR(-EIO);
}
- if (!IS_DNODE(page) || !is_cold_node(page))
+ if (!IS_DNODE(&folio->page) || !is_cold_node(&folio->page))
continue;
- if (ino_of_node(page) != ino)
+ if (ino_of_node(&folio->page) != ino)
continue;
- lock_page(page);
+ folio_lock(folio);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+ if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
continue_unlock:
- unlock_page(page);
+ folio_unlock(folio);
continue;
}
- if (ino_of_node(page) != ino)
+ if (ino_of_node(&folio->page) != ino)
goto continue_unlock;
- if (!PageDirty(page)) {
+ if (!folio_test_dirty(folio)) {
/* someone wrote it for us */
goto continue_unlock;
}
- if (last_page)
- f2fs_put_page(last_page, 0);
+ if (last_folio)
+ f2fs_folio_put(last_folio, false);
- get_page(page);
- last_page = page;
- unlock_page(page);
+ folio_get(folio);
+ last_folio = folio;
+ folio_unlock(folio);
}
folio_batch_release(&fbatch);
cond_resched();
}
- return last_page;
+ return last_folio;
}
static int __write_node_page(struct page *page, bool atomic, bool *submitted,
@@ -1692,7 +1741,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
/* should add to global list before clearing PAGECACHE status */
- if (f2fs_in_warm_node_list(sbi, page)) {
+ if (f2fs_in_warm_node_list(sbi, folio)) {
seq = f2fs_add_fsync_node_entry(sbi, page);
if (seq_id)
*seq_id = seq;
@@ -1767,13 +1816,6 @@ release_page:
return err;
}
-static int f2fs_write_node_page(struct page *page,
- struct writeback_control *wbc)
-{
- return __write_node_page(page, false, NULL, wbc, false,
- FS_NODE_IO, NULL);
-}
-
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic,
unsigned int *seq_id)
@@ -1781,16 +1823,16 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
pgoff_t index;
struct folio_batch fbatch;
int ret = 0;
- struct page *last_page = NULL;
+ struct folio *last_folio = NULL;
bool marked = false;
nid_t ino = inode->i_ino;
int nr_folios;
int nwritten = 0;
if (atomic) {
- last_page = last_fsync_dnode(sbi, ino);
- if (IS_ERR_OR_NULL(last_page))
- return PTR_ERR_OR_ZERO(last_page);
+ last_folio = last_fsync_dnode(sbi, ino);
+ if (IS_ERR_OR_NULL(last_folio))
+ return PTR_ERR_OR_ZERO(last_folio);
}
retry:
folio_batch_init(&fbatch);
@@ -1802,73 +1844,73 @@ retry:
int i;
for (i = 0; i < nr_folios; i++) {
- struct page *page = &fbatch.folios[i]->page;
+ struct folio *folio = fbatch.folios[i];
bool submitted = false;
if (unlikely(f2fs_cp_error(sbi))) {
- f2fs_put_page(last_page, 0);
+ f2fs_folio_put(last_folio, false);
folio_batch_release(&fbatch);
ret = -EIO;
goto out;
}
- if (!IS_DNODE(page) || !is_cold_node(page))
+ if (!IS_DNODE(&folio->page) || !is_cold_node(&folio->page))
continue;
- if (ino_of_node(page) != ino)
+ if (ino_of_node(&folio->page) != ino)
continue;
- lock_page(page);
+ folio_lock(folio);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+ if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
continue_unlock:
- unlock_page(page);
+ folio_unlock(folio);
continue;
}
- if (ino_of_node(page) != ino)
+ if (ino_of_node(&folio->page) != ino)
goto continue_unlock;
- if (!PageDirty(page) && page != last_page) {
+ if (!folio_test_dirty(folio) && folio != last_folio) {
/* someone wrote it for us */
goto continue_unlock;
}
- f2fs_wait_on_page_writeback(page, NODE, true, true);
+ f2fs_folio_wait_writeback(folio, NODE, true, true);
- set_fsync_mark(page, 0);
- set_dentry_mark(page, 0);
+ set_fsync_mark(&folio->page, 0);
+ set_dentry_mark(&folio->page, 0);
- if (!atomic || page == last_page) {
- set_fsync_mark(page, 1);
+ if (!atomic || folio == last_folio) {
+ set_fsync_mark(&folio->page, 1);
percpu_counter_inc(&sbi->rf_node_block_count);
- if (IS_INODE(page)) {
+ if (IS_INODE(&folio->page)) {
if (is_inode_flag_set(inode,
FI_DIRTY_INODE))
- f2fs_update_inode(inode, page);
- set_dentry_mark(page,
+ f2fs_update_inode(inode, &folio->page);
+ set_dentry_mark(&folio->page,
f2fs_need_dentry_mark(sbi, ino));
}
/* may be written by other thread */
- if (!PageDirty(page))
- set_page_dirty(page);
+ if (!folio_test_dirty(folio))
+ folio_mark_dirty(folio);
}
- if (!clear_page_dirty_for_io(page))
+ if (!folio_clear_dirty_for_io(folio))
goto continue_unlock;
- ret = __write_node_page(page, atomic &&
- page == last_page,
+ ret = __write_node_page(&folio->page, atomic &&
+ folio == last_folio,
&submitted, wbc, true,
FS_NODE_IO, seq_id);
if (ret) {
- unlock_page(page);
- f2fs_put_page(last_page, 0);
+ folio_unlock(folio);
+ f2fs_folio_put(last_folio, false);
break;
} else if (submitted) {
nwritten++;
}
- if (page == last_page) {
- f2fs_put_page(page, 0);
+ if (folio == last_folio) {
+ f2fs_folio_put(folio, false);
marked = true;
break;
}
@@ -1881,11 +1923,11 @@ continue_unlock:
}
if (!ret && atomic && !marked) {
f2fs_debug(sbi, "Retry to write fsync mark: ino=%u, idx=%lx",
- 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);
- unlock_page(last_page);
+ ino, last_folio->index);
+ folio_lock(last_folio);
+ f2fs_folio_wait_writeback(last_folio, NODE, true, true);
+ folio_mark_dirty(last_folio);
+ folio_unlock(last_folio);
goto retry;
}
out:
@@ -1918,18 +1960,18 @@ static int f2fs_match_ino(struct inode *inode, unsigned long ino, void *data)
return 1;
}
-static bool flush_dirty_inode(struct page *page)
+static bool flush_dirty_inode(struct folio *folio)
{
- struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+ struct f2fs_sb_info *sbi = F2FS_F_SB(folio);
struct inode *inode;
- nid_t ino = ino_of_node(page);
+ nid_t ino = ino_of_node(&folio->page);
inode = find_inode_nowait(sbi->sb, ino, f2fs_match_ino, NULL);
if (!inode)
return false;
- f2fs_update_inode(inode, page);
- unlock_page(page);
+ f2fs_update_inode(inode, &folio->page);
+ folio_unlock(folio);
iput(inode);
return true;
@@ -1949,32 +1991,27 @@ void f2fs_flush_inline_data(struct f2fs_sb_info *sbi)
int i;
for (i = 0; i < nr_folios; i++) {
- struct page *page = &fbatch.folios[i]->page;
+ struct folio *folio = fbatch.folios[i];
- if (!IS_INODE(page))
+ if (!IS_INODE(&folio->page))
continue;
- lock_page(page);
+ folio_lock(folio);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
-continue_unlock:
- unlock_page(page);
- continue;
- }
-
- if (!PageDirty(page)) {
- /* someone wrote it for us */
- goto continue_unlock;
- }
+ if (unlikely(folio->mapping != NODE_MAPPING(sbi)))
+ goto unlock;
+ if (!folio_test_dirty(folio))
+ goto unlock;
/* flush inline_data, if it's async context. */
- if (page_private_inline(page)) {
- clear_page_private_inline(page);
- unlock_page(page);
- flush_inline_data(sbi, ino_of_node(page));
+ if (page_private_inline(&folio->page)) {
+ clear_page_private_inline(&folio->page);
+ folio_unlock(folio);
+ flush_inline_data(sbi, ino_of_node(&folio->page));
continue;
}
- unlock_page(page);
+unlock:
+ folio_unlock(folio);
}
folio_batch_release(&fbatch);
cond_resched();
@@ -2003,7 +2040,7 @@ next_step:
int i;
for (i = 0; i < nr_folios; i++) {
- struct page *page = &fbatch.folios[i]->page;
+ struct folio *folio = fbatch.folios[i];
bool submitted = false;
/* give a priority to WB_SYNC threads */
@@ -2019,27 +2056,27 @@ next_step:
* 1. dentry dnodes
* 2. file dnodes
*/
- if (step == 0 && IS_DNODE(page))
+ if (step == 0 && IS_DNODE(&folio->page))
continue;
- if (step == 1 && (!IS_DNODE(page) ||
- is_cold_node(page)))
+ if (step == 1 && (!IS_DNODE(&folio->page) ||
+ is_cold_node(&folio->page)))
continue;
- if (step == 2 && (!IS_DNODE(page) ||
- !is_cold_node(page)))
+ if (step == 2 && (!IS_DNODE(&folio->page) ||
+ !is_cold_node(&folio->page)))
continue;
lock_node:
if (wbc->sync_mode == WB_SYNC_ALL)
- lock_page(page);
- else if (!trylock_page(page))
+ folio_lock(folio);
+ else if (!folio_trylock(folio))
continue;
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+ if (unlikely(folio->mapping != NODE_MAPPING(sbi))) {
continue_unlock:
- unlock_page(page);
+ folio_unlock(folio);
continue;
}
- if (!PageDirty(page)) {
+ if (!folio_test_dirty(folio)) {
/* someone wrote it for us */
goto continue_unlock;
}
@@ -2049,31 +2086,35 @@ continue_unlock:
goto write_node;
/* flush inline_data */
- if (page_private_inline(page)) {
- clear_page_private_inline(page);
- unlock_page(page);
- flush_inline_data(sbi, ino_of_node(page));
+ if (page_private_inline(&folio->page)) {
+ clear_page_private_inline(&folio->page);
+ folio_unlock(folio);
+ flush_inline_data(sbi, ino_of_node(&folio->page));
goto lock_node;
}
/* flush dirty inode */
- if (IS_INODE(page) && flush_dirty_inode(page))
+ if (IS_INODE(&folio->page) && flush_dirty_inode(folio))
goto lock_node;
write_node:
- f2fs_wait_on_page_writeback(page, NODE, true, true);
+ f2fs_folio_wait_writeback(folio, NODE, true, true);
- if (!clear_page_dirty_for_io(page))
+ if (!folio_clear_dirty_for_io(folio))
goto continue_unlock;
- set_fsync_mark(page, 0);
- set_dentry_mark(page, 0);
+ set_fsync_mark(&folio->page, 0);
+ set_dentry_mark(&folio->page, 0);
- ret = __write_node_page(page, false, &submitted,
+ ret = __write_node_page(&folio->page, false, &submitted,
wbc, do_balance, io_type, NULL);
- if (ret)
- unlock_page(page);
- else if (submitted)
+ if (ret) {
+ folio_unlock(folio);
+ folio_batch_release(&fbatch);
+ ret = -EIO;
+ goto out;
+ } else if (submitted) {
nwritten++;
+ }
if (--wbc->nr_to_write == 0)
break;
@@ -2205,7 +2246,6 @@ static bool f2fs_dirty_node_folio(struct address_space *mapping,
* Structure of the f2fs node operations
*/
const struct address_space_operations f2fs_node_aops = {
- .writepage = f2fs_write_node_page,
.writepages = f2fs_write_node_pages,
.dirty_folio = f2fs_dirty_node_folio,
.invalidate_folio = f2fs_invalidate_folio,
@@ -2267,24 +2307,6 @@ static void __move_free_nid(struct f2fs_sb_info *sbi, struct free_nid *i,
}
}
-bool f2fs_nat_bitmap_enabled(struct f2fs_sb_info *sbi)
-{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
- unsigned int i;
- bool ret = true;
-
- f2fs_down_read(&nm_i->nat_tree_lock);
- for (i = 0; i < nm_i->nat_blocks; i++) {
- if (!test_bit_le(i, nm_i->nat_block_bitmap)) {
- ret = false;
- break;
- }
- }
- f2fs_up_read(&nm_i->nat_tree_lock);
-
- return ret;
-}
-
static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
bool set, bool build)
{
@@ -2715,7 +2737,7 @@ int f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
struct page *ipage;
struct f2fs_inode *ri;
- ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
+ ipage = f2fs_get_inode_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
@@ -2763,7 +2785,7 @@ 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);
@@ -2963,23 +2985,7 @@ add_out:
list_add_tail(&nes->set_list, head);
}
-static void __update_nat_bits(struct f2fs_nm_info *nm_i, unsigned int nat_ofs,
- unsigned int valid)
-{
- if (valid == 0) {
- __set_bit_le(nat_ofs, nm_i->empty_nat_bits);
- __clear_bit_le(nat_ofs, nm_i->full_nat_bits);
- return;
- }
-
- __clear_bit_le(nat_ofs, nm_i->empty_nat_bits);
- if (valid == NAT_ENTRY_PER_BLOCK)
- __set_bit_le(nat_ofs, nm_i->full_nat_bits);
- else
- __clear_bit_le(nat_ofs, nm_i->full_nat_bits);
-}
-
-static void update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
struct page *page)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -2988,7 +2994,7 @@ static void update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
int valid = 0;
int i = 0;
- if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
+ if (!enabled_nat_bits(sbi, NULL))
return;
if (nat_index == 0) {
@@ -2999,36 +3005,17 @@ static void update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
if (le32_to_cpu(nat_blk->entries[i].block_addr) != NULL_ADDR)
valid++;
}
-
- __update_nat_bits(nm_i, nat_index, valid);
-}
-
-void f2fs_enable_nat_bits(struct f2fs_sb_info *sbi)
-{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
- unsigned int nat_ofs;
-
- f2fs_down_read(&nm_i->nat_tree_lock);
-
- for (nat_ofs = 0; nat_ofs < nm_i->nat_blocks; nat_ofs++) {
- unsigned int valid = 0, nid_ofs = 0;
-
- /* handle nid zero due to it should never be used */
- if (unlikely(nat_ofs == 0)) {
- valid = 1;
- nid_ofs = 1;
- }
-
- for (; nid_ofs < NAT_ENTRY_PER_BLOCK; nid_ofs++) {
- if (!test_bit_le(nid_ofs,
- nm_i->free_nid_bitmap[nat_ofs]))
- valid++;
- }
-
- __update_nat_bits(nm_i, nat_ofs, valid);
+ if (valid == 0) {
+ __set_bit_le(nat_index, nm_i->empty_nat_bits);
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
+ return;
}
- f2fs_up_read(&nm_i->nat_tree_lock);
+ __clear_bit_le(nat_index, nm_i->empty_nat_bits);
+ if (valid == NAT_ENTRY_PER_BLOCK)
+ __set_bit_le(nat_index, nm_i->full_nat_bits);
+ else
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
}
static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
@@ -3047,7 +3034,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
* #1, flush nat entries to journal in current hot data summary block.
* #2, flush nat entries to nat page.
*/
- if ((cpc->reason & CP_UMOUNT) ||
+ if (enabled_nat_bits(sbi, cpc) ||
!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
to_journal = false;
@@ -3094,7 +3081,7 @@ static int __flush_nat_entry_set(struct f2fs_sb_info *sbi,
if (to_journal) {
up_write(&curseg->journal_rwsem);
} else {
- update_nat_bits(sbi, start_nid, page);
+ __update_nat_bits(sbi, start_nid, page);
f2fs_put_page(page, 1);
}
@@ -3125,7 +3112,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
* during unmount, let's flush nat_bits before checking
* nat_cnt[DIRTY_NAT].
*/
- if (cpc->reason & CP_UMOUNT) {
+ if (enabled_nat_bits(sbi, cpc)) {
f2fs_down_write(&nm_i->nat_tree_lock);
remove_nats_in_journal(sbi);
f2fs_up_write(&nm_i->nat_tree_lock);
@@ -3141,7 +3128,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
* entries, remove all entries from journal and merge them
* into nat entry set.
*/
- if (cpc->reason & CP_UMOUNT ||
+ if (enabled_nat_bits(sbi, cpc) ||
!__has_cursum_space(journal,
nm_i->nat_cnt[DIRTY_NAT], NAT_JOURNAL))
remove_nats_in_journal(sbi);
@@ -3178,18 +3165,15 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
__u64 cp_ver = cur_cp_version(ckpt);
block_t nat_bits_addr;
+ if (!enabled_nat_bits(sbi, NULL))
+ return 0;
+
nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8);
nm_i->nat_bits = f2fs_kvzalloc(sbi,
F2FS_BLK_TO_BYTES(nm_i->nat_bits_blocks), GFP_KERNEL);
if (!nm_i->nat_bits)
return -ENOMEM;
- nm_i->full_nat_bits = nm_i->nat_bits + 8;
- nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
-
- if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
- return 0;
-
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++) {
@@ -3206,12 +3190,13 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
cp_ver |= (cur_cp_crc(ckpt) << 32);
if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) {
- clear_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
- f2fs_notice(sbi, "Disable nat_bits due to incorrect cp_ver (%llu, %llu)",
- cp_ver, le64_to_cpu(*(__le64 *)nm_i->nat_bits));
+ disable_nat_bits(sbi, true);
return 0;
}
+ nm_i->full_nat_bits = nm_i->nat_bits + 8;
+ nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
+
f2fs_notice(sbi, "Found nat_bits in checkpoint");
return 0;
}
@@ -3222,7 +3207,7 @@ static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
unsigned int i = 0;
nid_t nid, last_nid;
- if (!is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG))
+ if (!enabled_nat_bits(sbi, NULL))
return;
for (i = 0; i < nm_i->nat_blocks; i++) {
@@ -3294,6 +3279,9 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
if (!nm_i->nat_bitmap)
return -ENOMEM;
+ if (!test_opt(sbi, NAT_BITS))
+ disable_nat_bits(sbi, true);
+
err = __get_nat_bitmaps(sbi);
if (err)
return err;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 6aea13024ac1..103a437e6425 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -52,6 +52,13 @@ enum {
IS_PREALLOC, /* nat entry is preallocated */
};
+/* For node type in __get_node_folio() */
+enum node_type {
+ NODE_TYPE_REGULAR,
+ NODE_TYPE_INODE,
+ NODE_TYPE_XATTR,
+};
+
/*
* For node information
*/
@@ -248,7 +255,7 @@ static inline nid_t nid_of_node(struct page *node_page)
return le32_to_cpu(rn->footer.nid);
}
-static inline unsigned int ofs_of_node(struct page *node_page)
+static inline unsigned int ofs_of_node(const struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
unsigned flag = le32_to_cpu(rn->footer.flag);
@@ -342,7 +349,7 @@ static inline bool is_recoverable_dnode(struct page *page)
* `- indirect node ((6 + 2N) + (N - 1)(N + 1))
* `- direct node
*/
-static inline bool IS_DNODE(struct page *node_page)
+static inline bool IS_DNODE(const struct page *node_page)
{
unsigned int ofs = ofs_of_node(node_page);
@@ -389,7 +396,7 @@ static inline nid_t get_nid(struct page *p, int off, bool i)
* - Mark cold data pages in page cache
*/
-static inline int is_node(struct page *page, int type)
+static inline int is_node(const struct page *page, int type)
{
struct f2fs_node *rn = F2FS_NODE(page);
return le32_to_cpu(rn->footer.flag) & BIT(type);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index f35be2c48e3c..69a2027e3ebc 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -899,10 +899,8 @@ skip:
* and the f2fs is not read only, check and fix zoned block devices'
* write pointer consistency.
*/
- if (!err) {
+ if (!err)
err = f2fs_check_and_fix_write_pointer(sbi);
- ret = err;
- }
if (!err)
clear_sbi_flag(sbi, SBI_POR_DOING);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index eade36c5ef13..876e97ec5f57 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -201,6 +201,12 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
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);
@@ -245,7 +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,
@@ -370,7 +376,13 @@ out:
} else {
sbi->committed_atomic_block += fi->atomic_write_cnt;
set_inode_flag(inode, FI_ATOMIC_COMMITTED);
+
+ /*
+ * inode may has no FI_ATOMIC_DIRTIED flag due to no write
+ * before commit.
+ */
if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
+ /* clear atomic dirty status and set vfs dirty status */
clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
f2fs_mark_inode_dirty_sync(inode, true);
}
@@ -418,7 +430,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
if (need && excess_cached_nats(sbi))
f2fs_balance_fs_bg(sbi, false);
- if (!f2fs_is_checkpoint_ready(sbi))
+ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return;
/*
@@ -2090,7 +2102,9 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
return false;
if (!force) {
- if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks ||
+ if (!f2fs_realtime_discard_enable(sbi) ||
+ (!se->valid_blocks &&
+ !IS_CURSEG(sbi, cpc->trim_start)) ||
SM_I(sbi)->dcc_info->nr_discards >=
SM_I(sbi)->dcc_info->max_discards)
return false;
@@ -2314,10 +2328,9 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
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)
+ if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SEGMENT ||
+ F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
dcc->discard_granularity = BLKS_PER_SEG(sbi);
- else if (F2FS_OPTION(sbi).discard_unit == DISCARD_UNIT_SECTION)
- dcc->discard_granularity = BLKS_PER_SEC(sbi);
INIT_LIST_HEAD(&dcc->entry_list);
for (i = 0; i < MAX_PLIST_NUM; i++)
@@ -2426,78 +2439,38 @@ 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);
- 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) {
- 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
@@ -2505,7 +2478,7 @@ 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);
@@ -2513,12 +2486,91 @@ 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 */
@@ -2528,25 +2580,43 @@ 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);
}
@@ -2713,7 +2783,7 @@ static int get_new_segment(struct f2fs_sb_info *sbi,
if (sbi->blkzone_alloc_policy == BLKZONE_ALLOC_PRIOR_CONV || pinning)
segno = 0;
else
- segno = max(sbi->first_zoned_segno, *newseg);
+ segno = max(sbi->first_seq_zone_segno, *newseg);
hint = GET_SEC_FROM_SEG(sbi, segno);
}
#endif
@@ -2725,7 +2795,7 @@ find_other_zone:
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);
+ hint = GET_SEC_FROM_SEG(sbi, sbi->first_seq_zone_segno);
secno = find_next_zero_bit(free_i->free_secmap, MAIN_SECS(sbi), hint);
} else
secno = find_first_zero_bit(free_i->free_secmap,
@@ -2743,7 +2813,7 @@ find_other_zone:
MAIN_SECS(sbi));
if (secno >= MAIN_SECS(sbi)) {
ret = -ENOSPC;
- f2fs_bug_on(sbi, 1);
+ f2fs_bug_on(sbi, !pinning);
goto out_unlock;
}
}
@@ -2772,11 +2842,15 @@ find_other_zone:
}
got_it:
/* set it as dirty segment in free segmap */
- f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
+ if (test_bit(segno, free_i->free_segmap)) {
+ ret = -EFSCORRUPTED;
+ f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_CORRUPTED_FREE_BITMAP);
+ goto out_unlock;
+ }
- /* no free section in conventional zone */
+ /* no free section in conventional device or conventional zone */
if (new_sec && pinning &&
- !f2fs_valid_pinned_area(sbi, START_BLOCK(sbi, segno))) {
+ f2fs_is_sequential_zone_area(sbi, START_BLOCK(sbi, segno))) {
ret = -EAGAIN;
goto out_unlock;
}
@@ -2785,7 +2859,7 @@ got_it:
out_unlock:
spin_unlock(&free_i->segmap_lock);
- if (ret == -ENOSPC)
+ if (ret == -ENOSPC && !pinning)
f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_NO_SEGMENT);
return ret;
}
@@ -2858,6 +2932,13 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
return curseg->segno;
}
+static void reset_curseg_fields(struct curseg_info *curseg)
+{
+ curseg->inited = false;
+ curseg->segno = NULL_SEGNO;
+ curseg->next_segno = 0;
+}
+
/*
* Allocate a current working segment.
* This function always allocates a free segment in LFS manner.
@@ -2876,7 +2957,7 @@ static int new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
ret = get_new_segment(sbi, &segno, new_sec, pinning);
if (ret) {
if (ret == -ENOSPC)
- curseg->segno = NULL_SEGNO;
+ reset_curseg_fields(curseg);
return ret;
}
@@ -3240,7 +3321,7 @@ retry:
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),
+ err = f2fs_gc_range(sbi, 0, sbi->first_seq_zone_segno - 1,
true, ZONED_PIN_SEC_REQUIRED_COUNT);
f2fs_up_write(&sbi->gc_lock);
@@ -3647,13 +3728,6 @@ static void f2fs_randomize_chunk(struct f2fs_sb_info *sbi,
get_random_u32_inclusive(1, sbi->max_fragment_hole);
}
-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,
@@ -3839,6 +3913,7 @@ static int log_type_to_seg_type(enum log_type type)
static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
+ struct folio *folio = page_folio(fio->page);
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) &&
@@ -3849,15 +3924,15 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *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))
+ if (fscrypt_inode_uses_fs_layer_crypto(folio->mapping->host))
fscrypt_finalize_bounce_page(&fio->encrypted_page);
- end_page_writeback(fio->page);
- if (f2fs_in_warm_node_list(fio->sbi, fio->page))
+ folio_end_writeback(folio);
+ if (f2fs_in_warm_node_list(fio->sbi, folio))
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);
@@ -4049,7 +4124,7 @@ 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);
@@ -4091,22 +4166,21 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
f2fs_update_data_blkaddr(dn, new_addr);
}
-void f2fs_wait_on_page_writeback(struct page *page,
- enum page_type type, bool ordered, bool locked)
+void f2fs_folio_wait_writeback(struct folio *folio, enum page_type type,
+ bool ordered, bool locked)
{
- if (folio_test_writeback(page_folio(page))) {
- struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+ if (folio_test_writeback(folio)) {
+ struct f2fs_sb_info *sbi = F2FS_F_SB(folio);
/* submit cached LFS IO */
- f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type);
+ f2fs_submit_merged_write_cond(sbi, NULL, &folio->page, 0, type);
/* submit cached IPU IO */
- f2fs_submit_merged_ipu_write(sbi, NULL, page);
+ f2fs_submit_merged_ipu_write(sbi, NULL, &folio->page);
if (ordered) {
- wait_on_page_writeback(page);
- f2fs_bug_on(sbi, locked &&
- folio_test_writeback(page_folio(page)));
+ folio_wait_writeback(folio);
+ f2fs_bug_on(sbi, locked && folio_test_writeback(folio));
} else {
- wait_for_stable_page(page);
+ folio_wait_stable(folio);
}
}
}
@@ -5405,7 +5479,8 @@ int f2fs_check_and_fix_write_pointer(struct f2fs_sb_info *sbi)
{
int ret;
- if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb))
+ if (!f2fs_sb_has_blkzoned(sbi) || f2fs_readonly(sbi->sb) ||
+ f2fs_hw_is_readonly(sbi))
return 0;
f2fs_notice(sbi, "Checking entire write pointers");
@@ -5492,8 +5567,10 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
secno = GET_SEC_FROM_SEG(sbi, segno);
start = GET_SEG_FROM_SEC(sbi, secno);
- if (!__is_large_section(sbi))
- return get_seg_entry(sbi, start + i)->mtime;
+ 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 */
@@ -5506,7 +5583,11 @@ unsigned long long f2fs_get_section_mtime(struct f2fs_sb_info *sbi,
if (total_valid_blocks == 0)
return INVALID_MTIME;
- return div_u64(mtime, total_valid_blocks);
+ mtime = div_u64(mtime, total_valid_blocks);
+out:
+ if (unlikely(mtime == INVALID_MTIME))
+ mtime -= 1;
+ return mtime;
}
/*
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 943be4f1d6d2..503f6df690bf 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -429,7 +429,6 @@ 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);
spin_lock(&free_i->segmap_lock);
clear_bit(segno, free_i->free_segmap);
@@ -437,7 +436,7 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
next = find_next_bit(free_i->free_segmap,
start_segno + SEGS_PER_SEC(sbi), start_segno);
- if (next >= start_segno + usable_segs) {
+ if (next >= start_segno + f2fs_usable_segs_in_sec(sbi)) {
clear_bit(secno, free_i->free_secmap);
free_i->free_sections++;
}
@@ -463,22 +462,36 @@ 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);
+ bool ret;
spin_lock(&free_i->segmap_lock);
- if (test_and_clear_bit(segno, free_i->free_segmap)) {
- free_i->free_segments++;
-
- if (!inmem && IS_CURSEC(sbi, secno))
- goto skip_free;
- next = find_next_bit(free_i->free_segmap,
- 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++;
- }
- }
-skip_free:
+ ret = test_and_clear_bit(segno, free_i->free_segmap);
+ if (!ret)
+ goto unlock_out;
+
+ free_i->free_segments++;
+
+ if (!inmem && IS_CURSEC(sbi, secno))
+ goto unlock_out;
+
+ /* check large section */
+ next = find_next_bit(free_i->free_segmap,
+ start_segno + SEGS_PER_SEC(sbi), start_segno);
+ if (next < start_segno + f2fs_usable_segs_in_sec(sbi))
+ goto unlock_out;
+
+ ret = test_and_clear_bit(secno, free_i->free_secmap);
+ if (!ret)
+ goto unlock_out;
+
+ free_i->free_sections++;
+
+ if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[BG_GC]) == secno)
+ sbi->next_victim_seg[BG_GC] = NULL_SEGNO;
+ if (GET_SEC_FROM_SEG(sbi, sbi->next_victim_seg[FG_GC]) == secno)
+ sbi->next_victim_seg[FG_GC] = NULL_SEGNO;
+
+unlock_out:
spin_unlock(&free_i->segmap_lock);
}
@@ -559,13 +572,16 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
unsigned int node_blocks, unsigned int data_blocks,
unsigned int dent_blocks)
{
-
unsigned int segno, left_blocks, blocks;
int 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;
+
+ if (unlikely(segno == NULL_SEGNO))
+ return false;
+
left_blocks = CAP_BLKS_PER_SEC(sbi) -
get_ckpt_valid_blocks(sbi, segno, true);
@@ -576,6 +592,10 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi,
/* check current data section for dentry blocks. */
segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno;
+
+ if (unlikely(segno == NULL_SEGNO))
+ return false;
+
left_blocks = CAP_BLKS_PER_SEC(sbi) -
get_ckpt_valid_blocks(sbi, segno, true);
if (dent_blocks > left_blocks)
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
index 83d6fb97dcae..9c8d3aee89af 100644
--- a/fs/f2fs/shrinker.c
+++ b/fs/f2fs/shrinker.c
@@ -73,7 +73,7 @@ unsigned long f2fs_shrink_count(struct shrinker *shrink,
mutex_unlock(&sbi->umount_mutex);
}
spin_unlock(&f2fs_list_lock);
- return count;
+ return count ?: SHRINK_EMPTY;
}
unsigned long f2fs_shrink_scan(struct shrinker *shrink,
@@ -130,6 +130,96 @@ unsigned long f2fs_shrink_scan(struct shrinker *shrink,
return freed;
}
+unsigned int f2fs_donate_files(void)
+{
+ struct f2fs_sb_info *sbi;
+ struct list_head *p;
+ unsigned int donate_files = 0;
+
+ spin_lock(&f2fs_list_lock);
+ p = f2fs_list.next;
+ while (p != &f2fs_list) {
+ sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+ /* stop f2fs_put_super */
+ if (!mutex_trylock(&sbi->umount_mutex)) {
+ p = p->next;
+ continue;
+ }
+ spin_unlock(&f2fs_list_lock);
+
+ donate_files += sbi->donate_files;
+
+ spin_lock(&f2fs_list_lock);
+ p = p->next;
+ mutex_unlock(&sbi->umount_mutex);
+ }
+ spin_unlock(&f2fs_list_lock);
+
+ return donate_files;
+}
+
+static unsigned int do_reclaim_caches(struct f2fs_sb_info *sbi,
+ unsigned int reclaim_caches_kb)
+{
+ struct inode *inode;
+ struct f2fs_inode_info *fi;
+ unsigned int nfiles = sbi->donate_files;
+ pgoff_t npages = reclaim_caches_kb >> (PAGE_SHIFT - 10);
+
+ while (npages && nfiles--) {
+ pgoff_t len;
+
+ spin_lock(&sbi->inode_lock[DONATE_INODE]);
+ if (list_empty(&sbi->inode_list[DONATE_INODE])) {
+ spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+ break;
+ }
+ fi = list_first_entry(&sbi->inode_list[DONATE_INODE],
+ struct f2fs_inode_info, gdonate_list);
+ list_move_tail(&fi->gdonate_list, &sbi->inode_list[DONATE_INODE]);
+ inode = igrab(&fi->vfs_inode);
+ spin_unlock(&sbi->inode_lock[DONATE_INODE]);
+
+ if (!inode)
+ continue;
+
+ len = fi->donate_end - fi->donate_start + 1;
+ npages = npages < len ? 0 : npages - len;
+ invalidate_inode_pages2_range(inode->i_mapping,
+ fi->donate_start, fi->donate_end);
+ iput(inode);
+ cond_resched();
+ }
+ return npages << (PAGE_SHIFT - 10);
+}
+
+void f2fs_reclaim_caches(unsigned int reclaim_caches_kb)
+{
+ struct f2fs_sb_info *sbi;
+ struct list_head *p;
+
+ spin_lock(&f2fs_list_lock);
+ p = f2fs_list.next;
+ while (p != &f2fs_list && reclaim_caches_kb) {
+ sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+ /* stop f2fs_put_super */
+ if (!mutex_trylock(&sbi->umount_mutex)) {
+ p = p->next;
+ continue;
+ }
+ spin_unlock(&f2fs_list_lock);
+
+ reclaim_caches_kb = do_reclaim_caches(sbi, reclaim_caches_kb);
+
+ spin_lock(&f2fs_list_lock);
+ p = p->next;
+ mutex_unlock(&sbi->umount_mutex);
+ }
+ spin_unlock(&f2fs_list_lock);
+}
+
void f2fs_join_shrinker(struct f2fs_sb_info *sbi)
{
spin_lock(&f2fs_list_lock);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index fc7d463dee15..86dd30eb50b1 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -63,6 +63,7 @@ const char *f2fs_fault_name[FAULT_MAX] = {
[FAULT_BLKADDR_VALIDITY] = "invalid blkaddr",
[FAULT_BLKADDR_CONSISTENCE] = "inconsistent blkaddr",
[FAULT_NO_SEGMENT] = "no free segment",
+ [FAULT_INCONSISTENT_FOOTER] = "inconsistent footer",
};
int f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned long rate,
@@ -190,6 +191,7 @@ enum {
Opt_memory_mode,
Opt_age_extent_cache,
Opt_errors,
+ Opt_nat_bits,
Opt_err,
};
@@ -269,6 +271,7 @@ static match_table_t f2fs_tokens = {
{Opt_memory_mode, "memory=%s"},
{Opt_age_extent_cache, "age_extent_cache"},
{Opt_errors, "errors=%s"},
+ {Opt_nat_bits, "nat_bits"},
{Opt_err, NULL},
};
@@ -383,10 +386,10 @@ static void init_once(void *foo)
#ifdef CONFIG_QUOTA
static const char * const quotatypes[] = INITQFNAMES;
#define QTYPE2NAME(t) (quotatypes[t])
-static int f2fs_set_qf_name(struct super_block *sb, int qtype,
+static int f2fs_set_qf_name(struct f2fs_sb_info *sbi, int qtype,
substring_t *args)
{
- struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct super_block *sb = sbi->sb;
char *qname;
int ret = -EINVAL;
@@ -424,9 +427,9 @@ errout:
return ret;
}
-static int f2fs_clear_qf_name(struct super_block *sb, int qtype)
+static int f2fs_clear_qf_name(struct f2fs_sb_info *sbi, int qtype)
{
- struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct super_block *sb = sbi->sb;
if (sb_any_quota_loaded(sb) && F2FS_OPTION(sbi).s_qf_names[qtype]) {
f2fs_err(sbi, "Cannot change journaled quota options when quota turned on");
@@ -483,12 +486,11 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi)
}
#endif
-static int f2fs_set_test_dummy_encryption(struct super_block *sb,
+static int f2fs_set_test_dummy_encryption(struct f2fs_sb_info *sbi,
const char *opt,
const substring_t *arg,
bool is_remount)
{
- struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct fs_parameter param = {
.type = fs_value_is_string,
.string = arg->from ? arg->from : "",
@@ -671,9 +673,8 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str)
#endif
#endif
-static int parse_options(struct super_block *sb, char *options, bool is_remount)
+static int parse_options(struct f2fs_sb_info *sbi, char *options, bool is_remount)
{
- struct f2fs_sb_info *sbi = F2FS_SB(sb);
substring_t args[MAX_OPT_ARGS];
#ifdef CONFIG_F2FS_FS_COMPRESSION
unsigned char (*ext)[F2FS_EXTENSION_LEN];
@@ -687,7 +688,7 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
int ret;
if (!options)
- goto default_check;
+ return 0;
while ((p = strsep(&options, ",")) != NULL) {
int token;
@@ -728,10 +729,8 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
set_opt(sbi, DISABLE_ROLL_FORWARD);
break;
case Opt_norecovery:
- /* this option mounts f2fs with ro */
+ /* requires ro mount, checked in f2fs_default_check */
set_opt(sbi, NORECOVERY);
- if (!f2fs_readonly(sb))
- return -EINVAL;
break;
case Opt_discard:
if (!f2fs_hw_support_discard(sbi)) {
@@ -772,16 +771,11 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
break;
#else
case Opt_user_xattr:
- f2fs_info(sbi, "user_xattr options not supported");
- break;
case Opt_nouser_xattr:
- f2fs_info(sbi, "nouser_xattr options not supported");
- break;
case Opt_inline_xattr:
- f2fs_info(sbi, "inline_xattr options not supported");
- break;
case Opt_noinline_xattr:
- f2fs_info(sbi, "noinline_xattr options not supported");
+ case Opt_inline_xattr_size:
+ f2fs_info(sbi, "xattr options not supported");
break;
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
@@ -793,10 +787,8 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
break;
#else
case Opt_acl:
- f2fs_info(sbi, "acl options not supported");
- break;
case Opt_noacl:
- f2fs_info(sbi, "noacl options not supported");
+ f2fs_info(sbi, "acl options not supported");
break;
#endif
case Opt_active_logs:
@@ -838,7 +830,7 @@ 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)) {
+ if (f2fs_sb_has_device_alias(sbi)) {
f2fs_err(sbi, "device aliasing requires extent cache");
return -EINVAL;
}
@@ -919,18 +911,15 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
break;
#else
case Opt_fault_injection:
- f2fs_info(sbi, "fault_injection options not supported");
- break;
-
case Opt_fault_type:
- f2fs_info(sbi, "fault_type options not supported");
+ f2fs_info(sbi, "fault injection options not supported");
break;
#endif
case Opt_lazytime:
- sb->s_flags |= SB_LAZYTIME;
+ set_opt(sbi, LAZYTIME);
break;
case Opt_nolazytime:
- sb->s_flags &= ~SB_LAZYTIME;
+ clear_opt(sbi, LAZYTIME);
break;
#ifdef CONFIG_QUOTA
case Opt_quota:
@@ -944,32 +933,32 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
set_opt(sbi, PRJQUOTA);
break;
case Opt_usrjquota:
- ret = f2fs_set_qf_name(sb, USRQUOTA, &args[0]);
+ ret = f2fs_set_qf_name(sbi, USRQUOTA, &args[0]);
if (ret)
return ret;
break;
case Opt_grpjquota:
- ret = f2fs_set_qf_name(sb, GRPQUOTA, &args[0]);
+ ret = f2fs_set_qf_name(sbi, GRPQUOTA, &args[0]);
if (ret)
return ret;
break;
case Opt_prjjquota:
- ret = f2fs_set_qf_name(sb, PRJQUOTA, &args[0]);
+ ret = f2fs_set_qf_name(sbi, PRJQUOTA, &args[0]);
if (ret)
return ret;
break;
case Opt_offusrjquota:
- ret = f2fs_clear_qf_name(sb, USRQUOTA);
+ ret = f2fs_clear_qf_name(sbi, USRQUOTA);
if (ret)
return ret;
break;
case Opt_offgrpjquota:
- ret = f2fs_clear_qf_name(sb, GRPQUOTA);
+ ret = f2fs_clear_qf_name(sbi, GRPQUOTA);
if (ret)
return ret;
break;
case Opt_offprjjquota:
- ret = f2fs_clear_qf_name(sb, PRJQUOTA);
+ ret = f2fs_clear_qf_name(sbi, PRJQUOTA);
if (ret)
return ret;
break;
@@ -1039,14 +1028,14 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
kfree(name);
break;
case Opt_test_dummy_encryption:
- ret = f2fs_set_test_dummy_encryption(sb, p, &args[0],
+ ret = f2fs_set_test_dummy_encryption(sbi, p, &args[0],
is_remount);
if (ret)
return ret;
break;
case Opt_inlinecrypt:
#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
- sb->s_flags |= SB_INLINECRYPT;
+ set_opt(sbi, INLINECRYPT);
#else
f2fs_info(sbi, "inline encryption not supported");
#endif
@@ -1322,13 +1311,20 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount)
}
kfree(name);
break;
+ case Opt_nat_bits:
+ set_opt(sbi, NAT_BITS);
+ break;
default:
f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
p);
return -EINVAL;
}
}
-default_check:
+ return 0;
+}
+
+static int f2fs_default_check(struct f2fs_sb_info *sbi)
+{
#ifdef CONFIG_QUOTA
if (f2fs_check_quota_options(sbi))
return -EINVAL;
@@ -1418,6 +1414,12 @@ default_check:
f2fs_err(sbi, "Allow to mount readonly mode only");
return -EROFS;
}
+
+ if (test_opt(sbi, NORECOVERY) && !f2fs_readonly(sbi->sb)) {
+ f2fs_err(sbi, "norecovery requires readonly mount");
+ return -EINVAL;
+ }
+
return 0;
}
@@ -1441,6 +1443,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
spin_lock_init(&fi->i_size_lock);
INIT_LIST_HEAD(&fi->dirty_list);
INIT_LIST_HEAD(&fi->gdirty_list);
+ INIT_LIST_HEAD(&fi->gdonate_list);
init_f2fs_rwsem(&fi->i_gc_rwsem[READ]);
init_f2fs_rwsem(&fi->i_gc_rwsem[WRITE]);
init_f2fs_rwsem(&fi->i_xattr_sem);
@@ -1527,6 +1530,12 @@ int f2fs_inode_dirtied(struct inode *inode, bool sync)
inc_page_count(sbi, F2FS_DIRTY_IMETA);
}
spin_unlock(&sbi->inode_lock[DIRTY_META]);
+
+ /* if atomic write is not committed, set inode w/ atomic dirty */
+ if (!ret && f2fs_is_atomic_file(inode) &&
+ !is_inode_flag_set(inode, FI_ATOMIC_COMMITTED))
+ set_inode_flag(inode, FI_ATOMIC_DIRTIED);
+
return ret;
}
@@ -1694,8 +1703,6 @@ 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);
@@ -1739,22 +1746,28 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
static int f2fs_freeze(struct super_block *sb)
{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
if (f2fs_readonly(sb))
return 0;
/* IO error happened before */
- if (unlikely(f2fs_cp_error(F2FS_SB(sb))))
+ if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
/* must be clean, since sync_filesystem() was already called */
- if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY))
+ if (is_sbi_flag_set(sbi, SBI_IS_DIRTY))
return -EINVAL;
+ sbi->umount_lock_holder = current;
+
/* Let's flush checkpoints and stop the thread. */
- f2fs_flush_ckpt_thread(F2FS_SB(sb));
+ f2fs_flush_ckpt_thread(sbi);
+
+ sbi->umount_lock_holder = NULL;
/* to avoid deadlock on f2fs_evict_inode->SB_FREEZE_FS */
- set_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING);
+ set_sbi_flag(sbi, SBI_IS_FREEZING);
return 0;
}
@@ -1793,26 +1806,32 @@ static int f2fs_statfs_project(struct super_block *sb,
limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit,
dquot->dq_dqb.dqb_bhardlimit);
- if (limit)
- limit >>= sb->s_blocksize_bits;
+ limit >>= sb->s_blocksize_bits;
+
+ if (limit) {
+ uint64_t remaining = 0;
- if (limit && buf->f_blocks > limit) {
curblock = (dquot->dq_dqb.dqb_curspace +
dquot->dq_dqb.dqb_rsvspace) >> sb->s_blocksize_bits;
- buf->f_blocks = limit;
- buf->f_bfree = buf->f_bavail =
- (buf->f_blocks > curblock) ?
- (buf->f_blocks - curblock) : 0;
+ if (limit > curblock)
+ remaining = limit - curblock;
+
+ buf->f_blocks = min(buf->f_blocks, limit);
+ buf->f_bfree = min(buf->f_bfree, remaining);
+ buf->f_bavail = min(buf->f_bavail, remaining);
}
limit = min_not_zero(dquot->dq_dqb.dqb_isoftlimit,
dquot->dq_dqb.dqb_ihardlimit);
- if (limit && buf->f_files > limit) {
- buf->f_files = limit;
- buf->f_ffree =
- (buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
- (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
+ if (limit) {
+ uint64_t remaining = 0;
+
+ if (limit > dquot->dq_dqb.dqb_curinodes)
+ remaining = limit - dquot->dq_dqb.dqb_curinodes;
+
+ buf->f_files = min(buf->f_files, limit);
+ buf->f_ffree = min(buf->f_ffree, remaining);
}
spin_unlock(&dquot->dq_dqb_lock);
@@ -1838,7 +1857,8 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_blocks = total_count - start_count;
spin_lock(&sbi->stat_lock);
-
+ if (sbi->carve_out)
+ buf->f_blocks -= sbi->current_reserved_blocks;
user_block_count = sbi->user_block_count;
total_valid_node_count = valid_node_count(sbi);
avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
@@ -1870,9 +1890,9 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_fsid = u64_to_fsid(id);
#ifdef CONFIG_QUOTA
- if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) &&
+ if (is_inode_flag_set(d_inode(dentry), FI_PROJ_INHERIT) &&
sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
- f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf);
+ f2fs_statfs_project(sb, F2FS_I(d_inode(dentry))->i_projid, buf);
}
#endif
return 0;
@@ -2130,6 +2150,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC)
seq_printf(seq, ",errors=%s", "panic");
+ if (test_opt(sbi, NAT_BITS))
+ seq_puts(seq, ",nat_bits");
+
return 0;
}
@@ -2177,8 +2200,8 @@ static void default_options(struct f2fs_sb_info *sbi, bool remount)
set_opt(sbi, INLINE_DATA);
set_opt(sbi, INLINE_DENTRY);
set_opt(sbi, MERGE_CHECKPOINT);
+ set_opt(sbi, LAZYTIME);
F2FS_OPTION(sbi).unusable_cap = 0;
- sbi->sb->s_flags |= SB_LAZYTIME;
if (!f2fs_is_readonly(sbi))
set_opt(sbi, FLUSH_MERGE);
if (f2fs_sb_has_blkzoned(sbi))
@@ -2320,6 +2343,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
bool no_discard = !test_opt(sbi, DISCARD);
bool no_compress_cache = !test_opt(sbi, COMPRESS_CACHE);
bool block_unit_discard = f2fs_block_unit_discard(sbi);
+ bool no_nat_bits = !test_opt(sbi, NAT_BITS);
#ifdef CONFIG_QUOTA
int i, j;
#endif
@@ -2331,6 +2355,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
org_mount_opt = sbi->mount_opt;
old_sb_flags = sb->s_flags;
+ sbi->umount_lock_holder = current;
+
#ifdef CONFIG_QUOTA
org_mount_opt.s_jquota_fmt = F2FS_OPTION(sbi).s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
@@ -2361,7 +2387,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
default_options(sbi, true);
/* parse mount options */
- err = parse_options(sb, data, true);
+ err = parse_options(sbi, data, true);
if (err)
goto restore_opts;
@@ -2376,6 +2402,10 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
}
#endif
+ err = f2fs_default_check(sbi);
+ if (err)
+ goto restore_opts;
+
/* flush outstanding errors before changing fs state */
flush_work(&sbi->s_error_work);
@@ -2446,6 +2476,12 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
+ if (no_nat_bits == !!test_opt(sbi, NAT_BITS)) {
+ err = -EINVAL;
+ f2fs_warn(sbi, "switch nat_bits option is not allowed");
+ goto restore_opts;
+ }
+
if ((*flags & SB_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) {
err = -EINVAL;
f2fs_warn(sbi, "disabling checkpoint not compatible with read-only");
@@ -2554,6 +2590,8 @@ skip:
limit_reserve_root(sbi);
*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
+
+ sbi->umount_lock_holder = NULL;
return 0;
restore_checkpoint:
if (need_enable_checkpoint) {
@@ -2594,6 +2632,8 @@ restore_opts:
#endif
sbi->mount_opt = org_mount_opt;
sb->s_flags = old_sb_flags;
+
+ sbi->umount_lock_holder = NULL;
return err;
}
@@ -2910,7 +2950,7 @@ out:
return ret;
}
-int f2fs_quota_sync(struct super_block *sb, int type)
+int f2fs_do_quota_sync(struct super_block *sb, int type)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct quota_info *dqopt = sb_dqopt(sb);
@@ -2958,11 +2998,21 @@ int f2fs_quota_sync(struct super_block *sb, int type)
return ret;
}
+static int f2fs_quota_sync(struct super_block *sb, int type)
+{
+ int ret;
+
+ F2FS_SB(sb)->umount_lock_holder = current;
+ ret = f2fs_do_quota_sync(sb, type);
+ F2FS_SB(sb)->umount_lock_holder = NULL;
+ return ret;
+}
+
static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
const struct path *path)
{
struct inode *inode;
- int err;
+ int err = 0;
/* if quota sysfile exists, deny enabling quota with specific file */
if (f2fs_sb_has_quota_ino(F2FS_SB(sb))) {
@@ -2973,31 +3023,34 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
if (path->dentry->d_sb != sb)
return -EXDEV;
- err = f2fs_quota_sync(sb, type);
+ F2FS_SB(sb)->umount_lock_holder = current;
+
+ err = f2fs_do_quota_sync(sb, type);
if (err)
- return err;
+ goto out;
inode = d_inode(path->dentry);
err = filemap_fdatawrite(inode->i_mapping);
if (err)
- return err;
+ goto out;
err = filemap_fdatawait(inode->i_mapping);
if (err)
- return err;
+ goto out;
err = dquot_quota_on(sb, type, format_id, path);
if (err)
- return err;
+ goto out;
inode_lock(inode);
F2FS_I(inode)->i_flags |= F2FS_QUOTA_DEFAULT_FL;
f2fs_set_inode_flags(inode);
inode_unlock(inode);
f2fs_mark_inode_dirty_sync(inode, false);
-
- return 0;
+out:
+ F2FS_SB(sb)->umount_lock_holder = NULL;
+ return err;
}
static int __f2fs_quota_off(struct super_block *sb, int type)
@@ -3008,7 +3061,7 @@ static int __f2fs_quota_off(struct super_block *sb, int type)
if (!inode || !igrab(inode))
return dquot_quota_off(sb, type);
- err = f2fs_quota_sync(sb, type);
+ err = f2fs_do_quota_sync(sb, type);
if (err)
goto out_put;
@@ -3031,6 +3084,8 @@ static int f2fs_quota_off(struct super_block *sb, int type)
struct f2fs_sb_info *sbi = F2FS_SB(sb);
int err;
+ F2FS_SB(sb)->umount_lock_holder = current;
+
err = __f2fs_quota_off(sb, type);
/*
@@ -3040,6 +3095,9 @@ static int f2fs_quota_off(struct super_block *sb, int type)
*/
if (is_journalled_quota(sbi))
set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR);
+
+ F2FS_SB(sb)->umount_lock_holder = NULL;
+
return err;
}
@@ -3172,7 +3230,7 @@ int f2fs_dquot_initialize(struct inode *inode)
return 0;
}
-int f2fs_quota_sync(struct super_block *sb, int type)
+int f2fs_do_quota_sync(struct super_block *sb, int type)
{
return 0;
}
@@ -3667,6 +3725,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi)
block_t user_block_count, valid_user_blocks;
block_t avail_node_count, valid_node_count;
unsigned int nat_blocks, nat_bits_bytes, nat_bits_blocks;
+ unsigned int sit_blk_cnt;
int i, j;
total = le32_to_cpu(raw_super->segment_count);
@@ -3778,6 +3837,13 @@ skip_cross:
return 1;
}
+ sit_blk_cnt = DIV_ROUND_UP(main_segs, SIT_ENTRY_PER_BLOCK);
+ if (sit_bitmap_size * 8 < sit_blk_cnt) {
+ f2fs_err(sbi, "Wrong bitmap size: sit: %u, sit_blk_cnt:%u",
+ sit_bitmap_size, sit_blk_cnt);
+ return 1;
+ }
+
cp_pack_start_sum = __start_sum_addr(sbi);
cp_payload = __cp_payload(sbi);
if (cp_pack_start_sum < cp_payload + 1 ||
@@ -4222,6 +4288,8 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason)
if (shutdown)
set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+ else
+ dump_stack();
/*
* Continue filesystem operators if errors=continue. Should not set
@@ -4252,14 +4320,35 @@ 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)
+static inline unsigned int get_first_seq_zone_segno(struct f2fs_sb_info *sbi)
{
+#ifdef CONFIG_BLK_DEV_ZONED
+ unsigned int zoneno, total_zones;
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;
+ if (!f2fs_sb_has_blkzoned(sbi))
+ return NULL_SEGNO;
+
+ for (devi = 0; devi < sbi->s_ndevs; devi++) {
+ if (!bdev_is_zoned(FDEV(devi).bdev))
+ continue;
+
+ total_zones = GET_ZONE_FROM_SEG(sbi, FDEV(devi).total_segments);
+
+ for (zoneno = 0; zoneno < total_zones; zoneno++) {
+ unsigned int segs, blks;
+
+ if (!f2fs_zone_is_seq(sbi, devi, zoneno))
+ continue;
+
+ segs = GET_SEG_FROM_SEC(sbi,
+ zoneno * sbi->secs_per_zone);
+ blks = SEGS_TO_BLKS(sbi, segs);
+ return GET_SEGNO(sbi, FDEV(devi).start_blk + blks);
+ }
+ }
+#endif
+ return NULL_SEGNO;
}
static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
@@ -4296,6 +4385,14 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
#endif
for (i = 0; i < max_devices; i++) {
+ if (max_devices == 1) {
+ FDEV(i).total_segments =
+ le32_to_cpu(raw_super->segment_count_main);
+ FDEV(i).start_blk = 0;
+ FDEV(i).end_blk = FDEV(i).total_segments *
+ BLKS_PER_SEG(sbi);
+ }
+
if (i == 0)
FDEV(0).bdev_file = sbi->sb->s_bdev_file;
else if (!RDEV(i).path[0])
@@ -4466,15 +4563,6 @@ 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");
@@ -4506,7 +4594,11 @@ try_onemore:
goto free_sb_buf;
}
- err = parse_options(sb, options, false);
+ err = parse_options(sbi, options, false);
+ if (err)
+ goto free_options;
+
+ err = f2fs_default_check(sbi);
if (err)
goto free_options;
@@ -4544,6 +4636,14 @@ try_onemore:
sb->s_time_gran = 1;
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
+ if (test_opt(sbi, INLINECRYPT))
+ sb->s_flags |= SB_INLINECRYPT;
+
+ if (test_opt(sbi, LAZYTIME))
+ sb->s_flags |= SB_LAZYTIME;
+ else
+ sb->s_flags &= ~SB_LAZYTIME;
+
super_set_uuid(sb, (void *) raw_super->uuid, sizeof(raw_super->uuid));
super_set_sysfs_name_bdev(sb);
sb->s_iflags |= SB_I_CGROUPWB;
@@ -4663,7 +4763,7 @@ try_onemore:
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);
+ sbi->first_seq_zone_segno = get_first_seq_zone_segno(sbi);
/* Read accumulated write IO statistics if exists */
seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
@@ -4714,6 +4814,7 @@ try_onemore:
if (err)
goto free_compress_inode;
+ sbi->umount_lock_holder = current;
#ifdef CONFIG_QUOTA
/* Enable quota usage during mount */
if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) {
@@ -4729,8 +4830,10 @@ try_onemore:
if (err)
goto free_meta;
- if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)))
+ if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) {
+ skip_recovery = true;
goto reset_checkpoint;
+ }
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD) &&
@@ -4780,10 +4883,10 @@ try_onemore:
}
}
+reset_checkpoint:
#ifdef CONFIG_QUOTA
f2fs_recover_quota_end(sbi, quota_enabled);
#endif
-reset_checkpoint:
/*
* If the f2fs is not readonly and fsync data recovery succeeds,
* write pointer consistency of cursegs and other zones are already
@@ -4840,6 +4943,8 @@ reset_checkpoint:
f2fs_update_time(sbi, CP_TIME);
f2fs_update_time(sbi, REQ_TIME);
clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK);
+
+ sbi->umount_lock_holder = NULL;
return 0;
sync_free_meta:
@@ -4919,8 +5024,6 @@ 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;
@@ -4944,6 +5047,8 @@ static void kill_f2fs_super(struct super_block *sb)
struct f2fs_sb_info *sbi = F2FS_SB(sb);
if (sb->s_root) {
+ sbi->umount_lock_holder = current;
+
set_sbi_flag(sbi, SBI_IS_CLOSE);
f2fs_stop_gc_thread(sbi);
f2fs_stop_discard_thread(sbi);
@@ -5127,5 +5232,3 @@ 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 6b99dc49f776..c69161366467 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -61,6 +61,12 @@ struct f2fs_attr {
int id;
};
+struct f2fs_base_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct f2fs_base_attr *a, char *buf);
+ ssize_t (*store)(struct f2fs_base_attr *a, const char *buf, size_t len);
+};
+
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf);
@@ -862,6 +868,25 @@ static void f2fs_sb_release(struct kobject *kobj)
complete(&sbi->s_kobj_unregister);
}
+static ssize_t f2fs_base_attr_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct f2fs_base_attr *a = container_of(attr,
+ struct f2fs_base_attr, attr);
+
+ return a->show ? a->show(a, buf) : 0;
+}
+
+static ssize_t f2fs_base_attr_store(struct kobject *kobj,
+ struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct f2fs_base_attr *a = container_of(attr,
+ struct f2fs_base_attr, attr);
+
+ return a->store ? a->store(a, buf, len) : 0;
+}
+
/*
* Note that there are three feature list entries:
* 1) /sys/fs/f2fs/features
@@ -880,18 +905,50 @@ static void f2fs_sb_release(struct kobject *kobj)
* please add new on-disk feature in this list only.
* - ref. F2FS_SB_FEATURE_RO_ATTR()
*/
-static ssize_t f2fs_feature_show(struct f2fs_attr *a,
- struct f2fs_sb_info *sbi, char *buf)
+static ssize_t f2fs_feature_show(struct f2fs_base_attr *a, char *buf)
{
return sysfs_emit(buf, "supported\n");
}
#define F2FS_FEATURE_RO_ATTR(_name) \
-static struct f2fs_attr f2fs_attr_##_name = { \
+static struct f2fs_base_attr f2fs_base_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = 0444 }, \
.show = f2fs_feature_show, \
}
+static ssize_t f2fs_tune_show(struct f2fs_base_attr *a, char *buf)
+{
+ unsigned int res = 0;
+
+ if (!strcmp(a->attr.name, "reclaim_caches_kb"))
+ res = f2fs_donate_files();
+
+ return sysfs_emit(buf, "%u\n", res);
+}
+
+static ssize_t f2fs_tune_store(struct f2fs_base_attr *a,
+ const char *buf, size_t count)
+{
+ unsigned long t;
+ int ret;
+
+ ret = kstrtoul(skip_spaces(buf), 0, &t);
+ if (ret)
+ return ret;
+
+ if (!strcmp(a->attr.name, "reclaim_caches_kb"))
+ f2fs_reclaim_caches(t);
+
+ return count;
+}
+
+#define F2FS_TUNE_RW_ATTR(_name) \
+static struct f2fs_base_attr f2fs_base_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = 0644 }, \
+ .show = f2fs_tune_show, \
+ .store = f2fs_tune_store, \
+}
+
static ssize_t f2fs_sb_feature_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -1065,6 +1122,7 @@ F2FS_SBI_GENERAL_RW_ATTR(max_read_extent_count);
F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec);
F2FS_SBI_GENERAL_RW_ATTR(blkzone_alloc_policy);
#endif
+F2FS_SBI_GENERAL_RW_ATTR(carve_out);
/* STAT_INFO ATTR */
#ifdef CONFIG_F2FS_STAT_FS
@@ -1252,41 +1310,43 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(warm_data_age_threshold),
ATTR_LIST(last_age_weight),
ATTR_LIST(max_read_extent_count),
+ ATTR_LIST(carve_out),
NULL,
};
ATTRIBUTE_GROUPS(f2fs);
+#define BASE_ATTR_LIST(name) (&f2fs_base_attr_##name.attr)
static struct attribute *f2fs_feat_attrs[] = {
#ifdef CONFIG_FS_ENCRYPTION
- ATTR_LIST(encryption),
- ATTR_LIST(test_dummy_encryption_v2),
+ BASE_ATTR_LIST(encryption),
+ BASE_ATTR_LIST(test_dummy_encryption_v2),
#if IS_ENABLED(CONFIG_UNICODE)
- ATTR_LIST(encrypted_casefold),
+ BASE_ATTR_LIST(encrypted_casefold),
#endif
#endif /* CONFIG_FS_ENCRYPTION */
#ifdef CONFIG_BLK_DEV_ZONED
- ATTR_LIST(block_zoned),
+ BASE_ATTR_LIST(block_zoned),
#endif
- ATTR_LIST(atomic_write),
- ATTR_LIST(extra_attr),
- ATTR_LIST(project_quota),
- ATTR_LIST(inode_checksum),
- ATTR_LIST(flexible_inline_xattr),
- ATTR_LIST(quota_ino),
- ATTR_LIST(inode_crtime),
- ATTR_LIST(lost_found),
+ BASE_ATTR_LIST(atomic_write),
+ BASE_ATTR_LIST(extra_attr),
+ BASE_ATTR_LIST(project_quota),
+ BASE_ATTR_LIST(inode_checksum),
+ BASE_ATTR_LIST(flexible_inline_xattr),
+ BASE_ATTR_LIST(quota_ino),
+ BASE_ATTR_LIST(inode_crtime),
+ BASE_ATTR_LIST(lost_found),
#ifdef CONFIG_FS_VERITY
- ATTR_LIST(verity),
+ BASE_ATTR_LIST(verity),
#endif
- ATTR_LIST(sb_checksum),
+ BASE_ATTR_LIST(sb_checksum),
#if IS_ENABLED(CONFIG_UNICODE)
- ATTR_LIST(casefold),
+ BASE_ATTR_LIST(casefold),
#endif
- ATTR_LIST(readonly),
+ BASE_ATTR_LIST(readonly),
#ifdef CONFIG_F2FS_FS_COMPRESSION
- ATTR_LIST(compression),
+ BASE_ATTR_LIST(compression),
#endif
- ATTR_LIST(pin_file),
+ BASE_ATTR_LIST(pin_file),
NULL,
};
ATTRIBUTE_GROUPS(f2fs_feat);
@@ -1343,6 +1403,14 @@ static struct attribute *f2fs_sb_feat_attrs[] = {
};
ATTRIBUTE_GROUPS(f2fs_sb_feat);
+F2FS_TUNE_RW_ATTR(reclaim_caches_kb);
+
+static struct attribute *f2fs_tune_attrs[] = {
+ BASE_ATTR_LIST(reclaim_caches_kb),
+ NULL,
+};
+ATTRIBUTE_GROUPS(f2fs_tune);
+
static const struct sysfs_ops f2fs_attr_ops = {
.show = f2fs_attr_show,
.store = f2fs_attr_store,
@@ -1362,15 +1430,34 @@ static struct kset f2fs_kset = {
.kobj = {.ktype = &f2fs_ktype},
};
+static const struct sysfs_ops f2fs_feat_attr_ops = {
+ .show = f2fs_base_attr_show,
+ .store = f2fs_base_attr_store,
+};
+
static const struct kobj_type f2fs_feat_ktype = {
.default_groups = f2fs_feat_groups,
- .sysfs_ops = &f2fs_attr_ops,
+ .sysfs_ops = &f2fs_feat_attr_ops,
};
static struct kobject f2fs_feat = {
.kset = &f2fs_kset,
};
+static const struct sysfs_ops f2fs_tune_attr_ops = {
+ .show = f2fs_base_attr_show,
+ .store = f2fs_base_attr_store,
+};
+
+static const struct kobj_type f2fs_tune_ktype = {
+ .default_groups = f2fs_tune_groups,
+ .sysfs_ops = &f2fs_tune_attr_ops,
+};
+
+static struct kobject f2fs_tune = {
+ .kset = &f2fs_kset,
+};
+
static ssize_t f2fs_stat_attr_show(struct kobject *kobj,
struct attribute *attr, char *buf)
{
@@ -1472,7 +1559,7 @@ 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++) {
@@ -1482,6 +1569,7 @@ 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;
@@ -1606,6 +1694,11 @@ int __init f2fs_init_sysfs(void)
if (ret)
goto put_kobject;
+ ret = kobject_init_and_add(&f2fs_tune, &f2fs_tune_ktype,
+ NULL, "tuning");
+ if (ret)
+ goto put_kobject;
+
f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
if (!f2fs_proc_root) {
ret = -ENOMEM;
@@ -1613,7 +1706,9 @@ int __init f2fs_init_sysfs(void)
}
return 0;
+
put_kobject:
+ kobject_put(&f2fs_tune);
kobject_put(&f2fs_feat);
kset_unregister(&f2fs_kset);
return ret;
@@ -1621,6 +1716,7 @@ put_kobject:
void f2fs_exit_sysfs(void)
{
+ kobject_put(&f2fs_tune);
kobject_put(&f2fs_feat);
kset_unregister(&f2fs_kset);
remove_proc_entry("fs/f2fs", NULL);
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 3f3874943679..c691b35618ad 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -282,7 +282,7 @@ static int read_inline_xattr(struct inode *inode, struct page *ipage,
if (ipage) {
inline_addr = inline_xattr_addr(inode, ipage);
} else {
- page = f2fs_get_node_page(sbi, inode->i_ino);
+ page = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(page))
return PTR_ERR(page);
@@ -303,7 +303,7 @@ static int read_xattr_block(struct inode *inode, void *txattr_addr)
void *xattr_addr;
/* The inode already has an extended attribute block. */
- xpage = f2fs_get_node_page(sbi, xnid);
+ xpage = f2fs_get_xnode_page(sbi, xnid);
if (IS_ERR(xpage))
return PTR_ERR(xpage);
@@ -449,7 +449,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
if (ipage) {
inline_addr = inline_xattr_addr(inode, ipage);
} else {
- in_page = f2fs_get_node_page(sbi, inode->i_ino);
+ in_page = f2fs_get_inode_page(sbi, inode->i_ino);
if (IS_ERR(in_page)) {
f2fs_alloc_nid_failed(sbi, new_nid);
return PTR_ERR(in_page);
@@ -475,7 +475,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
/* write to xattr node block */
if (F2FS_I(inode)->i_xattr_nid) {
- xpage = f2fs_get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+ xpage = f2fs_get_xnode_page(sbi, F2FS_I(inode)->i_xattr_nid);
if (IS_ERR(xpage)) {
err = PTR_ERR(xpage);
f2fs_alloc_nid_failed(sbi, new_nid);
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-12 13:32:46 +0300