summaryrefslogtreecommitdiffstats
path: root/fs/f2fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/f2fs')
-rw-r--r--fs/f2fs/Kconfig10
-rw-r--r--fs/f2fs/acl.h2
-rw-r--r--fs/f2fs/checkpoint.c52
-rw-r--r--fs/f2fs/compress.c263
-rw-r--r--fs/f2fs/data.c389
-rw-r--r--fs/f2fs/debug.c64
-rw-r--r--fs/f2fs/dir.c376
-rw-r--r--fs/f2fs/extent_cache.c18
-rw-r--r--fs/f2fs/f2fs.h270
-rw-r--r--fs/f2fs/file.c659
-rw-r--r--fs/f2fs/gc.c200
-rw-r--r--fs/f2fs/gc.h2
-rw-r--r--fs/f2fs/hash.c77
-rw-r--r--fs/f2fs/inline.c71
-rw-r--r--fs/f2fs/inode.c4
-rw-r--r--fs/f2fs/namei.c37
-rw-r--r--fs/f2fs/node.c132
-rw-r--r--fs/f2fs/node.h5
-rw-r--r--fs/f2fs/recovery.c63
-rw-r--r--fs/f2fs/segment.c149
-rw-r--r--fs/f2fs/segment.h12
-rw-r--r--fs/f2fs/super.c272
-rw-r--r--fs/f2fs/sysfs.c124
-rw-r--r--fs/f2fs/trace.h2
-rw-r--r--fs/f2fs/verity.c41
-rw-r--r--fs/f2fs/xattr.c4
-rw-r--r--fs/f2fs/xattr.h8
27 files changed, 2394 insertions, 912 deletions
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index bb68d21e1f8c..d13c5c6a9787 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -127,3 +127,13 @@ config F2FS_FS_ZSTD
default y
help
Support ZSTD compress algorithm, if unsure, say Y.
+
+config F2FS_FS_LZORLE
+ bool "LZO-RLE compression support"
+ depends on F2FS_FS_COMPRESSION
+ depends on F2FS_FS_LZO
+ select LZO_COMPRESS
+ select LZO_DECOMPRESS
+ default y
+ help
+ Support LZO-RLE compress algorithm, if unsure, say Y.
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
index b96823c59b15..124868c13f80 100644
--- a/fs/f2fs/acl.h
+++ b/fs/f2fs/acl.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* fs/f2fs/acl.h
*
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 852890b72d6a..ff807e14c891 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -86,6 +86,8 @@ repeat:
return ERR_PTR(err);
}
+ f2fs_update_iostat(sbi, FS_META_READ_IO, F2FS_BLKSIZE);
+
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
@@ -220,6 +222,7 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
.is_por = (type == META_POR),
};
struct blk_plug plug;
+ int err;
if (unlikely(type == META_POR))
fio.op_flags &= ~REQ_META;
@@ -263,8 +266,11 @@ int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
}
fio.page = page;
- f2fs_submit_page_bio(&fio);
- f2fs_put_page(page, 0);
+ err = f2fs_submit_page_bio(&fio);
+ f2fs_put_page(page, err ? 1 : 0);
+
+ if (!err)
+ f2fs_update_iostat(sbi, FS_META_READ_IO, F2FS_BLKSIZE);
}
out:
blk_finish_plug(&plug);
@@ -517,7 +523,7 @@ void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
__remove_ino_entry(sbi, ino, type);
}
-/* mode should be APPEND_INO or UPDATE_INO */
+/* mode should be APPEND_INO, UPDATE_INO or TRANS_DIR_INO */
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
struct inode_management *im = &sbi->im[mode];
@@ -889,8 +895,8 @@ int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
int i;
int err;
- sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
- GFP_KERNEL);
+ sbi->ckpt = f2fs_kvzalloc(sbi, array_size(blk_size, cp_blks),
+ GFP_KERNEL);
if (!sbi->ckpt)
return -ENOMEM;
/*
@@ -1160,10 +1166,12 @@ static int block_operations(struct f2fs_sb_info *sbi)
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
- struct blk_plug plug;
int err = 0, cnt = 0;
- blk_start_plug(&plug);
+ /*
+ * Let's flush inline_data in dirty node pages.
+ */
+ f2fs_flush_inline_data(sbi);
retry_flush_quotas:
f2fs_lock_all(sbi);
@@ -1192,7 +1200,7 @@ retry_flush_dents:
f2fs_unlock_all(sbi);
err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
if (err)
- goto out;
+ return err;
cond_resched();
goto retry_flush_quotas;
}
@@ -1208,7 +1216,7 @@ retry_flush_dents:
f2fs_unlock_all(sbi);
err = f2fs_sync_inode_meta(sbi);
if (err)
- goto out;
+ return err;
cond_resched();
goto retry_flush_quotas;
}
@@ -1224,7 +1232,7 @@ retry_flush_nodes:
if (err) {
up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
- goto out;
+ return err;
}
cond_resched();
goto retry_flush_nodes;
@@ -1236,8 +1244,6 @@ retry_flush_nodes:
*/
__prepare_cp_block(sbi);
up_write(&sbi->node_change);
-out:
- blk_finish_plug(&plug);
return err;
}
@@ -1252,14 +1258,19 @@ void f2fs_wait_on_all_pages(struct f2fs_sb_info *sbi, int type)
DEFINE_WAIT(wait);
for (;;) {
- prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
-
if (!get_pages(sbi, type))
break;
if (unlikely(f2fs_cp_error(sbi)))
break;
+ if (type == F2FS_DIRTY_META)
+ f2fs_sync_meta_pages(sbi, META, LONG_MAX,
+ FS_CP_META_IO);
+ else if (type == F2FS_WB_CP_DATA)
+ f2fs_submit_merged_write(sbi, DATA);
+
+ prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
io_schedule_timeout(DEFAULT_IO_TIMEOUT);
}
finish_wait(&sbi->cp_wait, &wait);
@@ -1406,7 +1417,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
}
- /* 2 cp + n data seg summary + orphan inode blocks */
+ /* 2 cp + n data seg summary + orphan inode blocks */
data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false);
spin_lock_irqsave(&sbi->cp_lock, flags);
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
@@ -1506,9 +1517,10 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/*
* invalidate intermediate page cache borrowed from meta inode which are
- * used for migration of encrypted or verity inode's blocks.
+ * used for migration of encrypted, verity or compressed inode's blocks.
*/
- if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi))
+ if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) ||
+ f2fs_sb_has_compression(sbi))
invalidate_mapping_pages(META_MAPPING(sbi),
MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
@@ -1553,7 +1565,8 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
return 0;
f2fs_warn(sbi, "Start checkpoint disabled!");
}
- mutex_lock(&sbi->cp_mutex);
+ if (cpc->reason != CP_RESIZE)
+ mutex_lock(&sbi->cp_mutex);
if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
@@ -1622,7 +1635,8 @@ stop:
f2fs_update_time(sbi, CP_TIME);
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
out:
- mutex_unlock(&sbi->cp_mutex);
+ if (cpc->reason != CP_RESIZE)
+ mutex_unlock(&sbi->cp_mutex);
return err;
}
diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
index df7b2d15eacd..1dfb126a0cb2 100644
--- a/fs/f2fs/compress.c
+++ b/fs/f2fs/compress.c
@@ -49,6 +49,13 @@ bool f2fs_is_compressed_page(struct page *page)
return false;
if (IS_ATOMIC_WRITTEN_PAGE(page) || IS_DUMMY_WRITTEN_PAGE(page))
return false;
+ /*
+ * page->private may be set with pid.
+ * pid_max is enough to check if it is traced.
+ */
+ if (IS_IO_TRACED_PAGE(page))
+ return false;
+
f2fs_bug_on(F2FS_M_SB(page->mapping),
*((u32 *)page_private(page)) != F2FS_COMPRESSED_PAGE_MAGIC);
return true;
@@ -65,15 +72,6 @@ static void f2fs_set_compressed_page(struct page *page,
page->mapping = inode->i_mapping;
}
-static void f2fs_put_compressed_page(struct page *page)
-{
- set_page_private(page, (unsigned long)NULL);
- ClearPagePrivate(page);
- page->mapping = NULL;
- unlock_page(page);
- put_page(page);
-}
-
static void f2fs_drop_rpages(struct compress_ctx *cc, int len, bool unlock)
{
int i;
@@ -98,8 +96,7 @@ static void f2fs_unlock_rpages(struct compress_ctx *cc, int len)
f2fs_drop_rpages(cc, len, true);
}
-static void f2fs_put_rpages_mapping(struct compress_ctx *cc,
- struct address_space *mapping,
+static void f2fs_put_rpages_mapping(struct address_space *mapping,
pgoff_t start, int len)
{
int i;
@@ -236,7 +233,12 @@ static int lz4_init_compress_ctx(struct compress_ctx *cc)
if (!cc->private)
return -ENOMEM;
- cc->clen = LZ4_compressBound(PAGE_SIZE << cc->log_cluster_size);
+ /*
+ * we do not change cc->clen to LZ4_compressBound(inputsize) to
+ * adapt worst compress case, because lz4 compressor can handle
+ * output budget properly.
+ */
+ cc->clen = cc->rlen - PAGE_SIZE - COMPRESS_HEADER_SIZE;
return 0;
}
@@ -252,11 +254,9 @@ static int lz4_compress_pages(struct compress_ctx *cc)
len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen,
cc->clen, cc->private);
- if (!len) {
- printk_ratelimited("%sF2FS-fs (%s): lz4 compress failed\n",
- KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id);
- return -EIO;
- }
+ if (!len)
+ return -EAGAIN;
+
cc->clen = len;
return 0;
}
@@ -366,6 +366,13 @@ static int zstd_compress_pages(struct compress_ctx *cc)
return -EIO;
}
+ /*
+ * there is compressed data remained in intermediate buffer due to
+ * no more space in cbuf.cdata
+ */
+ if (ret)
+ return -EAGAIN;
+
cc->clen = outbuf.pos;
return 0;
}
@@ -451,6 +458,31 @@ static const struct f2fs_compress_ops f2fs_zstd_ops = {
};
#endif
+#ifdef CONFIG_F2FS_FS_LZO
+#ifdef CONFIG_F2FS_FS_LZORLE
+static int lzorle_compress_pages(struct compress_ctx *cc)
+{
+ int ret;
+
+ ret = lzorle1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata,
+ &cc->clen, cc->private);
+ if (ret != LZO_E_OK) {
+ printk_ratelimited("%sF2FS-fs (%s): lzo-rle compress failed, ret:%d\n",
+ KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, ret);
+ return -EIO;
+ }
+ return 0;
+}
+
+static const struct f2fs_compress_ops f2fs_lzorle_ops = {
+ .init_compress_ctx = lzo_init_compress_ctx,
+ .destroy_compress_ctx = lzo_destroy_compress_ctx,
+ .compress_pages = lzorle_compress_pages,
+ .decompress_pages = lzo_decompress_pages,
+};
+#endif
+#endif
+
static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = {
#ifdef CONFIG_F2FS_FS_LZO
&f2fs_lzo_ops,
@@ -467,6 +499,11 @@ static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = {
#else
NULL,
#endif
+#if defined(CONFIG_F2FS_FS_LZO) && defined(CONFIG_F2FS_FS_LZORLE)
+ &f2fs_lzorle_ops,
+#else
+ NULL,
+#endif
};
bool f2fs_is_compress_backend_ready(struct inode *inode)
@@ -476,17 +513,47 @@ bool f2fs_is_compress_backend_ready(struct inode *inode)
return f2fs_cops[F2FS_I(inode)->i_compress_algorithm];
}
-static struct page *f2fs_grab_page(void)
+static mempool_t *compress_page_pool;
+static int num_compress_pages = 512;
+module_param(num_compress_pages, uint, 0444);
+MODULE_PARM_DESC(num_compress_pages,
+ "Number of intermediate compress pages to preallocate");
+
+int f2fs_init_compress_mempool(void)
+{
+ compress_page_pool = mempool_create_page_pool(num_compress_pages, 0);
+ if (!compress_page_pool)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void f2fs_destroy_compress_mempool(void)
+{
+ mempool_destroy(compress_page_pool);
+}
+
+static struct page *f2fs_compress_alloc_page(void)
{
struct page *page;
- page = alloc_page(GFP_NOFS);
- if (!page)
- return NULL;
+ page = mempool_alloc(compress_page_pool, GFP_NOFS);
lock_page(page);
+
return page;
}
+static void f2fs_compress_free_page(struct page *page)
+{
+ if (!page)
+ return;
+ set_page_private(page, (unsigned long)NULL);
+ ClearPagePrivate(page);
+ page->mapping = NULL;
+ unlock_page(page);
+ mempool_free(page, compress_page_pool);
+}
+
static int f2fs_compress_pages(struct compress_ctx *cc)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode);
@@ -516,7 +583,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
}
for (i = 0; i < cc->nr_cpages; i++) {
- cc->cpages[i] = f2fs_grab_page();
+ cc->cpages[i] = f2fs_compress_alloc_page();
if (!cc->cpages[i]) {
ret = -ENOMEM;
goto out_free_cpages;
@@ -561,7 +628,7 @@ static int f2fs_compress_pages(struct compress_ctx *cc)
vunmap(cc->rbuf);
for (i = nr_cpages; i < cc->nr_cpages; i++) {
- f2fs_put_compressed_page(cc->cpages[i]);
+ f2fs_compress_free_page(cc->cpages[i]);
cc->cpages[i] = NULL;
}
@@ -581,7 +648,7 @@ out_vunmap_rbuf:
out_free_cpages:
for (i = 0; i < cc->nr_cpages; i++) {
if (cc->cpages[i])
- f2fs_put_compressed_page(cc->cpages[i]);
+ f2fs_compress_free_page(cc->cpages[i]);
}
kfree(cc->cpages);
cc->cpages = NULL;
@@ -603,6 +670,7 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
const struct f2fs_compress_ops *cops =
f2fs_cops[fi->i_compress_algorithm];
int ret;
+ int i;
dec_page_count(sbi, F2FS_RD_DATA);
@@ -621,6 +689,26 @@ void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity)
goto out_free_dic;
}
+ dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
+ dic->cluster_size, GFP_NOFS);
+ if (!dic->tpages) {
+ ret = -ENOMEM;
+ goto out_free_dic;
+ }
+
+ for (i = 0; i < dic->cluster_size; i++) {
+ if (dic->rpages[i]) {
+ dic->tpages[i] = dic->rpages[i];
+ continue;
+ }
+
+ dic->tpages[i] = f2fs_compress_alloc_page();
+ if (!dic->tpages[i]) {
+ ret = -ENOMEM;
+ goto out_free_dic;
+ }
+ }
+
if (cops->init_decompress_ctx) {
ret = cops->init_decompress_ctx(dic);
if (ret)
@@ -761,7 +849,7 @@ static int f2fs_compressed_blocks(struct compress_ctx *cc)
}
/* return # of valid blocks in compressed cluster */
-static int f2fs_cluster_blocks(struct compress_ctx *cc, bool compr)
+static int f2fs_cluster_blocks(struct compress_ctx *cc)
{
return __f2fs_cluster_blocks(cc, false);
}
@@ -775,7 +863,7 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
.cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size,
};
- return f2fs_cluster_blocks(&cc, false);
+ return f2fs_cluster_blocks(&cc);
}
static bool cluster_may_compress(struct compress_ctx *cc)
@@ -788,6 +876,8 @@ static bool cluster_may_compress(struct compress_ctx *cc)
return false;
if (!f2fs_cluster_is_full(cc))
return false;
+ if (unlikely(f2fs_cp_error(F2FS_I_SB(cc->inode))))
+ return false;
return __cluster_may_compress(cc);
}
@@ -824,7 +914,7 @@ static int prepare_compress_overwrite(struct compress_ctx *cc,
bool prealloc;
retry:
- ret = f2fs_cluster_blocks(cc, false);
+ ret = f2fs_cluster_blocks(cc);
if (ret <= 0)
return ret;
@@ -879,7 +969,7 @@ retry:
if (!PageUptodate(page)) {
f2fs_unlock_rpages(cc, i + 1);
- f2fs_put_rpages_mapping(cc, mapping, start_idx,
+ f2fs_put_rpages_mapping(mapping, start_idx,
cc->cluster_size);
f2fs_destroy_compress_ctx(cc);
goto retry;
@@ -887,7 +977,7 @@ retry:
}
if (prealloc) {
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
@@ -902,7 +992,7 @@ retry:
break;
}
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
}
if (likely(!ret)) {
@@ -914,7 +1004,7 @@ retry:
unlock_pages:
f2fs_unlock_rpages(cc, i);
release_pages:
- f2fs_put_rpages_mapping(cc, mapping, start_idx, i);
+ f2fs_put_rpages_mapping(mapping, start_idx, i);
f2fs_destroy_compress_ctx(cc);
return ret;
}
@@ -954,6 +1044,55 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
return first_index;
}
+int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock)
+{
+ void *fsdata = NULL;
+ struct page *pagep;
+ int log_cluster_size = F2FS_I(inode)->i_log_cluster_size;
+ pgoff_t start_idx = from >> (PAGE_SHIFT + log_cluster_size) <<
+ log_cluster_size;
+ int err;
+
+ err = f2fs_is_compressed_cluster(inode, start_idx);
+ if (err < 0)
+ return err;
+
+ /* truncate normal cluster */
+ if (!err)
+ return f2fs_do_truncate_blocks(inode, from, lock);
+
+ /* truncate compressed cluster */
+ err = f2fs_prepare_compress_overwrite(inode, &pagep,
+ start_idx, &fsdata);
+
+ /* should not be a normal cluster */
+ f2fs_bug_on(F2FS_I_SB(inode), err == 0);
+
+ if (err <= 0)
+ return err;
+
+ if (err > 0) {
+ struct page **rpages = fsdata;
+ int cluster_size = F2FS_I(inode)->i_cluster_size;
+ int i;
+
+ for (i = cluster_size - 1; i >= 0; i--) {
+ loff_t start = rpages[i]->index << PAGE_SHIFT;
+
+ if (from <= start) {
+ zero_user_segment(rpages[i], 0, PAGE_SIZE);
+ } else {
+ zero_user_segment(rpages[i], from - start,
+ PAGE_SIZE);
+ break;
+ }
+ }
+
+ f2fs_compress_write_end(inode, fsdata, start_idx, true);
+ }
+ return 0;
+}
+
static int f2fs_write_compressed_pages(struct compress_ctx *cc,
int *submitted,
struct writeback_control *wbc,
@@ -975,7 +1114,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
.submitted = false,
.io_type = io_type,
.io_wbc = wbc,
- .encrypted = f2fs_encrypted_file(cc->inode),
+ .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode),
};
struct dnode_of_data dn;
struct node_info ni;
@@ -985,8 +1124,16 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
loff_t psize;
int i, err;
- if (!f2fs_trylock_op(sbi))
+ if (IS_NOQUOTA(inode)) {
+ /*
+ * We need to wait for node_write to avoid block allocation during
+ * checkpoint. This can only happen to quota writes which can cause
+ * the below discard race condition.
+ */
+ down_read(&sbi->node_write);
+ } else if (!f2fs_trylock_op(sbi)) {
return -EAGAIN;
+ }
set_new_dnode(&dn, cc->inode, NULL, NULL, 0);
@@ -1026,6 +1173,13 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc,
f2fs_set_compressed_page(cc->cpages[i], inode,
cc->rpages[i + 1]->index, cic);
fio.compressed_page = cc->cpages[i];
+
+ fio.old_blkaddr = data_blkaddr(dn.inode, dn.node_page,
+ dn.ofs_in_node + i + 1);
+
+ /* wait for GCed page writeback via META_MAPPING */
+ f2fs_wait_on_block_writeback(inode, fio.old_blkaddr);
+
if (fio.encrypted) {
fio.page = cc->rpages[i + 1];
err = f2fs_encrypt_one_page(&fio);
@@ -1092,7 +1246,10 @@ unlock_continue:
set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
f2fs_put_dnode(&dn);
- f2fs_unlock_op(sbi);
+ if (IS_NOQUOTA(inode))
+ up_read(&sbi->node_write);
+ else
+ f2fs_unlock_op(sbi);
spin_lock(&fi->i_size_lock);
if (fi->last_disk_size < psize)
@@ -1118,7 +1275,10 @@ out_put_cic:
out_put_dnode:
f2fs_put_dnode(&dn);
out_unlock_op:
- f2fs_unlock_op(sbi);
+ if (IS_NOQUOTA(inode))
+ up_read(&sbi->node_write);
+ else
+ f2fs_unlock_op(sbi);
return -EAGAIN;
}
@@ -1132,7 +1292,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page)
if (unlikely(bio->bi_status))
mapping_set_error(cic->inode->i_mapping, -EIO);
- f2fs_put_compressed_page(page);
+ f2fs_compress_free_page(page);
dec_page_count(sbi, F2FS_WB_DATA);
@@ -1197,6 +1357,12 @@ retry_write:
congestion_wait(BLK_RW_ASYNC,
DEFAULT_IO_TIMEOUT);
lock_page(cc->rpages[i]);
+
+ if (!PageDirty(cc->rpages[i])) {
+ unlock_page(cc->rpages[i]);
+ continue;
+ }
+
clear_page_dirty_for_io(cc->rpages[i]);
goto retry_write;
}
@@ -1240,6 +1406,8 @@ int f2fs_write_multi_pages(struct compress_ctx *cc,
err = f2fs_write_compressed_pages(cc, submitted,
wbc, io_type);
cops->destroy_compress_ctx(cc);
+ kfree(cc->cpages);
+ cc->cpages = NULL;
if (!err)
return 0;
f2fs_bug_on(F2FS_I_SB(cc->inode), err != -EAGAIN);
@@ -1293,7 +1461,7 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
for (i = 0; i < dic->nr_cpages; i++) {
struct page *page;
- page = f2fs_grab_page();
+ page = f2fs_compress_alloc_page();
if (!page)
goto out_free;
@@ -1302,22 +1470,6 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc)
dic->cpages[i] = page;
}
- dic->tpages = f2fs_kzalloc(sbi, sizeof(struct page *) *
- dic->cluster_size, GFP_NOFS);
- if (!dic->tpages)
- goto out_free;
-
- for (i = 0; i < dic->cluster_size; i++) {
- if (cc->rpages[i]) {
- dic->tpages[i] = cc->rpages[i];
- continue;
- }
-
- dic->tpages[i] = f2fs_grab_page();
- if (!dic->tpages[i])
- goto out_free;
- }
-
return dic;
out_free:
@@ -1335,8 +1487,7 @@ void f2fs_free_dic(struct decompress_io_ctx *dic)
continue;
if (!dic->tpages[i])
continue;
- unlock_page(dic->tpages[i]);
- put_page(dic->tpages[i]);
+ f2fs_compress_free_page(dic->tpages[i]);
}
kfree(dic->tpages);
}
@@ -1345,7 +1496,7 @@ void f2fs_free_dic(struct decompress_io_ctx *dic)
for (i = 0; i < dic->nr_cpages; i++) {
if (!dic->cpages[i])
continue;
- f2fs_put_compressed_page(dic->cpages[i]);
+ f2fs_compress_free_page(dic->cpages[i]);
}
kfree(dic->cpages);
}
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index cdf2f626bea7..73683e58a08d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -14,11 +14,13 @@
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
+#include <linux/blk-crypto.h>
#include <linux/swap.h>
#include <linux/prefetch.h>
#include <linux/uio.h>
#include <linux/cleancache.h>
#include <linux/sched/signal.h>
+#include <linux/fiemap.h>
#include "f2fs.h"
#include "node.h"
@@ -85,7 +87,7 @@ static bool __is_cp_guaranteed(struct page *page)
sbi = F2FS_I_SB(inode);
if (inode->i_ino == F2FS_META_INO(sbi) ||
- inode->i_ino == F2FS_NODE_INO(sbi) ||
+ inode->i_ino == F2FS_NODE_INO(sbi) ||
S_ISDIR(inode->i_mode) ||
(S_ISREG(inode->i_mode) &&
(f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) ||
@@ -114,7 +116,8 @@ static enum count_type __read_io_type(struct page *page)
/* postprocessing steps for read bios */
enum bio_post_read_step {
STEP_DECRYPT,
- STEP_DECOMPRESS,
+ STEP_DECOMPRESS_NOWQ, /* handle normal cluster data inplace */
+ STEP_DECOMPRESS, /* handle compressed cluster data in workqueue */
STEP_VERITY,
};
@@ -457,6 +460,33 @@ static struct bio *__bio_alloc(struct f2fs_io_info *fio, int npages)
return bio;
}
+static void f2fs_set_bio_crypt_ctx(struct bio *bio, const struct inode *inode,
+ pgoff_t first_idx,
+ const struct f2fs_io_info *fio,
+ gfp_t gfp_mask)
+{
+ /*
+ * The f2fs garbage collector sets ->encrypted_page when it wants to
+ * read/write raw data without encryption.
+ */
+ if (!fio || !fio->encrypted_page)
+ fscrypt_set_bio_crypt_ctx(bio, inode, first_idx, gfp_mask);
+}
+
+static bool f2fs_crypt_mergeable_bio(struct bio *bio, const struct inode *inode,
+ pgoff_t next_idx,
+ const struct f2fs_io_info *fio)
+{
+ /*
+ * The f2fs garbage collector sets ->encrypted_page when it wants to
+ * read/write raw data without encryption.
+ */
+ if (fio && fio->encrypted_page)
+ return !bio_has_crypt_ctx(bio);
+
+ return fscrypt_mergeable_bio(bio, inode, next_idx);
+}
+
static inline void __submit_bio(struct f2fs_sb_info *sbi,
struct bio *bio, enum page_type type)
{
@@ -513,6 +543,34 @@ void f2fs_submit_bio(struct f2fs_sb_info *sbi,
__submit_bio(sbi, bio, type);
}
+static void __attach_io_flag(struct f2fs_io_info *fio)
+{
+ struct f2fs_sb_info *sbi = fio->sbi;
+ unsigned int temp_mask = (1 << NR_TEMP_TYPE) - 1;
+ unsigned int io_flag, fua_flag, meta_flag;
+
+ if (fio->type == DATA)
+ io_flag = sbi->data_io_flag;
+ else if (fio->type == NODE)
+ io_flag = sbi->node_io_flag;
+ else
+ return;
+
+ fua_flag = io_flag & temp_mask;
+ meta_flag = (io_flag >> NR_TEMP_TYPE) & temp_mask;
+
+ /*
+ * data/node io flag bits per temp:
+ * REQ_META | REQ_FUA |
+ * 5 | 4 | 3 | 2 | 1 | 0 |
+ * Cold | Warm | Hot | Cold | Warm | Hot |
+ */
+ if ((1 << fio->temp) & meta_flag)
+ fio->op_flags |= REQ_META;
+ if ((1 << fio->temp) & fua_flag)
+ fio->op_flags |= REQ_FUA;
+}
+
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
@@ -520,6 +578,7 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
if (!io->bio)
return;
+ __attach_io_flag(fio);
bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
if (is_read_io(fio->op))
@@ -653,6 +712,9 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
/* Allocate a new bio */
bio = __bio_alloc(fio, 1);
+ f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
+ fio->page->index, fio, GFP_NOIO);
+
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
return -EFAULT;
@@ -661,6 +723,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
if (fio->io_wbc && !is_read_io(fio->op))
wbc_account_cgroup_owner(fio->io_wbc, page, PAGE_SIZE);
+ __attach_io_flag(fio);
bio_set_op_attrs(bio, fio->op, fio->op_flags);
inc_page_count(fio->sbi, is_read_io(fio->op) ?
@@ -731,9 +794,10 @@ static void del_bio_entry(struct bio_entry *be)
kmem_cache_free(bio_entry_slab, be);
}
-static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio,
+static int add_ipu_page(struct f2fs_io_info *fio, struct bio **bio,
struct page *page)
{
+ struct f2fs_sb_info *sbi = fio->sbi;
enum temp_type temp;
bool found = false;
int ret = -EAGAIN;
@@ -750,13 +814,19 @@ static int add_ipu_page(struct f2fs_sb_info *sbi, struct bio **bio,
found = true;
- if (bio_add_page(*bio, page, PAGE_SIZE, 0) ==
- PAGE_SIZE) {
+ f2fs_bug_on(sbi, !page_is_mergeable(sbi, *bio,
+ *fio->last_block,
+ fio->new_blkaddr));
+ if (f2fs_crypt_mergeable_bio(*bio,
+ fio->page->mapping->host,
+ fio->page->index, fio) &&
+ bio_add_page(*bio, page, PAGE_SIZE, 0) ==
+ PAGE_SIZE) {
ret = 0;
break;
}
- /* bio is full */
+ /* page can't be merged into bio; submit the bio */
del_bio_entry(be);
__submit_bio(sbi, *bio, DATA);
break;
@@ -847,11 +917,14 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
alloc_new:
if (!bio) {
bio = __bio_alloc(fio, BIO_MAX_PAGES);
+ __attach_io_flag(fio);
+ f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
+ fio->page->index, fio, GFP_NOIO);
bio_set_op_attrs(bio, fio->op, fio->op_flags);
add_bio_entry(fio->sbi, bio, page, fio->temp);
} else {
- if (add_ipu_page(fio->sbi, &bio, page))
+ if (add_ipu_page(fio, &bio, page))
goto alloc_new;
}
@@ -903,8 +976,11 @@ next:
inc_page_count(sbi, WB_DATA_TYPE(bio_page));
- if (io->bio && !io_is_mergeable(sbi, io->bio, io, fio,
- io->last_block_in_bio, fio->new_blkaddr))
+ if (io->bio &&
+ (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio,
+ fio->new_blkaddr) ||
+ !f2fs_crypt_mergeable_bio(io->bio, fio->page->mapping->host,
+ bio_page->index, fio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
@@ -916,6 +992,8 @@ alloc_new:
goto skip;
}
io->bio = __bio_alloc(fio, BIO_MAX_PAGES);
+ f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
+ bio_page->index, fio, GFP_NOIO);
io->fio = *fio;
}
@@ -960,14 +1038,17 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
for_write);
if (!bio)
return ERR_PTR(-ENOMEM);
+
+ f2fs_set_bio_crypt_ctx(bio, inode, first_idx, NULL, GFP_NOFS);
+
f2fs_target_device(sbi, blkaddr, bio);
bio->bi_end_io = f2fs_read_end_io;
bio_set_op_attrs(bio, REQ_OP_READ, op_flag);
- if (f2fs_encrypted_file(inode))
+ if (fscrypt_inode_uses_fs_layer_crypto(inode))
post_read_steps |= 1 << STEP_DECRYPT;
if (f2fs_compressed_file(inode))
- post_read_steps |= 1 << STEP_DECOMPRESS;
+ post_read_steps |= 1 << STEP_DECOMPRESS_NOWQ;
if (f2fs_need_verity(inode, first_idx))
post_read_steps |= 1 << STEP_VERITY;
@@ -992,12 +1073,13 @@ static void f2fs_release_read_bio(struct bio *bio)
/* This can handle encryption stuffs */
static int f2fs_submit_page_read(struct inode *inode, struct page *page,
- block_t blkaddr, bool for_write)
+ block_t blkaddr, int op_flags, bool for_write)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct bio *bio;
- bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0, page->index, for_write);
+ bio = f2fs_grab_read_bio(inode, blkaddr, 1, op_flags,
+ page->index, for_write);
if (IS_ERR(bio))
return PTR_ERR(bio);
@@ -1010,6 +1092,7 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page,
}
ClearPageError(page);
inc_page_count(sbi, F2FS_RD_DATA);
+ f2fs_update_iostat(sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
__submit_bio(sbi, bio, DATA);
return 0;
}
@@ -1111,7 +1194,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
{
- struct extent_info ei = {0,0,0};
+ struct extent_info ei = {0, 0, 0};
struct inode *inode = dn->inode;
if (f2fs_lookup_extent_cache(inode, index, &ei)) {
@@ -1183,7 +1266,8 @@ got_it:
return page;
}
- err = f2fs_submit_page_read(inode, page, dn.data_blkaddr, for_write);
+ err = f2fs_submit_page_read(inode, page, dn.data_blkaddr,
+ op_flags, for_write);
if (err)
goto put_err;
return page;
@@ -1332,7 +1416,7 @@ alloc:
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
old_blkaddr = dn->data_blkaddr;
f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr,
- &sum, seg_type, NULL, false);
+ &sum, seg_type, NULL);
if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
invalidate_mapping_pages(META_MAPPING(sbi),
old_blkaddr, old_blkaddr);
@@ -1392,7 +1476,7 @@ map_blocks:
return err;
}
-void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
+void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
{
if (flag == F2FS_GET_BLOCK_PRE_AIO) {
if (lock)
@@ -1457,7 +1541,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
next_dnode:
if (map->m_may_create)
- __do_map_lock(sbi, flag, true);
+ f2fs_do_map_lock(sbi, flag, true);
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -1606,7 +1690,7 @@ skip:
f2fs_put_dnode(&dn);
if (map->m_may_create) {
- __do_map_lock(sbi, flag, false);
+ f2fs_do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
goto next_dnode;
@@ -1632,7 +1716,7 @@ sync_out:
f2fs_put_dnode(&dn);
unlock_out:
if (map->m_may_create) {
- __do_map_lock(sbi, flag, false);
+ f2fs_do_map_lock(sbi, flag, false);
f2fs_balance_fs(sbi, dn.node_changed);
}
out:
@@ -1779,6 +1863,7 @@ static int f2fs_xattr_fiemap(struct inode *inode,
flags |= FIEMAP_EXTENT_LAST;
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+ trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
if (err || err == 1)
return err;
}
@@ -1802,12 +1887,33 @@ static int f2fs_xattr_fiemap(struct inode *inode,
flags = FIEMAP_EXTENT_LAST;
}
- if (phys)
+ if (phys) {
err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags);
+ trace_f2fs_fiemap(inode, 0, phys, len, flags, err);
+ }
return (err < 0 ? err : 0);
}
+static loff_t max_inode_blocks(struct inode *inode)
+{
+ loff_t result = ADDRS_PER_INODE(inode);
+ loff_t leaf_count = ADDRS_PER_BLOCK(inode);
+
+ /* two direct node blocks */
+ result += (leaf_count * 2);
+
+ /* two indirect node blocks */
+ leaf_count *= NIDS_PER_BLOCK;
+ result += (leaf_count * 2);
+
+ /* one double indirect node block */
+ leaf_count *= NIDS_PER_BLOCK;
+ result += leaf_count;
+
+ return result;
+}
+
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
@@ -1817,6 +1923,8 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 logical = 0, phys = 0, size = 0;
u32 flags = 0;
int ret = 0;
+ bool compr_cluster = false;
+ unsigned int cluster_size = F2FS_I(inode)->i_cluster_size;
if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
ret = f2fs_precache_extents(inode);
@@ -1824,7 +1932,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return ret;
}
- ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR);
+ ret = fiemap_prep(inode, fieinfo, start, &len, FIEMAP_FLAG_XATTR);
if (ret)
return ret;
@@ -1851,6 +1959,9 @@ next:
memset(&map_bh, 0, sizeof(struct buffer_head));
map_bh.b_size = len;
+ if (compr_cluster)
+ map_bh.b_size = blk_to_logical(inode, cluster_size - 1);
+
ret = get_data_block(inode, start_blk, &map_bh, 0,
F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
if (ret)
@@ -1861,7 +1972,7 @@ next:
start_blk = next_pgofs;
if (blk_to_logical(inode, start_blk) < blk_to_logical(inode,
- F2FS_I_SB(inode)->max_file_blocks))
+ max_inode_blocks(inode)))
goto prep_next;
flags |= FIEMAP_EXTENT_LAST;
@@ -1873,11 +1984,39 @@ next:
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
+ trace_f2fs_fiemap(inode, logical, phys, size, flags, ret);
+ if (ret)
+ goto out;
+ size = 0;
}
- if (start_blk > last_blk || ret)
+ if (start_blk > last_blk)
goto out;
+ if (compr_cluster) {
+ compr_cluster = false;
+
+
+ logical = blk_to_logical(inode, start_blk - 1);
+ phys = blk_to_logical(inode, map_bh.b_blocknr);
+ size = blk_to_logical(inode, cluster_size);
+
+ flags |= FIEMAP_EXTENT_ENCODED;
+
+ start_blk += cluster_size - 1;
+
+ if (start_blk > last_blk)
+ goto out;
+
+ goto prep_next;
+ }
+
+ if (map_bh.b_blocknr == COMPRESS_ADDR) {
+ compr_cluster = true;
+ start_blk++;
+ goto prep_next;
+ }
+
logical = blk_to_logical(inode, start_blk);
phys = blk_to_logical(inode, map_bh.b_blocknr);
size = map_bh.b_size;
@@ -1988,8 +2127,9 @@ zero_out:
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
- if (bio && !page_is_mergeable(F2FS_I_SB(inode), bio,
- *last_block_in_bio, block_nr)) {
+ if (bio && (!page_is_mergeable(F2FS_I_SB(inode), bio,
+ *last_block_in_bio, block_nr) ||
+ !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
submit_and_realloc:
__submit_bio(F2FS_I_SB(inode), bio, DATA);
bio = NULL;
@@ -2015,6 +2155,7 @@ submit_and_realloc:
goto submit_and_realloc;
inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA);
+ f2fs_update_iostat(F2FS_I_SB(inode), FS_DATA_READ_IO, F2FS_BLKSIZE);
ClearPageError(page);
*last_block_in_bio = block_nr;
goto out;
@@ -2078,9 +2219,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
if (ret)
goto out;
- /* cluster was overwritten as normal cluster */
- if (dn.data_blkaddr != COMPRESS_ADDR)
- goto out;
+ f2fs_bug_on(sbi, dn.data_blkaddr != COMPRESS_ADDR);
for (i = 1; i < cc->cluster_size; i++) {
block_t blkaddr;
@@ -2113,12 +2252,14 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
for (i = 0; i < dic->nr_cpages; i++) {
struct page *page = dic->cpages[i];
block_t blkaddr;
+ struct bio_post_read_ctx *ctx;
blkaddr = data_blkaddr(dn.inode, dn.node_page,
dn.ofs_in_node + i + 1);
- if (bio && !page_is_mergeable(sbi, bio,
- *last_block_in_bio, blkaddr)) {
+ if (bio && (!page_is_mergeable(sbi, bio,
+ *last_block_in_bio, blkaddr) ||
+ !f2fs_crypt_mergeable_bio(bio, inode, page->index, NULL))) {
submit_and_realloc:
__submit_bio(sbi, bio, DATA);
bio = NULL;
@@ -2130,16 +2271,16 @@ submit_and_realloc:
page->index, for_write);
if (IS_ERR(bio)) {
ret = PTR_ERR(bio);
- bio = NULL;
dic->failed = true;
if (refcount_sub_and_test(dic->nr_cpages - i,
- &dic->ref))
+ &dic->ref)) {
f2fs_decompress_end_io(dic->rpages,
cc->cluster_size, true,
false);
- f2fs_free_dic(dic);
+ f2fs_free_dic(dic);
+ }
f2fs_put_dnode(&dn);
- *bio_ret = bio;
+ *bio_ret = NULL;
return ret;
}
}
@@ -2149,7 +2290,14 @@ submit_and_realloc:
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
+ /* tag STEP_DECOMPRESS to handle IO in wq */
+ ctx = bio->bi_private;
+ if (!(ctx->enabled_steps & (1 << STEP_DECOMPRESS)))
+ ctx->enabled_steps |= 1 << STEP_DECOMPRESS;
+
inc_page_count(sbi, F2FS_RD_DATA);
+ f2fs_update_iostat(sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, FS_CDATA_READ_IO, F2FS_BLKSIZE);
ClearPageError(page);
*last_block_in_bio = blkaddr;
}
@@ -2177,13 +2325,11 @@ out:
* use ->readpage() or do the necessary surgery to decouple ->readpages()
* from read-ahead.
*/
-int f2fs_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead)
+static int f2fs_mpage_readpages(struct inode *inode,
+ struct readahead_control *rac, struct page *page)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
- struct inode *inode = mapping->host;
struct f2fs_map_blocks map;
#ifdef CONFIG_F2FS_FS_COMPRESSION
struct compress_ctx cc = {
@@ -2197,8 +2343,10 @@ int f2fs_mpage_readpages(struct address_space *mapping,
.nr_cpages = 0,
};
#endif
+ unsigned nr_pages = rac ? readahead_count(rac) : 1;
unsigned max_nr_pages = nr_pages;
int ret = 0;
+ bool drop_ra = false;
map.m_pblk = 0;
map.m_lblk = 0;
@@ -2209,16 +2357,26 @@ int f2fs_mpage_readpages(struct address_space *mapping,
map.m_seg_type = NO_CHECK_TYPE;
map.m_may_create = false;
- for (; nr_pages; nr_pages--) {
- if (pages) {
- page = list_last_entry(pages, struct page, lru);
+ /*
+ * Two readahead threads for same address range can cause race condition
+ * which fragments sequential read IOs. So let's avoid each other.
+ */
+ if (rac && readahead_count(rac)) {
+ if (READ_ONCE(F2FS_I(inode)->ra_offset) == readahead_index(rac))
+ drop_ra = true;
+ else
+ WRITE_ONCE(F2FS_I(inode)->ra_offset,
+ readahead_index(rac));
+ }
+ for (; nr_pages; nr_pages--) {
+ if (rac) {
+ page = readahead_page(rac);
prefetchw(&page->flags);
- list_del(&page->lru);
- if (add_to_page_cache_lru(page, mapping,
- page_index(page),
- readahead_gfp_mask(mapping)))
- goto next_page;
+ if (drop_ra) {
+ f2fs_put_page(page, 1);
+ continue;
+ }
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -2228,7 +2386,7 @@ int f2fs_mpage_readpages(struct address_space *mapping,
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
- is_readahead, false);
+ rac != NULL, false);
f2fs_destroy_compress_ctx(&cc);
if (ret)
goto set_error_page;
@@ -2251,7 +2409,7 @@ read_single_page:
#endif
ret = f2fs_read_single_page(inode, page, max_nr_pages, &map,
- &bio, &last_block_in_bio, is_readahead);
+ &bio, &last_block_in_bio, rac);
if (ret) {
#ifdef CONFIG_F2FS_FS_COMPRESSION
set_error_page:
@@ -2260,8 +2418,10 @@ set_error_page:
zero_user_segment(page, 0, PAGE_SIZE);
unlock_page(page);
}
+#ifdef CONFIG_F2FS_FS_COMPRESSION
next_page:
- if (pages)
+#endif
+ if (rac)
put_page(page);
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -2271,16 +2431,18 @@ next_page:
ret = f2fs_read_multi_pages(&cc, &bio,
max_nr_pages,
&last_block_in_bio,
- is_readahead, false);
+ rac != NULL, false);
f2fs_destroy_compress_ctx(&cc);
}
}
#endif
}
- BUG_ON(pages && !list_empty(pages));
if (bio)
__submit_bio(F2FS_I_SB(inode), bio, DATA);
- return pages ? 0 : ret;
+
+ if (rac && readahead_count(rac) && !drop_ra)
+ WRITE_ONCE(F2FS_I(inode)->ra_offset, -1);
+ return ret;
}
static int f2fs_read_data_page(struct file *file, struct page *page)
@@ -2299,28 +2461,24 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
if (ret == -EAGAIN)
- ret = f2fs_mpage_readpages(page_file_mapping(page),
- NULL, page, 1, false);
+ ret = f2fs_mpage_readpages(inode, NULL, page);
return ret;
}
-static int f2fs_read_data_pages(struct file *file,
- struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void f2fs_readahead(struct readahead_control *rac)
{
- struct inode *inode = mapping->host;
- struct page *page = list_last_entry(pages, struct page, lru);
+ struct inode *inode = rac->mapping->host;
- trace_f2fs_readpages(inode, page, nr_pages);
+ trace_f2fs_readpages(inode, readahead_index(rac), readahead_count(rac));
if (!f2fs_is_compress_backend_ready(inode))
- return 0;
+ return;
/* If the file has inline data, skip readpages */
if (f2fs_has_inline_data(inode))
- return 0;
+ return;
- return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true);
+ f2fs_mpage_readpages(inode, rac, NULL);
}
int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
@@ -2337,6 +2495,9 @@ int f2fs_encrypt_one_page(struct f2fs_io_info *fio)
/* wait for GCed page writeback via META_MAPPING */
f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
+ if (fscrypt_inode_uses_inline_crypto(inode))
+ return 0;
+
retry_encrypt:
fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(page,
PAGE_SIZE, 0, gfp_flags);
@@ -2510,7 +2671,7 @@ got_it:
f2fs_unlock_op(fio->sbi);
err = f2fs_inplace_write_data(fio);
if (err) {
- if (f2fs_encrypted_file(inode))
+ if (fscrypt_inode_uses_fs_layer_crypto(inode))
fscrypt_finalize_bounce_page(&fio->encrypted_page);
if (PageWriteback(page))
end_page_writeback(page);
@@ -2633,10 +2794,22 @@ write:
f2fs_available_free_memory(sbi, BASE_CHECK))))
goto redirty_out;
- /* Dentry blocks are controlled by checkpoint */
- if (S_ISDIR(inode->i_mode)) {
+ /* Dentry/quota blocks are controlled by checkpoint */
+ if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) {
+ /*
+ * We need to wait for node_write to avoid block allocation during
+ * checkpoint. This can only happen to quota writes which can cause
+ * the below discard race condition.
+ */
+ if (IS_NOQUOTA(inode))
+ down_read(&sbi->node_write);
+
fio.need_lock = LOCK_DONE;
err = f2fs_do_write_data_page(&fio);
+
+ if (IS_NOQUOTA(inode))
+ up_read(&sbi->node_write);
+
goto done;
}
@@ -2772,11 +2945,9 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
};
#endif
int nr_pages;
- pgoff_t uninitialized_var(writeback_index);
pgoff_t index;
pgoff_t end; /* Inclusive */
pgoff_t done_index;
- int cycled;
int range_whole = 0;
xa_mark_t tag;
int nwritten = 0;
@@ -2792,19 +2963,13 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
clear_inode_flag(mapping->host, FI_HOT_DATA);
if (wbc->range_cyclic) {
- writeback_index = mapping->writeback_index; /* prev offset */
- index = writeback_index;
- if (index == 0)
- cycled = 1;
- else
- cycled = 0;
+ index = mapping->writeback_index; /* prev offset */
end = -1;
} else {
index = wbc->range_start >> PAGE_SHIFT;
end = wbc->range_end >> PAGE_SHIFT;
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
range_whole = 1;
- cycled = 1; /* ignore range_cyclic tests */
}
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
@@ -2969,12 +3134,13 @@ next:
}
}
#endif
- if ((!cycled && !done) || retry) {
- cycled = 1;
+ if (retry) {
index = 0;
- end = writeback_index - 1;
+ end = -1;
goto retry;
}
+ if (wbc->range_cyclic && !done)
+ done_index = 0;
if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
mapping->writeback_index = done_index;
@@ -3138,7 +3304,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
if (f2fs_has_inline_data(inode) ||
(pos & PAGE_MASK) >= i_size_read(inode)) {
- __do_map_lock(sbi, flag, true);
+ f2fs_do_map_lock(sbi, flag, true);
locked = true;
}
@@ -3175,7 +3341,7 @@ restart:
err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
if (err || dn.data_blkaddr == NULL_ADDR) {
f2fs_put_dnode(&dn);
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
true);
WARN_ON(flag != F2FS_GET_BLOCK_PRE_AIO);
locked = true;
@@ -3191,7 +3357,7 @@ out:
f2fs_put_dnode(&dn);
unlock_out:
if (locked)
- __do_map_lock(sbi, flag, false);
+ f2fs_do_map_lock(sbi, flag, false);
return err;
}
@@ -3303,7 +3469,7 @@ repeat:
err = -EFSCORRUPTED;
goto fail;
}
- err = f2fs_submit_page_read(inode, page, blkaddr, true);
+ err = f2fs_submit_page_read(inode, page, blkaddr, 0, true);
if (err)
goto fail;
@@ -3353,6 +3519,10 @@ static int f2fs_write_end(struct file *file,
if (f2fs_compressed_file(inode) && fsdata) {
f2fs_compress_write_end(inode, fsdata, page->index, copied);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+
+ if (pos + copied > i_size_read(inode) &&
+ !f2fs_verity_in_progress(inode))
+ f2fs_i_size_write(inode, pos + copied);
return copied;
}
#endif
@@ -3380,6 +3550,9 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
unsigned long align = offset | iov_iter_alignment(iter);
struct block_device *bdev = inode->i_sb->s_bdev;
+ if (iov_iter_rw(iter) == READ && offset >= i_size_read(inode))
+ return 1;
+
if (align & blocksize_mask) {
if (bdev)
blkbits = blksize_bits(bdev_logical_block_size(bdev));
@@ -3503,6 +3676,9 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
} else if (err < 0) {
f2fs_write_failed(mapping, offset + count);
}
+ } else {
+ if (err > 0)
+ f2fs_update_iostat(sbi, APP_DIRECT_READ_IO, err);
}
out:
@@ -3586,18 +3762,59 @@ static int f2fs_set_data_page_dirty(struct page *page)
return 0;
}
+
+static sector_t f2fs_bmap_compress(struct inode *inode, sector_t block)
+{
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ struct dnode_of_data dn;
+ sector_t start_idx, blknr = 0;
+ int ret;
+
+ start_idx = round_down(block, F2FS_I(inode)->i_cluster_size);
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE);
+ if (ret)
+ return 0;
+
+ if (dn.data_blkaddr != COMPRESS_ADDR) {
+ dn.ofs_in_node += block - start_idx;
+ blknr = f2fs_data_blkaddr(&dn);
+ if (!__is_valid_data_blkaddr(blknr))
+ blknr = 0;
+ }
+
+ f2fs_put_dnode(&dn);
+ return blknr;
+#else
+ return 0;
+#endif
+}
+
+
static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
struct inode *inode = mapping->host;
+ struct buffer_head tmp = {
+ .b_size = i_blocksize(inode),
+ };
+ sector_t blknr = 0;
if (f2fs_has_inline_data(inode))
- return 0;
+ goto out;
/* make sure allocating whole blocks */
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
filemap_write_and_wait(mapping);
- return generic_block_bmap(mapping, block, get_data_block_bmap);
+ if (f2fs_compressed_file(inode))
+ blknr = f2fs_bmap_compress(inode, block);
+
+ if (!get_data_block_bmap(inode, block, &tmp, 0))
+ blknr = tmp.b_blocknr;
+out:
+ trace_f2fs_bmap(inode, block, blknr);
+ return blknr;
}
#ifdef CONFIG_MIGRATION
@@ -3805,7 +4022,7 @@ static void f2fs_swap_deactivate(struct file *file)
const struct address_space_operations f2fs_dblock_aops = {
.readpage = f2fs_read_data_page,
- .readpages = f2fs_read_data_pages,
+ .readahead = f2fs_readahead,
.writepage = f2fs_write_data_page,
.writepages = f2fs_write_data_pages,
.write_begin = f2fs_write_begin,
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 0dbcb0f9c019..4276c0f79beb 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -174,6 +174,26 @@ static void update_general_status(struct f2fs_sb_info *sbi)
for (i = META_CP; i < META_MAX; i++)
si->meta_count[i] = atomic_read(&sbi->meta_count[i]);
+ for (i = 0; i < NO_CHECK_TYPE; i++) {
+ si->dirty_seg[i] = 0;
+ si->full_seg[i] = 0;
+ si->valid_blks[i] = 0;
+ }
+
+ for (i = 0; i < MAIN_SEGS(sbi); i++) {
+ int blks = get_seg_entry(sbi, i)->valid_blocks;
+ int type = get_seg_entry(sbi, i)->type;
+
+ if (!blks)
+ continue;
+
+ if (blks == sbi->blocks_per_seg)
+ si->full_seg[type]++;
+ else
+ si->dirty_seg[type]++;
+ si->valid_blks[type] += blks;
+ }
+
for (i = 0; i < 2; i++) {
si->segment_count[i] = sbi->segment_count[i];
si->block_count[i] = sbi->block_count[i];
@@ -329,30 +349,50 @@ static int stat_show(struct seq_file *s, void *v)
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
si->main_area_segs, si->main_area_sections,
si->main_area_zones);
- seq_printf(s, " - COLD data: %d, %d, %d\n",
+ seq_printf(s, " TYPE %8s %8s %8s %10s %10s %10s\n",
+ "segno", "secno", "zoneno", "dirty_seg", "full_seg", "valid_blk");
+ seq_printf(s, " - COLD data: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_COLD_DATA],
si->cursec[CURSEG_COLD_DATA],
- si->curzone[CURSEG_COLD_DATA]);
- seq_printf(s, " - WARM data: %d, %d, %d\n",
+ si->curzone[CURSEG_COLD_DATA],
+ si->dirty_seg[CURSEG_COLD_DATA],
+ si->full_seg[CURSEG_COLD_DATA],
+ si->valid_blks[CURSEG_COLD_DATA]);
+ seq_printf(s, " - WARM data: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_WARM_DATA],
si->cursec[CURSEG_WARM_DATA],
- si->curzone[CURSEG_WARM_DATA]);
- seq_printf(s, " - HOT data: %d, %d, %d\n",
+ si->curzone[CURSEG_WARM_DATA],
+ si->dirty_seg[CURSEG_WARM_DATA],
+ si->full_seg[CURSEG_WARM_DATA],
+ si->valid_blks[CURSEG_WARM_DATA]);
+ seq_printf(s, " - HOT data: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_HOT_DATA],
si->cursec[CURSEG_HOT_DATA],
- si->curzone[CURSEG_HOT_DATA]);
- seq_printf(s, " - Dir dnode: %d, %d, %d\n",
+ si->curzone[CURSEG_HOT_DATA],
+ si->dirty_seg[CURSEG_HOT_DATA],
+ si->full_seg[CURSEG_HOT_DATA],
+ si->valid_blks[CURSEG_HOT_DATA]);
+ seq_printf(s, " - Dir dnode: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_HOT_NODE],
si->cursec[CURSEG_HOT_NODE],
- si->curzone[CURSEG_HOT_NODE]);
- seq_printf(s, " - File dnode: %d, %d, %d\n",
+ si->curzone[CURSEG_HOT_NODE],
+ si->dirty_seg[CURSEG_HOT_NODE],
+ si->full_seg[CURSEG_HOT_NODE],
+ si->valid_blks[CURSEG_HOT_NODE]);
+ seq_printf(s, " - File dnode: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_WARM_NODE],
si->cursec[CURSEG_WARM_NODE],
- si->curzone[CURSEG_WARM_NODE]);
- seq_printf(s, " - Indir nodes: %d, %d, %d\n",
+ si->curzone[CURSEG_WARM_NODE],
+ si->dirty_seg[CURSEG_WARM_NODE],
+ si->full_seg[CURSEG_WARM_NODE],
+ si->valid_blks[CURSEG_WARM_NODE]);
+ seq_printf(s, " - Indir nodes: %8d %8d %8d %10u %10u %10u\n",
si->curseg[CURSEG_COLD_NODE],
si->cursec[CURSEG_COLD_NODE],
- si->curzone[CURSEG_COLD_NODE]);
+ si->curzone[CURSEG_COLD_NODE],
+ si->dirty_seg[CURSEG_COLD_NODE],
+ si->full_seg[CURSEG_COLD_NODE],
+ si->valid_blks[CURSEG_COLD_NODE]);
seq_printf(s, "\n - Valid: %d\n - Dirty: %d\n",
si->main_area_segs - si->dirty_count -
si->prefree_count - si->free_segs,
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 44bfc464df78..069f498af1e3 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -70,6 +70,111 @@ unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de)
return DT_UNKNOWN;
}
+/* If @dir is casefolded, initialize @fname->cf_name from @fname->usr_fname. */
+int f2fs_init_casefolded_name(const struct inode *dir,
+ struct f2fs_filename *fname)
+{
+#ifdef CONFIG_UNICODE
+ struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+
+ if (IS_CASEFOLDED(dir)) {
+ fname->cf_name.name = f2fs_kmalloc(sbi, F2FS_NAME_LEN,
+ GFP_NOFS);
+ if (!fname->cf_name.name)
+ return -ENOMEM;
+ fname->cf_name.len = utf8_casefold(sbi->s_encoding,
+ fname->usr_fname,
+ fname->cf_name.name,
+ F2FS_NAME_LEN);
+ if ((int)fname->cf_name.len <= 0) {
+ kfree(fname->cf_name.name);
+ fname->cf_name.name = NULL;
+ if (f2fs_has_strict_mode(sbi))
+ return -EINVAL;
+ /* fall back to treating name as opaque byte sequence */
+ }
+ }
+#endif
+ return 0;
+}
+
+static int __f2fs_setup_filename(const struct inode *dir,
+ const struct fscrypt_name *crypt_name,
+ struct f2fs_filename *fname)
+{
+ int err;
+
+ memset(fname, 0, sizeof(*fname));
+
+ fname->usr_fname = crypt_name->usr_fname;
+ fname->disk_name = crypt_name->disk_name;
+#ifdef CONFIG_FS_ENCRYPTION
+ fname->crypto_buf = crypt_name->crypto_buf;
+#endif
+ if (crypt_name->is_ciphertext_name) {
+ /* hash was decoded from the no-key name */
+ fname->hash = cpu_to_le32(crypt_name->hash);
+ } else {
+ err = f2fs_init_casefolded_name(dir, fname);
+ if (err) {
+ f2fs_free_filename(fname);
+ return err;
+ }
+ f2fs_hash_filename(dir, fname);
+ }
+ return 0;
+}
+
+/*
+ * Prepare to search for @iname in @dir. This is similar to
+ * fscrypt_setup_filename(), but this also handles computing the casefolded name
+ * and the f2fs dirhash if needed, then packing all the information about this
+ * filename up into a 'struct f2fs_filename'.
+ */
+int f2fs_setup_filename(struct inode *dir, const struct qstr *iname,
+ int lookup, struct f2fs_filename *fname)
+{
+ struct fscrypt_name crypt_name;
+ int err;
+
+ err = fscrypt_setup_filename(dir, iname, lookup, &crypt_name);
+ if (err)
+ return err;
+
+ return __f2fs_setup_filename(dir, &crypt_name, fname);
+}
+
+/*
+ * Prepare to look up @dentry in @dir. This is similar to
+ * fscrypt_prepare_lookup(), but this also handles computing the casefolded name
+ * and the f2fs dirhash if needed, then packing all the information about this
+ * filename up into a 'struct f2fs_filename'.
+ */
+int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
+ struct f2fs_filename *fname)
+{
+ struct fscrypt_name crypt_name;
+ int err;
+
+ err = fscrypt_prepare_lookup(dir, dentry, &crypt_name);
+ if (err)
+ return err;
+
+ return __f2fs_setup_filename(dir, &crypt_name, fname);
+}
+
+void f2fs_free_filename(struct f2fs_filename *fname)
+{
+#ifdef CONFIG_FS_ENCRYPTION
+ kfree(fname->crypto_buf.name);
+ fname->crypto_buf.name = NULL;
+#endif
+#ifdef CONFIG_UNICODE
+ kfree(fname->cf_name.name);
+ fname->cf_name.name = NULL;
+#endif
+}
+
static unsigned long dir_block_index(unsigned int level,
int dir_level, unsigned int idx)
{
@@ -84,8 +189,7 @@ static unsigned long dir_block_index(unsigned int level,
static struct f2fs_dir_entry *find_in_block(struct inode *dir,
struct page *dentry_page,
- struct fscrypt_name *fname,
- f2fs_hash_t namehash,
+ const struct f2fs_filename *fname,
int *max_slots,
struct page **res_page)
{
@@ -96,7 +200,7 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page);
make_dentry_ptr_block(dir, &d, dentry_blk);
- de = f2fs_find_target_dentry(fname, namehash, max_slots, &d);
+ de = f2fs_find_target_dentry(&d, fname, max_slots);
if (de)
*res_page = dentry_page;
@@ -107,112 +211,57 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
/*
* Test whether a case-insensitive directory entry matches the filename
* being searched for.
- *
- * Returns: 0 if the directory entry matches, more than 0 if it
- * doesn't match or less than zero on error.
*/
-int f2fs_ci_compare(const struct inode *parent, const struct qstr *name,
- const struct qstr *entry, bool quick)
+static bool f2fs_match_ci_name(const struct inode *dir, const struct qstr *name,
+ const u8 *de_name, u32 de_name_len)
{
- const struct f2fs_sb_info *sbi = F2FS_SB(parent->i_sb);
+ const struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
const struct unicode_map *um = sbi->s_encoding;
- int ret;
-
- if (quick)
- ret = utf8_strncasecmp_folded(um, name, entry);
- else
- ret = utf8_strncasecmp(um, name, entry);
+ struct qstr entry = QSTR_INIT(de_name, de_name_len);
+ int res;
- if (ret < 0) {
- /* Handle invalid character sequence as either an error
- * or as an opaque byte sequence.
+ res = utf8_strncasecmp_folded(um, name, &entry);
+ if (res < 0) {
+ /*
+ * In strict mode, ignore invalid names. In non-strict mode,
+ * fall back to treating them as opaque byte sequences.
*/
- if (f2fs_has_strict_mode(sbi))
- return -EINVAL;
-
- if (name->len != entry->len)
- return 1;
-
- return !!memcmp(name->name, entry->name, name->len);
+ if (f2fs_has_strict_mode(sbi) || name->len != entry.len)
+ return false;
+ return !memcmp(name->name, entry.name, name->len);
}
-
- return ret;
+ return res == 0;
}
+#endif /* CONFIG_UNICODE */
-static void f2fs_fname_setup_ci_filename(struct inode *dir,
- const struct qstr *iname,
- struct fscrypt_str *cf_name)
+static inline bool f2fs_match_name(const struct inode *dir,
+ const struct f2fs_filename *fname,
+ const u8 *de_name, u32 de_name_len)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
-
- if (!IS_CASEFOLDED(dir)) {
- cf_name->name = NULL;
- return;
- }
+ struct fscrypt_name f;
- cf_name->name = f2fs_kmalloc(sbi, F2FS_NAME_LEN, GFP_NOFS);
- if (!cf_name->name)
- return;
-
- cf_name->len = utf8_casefold(sbi->s_encoding,
- iname, cf_name->name,
- F2FS_NAME_LEN);
- if ((int)cf_name->len <= 0) {
- kvfree(cf_name->name);
- cf_name->name = NULL;
- }
-}
-#endif
-
-static inline bool f2fs_match_name(struct f2fs_dentry_ptr *d,
- struct f2fs_dir_entry *de,
- struct fscrypt_name *fname,
- struct fscrypt_str *cf_str,
- unsigned long bit_pos,
- f2fs_hash_t namehash)
-{
#ifdef CONFIG_UNICODE
- struct inode *parent = d->inode;
- struct f2fs_sb_info *sbi = F2FS_I_SB(parent);
- struct qstr entry;
-#endif
-
- if (de->hash_code != namehash)
- return false;
+ if (fname->cf_name.name) {
+ struct qstr cf = FSTR_TO_QSTR(&fname->cf_name);
-#ifdef CONFIG_UNICODE
- entry.name = d->filename[bit_pos];
- entry.len = de->name_len;
-
- if (sbi->s_encoding && IS_CASEFOLDED(parent)) {
- if (cf_str->name) {
- struct qstr cf = {.name = cf_str->name,
- .len = cf_str->len};
- return !f2fs_ci_compare(parent, &cf, &entry, true);
- }
- return !f2fs_ci_compare(parent, fname->usr_fname, &entry,
- false);
+ return f2fs_match_ci_name(dir, &cf, de_name, de_name_len);
}
#endif
- if (fscrypt_match_name(fname, d->filename[bit_pos],
- le16_to_cpu(de->name_len)))
- return true;
- return false;
+ f.usr_fname = fname->usr_fname;
+ f.disk_name = fname->disk_name;
+#ifdef CONFIG_FS_ENCRYPTION
+ f.crypto_buf = fname->crypto_buf;
+#endif
+ return fscrypt_match_name(&f, de_name, de_name_len);
}
-struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
- f2fs_hash_t namehash, int *max_slots,
- struct f2fs_dentry_ptr *d)
+struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
+ const struct f2fs_filename *fname, int *max_slots)
{
struct f2fs_dir_entry *de;
- struct fscrypt_str cf_str = { .name = NULL, .len = 0 };
unsigned long bit_pos = 0;
int max_len = 0;
-#ifdef CONFIG_UNICODE
- f2fs_fname_setup_ci_filename(d->inode, fname->usr_fname, &cf_str);
-#endif
-
if (max_slots)
*max_slots = 0;
while (bit_pos < d->max) {
@@ -229,7 +278,9 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
continue;
}
- if (f2fs_match_name(d, de, fname, &cf_str, bit_pos, namehash))
+ if (de->hash_code == fname->hash &&
+ f2fs_match_name(d->inode, fname, d->filename[bit_pos],
+ le16_to_cpu(de->name_len)))
goto found;
if (max_slots && max_len > *max_slots)
@@ -243,33 +294,27 @@ struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
found:
if (max_slots && max_len > *max_slots)
*max_slots = max_len;
-
-#ifdef CONFIG_UNICODE
- kvfree(cf_str.name);
-#endif
return de;
}
static struct f2fs_dir_entry *find_in_level(struct inode *dir,
unsigned int level,
- struct fscrypt_name *fname,
+ const struct f2fs_filename *fname,
struct page **res_page)
{
- struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
- int s = GET_DENTRY_SLOTS(name.len);
+ int s = GET_DENTRY_SLOTS(fname->disk_name.len);
unsigned int nbucket, nblock;
unsigned int bidx, end_block;
struct page *dentry_page;
struct f2fs_dir_entry *de = NULL;
bool room = false;
int max_slots;
- f2fs_hash_t namehash = f2fs_dentry_hash(dir, &name, fname);
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
- le32_to_cpu(namehash) % nbucket);
+ le32_to_cpu(fname->hash) % nbucket);
end_block = bidx + nblock;
for (; bidx < end_block; bidx++) {
@@ -285,8 +330,8 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
}
}
- de = find_in_block(dir, dentry_page, fname, namehash,
- &max_slots, res_page);
+ de = find_in_block(dir, dentry_page, fname, &max_slots,
+ res_page);
if (de)
break;
@@ -295,8 +340,8 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
f2fs_put_page(dentry_page, 0);
}
- if (!de && room && F2FS_I(dir)->chash != namehash) {
- F2FS_I(dir)->chash = namehash;
+ if (!de && room && F2FS_I(dir)->chash != fname->hash) {
+ F2FS_I(dir)->chash = fname->hash;
F2FS_I(dir)->clevel = level;
}
@@ -304,7 +349,8 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
}
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
- struct fscrypt_name *fname, struct page **res_page)
+ const struct f2fs_filename *fname,
+ struct page **res_page)
{
unsigned long npages = dir_blocks(dir);
struct f2fs_dir_entry *de = NULL;
@@ -353,18 +399,10 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
const struct qstr *child, struct page **res_page)
{
struct f2fs_dir_entry *de = NULL;
- struct fscrypt_name fname;
+ struct f2fs_filename fname;
int err;
-#ifdef CONFIG_UNICODE
- if (f2fs_has_strict_mode(F2FS_I_SB(dir)) && IS_CASEFOLDED(dir) &&
- utf8_validate(F2FS_I_SB(dir)->s_encoding, child)) {
- *res_page = ERR_PTR(-EINVAL);
- return NULL;
- }
-#endif
-
- err = fscrypt_setup_filename(dir, child, 1, &fname);
+ err = f2fs_setup_filename(dir, child, 1, &fname);
if (err) {
if (err == -ENOENT)
*res_page = NULL;
@@ -375,7 +413,7 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
de = __f2fs_find_entry(dir, &fname, res_page);
- fscrypt_free_filename(&fname);
+ f2fs_free_filename(&fname);
return de;
}
@@ -416,7 +454,8 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
f2fs_put_page(page, 1);
}
-static void init_dent_inode(const struct qstr *name, struct page *ipage)
+static void init_dent_inode(const struct f2fs_filename *fname,
+ struct page *ipage)
{
struct f2fs_inode *ri;
@@ -424,16 +463,16 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
/* copy name info. to this inode page */
ri = F2FS_INODE(ipage);
- ri->i_namelen = cpu_to_le32(name->len);
- memcpy(ri->i_name, name->name, name->len);
+ ri->i_namelen = cpu_to_le32(fname->disk_name.len);
+ memcpy(ri->i_name, fname->disk_name.name, fname->disk_name.len);
set_page_dirty(ipage);
}
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
struct f2fs_dentry_ptr *d)
{
- struct qstr dot = QSTR_INIT(".", 1);
- struct qstr dotdot = QSTR_INIT("..", 2);
+ struct fscrypt_str dot = FSTR_INIT(".", 1);
+ struct fscrypt_str dotdot = FSTR_INIT("..", 2);
/* update dirent of "." */
f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
@@ -467,8 +506,7 @@ static int make_empty_dir(struct inode *inode,
}
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
- const struct qstr *new_name, const struct qstr *orig_name,
- struct page *dpage)
+ const struct f2fs_filename *fname, struct page *dpage)
{
struct page *page;
int err;
@@ -493,7 +531,8 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
if (err)
goto put_error;
- err = f2fs_init_security(inode, dir, orig_name, page);
+ err = f2fs_init_security(inode, dir,
+ fname ? fname->usr_fname : NULL, page);
if (err)
goto put_error;
@@ -508,8 +547,8 @@ struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
return page;
}
- if (new_name) {
- init_dent_inode(new_name, page);
+ if (fname) {
+ init_dent_inode(fname, page);
if (IS_ENCRYPTED(dir))
file_set_enc_name(inode);
}
@@ -577,11 +616,11 @@ next:
}
bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
- struct fscrypt_name *fname)
+ const struct f2fs_filename *fname)
{
struct f2fs_dentry_ptr d;
unsigned int bit_pos;
- int slots = GET_DENTRY_SLOTS(fname_len(fname));
+ int slots = GET_DENTRY_SLOTS(fname->disk_name.len);
make_dentry_ptr_inline(dir, &d, inline_data_addr(dir, ipage));
@@ -591,8 +630,8 @@ bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
}
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
- const struct qstr *name, f2fs_hash_t name_hash,
- unsigned int bit_pos)
+ const struct fscrypt_str *name, f2fs_hash_t name_hash,
+ unsigned int bit_pos)
{
struct f2fs_dir_entry *de;
int slots = GET_DENTRY_SLOTS(name->len);
@@ -612,15 +651,13 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
}
}
-int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
- const struct qstr *orig_name,
- struct inode *inode, nid_t ino, umode_t mode)
+int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname,
+ struct inode *inode, nid_t ino, umode_t mode)
{
unsigned int bit_pos;
unsigned int level;
unsigned int current_depth;
unsigned long bidx, block;
- f2fs_hash_t dentry_hash;
unsigned int nbucket, nblock;
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
@@ -629,11 +666,10 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
int slots, err = 0;
level = 0;
- slots = GET_DENTRY_SLOTS(new_name->len);
- dentry_hash = f2fs_dentry_hash(dir, new_name, NULL);
+ slots = GET_DENTRY_SLOTS(fname->disk_name.len);
current_depth = F2FS_I(dir)->i_current_depth;
- if (F2FS_I(dir)->chash == dentry_hash) {
+ if (F2FS_I(dir)->chash == fname->hash) {
level = F2FS_I(dir)->clevel;
F2FS_I(dir)->chash = 0;
}
@@ -655,7 +691,7 @@ start:
nblock = bucket_blocks(level);
bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
- (le32_to_cpu(dentry_hash) % nbucket));
+ (le32_to_cpu(fname->hash) % nbucket));
for (block = bidx; block <= (bidx + nblock - 1); block++) {
dentry_page = f2fs_get_new_data_page(dir, NULL, block, true);
@@ -679,8 +715,7 @@ add_dentry:
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = f2fs_init_inode_metadata(inode, dir, new_name,
- orig_name, NULL);
+ page = f2fs_init_inode_metadata(inode, dir, fname, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -688,7 +723,8 @@ add_dentry:
}
make_dentry_ptr_block(NULL, &d, dentry_blk);
- f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
+ f2fs_update_dentry(ino, mode, &d, &fname->disk_name, fname->hash,
+ bit_pos);
set_page_dirty(dentry_page);
@@ -712,21 +748,15 @@ fail:
return err;
}
-int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
- struct inode *inode, nid_t ino, umode_t mode)
+int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname,
+ struct inode *inode, nid_t ino, umode_t mode)
{
- struct qstr new_name;
int err = -EAGAIN;
- new_name.name = fname_name(fname);
- new_name.len = fname_len(fname);
-
if (f2fs_has_inline_dentry(dir))
- err = f2fs_add_inline_entry(dir, &new_name, fname->usr_fname,
- inode, ino, mode);
+ err = f2fs_add_inline_entry(dir, fname, inode, ino, mode);
if (err == -EAGAIN)
- err = f2fs_add_regular_entry(dir, &new_name, fname->usr_fname,
- inode, ino, mode);
+ err = f2fs_add_regular_entry(dir, fname, inode, ino, mode);
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
return err;
@@ -739,17 +769,17 @@ int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode)
{
- struct fscrypt_name fname;
+ struct f2fs_filename fname;
struct page *page = NULL;
struct f2fs_dir_entry *de = NULL;
int err;
- err = fscrypt_setup_filename(dir, name, 0, &fname);
+ err = f2fs_setup_filename(dir, name, 0, &fname);
if (err)
return err;
/*
- * An immature stakable filesystem shows a race condition between lookup
+ * An immature stackable filesystem shows a race condition between lookup
* and create. If we have same task when doing lookup and create, it's
* definitely fine as expected by VFS normally. Otherwise, let's just
* verify on-disk dentry one more time, which guarantees filesystem
@@ -767,7 +797,7 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
} else {
err = f2fs_add_dentry(dir, &fname, inode, ino, mode);
}
- fscrypt_free_filename(&fname);
+ f2fs_free_filename(&fname);
return err;
}
@@ -777,7 +807,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
int err = 0;
down_write(&F2FS_I(inode)->i_sem);
- page = f2fs_init_inode_metadata(inode, dir, NULL, NULL, NULL);
+ page = f2fs_init_inode_metadata(inode, dir, NULL, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -1080,17 +1110,41 @@ const struct file_operations f2fs_dir_operations = {
static int f2fs_d_compare(const struct dentry *dentry, unsigned int len,
const char *str, const struct qstr *name)
{
- struct qstr qstr = {.name = str, .len = len };
const struct dentry *parent = READ_ONCE(dentry->d_parent);
- const struct inode *inode = READ_ONCE(parent->d_inode);
+ const struct inode *dir = READ_ONCE(parent->d_inode);
+ const struct f2fs_sb_info *sbi = F2FS_SB(dentry->d_sb);
+ struct qstr entry = QSTR_INIT(str, len);
+ char strbuf[DNAME_INLINE_LEN];
+ int res;
+
+ if (!dir || !IS_CASEFOLDED(dir))
+ goto fallback;
- if (!inode || !IS_CASEFOLDED(inode)) {
- if (len != name->len)
- return -1;
- return memcmp(str, name->name, len);
+ /*
+ * If the dentry name is stored in-line, then it may be concurrently
+ * modified by a rename. If this happens, the VFS will eventually retry
+ * the lookup, so it doesn't matter what ->d_compare() returns.
+ * However, it's unsafe to call utf8_strncasecmp() with an unstable
+ * string. Therefore, we have to copy the name into a temporary buffer.
+ */
+ if (len <= DNAME_INLINE_LEN - 1) {
+ memcpy(strbuf, str, len);
+ strbuf[len] = 0;
+ entry.name = strbuf;
+ /* prevent compiler from optimizing out the temporary buffer */
+ barrier();
}
- return f2fs_ci_compare(inode, name, &qstr, false);
+ res = utf8_strncasecmp(sbi->s_encoding, name, &entry);
+ if (res >= 0)
+ return res;
+
+ if (f2fs_has_strict_mode(sbi))
+ return -EINVAL;
+fallback:
+ if (len != name->len)
+ return 1;
+ return !!memcmp(str, name->name, len);
}
static int f2fs_d_hash(const struct dentry *dentry, struct qstr *str)
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index e60078460ad1..686c68b98610 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -325,9 +325,10 @@ static void __drop_largest_extent(struct extent_tree *et,
}
/* return true, if inode page is changed */
-static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+static void __f2fs_init_extent_tree(struct inode *inode, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_extent *i_ext = ipage ? &F2FS_INODE(ipage)->i_ext : NULL;
struct extent_tree *et;
struct extent_node *en;
struct extent_info ei;
@@ -335,16 +336,18 @@ static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_e
if (!f2fs_may_extent_tree(inode)) {
/* drop largest extent */
if (i_ext && i_ext->len) {
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
i_ext->len = 0;
- return true;
+ set_page_dirty(ipage);
+ return;
}
- return false;
+ return;
}
et = __grab_extent_tree(inode);
if (!i_ext || !i_ext->len)
- return false;
+ return;
get_extent_info(&ei, i_ext);
@@ -360,17 +363,14 @@ static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_e
}
out:
write_unlock(&et->lock);
- return false;
}
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+void f2fs_init_extent_tree(struct inode *inode, struct page *ipage)
{
- bool ret = __f2fs_init_extent_tree(inode, i_ext);
+ __f2fs_init_extent_tree(inode, ipage);
if (!F2FS_I(inode)->extent_tree)
set_inode_flag(inode, FI_NO_EXTENT);
-
- return ret;
}
static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ba470d5687fe..d9e52a7f3702 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* fs/f2fs/f2fs.h
*
@@ -138,7 +138,8 @@ struct f2fs_mount_info {
int fsync_mode; /* fsync policy */
int fs_mode; /* fs mode: LFS or ADAPTIVE */
int bggc_mode; /* bggc mode: off, on or sync */
- bool test_dummy_encryption; /* test dummy encryption */
+ struct fscrypt_dummy_context dummy_enc_ctx; /* test dummy encryption */
+ block_t unusable_cap_perc; /* percentage for cap */
block_t unusable_cap; /* Amount of space allowed to be
* unusable when disabling checkpoint
*/
@@ -194,6 +195,7 @@ enum {
#define CP_DISCARD 0x00000010
#define CP_TRIMMED 0x00000020
#define CP_PAUSE 0x00000040
+#define CP_RESIZE 0x00000080
#define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi)
#define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */
@@ -400,12 +402,8 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
}
/*
- * ioctl commands
+ * f2fs-specific ioctl commands
*/
-#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
-#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
-#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION
-
#define F2FS_IOCTL_MAGIC 0xf5
#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
@@ -428,13 +426,12 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
#define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15)
#define F2FS_IOC_RESIZE_FS _IOW(F2FS_IOCTL_MAGIC, 16, __u64)
#define F2FS_IOC_GET_COMPRESS_BLOCKS _IOR(F2FS_IOCTL_MAGIC, 17, __u64)
-
-#define F2FS_IOC_GET_VOLUME_NAME FS_IOC_GETFSLABEL
-#define F2FS_IOC_SET_VOLUME_NAME FS_IOC_SETFSLABEL
-
-#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
-#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
-#define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT
+#define F2FS_IOC_RELEASE_COMPRESS_BLOCKS \
+ _IOR(F2FS_IOCTL_MAGIC, 18, __u64)
+#define F2FS_IOC_RESERVE_COMPRESS_BLOCKS \
+ _IOR(F2FS_IOCTL_MAGIC, 19, __u64)
+#define F2FS_IOC_SEC_TRIM_FILE _IOW(F2FS_IOCTL_MAGIC, 20, \
+ struct f2fs_sectrim_range)
/*
* should be same as XFS_IOC_GOINGDOWN.
@@ -447,17 +444,12 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
#define F2FS_GOING_DOWN_NEED_FSCK 0x4 /* going down to trigger fsck */
-#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
- * ioctl commands in 32 bit emulation
+ * Flags used by F2FS_IOC_SEC_TRIM_FILE
*/
-#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
-#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION
-#endif
-
-#define F2FS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
-#define F2FS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
+#define F2FS_TRIM_FILE_DISCARD 0x1 /* send discard command */
+#define F2FS_TRIM_FILE_ZEROOUT 0x2 /* zero out */
+#define F2FS_TRIM_FILE_MASK 0x3
struct f2fs_gc_range {
u32 sync;
@@ -482,6 +474,12 @@ struct f2fs_flush_device {
u32 segments; /* # of segments to flush */
};
+struct f2fs_sectrim_range {
+ u64 start;
+ u64 len;
+ u64 flags;
+};
+
/* for inline stuff */
#define DEF_INLINE_RESERVED_SIZE 1
static inline int get_extra_isize(struct inode *inode);
@@ -506,6 +504,42 @@ static inline int get_inline_xattr_addrs(struct inode *inode);
* For INODE and NODE manager
*/
/* for directory operations */
+
+struct f2fs_filename {
+ /*
+ * The filename the user specified. This is NULL for some
+ * filesystem-internal operations, e.g. converting an inline directory
+ * to a non-inline one, or roll-forward recovering an encrypted dentry.
+ */
+ const struct qstr *usr_fname;
+
+ /*
+ * The on-disk filename. For encrypted directories, this is encrypted.
+ * This may be NULL for lookups in an encrypted dir without the key.
+ */
+ struct fscrypt_str disk_name;
+
+ /* The dirhash of this filename */
+ f2fs_hash_t hash;
+
+#ifdef CONFIG_FS_ENCRYPTION
+ /*
+ * For lookups in encrypted directories: either the buffer backing
+ * disk_name, or a buffer that holds the decoded no-key name.
+ */
+ struct fscrypt_str crypto_buf;
+#endif
+#ifdef CONFIG_UNICODE
+ /*
+ * For casefolded directories: the casefolded name, but it's left NULL
+ * if the original name is not valid Unicode or if the filesystem is
+ * doing an internal operation where usr_fname is also NULL. In these
+ * cases we fall back to treating the name as an opaque byte sequence.
+ */
+ struct fscrypt_str cf_name;
+#endif
+};
+
struct f2fs_dentry_ptr {
struct inode *inode;
void *bitmap;
@@ -752,6 +786,7 @@ struct f2fs_inode_info {
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct task_struct *inmem_task; /* store inmemory task */
struct mutex inmem_lock; /* lock for inmemory pages */
+ pgoff_t ra_offset; /* ongoing readahead offset */
struct extent_tree *extent_tree; /* cached extent_tree entry */
/* avoid racing between foreground op and gc */
@@ -1088,8 +1123,9 @@ enum cp_reason_type {
};
enum iostat_type {
- APP_DIRECT_IO, /* app direct IOs */
- APP_BUFFERED_IO, /* app buffered IOs */
+ /* WRITE IO */
+ APP_DIRECT_IO, /* app direct write IOs */
+ APP_BUFFERED_IO, /* app buffered write IOs */
APP_WRITE_IO, /* app write IOs */
APP_MAPPED_IO, /* app mapped IOs */
FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */
@@ -1100,6 +1136,19 @@ enum iostat_type {
FS_CP_DATA_IO, /* data IOs from checkpoint */
FS_CP_NODE_IO, /* node IOs from checkpoint */
FS_CP_META_IO, /* meta IOs from checkpoint */
+
+ /* READ IO */
+ APP_DIRECT_READ_IO, /* app direct read IOs */
+ APP_BUFFERED_READ_IO, /* app buffered read IOs */
+ APP_READ_IO, /* app read IOs */
+ APP_MAPPED_READ_IO, /* app mapped read IOs */
+ FS_DATA_READ_IO, /* data read IOs */
+ FS_GDATA_READ_IO, /* data read IOs from background gc */
+ FS_CDATA_READ_IO, /* compressed data read IOs */
+ FS_NODE_READ_IO, /* node read IOs */
+ FS_META_READ_IO, /* meta read IOs */
+
+ /* other */
FS_DISCARD, /* discard */
NR_IO_TYPE,
};
@@ -1211,7 +1260,8 @@ enum {
GC_NORMAL,
GC_IDLE_CB,
GC_IDLE_GREEDY,
- GC_URGENT,
+ GC_URGENT_HIGH,
+ GC_URGENT_LOW,
};
enum {
@@ -1257,9 +1307,17 @@ enum fsync_mode {
#define IS_DUMMY_WRITTEN_PAGE(page) \
(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
+#ifdef CONFIG_F2FS_IO_TRACE
+#define IS_IO_TRACED_PAGE(page) \
+ (page_private(page) > 0 && \
+ page_private(page) < (unsigned long)PID_MAX_LIMIT)
+#else
+#define IS_IO_TRACED_PAGE(page) (0)
+#endif
+
#ifdef CONFIG_FS_ENCRYPTION
#define DUMMY_ENCRYPTION_ENABLED(sbi) \
- (unlikely(F2FS_OPTION(sbi).test_dummy_encryption))
+ (unlikely(F2FS_OPTION(sbi).dummy_enc_ctx.ctx != NULL))
#else
#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
#endif
@@ -1269,6 +1327,7 @@ enum compress_algorithm_type {
COMPRESS_LZO,
COMPRESS_LZ4,
COMPRESS_ZSTD,
+ COMPRESS_LZORLE,
COMPRESS_MAX,
};
@@ -1381,7 +1440,7 @@ struct f2fs_sb_info {
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
long interval_time[MAX_TIME]; /* to store thresholds */
- struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
+ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
spinlock_t fsync_node_lock; /* for node entry lock */
struct list_head fsync_node_list; /* node list head */
@@ -1418,7 +1477,6 @@ struct f2fs_sb_info {
unsigned int segs_per_sec; /* segments per section */
unsigned int secs_per_zone; /* sections per zone */
unsigned int total_sections; /* total section count */
- struct mutex resize_mutex; /* for resize exclusion */
unsigned int total_node_count; /* total node block count */
unsigned int total_valid_node_count; /* valid node block count */
loff_t max_file_blocks; /* max block index of file */
@@ -1460,8 +1518,9 @@ struct f2fs_sb_info {
unsigned int cur_victim_sec; /* current victim section num */
unsigned int gc_mode; /* current GC state */
unsigned int next_victim_seg[2]; /* next segment in victim section */
+
/* for skip statistic */
- unsigned int atomic_files; /* # of opened atomic file */
+ unsigned int atomic_files; /* # of opened atomic file */
unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */
unsigned long long skipped_gc_rwsem; /* FG_GC only */
@@ -1504,8 +1563,15 @@ struct f2fs_sb_info {
/* For app/fs IO statistics */
spinlock_t iostat_lock;
- unsigned long long write_iostat[NR_IO_TYPE];
+ unsigned long long rw_iostat[NR_IO_TYPE];
+ unsigned long long prev_rw_iostat[NR_IO_TYPE];
bool iostat_enable;
+ unsigned long iostat_next_period;
+ unsigned int iostat_period_ms;
+
+ /* to attach REQ_META|REQ_FUA flags */
+ unsigned int data_io_flag;
+ unsigned int node_io_flag;
/* For sysfs suppport */
struct kobject s_kobj;
@@ -2393,7 +2459,7 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep,
static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
{
- if (sbi->gc_mode == GC_URGENT)
+ if (sbi->gc_mode == GC_URGENT_HIGH)
return true;
if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) ||
@@ -2411,6 +2477,10 @@ static inline bool is_idle(struct f2fs_sb_info *sbi, int type)
atomic_read(&SM_I(sbi)->fcc_info->queued_flush))
return false;
+ if (sbi->gc_mode == GC_URGENT_LOW &&
+ (type == DISCARD_TIME || type == GC_TIME))
+ return true;
+
return f2fs_time_over(sbi, type);
}
@@ -2576,7 +2646,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
case FI_NEW_INODE:
if (set)
return;
- /* fall through */
+ fallthrough;
case FI_DATA_EXIST:
case FI_INLINE_DOTS:
case FI_PIN_FILE:
@@ -2586,7 +2656,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
static inline void set_inode_flag(struct inode *inode, int flag)
{
- test_and_set_bit(flag, F2FS_I(inode)->flags);
+ set_bit(flag, F2FS_I(inode)->flags);
__mark_inode_dirty_flag(inode, flag, true);
}
@@ -2597,7 +2667,7 @@ static inline int is_inode_flag_set(struct inode *inode, int flag)
static inline void clear_inode_flag(struct inode *inode, int flag)
{
- test_and_clear_bit(flag, F2FS_I(inode)->flags);
+ clear_bit(flag, F2FS_I(inode)->flags);
__mark_inode_dirty_flag(inode, flag, false);
}
@@ -2902,12 +2972,12 @@ static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
}
-static inline bool is_dot_dotdot(const struct qstr *str)
+static inline bool is_dot_dotdot(const u8 *name, size_t len)
{
- if (str->len == 1 && str->name[0] == '.')
+ if (len == 1 && name[0] == '.')
return true;
- if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
+ if (len == 2 && name[0] == '.' && name[1] == '.')
return true;
return false;
@@ -2935,18 +3005,12 @@ static inline bool f2fs_may_extent_tree(struct inode *inode)
static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
size_t size, gfp_t flags)
{
- void *ret;
-
if (time_to_inject(sbi, FAULT_KMALLOC)) {
f2fs_show_injection_info(sbi, FAULT_KMALLOC);
return NULL;
}
- ret = kmalloc(size, flags);
- if (ret)
- return ret;
-
- return kvmalloc(size, flags);
+ return kmalloc(size, flags);
}
static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi,
@@ -2996,29 +3060,45 @@ static inline int get_inline_xattr_addrs(struct inode *inode)
sizeof((f2fs_inode)->field)) \
<= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \
+#define DEFAULT_IOSTAT_PERIOD_MS 3000
+#define MIN_IOSTAT_PERIOD_MS 100
+/* maximum period of iostat tracing is 1 day */
+#define MAX_IOSTAT_PERIOD_MS 8640000
+
static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi)
{
int i;
spin_lock(&sbi->iostat_lock);
- for (i = 0; i < NR_IO_TYPE; i++)
- sbi->write_iostat[i] = 0;
+ for (i = 0; i < NR_IO_TYPE; i++) {
+ sbi->rw_iostat[i] = 0;
+ sbi->prev_rw_iostat[i] = 0;
+ }
spin_unlock(&sbi->iostat_lock);
}
+extern void f2fs_record_iostat(struct f2fs_sb_info *sbi);
+
static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi,
enum iostat_type type, unsigned long long io_bytes)
{
if (!sbi->iostat_enable)
return;
spin_lock(&sbi->iostat_lock);
- sbi->write_iostat[type] += io_bytes;
+ sbi->rw_iostat[type] += io_bytes;
if (type == APP_WRITE_IO || type == APP_DIRECT_IO)
- sbi->write_iostat[APP_BUFFERED_IO] =
- sbi->write_iostat[APP_WRITE_IO] -
- sbi->write_iostat[APP_DIRECT_IO];
+ sbi->rw_iostat[APP_BUFFERED_IO] =
+ sbi->rw_iostat[APP_WRITE_IO] -
+ sbi->rw_iostat[APP_DIRECT_IO];
+
+ if (type == APP_READ_IO || type == APP_DIRECT_READ_IO)
+ sbi->rw_iostat[APP_BUFFERED_READ_IO] =
+ sbi->rw_iostat[APP_READ_IO] -
+ sbi->rw_iostat[APP_DIRECT_READ_IO];
spin_unlock(&sbi->iostat_lock);
+
+ f2fs_record_iostat(sbi);
}
#define __is_large_section(sbi) ((sbi)->segs_per_sec > 1)
@@ -3051,19 +3131,12 @@ static inline void f2fs_set_page_private(struct page *page,
if (PagePrivate(page))
return;
- get_page(page);
- SetPagePrivate(page);
- set_page_private(page, data);
+ attach_page_private(page, (void *)data);
}
static inline void f2fs_clear_page_private(struct page *page)
{
- if (!PagePrivate(page))
- return;
-
- set_page_private(page, 0);
- ClearPagePrivate(page);
- f2fs_put_page(page, 0);
+ detach_page_private(page);
}
/*
@@ -3071,6 +3144,7 @@ static inline void f2fs_clear_page_private(struct page *page)
*/
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
void f2fs_truncate_data_blocks(struct dnode_of_data *dn);
+int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock);
int f2fs_truncate(struct inode *inode);
int f2fs_getattr(const struct path *path, struct kstat *stat,
@@ -3106,31 +3180,32 @@ int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name,
bool hot, bool set);
struct dentry *f2fs_get_parent(struct dentry *child);
-extern int f2fs_ci_compare(const struct inode *parent,
- const struct qstr *name,
- const struct qstr *entry,
- bool quick);
-
/*
* dir.c
*/
unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de);
-struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname,
- f2fs_hash_t namehash, int *max_slots,
- struct f2fs_dentry_ptr *d);
+int f2fs_init_casefolded_name(const struct inode *dir,
+ struct f2fs_filename *fname);
+int f2fs_setup_filename(struct inode *dir, const struct qstr *iname,
+ int lookup, struct f2fs_filename *fname);
+int f2fs_prepare_lookup(struct inode *dir, struct dentry *dentry,
+ struct f2fs_filename *fname);
+void f2fs_free_filename(struct f2fs_filename *fname);
+struct f2fs_dir_entry *f2fs_find_target_dentry(const struct f2fs_dentry_ptr *d,
+ const struct f2fs_filename *fname, int *max_slots);
int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
unsigned int start_pos, struct fscrypt_str *fstr);
void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent,
struct f2fs_dentry_ptr *d);
struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir,
- const struct qstr *new_name,
- const struct qstr *orig_name, struct page *dpage);
+ const struct f2fs_filename *fname, struct page *dpage);
void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth);
int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots);
void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
- struct fscrypt_name *fname, struct page **res_page);
+ const struct f2fs_filename *fname,
+ struct page **res_page);
struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
const struct qstr *child, struct page **res_page);
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
@@ -3139,14 +3214,13 @@ ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode);
bool f2fs_has_enough_room(struct inode *dir, struct page *ipage,
- struct fscrypt_name *fname);
+ const struct f2fs_filename *fname);
void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
- const struct qstr *name, f2fs_hash_t name_hash,
+ const struct fscrypt_str *name, f2fs_hash_t name_hash,
unsigned int bit_pos);
-int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
- const struct qstr *orig_name,
+int f2fs_add_regular_entry(struct inode *dir, const struct f2fs_filename *fname,
struct inode *inode, nid_t ino, umode_t mode);
-int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname,
+int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname,
struct inode *inode, nid_t ino, umode_t mode);
int f2fs_do_add_link(struct inode *dir, const struct qstr *name,
struct inode *inode, nid_t ino, umode_t mode);
@@ -3176,8 +3250,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
* hash.c
*/
-f2fs_hash_t f2fs_dentry_hash(const struct inode *dir,
- const struct qstr *name_info, struct fscrypt_name *fname);
+void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname);
/*
* node.c
@@ -3209,6 +3282,7 @@ 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 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);
int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic,
unsigned int *seq_id);
@@ -3220,7 +3294,7 @@ bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
-void f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
+int f2fs_recover_inline_xattr(struct inode *inode, struct page *page);
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,
@@ -3258,9 +3332,10 @@ block_t f2fs_get_unusable_blocks(struct f2fs_sb_info *sbi);
int f2fs_disable_cp_again(struct f2fs_sb_info *sbi, block_t unusable);
void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi);
int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
-void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
+void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end);
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type);
+void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type);
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi);
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi,
struct cp_control *cpc);
@@ -3283,7 +3358,7 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
- struct f2fs_io_info *fio, bool add_list);
+ struct f2fs_io_info *fio);
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered, bool locked);
void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr);
@@ -3373,9 +3448,6 @@ int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
-int f2fs_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write);
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
@@ -3384,7 +3456,7 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
struct page *f2fs_get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size);
int f2fs_do_write_data_page(struct f2fs_io_info *fio);
-void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
+void f2fs_do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock);
int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int create, int flag);
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
@@ -3472,6 +3544,9 @@ struct f2fs_stat_info {
int curseg[NR_CURSEG_TYPE];
int cursec[NR_CURSEG_TYPE];
int curzone[NR_CURSEG_TYPE];
+ unsigned int dirty_seg[NR_CURSEG_TYPE];
+ unsigned int full_seg[NR_CURSEG_TYPE];
+ unsigned int valid_blks[NR_CURSEG_TYPE];
unsigned int meta_count[META_MAX];
unsigned int segment_count[2];
@@ -3655,7 +3730,7 @@ static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
static inline void __init f2fs_create_root_stats(void) { }
static inline void f2fs_destroy_root_stats(void) { }
-static inline void update_sit_info(struct f2fs_sb_info *sbi) {}
+static inline void f2fs_update_sit_info(struct f2fs_sb_info *sbi) {}
#endif
extern const struct file_operations f2fs_dir_operations;
@@ -3686,13 +3761,13 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
int f2fs_convert_inline_inode(struct inode *inode);
int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry);
int f2fs_write_inline_data(struct inode *inode, struct page *page);
-bool f2fs_recover_inline_data(struct inode *inode, struct page *npage);
+int f2fs_recover_inline_data(struct inode *inode, struct page *npage);
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
- struct fscrypt_name *fname, struct page **res_page);
+ const struct f2fs_filename *fname,
+ struct page **res_page);
int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage);
-int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
- const struct qstr *orig_name,
+int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
struct inode *inode, nid_t ino, umode_t mode);
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry,
struct page *page, struct inode *dir,
@@ -3731,7 +3806,7 @@ struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root,
bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi,
struct rb_root_cached *root);
unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
+void f2fs_init_extent_tree(struct inode *inode, struct page *ipage);
void f2fs_drop_extent_tree(struct inode *inode);
unsigned int f2fs_destroy_extent_node(struct inode *inode);
void f2fs_destroy_extent_tree(struct inode *inode);
@@ -3791,8 +3866,11 @@ int f2fs_prepare_compress_overwrite(struct inode *inode,
struct page **pagep, pgoff_t index, void **fsdata);
bool f2fs_compress_write_end(struct inode *inode, void *fsdata,
pgoff_t index, unsigned copied);
+int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock);
void f2fs_compress_write_end_io(struct bio *bio, struct page *page);
bool f2fs_is_compress_backend_ready(struct inode *inode);
+int f2fs_init_compress_mempool(void);
+void f2fs_destroy_compress_mempool(void);
void f2fs_decompress_pages(struct bio *bio, struct page *page, bool verity);
bool f2fs_cluster_is_empty(struct compress_ctx *cc);
bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index);
@@ -3826,6 +3904,8 @@ static inline struct page *f2fs_compress_control_page(struct page *page)
WARN_ON_ONCE(1);
return ERR_PTR(-EINVAL);
}
+static inline int f2fs_init_compress_mempool(void) { return 0; }
+static inline void f2fs_destroy_compress_mempool(void) { }
#endif
static inline void set_compress_context(struct inode *inode)
@@ -3972,6 +4052,10 @@ static inline void f2fs_i_compr_blocks_update(struct inode *inode,
{
int diff = F2FS_I(inode)->i_cluster_size - blocks;
+ /* don't update i_compr_blocks if saved blocks were released */
+ if (!add && !F2FS_I(inode)->i_compr_blocks)
+ return;
+
if (add) {
F2FS_I(inode)->i_compr_blocks += diff;
stat_add_compr_blocks(inode, diff);
@@ -4013,8 +4097,6 @@ static inline bool f2fs_force_buffered_io(struct inode *inode,
return true;
if (f2fs_is_multi_device(sbi))
return true;
- if (f2fs_compressed_file(inode))
- return true;
/*
* for blkzoned device, fallback direct IO to buffered IO, so
* all IOs can be serialized by log-structured write.
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6ab8f621a3c5..8a422400e824 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -21,6 +21,7 @@
#include <linux/uuid.h>
#include <linux/file.h>
#include <linux/nls.h>
+#include <linux/sched/signal.h>
#include "f2fs.h"
#include "node.h"
@@ -40,6 +41,10 @@ static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
ret = filemap_fault(vmf);
up_read(&F2FS_I(inode)->i_mmap_sem);
+ if (!ret)
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_MAPPED_READ_IO,
+ F2FS_BLKSIZE);
+
trace_f2fs_filemap_fault(inode, vmf->pgoff, (unsigned long)ret);
return ret;
@@ -101,11 +106,11 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
if (need_alloc) {
/* block allocation */
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_get_block(&dn, page->index);
f2fs_put_dnode(&dn);
- __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ f2fs_do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
}
#ifdef CONFIG_F2FS_FS_COMPRESSION
@@ -165,9 +170,11 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
{
struct dentry *dentry;
- inode = igrab(inode);
- dentry = d_find_any_alias(inode);
- iput(inode);
+ /*
+ * Make sure to get the non-deleted alias. The alias associated with
+ * the open file descriptor being fsync()'ed may be deleted already.
+ */
+ dentry = d_find_alias(inode);
if (!dentry)
return 0;
@@ -557,6 +564,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
bool compressed_cluster = false;
int cluster_index = 0, valid_blocks = 0;
int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+ bool released = !F2FS_I(dn->inode)->i_compr_blocks;
if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
base = get_extra_isize(dn->inode);
@@ -595,7 +603,9 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
f2fs_invalidate_blocks(sbi, blkaddr);
- nr_free++;
+
+ if (!released || blkaddr != COMPRESS_ADDR)
+ nr_free++;
}
if (compressed_cluster)
@@ -643,9 +653,6 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
return 0;
}
- if (f2fs_compressed_file(inode))
- return 0;
-
page = f2fs_get_lock_data_page(inode, index, true);
if (IS_ERR(page))
return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
@@ -661,7 +668,7 @@ truncate_out:
return 0;
}
-static int do_truncate_blocks(struct inode *inode, u64 from, bool lock)
+int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
@@ -729,23 +736,28 @@ free_partial:
int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock)
{
u64 free_from = from;
+ int err;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
/*
* for compressed file, only support cluster size
* aligned truncation.
*/
- if (f2fs_compressed_file(inode)) {
- size_t cluster_shift = PAGE_SHIFT +
- F2FS_I(inode)->i_log_cluster_size;
- size_t cluster_mask = (1 << cluster_shift) - 1;
+ if (f2fs_compressed_file(inode))
+ free_from = round_up(from,
+ F2FS_I(inode)->i_cluster_size << PAGE_SHIFT);
+#endif
- free_from = from >> cluster_shift;
- if (from & cluster_mask)
- free_from++;
- free_from <<= cluster_shift;
- }
+ err = f2fs_do_truncate_blocks(inode, free_from, lock);
+ if (err)
+ return err;
- return do_truncate_blocks(inode, free_from, lock);
+#ifdef CONFIG_F2FS_FS_COMPRESSION
+ if (from != free_from)
+ err = f2fs_truncate_partial_cluster(inode, from, lock);
+#endif
+
+ return err;
}
int f2fs_truncate(struct inode *inode)
@@ -968,9 +980,7 @@ const struct inode_operations f2fs_file_inode_operations = {
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
-#ifdef CONFIG_F2FS_FS_XATTR
.listxattr = f2fs_listxattr,
-#endif
.fiemap = f2fs_fiemap,
};
@@ -1364,8 +1374,6 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
truncate_pagecache(inode, offset);
new_size = i_size_read(inode) - len;
- truncate_pagecache(inode, new_size);
-
ret = f2fs_truncate_blocks(inode, new_size, true);
up_write(&F2FS_I(inode)->i_mmap_sem);
if (!ret)
@@ -1649,7 +1657,11 @@ next_alloc:
down_write(&sbi->pin_sem);
map.m_seg_type = CURSEG_COLD_DATA_PINNED;
- f2fs_allocate_new_segments(sbi, CURSEG_COLD_DATA);
+
+ f2fs_lock_op(sbi);
+ f2fs_allocate_new_segment(sbi, CURSEG_COLD_DATA);
+ f2fs_unlock_op(sbi);
+
err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
up_write(&sbi->pin_sem);
@@ -2219,8 +2231,15 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
if (in != F2FS_GOING_DOWN_FULLSYNC) {
ret = mnt_want_write_file(filp);
- if (ret)
+ if (ret) {
+ if (ret == -EROFS) {
+ ret = 0;
+ f2fs_stop_checkpoint(sbi, false);
+ set_sbi_flag(sbi, SBI_IS_SHUTDOWN);
+ trace_f2fs_shutdown(sbi, in, ret);
+ }
return ret;
+ }
}
switch (in) {
@@ -2507,6 +2526,11 @@ do_more:
}
ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
+ if (ret) {
+ if (ret == -EBUSY)
+ ret = -EAGAIN;
+ goto out;
+ }
range.start += BLKS_PER_SEC(sbi);
if (range.start <= end)
goto do_more;
@@ -3301,7 +3325,6 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp));
__u64 block_count;
- int ret;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -3313,9 +3336,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg)
sizeof(block_count)))
return -EFAULT;
- ret = f2fs_resize_fs(sbi, block_count);
-
- return ret;
+ return f2fs_resize_fs(sbi, block_count);
}
static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg)
@@ -3342,7 +3363,7 @@ static int f2fs_ioc_measure_verity(struct file *filp, unsigned long arg)
return fsverity_ioctl_measure(filp, (void __user *)arg);
}
-static int f2fs_get_volume_name(struct file *filp, unsigned long arg)
+static int f2fs_ioc_getfslabel(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -3368,7 +3389,7 @@ static int f2fs_get_volume_name(struct file *filp, unsigned long arg)
return err;
}
-static int f2fs_set_volume_name(struct file *filp, unsigned long arg)
+static int f2fs_ioc_setfslabel(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -3419,6 +3440,513 @@ static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg)
return put_user(blocks, (u64 __user *)arg);
}
+static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ unsigned int released_blocks = 0;
+ int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+ block_t blkaddr;
+ int i;
+
+ for (i = 0; i < count; i++) {
+ blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ dn->ofs_in_node + i);
+
+ if (!__is_valid_data_blkaddr(blkaddr))
+ continue;
+ if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
+ DATA_GENERIC_ENHANCE)))
+ return -EFSCORRUPTED;
+ }
+
+ while (count) {
+ int compr_blocks = 0;
+
+ for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
+ blkaddr = f2fs_data_blkaddr(dn);
+
+ if (i == 0) {
+ if (blkaddr == COMPRESS_ADDR)
+ continue;
+ dn->ofs_in_node += cluster_size;
+ goto next;
+ }
+
+ if (__is_valid_data_blkaddr(blkaddr))
+ compr_blocks++;
+
+ if (blkaddr != NEW_ADDR)
+ continue;
+
+ dn->data_blkaddr = NULL_ADDR;
+ f2fs_set_data_blkaddr(dn);
+ }
+
+ f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false);
+ dec_valid_block_count(sbi, dn->inode,
+ cluster_size - compr_blocks);
+
+ released_blocks += cluster_size - compr_blocks;
+next:
+ count -= cluster_size;
+ }
+
+ return released_blocks;
+}
+
+static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ pgoff_t page_idx = 0, last_idx;
+ unsigned int released_blocks = 0;
+ int ret;
+ int writecount;
+
+ if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+ return -EOPNOTSUPP;
+
+ if (!f2fs_compressed_file(inode))
+ return -EINVAL;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ f2fs_balance_fs(F2FS_I_SB(inode), true);
+
+ inode_lock(inode);
+
+ writecount = atomic_read(&inode->i_writecount);
+ if ((filp->f_mode & FMODE_WRITE && writecount != 1) || writecount) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ if (IS_IMMUTABLE(inode)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
+ if (ret)
+ goto out;
+
+ F2FS_I(inode)->i_flags |= F2FS_IMMUTABLE_FL;
+ f2fs_set_inode_flags(inode);
+ inode->i_ctime = current_time(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
+
+ if (!F2FS_I(inode)->i_compr_blocks)
+ goto out;
+
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
+ last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+
+ while (page_idx < last_idx) {
+ struct dnode_of_data dn;
+ pgoff_t end_offset, count;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
+ if (ret) {
+ if (ret == -ENOENT) {
+ page_idx = f2fs_get_next_page_offset(&dn,
+ page_idx);
+ ret = 0;
+ continue;
+ }
+ break;
+ }
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
+ count = round_up(count, F2FS_I(inode)->i_cluster_size);
+
+ ret = release_compress_blocks(&dn, count);
+
+ f2fs_put_dnode(&dn);
+
+ if (ret < 0)
+ break;
+
+ page_idx += count;
+ released_blocks += ret;
+ }
+
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+out:
+ inode_unlock(inode);
+
+ mnt_drop_write_file(filp);
+
+ if (ret >= 0) {
+ ret = put_user(released_blocks, (u64 __user *)arg);
+ } else if (released_blocks && F2FS_I(inode)->i_compr_blocks) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
+ "iblocks=%llu, released=%u, compr_blocks=%llu, "
+ "run fsck to fix.",
+ __func__, inode->i_ino, inode->i_blocks,
+ released_blocks,
+ F2FS_I(inode)->i_compr_blocks);
+ }
+
+ return ret;
+}
+
+static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ unsigned int reserved_blocks = 0;
+ int cluster_size = F2FS_I(dn->inode)->i_cluster_size;
+ block_t blkaddr;
+ int i;
+
+ for (i = 0; i < count; i++) {
+ blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ dn->ofs_in_node + i);
+
+ if (!__is_valid_data_blkaddr(blkaddr))
+ continue;
+ if (unlikely(!f2fs_is_valid_blkaddr(sbi, blkaddr,
+ DATA_GENERIC_ENHANCE)))
+ return -EFSCORRUPTED;
+ }
+
+ while (count) {
+ int compr_blocks = 0;
+ blkcnt_t reserved;
+ int ret;
+
+ for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) {
+ blkaddr = f2fs_data_blkaddr(dn);
+
+ if (i == 0) {
+ if (blkaddr == COMPRESS_ADDR)
+ continue;
+ dn->ofs_in_node += cluster_size;
+ goto next;
+ }
+
+ if (__is_valid_data_blkaddr(blkaddr)) {
+ compr_blocks++;
+ continue;
+ }
+
+ dn->data_blkaddr = NEW_ADDR;
+ f2fs_set_data_blkaddr(dn);
+ }
+
+ reserved = cluster_size - compr_blocks;
+ ret = inc_valid_block_count(sbi, dn->inode, &reserved);
+ if (ret)
+ return ret;
+
+ if (reserved != cluster_size - compr_blocks)
+ return -ENOSPC;
+
+ f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true);
+
+ reserved_blocks += reserved;
+next:
+ count -= cluster_size;
+ }
+
+ return reserved_blocks;
+}
+
+static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ pgoff_t page_idx = 0, last_idx;
+ unsigned int reserved_blocks = 0;
+ int ret;
+
+ if (!f2fs_sb_has_compression(F2FS_I_SB(inode)))
+ return -EOPNOTSUPP;
+
+ if (!f2fs_compressed_file(inode))
+ return -EINVAL;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (F2FS_I(inode)->i_compr_blocks)
+ goto out;
+
+ f2fs_balance_fs(F2FS_I_SB(inode), true);
+
+ inode_lock(inode);
+
+ if (!IS_IMMUTABLE(inode)) {
+ ret = -EINVAL;
+ goto unlock_inode;
+ }
+
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
+ last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
+
+ while (page_idx < last_idx) {
+ struct dnode_of_data dn;
+ pgoff_t end_offset, count;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, page_idx, LOOKUP_NODE);
+ if (ret) {
+ if (ret == -ENOENT) {
+ page_idx = f2fs_get_next_page_offset(&dn,
+ page_idx);
+ ret = 0;
+ continue;
+ }
+ break;
+ }
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
+ count = round_up(count, F2FS_I(inode)->i_cluster_size);
+
+ ret = reserve_compress_blocks(&dn, count);
+
+ f2fs_put_dnode(&dn);
+
+ if (ret < 0)
+ break;
+
+ page_idx += count;
+ reserved_blocks += ret;
+ }
+
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+
+ if (ret >= 0) {
+ F2FS_I(inode)->i_flags &= ~F2FS_IMMUTABLE_FL;
+ f2fs_set_inode_flags(inode);
+ inode->i_ctime = current_time(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
+ }
+unlock_inode:
+ inode_unlock(inode);
+out:
+ mnt_drop_write_file(filp);
+
+ if (ret >= 0) {
+ ret = put_user(reserved_blocks, (u64 __user *)arg);
+ } else if (reserved_blocks && F2FS_I(inode)->i_compr_blocks) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_warn(sbi, "%s: partial blocks were released i_ino=%lx "
+ "iblocks=%llu, reserved=%u, compr_blocks=%llu, "
+ "run fsck to fix.",
+ __func__, inode->i_ino, inode->i_blocks,
+ reserved_blocks,
+ F2FS_I(inode)->i_compr_blocks);
+ }
+
+ return ret;
+}
+
+static int f2fs_secure_erase(struct block_device *bdev, struct inode *inode,
+ pgoff_t off, block_t block, block_t len, u32 flags)
+{
+ struct request_queue *q = bdev_get_queue(bdev);
+ sector_t sector = SECTOR_FROM_BLOCK(block);
+ sector_t nr_sects = SECTOR_FROM_BLOCK(len);
+ int ret = 0;
+
+ if (!q)
+ return -ENXIO;
+
+ if (flags & F2FS_TRIM_FILE_DISCARD)
+ ret = blkdev_issue_discard(bdev, sector, nr_sects, GFP_NOFS,
+ blk_queue_secure_erase(q) ?
+ BLKDEV_DISCARD_SECURE : 0);
+
+ if (!ret && (flags & F2FS_TRIM_FILE_ZEROOUT)) {
+ if (IS_ENCRYPTED(inode))
+ ret = fscrypt_zeroout_range(inode, off, block, len);
+ else
+ ret = blkdev_issue_zeroout(bdev, sector, nr_sects,
+ GFP_NOFS, 0);
+ }
+
+ return ret;
+}
+
+static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct address_space *mapping = inode->i_mapping;
+ struct block_device *prev_bdev = NULL;
+ struct f2fs_sectrim_range range;
+ pgoff_t index, pg_end, prev_index = 0;
+ block_t prev_block = 0, len = 0;
+ loff_t end_addr;
+ bool to_end = false;
+ int ret = 0;
+
+ if (!(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(&range, (struct f2fs_sectrim_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ if (range.flags == 0 || (range.flags & ~F2FS_TRIM_FILE_MASK) ||
+ !S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if (((range.flags & F2FS_TRIM_FILE_DISCARD) &&
+ !f2fs_hw_support_discard(sbi)) ||
+ ((range.flags & F2FS_TRIM_FILE_ZEROOUT) &&
+ IS_ENCRYPTED(inode) && f2fs_is_multi_device(sbi)))
+ return -EOPNOTSUPP;
+
+ file_start_write(filp);
+ inode_lock(inode);
+
+ if (f2fs_is_atomic_file(inode) || f2fs_compressed_file(inode) ||
+ range.start >= inode->i_size) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ if (range.len == 0)
+ goto err;
+
+ if (inode->i_size - range.start > range.len) {
+ end_addr = range.start + range.len;
+ } else {
+ end_addr = range.len == (u64)-1 ?
+ sbi->sb->s_maxbytes : inode->i_size;
+ to_end = true;
+ }
+
+ if (!IS_ALIGNED(range.start, F2FS_BLKSIZE) ||
+ (!to_end && !IS_ALIGNED(end_addr, F2FS_BLKSIZE))) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ index = F2FS_BYTES_TO_BLK(range.start);
+ pg_end = DIV_ROUND_UP(end_addr, F2FS_BLKSIZE);
+
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ goto err;
+
+ down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+ down_write(&F2FS_I(inode)->i_mmap_sem);
+
+ ret = filemap_write_and_wait_range(mapping, range.start,
+ to_end ? LLONG_MAX : end_addr - 1);
+ if (ret)
+ goto out;
+
+ truncate_inode_pages_range(mapping, range.start,
+ to_end ? -1 : end_addr - 1);
+
+ while (index < pg_end) {
+ struct dnode_of_data dn;
+ pgoff_t end_offset, count;
+ int i;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ if (ret) {
+ if (ret == -ENOENT) {
+ index = f2fs_get_next_page_offset(&dn, index);
+ continue;
+ }
+ goto out;
+ }
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ count = min(end_offset - dn.ofs_in_node, pg_end - index);
+ for (i = 0; i < count; i++, index++, dn.ofs_in_node++) {
+ struct block_device *cur_bdev;
+ block_t blkaddr = f2fs_data_blkaddr(&dn);
+
+ if (!__is_valid_data_blkaddr(blkaddr))
+ continue;
+
+ if (!f2fs_is_valid_blkaddr(sbi, blkaddr,
+ DATA_GENERIC_ENHANCE)) {
+ ret = -EFSCORRUPTED;
+ f2fs_put_dnode(&dn);
+ goto out;
+ }
+
+ cur_bdev = f2fs_target_device(sbi, blkaddr, NULL);
+ if (f2fs_is_multi_device(sbi)) {
+ int di = f2fs_target_device_index(sbi, blkaddr);
+
+ blkaddr -= FDEV(di).start_blk;
+ }
+
+ if (len) {
+ if (prev_bdev == cur_bdev &&
+ index == prev_index + len &&
+ blkaddr == prev_block + len) {
+ len++;
+ } else {
+ ret = f2fs_secure_erase(prev_bdev,
+ inode, prev_index, prev_block,
+ len, range.flags);
+ if (ret) {
+ f2fs_put_dnode(&dn);
+ goto out;
+ }
+
+ len = 0;
+ }
+ }
+
+ if (!len) {
+ prev_bdev = cur_bdev;
+ prev_index = index;
+ prev_block = blkaddr;
+ len = 1;
+ }
+ }
+
+ f2fs_put_dnode(&dn);
+
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ goto out;
+ }
+ cond_resched();
+ }
+
+ if (len)
+ ret = f2fs_secure_erase(prev_bdev, inode, prev_index,
+ prev_block, len, range.flags);
+out:
+ up_write(&F2FS_I(inode)->i_mmap_sem);
+ up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+err:
+ inode_unlock(inode);
+ file_end_write(filp);
+
+ return ret;
+}
+
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp)))))
@@ -3427,11 +3955,11 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return -ENOSPC;
switch (cmd) {
- case F2FS_IOC_GETFLAGS:
+ case FS_IOC_GETFLAGS:
return f2fs_ioc_getflags(filp, arg);
- case F2FS_IOC_SETFLAGS:
+ case FS_IOC_SETFLAGS:
return f2fs_ioc_setflags(filp, arg);
- case F2FS_IOC_GETVERSION:
+ case FS_IOC_GETVERSION:
return f2fs_ioc_getversion(filp, arg);
case F2FS_IOC_START_ATOMIC_WRITE:
return f2fs_ioc_start_atomic_write(filp);
@@ -3447,11 +3975,11 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_shutdown(filp, arg);
case FITRIM:
return f2fs_ioc_fitrim(filp, arg);
- case F2FS_IOC_SET_ENCRYPTION_POLICY:
+ case FS_IOC_SET_ENCRYPTION_POLICY:
return f2fs_ioc_set_encryption_policy(filp, arg);
- case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_POLICY:
return f2fs_ioc_get_encryption_policy(filp, arg);
- case F2FS_IOC_GET_ENCRYPTION_PWSALT:
+ case FS_IOC_GET_ENCRYPTION_PWSALT:
return f2fs_ioc_get_encryption_pwsalt(filp, arg);
case FS_IOC_GET_ENCRYPTION_POLICY_EX:
return f2fs_ioc_get_encryption_policy_ex(filp, arg);
@@ -3479,9 +4007,9 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_flush_device(filp, arg);
case F2FS_IOC_GET_FEATURES:
return f2fs_ioc_get_features(filp, arg);
- case F2FS_IOC_FSGETXATTR:
+ case FS_IOC_FSGETXATTR:
return f2fs_ioc_fsgetxattr(filp, arg);
- case F2FS_IOC_FSSETXATTR:
+ case FS_IOC_FSSETXATTR:
return f2fs_ioc_fssetxattr(filp, arg);
case F2FS_IOC_GET_PIN_FILE:
return f2fs_ioc_get_pin_file(filp, arg);
@@ -3495,12 +4023,18 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_enable_verity(filp, arg);
case FS_IOC_MEASURE_VERITY:
return f2fs_ioc_measure_verity(filp, arg);
- case F2FS_IOC_GET_VOLUME_NAME:
- return f2fs_get_volume_name(filp, arg);
- case F2FS_IOC_SET_VOLUME_NAME:
- return f2fs_set_volume_name(filp, arg);
+ case FS_IOC_GETFSLABEL:
+ return f2fs_ioc_getfslabel(filp, arg);
+ case FS_IOC_SETFSLABEL:
+ return f2fs_ioc_setfslabel(filp, arg);
case F2FS_IOC_GET_COMPRESS_BLOCKS:
return f2fs_get_compress_blocks(filp, arg);
+ case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
+ return f2fs_release_compress_blocks(filp, arg);
+ case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
+ return f2fs_reserve_compress_blocks(filp, arg);
+ case F2FS_IOC_SEC_TRIM_FILE:
+ return f2fs_sec_trim_file(filp, arg);
default:
return -ENOTTY;
}
@@ -3510,11 +4044,17 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
+ int ret;
if (!f2fs_is_compress_backend_ready(inode))
return -EOPNOTSUPP;
- return generic_file_read_iter(iocb, iter);
+ ret = generic_file_read_iter(iocb, iter);
+
+ if (ret > 0)
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_READ_IO, ret);
+
+ return ret;
}
static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
@@ -3619,14 +4159,14 @@ out:
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
- case F2FS_IOC32_GETFLAGS:
- cmd = F2FS_IOC_GETFLAGS;
+ case FS_IOC32_GETFLAGS:
+ cmd = FS_IOC_GETFLAGS;
break;
- case F2FS_IOC32_SETFLAGS:
- cmd = F2FS_IOC_SETFLAGS;
+ case FS_IOC32_SETFLAGS:
+ cmd = FS_IOC_SETFLAGS;
break;
- case F2FS_IOC32_GETVERSION:
- cmd = F2FS_IOC_GETVERSION;
+ case FS_IOC32_GETVERSION:
+ cmd = FS_IOC_GETVERSION;
break;
case F2FS_IOC_START_ATOMIC_WRITE:
case F2FS_IOC_COMMIT_ATOMIC_WRITE:
@@ -3635,9 +4175,9 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_ABORT_VOLATILE_WRITE:
case F2FS_IOC_SHUTDOWN:
case FITRIM:
- case F2FS_IOC_SET_ENCRYPTION_POLICY:
- case F2FS_IOC_GET_ENCRYPTION_PWSALT:
- case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ case FS_IOC_SET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_PWSALT:
+ case FS_IOC_GET_ENCRYPTION_POLICY:
case FS_IOC_GET_ENCRYPTION_POLICY_EX:
case FS_IOC_ADD_ENCRYPTION_KEY:
case FS_IOC_REMOVE_ENCRYPTION_KEY:
@@ -3651,17 +4191,20 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_MOVE_RANGE:
case F2FS_IOC_FLUSH_DEVICE:
case F2FS_IOC_GET_FEATURES:
- case F2FS_IOC_FSGETXATTR:
- case F2FS_IOC_FSSETXATTR:
+ case FS_IOC_FSGETXATTR:
+ case FS_IOC_FSSETXATTR:
case F2FS_IOC_GET_PIN_FILE:
case F2FS_IOC_SET_PIN_FILE:
case F2FS_IOC_PRECACHE_EXTENTS:
case F2FS_IOC_RESIZE_FS:
case FS_IOC_ENABLE_VERITY:
case FS_IOC_MEASURE_VERITY:
- case F2FS_IOC_GET_VOLUME_NAME:
- case F2FS_IOC_SET_VOLUME_NAME:
+ case FS_IOC_GETFSLABEL:
+ case FS_IOC_SETFSLABEL:
case F2FS_IOC_GET_COMPRESS_BLOCKS:
+ case F2FS_IOC_RELEASE_COMPRESS_BLOCKS:
+ case F2FS_IOC_RESERVE_COMPRESS_BLOCKS:
+ case F2FS_IOC_SEC_TRIM_FILE:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 26248c8936db..11b4adde9baf 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -13,6 +13,7 @@
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/freezer.h>
+#include <linux/sched/signal.h>
#include "f2fs.h"
#include "node.h"
@@ -20,6 +21,9 @@
#include "gc.h"
#include <trace/events/f2fs.h>
+static unsigned int count_bits(const unsigned long *addr,
+ unsigned int offset, unsigned int len);
+
static int gc_thread_func(void *data)
{
struct f2fs_sb_info *sbi = data;
@@ -78,7 +82,7 @@ static int gc_thread_func(void *data)
* invalidated soon after by user update or deletion.
* So, I'd like to wait some time to collect dirty segments.
*/
- if (sbi->gc_mode == GC_URGENT) {
+ if (sbi->gc_mode == GC_URGENT_HIGH) {
wait_ms = gc_th->urgent_sleep_time;
down_write(&sbi->gc_lock);
goto do_gc;
@@ -172,7 +176,7 @@ static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type)
gc_mode = GC_CB;
break;
case GC_IDLE_GREEDY:
- case GC_URGENT:
+ case GC_URGENT_HIGH:
gc_mode = GC_GREEDY;
break;
}
@@ -186,14 +190,20 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
if (p->alloc_mode == SSR) {
p->gc_mode = GC_GREEDY;
- p->dirty_segmap = dirty_i->dirty_segmap[type];
+ p->dirty_bitmap = dirty_i->dirty_segmap[type];
p->max_search = dirty_i->nr_dirty[type];
p->ofs_unit = 1;
} else {
p->gc_mode = select_gc_type(sbi, gc_type);
- p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
- p->max_search = dirty_i->nr_dirty[DIRTY];
p->ofs_unit = sbi->segs_per_sec;
+ if (__is_large_section(sbi)) {
+ p->dirty_bitmap = dirty_i->dirty_secmap;
+ p->max_search = count_bits(p->dirty_bitmap,
+ 0, MAIN_SECS(sbi));
+ } else {
+ p->dirty_bitmap = dirty_i->dirty_segmap[DIRTY];
+ p->max_search = dirty_i->nr_dirty[DIRTY];
+ }
}
/*
@@ -201,7 +211,7 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
* foreground GC and urgent GC cases.
*/
if (gc_type != FG_GC &&
- (sbi->gc_mode != GC_URGENT) &&
+ (sbi->gc_mode != GC_URGENT_HIGH) &&
p->max_search > sbi->max_victim_search)
p->max_search = sbi->max_victim_search;
@@ -320,6 +330,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
unsigned int secno, last_victim;
unsigned int last_segment;
unsigned int nsearched = 0;
+ int ret = 0;
mutex_lock(&dirty_i->seglist_lock);
last_segment = MAIN_SECS(sbi) * sbi->segs_per_sec;
@@ -331,12 +342,19 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
p.min_cost = get_max_cost(sbi, &p);
if (*result != NULL_SEGNO) {
- if (get_valid_blocks(sbi, *result, false) &&
- !sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+ if (!get_valid_blocks(sbi, *result, false)) {
+ ret = -ENODATA;
+ goto out;
+ }
+
+ if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+ ret = -EBUSY;
+ else
p.min_segno = *result;
goto out;
}
+ ret = -ENODATA;
if (p.max_search == 0)
goto out;
@@ -364,10 +382,14 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
}
while (1) {
- unsigned long cost;
- unsigned int segno;
-
- segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
+ unsigned long cost, *dirty_bitmap;
+ unsigned int unit_no, segno;
+
+ dirty_bitmap = p.dirty_bitmap;
+ unit_no = find_next_bit(dirty_bitmap,
+ last_segment / p.ofs_unit,
+ p.offset / p.ofs_unit);
+ segno = unit_no * p.ofs_unit;
if (segno >= last_segment) {
if (sm->last_victim[p.gc_mode]) {
last_segment =
@@ -380,14 +402,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
}
p.offset = segno + p.ofs_unit;
- if (p.ofs_unit > 1) {
- p.offset -= segno % p.ofs_unit;
- nsearched += count_bits(p.dirty_segmap,
- p.offset - p.ofs_unit,
- p.ofs_unit);
- } else {
- nsearched++;
- }
+ nsearched++;
#ifdef CONFIG_F2FS_CHECK_FS
/*
@@ -420,9 +435,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
next:
if (nsearched >= p.max_search) {
if (!sm->last_victim[p.gc_mode] && segno <= last_victim)
- sm->last_victim[p.gc_mode] = last_victim + 1;
+ sm->last_victim[p.gc_mode] =
+ last_victim + p.ofs_unit;
else
- sm->last_victim[p.gc_mode] = segno + 1;
+ sm->last_victim[p.gc_mode] = segno + p.ofs_unit;
sm->last_victim[p.gc_mode] %=
(MAIN_SECS(sbi) * sbi->segs_per_sec);
break;
@@ -439,6 +455,7 @@ got_result:
else
set_bit(secno, dirty_i->victim_secmap);
}
+ ret = 0;
}
out:
@@ -448,7 +465,7 @@ out:
prefree_segments(sbi), free_segments(sbi));
mutex_unlock(&dirty_i->seglist_lock);
- return (p.min_segno == NULL_SEGNO) ? 0 : 1;
+ return ret;
}
static const struct victim_selection default_v_ops = {
@@ -737,6 +754,10 @@ got_it:
goto put_encrypted_page;
f2fs_put_page(fio.encrypted_page, 0);
f2fs_put_page(page, 1);
+
+ f2fs_update_iostat(sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(sbi, FS_GDATA_READ_IO, F2FS_BLKSIZE);
+
return 0;
put_encrypted_page:
f2fs_put_page(fio.encrypted_page, 1);
@@ -828,8 +849,10 @@ static int move_data_block(struct inode *inode, block_t bidx,
mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi),
fio.old_blkaddr, false);
- if (!mpage)
+ if (!mpage) {
+ err = -ENOMEM;
goto up_out;
+ }
fio.encrypted_page = mpage;
@@ -840,6 +863,10 @@ static int move_data_block(struct inode *inode, block_t bidx,
f2fs_put_page(mpage, 1);
goto up_out;
}
+
+ f2fs_update_iostat(fio.sbi, FS_DATA_READ_IO, F2FS_BLKSIZE);
+ f2fs_update_iostat(fio.sbi, FS_GDATA_READ_IO, F2FS_BLKSIZE);
+
lock_page(mpage);
if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) ||
!PageUptodate(mpage))) {
@@ -850,7 +877,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
}
f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
- &sum, CURSEG_COLD_DATA, NULL, false);
+ &sum, CURSEG_COLD_DATA, NULL);
fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS);
@@ -1324,10 +1351,9 @@ gc_more:
ret = -EINVAL;
goto stop;
}
- if (!__get_victim(sbi, &segno, gc_type)) {
- ret = -ENODATA;
+ ret = __get_victim(sbi, &segno, gc_type);
+ if (ret)
goto stop;
- }
seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
@@ -1399,16 +1425,33 @@ void f2fs_build_gc_manager(struct f2fs_sb_info *sbi)
GET_SEGNO(sbi, FDEV(0).end_blk) + 1;
}
-static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start,
- unsigned int end)
+static int free_segment_range(struct f2fs_sb_info *sbi,
+ unsigned int secs, bool gc_only)
{
- int type;
- unsigned int segno, next_inuse;
+ unsigned int segno, next_inuse, start, end;
+ struct cp_control cpc = { CP_RESIZE, 0, 0, 0 };
+ int gc_mode, gc_type;
int err = 0;
+ int type;
+
+ /* Force block allocation for GC */
+ MAIN_SECS(sbi) -= secs;
+ start = MAIN_SECS(sbi) * sbi->segs_per_sec;
+ end = MAIN_SEGS(sbi) - 1;
+
+ mutex_lock(&DIRTY_I(sbi)->seglist_lock);
+ for (gc_mode = 0; gc_mode < MAX_GC_POLICY; gc_mode++)
+ if (SIT_I(sbi)->last_victim[gc_mode] >= start)
+ SIT_I(sbi)->last_victim[gc_mode] = 0;
+
+ for (gc_type = BG_GC; gc_type <= FG_GC; gc_type++)
+ if (sbi->next_victim_seg[gc_type] >= start)
+ sbi->next_victim_seg[gc_type] = NULL_SEGNO;
+ mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
/* Move out cursegs from the target range */
for (type = CURSEG_HOT_DATA; type < NR_CURSEG_TYPE; type++)
- allocate_segment_for_resize(sbi, type, start, end);
+ f2fs_allocate_segment_for_resize(sbi, type, start, end);
/* do GC to move out valid blocks in the range */
for (segno = start; segno <= end; segno += sbi->segs_per_sec) {
@@ -1417,18 +1460,24 @@ static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start,
.iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS),
};
- down_write(&sbi->gc_lock);
do_garbage_collect(sbi, segno, &gc_list, FG_GC);
- up_write(&sbi->gc_lock);
put_gc_inode(&gc_list);
- if (get_valid_blocks(sbi, segno, true))
- return -EAGAIN;
+ if (!gc_only && get_valid_blocks(sbi, segno, true)) {
+ err = -EAGAIN;
+ goto out;
+ }
+ if (fatal_signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto out;
+ }
}
+ if (gc_only)
+ goto out;
- err = f2fs_sync_fs(sbi->sb, 1);
+ err = f2fs_write_checkpoint(sbi, &cpc);
if (err)
- return err;
+ goto out;
next_inuse = find_next_inuse(FREE_I(sbi), end + 1, start);
if (next_inuse <= end) {
@@ -1436,6 +1485,8 @@ static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int start,
next_inuse);
f2fs_bug_on(sbi, 1);
}
+out:
+ MAIN_SECS(sbi) += secs;
return err;
}
@@ -1481,6 +1532,7 @@ static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs)
SM_I(sbi)->segment_count = (int)SM_I(sbi)->segment_count + segs;
MAIN_SEGS(sbi) = (int)MAIN_SEGS(sbi) + segs;
+ MAIN_SECS(sbi) += secs;
FREE_I(sbi)->free_sections = (int)FREE_I(sbi)->free_sections + secs;
FREE_I(sbi)->free_segments = (int)FREE_I(sbi)->free_segments + segs;
F2FS_CKPT(sbi)->user_block_count = cpu_to_le64(user_block_count + blks);
@@ -1502,8 +1554,8 @@ static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs)
int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
{
__u64 old_block_count, shrunk_blocks;
+ struct cp_control cpc = { CP_RESIZE, 0, 0, 0 };
unsigned int secs;
- int gc_mode, gc_type;
int err = 0;
__u32 rem;
@@ -1538,10 +1590,27 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
return -EINVAL;
}
- freeze_bdev(sbi->sb->s_bdev);
-
shrunk_blocks = old_block_count - block_count;
secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi));
+
+ /* stop other GC */
+ if (!down_write_trylock(&sbi->gc_lock))
+ return -EAGAIN;
+
+ /* stop CP to protect MAIN_SEC in free_segment_range */
+ f2fs_lock_op(sbi);
+ err = free_segment_range(sbi, secs, true);
+ f2fs_unlock_op(sbi);
+ up_write(&sbi->gc_lock);
+ if (err)
+ return err;
+
+ set_sbi_flag(sbi, SBI_IS_RESIZEFS);
+
+ freeze_super(sbi->sb);
+ down_write(&sbi->gc_lock);
+ mutex_lock(&sbi->cp_mutex);
+
spin_lock(&sbi->stat_lock);
if (shrunk_blocks + valid_user_blocks(sbi) +
sbi->current_reserved_blocks + sbi->unusable_block_count +
@@ -1550,69 +1619,44 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count)
else
sbi->user_block_count -= shrunk_blocks;
spin_unlock(&sbi->stat_lock);
- if (err) {
- thaw_bdev(sbi->sb->s_bdev, sbi->sb);
- return err;
- }
-
- mutex_lock(&sbi->resize_mutex);
- set_sbi_flag(sbi, SBI_IS_RESIZEFS);
-
- mutex_lock(&DIRTY_I(sbi)->seglist_lock);
-
- MAIN_SECS(sbi) -= secs;
-
- for (gc_mode = 0; gc_mode < MAX_GC_POLICY; gc_mode++)
- if (SIT_I(sbi)->last_victim[gc_mode] >=
- MAIN_SECS(sbi) * sbi->segs_per_sec)
- SIT_I(sbi)->last_victim[gc_mode] = 0;
-
- for (gc_type = BG_GC; gc_type <= FG_GC; gc_type++)
- if (sbi->next_victim_seg[gc_type] >=
- MAIN_SECS(sbi) * sbi->segs_per_sec)
- sbi->next_victim_seg[gc_type] = NULL_SEGNO;
-
- mutex_unlock(&DIRTY_I(sbi)->seglist_lock);
+ if (err)
+ goto out_err;
- err = free_segment_range(sbi, MAIN_SECS(sbi) * sbi->segs_per_sec,
- MAIN_SEGS(sbi) - 1);
+ err = free_segment_range(sbi, secs, false);
if (err)
- goto out;
+ goto recover_out;
update_sb_metadata(sbi, -secs);
err = f2fs_commit_super(sbi, false);
if (err) {
update_sb_metadata(sbi, secs);
- goto out;
+ goto recover_out;
}
- mutex_lock(&sbi->cp_mutex);
update_fs_metadata(sbi, -secs);
clear_sbi_flag(sbi, SBI_IS_RESIZEFS);
set_sbi_flag(sbi, SBI_IS_DIRTY);
- mutex_unlock(&sbi->cp_mutex);
- err = f2fs_sync_fs(sbi->sb, 1);
+ err = f2fs_write_checkpoint(sbi, &cpc);
if (err) {
- mutex_lock(&sbi->cp_mutex);
update_fs_metadata(sbi, secs);
- mutex_unlock(&sbi->cp_mutex);
update_sb_metadata(sbi, secs);
f2fs_commit_super(sbi, false);
}
-out:
+recover_out:
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_err(sbi, "resize_fs failed, should run fsck to repair!");
- MAIN_SECS(sbi) += secs;
spin_lock(&sbi->stat_lock);
sbi->user_block_count += shrunk_blocks;
spin_unlock(&sbi->stat_lock);
}
+out_err:
+ mutex_unlock(&sbi->cp_mutex);
+ up_write(&sbi->gc_lock);
+ thaw_super(sbi->sb);
clear_sbi_flag(sbi, SBI_IS_RESIZEFS);
- mutex_unlock(&sbi->resize_mutex);
- thaw_bdev(sbi->sb->s_bdev, sbi->sb);
return err;
}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index bbac9d3787bd..db3c61046aa4 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* fs/f2fs/gc.h
*
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 5bc4dcd8fc03..de841aaf3c43 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -12,7 +12,6 @@
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
-#include <linux/cryptohash.h>
#include <linux/pagemap.h>
#include <linux/unicode.h>
@@ -68,22 +67,9 @@ static void str2hashbuf(const unsigned char *msg, size_t len,
*buf++ = pad;
}
-static f2fs_hash_t __f2fs_dentry_hash(const struct qstr *name_info,
- struct fscrypt_name *fname)
+static u32 TEA_hash_name(const u8 *p, size_t len)
{
- __u32 hash;
- f2fs_hash_t f2fs_hash;
- const unsigned char *p;
__u32 in[8], buf[4];
- const unsigned char *name = name_info->name;
- size_t len = name_info->len;
-
- /* encrypted bigname case */
- if (fname && !fname->disk_name.name)
- return cpu_to_le32(fname->hash);
-
- if (is_dot_dotdot(name_info))
- return 0;
/* Initialize the default seed for the hash checksum functions */
buf[0] = 0x67452301;
@@ -91,7 +77,6 @@ static f2fs_hash_t __f2fs_dentry_hash(const struct qstr *name_info,
buf[2] = 0x98badcfe;
buf[3] = 0x10325476;
- p = name;
while (1) {
str2hashbuf(p, len, in, 4);
TEA_transform(buf, in);
@@ -100,41 +85,43 @@ static f2fs_hash_t __f2fs_dentry_hash(const struct qstr *name_info,
break;
len -= 16;
}
- hash = buf[0];
- f2fs_hash = cpu_to_le32(hash & ~F2FS_HASH_COL_BIT);
- return f2fs_hash;
+ return buf[0] & ~F2FS_HASH_COL_BIT;
}
-f2fs_hash_t f2fs_dentry_hash(const struct inode *dir,
- const struct qstr *name_info, struct fscrypt_name *fname)
+/*
+ * Compute @fname->hash. For all directories, @fname->disk_name must be set.
+ * For casefolded directories, @fname->usr_fname must be set, and also
+ * @fname->cf_name if the filename is valid Unicode.
+ */
+void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
{
-#ifdef CONFIG_UNICODE
- struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
- const struct unicode_map *um = sbi->s_encoding;
- int r, dlen;
- unsigned char *buff;
- struct qstr folded;
+ const u8 *name = fname->disk_name.name;
+ size_t len = fname->disk_name.len;
- if (!name_info->len || !IS_CASEFOLDED(dir))
- goto opaque_seq;
+ WARN_ON_ONCE(!name);
- buff = f2fs_kzalloc(sbi, sizeof(char) * PATH_MAX, GFP_KERNEL);
- if (!buff)
- return -ENOMEM;
-
- dlen = utf8_casefold(um, name_info, buff, PATH_MAX);
- if (dlen < 0) {
- kvfree(buff);
- goto opaque_seq;
+ if (is_dot_dotdot(name, len)) {
+ fname->hash = 0;
+ return;
}
- folded.name = buff;
- folded.len = dlen;
- r = __f2fs_dentry_hash(&folded, fname);
-
- kvfree(buff);
- return r;
-opaque_seq:
+#ifdef CONFIG_UNICODE
+ if (IS_CASEFOLDED(dir)) {
+ /*
+ * If the casefolded name is provided, hash it instead of the
+ * on-disk name. If the casefolded name is *not* provided, that
+ * should only be because the name wasn't valid Unicode, so fall
+ * back to treating the name as an opaque byte sequence.
+ */
+ WARN_ON_ONCE(!fname->usr_fname->name);
+ if (fname->cf_name.name) {
+ name = fname->cf_name.name;
+ len = fname->cf_name.len;
+ } else {
+ name = fname->usr_fname->name;
+ len = fname->usr_fname->len;
+ }
+ }
#endif
- return __f2fs_dentry_hash(name_info, fname);
+ fname->hash = cpu_to_le32(TEA_hash_name(name, len));
}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 4167e5408151..102df444f623 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -8,9 +8,11 @@
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
+#include <linux/fiemap.h>
#include "f2fs.h"
#include "node.h"
+#include <trace/events/f2fs.h>
bool f2fs_may_inline_data(struct inode *inode)
{
@@ -252,7 +254,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
return 0;
}
-bool f2fs_recover_inline_data(struct inode *inode, struct page *npage)
+int f2fs_recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
@@ -274,7 +276,8 @@ bool f2fs_recover_inline_data(struct inode *inode, struct page *npage)
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
ipage = f2fs_get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(sbi, IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true, true);
@@ -287,33 +290,36 @@ process_inline:
set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
- return true;
+ return 1;
}
if (f2fs_has_inline_data(inode)) {
ipage = f2fs_get_node_page(sbi, inode->i_ino);
- f2fs_bug_on(sbi, IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
f2fs_truncate_inline_inode(inode, ipage, 0);
clear_inode_flag(inode, FI_INLINE_DATA);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
- if (f2fs_truncate_blocks(inode, 0, false))
- return false;
+ int ret;
+
+ ret = f2fs_truncate_blocks(inode, 0, false);
+ if (ret)
+ return ret;
goto process_inline;
}
- return false;
+ return 0;
}
struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
- struct fscrypt_name *fname, struct page **res_page)
+ const struct f2fs_filename *fname,
+ struct page **res_page)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
- struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
struct f2fs_dir_entry *de;
struct f2fs_dentry_ptr d;
struct page *ipage;
void *inline_dentry;
- f2fs_hash_t namehash;
ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage)) {
@@ -321,12 +327,10 @@ struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir,
return NULL;
}
- namehash = f2fs_dentry_hash(dir, &name, fname);
-
inline_dentry = inline_data_addr(dir, ipage);
make_dentry_ptr_inline(dir, &d, inline_dentry);
- de = f2fs_find_target_dentry(fname, namehash, NULL, &d);
+ de = f2fs_find_target_dentry(&d, fname, NULL);
unlock_page(ipage);
if (de)
*res_page = ipage;
@@ -443,7 +447,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry)
while (bit_pos < d.max) {
struct f2fs_dir_entry *de;
- struct qstr new_name;
+ struct f2fs_filename fname;
nid_t ino;
umode_t fake_mode;
@@ -459,14 +463,19 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry)
continue;
}
- new_name.name = d.filename[bit_pos];
- new_name.len = le16_to_cpu(de->name_len);
+ /*
+ * We only need the disk_name and hash to move the dentry.
+ * We don't need the original or casefolded filenames.
+ */
+ memset(&fname, 0, sizeof(fname));
+ fname.disk_name.name = d.filename[bit_pos];
+ fname.disk_name.len = le16_to_cpu(de->name_len);
+ fname.hash = de->hash_code;
ino = le32_to_cpu(de->ino);
fake_mode = f2fs_get_de_type(de) << S_SHIFT;
- err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL,
- ino, fake_mode);
+ err = f2fs_add_regular_entry(dir, &fname, NULL, ino, fake_mode);
if (err)
goto punch_dentry_pages;
@@ -543,7 +552,7 @@ int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
- struct fscrypt_name fname;
+ struct f2fs_filename fname;
void *inline_dentry = NULL;
int err = 0;
@@ -552,19 +561,19 @@ int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry)
f2fs_lock_op(sbi);
- err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &fname);
+ err = f2fs_setup_filename(dir, &dentry->d_name, 0, &fname);
if (err)
goto out;
ipage = f2fs_get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
- goto out;
+ goto out_fname;
}
if (f2fs_has_enough_room(dir, ipage, &fname)) {
f2fs_put_page(ipage, 1);
- goto out;
+ goto out_fname;
}
inline_dentry = inline_data_addr(dir, ipage);
@@ -572,22 +581,22 @@ int f2fs_try_convert_inline_dir(struct inode *dir, struct dentry *dentry)
err = do_convert_inline_dir(dir, ipage, inline_dentry);
if (!err)
f2fs_put_page(ipage, 1);
+out_fname:
+ f2fs_free_filename(&fname);
out:
f2fs_unlock_op(sbi);
return err;
}
-int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
- const struct qstr *orig_name,
- struct inode *inode, nid_t ino, umode_t mode)
+int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
+ struct inode *inode, nid_t ino, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
unsigned int bit_pos;
- f2fs_hash_t name_hash;
void *inline_dentry = NULL;
struct f2fs_dentry_ptr d;
- int slots = GET_DENTRY_SLOTS(new_name->len);
+ int slots = GET_DENTRY_SLOTS(fname->disk_name.len);
struct page *page = NULL;
int err = 0;
@@ -609,8 +618,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
- page = f2fs_init_inode_metadata(inode, dir, new_name,
- orig_name, ipage);
+ page = f2fs_init_inode_metadata(inode, dir, fname, ipage);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
@@ -619,8 +627,8 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
f2fs_wait_on_page_writeback(ipage, NODE, true, true);
- name_hash = f2fs_dentry_hash(dir, new_name, NULL);
- f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
+ f2fs_update_dentry(ino, mode, &d, &fname->disk_name, fname->hash,
+ bit_pos);
set_page_dirty(ipage);
@@ -774,6 +782,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
byteaddr += (char *)inline_data_addr(inode, ipage) -
(char *)F2FS_INODE(ipage);
err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
+ trace_f2fs_fiemap(inode, start, byteaddr, ilen, flags, err);
out:
f2fs_put_page(ipage, 1);
return err;
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 44582a4db513..66969ae852b9 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -367,8 +367,7 @@ static int do_read_inode(struct inode *inode)
fi->i_pino = le32_to_cpu(ri->i_pino);
fi->i_dir_level = ri->i_dir_level;
- if (f2fs_init_extent_tree(inode, &ri->i_ext))
- set_page_dirty(node_page);
+ f2fs_init_extent_tree(inode, node_page);
get_inline_info(inode, ri);
@@ -402,6 +401,7 @@ static int do_read_inode(struct inode *inode)
/* try to recover cold bit for non-dir inode */
if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) {
+ f2fs_wait_on_page_writeback(node_page, NODE, true, true);
set_cold_node(node_page, false);
set_page_dirty(node_page);
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index f54119da2217..84e4bbc1a64d 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -482,7 +482,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
nid_t ino = -1;
int err = 0;
unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
- struct fscrypt_name fname;
+ struct f2fs_filename fname;
trace_f2fs_lookup_start(dir, dentry, flags);
@@ -491,19 +491,20 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- err = fscrypt_prepare_lookup(dir, dentry, &fname);
+ err = f2fs_prepare_lookup(dir, dentry, &fname);
if (err == -ENOENT)
goto out_splice;
if (err)
goto out;
de = __f2fs_find_entry(dir, &fname, &page);
- fscrypt_free_filename(&fname);
+ f2fs_free_filename(&fname);
if (!de) {
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out;
}
+ err = -ENOENT;
goto out_splice;
}
@@ -549,7 +550,7 @@ out_splice:
#endif
new = d_splice_alias(inode, dentry);
err = PTR_ERR_OR_ZERO(new);
- trace_f2fs_lookup_end(dir, dentry, ino, err);
+ trace_f2fs_lookup_end(dir, dentry, ino, !new ? -ENOENT : err);
return new;
out_iput:
iput(inode);
@@ -564,19 +565,21 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
struct inode *inode = d_inode(dentry);
struct f2fs_dir_entry *de;
struct page *page;
- int err = -ENOENT;
+ int err;
trace_f2fs_unlink_enter(dir, dentry);
- if (unlikely(f2fs_cp_error(sbi)))
- return -EIO;
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto fail;
+ }
err = dquot_initialize(dir);
if (err)
- return err;
+ goto fail;
err = dquot_initialize(inode);
if (err)
- return err;
+ goto fail;
de = f2fs_find_entry(dir, &dentry->d_name, &page);
if (!de) {
@@ -599,7 +602,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
- * negative dentries at f2fs_lookup(), when it is better
+ * negative dentries at f2fs_lookup(), when it is better
* supported by the VFS for the CI case.
*/
if (IS_CASEFOLDED(dir))
@@ -1284,12 +1287,10 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
}
const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
- .get_link = f2fs_encrypted_get_link,
+ .get_link = f2fs_encrypted_get_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
-#ifdef CONFIG_F2FS_FS_XATTR
.listxattr = f2fs_listxattr,
-#endif
};
const struct inode_operations f2fs_dir_inode_operations = {
@@ -1307,27 +1308,21 @@ const struct inode_operations f2fs_dir_inode_operations = {
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
-#ifdef CONFIG_F2FS_FS_XATTR
.listxattr = f2fs_listxattr,
-#endif
.fiemap = f2fs_fiemap,
};
const struct inode_operations f2fs_symlink_inode_operations = {
- .get_link = f2fs_get_link,
+ .get_link = f2fs_get_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
-#ifdef CONFIG_F2FS_FS_XATTR
.listxattr = f2fs_listxattr,
-#endif
};
const struct inode_operations f2fs_special_inode_operations = {
.getattr = f2fs_getattr,
- .setattr = f2fs_setattr,
+ .setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
.set_acl = f2fs_set_acl,
-#ifdef CONFIG_F2FS_FS_XATTR
.listxattr = f2fs_listxattr,
-#endif
};
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index ecbd6bd14a49..cb1b5b61a1da 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -618,10 +618,10 @@ pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
switch (dn->max_level) {
case 3:
base += 2 * indirect_blks;
- /* fall through */
+ fallthrough;
case 2:
base += 2 * direct_blks;
- /* fall through */
+ fallthrough;
case 1:
base += direct_index;
break;
@@ -1041,8 +1041,10 @@ int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from)
trace_f2fs_truncate_inode_blocks_enter(inode, from);
level = get_node_path(inode, from, offset, noffset);
- if (level < 0)
+ if (level < 0) {
+ trace_f2fs_truncate_inode_blocks_exit(inode, level);
return level;
+ }
page = f2fs_get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
@@ -1300,7 +1302,13 @@ static int read_node_page(struct page *page, int op_flags)
}
fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr;
- return f2fs_submit_page_bio(&fio);
+
+ err = f2fs_submit_page_bio(&fio);
+
+ if (!err)
+ f2fs_update_iostat(sbi, FS_NODE_READ_IO, F2FS_BLKSIZE);
+
+ return err;
}
/*
@@ -1514,8 +1522,15 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
trace_f2fs_writepage(page, NODE);
- if (unlikely(f2fs_cp_error(sbi)))
+ if (unlikely(f2fs_cp_error(sbi))) {
+ if (is_sbi_flag_set(sbi, SBI_IS_CLOSE)) {
+ ClearPageUptodate(page);
+ dec_page_count(sbi, F2FS_DIRTY_NODES);
+ unlock_page(page);
+ return 0;
+ }
goto redirty_out;
+ }
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
@@ -1713,7 +1728,7 @@ continue_unlock:
set_dentry_mark(page,
f2fs_need_dentry_mark(sbi, ino));
}
- /* may be written by other thread */
+ /* may be written by other thread */
if (!PageDirty(page))
set_page_dirty(page);
}
@@ -1801,6 +1816,51 @@ static bool flush_dirty_inode(struct page *page)
return true;
}
+void f2fs_flush_inline_data(struct f2fs_sb_info *sbi)
+{
+ pgoff_t index = 0;
+ struct pagevec pvec;
+ int nr_pages;
+
+ pagevec_init(&pvec);
+
+ while ((nr_pages = pagevec_lookup_tag(&pvec,
+ NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY))) {
+ int i;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+
+ if (!IS_DNODE(page))
+ continue;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+
+ if (!PageDirty(page)) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ /* flush inline_data, if it's async context. */
+ if (is_inline_node(page)) {
+ clear_inline_node(page);
+ unlock_page(page);
+ flush_inline_data(sbi, ino_of_node(page));
+ continue;
+ }
+ unlock_page(page);
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+}
+
int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
struct writeback_control *wbc,
bool do_balance, enum iostat_type io_type)
@@ -1864,6 +1924,10 @@ continue_unlock:
goto continue_unlock;
}
+ /* flush inline_data/inode, if it's async context. */
+ if (!do_balance)
+ goto write_node;
+
/* flush inline_data */
if (is_inline_node(page)) {
clear_inline_node(page);
@@ -1878,7 +1942,7 @@ continue_unlock:
if (flush_dirty_inode(page))
goto lock_node;
}
-
+write_node:
f2fs_wait_on_page_writeback(page, NODE, true, true);
if (!clear_page_dirty_for_io(page))
@@ -2037,7 +2101,7 @@ const struct address_space_operations f2fs_node_aops = {
.invalidatepage = f2fs_invalidate_page,
.releasepage = f2fs_release_page,
#ifdef CONFIG_MIGRATION
- .migratepage = f2fs_migrate_page,
+ .migratepage = f2fs_migrate_page,
#endif
};
@@ -2048,7 +2112,7 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
}
static int __insert_free_nid(struct f2fs_sb_info *sbi,
- struct free_nid *i, enum nid_state state)
+ struct free_nid *i)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
@@ -2056,10 +2120,8 @@ static int __insert_free_nid(struct f2fs_sb_info *sbi,
if (err)
return err;
- f2fs_bug_on(sbi, state != i->state);
- nm_i->nid_cnt[state]++;
- if (state == FREE_NID)
- list_add_tail(&i->list, &nm_i->free_nid_list);
+ nm_i->nid_cnt[FREE_NID]++;
+ list_add_tail(&i->list, &nm_i->free_nid_list);
return 0;
}
@@ -2181,7 +2243,7 @@ static bool add_free_nid(struct f2fs_sb_info *sbi,
}
}
ret = true;
- err = __insert_free_nid(sbi, i, FREE_NID);
+ err = __insert_free_nid(sbi, i);
err_out:
if (update) {
update_free_nid_bitmap(sbi, nid, ret, build);
@@ -2311,6 +2373,9 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi,
if (unlikely(nid >= nm_i->max_nid))
nid = 0;
+ if (unlikely(nid % NAT_ENTRY_PER_BLOCK))
+ nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK;
+
/* Enough entries */
if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK)
return 0;
@@ -2482,7 +2547,6 @@ void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct free_nid *i, *next;
int nr = nr_shrink;
if (nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS)
@@ -2491,23 +2555,29 @@ int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
if (!mutex_trylock(&nm_i->build_lock))
return 0;
- spin_lock(&nm_i->nid_list_lock);
- list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
- if (nr_shrink <= 0 ||
- nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS)
- break;
+ while (nr_shrink && nm_i->nid_cnt[FREE_NID] > MAX_FREE_NIDS) {
+ struct free_nid *i, *next;
+ unsigned int batch = SHRINK_NID_BATCH_SIZE;
- __remove_free_nid(sbi, i, FREE_NID);
- kmem_cache_free(free_nid_slab, i);
- nr_shrink--;
+ spin_lock(&nm_i->nid_list_lock);
+ list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) {
+ if (!nr_shrink || !batch ||
+ nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS)
+ break;
+ __remove_free_nid(sbi, i, FREE_NID);
+ kmem_cache_free(free_nid_slab, i);
+ nr_shrink--;
+ batch--;
+ }
+ spin_unlock(&nm_i->nid_list_lock);
}
- spin_unlock(&nm_i->nid_list_lock);
+
mutex_unlock(&nm_i->build_lock);
return nr - nr_shrink;
}
-void f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
+int f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
size_t inline_size;
@@ -2515,7 +2585,8 @@ void f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
struct f2fs_inode *ri;
ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino);
- f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage));
+ if (IS_ERR(ipage))
+ return PTR_ERR(ipage);
ri = F2FS_INODE(page);
if (ri->i_inline & F2FS_INLINE_XATTR) {
@@ -2534,6 +2605,7 @@ void f2fs_recover_inline_xattr(struct inode *inode, struct page *page)
update_inode:
f2fs_update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
+ return 0;
}
int f2fs_recover_xattr_data(struct inode *inode, struct page *page)
@@ -2928,7 +3000,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
return 0;
nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8);
- nm_i->nat_bits = f2fs_kzalloc(sbi,
+ nm_i->nat_bits = f2fs_kvzalloc(sbi,
nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL);
if (!nm_i->nat_bits)
return -ENOMEM;
@@ -3061,9 +3133,9 @@ static int init_free_nid_cache(struct f2fs_sb_info *sbi)
int i;
nm_i->free_nid_bitmap =
- f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *),
- nm_i->nat_blocks),
- GFP_KERNEL);
+ f2fs_kvzalloc(sbi, array_size(sizeof(unsigned char *),
+ nm_i->nat_blocks),
+ GFP_KERNEL);
if (!nm_i->free_nid_bitmap)
return -ENOMEM;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index e05af5df5648..69e5859e993c 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* fs/f2fs/node.h
*
@@ -15,6 +15,9 @@
#define FREE_NID_PAGES 8
#define MAX_FREE_NIDS (NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
+/* size of free nid batch when shrinking */
+#define SHRINK_NID_BATCH_SIZE 8
+
#define DEF_RA_NID_PAGES 0 /* # of nid pages to be readaheaded */
/* maximum readahead size for node during getting data blocks */
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index dd804c07eeb0..4f12ade6410a 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -107,13 +107,51 @@ static void del_fsync_inode(struct fsync_inode_entry *entry, int drop)
kmem_cache_free(fsync_entry_slab, entry);
}
+static int init_recovered_filename(const struct inode *dir,
+ struct f2fs_inode *raw_inode,
+ struct f2fs_filename *fname,
+ struct qstr *usr_fname)
+{
+ int err;
+
+ memset(fname, 0, sizeof(*fname));
+ fname->disk_name.len = le32_to_cpu(raw_inode->i_namelen);
+ fname->disk_name.name = raw_inode->i_name;
+
+ if (WARN_ON(fname->disk_name.len > F2FS_NAME_LEN))
+ return -ENAMETOOLONG;
+
+ if (!IS_ENCRYPTED(dir)) {
+ usr_fname->name = fname->disk_name.name;
+ usr_fname->len = fname->disk_name.len;
+ fname->usr_fname = usr_fname;
+ }
+
+ /* Compute the hash of the filename */
+ if (IS_CASEFOLDED(dir)) {
+ err = f2fs_init_casefolded_name(dir, fname);
+ if (err)
+ return err;
+ f2fs_hash_filename(dir, fname);
+#ifdef CONFIG_UNICODE
+ /* Case-sensitive match is fine for recovery */
+ kfree(fname->cf_name.name);
+ fname->cf_name.name = NULL;
+#endif
+ } else {
+ f2fs_hash_filename(dir, fname);
+ }
+ return 0;
+}
+
static int recover_dentry(struct inode *inode, struct page *ipage,
struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
struct f2fs_dir_entry *de;
- struct fscrypt_name fname;
+ struct f2fs_filename fname;
+ struct qstr usr_fname;
struct page *page;
struct inode *dir, *einode;
struct fsync_inode_entry *entry;
@@ -132,16 +170,9 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
}
dir = entry->inode;
-
- memset(&fname, 0, sizeof(struct fscrypt_name));
- fname.disk_name.len = le32_to_cpu(raw_inode->i_namelen);
- fname.disk_name.name = raw_inode->i_name;
-
- if (unlikely(fname.disk_name.len > F2FS_NAME_LEN)) {
- WARN_ON(1);
- err = -ENAMETOOLONG;
+ err = init_recovered_filename(dir, raw_inode, &fname, &usr_fname);
+ if (err)
goto out;
- }
retry:
de = __f2fs_find_entry(dir, &fname, &page);
if (de && inode->i_ino == le32_to_cpu(de->ino))
@@ -513,7 +544,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
/* step 1: recover xattr */
if (IS_INODE(page)) {
- f2fs_recover_inline_xattr(inode, page);
+ err = f2fs_recover_inline_xattr(inode, page);
+ if (err)
+ goto out;
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
err = f2fs_recover_xattr_data(inode, page);
if (!err)
@@ -522,8 +555,12 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
}
/* step 2: recover inline data */
- if (f2fs_recover_inline_data(inode, page))
+ err = f2fs_recover_inline_data(inode, page);
+ if (err) {
+ if (err == 1)
+ err = 0;
goto out;
+ }
/* step 3: recover data indices */
start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
@@ -711,7 +748,7 @@ next:
f2fs_put_page(page, 1);
}
if (!err)
- f2fs_allocate_new_segments(sbi, NO_CHECK_TYPE);
+ f2fs_allocate_new_segments(sbi);
return err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index b7a9421472a7..e247a5ef3713 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -174,7 +174,7 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi)
if (f2fs_lfs_mode(sbi))
return false;
- if (sbi->gc_mode == GC_URGENT)
+ if (sbi->gc_mode == GC_URGENT_HIGH)
return true;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED)))
return true;
@@ -796,6 +796,18 @@ static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
}
if (!test_and_set_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]++;
+
+ if (__is_large_section(sbi)) {
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ block_t valid_blocks =
+ get_valid_blocks(sbi, segno, true);
+
+ f2fs_bug_on(sbi, unlikely(!valid_blocks ||
+ valid_blocks == BLKS_PER_SEC(sbi)));
+
+ if (!IS_CURSEC(sbi, secno))
+ set_bit(secno, dirty_i->dirty_secmap);
+ }
}
}
@@ -803,6 +815,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
enum dirty_type dirty_type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ block_t valid_blocks;
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[dirty_type]))
dirty_i->nr_dirty[dirty_type]--;
@@ -814,13 +827,26 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]--;
- if (get_valid_blocks(sbi, segno, true) == 0) {
+ valid_blocks = get_valid_blocks(sbi, segno, true);
+ if (valid_blocks == 0) {
clear_bit(GET_SEC_FROM_SEG(sbi, segno),
dirty_i->victim_secmap);
#ifdef CONFIG_F2FS_CHECK_FS
clear_bit(segno, SIT_I(sbi)->invalid_segmap);
#endif
}
+ if (__is_large_section(sbi)) {
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
+ if (!valid_blocks ||
+ valid_blocks == BLKS_PER_SEC(sbi)) {
+ clear_bit(secno, dirty_i->dirty_secmap);
+ return;
+ }
+
+ if (!IS_CURSEC(sbi, secno))
+ set_bit(secno, dirty_i->dirty_secmap);
+ }
}
}
@@ -1029,9 +1055,9 @@ static void f2fs_submit_discard_endio(struct bio *bio)
struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
unsigned long flags;
- dc->error = blk_status_to_errno(bio->bi_status);
-
spin_lock_irqsave(&dc->lock, flags);
+ if (!dc->error)
+ dc->error = blk_status_to_errno(bio->bi_status);
dc->bio_ref--;
if (!dc->bio_ref && dc->state == D_SUBMIT) {
dc->state = D_DONE;
@@ -1101,7 +1127,6 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi,
} else if (discard_type == DPOLICY_FSTRIM) {
dpolicy->io_aware = false;
} else if (discard_type == DPOLICY_UMOUNT) {
- dpolicy->max_requests = UINT_MAX;
dpolicy->io_aware = false;
/* we need to issue all to keep CP_TRIMMED_FLAG */
dpolicy->granularity = 1;
@@ -1215,12 +1240,14 @@ submit:
len = total_len;
}
- if (!err && len)
+ if (!err && len) {
+ dcc->undiscard_blks -= len;
__update_discard_tree_range(sbi, bdev, lstart, start, len);
+ }
return err;
}
-static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
+static void __insert_discard_tree(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t lstart,
block_t start, block_t len,
struct rb_node **insert_p,
@@ -1229,7 +1256,6 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct rb_node **p;
struct rb_node *parent = NULL;
- struct discard_cmd *dc = NULL;
bool leftmost = true;
if (insert_p && insert_parent) {
@@ -1241,12 +1267,8 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent,
lstart, &leftmost);
do_insert:
- dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent,
+ __attach_discard_cmd(sbi, bdev, lstart, start, len, parent,
p, leftmost);
- if (!dc)
- return NULL;
-
- return dc;
}
static void __relocate_discard_cmd(struct discard_cmd_control *dcc,
@@ -1463,6 +1485,8 @@ next:
return issued;
}
+static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_policy *dpolicy);
static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
struct discard_policy *dpolicy)
@@ -1471,12 +1495,14 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi,
struct list_head *pend_list;
struct discard_cmd *dc, *tmp;
struct blk_plug plug;
- int i, issued = 0;
+ int i, issued;
bool io_interrupted = false;
if (dpolicy->timeout)
f2fs_update_time(sbi, UMOUNT_DISCARD_TIMEOUT);
+retry:
+ issued = 0;
for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
if (dpolicy->timeout &&
f2fs_time_over(sbi, UMOUNT_DISCARD_TIMEOUT))
@@ -1523,6 +1549,11 @@ next:
break;
}
+ if (dpolicy->type == DPOLICY_UMOUNT && issued) {
+ __wait_all_discard_cmd(sbi, dpolicy);
+ goto retry;
+ }
+
if (!issued && io_interrupted)
issued = -1;
@@ -1728,7 +1759,7 @@ static int issue_discard_thread(void *data)
continue;
}
- if (sbi->gc_mode == GC_URGENT)
+ if (sbi->gc_mode == GC_URGENT_HIGH)
__init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1);
sb_start_intwrite(sbi->sb);
@@ -2135,7 +2166,7 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
new_vblocks = se->valid_blocks + del;
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
- f2fs_bug_on(sbi, (new_vblocks >> (sizeof(unsigned short) << 3) ||
+ f2fs_bug_on(sbi, (new_vblocks < 0 ||
(new_vblocks > sbi->blocks_per_seg)));
se->valid_blocks = new_vblocks;
@@ -2600,7 +2631,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
bool reversed = false;
/* f2fs_need_SSR() already forces to do this */
- if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
+ if (!v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
curseg->next_segno = segno;
return 1;
}
@@ -2627,7 +2658,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
for (; cnt-- > 0; reversed ? i-- : i++) {
if (i == type)
continue;
- if (v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
+ if (!v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
curseg->next_segno = segno;
return 1;
}
@@ -2669,7 +2700,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
stat_inc_seg_type(sbi, curseg);
}
-void allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
+void f2fs_allocate_segment_for_resize(struct f2fs_sb_info *sbi, int type,
unsigned int start, unsigned int end)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -2702,28 +2733,35 @@ unlock:
up_read(&SM_I(sbi)->curseg_lock);
}
-void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi, int type)
+static void __allocate_new_segment(struct f2fs_sb_info *sbi, int type)
{
- struct curseg_info *curseg;
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
unsigned int old_segno;
- int i;
- down_write(&SIT_I(sbi)->sentry_lock);
+ if (!curseg->next_blkoff &&
+ !get_valid_blocks(sbi, curseg->segno, false) &&
+ !get_ckpt_valid_blocks(sbi, curseg->segno))
+ return;
- for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
- if (type != NO_CHECK_TYPE && i != type)
- continue;
+ old_segno = curseg->segno;
+ SIT_I(sbi)->s_ops->allocate_segment(sbi, type, true);
+ locate_dirty_segment(sbi, old_segno);
+}
- curseg = CURSEG_I(sbi, i);
- if (type == NO_CHECK_TYPE || curseg->next_blkoff ||
- get_valid_blocks(sbi, curseg->segno, false) ||
- get_ckpt_valid_blocks(sbi, curseg->segno)) {
- old_segno = curseg->segno;
- SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
- locate_dirty_segment(sbi, old_segno);
- }
- }
+void f2fs_allocate_new_segment(struct f2fs_sb_info *sbi, int type)
+{
+ down_write(&SIT_I(sbi)->sentry_lock);
+ __allocate_new_segment(sbi, type);
+ up_write(&SIT_I(sbi)->sentry_lock);
+}
+
+void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi)
+{
+ int i;
+ down_write(&SIT_I(sbi)->sentry_lock);
+ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++)
+ __allocate_new_segment(sbi, i);
up_write(&SIT_I(sbi)->sentry_lock);
}
@@ -3084,7 +3122,7 @@ static int __get_segment_type(struct f2fs_io_info *fio)
void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
block_t old_blkaddr, block_t *new_blkaddr,
struct f2fs_summary *sum, int type,
- struct f2fs_io_info *fio, bool add_list)
+ struct f2fs_io_info *fio)
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -3152,7 +3190,7 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
if (F2FS_IO_ALIGNED(sbi))
fio->retry = false;
- if (add_list) {
+ if (fio) {
struct f2fs_bio_info *io;
INIT_LIST_HEAD(&fio->list);
@@ -3201,7 +3239,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
down_read(&fio->sbi->io_order_lock);
reallocate:
f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
- &fio->new_blkaddr, sum, type, fio, true);
+ &fio->new_blkaddr, sum, type, fio);
if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO)
invalidate_mapping_pages(META_MAPPING(fio->sbi),
fio->old_blkaddr, fio->old_blkaddr);
@@ -4277,8 +4315,9 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int segno = 0, offset = 0;
- unsigned short valid_blocks;
+ unsigned int segno = 0, offset = 0, secno;
+ block_t valid_blocks;
+ block_t blks_per_sec = BLKS_PER_SEC(sbi);
while (1) {
/* find dirty segment based on free segmap */
@@ -4297,6 +4336,22 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
__locate_dirty_segment(sbi, segno, DIRTY);
mutex_unlock(&dirty_i->seglist_lock);
}
+
+ if (!__is_large_section(sbi))
+ return;
+
+ mutex_lock(&dirty_i->seglist_lock);
+ for (segno = 0; segno < MAIN_SECS(sbi); segno += blks_per_sec) {
+ valid_blocks = get_valid_blocks(sbi, segno, true);
+ secno = GET_SEC_FROM_SEG(sbi, segno);
+
+ if (!valid_blocks || valid_blocks == blks_per_sec)
+ continue;
+ if (IS_CURSEC(sbi, secno))
+ continue;
+ set_bit(secno, dirty_i->dirty_secmap);
+ }
+ mutex_unlock(&dirty_i->seglist_lock);
}
static int init_victim_secmap(struct f2fs_sb_info *sbi)
@@ -4333,6 +4388,14 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
return -ENOMEM;
}
+ if (__is_large_section(sbi)) {
+ bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
+ dirty_i->dirty_secmap = f2fs_kvzalloc(sbi,
+ bitmap_size, GFP_KERNEL);
+ if (!dirty_i->dirty_secmap)
+ return -ENOMEM;
+ }
+
init_dirty_segmap(sbi);
return init_victim_secmap(sbi);
}
@@ -4759,6 +4822,12 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
for (i = 0; i < NR_DIRTY_TYPE; i++)
discard_dirty_segmap(sbi, i);
+ if (__is_large_section(sbi)) {
+ mutex_lock(&dirty_i->seglist_lock);
+ kvfree(dirty_i->dirty_secmap);
+ mutex_unlock(&dirty_i->seglist_lock);
+ }
+
destroy_victim_secmap(sbi);
SM_I(sbi)->dirty_info = NULL;
kvfree(dirty_i);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 7a83bd530812..752b177073b2 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* fs/f2fs/segment.h
*
@@ -166,8 +166,11 @@ enum {
struct victim_sel_policy {
int alloc_mode; /* LFS or SSR */
int gc_mode; /* GC_CB or GC_GREEDY */
- unsigned long *dirty_segmap; /* dirty segment bitmap */
- unsigned int max_search; /* maximum # of segments to search */
+ unsigned long *dirty_bitmap; /* dirty segment/section bitmap */
+ unsigned int max_search; /*
+ * maximum # of segments/sections
+ * to search
+ */
unsigned int offset; /* last scanned bitmap offset */
unsigned int ofs_unit; /* bitmap search unit */
unsigned int min_cost; /* minimum cost */
@@ -184,7 +187,7 @@ struct seg_entry {
unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */
#endif
/*
- * # of valid blocks and the validity bitmap stored in the the last
+ * # of valid blocks and the validity bitmap stored in the last
* checkpoint pack. This information is used by the SSR mode.
*/
unsigned char *ckpt_valid_map; /* validity bitmap of blocks last cp */
@@ -266,6 +269,7 @@ enum dirty_type {
struct dirty_seglist_info {
const struct victim_selection *v_ops; /* victim selction operation */
unsigned long *dirty_segmap[NR_DIRTY_TYPE];
+ unsigned long *dirty_secmap;
struct mutex seglist_lock; /* lock for segment bitmaps */
int nr_dirty[NR_DIRTY_TYPE]; /* # of dirty segments */
unsigned long *victim_secmap; /* background GC victims */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f2dfc21c6abb..dfa072fa8081 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -138,6 +138,7 @@ enum {
Opt_alloc,
Opt_fsync,
Opt_test_dummy_encryption,
+ Opt_inlinecrypt,
Opt_checkpoint_disable,
Opt_checkpoint_disable_cap,
Opt_checkpoint_disable_cap_perc,
@@ -202,7 +203,9 @@ static match_table_t f2fs_tokens = {
{Opt_whint, "whint_mode=%s"},
{Opt_alloc, "alloc_mode=%s"},
{Opt_fsync, "fsync_mode=%s"},
+ {Opt_test_dummy_encryption, "test_dummy_encryption=%s"},
{Opt_test_dummy_encryption, "test_dummy_encryption"},
+ {Opt_inlinecrypt, "inlinecrypt"},
{Opt_checkpoint_disable, "checkpoint=disable"},
{Opt_checkpoint_disable_cap, "checkpoint=disable:%u"},
{Opt_checkpoint_disable_cap_perc, "checkpoint=disable:%u%%"},
@@ -284,6 +287,22 @@ static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).s_resgid));
}
+static inline void adjust_unusable_cap_perc(struct f2fs_sb_info *sbi)
+{
+ if (!F2FS_OPTION(sbi).unusable_cap_perc)
+ return;
+
+ if (F2FS_OPTION(sbi).unusable_cap_perc == 100)
+ F2FS_OPTION(sbi).unusable_cap = sbi->user_block_count;
+ else
+ F2FS_OPTION(sbi).unusable_cap = (sbi->user_block_count / 100) *
+ F2FS_OPTION(sbi).unusable_cap_perc;
+
+ f2fs_info(sbi, "Adjust unusable cap for checkpoint=disable = %u / %u%%",
+ F2FS_OPTION(sbi).unusable_cap,
+ F2FS_OPTION(sbi).unusable_cap_perc);
+}
+
static void init_once(void *foo)
{
struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;
@@ -331,7 +350,7 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype,
set_opt(sbi, QUOTA);
return 0;
errout:
- kvfree(qname);
+ kfree(qname);
return ret;
}
@@ -343,7 +362,7 @@ static int f2fs_clear_qf_name(struct super_block *sb, int qtype)
f2fs_err(sbi, "Cannot change journaled quota options when quota turned on");
return -EINVAL;
}
- kvfree(F2FS_OPTION(sbi).s_qf_names[qtype]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[qtype]);
F2FS_OPTION(sbi).s_qf_names[qtype] = NULL;
return 0;
}
@@ -394,18 +413,64 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi)
}
#endif
-static int parse_options(struct super_block *sb, char *options)
+static int f2fs_set_test_dummy_encryption(struct super_block *sb,
+ const char *opt,
+ const substring_t *arg,
+ bool is_remount)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+#ifdef CONFIG_FS_ENCRYPTION
+ int err;
+
+ if (!f2fs_sb_has_encrypt(sbi)) {
+ f2fs_err(sbi, "Encrypt feature is off");
+ return -EINVAL;
+ }
+
+ /*
+ * This mount option is just for testing, and it's not worthwhile to
+ * implement the extra complexity (e.g. RCU protection) that would be
+ * needed to allow it to be set or changed during remount. We do allow
+ * it to be specified during remount, but only if there is no change.
+ */
+ if (is_remount && !F2FS_OPTION(sbi).dummy_enc_ctx.ctx) {
+ f2fs_warn(sbi, "Can't set test_dummy_encryption on remount");
+ return -EINVAL;
+ }
+ err = fscrypt_set_test_dummy_encryption(
+ sb, arg, &F2FS_OPTION(sbi).dummy_enc_ctx);
+ if (err) {
+ if (err == -EEXIST)
+ f2fs_warn(sbi,
+ "Can't change test_dummy_encryption on remount");
+ else if (err == -EINVAL)
+ f2fs_warn(sbi, "Value of option \"%s\" is unrecognized",
+ opt);
+ else
+ f2fs_warn(sbi, "Error processing option \"%s\" [%d]",
+ opt, err);
+ return -EINVAL;
+ }
+ f2fs_warn(sbi, "Test dummy encryption mode enabled");
+#else
+ f2fs_warn(sbi, "Test dummy encryption mount option ignored");
+#endif
+ return 0;
+}
+
+static int parse_options(struct super_block *sb, 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];
+ int ext_cnt;
+#endif
char *p, *name;
- int arg = 0, ext_cnt;
+ int arg = 0;
kuid_t uid;
kgid_t gid;
-#ifdef CONFIG_QUOTA
int ret;
-#endif
if (!options)
return 0;
@@ -427,17 +492,17 @@ static int parse_options(struct super_block *sb, char *options)
if (!name)
return -ENOMEM;
- if (strlen(name) == 2 && !strncmp(name, "on", 2)) {
+ if (!strcmp(name, "on")) {
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
- } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) {
+ } else if (!strcmp(name, "off")) {
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_OFF;
- } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) {
+ } else if (!strcmp(name, "sync")) {
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_SYNC;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_disable_roll_forward:
set_opt(sbi, DISABLE_ROLL_FORWARD);
@@ -591,22 +656,20 @@ static int parse_options(struct super_block *sb, char *options)
if (!name)
return -ENOMEM;
- if (strlen(name) == 8 &&
- !strncmp(name, "adaptive", 8)) {
+ if (!strcmp(name, "adaptive")) {
if (f2fs_sb_has_blkzoned(sbi)) {
f2fs_warn(sbi, "adaptive mode is not allowed with zoned block device feature");
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE;
- } else if (strlen(name) == 3 &&
- !strncmp(name, "lfs", 3)) {
+ } else if (!strcmp(name, "lfs")) {
F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_io_size_bits:
if (args->from && match_int(args, &arg))
@@ -725,69 +788,61 @@ static int parse_options(struct super_block *sb, char *options)
name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
- if (strlen(name) == 10 &&
- !strncmp(name, "user-based", 10)) {
+ if (!strcmp(name, "user-based")) {
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER;
- } else if (strlen(name) == 3 &&
- !strncmp(name, "off", 3)) {
+ } else if (!strcmp(name, "off")) {
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
- } else if (strlen(name) == 8 &&
- !strncmp(name, "fs-based", 8)) {
+ } else if (!strcmp(name, "fs-based")) {
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_alloc:
name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
- if (strlen(name) == 7 &&
- !strncmp(name, "default", 7)) {
+ if (!strcmp(name, "default")) {
F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
- } else if (strlen(name) == 5 &&
- !strncmp(name, "reuse", 5)) {
+ } else if (!strcmp(name, "reuse")) {
F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_fsync:
name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
- if (strlen(name) == 5 &&
- !strncmp(name, "posix", 5)) {
+ if (!strcmp(name, "posix")) {
F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX;
- } else if (strlen(name) == 6 &&
- !strncmp(name, "strict", 6)) {
+ } else if (!strcmp(name, "strict")) {
F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_STRICT;
- } else if (strlen(name) == 9 &&
- !strncmp(name, "nobarrier", 9)) {
+ } else if (!strcmp(name, "nobarrier")) {
F2FS_OPTION(sbi).fsync_mode =
FSYNC_MODE_NOBARRIER;
} else {
- kvfree(name);
+ kfree(name);
return -EINVAL;
}
- kvfree(name);
+ kfree(name);
break;
case Opt_test_dummy_encryption:
-#ifdef CONFIG_FS_ENCRYPTION
- if (!f2fs_sb_has_encrypt(sbi)) {
- f2fs_err(sbi, "Encrypt feature is off");
- return -EINVAL;
- }
-
- F2FS_OPTION(sbi).test_dummy_encryption = true;
- f2fs_info(sbi, "Test dummy encryption mode enabled");
+ ret = f2fs_set_test_dummy_encryption(sb, p, &args[0],
+ is_remount);
+ if (ret)
+ return ret;
+ break;
+ case Opt_inlinecrypt:
+#ifdef CONFIG_FS_ENCRYPTION_INLINE_CRYPT
+ sb->s_flags |= SB_INLINECRYPT;
#else
- f2fs_info(sbi, "Test dummy encryption mount option ignored");
+ f2fs_info(sbi, "inline encryption not supported");
#endif
break;
case Opt_checkpoint_disable_cap_perc:
@@ -795,12 +850,7 @@ static int parse_options(struct super_block *sb, char *options)
return -EINVAL;
if (arg < 0 || arg > 100)
return -EINVAL;
- if (arg == 100)
- F2FS_OPTION(sbi).unusable_cap =
- sbi->user_block_count;
- else
- F2FS_OPTION(sbi).unusable_cap =
- (sbi->user_block_count / 100) * arg;
+ F2FS_OPTION(sbi).unusable_cap_perc = arg;
set_opt(sbi, DISABLE_CHECKPOINT);
break;
case Opt_checkpoint_disable_cap:
@@ -815,6 +865,7 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_checkpoint_enable:
clear_opt(sbi, DISABLE_CHECKPOINT);
break;
+#ifdef CONFIG_F2FS_FS_COMPRESSION
case Opt_compress_algorithm:
if (!f2fs_sb_has_compression(sbi)) {
f2fs_err(sbi, "Compression feature if off");
@@ -823,17 +874,18 @@ static int parse_options(struct super_block *sb, char *options)
name = match_strdup(&args[0]);
if (!name)
return -ENOMEM;
- if (strlen(name) == 3 && !strcmp(name, "lzo")) {
+ if (!strcmp(name, "lzo")) {
F2FS_OPTION(sbi).compress_algorithm =
COMPRESS_LZO;
- } else if (strlen(name) == 3 &&
- !strcmp(name, "lz4")) {
+ } else if (!strcmp(name, "lz4")) {
F2FS_OPTION(sbi).compress_algorithm =
COMPRESS_LZ4;
- } else if (strlen(name) == 4 &&
- !strcmp(name, "zstd")) {
+ } else if (!strcmp(name, "zstd")) {
F2FS_OPTION(sbi).compress_algorithm =
COMPRESS_ZSTD;
+ } else if (!strcmp(name, "lzo-rle")) {
+ F2FS_OPTION(sbi).compress_algorithm =
+ COMPRESS_LZORLE;
} else {
kfree(name);
return -EINVAL;
@@ -879,6 +931,13 @@ static int parse_options(struct super_block *sb, char *options)
F2FS_OPTION(sbi).compress_ext_cnt++;
kfree(name);
break;
+#else
+ case Opt_compress_algorithm:
+ case Opt_compress_log_size:
+ case Opt_compress_extension:
+ f2fs_info(sbi, "compression options not supported");
+ break;
+#endif
default:
f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value",
p);
@@ -976,6 +1035,8 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
+ fi->ra_offset = -1;
+
return &fi->vfs_inode;
}
@@ -1134,6 +1195,9 @@ static void f2fs_put_super(struct super_block *sb)
int i;
bool dropped;
+ /* unregister procfs/sysfs entries in advance to avoid race case */
+ f2fs_unregister_sysfs(sbi);
+
f2fs_quota_off_umount(sb);
/* prevent remaining shrinker jobs */
@@ -1199,27 +1263,26 @@ static void f2fs_put_super(struct super_block *sb)
kvfree(sbi->ckpt);
- f2fs_unregister_sysfs(sbi);
-
sb->s_fs_info = NULL;
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
- kvfree(sbi->raw_super);
+ kfree(sbi->raw_super);
destroy_device_list(sbi);
f2fs_destroy_xattr_caches(sbi);
mempool_destroy(sbi->write_io_dummy);
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
- kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[i]);
#endif
+ fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
destroy_percpu_info(sbi);
for (i = 0; i < NR_PAGE_TYPE; i++)
kvfree(sbi->write_io[i]);
#ifdef CONFIG_UNICODE
utf8_unload(sbi->s_encoding);
#endif
- kvfree(sbi);
+ kfree(sbi);
}
int f2fs_sync_fs(struct super_block *sb, int sync)
@@ -1292,7 +1355,8 @@ static int f2fs_statfs_project(struct super_block *sb,
limit >>= sb->s_blocksize_bits;
if (limit && buf->f_blocks > limit) {
- curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+ 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) ?
@@ -1427,6 +1491,9 @@ static inline void f2fs_show_compress_options(struct seq_file *seq,
case COMPRESS_ZSTD:
algtype = "zstd";
break;
+ case COMPRESS_LZORLE:
+ algtype = "lzo-rle";
+ break;
}
seq_printf(seq, ",compress_algorithm=%s", algtype);
@@ -1543,10 +1610,11 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_printf(seq, ",whint_mode=%s", "user-based");
else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS)
seq_printf(seq, ",whint_mode=%s", "fs-based");
-#ifdef CONFIG_FS_ENCRYPTION
- if (F2FS_OPTION(sbi).test_dummy_encryption)
- seq_puts(seq, ",test_dummy_encryption");
-#endif
+
+ fscrypt_show_test_dummy_encryption(seq, ',', sbi->sb);
+
+ if (sbi->sb->s_flags & SB_INLINECRYPT)
+ seq_puts(seq, ",inlinecrypt");
if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT)
seq_printf(seq, ",alloc_mode=%s", "default");
@@ -1563,7 +1631,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER)
seq_printf(seq, ",fsync_mode=%s", "nobarrier");
+#ifdef CONFIG_F2FS_FS_COMPRESSION
f2fs_show_compress_options(seq, sbi->sb);
+#endif
return 0;
}
@@ -1575,7 +1645,6 @@ static void default_options(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF;
F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT;
F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX;
- F2FS_OPTION(sbi).test_dummy_encryption = false;
F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID);
F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID);
F2FS_OPTION(sbi).compress_algorithm = COMPRESS_LZ4;
@@ -1583,6 +1652,8 @@ static void default_options(struct f2fs_sb_info *sbi)
F2FS_OPTION(sbi).compress_ext_cnt = 0;
F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON;
+ sbi->sb->s_flags &= ~SB_INLINECRYPT;
+
set_opt(sbi, INLINE_XATTR);
set_opt(sbi, INLINE_DATA);
set_opt(sbi, INLINE_DENTRY);
@@ -1713,7 +1784,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
GFP_KERNEL);
if (!org_mount_opt.s_qf_names[i]) {
for (j = 0; j < i; j++)
- kvfree(org_mount_opt.s_qf_names[j]);
+ kfree(org_mount_opt.s_qf_names[j]);
return -ENOMEM;
}
} else {
@@ -1734,7 +1805,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
default_options(sbi);
/* parse mount options */
- err = parse_options(sb, data);
+ err = parse_options(sb, data, true);
if (err)
goto restore_opts;
checkpoint_changed =
@@ -1838,13 +1909,14 @@ skip:
#ifdef CONFIG_QUOTA
/* Release old quota file names */
for (i = 0; i < MAXQUOTAS; i++)
- kvfree(org_mount_opt.s_qf_names[i]);
+ kfree(org_mount_opt.s_qf_names[i]);
#endif
/* Update the POSIXACL Flag */
sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? SB_POSIXACL : 0);
limit_reserve_root(sbi);
+ adjust_unusable_cap_perc(sbi);
*flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME);
return 0;
restore_gc:
@@ -1858,7 +1930,7 @@ restore_opts:
#ifdef CONFIG_QUOTA
F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt;
for (i = 0; i < MAXQUOTAS; i++) {
- kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[i]);
F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i];
}
#endif
@@ -2410,9 +2482,10 @@ static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
ctx, len, fs_data, XATTR_CREATE);
}
-static bool f2fs_dummy_context(struct inode *inode)
+static const union fscrypt_context *
+f2fs_get_dummy_context(struct super_block *sb)
{
- return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode));
+ return F2FS_OPTION(F2FS_SB(sb)).dummy_enc_ctx.ctx;
}
static bool f2fs_has_stable_inodes(struct super_block *sb)
@@ -2427,15 +2500,36 @@ static void f2fs_get_ino_and_lblk_bits(struct super_block *sb,
*lblk_bits_ret = 8 * sizeof(block_t);
}
+static int f2fs_get_num_devices(struct super_block *sb)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+ if (f2fs_is_multi_device(sbi))
+ return sbi->s_ndevs;
+ return 1;
+}
+
+static void f2fs_get_devices(struct super_block *sb,
+ struct request_queue **devs)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++)
+ devs[i] = bdev_get_queue(FDEV(i).bdev);
+}
+
static const struct fscrypt_operations f2fs_cryptops = {
.key_prefix = "f2fs:",
.get_context = f2fs_get_context,
.set_context = f2fs_set_context,
- .dummy_context = f2fs_dummy_context,
+ .get_dummy_context = f2fs_get_dummy_context,
.empty_dir = f2fs_empty_dir,
.max_namelen = F2FS_NAME_LEN,
.has_stable_inodes = f2fs_has_stable_inodes,
.get_ino_and_lblk_bits = f2fs_get_ino_and_lblk_bits,
+ .get_num_devices = f2fs_get_num_devices,
+ .get_devices = f2fs_get_devices,
};
#endif
@@ -3026,7 +3120,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
if (nr_sectors & (bdev_zone_sectors(bdev) - 1))
FDEV(devi).nr_blkz++;
- FDEV(devi).blkz_seq = f2fs_kzalloc(sbi,
+ FDEV(devi).blkz_seq = f2fs_kvzalloc(sbi,
BITS_TO_LONGS(FDEV(devi).nr_blkz)
* sizeof(unsigned long),
GFP_KERNEL);
@@ -3094,7 +3188,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi,
/* No valid superblock */
if (!*raw_super)
- kvfree(super);
+ kfree(super);
else
err = 0;
@@ -3366,7 +3460,7 @@ try_onemore:
goto free_sb_buf;
}
- err = parse_options(sb, options);
+ err = parse_options(sb, options, false);
if (err)
goto free_options;
@@ -3413,7 +3507,6 @@ try_onemore:
init_rwsem(&sbi->gc_lock);
mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
- mutex_init(&sbi->resize_mutex);
init_rwsem(&sbi->node_write);
init_rwsem(&sbi->node_change);
@@ -3424,6 +3517,7 @@ try_onemore:
/* init iostat info */
spin_lock_init(&sbi->iostat_lock);
sbi->iostat_enable = false;
+ sbi->iostat_period_ms = DEFAULT_IOSTAT_PERIOD_MS;
for (i = 0; i < NR_PAGE_TYPE; i++) {
int n = (i == META) ? 1: NR_TEMP_TYPE;
@@ -3521,6 +3615,7 @@ try_onemore:
sbi->reserved_blocks = 0;
sbi->current_reserved_blocks = 0;
limit_reserve_root(sbi);
+ adjust_unusable_cap_perc(sbi);
for (i = 0; i < NR_INODE_TYPE; i++) {
INIT_LIST_HEAD(&sbi->inode_list[i]);
@@ -3767,15 +3862,16 @@ free_bio_info:
free_options:
#ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++)
- kvfree(F2FS_OPTION(sbi).s_qf_names[i]);
+ kfree(F2FS_OPTION(sbi).s_qf_names[i]);
#endif
+ fscrypt_free_dummy_context(&F2FS_OPTION(sbi).dummy_enc_ctx);
kvfree(options);
free_sb_buf:
- kvfree(raw_super);
+ kfree(raw_super);
free_sbi:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
- kvfree(sbi);
+ kfree(sbi);
/* give only one another chance */
if (retry_cnt > 0 && skip_recovery) {
@@ -3890,7 +3986,12 @@ static int __init init_f2fs_fs(void)
err = f2fs_init_bioset();
if (err)
goto free_bio_enrty_cache;
+ err = f2fs_init_compress_mempool();
+ if (err)
+ goto free_bioset;
return 0;
+free_bioset:
+ f2fs_destroy_bioset();
free_bio_enrty_cache:
f2fs_destroy_bio_entry_cache();
free_post_read:
@@ -3918,6 +4019,7 @@ fail:
static void __exit exit_f2fs_fs(void)
{
+ f2fs_destroy_compress_mempool();
f2fs_destroy_bioset();
f2fs_destroy_bio_entry_cache();
f2fs_destroy_post_read_processing();
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index e3bbbef9b4f0..88ed9969cc86 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -15,6 +15,7 @@
#include "f2fs.h"
#include "segment.h"
#include "gc.h"
+#include <trace/events/f2fs.h>
static struct proc_dir_entry *f2fs_proc_root;
@@ -26,7 +27,7 @@ enum {
NM_INFO, /* struct f2fs_nm_info */
F2FS_SBI, /* struct f2fs_sb_info */
#ifdef CONFIG_F2FS_STAT_FS
- STAT_INFO, /* struct f2fs_stat_info */
+ STAT_INFO, /* struct f2fs_stat_info */
#endif
#ifdef CONFIG_F2FS_FAULT_INJECTION
FAULT_INFO_RATE, /* struct f2fs_fault_info */
@@ -222,6 +223,13 @@ static ssize_t avg_vblocks_show(struct f2fs_attr *a,
}
#endif
+static ssize_t main_blkaddr_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)MAIN_BLKADDR(sbi));
+}
+
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -349,16 +357,20 @@ out:
return -EINVAL;
if (!strcmp(a->attr.name, "gc_urgent")) {
- if (t >= 1) {
- sbi->gc_mode = GC_URGENT;
+ if (t == 0) {
+ sbi->gc_mode = GC_NORMAL;
+ } else if (t == 1) {
+ sbi->gc_mode = GC_URGENT_HIGH;
if (sbi->gc_thread) {
sbi->gc_thread->gc_wake = 1;
wake_up_interruptible_all(
&sbi->gc_thread->gc_wait_queue_head);
wake_up_discard_thread(sbi, true);
}
+ } else if (t == 2) {
+ sbi->gc_mode = GC_URGENT_LOW;
} else {
- sbi->gc_mode = GC_NORMAL;
+ return -EINVAL;
}
return count;
}
@@ -372,7 +384,6 @@ out:
return count;
}
-
if (!strcmp(a->attr.name, "iostat_enable")) {
sbi->iostat_enable = !!t;
if (!sbi->iostat_enable)
@@ -380,6 +391,15 @@ out:
return count;
}
+ if (!strcmp(a->attr.name, "iostat_period_ms")) {
+ if (t < MIN_IOSTAT_PERIOD_MS || t > MAX_IOSTAT_PERIOD_MS)
+ return -EINVAL;
+ spin_lock(&sbi->iostat_lock);
+ sbi->iostat_period_ms = (unsigned int)t;
+ spin_unlock(&sbi->iostat_lock);
+ return count;
+ }
+
*ui = (unsigned int)t;
return count;
@@ -446,6 +466,7 @@ enum feat_id {
FEAT_SB_CHECKSUM,
FEAT_CASEFOLD,
FEAT_COMPRESSION,
+ FEAT_TEST_DUMMY_ENCRYPTION_V2,
};
static ssize_t f2fs_feature_show(struct f2fs_attr *a,
@@ -466,6 +487,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a,
case FEAT_SB_CHECKSUM:
case FEAT_CASEFOLD:
case FEAT_COMPRESSION:
+ case FEAT_TEST_DUMMY_ENCRYPTION_V2:
return sprintf(buf, "supported\n");
}
return 0;
@@ -511,7 +533,6 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, main_blkaddr, main_blkaddr);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity);
F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks);
@@ -536,6 +557,7 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info,
umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_period_ms, iostat_period_ms);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold);
F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list);
@@ -543,6 +565,8 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list);
F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
#endif
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, data_io_flag, data_io_flag);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, node_io_flag, node_io_flag);
F2FS_GENERAL_RO_ATTR(dirty_segments);
F2FS_GENERAL_RO_ATTR(free_segments);
F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
@@ -551,6 +575,7 @@ F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
F2FS_GENERAL_RO_ATTR(unusable);
F2FS_GENERAL_RO_ATTR(encoding);
F2FS_GENERAL_RO_ATTR(mounted_time_sec);
+F2FS_GENERAL_RO_ATTR(main_blkaddr);
#ifdef CONFIG_F2FS_STAT_FS
F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count);
F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count);
@@ -563,6 +588,7 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks);
#ifdef CONFIG_FS_ENCRYPTION
F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
+F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2, FEAT_TEST_DUMMY_ENCRYPTION_V2);
#endif
#ifdef CONFIG_BLK_DEV_ZONED
F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED);
@@ -615,6 +641,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(gc_idle_interval),
ATTR_LIST(umount_discard_timeout),
ATTR_LIST(iostat_enable),
+ ATTR_LIST(iostat_period_ms),
ATTR_LIST(readdir_ra),
ATTR_LIST(gc_pin_file_thresh),
ATTR_LIST(extension_list),
@@ -622,6 +649,8 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(inject_rate),
ATTR_LIST(inject_type),
#endif
+ ATTR_LIST(data_io_flag),
+ ATTR_LIST(node_io_flag),
ATTR_LIST(dirty_segments),
ATTR_LIST(free_segments),
ATTR_LIST(unusable),
@@ -647,6 +676,7 @@ ATTRIBUTE_GROUPS(f2fs);
static struct attribute *f2fs_feat_attrs[] = {
#ifdef CONFIG_FS_ENCRYPTION
ATTR_LIST(encryption),
+ ATTR_LIST(test_dummy_encryption_v2),
#endif
#ifdef CONFIG_BLK_DEV_ZONED
ATTR_LIST(block_zoned),
@@ -687,7 +717,7 @@ static struct kobj_type f2fs_ktype = {
};
static struct kset f2fs_kset = {
- .kobj = {.ktype = &f2fs_ktype},
+ .kobj = {.ktype = &f2fs_ktype},
};
static struct kobj_type f2fs_feat_ktype = {
@@ -750,6 +780,33 @@ static int __maybe_unused segment_bits_seq_show(struct seq_file *seq,
return 0;
}
+void f2fs_record_iostat(struct f2fs_sb_info *sbi)
+{
+ unsigned long long iostat_diff[NR_IO_TYPE];
+ int i;
+
+ if (time_is_after_jiffies(sbi->iostat_next_period))
+ return;
+
+ /* Need double check under the lock */
+ spin_lock(&sbi->iostat_lock);
+ if (time_is_after_jiffies(sbi->iostat_next_period)) {
+ spin_unlock(&sbi->iostat_lock);
+ return;
+ }
+ sbi->iostat_next_period = jiffies +
+ msecs_to_jiffies(sbi->iostat_period_ms);
+
+ for (i = 0; i < NR_IO_TYPE; i++) {
+ iostat_diff[i] = sbi->rw_iostat[i] -
+ sbi->prev_rw_iostat[i];
+ sbi->prev_rw_iostat[i] = sbi->rw_iostat[i];
+ }
+ spin_unlock(&sbi->iostat_lock);
+
+ trace_f2fs_iostat(sbi, iostat_diff);
+}
+
static int __maybe_unused iostat_info_seq_show(struct seq_file *seq,
void *offset)
{
@@ -762,33 +819,58 @@ static int __maybe_unused iostat_info_seq_show(struct seq_file *seq,
seq_printf(seq, "time: %-16llu\n", now);
- /* print app IOs */
+ /* print app write IOs */
+ seq_puts(seq, "[WRITE]\n");
seq_printf(seq, "app buffered: %-16llu\n",
- sbi->write_iostat[APP_BUFFERED_IO]);
+ sbi->rw_iostat[APP_BUFFERED_IO]);
seq_printf(seq, "app direct: %-16llu\n",
- sbi->write_iostat[APP_DIRECT_IO]);
+ sbi->rw_iostat[APP_DIRECT_IO]);
seq_printf(seq, "app mapped: %-16llu\n",
- sbi->write_iostat[APP_MAPPED_IO]);
+ sbi->rw_iostat[APP_MAPPED_IO]);
- /* print fs IOs */
+ /* print fs write IOs */
seq_printf(seq, "fs data: %-16llu\n",
- sbi->write_iostat[FS_DATA_IO]);
+ sbi->rw_iostat[FS_DATA_IO]);
seq_printf(seq, "fs node: %-16llu\n",
- sbi->write_iostat[FS_NODE_IO]);
+ sbi->rw_iostat[FS_NODE_IO]);
seq_printf(seq, "fs meta: %-16llu\n",
- sbi->write_iostat[FS_META_IO]);
+ sbi->rw_iostat[FS_META_IO]);
seq_printf(seq, "fs gc data: %-16llu\n",
- sbi->write_iostat[FS_GC_DATA_IO]);
+ sbi->rw_iostat[FS_GC_DATA_IO]);
seq_printf(seq, "fs gc node: %-16llu\n",
- sbi->write_iostat[FS_GC_NODE_IO]);
+ sbi->rw_iostat[FS_GC_NODE_IO]);
seq_printf(seq, "fs cp data: %-16llu\n",
- sbi->write_iostat[FS_CP_DATA_IO]);
+ sbi->rw_iostat[FS_CP_DATA_IO]);
seq_printf(seq, "fs cp node: %-16llu\n",
- sbi->write_iostat[FS_CP_NODE_IO]);
+ sbi->rw_iostat[FS_CP_NODE_IO]);
seq_printf(seq, "fs cp meta: %-16llu\n",
- sbi->write_iostat[FS_CP_META_IO]);
+ sbi->rw_iostat[FS_CP_META_IO]);
+
+ /* print app read IOs */
+ seq_puts(seq, "[READ]\n");
+ seq_printf(seq, "app buffered: %-16llu\n",
+ sbi->rw_iostat[APP_BUFFERED_READ_IO]);
+ seq_printf(seq, "app direct: %-16llu\n",
+ sbi->rw_iostat[APP_DIRECT_READ_IO]);
+ seq_printf(seq, "app mapped: %-16llu\n",
+ sbi->rw_iostat[APP_MAPPED_READ_IO]);
+
+ /* print fs read IOs */
+ seq_printf(seq, "fs data: %-16llu\n",
+ sbi->rw_iostat[FS_DATA_READ_IO]);
+ seq_printf(seq, "fs gc data: %-16llu\n",
+ sbi->rw_iostat[FS_GDATA_READ_IO]);
+ seq_printf(seq, "fs compr_data: %-16llu\n",
+ sbi->rw_iostat[FS_CDATA_READ_IO]);
+ seq_printf(seq, "fs node: %-16llu\n",
+ sbi->rw_iostat[FS_NODE_READ_IO]);
+ seq_printf(seq, "fs meta: %-16llu\n",
+ sbi->rw_iostat[FS_META_READ_IO]);
+
+ /* print other IOs */
+ seq_puts(seq, "[OTHER]\n");
seq_printf(seq, "fs discard: %-16llu\n",
- sbi->write_iostat[FS_DISCARD]);
+ sbi->rw_iostat[FS_DISCARD]);
return 0;
}
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
index e8075fc5b228..789f6aa727fc 100644
--- a/fs/f2fs/trace.h
+++ b/fs/f2fs/trace.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* f2fs IO tracer
*
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index d7d430a6f130..9eb0dba851e8 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -29,6 +29,8 @@
#include "f2fs.h"
#include "xattr.h"
+#define F2FS_VERIFY_VER (1)
+
static inline loff_t f2fs_verity_metadata_pos(const struct inode *inode)
{
return round_up(inode->i_size, 65536);
@@ -152,7 +154,7 @@ static int f2fs_end_enable_verity(struct file *filp, const void *desc,
struct inode *inode = file_inode(filp);
u64 desc_pos = f2fs_verity_metadata_pos(inode) + merkle_tree_size;
struct fsverity_descriptor_location dloc = {
- .version = cpu_to_le32(1),
+ .version = cpu_to_le32(F2FS_VERIFY_VER),
.size = cpu_to_le32(desc_size),
.pos = cpu_to_le64(desc_pos),
};
@@ -199,7 +201,7 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
F2FS_XATTR_NAME_VERITY, &dloc, sizeof(dloc), NULL);
if (res < 0 && res != -ERANGE)
return res;
- if (res != sizeof(dloc) || dloc.version != cpu_to_le32(1)) {
+ if (res != sizeof(dloc) || dloc.version != cpu_to_le32(F2FS_VERIFY_VER)) {
f2fs_warn(F2FS_I_SB(inode), "unknown verity xattr format");
return -EINVAL;
}
@@ -222,37 +224,6 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
return size;
}
-/*
- * Prefetch some pages from the file's Merkle tree.
- *
- * This is basically a stripped-down version of __do_page_cache_readahead()
- * which works on pages past i_size.
- */
-static void f2fs_merkle_tree_readahead(struct address_space *mapping,
- pgoff_t start_index, unsigned long count)
-{
- LIST_HEAD(pages);
- unsigned int nr_pages = 0;
- struct page *page;
- pgoff_t index;
- struct blk_plug plug;
-
- for (index = start_index; index < start_index + count; index++) {
- page = xa_load(&mapping->i_pages, index);
- if (!page || xa_is_value(page)) {
- page = __page_cache_alloc(readahead_gfp_mask(mapping));
- if (!page)
- break;
- page->index = index;
- list_add(&page->lru, &pages);
- nr_pages++;
- }
- }
- blk_start_plug(&plug);
- f2fs_mpage_readpages(mapping, &pages, NULL, nr_pages, true);
- blk_finish_plug(&plug);
-}
-
static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
@@ -266,8 +237,8 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
if (page)
put_page(page);
else if (num_ra_pages > 1)
- f2fs_merkle_tree_readahead(inode->i_mapping, index,
- num_ra_pages);
+ page_cache_readahead_unbounded(inode->i_mapping, NULL,
+ index, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 4f6582ef7ee3..1b0736ce0918 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -175,8 +175,8 @@ const struct xattr_handler f2fs_xattr_trusted_handler = {
const struct xattr_handler f2fs_xattr_advise_handler = {
.name = F2FS_SYSTEM_ADVISE_NAME,
.flags = F2FS_XATTR_INDEX_ADVISE,
- .get = f2fs_xattr_advise_get,
- .set = f2fs_xattr_advise_set,
+ .get = f2fs_xattr_advise_get,
+ .set = f2fs_xattr_advise_set,
};
const struct xattr_handler f2fs_xattr_security_handler = {
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 938fcd20565d..416d652774a3 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* fs/f2fs/xattr.h
*
@@ -136,6 +136,7 @@ extern void f2fs_destroy_xattr_caches(struct f2fs_sb_info *);
#else
#define f2fs_xattr_handlers NULL
+#define f2fs_listxattr NULL
static inline int f2fs_setxattr(struct inode *inode, int index,
const char *name, const void *value, size_t size,
struct page *page, int flags)
@@ -148,11 +149,6 @@ static inline int f2fs_getxattr(struct inode *inode, int index,
{
return -EOPNOTSUPP;
}
-static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer,
- size_t buffer_size)
-{
- return -EOPNOTSUPP;
-}
static inline int f2fs_init_xattr_caches(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_xattr_caches(struct f2fs_sb_info *sbi) { }
#endif
generated by cgit v1.2.3 (git 2.39.1) at 2024-10-10 07:35:01 +0000