summaryrefslogtreecommitdiff
path: root/fs/f2fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/f2fs')
-rw-r--r--fs/f2fs/acl.c5
-rw-r--r--fs/f2fs/checkpoint.c60
-rw-r--r--fs/f2fs/data.c177
-rw-r--r--fs/f2fs/dir.c7
-rw-r--r--fs/f2fs/f2fs.h285
-rw-r--r--fs/f2fs/file.c360
-rw-r--r--fs/f2fs/gc.c115
-rw-r--r--fs/f2fs/gc.h27
-rw-r--r--fs/f2fs/inline.c142
-rw-r--r--fs/f2fs/inode.c132
-rw-r--r--fs/f2fs/namei.c43
-rw-r--r--fs/f2fs/node.c79
-rw-r--r--fs/f2fs/recovery.c83
-rw-r--r--fs/f2fs/segment.c292
-rw-r--r--fs/f2fs/segment.h47
-rw-r--r--fs/f2fs/super.c433
-rw-r--r--fs/f2fs/sysfs.c251
-rw-r--r--fs/f2fs/xattr.c8
18 files changed, 2062 insertions, 484 deletions
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index b4b8438c42ef..436b3a1464d9 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -207,15 +207,16 @@ static int __f2fs_set_acl(struct inode *inode, int type,
void *value = NULL;
size_t size = 0;
int error;
+ umode_t mode = inode->i_mode;
switch (type) {
case ACL_TYPE_ACCESS:
name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl && !ipage) {
- error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+ error = posix_acl_update_mode(inode, &mode, &acl);
if (error)
return error;
- set_acl_inode(inode, inode->i_mode);
+ set_acl_inode(inode, mode);
}
break;
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 5b876f6d3f6b..04fe1df052b2 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -230,8 +230,9 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
}
-static int f2fs_write_meta_page(struct page *page,
- struct writeback_control *wbc)
+static int __f2fs_write_meta_page(struct page *page,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
@@ -244,7 +245,7 @@ static int f2fs_write_meta_page(struct page *page,
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
- write_meta_page(sbi, page);
+ write_meta_page(sbi, page, io_type);
dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim)
@@ -263,6 +264,12 @@ redirty_out:
return AOP_WRITEPAGE_ACTIVATE;
}
+static int f2fs_write_meta_page(struct page *page,
+ struct writeback_control *wbc)
+{
+ return __f2fs_write_meta_page(page, wbc, FS_META_IO);
+}
+
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -283,7 +290,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
trace_f2fs_writepages(mapping->host, wbc, META);
diff = nr_pages_to_write(sbi, META, wbc);
- written = sync_meta_pages(sbi, META, wbc->nr_to_write);
+ written = sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
mutex_unlock(&sbi->cp_mutex);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
return 0;
@@ -295,7 +302,7 @@ skip_write:
}
long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
- long nr_to_write)
+ long nr_to_write, enum iostat_type io_type)
{
struct address_space *mapping = META_MAPPING(sbi);
pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX;
@@ -346,7 +353,7 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- if (mapping->a_ops->writepage(page, &wbc)) {
+ if (__f2fs_write_meta_page(page, &wbc, io_type)) {
unlock_page(page);
break;
}
@@ -581,11 +588,24 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
int recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
block_t start_blk, orphan_blocks, i, j;
- int err;
+ unsigned int s_flags = sbi->sb->s_flags;
+ int err = 0;
if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
return 0;
+ if (s_flags & MS_RDONLY) {
+ f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
+ sbi->sb->s_flags &= ~MS_RDONLY;
+ }
+
+#ifdef CONFIG_QUOTA
+ /* Needed for iput() to work correctly and not trash data */
+ sbi->sb->s_flags |= MS_ACTIVE;
+ /* Turn on quotas so that they are updated correctly */
+ f2fs_enable_quota_files(sbi);
+#endif
+
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
@@ -601,14 +621,21 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
err = recover_orphan_inode(sbi, ino);
if (err) {
f2fs_put_page(page, 1);
- return err;
+ goto out;
}
}
f2fs_put_page(page, 1);
}
/* clear Orphan Flag */
clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
- return 0;
+out:
+#ifdef CONFIG_QUOTA
+ /* Turn quotas off */
+ f2fs_quota_off_umount(sbi->sb);
+#endif
+ sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+
+ return err;
}
static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
@@ -904,7 +931,14 @@ retry:
if (inode) {
unsigned long cur_ino = inode->i_ino;
+ if (is_dir)
+ F2FS_I(inode)->cp_task = current;
+
filemap_fdatawrite(inode->i_mapping);
+
+ if (is_dir)
+ F2FS_I(inode)->cp_task = NULL;
+
iput(inode);
/* We need to give cpu to another writers. */
if (ino == cur_ino) {
@@ -1017,7 +1051,7 @@ retry_flush_nodes:
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
- err = sync_node_pages(sbi, &wbc);
+ err = sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
if (err) {
up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
@@ -1115,7 +1149,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
- sync_meta_pages(sbi, META, LONG_MAX);
+ sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
}
@@ -1194,7 +1228,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
/* Flush all the NAT BITS pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
- sync_meta_pages(sbi, META, LONG_MAX);
+ sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
}
@@ -1249,7 +1283,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
percpu_counter_set(&sbi->alloc_valid_block_count, 0);
/* Here, we only have one bio having CP pack */
- sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
+ sync_meta_pages(sbi, META_FLUSH, LONG_MAX, FS_CP_META_IO);
/* wait for previous submitted meta pages writeback */
wait_on_all_pages_writeback(sbi);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index fb96bb71da00..36b535207c88 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -457,14 +457,65 @@ out_fail:
return err;
}
+static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr,
+ unsigned nr_pages)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct fscrypt_ctx *ctx = NULL;
+ struct bio *bio;
+
+ if (f2fs_encrypted_file(inode)) {
+ ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+ if (IS_ERR(ctx))
+ return ERR_CAST(ctx);
+
+ /* wait the page to be moved by cleaning */
+ f2fs_wait_on_block_writeback(sbi, blkaddr);
+ }
+
+ bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+ if (!bio) {
+ if (ctx)
+ fscrypt_release_ctx(ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ f2fs_target_device(sbi, blkaddr, bio);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = ctx;
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ return bio;
+}
+
+/* This can handle encryption stuffs */
+static int f2fs_submit_page_read(struct inode *inode, struct page *page,
+ block_t blkaddr)
+{
+ struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1);
+
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+ bio_put(bio);
+ return -EFAULT;
+ }
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ return 0;
+}
+
static void __set_data_blkaddr(struct dnode_of_data *dn)
{
struct f2fs_node *rn = F2FS_NODE(dn->node_page);
__le32 *addr_array;
+ int base = 0;
+
+ if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
+ base = get_extra_isize(dn->inode);
/* Get physical address of data block */
addr_array = blkaddr_in_node(rn);
- addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
+ addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
}
/*
@@ -508,8 +559,8 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
for (; count > 0; dn->ofs_in_node++) {
- block_t blkaddr =
- datablock_addr(dn->node_page, dn->ofs_in_node);
+ block_t blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
if (blkaddr == NULL_ADDR) {
dn->data_blkaddr = NEW_ADDR;
__set_data_blkaddr(dn);
@@ -570,16 +621,6 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
struct page *page;
struct extent_info ei = {0,0,0};
int err;
- struct f2fs_io_info fio = {
- .sbi = F2FS_I_SB(inode),
- .type = DATA,
- .op = REQ_OP_READ,
- .op_flags = op_flags,
- .encrypted_page = NULL,
- };
-
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- return read_mapping_page(mapping, index, NULL);
page = f2fs_grab_cache_page(mapping, index, for_write);
if (!page)
@@ -620,9 +661,7 @@ got_it:
return page;
}
- fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
- fio.page = page;
- err = f2fs_submit_page_bio(&fio);
+ err = f2fs_submit_page_read(inode, page, dn.data_blkaddr);
if (err)
goto put_err;
return page;
@@ -756,7 +795,8 @@ static int __allocate_data_block(struct dnode_of_data *dn)
if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
if (dn->data_blkaddr == NEW_ADDR)
goto alloc;
@@ -782,7 +822,7 @@ alloc:
static inline bool __force_buffered_io(struct inode *inode, int rw)
{
- return ((f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) ||
+ return (f2fs_encrypted_file(inode) ||
(rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
F2FS_I_SB(inode)->s_ndevs);
}
@@ -814,7 +854,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
F2FS_GET_BLOCK_PRE_AIO :
F2FS_GET_BLOCK_PRE_DIO);
}
- if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
+ if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
err = f2fs_convert_inline_inode(inode);
if (err)
return err;
@@ -903,7 +943,7 @@ next_dnode:
end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
next_block:
- blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
if (create) {
@@ -1040,7 +1080,7 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
return __get_data_block(inode, iblock, bh_result, create,
- F2FS_GET_BLOCK_DIO, NULL);
+ F2FS_GET_BLOCK_DEFAULT, NULL);
}
static int get_data_block_bmap(struct inode *inode, sector_t iblock,
@@ -1146,35 +1186,6 @@ out:
return ret;
}
-static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
- unsigned nr_pages)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct fscrypt_ctx *ctx = NULL;
- struct bio *bio;
-
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
- ctx = fscrypt_get_ctx(inode, GFP_NOFS);
- if (IS_ERR(ctx))
- return ERR_CAST(ctx);
-
- /* wait the page to be moved by cleaning */
- f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
- }
-
- bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
- if (!bio) {
- if (ctx)
- fscrypt_release_ctx(ctx);
- return ERR_PTR(-ENOMEM);
- }
- f2fs_target_device(sbi, blkaddr, bio);
- bio->bi_end_io = f2fs_read_end_io;
- bio->bi_private = ctx;
-
- return bio;
-}
-
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
@@ -1240,7 +1251,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
map.m_len = last_block - block_in_file;
if (f2fs_map_blocks(inode, &map, 0,
- F2FS_GET_BLOCK_READ))
+ F2FS_GET_BLOCK_DEFAULT))
goto set_error_page;
}
got_it:
@@ -1271,12 +1282,11 @@ submit_and_realloc:
bio = NULL;
}
if (bio == NULL) {
- bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+ bio = f2fs_grab_read_bio(inode, block_nr, nr_pages);
if (IS_ERR(bio)) {
bio = NULL;
goto set_error_page;
}
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
@@ -1341,11 +1351,11 @@ static int encrypt_one_page(struct f2fs_io_info *fio)
struct inode *inode = fio->page->mapping->host;
gfp_t gfp_flags = GFP_NOFS;
- if (!f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
+ if (!f2fs_encrypted_file(inode))
return 0;
/* wait for GCed encrypted page writeback */
- f2fs_wait_on_encrypted_page_writeback(fio->sbi, fio->old_blkaddr);
+ f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr);
retry_encrypt:
fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
@@ -1471,7 +1481,8 @@ out:
}
static int __write_data_page(struct page *page, bool *submitted,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -1492,6 +1503,7 @@ static int __write_data_page(struct page *page, bool *submitted,
.encrypted_page = NULL,
.submitted = false,
.need_lock = LOCK_RETRY,
+ .io_type = io_type,
};
trace_f2fs_writepage(page, DATA);
@@ -1598,7 +1610,7 @@ redirty_out:
static int f2fs_write_data_page(struct page *page,
struct writeback_control *wbc)
{
- return __write_data_page(page, NULL, wbc);
+ return __write_data_page(page, NULL, wbc, FS_DATA_IO);
}
/*
@@ -1607,7 +1619,8 @@ static int f2fs_write_data_page(struct page *page,
* warm/hot data page.
*/
static int f2fs_write_cache_pages(struct address_space *mapping,
- struct writeback_control *wbc)
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
int ret = 0;
int done = 0;
@@ -1697,7 +1710,7 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- ret = __write_data_page(page, &submitted, wbc);
+ ret = __write_data_page(page, &submitted, wbc, io_type);
if (unlikely(ret)) {
/*
* keep nr_to_write, since vfs uses this to
@@ -1752,8 +1765,9 @@ continue_unlock:
return ret;
}
-static int f2fs_write_data_pages(struct address_space *mapping,
- struct writeback_control *wbc)
+int __f2fs_write_data_pages(struct address_space *mapping,
+ struct writeback_control *wbc,
+ enum iostat_type io_type)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -1790,7 +1804,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
goto skip_write;
blk_start_plug(&plug);
- ret = f2fs_write_cache_pages(mapping, wbc);
+ ret = f2fs_write_cache_pages(mapping, wbc, io_type);
blk_finish_plug(&plug);
if (wbc->sync_mode == WB_SYNC_ALL)
@@ -1809,6 +1823,16 @@ skip_write:
return 0;
}
+static int f2fs_write_data_pages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct inode *inode = mapping->host;
+
+ return __f2fs_write_data_pages(mapping, wbc,
+ F2FS_I(inode)->cp_task == current ?
+ FS_CP_DATA_IO : FS_DATA_IO);
+}
+
static void f2fs_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
@@ -1858,7 +1882,7 @@ restart:
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode)) {
- if (pos + len <= MAX_INLINE_DATA) {
+ if (pos + len <= MAX_INLINE_DATA(inode)) {
read_inline_data(page, ipage);
set_inode_flag(inode, FI_DATA_EXIST);
if (inode->i_nlink)
@@ -1956,8 +1980,8 @@ repeat:
f2fs_wait_on_page_writeback(page, DATA, false);
/* wait for GCed encrypted page writeback */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+ if (f2fs_encrypted_file(inode))
+ f2fs_wait_on_block_writeback(sbi, blkaddr);
if (len == PAGE_SIZE || PageUptodate(page))
return 0;
@@ -1971,21 +1995,9 @@ repeat:
zero_user_segment(page, 0, PAGE_SIZE);
SetPageUptodate(page);
} else {
- struct bio *bio;
-
- bio = f2fs_grab_bio(inode, blkaddr, 1);
- if (IS_ERR(bio)) {
- err = PTR_ERR(bio);
- goto fail;
- }
- bio->bi_opf = REQ_OP_READ;
- if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
- bio_put(bio);
- err = -EFAULT;
+ err = f2fs_submit_page_read(inode, page, blkaddr);
+ if (err)
goto fail;
- }
-
- __submit_bio(sbi, bio, DATA);
lock_page(page);
if (unlikely(page->mapping != mapping)) {
@@ -2075,10 +2087,13 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
up_read(&F2FS_I(inode)->dio_rwsem[rw]);
if (rw == WRITE) {
- if (err > 0)
+ if (err > 0) {
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO,
+ err);
set_inode_flag(inode, FI_UPDATE_WRITE);
- else if (err < 0)
+ } else if (err < 0) {
f2fs_write_failed(mapping, offset + count);
+ }
}
trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 37f9c7f55605..c0c933ad43c8 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -705,6 +705,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
+ struct address_space *mapping = page_mapping(page);
+ unsigned long flags;
int i;
f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
@@ -735,6 +737,11 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
if (bit_pos == NR_DENTRY_IN_BLOCK &&
!truncate_hole(dir, page->index, page->index + 1)) {
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ radix_tree_tag_clear(&mapping->page_tree, page_index(page),
+ PAGECACHE_TAG_DIRTY);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+
clear_page_dirty_for_io(page);
ClearPagePrivate(page);
ClearPageUptodate(page);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 94a88b233e98..9a7c90386947 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -91,6 +91,8 @@ extern char *fault_name[FAULT_MAX];
#define F2FS_MOUNT_LFS 0x00040000
#define F2FS_MOUNT_USRQUOTA 0x00080000
#define F2FS_MOUNT_GRPQUOTA 0x00100000
+#define F2FS_MOUNT_PRJQUOTA 0x00200000
+#define F2FS_MOUNT_QUOTA 0x00400000
#define clear_opt(sbi, option) ((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option) ((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -110,8 +112,12 @@ struct f2fs_mount_info {
unsigned int opt;
};
-#define F2FS_FEATURE_ENCRYPT 0x0001
-#define F2FS_FEATURE_BLKZONED 0x0002
+#define F2FS_FEATURE_ENCRYPT 0x0001
+#define F2FS_FEATURE_BLKZONED 0x0002
+#define F2FS_FEATURE_ATOMIC_WRITE 0x0004
+#define F2FS_FEATURE_EXTRA_ATTR 0x0008
+#define F2FS_FEATURE_PRJQUOTA 0x0010
+#define F2FS_FEATURE_INODE_CHKSUM 0x0020
#define F2FS_HAS_FEATURE(sb, mask) \
((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
@@ -142,6 +148,8 @@ enum {
(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
#define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi)
#define DISCARD_ISSUE_RATE 8
+#define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */
+#define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */
#define DEF_CP_INTERVAL 60 /* 60 secs */
#define DEF_IDLE_INTERVAL 5 /* 5 secs */
@@ -190,11 +198,18 @@ struct discard_entry {
unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */
};
+/* default discard granularity of inner discard thread, unit: block count */
+#define DEFAULT_DISCARD_GRANULARITY 16
+
/* max discard pend list number */
#define MAX_PLIST_NUM 512
#define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \
(MAX_PLIST_NUM - 1) : (blk_num - 1))
+#define P_ACTIVE 0x01
+#define P_TRIM 0x02
+#define plist_issue(tag) (((tag) & P_ACTIVE) || ((tag) & P_TRIM))
+
enum {
D_PREP,
D_SUBMIT,
@@ -230,11 +245,14 @@ struct discard_cmd_control {
struct task_struct *f2fs_issue_discard; /* discard thread */
struct list_head entry_list; /* 4KB discard entry list */
struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
+ unsigned char pend_list_tag[MAX_PLIST_NUM];/* tag for pending entries */
struct list_head wait_list; /* store on-flushing entries */
wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */
+ unsigned int discard_wake; /* to wake up discard thread */
struct mutex cmd_lock;
unsigned int nr_discards; /* # of discards in the list */
unsigned int max_discards; /* max. discards to be issued */
+ unsigned int discard_granularity; /* discard granularity */
unsigned int undiscard_blks; /* # of undiscard blocks */
atomic_t issued_discard; /* # of issued discard */
atomic_t issing_discard; /* # of issing discard */
@@ -308,6 +326,7 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
struct f2fs_flush_device)
#define F2FS_IOC_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11, \
struct f2fs_gc_range)
+#define F2FS_IOC_GET_FEATURES _IOR(F2FS_IOCTL_MAGIC, 12, __u32)
#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
@@ -332,6 +351,9 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION
#endif
+#define F2FS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
+#define F2FS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
+
struct f2fs_gc_range {
u32 sync;
u64 start;
@@ -355,16 +377,36 @@ struct f2fs_flush_device {
u32 segments; /* # of segments to flush */
};
+/* for inline stuff */
+#define DEF_INLINE_RESERVED_SIZE 1
+static inline int get_extra_isize(struct inode *inode);
+#define MAX_INLINE_DATA(inode) (sizeof(__le32) * \
+ (CUR_ADDRS_PER_INODE(inode) - \
+ DEF_INLINE_RESERVED_SIZE - \
+ F2FS_INLINE_XATTR_ADDRS))
+
+/* for inline dir */
+#define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \
+ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+ BITS_PER_BYTE + 1))
+#define INLINE_DENTRY_BITMAP_SIZE(inode) ((NR_INLINE_DENTRY(inode) + \
+ BITS_PER_BYTE - 1) / BITS_PER_BYTE)
+#define INLINE_RESERVED_SIZE(inode) (MAX_INLINE_DATA(inode) - \
+ ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+ NR_INLINE_DENTRY(inode) + \
+ INLINE_DENTRY_BITMAP_SIZE(inode)))
+
/*
* For INODE and NODE manager
*/
/* for directory operations */
struct f2fs_dentry_ptr {
struct inode *inode;
- const void *bitmap;
+ void *bitmap;
struct f2fs_dir_entry *dentry;
__u8 (*filename)[F2FS_SLOT_LEN];
int max;
+ int nr_bitmap;
};
static inline void make_dentry_ptr_block(struct inode *inode,
@@ -372,19 +414,26 @@ static inline void make_dentry_ptr_block(struct inode *inode,
{
d->inode = inode;
d->max = NR_DENTRY_IN_BLOCK;
+ d->nr_bitmap = SIZE_OF_DENTRY_BITMAP;
d->bitmap = &t->dentry_bitmap;
d->dentry = t->dentry;
d->filename = t->filename;
}
static inline void make_dentry_ptr_inline(struct inode *inode,
- struct f2fs_dentry_ptr *d, struct f2fs_inline_dentry *t)
+ struct f2fs_dentry_ptr *d, void *t)
{
+ int entry_cnt = NR_INLINE_DENTRY(inode);
+ int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode);
+ int reserved_size = INLINE_RESERVED_SIZE(inode);
+
d->inode = inode;
- d->max = NR_INLINE_DENTRY;
- d->bitmap = &t->dentry_bitmap;
- d->dentry = t->dentry;
- d->filename = t->filename;
+ d->max = entry_cnt;
+ d->nr_bitmap = bitmap_size;
+ d->bitmap = t;
+ d->dentry = t + bitmap_size + reserved_size;
+ d->filename = t + bitmap_size + reserved_size +
+ SIZE_OF_DIR_ENTRY * entry_cnt;
}
/*
@@ -473,12 +522,13 @@ struct f2fs_map_blocks {
};
/* for flag in get_data_block */
-#define F2FS_GET_BLOCK_READ 0
-#define F2FS_GET_BLOCK_DIO 1
-#define F2FS_GET_BLOCK_FIEMAP 2
-#define F2FS_GET_BLOCK_BMAP 3
-#define F2FS_GET_BLOCK_PRE_DIO 4
-#define F2FS_GET_BLOCK_PRE_AIO 5
+enum {
+ F2FS_GET_BLOCK_DEFAULT,
+ F2FS_GET_BLOCK_FIEMAP,
+ F2FS_GET_BLOCK_BMAP,
+ F2FS_GET_BLOCK_PRE_DIO,
+ F2FS_GET_BLOCK_PRE_AIO,
+};
/*
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
@@ -521,6 +571,7 @@ struct f2fs_inode_info {
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
struct task_struct *task; /* lookup and create consistency */
+ struct task_struct *cp_task; /* separate cp/wb IO stats*/
nid_t i_xattr_nid; /* node id that contains xattrs */
loff_t last_disk_size; /* lastly written file size */
@@ -533,10 +584,15 @@ struct f2fs_inode_info {
struct list_head dirty_list; /* dirty list for dirs and files */
struct list_head gdirty_list; /* linked in global dirty list */
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 */
struct extent_tree *extent_tree; /* cached extent_tree entry */
struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
struct rw_semaphore i_mmap_sem;
+ struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */
+
+ int i_extra_isize; /* size of extra space located in i_addr */
+ kprojid_t i_projid; /* id for project quota */
};
static inline void get_extent_info(struct extent_info *ext,
@@ -823,6 +879,23 @@ enum need_lock_type {
LOCK_RETRY,
};
+enum iostat_type {
+ APP_DIRECT_IO, /* app direct IOs */
+ APP_BUFFERED_IO, /* app buffered IOs */
+ APP_WRITE_IO, /* app write IOs */
+ APP_MAPPED_IO, /* app mapped IOs */
+ FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */
+ FS_NODE_IO, /* node IOs from kworker/fsync/reclaimer */
+ FS_META_IO, /* meta IOs from kworker/reclaimer */
+ FS_GC_DATA_IO, /* data IOs from forground gc */
+ FS_GC_NODE_IO, /* node IOs from forground gc */
+ FS_CP_DATA_IO, /* data IOs from checkpoint */
+ FS_CP_NODE_IO, /* node IOs from checkpoint */
+ FS_CP_META_IO, /* meta IOs from checkpoint */
+ FS_DISCARD, /* discard */
+ NR_IO_TYPE,
+};
+
struct f2fs_io_info {
struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
@@ -837,6 +910,7 @@ struct f2fs_io_info {
bool submitted; /* indicate IO submission */
int need_lock; /* indicate we need to lock cp_rwsem */
bool in_list; /* indicate fio is in io_list */
+ enum iostat_type io_type; /* io type */
};
#define is_read_io(rw) ((rw) == READ)
@@ -1028,6 +1102,11 @@ struct f2fs_sb_info {
#endif
spinlock_t stat_lock; /* lock for stat operations */
+ /* For app/fs IO statistics */
+ spinlock_t iostat_lock;
+ unsigned long long write_iostat[NR_IO_TYPE];
+ bool iostat_enable;
+
/* For sysfs suppport */
struct kobject s_kobj;
struct completion s_kobj_unregister;
@@ -1046,10 +1125,19 @@ struct f2fs_sb_info {
/* Reference to checksum algorithm driver via cryptoapi */
struct crypto_shash *s_chksum_driver;
+ /* Precomputed FS UUID checksum for seeding other checksums */
+ __u32 s_chksum_seed;
+
/* For fault injection */
#ifdef CONFIG_F2FS_FAULT_INJECTION
struct f2fs_fault_info fault_info;
#endif
+
+#ifdef CONFIG_QUOTA
+ /* Names of quota files with journalled quota */
+ char *s_qf_names[MAXQUOTAS];
+ int s_jquota_fmt; /* Format of quota to use */
+#endif
};
#ifdef CONFIG_F2FS_FAULT_INJECTION
@@ -1137,6 +1225,27 @@ static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
}
+static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc,
+ const void *address, unsigned int length)
+{
+ struct {
+ struct shash_desc shash;
+ char ctx[4];
+ } desc;
+ int err;
+
+ BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));
+
+ desc.shash.tfm = sbi->s_chksum_driver;
+ desc.shash.flags = 0;
+ *(u32 *)desc.ctx = crc;
+
+ err = crypto_shash_update(&desc.shash, address, length);
+ BUG_ON(err);
+
+ return *(u32 *)desc.ctx;
+}
+
static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
{
return container_of(inode, struct f2fs_inode_info, vfs_inode);
@@ -1760,20 +1869,38 @@ static inline bool IS_INODE(struct page *page)
return RAW_IS_INODE(p);
}
+static inline int offset_in_addr(struct f2fs_inode *i)
+{
+ return (i->i_inline & F2FS_EXTRA_ATTR) ?
+ (le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0;
+}
+
static inline __le32 *blkaddr_in_node(struct f2fs_node *node)
{
return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr;
}
-static inline block_t datablock_addr(struct page *node_page,
- unsigned int offset)
+static inline int f2fs_has_extra_attr(struct inode *inode);
+static inline block_t datablock_addr(struct inode *inode,
+ struct page *node_page, unsigned int offset)
{
struct f2fs_node *raw_node;
__le32 *addr_array;
+ int base = 0;
+ bool is_inode = IS_INODE(node_page);
raw_node = F2FS_NODE(node_page);
+
+ /* from GC path only */
+ if (!inode) {
+ if (is_inode)
+ base = offset_in_addr(&raw_node->i);
+ } else if (f2fs_has_extra_attr(inode) && is_inode) {
+ base = get_extra_isize(inode);
+ }
+
addr_array = blkaddr_in_node(raw_node);
- return le32_to_cpu(addr_array[offset]);
+ return le32_to_cpu(addr_array[base + offset]);
}
static inline int f2fs_test_bit(unsigned int nr, char *addr)
@@ -1836,6 +1963,20 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
*addr ^= mask;
}
+#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
+#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
+#define F2FS_FL_INHERITED (FS_PROJINHERIT_FL)
+
+static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
+{
+ if (S_ISDIR(mode))
+ return flags;
+ else if (S_ISREG(mode))
+ return flags & F2FS_REG_FLMASK;
+ else
+ return flags & F2FS_OTHER_FLMASK;
+}
+
/* used for f2fs_inode_info->flags */
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
@@ -1864,6 +2005,8 @@ enum {
FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
FI_NO_PREALLOC, /* indicate skipped preallocated blocks */
FI_HOT_DATA, /* indicate file is hot */
+ FI_EXTRA_ATTR, /* indicate file has extra attribute */
+ FI_PROJ_INHERIT, /* indicate file inherits projectid */
};
static inline void __mark_inode_dirty_flag(struct inode *inode,
@@ -1983,6 +2126,8 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
set_bit(FI_DATA_EXIST, &fi->flags);
if (ri->i_inline & F2FS_INLINE_DOTS)
set_bit(FI_INLINE_DOTS, &fi->flags);
+ if (ri->i_inline & F2FS_EXTRA_ATTR)
+ set_bit(FI_EXTRA_ATTR, &fi->flags);
}
static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
@@ -1999,6 +2144,13 @@ static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
ri->i_inline |= F2FS_DATA_EXIST;
if (is_inode_flag_set(inode, FI_INLINE_DOTS))
ri->i_inline |= F2FS_INLINE_DOTS;
+ if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
+ ri->i_inline |= F2FS_EXTRA_ATTR;
+}
+
+static inline int f2fs_has_extra_attr(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_EXTRA_ATTR);
}
static inline int f2fs_has_inline_xattr(struct inode *inode)
@@ -2009,8 +2161,8 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
static inline unsigned int addrs_per_inode(struct inode *inode)
{
if (f2fs_has_inline_xattr(inode))
- return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
- return DEF_ADDRS_PER_INODE;
+ return CUR_ADDRS_PER_INODE(inode) - F2FS_INLINE_XATTR_ADDRS;
+ return CUR_ADDRS_PER_INODE(inode);
}
static inline void *inline_xattr_addr(struct page *page)
@@ -2069,11 +2221,12 @@ static inline bool f2fs_is_drop_cache(struct inode *inode)
return is_inode_flag_set(inode, FI_DROP_CACHE);
}
-static inline void *inline_data_addr(struct page *page)
+static inline void *inline_data_addr(struct inode *inode, struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
+ int extra_size = get_extra_isize(inode);
- return (void *)&(ri->i_addr[1]);
+ return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]);
}
static inline int f2fs_has_inline_dentry(struct inode *inode)
@@ -2164,10 +2317,50 @@ static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
return kmalloc(size, flags);
}
+static inline int get_extra_isize(struct inode *inode)
+{
+ return F2FS_I(inode)->i_extra_isize / sizeof(__le32);
+}
+
#define get_inode_mode(i) \
((is_inode_flag_set(i, FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
+#define F2FS_TOTAL_EXTRA_ATTR_SIZE \
+ (offsetof(struct f2fs_inode, i_extra_end) - \
+ offsetof(struct f2fs_inode, i_extra_isize)) \
+
+#define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr))
+#define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \
+ ((offsetof(typeof(*f2fs_inode), field) + \
+ sizeof((f2fs_inode)->field)) \
+ <= (F2FS_OLD_ATTRIBUTE_SIZE + extra_isize)) \
+
+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;
+ spin_unlock(&sbi->iostat_lock);
+}
+
+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;
+
+ 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];
+ spin_unlock(&sbi->iostat_lock);
+}
+
/*
* file.c
*/
@@ -2187,6 +2380,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
* inode.c
*/
void f2fs_set_inode_flags(struct inode *inode);
+bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page);
+void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page);
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
@@ -2255,6 +2450,8 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
*/
int f2fs_inode_dirtied(struct inode *inode, bool sync);
void f2fs_inode_synced(struct inode *inode);
+void f2fs_enable_quota_files(struct f2fs_sb_info *sbi);
+void f2fs_quota_off_umount(struct super_block *sb);
int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
int f2fs_sync_fs(struct super_block *sb, int sync);
extern __printf(3, 4)
@@ -2285,15 +2482,15 @@ int truncate_xattr_node(struct inode *inode, struct page *page);
int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
int remove_inode_page(struct inode *inode);
struct page *new_inode_page(struct inode *inode);
-struct page *new_node_page(struct dnode_of_data *dn,
- unsigned int ofs, struct page *ipage);
+struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs);
void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
struct page *get_node_page_ra(struct page *parent, int start);
void move_node_page(struct page *node_page, int gc_type);
int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
struct writeback_control *wbc, bool atomic);
-int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc);
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc,
+ bool do_balance, enum iostat_type io_type);
void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
@@ -2314,6 +2511,7 @@ void destroy_node_manager_caches(void);
/*
* segment.c
*/
+bool need_SSR(struct f2fs_sb_info *sbi);
void register_inmem_page(struct inode *inode, struct page *page);
void drop_inmem_pages(struct inode *inode);
void drop_inmem_page(struct inode *inode, struct page *page);
@@ -2336,7 +2534,8 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc);
struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr);
-void write_meta_page(struct f2fs_sb_info *sbi, struct page *page);
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+ enum iostat_type io_type);
void write_node_page(unsigned int nid, struct f2fs_io_info *fio);
void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio);
int rewrite_data_page(struct f2fs_io_info *fio);
@@ -2353,8 +2552,7 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
struct f2fs_io_info *fio, bool add_list);
void f2fs_wait_on_page_writeback(struct page *page,
enum page_type type, bool ordered);
-void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
- block_t blkaddr);
+void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr);
void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
@@ -2377,7 +2575,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync);
void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
- long nr_to_write);
+ long nr_to_write, enum iostat_type io_type);
void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
@@ -2430,6 +2628,9 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len);
void f2fs_set_page_dirty_nobuffers(struct page *page);
+int __f2fs_write_data_pages(struct address_space *mapping,
+ struct writeback_control *wbc,
+ enum iostat_type io_type);
void f2fs_invalidate_page(struct page *page, unsigned int offset,
unsigned int length);
int f2fs_release_page(struct page *page, gfp_t wait);
@@ -2726,10 +2927,10 @@ void destroy_extent_cache(void);
/*
* sysfs.c
*/
-int __init f2fs_register_sysfs(void);
-void f2fs_unregister_sysfs(void);
-int f2fs_init_sysfs(struct f2fs_sb_info *sbi);
-void f2fs_exit_sysfs(struct f2fs_sb_info *sbi);
+int __init f2fs_init_sysfs(void);
+void f2fs_exit_sysfs(void);
+int f2fs_register_sysfs(struct f2fs_sb_info *sbi);
+void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi);
/*
* crypto support
@@ -2739,6 +2940,11 @@ static inline bool f2fs_encrypted_inode(struct inode *inode)
return file_is_encrypt(inode);
}
+static inline bool f2fs_encrypted_file(struct inode *inode)
+{
+ return f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode);
+}
+
static inline void f2fs_set_encrypted_inode(struct inode *inode)
{
#ifdef CONFIG_F2FS_FS_ENCRYPTION
@@ -2761,6 +2967,21 @@ static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb)
return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED);
}
+static inline int f2fs_sb_has_extra_attr(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_EXTRA_ATTR);
+}
+
+static inline int f2fs_sb_has_project_quota(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_PRJQUOTA);
+}
+
+static inline int f2fs_sb_has_inode_chksum(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_INODE_CHKSUM);
+}
+
#ifdef CONFIG_BLK_DEV_ZONED
static inline int get_blkz_type(struct f2fs_sb_info *sbi,
struct block_device *bdev, block_t blkaddr)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 843a0d99f7ea..517e112c8a9a 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -98,14 +98,16 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
if (!PageUptodate(page))
SetPageUptodate(page);
+ f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE);
+
trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
/* fill the page */
f2fs_wait_on_page_writeback(page, DATA, false);
/* wait for GCed encrypted page writeback */
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+ if (f2fs_encrypted_file(inode))
+ f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr);
out_sem:
up_read(&F2FS_I(inode)->i_mmap_sem);
@@ -274,9 +276,19 @@ sync_nodes:
goto sync_nodes;
}
- ret = wait_on_node_pages_writeback(sbi, ino);
- if (ret)
- goto out;
+ /*
+ * If it's atomic_write, it's just fine to keep write ordering. So
+ * here we don't need to wait for node write completion, since we use
+ * node chain which serializes node blocks. If one of node writes are
+ * reordered, we can see simply broken chain, resulting in stopping
+ * roll-forward recovery. It means we'll recover all or none node blocks
+ * given fsync mark.
+ */
+ if (!atomic) {
+ ret = wait_on_node_pages_writeback(sbi, ino);
+ if (ret)
+ goto out;
+ }
/* once recovery info is written, don't need to tack this */
remove_ino_entry(sbi, ino, APPEND_INO);
@@ -382,7 +394,8 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
dn.ofs_in_node++, pgofs++,
data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
- blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
if (__found_offset(blkaddr, dirty, pgofs, whence)) {
f2fs_put_dnode(&dn);
@@ -467,9 +480,13 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
struct f2fs_node *raw_node;
int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
+ int base = 0;
+
+ if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode))
+ base = get_extra_isize(dn->inode);
raw_node = F2FS_NODE(dn->node_page);
- addr = blkaddr_in_node(raw_node) + ofs;
+ addr = blkaddr_in_node(raw_node) + base + ofs;
for (; count > 0; count--, addr++, dn->ofs_in_node++) {
block_t blkaddr = le32_to_cpu(*addr);
@@ -647,7 +664,7 @@ int f2fs_getattr(const struct path *path, struct kstat *stat,
struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int flags;
- flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ flags = fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL);
if (flags & FS_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
if (flags & FS_COMPR_FL)
@@ -927,7 +944,8 @@ next_dnode:
done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
dn.ofs_in_node, len);
for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
- *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ *blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
if (!is_checkpointed_data(sbi, *blkaddr)) {
if (test_opt(sbi, LFS)) {
@@ -1003,8 +1021,8 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
ADDRS_PER_PAGE(dn.node_page, dst_inode) -
dn.ofs_in_node, len - i);
do {
- dn.data_blkaddr = datablock_addr(dn.node_page,
- dn.ofs_in_node);
+ dn.data_blkaddr = datablock_addr(dn.inode,
+ dn.node_page, dn.ofs_in_node);
truncate_data_blocks_range(&dn, 1);
if (do_replace[i]) {
@@ -1173,7 +1191,8 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
int ret;
for (; index < end; index++, dn->ofs_in_node++) {
- if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR)
+ if (datablock_addr(dn->inode, dn->node_page,
+ dn->ofs_in_node) == NULL_ADDR)
count++;
}
@@ -1184,8 +1203,8 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
dn->ofs_in_node = ofs_in_node;
for (index = start; index < end; index++, dn->ofs_in_node++) {
- dn->data_blkaddr =
- datablock_addr(dn->node_page, dn->ofs_in_node);
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
/*
* reserve_new_blocks will not guarantee entire block
* allocation.
@@ -1495,33 +1514,67 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
return 0;
}
-#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
-#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
-
-static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
+static int f2fs_file_flush(struct file *file, fl_owner_t id)
{
- if (S_ISDIR(mode))
- return flags;
- else if (S_ISREG(mode))
- return flags & F2FS_REG_FLMASK;
- else
- return flags & F2FS_OTHER_FLMASK;
+ struct inode *inode = file_inode(file);
+
+ /*
+ * If the process doing a transaction is crashed, we should do
+ * roll-back. Otherwise, other reader/write can see corrupted database
+ * until all the writers close its file. Since this should be done
+ * before dropping file lock, it needs to do in ->flush.
+ */
+ if (f2fs_is_atomic_file(inode) &&
+ F2FS_I(inode)->inmem_task == current)
+ drop_inmem_pages(inode);
+ return 0;
}
static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ unsigned int flags = fi->i_flags &
+ (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL);
return put_user(flags, (int __user *)arg);
}
+static int __f2fs_ioc_setflags(struct inode *inode, unsigned int flags)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ unsigned int oldflags;
+
+ /* Is it quota file? Do not allow user to mess with it */
+ if (IS_NOQUOTA(inode))
+ return -EPERM;
+
+ flags = f2fs_mask_flags(inode->i_mode, flags);
+
+ oldflags = fi->i_flags;
+
+ if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL))
+ if (!capable(CAP_LINUX_IMMUTABLE))
+ return -EPERM;
+
+ flags = flags & (FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL);
+ flags |= oldflags & ~(FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL);
+ fi->i_flags = flags;
+
+ if (fi->i_flags & FS_PROJINHERIT_FL)
+ set_inode_flag(inode, FI_PROJ_INHERIT);
+ else
+ clear_inode_flag(inode, FI_PROJ_INHERIT);
+
+ inode->i_ctime = current_time(inode);
+ f2fs_set_inode_flags(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
+ return 0;
+}
+
static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
- struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int flags;
- unsigned int oldflags;
int ret;
if (!inode_owner_or_capable(inode))
@@ -1536,31 +1589,8 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
inode_lock(inode);
- /* Is it quota file? Do not allow user to mess with it */
- if (IS_NOQUOTA(inode)) {
- ret = -EPERM;
- goto unlock_out;
- }
-
- flags = f2fs_mask_flags(inode->i_mode, flags);
-
- oldflags = fi->i_flags;
-
- if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
- if (!capable(CAP_LINUX_IMMUTABLE)) {
- ret = -EPERM;
- goto unlock_out;
- }
- }
-
- flags = flags & FS_FL_USER_MODIFIABLE;
- flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
- fi->i_flags = flags;
+ ret = __f2fs_ioc_setflags(inode, flags);
- inode->i_ctime = current_time(inode);
- f2fs_set_inode_flags(inode);
- f2fs_mark_inode_dirty_sync(inode, false);
-unlock_out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
@@ -1610,10 +1640,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
if (ret) {
clear_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_HOT_DATA);
goto out;
}
inc_stat:
+ F2FS_I(inode)->inmem_task = current;
stat_inc_atomic_write(inode);
stat_update_max_atomic_write(inode);
out:
@@ -1647,10 +1679,11 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
if (!ret) {
clear_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_HOT_DATA);
stat_dec_atomic_write(inode);
}
} else {
- ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false);
}
err_out:
inode_unlock(inode);
@@ -1786,7 +1819,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
f2fs_stop_checkpoint(sbi, false);
break;
case F2FS_GOING_DOWN_METAFLUSH:
- sync_meta_pages(sbi, META, LONG_MAX);
+ sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO);
f2fs_stop_checkpoint(sbi, false);
break;
default:
@@ -2043,7 +2076,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
*/
while (map.m_lblk < pg_end) {
map.m_len = pg_end - map.m_lblk;
- err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto out;
@@ -2085,7 +2118,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
do_map:
map.m_len = pg_end - map.m_lblk;
- err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT);
if (err)
goto clear_out;
@@ -2384,6 +2417,210 @@ out:
return ret;
}
+static int f2fs_ioc_get_features(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ u32 sb_feature = le32_to_cpu(F2FS_I_SB(inode)->raw_super->feature);
+
+ /* Must validate to set it with SQLite behavior in Android. */
+ sb_feature |= F2FS_FEATURE_ATOMIC_WRITE;
+
+ return put_user(sb_feature, (u32 __user *)arg);
+}
+
+#ifdef CONFIG_QUOTA
+static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct super_block *sb = sbi->sb;
+ struct dquot *transfer_to[MAXQUOTAS] = {};
+ struct page *ipage;
+ kprojid_t kprojid;
+ int err;
+
+ if (!f2fs_sb_has_project_quota(sb)) {
+ if (projid != F2FS_DEF_PROJID)
+ return -EOPNOTSUPP;
+ else
+ return 0;
+ }
+
+ if (!f2fs_has_extra_attr(inode))
+ return -EOPNOTSUPP;
+
+ kprojid = make_kprojid(&init_user_ns, (projid_t)projid);
+
+ if (projid_eq(kprojid, F2FS_I(inode)->i_projid))
+ return 0;
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
+
+ err = -EPERM;
+ inode_lock(inode);
+
+ /* Is it quota file? Do not allow user to mess with it */
+ if (IS_NOQUOTA(inode))
+ goto out_unlock;
+
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto out_unlock;
+ }
+
+ if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize,
+ i_projid)) {
+ err = -EOVERFLOW;
+ f2fs_put_page(ipage, 1);
+ goto out_unlock;
+ }
+ f2fs_put_page(ipage, 1);
+
+ dquot_initialize(inode);
+
+ transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
+ if (!IS_ERR(transfer_to[PRJQUOTA])) {
+ err = __dquot_transfer(inode, transfer_to);
+ dqput(transfer_to[PRJQUOTA]);
+ if (err)
+ goto out_dirty;
+ }
+
+ F2FS_I(inode)->i_projid = kprojid;
+ inode->i_ctime = current_time(inode);
+out_dirty:
+ f2fs_mark_inode_dirty_sync(inode, true);
+out_unlock:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return err;
+}
+#else
+static int f2fs_ioc_setproject(struct file *filp, __u32 projid)
+{
+ if (projid != F2FS_DEF_PROJID)
+ return -EOPNOTSUPP;
+ return 0;
+}
+#endif
+
+/* Transfer internal flags to xflags */
+static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags)
+{
+ __u32 xflags = 0;
+
+ if (iflags & FS_SYNC_FL)
+ xflags |= FS_XFLAG_SYNC;
+ if (iflags & FS_IMMUTABLE_FL)
+ xflags |= FS_XFLAG_IMMUTABLE;
+ if (iflags & FS_APPEND_FL)
+ xflags |= FS_XFLAG_APPEND;
+ if (iflags & FS_NODUMP_FL)
+ xflags |= FS_XFLAG_NODUMP;
+ if (iflags & FS_NOATIME_FL)
+ xflags |= FS_XFLAG_NOATIME;
+ if (iflags & FS_PROJINHERIT_FL)
+ xflags |= FS_XFLAG_PROJINHERIT;
+ return xflags;
+}
+
+#define F2FS_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \
+ FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
+ FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT)
+
+/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
+#define F2FS_FL_XFLAG_VISIBLE (FS_SYNC_FL | \
+ FS_IMMUTABLE_FL | \
+ FS_APPEND_FL | \
+ FS_NODUMP_FL | \
+ FS_NOATIME_FL | \
+ FS_PROJINHERIT_FL)
+
+/* Transfer xflags flags to internal */
+static inline unsigned long f2fs_xflags_to_iflags(__u32 xflags)
+{
+ unsigned long iflags = 0;
+
+ if (xflags & FS_XFLAG_SYNC)
+ iflags |= FS_SYNC_FL;
+ if (xflags & FS_XFLAG_IMMUTABLE)
+ iflags |= FS_IMMUTABLE_FL;
+ if (xflags & FS_XFLAG_APPEND)
+ iflags |= FS_APPEND_FL;
+ if (xflags & FS_XFLAG_NODUMP)
+ iflags |= FS_NODUMP_FL;
+ if (xflags & FS_XFLAG_NOATIME)
+ iflags |= FS_NOATIME_FL;
+ if (xflags & FS_XFLAG_PROJINHERIT)
+ iflags |= FS_PROJINHERIT_FL;
+
+ return iflags;
+}
+
+static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct fsxattr fa;
+
+ memset(&fa, 0, sizeof(struct fsxattr));
+ fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags &
+ (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL));
+
+ if (f2fs_sb_has_project_quota(inode->i_sb))
+ fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
+ fi->i_projid);
+
+ if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa)))
+ return -EFAULT;
+ return 0;
+}
+
+static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct fsxattr fa;
+ unsigned int flags;
+ int err;
+
+ if (copy_from_user(&fa, (struct fsxattr __user *)arg, sizeof(fa)))
+ return -EFAULT;
+
+ /* Make sure caller has proper permission */
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (fa.fsx_xflags & ~F2FS_SUPPORTED_FS_XFLAGS)
+ return -EOPNOTSUPP;
+
+ flags = f2fs_xflags_to_iflags(fa.fsx_xflags);
+ if (f2fs_mask_flags(inode->i_mode, flags) != flags)
+ return -EOPNOTSUPP;
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
+
+ inode_lock(inode);
+ flags = (fi->i_flags & ~F2FS_FL_XFLAG_VISIBLE) |
+ (flags & F2FS_FL_XFLAG_VISIBLE);
+ err = __f2fs_ioc_setflags(inode, flags);
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ if (err)
+ return err;
+
+ err = f2fs_ioc_setproject(filp, fa.fsx_projid);
+ if (err)
+ return err;
+
+ return 0;
+}
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
@@ -2426,6 +2663,12 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_move_range(filp, arg);
case F2FS_IOC_FLUSH_DEVICE:
return f2fs_ioc_flush_device(filp, arg);
+ case F2FS_IOC_GET_FEATURES:
+ return f2fs_ioc_get_features(filp, arg);
+ case F2FS_IOC_FSGETXATTR:
+ return f2fs_ioc_fsgetxattr(filp, arg);
+ case F2FS_IOC_FSSETXATTR:
+ return f2fs_ioc_fssetxattr(filp, arg);
default:
return -ENOTTY;
}
@@ -2455,6 +2698,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
ret = __generic_file_write_iter(iocb, from);
blk_finish_plug(&plug);
clear_inode_flag(inode, FI_NO_PREALLOC);
+
+ if (ret > 0)
+ f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret);
}
inode_unlock(inode);
@@ -2491,6 +2737,9 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_DEFRAGMENT:
case F2FS_IOC_MOVE_RANGE:
case F2FS_IOC_FLUSH_DEVICE:
+ case F2FS_IOC_GET_FEATURES:
+ case F2FS_IOC_FSGETXATTR:
+ case F2FS_IOC_FSSETXATTR:
break;
default:
return -ENOIOCTLCMD;
@@ -2506,6 +2755,7 @@ const struct file_operations f2fs_file_operations = {
.open = f2fs_file_open,
.release = f2fs_release_file,
.mmap = f2fs_file_mmap,
+ .flush = f2fs_file_flush,
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
.unlocked_ioctl = f2fs_ioctl,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index fa3d2e2df8e7..bfe6a8ccc3a0 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -28,16 +28,21 @@ static int gc_thread_func(void *data)
struct f2fs_sb_info *sbi = data;
struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
- long wait_ms;
+ unsigned int wait_ms;
wait_ms = gc_th->min_sleep_time;
set_freezable();
do {
wait_event_interruptible_timeout(*wq,
- kthread_should_stop() || freezing(current),
+ kthread_should_stop() || freezing(current) ||
+ gc_th->gc_wake,
msecs_to_jiffies(wait_ms));
+ /* give it a try one time */
+ if (gc_th->gc_wake)
+ gc_th->gc_wake = 0;
+
if (try_to_freeze())
continue;
if (kthread_should_stop())
@@ -55,6 +60,9 @@ static int gc_thread_func(void *data)
}
#endif
+ if (!sb_start_write_trylock(sbi->sb))
+ continue;
+
/*
* [GC triggering condition]
* 0. GC is not conducted currently.
@@ -69,19 +77,24 @@ static int gc_thread_func(void *data)
* So, I'd like to wait some time to collect dirty segments.
*/
if (!mutex_trylock(&sbi->gc_mutex))
- continue;
+ goto next;
+
+ if (gc_th->gc_urgent) {
+ wait_ms = gc_th->urgent_sleep_time;
+ goto do_gc;
+ }
if (!is_idle(sbi)) {
increase_sleep_time(gc_th, &wait_ms);
mutex_unlock(&sbi->gc_mutex);
- continue;
+ goto next;
}
if (has_enough_invalid_blocks(sbi))
decrease_sleep_time(gc_th, &wait_ms);
else
increase_sleep_time(gc_th, &wait_ms);
-
+do_gc:
stat_inc_bggc_count(sbi);
/* if return value is not zero, no victim was selected */
@@ -93,6 +106,8 @@ static int gc_thread_func(void *data)
/* balancing f2fs's metadata periodically */
f2fs_balance_fs_bg(sbi);
+next:
+ sb_end_write(sbi->sb);
} while (!kthread_should_stop());
return 0;
@@ -110,11 +125,14 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
goto out;
}
+ gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME;
gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
gc_th->gc_idle = 0;
+ gc_th->gc_urgent = 0;
+ gc_th->gc_wake= 0;
sbi->gc_thread = gc_th;
init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
@@ -259,20 +277,11 @@ static unsigned int get_greedy_cost(struct f2fs_sb_info *sbi,
valid_blocks * 2 : valid_blocks;
}
-static unsigned int get_ssr_cost(struct f2fs_sb_info *sbi,
- unsigned int segno)
-{
- struct seg_entry *se = get_seg_entry(sbi, segno);
-
- return se->ckpt_valid_blocks > se->valid_blocks ?
- se->ckpt_valid_blocks : se->valid_blocks;
-}
-
static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
unsigned int segno, struct victim_sel_policy *p)
{
if (p->alloc_mode == SSR)
- return get_ssr_cost(sbi, segno);
+ return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
/* alloc_mode == LFS */
if (p->gc_mode == GC_GREEDY)
@@ -582,7 +591,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
}
*nofs = ofs_of_node(node_page);
- source_blkaddr = datablock_addr(node_page, ofs_in_node);
+ source_blkaddr = datablock_addr(NULL, node_page, ofs_in_node);
f2fs_put_page(node_page, 1);
if (source_blkaddr != blkaddr)
@@ -590,8 +599,12 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
return true;
}
-static void move_encrypted_block(struct inode *inode, block_t bidx,
- unsigned int segno, int off)
+/*
+ * Move data block via META_MAPPING while keeping locked data page.
+ * This can be used to move blocks, aka LBAs, directly on disk.
+ */
+static void move_data_block(struct inode *inode, block_t bidx,
+ unsigned int segno, int off)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(inode),
@@ -684,6 +697,8 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
fio.new_blkaddr = newaddr;
f2fs_submit_page_write(&fio);
+ f2fs_update_iostat(fio.sbi, FS_GC_DATA_IO, F2FS_BLKSIZE);
+
f2fs_update_data_blkaddr(&dn, newaddr);
set_inode_flag(inode, FI_APPEND_WRITE);
if (page->index == 0)
@@ -731,6 +746,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
.page = page,
.encrypted_page = NULL,
.need_lock = LOCK_REQ,
+ .io_type = FS_GC_DATA_IO,
};
bool is_dirty = PageDirty(page);
int err;
@@ -819,8 +835,7 @@ next_step:
continue;
/* if encrypted inode, let's go phase 3 */
- if (f2fs_encrypted_inode(inode) &&
- S_ISREG(inode->i_mode)) {
+ if (f2fs_encrypted_file(inode)) {
add_gc_inode(gc_list, inode);
continue;
}
@@ -854,14 +869,18 @@ next_step:
continue;
}
locked = true;
+
+ /* wait for all inflight aio data */
+ inode_dio_wait(inode);
}
start_bidx = start_bidx_of_node(nofs, inode)
+ ofs_in_node;
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
- move_encrypted_block(inode, start_bidx, segno, off);
+ if (f2fs_encrypted_file(inode))
+ move_data_block(inode, start_bidx, segno, off);
else
- move_data_page(inode, start_bidx, gc_type, segno, off);
+ move_data_page(inode, start_bidx, gc_type,
+ segno, off);
if (locked) {
up_write(&fi->dio_rwsem[WRITE]);
@@ -898,7 +917,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
struct blk_plug plug;
unsigned int segno = start_segno;
unsigned int end_segno = start_segno + sbi->segs_per_sec;
- int sec_freed = 0;
+ int seg_freed = 0;
unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
SUM_TYPE_DATA : SUM_TYPE_NODE;
@@ -944,6 +963,10 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
gc_type);
stat_inc_seg_count(sbi, type, gc_type);
+
+ if (gc_type == FG_GC &&
+ get_valid_blocks(sbi, segno, false) == 0)
+ seg_freed++;
next:
f2fs_put_page(sum_page, 0);
}
@@ -954,21 +977,17 @@ next:
blk_finish_plug(&plug);
- if (gc_type == FG_GC &&
- get_valid_blocks(sbi, start_segno, true) == 0)
- sec_freed = 1;
-
stat_inc_call_count(sbi->stat_info);
- return sec_freed;
+ return seg_freed;
}
int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
bool background, unsigned int segno)
{
int gc_type = sync ? FG_GC : BG_GC;
- int sec_freed = 0;
- int ret;
+ int sec_freed = 0, seg_freed = 0, total_freed = 0;
+ int ret = 0;
struct cp_control cpc;
unsigned int init_segno = segno;
struct gc_inode_list gc_list = {
@@ -976,6 +995,15 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
.iroot = RADIX_TREE_INIT(GFP_NOFS),
};
+ trace_f2fs_gc_begin(sbi->sb, sync, background,
+ get_pages(sbi, F2FS_DIRTY_NODES),
+ get_pages(sbi, F2FS_DIRTY_DENTS),
+ get_pages(sbi, F2FS_DIRTY_IMETA),
+ free_sections(sbi),
+ free_segments(sbi),
+ reserved_segments(sbi),
+ prefree_segments(sbi));
+
cpc.reason = __get_cp_reason(sbi);
gc_more:
if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) {
@@ -1002,17 +1030,20 @@ gc_more:
gc_type = FG_GC;
}
- ret = -EINVAL;
/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
- if (gc_type == BG_GC && !background)
+ if (gc_type == BG_GC && !background) {
+ ret = -EINVAL;
goto stop;
- if (!__get_victim(sbi, &segno, gc_type))
+ }
+ if (!__get_victim(sbi, &segno, gc_type)) {
+ ret = -ENODATA;
goto stop;
- ret = 0;
+ }
- if (do_garbage_collect(sbi, segno, &gc_list, gc_type) &&
- gc_type == FG_GC)
+ seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
+ if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
sec_freed++;
+ total_freed += seg_freed;
if (gc_type == FG_GC)
sbi->cur_victim_sec = NULL_SEGNO;
@@ -1029,6 +1060,16 @@ gc_more:
stop:
SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0;
SIT_I(sbi)->last_victim[FLUSH_DEVICE] = init_segno;
+
+ trace_f2fs_gc_end(sbi->sb, ret, total_freed, sec_freed,
+ get_pages(sbi, F2FS_DIRTY_NODES),
+ get_pages(sbi, F2FS_DIRTY_DENTS),
+ get_pages(sbi, F2FS_DIRTY_IMETA),
+ free_sections(sbi),
+ free_segments(sbi),
+ reserved_segments(sbi),
+ prefree_segments(sbi));
+
mutex_unlock(&sbi->gc_mutex);
put_gc_inode(&gc_list);
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index a993967dcdb9..9325191fab2d 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -13,6 +13,7 @@
* whether IO subsystem is idle
* or not
*/
+#define DEF_GC_THREAD_URGENT_SLEEP_TIME 500 /* 500 ms */
#define DEF_GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */
#define DEF_GC_THREAD_MAX_SLEEP_TIME 60000
#define DEF_GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */
@@ -27,12 +28,15 @@ struct f2fs_gc_kthread {
wait_queue_head_t gc_wait_queue_head;
/* for gc sleep time */
+ unsigned int urgent_sleep_time;
unsigned int min_sleep_time;
unsigned int max_sleep_time;
unsigned int no_gc_sleep_time;
/* for changing gc mode */
unsigned int gc_idle;
+ unsigned int gc_urgent;
+ unsigned int gc_wake;
};
struct gc_inode_list {
@@ -65,25 +69,32 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
}
static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
- long *wait)
+ unsigned int *wait)
{
+ unsigned int min_time = gc_th->min_sleep_time;
+ unsigned int max_time = gc_th->max_sleep_time;
+
if (*wait == gc_th->no_gc_sleep_time)
return;
- *wait += gc_th->min_sleep_time;
- if (*wait > gc_th->max_sleep_time)
- *wait = gc_th->max_sleep_time;
+ if ((long long)*wait + (long long)min_time > (long long)max_time)
+ *wait = max_time;
+ else
+ *wait += min_time;
}
static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
- long *wait)
+ unsigned int *wait)
{
+ unsigned int min_time = gc_th->min_sleep_time;
+
if (*wait == gc_th->no_gc_sleep_time)
*wait = gc_th->max_sleep_time;
- *wait -= gc_th->min_sleep_time;
- if (*wait <= gc_th->min_sleep_time)
- *wait = gc_th->min_sleep_time;
+ if ((long long)*wait - (long long)min_time < (long long)min_time)
+ *wait = min_time;
+ else
+ *wait -= min_time;
}
static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index e0fd4376e6fb..8322e4e7bb3f 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -22,10 +22,10 @@ bool f2fs_may_inline_data(struct inode *inode)
if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
return false;
- if (i_size_read(inode) > MAX_INLINE_DATA)
+ if (i_size_read(inode) > MAX_INLINE_DATA(inode))
return false;
- if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ if (f2fs_encrypted_file(inode))
return false;
return true;
@@ -44,6 +44,7 @@ bool f2fs_may_inline_dentry(struct inode *inode)
void read_inline_data(struct page *page, struct page *ipage)
{
+ struct inode *inode = page->mapping->host;
void *src_addr, *dst_addr;
if (PageUptodate(page))
@@ -51,12 +52,12 @@ void read_inline_data(struct page *page, struct page *ipage)
f2fs_bug_on(F2FS_P_SB(page), page->index);
- zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
+ zero_user_segment(page, MAX_INLINE_DATA(inode), PAGE_SIZE);
/* Copy the whole inline data block */
- src_addr = inline_data_addr(ipage);
+ src_addr = inline_data_addr(inode, ipage);
dst_addr = kmap_atomic(page);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+ memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
flush_dcache_page(page);
kunmap_atomic(dst_addr);
if (!PageUptodate(page))
@@ -67,13 +68,13 @@ void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from)
{
void *addr;
- if (from >= MAX_INLINE_DATA)
+ if (from >= MAX_INLINE_DATA(inode))
return;
- addr = inline_data_addr(ipage);
+ addr = inline_data_addr(inode, ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true);
- memset(addr + from, 0, MAX_INLINE_DATA - from);
+ memset(addr + from, 0, MAX_INLINE_DATA(inode) - from);
set_page_dirty(ipage);
if (from == 0)
@@ -116,6 +117,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
.op_flags = REQ_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
+ .io_type = FS_DATA_IO,
};
int dirty, err;
@@ -200,6 +202,8 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct dnode_of_data dn;
+ struct address_space *mapping = page_mapping(page);
+ unsigned long flags;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -216,11 +220,16 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
src_addr = kmap_atomic(page);
- dst_addr = inline_data_addr(dn.inode_page);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+ dst_addr = inline_data_addr(inode, dn.inode_page);
+ memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
kunmap_atomic(src_addr);
set_page_dirty(dn.inode_page);
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ radix_tree_tag_clear(&mapping->page_tree, page_index(page),
+ PAGECACHE_TAG_DIRTY);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
@@ -255,9 +264,9 @@ process_inline:
f2fs_wait_on_page_writeback(ipage, NODE, true);
- src_addr = inline_data_addr(npage);
- dst_addr = inline_data_addr(ipage);
- memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+ src_addr = inline_data_addr(inode, npage);
+ dst_addr = inline_data_addr(inode, ipage);
+ memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode));
set_inode_flag(inode, FI_INLINE_DATA);
set_inode_flag(inode, FI_DATA_EXIST);
@@ -285,11 +294,11 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
- struct f2fs_inline_dentry *inline_dentry;
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 = get_node_page(sbi, dir->i_ino);
@@ -300,9 +309,9 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
namehash = f2fs_dentry_hash(&name, fname);
- inline_dentry = inline_data_addr(ipage);
+ inline_dentry = inline_data_addr(dir, ipage);
- make_dentry_ptr_inline(NULL, &d, inline_dentry);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
de = find_target_dentry(fname, namehash, NULL, &d);
unlock_page(ipage);
if (de)
@@ -316,19 +325,19 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
int make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage)
{
- struct f2fs_inline_dentry *inline_dentry;
struct f2fs_dentry_ptr d;
+ void *inline_dentry;
- inline_dentry = inline_data_addr(ipage);
+ inline_dentry = inline_data_addr(inode, ipage);
- make_dentry_ptr_inline(NULL, &d, inline_dentry);
+ make_dentry_ptr_inline(inode, &d, inline_dentry);
do_make_empty_dir(inode, parent, &d);
set_page_dirty(ipage);
/* update i_size to MAX_INLINE_DATA */
- if (i_size_read(inode) < MAX_INLINE_DATA)
- f2fs_i_size_write(inode, MAX_INLINE_DATA);
+ if (i_size_read(inode) < MAX_INLINE_DATA(inode))
+ f2fs_i_size_write(inode, MAX_INLINE_DATA(inode));
return 0;
}
@@ -337,11 +346,12 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
* release ipage in this function.
*/
static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
- struct f2fs_inline_dentry *inline_dentry)
+ void *inline_dentry)
{
struct page *page;
struct dnode_of_data dn;
struct f2fs_dentry_block *dentry_blk;
+ struct f2fs_dentry_ptr src, dst;
int err;
page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
@@ -356,25 +366,24 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
goto out;
f2fs_wait_on_page_writeback(page, DATA, true);
- zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
+ zero_user_segment(page, MAX_INLINE_DATA(dir), PAGE_SIZE);
dentry_blk = kmap_atomic(page);
+ make_dentry_ptr_inline(dir, &src, inline_dentry);
+ make_dentry_ptr_block(dir, &dst, dentry_blk);
+
/* copy data from inline dentry block to new dentry block */
- memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap,
- INLINE_DENTRY_BITMAP_SIZE);
- memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0,
- SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE);
+ memcpy(dst.bitmap, src.bitmap, src.nr_bitmap);
+ memset(dst.bitmap + src.nr_bitmap, 0, dst.nr_bitmap - src.nr_bitmap);
/*
* we do not need to zero out remainder part of dentry and filename
* field, since we have used bitmap for marking the usage status of
* them, besides, we can also ignore copying/zeroing reserved space
* of dentry block, because them haven't been used so far.
*/
- memcpy(dentry_blk->dentry, inline_dentry->dentry,
- sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY);
- memcpy(dentry_blk->filename, inline_dentry->filename,
- NR_INLINE_DENTRY * F2FS_SLOT_LEN);
+ memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max);
+ memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN);
kunmap_atomic(dentry_blk);
if (!PageUptodate(page))
@@ -395,14 +404,13 @@ out:
return err;
}
-static int f2fs_add_inline_entries(struct inode *dir,
- struct f2fs_inline_dentry *inline_dentry)
+static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry)
{
struct f2fs_dentry_ptr d;
unsigned long bit_pos = 0;
int err = 0;
- make_dentry_ptr_inline(NULL, &d, inline_dentry);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
while (bit_pos < d.max) {
struct f2fs_dir_entry *de;
@@ -444,19 +452,19 @@ punch_dentry_pages:
}
static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
- struct f2fs_inline_dentry *inline_dentry)
+ void *inline_dentry)
{
- struct f2fs_inline_dentry *backup_dentry;
+ void *backup_dentry;
int err;
backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir),
- sizeof(struct f2fs_inline_dentry), GFP_F2FS_ZERO);
+ MAX_INLINE_DATA(dir), GFP_F2FS_ZERO);
if (!backup_dentry) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
}
- memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+ memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir));
truncate_inline_inode(dir, ipage, 0);
unlock_page(ipage);
@@ -473,9 +481,9 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
return 0;
recover:
lock_page(ipage);
- memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir));
f2fs_i_depth_write(dir, 0);
- f2fs_i_size_write(dir, MAX_INLINE_DATA);
+ f2fs_i_size_write(dir, MAX_INLINE_DATA(dir));
set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
@@ -484,7 +492,7 @@ recover:
}
static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
- struct f2fs_inline_dentry *inline_dentry)
+ void *inline_dentry)
{
if (!F2FS_I(dir)->i_dir_level)
return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
@@ -500,7 +508,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
struct page *ipage;
unsigned int bit_pos;
f2fs_hash_t name_hash;
- struct f2fs_inline_dentry *inline_dentry = NULL;
+ void *inline_dentry = NULL;
struct f2fs_dentry_ptr d;
int slots = GET_DENTRY_SLOTS(new_name->len);
struct page *page = NULL;
@@ -510,10 +518,11 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
if (IS_ERR(ipage))
return PTR_ERR(ipage);
- inline_dentry = inline_data_addr(ipage);
- bit_pos = room_for_filename(&inline_dentry->dentry_bitmap,
- slots, NR_INLINE_DENTRY);
- if (bit_pos >= NR_INLINE_DENTRY) {
+ inline_dentry = inline_data_addr(dir, ipage);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+ bit_pos = room_for_filename(d.bitmap, slots, d.max);
+ if (bit_pos >= d.max) {
err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
if (err)
return err;
@@ -534,7 +543,6 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
f2fs_wait_on_page_writeback(ipage, NODE, true);
name_hash = f2fs_dentry_hash(new_name, NULL);
- make_dentry_ptr_inline(NULL, &d, inline_dentry);
f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
set_page_dirty(ipage);
@@ -557,7 +565,8 @@ out:
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode)
{
- struct f2fs_inline_dentry *inline_dentry;
+ struct f2fs_dentry_ptr d;
+ void *inline_dentry;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
unsigned int bit_pos;
int i;
@@ -565,11 +574,12 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
lock_page(page);
f2fs_wait_on_page_writeback(page, NODE, true);
- inline_dentry = inline_data_addr(page);
- bit_pos = dentry - inline_dentry->dentry;
+ inline_dentry = inline_data_addr(dir, page);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+ bit_pos = dentry - d.dentry;
for (i = 0; i < slots; i++)
- __clear_bit_le(bit_pos + i,
- &inline_dentry->dentry_bitmap);
+ __clear_bit_le(bit_pos + i, d.bitmap);
set_page_dirty(page);
f2fs_put_page(page, 1);
@@ -586,20 +596,21 @@ bool f2fs_empty_inline_dir(struct inode *dir)
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
unsigned int bit_pos = 2;
- struct f2fs_inline_dentry *inline_dentry;
+ void *inline_dentry;
+ struct f2fs_dentry_ptr d;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return false;
- inline_dentry = inline_data_addr(ipage);
- bit_pos = find_next_bit_le(&inline_dentry->dentry_bitmap,
- NR_INLINE_DENTRY,
- bit_pos);
+ inline_dentry = inline_data_addr(dir, ipage);
+ make_dentry_ptr_inline(dir, &d, inline_dentry);
+
+ bit_pos = find_next_bit_le(d.bitmap, d.max, bit_pos);
f2fs_put_page(ipage, 1);
- if (bit_pos < NR_INLINE_DENTRY)
+ if (bit_pos < d.max)
return false;
return true;
@@ -609,25 +620,27 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
struct fscrypt_str *fstr)
{
struct inode *inode = file_inode(file);
- struct f2fs_inline_dentry *inline_dentry = NULL;
struct page *ipage = NULL;
struct f2fs_dentry_ptr d;
+ void *inline_dentry = NULL;
int err;
- if (ctx->pos == NR_INLINE_DENTRY)
+ make_dentry_ptr_inline(inode, &d, inline_dentry);
+
+ if (ctx->pos == d.max)
return 0;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
- inline_dentry = inline_data_addr(ipage);
+ inline_dentry = inline_data_addr(inode, ipage);
make_dentry_ptr_inline(inode, &d, inline_dentry);
err = f2fs_fill_dentries(ctx, &d, 0, fstr);
if (!err)
- ctx->pos = NR_INLINE_DENTRY;
+ ctx->pos = d.max;
f2fs_put_page(ipage, 1);
return err < 0 ? err : 0;
@@ -652,7 +665,7 @@ int f2fs_inline_data_fiemap(struct inode *inode,
goto out;
}
- ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode));
+ ilen = min_t(size_t, MAX_INLINE_DATA(inode), i_size_read(inode));
if (start >= ilen)
goto out;
if (start + len < ilen)
@@ -661,7 +674,8 @@ int f2fs_inline_data_fiemap(struct inode *inode,
get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
- byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage);
+ byteaddr += (char *)inline_data_addr(inode, ipage) -
+ (char *)F2FS_INODE(ipage);
err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
out:
f2fs_put_page(ipage, 1);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 6cd312a17c69..50c88e37ed66 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -49,20 +49,22 @@ void f2fs_set_inode_flags(struct inode *inode)
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
+ int extra_size = get_extra_isize(inode);
+
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
- if (ri->i_addr[0])
- inode->i_rdev =
- old_decode_dev(le32_to_cpu(ri->i_addr[0]));
+ if (ri->i_addr[extra_size])
+ inode->i_rdev = old_decode_dev(
+ le32_to_cpu(ri->i_addr[extra_size]));
else
- inode->i_rdev =
- new_decode_dev(le32_to_cpu(ri->i_addr[1]));
+ inode->i_rdev = new_decode_dev(
+ le32_to_cpu(ri->i_addr[extra_size + 1]));
}
}
static bool __written_first_block(struct f2fs_inode *ri)
{
- block_t addr = le32_to_cpu(ri->i_addr[0]);
+ block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]);
if (addr != NEW_ADDR && addr != NULL_ADDR)
return true;
@@ -71,25 +73,27 @@ static bool __written_first_block(struct f2fs_inode *ri)
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
+ int extra_size = get_extra_isize(inode);
+
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
- ri->i_addr[0] =
+ ri->i_addr[extra_size] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
- ri->i_addr[1] = 0;
+ ri->i_addr[extra_size + 1] = 0;
} else {
- ri->i_addr[0] = 0;
- ri->i_addr[1] =
+ ri->i_addr[extra_size] = 0;
+ ri->i_addr[extra_size + 1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
- ri->i_addr[2] = 0;
+ ri->i_addr[extra_size + 2] = 0;
}
}
}
static void __recover_inline_status(struct inode *inode, struct page *ipage)
{
- void *inline_data = inline_data_addr(ipage);
+ void *inline_data = inline_data_addr(inode, ipage);
__le32 *start = inline_data;
- __le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
+ __le32 *end = start + MAX_INLINE_DATA(inode) / sizeof(__le32);
while (start < end) {
if (*start++) {
@@ -104,12 +108,84 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
return;
}
+static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_inode *ri = &F2FS_NODE(page)->i;
+ int extra_isize = le32_to_cpu(ri->i_extra_isize);
+
+ if (!f2fs_sb_has_inode_chksum(sbi->sb))
+ return false;
+
+ if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR))
+ return false;
+
+ if (!F2FS_FITS_IN_INODE(ri, extra_isize, i_inode_checksum))
+ return false;
+
+ return true;
+}
+
+static __u32 f2fs_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_node *node = F2FS_NODE(page);
+ struct f2fs_inode *ri = &node->i;
+ __le32 ino = node->footer.ino;
+ __le32 gen = ri->i_generation;
+ __u32 chksum, chksum_seed;
+ __u32 dummy_cs = 0;
+ unsigned int offset = offsetof(struct f2fs_inode, i_inode_checksum);
+ unsigned int cs_size = sizeof(dummy_cs);
+
+ chksum = f2fs_chksum(sbi, sbi->s_chksum_seed, (__u8 *)&ino,
+ sizeof(ino));
+ chksum_seed = f2fs_chksum(sbi, chksum, (__u8 *)&gen, sizeof(gen));
+
+ chksum = f2fs_chksum(sbi, chksum_seed, (__u8 *)ri, offset);
+ chksum = f2fs_chksum(sbi, chksum, (__u8 *)&dummy_cs, cs_size);
+ offset += cs_size;
+ chksum = f2fs_chksum(sbi, chksum, (__u8 *)ri + offset,
+ F2FS_BLKSIZE - offset);
+ return chksum;
+}
+
+bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_inode *ri;
+ __u32 provided, calculated;
+
+ if (!f2fs_enable_inode_chksum(sbi, page) ||
+ PageDirty(page) || PageWriteback(page))
+ return true;
+
+ ri = &F2FS_NODE(page)->i;
+ provided = le32_to_cpu(ri->i_inode_checksum);
+ calculated = f2fs_inode_chksum(sbi, page);
+
+ if (provided != calculated)
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "checksum invalid, ino = %x, %x vs. %x",
+ ino_of_node(page), provided, calculated);
+
+ return provided == calculated;
+}
+
+void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page)
+{
+ struct f2fs_inode *ri = &F2FS_NODE(page)->i;
+
+ if (!f2fs_enable_inode_chksum(sbi, page))
+ return;
+
+ ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page));
+}
+
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
+ projid_t i_projid;
/* Check if ino is within scope */
if (check_nid_range(sbi, inode->i_ino)) {
@@ -153,6 +229,9 @@ static int do_read_inode(struct inode *inode)
get_inline_info(inode, ri);
+ fi->i_extra_isize = f2fs_has_extra_attr(inode) ?
+ le16_to_cpu(ri->i_extra_isize) : 0;
+
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
@@ -166,6 +245,16 @@ static int do_read_inode(struct inode *inode)
if (!need_inode_block_update(sbi, inode->i_ino))
fi->last_disk_size = inode->i_size;
+ if (fi->i_flags & FS_PROJINHERIT_FL)
+ set_inode_flag(inode, FI_PROJ_INHERIT);
+
+ if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) &&
+ F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid))
+ i_projid = (projid_t)le32_to_cpu(ri->i_projid);
+ else
+ i_projid = F2FS_DEF_PROJID;
+ fi->i_projid = make_kprojid(&init_user_ns, i_projid);
+
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
@@ -292,6 +381,20 @@ int update_inode(struct inode *inode, struct page *node_page)
ri->i_generation = cpu_to_le32(inode->i_generation);
ri->i_dir_level = F2FS_I(inode)->i_dir_level;
+ if (f2fs_has_extra_attr(inode)) {
+ ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize);
+
+ if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) &&
+ F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
+ i_projid)) {
+ projid_t i_projid;
+
+ i_projid = from_kprojid(&init_user_ns,
+ F2FS_I(inode)->i_projid);
+ ri->i_projid = cpu_to_le32(i_projid);
+ }
+ }
+
__set_inode_rdev(inode, ri);
set_cold_node(inode, node_page);
@@ -416,6 +519,9 @@ no_delete:
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
+ if (!is_set_ckpt_flags(sbi, CP_ERROR_FLAG))
+ f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
+
/* ino == 0, if f2fs_new_inode() was failed t*/
if (inode->i_ino)
invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 760d85223c81..a4dab98c4b7b 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -58,6 +58,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
goto fail;
}
+ if (f2fs_sb_has_project_quota(sbi->sb) &&
+ (F2FS_I(dir)->i_flags & FS_PROJINHERIT_FL))
+ F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid;
+ else
+ F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns,
+ F2FS_DEF_PROJID);
+
err = dquot_initialize(inode);
if (err)
goto fail_drop;
@@ -72,6 +79,11 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
set_inode_flag(inode, FI_NEW_INODE);
+ if (f2fs_sb_has_extra_attr(sbi->sb)) {
+ set_inode_flag(inode, FI_EXTRA_ATTR);
+ F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE;
+ }
+
if (test_opt(sbi, INLINE_XATTR))
set_inode_flag(inode, FI_INLINE_XATTR);
if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
@@ -85,6 +97,15 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
+ F2FS_I(inode)->i_flags =
+ f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED);
+
+ if (S_ISDIR(inode->i_mode))
+ F2FS_I(inode)->i_flags |= FS_INDEX_FL;
+
+ if (F2FS_I(inode)->i_flags & FS_PROJINHERIT_FL)
+ set_inode_flag(inode, FI_PROJ_INHERIT);
+
trace_f2fs_new_inode(inode, 0);
return inode;
@@ -204,6 +225,11 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
!fscrypt_has_permitted_context(dir, inode))
return -EPERM;
+ if (is_inode_flag_set(dir, FI_PROJ_INHERIT) &&
+ (!projid_eq(F2FS_I(dir)->i_projid,
+ F2FS_I(old_dentry->d_inode)->i_projid)))
+ return -EXDEV;
+
err = dquot_initialize(dir);
if (err)
return err;
@@ -261,6 +287,10 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
return 0;
}
+ err = dquot_initialize(dir);
+ if (err)
+ return err;
+
f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
@@ -724,6 +754,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out;
}
+ if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+ (!projid_eq(F2FS_I(new_dir)->i_projid,
+ F2FS_I(old_dentry->d_inode)->i_projid)))
+ return -EXDEV;
+
err = dquot_initialize(old_dir);
if (err)
goto out;
@@ -912,6 +947,14 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
!fscrypt_has_permitted_context(old_dir, new_inode)))
return -EPERM;
+ if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+ !projid_eq(F2FS_I(new_dir)->i_projid,
+ F2FS_I(old_dentry->d_inode)->i_projid)) ||
+ (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) &&
+ !projid_eq(F2FS_I(old_dir)->i_projid,
+ F2FS_I(new_dentry->d_inode)->i_projid)))
+ return -EXDEV;
+
err = dquot_initialize(old_dir);
if (err)
goto out;
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index d53fe620939e..fca87835a1da 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -19,6 +19,7 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "xattr.h"
#include "trace.h"
#include <trace/events/f2fs.h>
@@ -554,7 +555,7 @@ static int get_node_path(struct inode *inode, long block,
level = 3;
goto got;
} else {
- BUG();
+ return -E2BIG;
}
got:
return level;
@@ -578,6 +579,8 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
int err = 0;
level = get_node_path(dn->inode, index, offset, noffset);
+ if (level < 0)
+ return level;
nids[0] = dn->inode->i_ino;
npage[0] = dn->inode_page;
@@ -613,7 +616,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
}
dn->nid = nids[i];
- npage[i] = new_node_page(dn, noffset[i], NULL);
+ npage[i] = new_node_page(dn, noffset[i]);
if (IS_ERR(npage[i])) {
alloc_nid_failed(sbi, nids[i]);
err = PTR_ERR(npage[i]);
@@ -654,7 +657,8 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
dn->nid = nids[level];
dn->ofs_in_node = offset[level];
dn->node_page = npage[level];
- dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
+ dn->data_blkaddr = datablock_addr(dn->inode,
+ dn->node_page, dn->ofs_in_node);
return 0;
release_pages:
@@ -876,6 +880,8 @@ int 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)
+ return level;
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
@@ -1022,11 +1028,10 @@ struct page *new_inode_page(struct inode *inode)
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
/* caller should f2fs_put_page(page, 1); */
- return new_node_page(&dn, 0, NULL);
+ return new_node_page(&dn, 0);
}
-struct page *new_node_page(struct dnode_of_data *dn,
- unsigned int ofs, struct page *ipage)
+struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct node_info new_ni;
@@ -1170,6 +1175,11 @@ repeat:
err = -EIO;
goto out_err;
}
+
+ if (!f2fs_inode_chksum_verify(sbi, page)) {
+ err = -EBADMSG;
+ goto out_err;
+ }
page_hit:
if(unlikely(nid != nid_of_node(page))) {
f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, "
@@ -1177,9 +1187,9 @@ page_hit:
nid, nid_of_node(page), ino_of_node(page),
ofs_of_node(page), cpver_of_node(page),
next_blkaddr_of_node(page));
- ClearPageUptodate(page);
err = -EINVAL;
out_err:
+ ClearPageUptodate(page);
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
@@ -1326,7 +1336,8 @@ continue_unlock:
}
static int __write_node_page(struct page *page, bool atomic, bool *submitted,
- struct writeback_control *wbc)
+ struct writeback_control *wbc, bool do_balance,
+ enum iostat_type io_type)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
nid_t nid;
@@ -1339,6 +1350,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
.page = page,
.encrypted_page = NULL,
.submitted = false,
+ .io_type = io_type,
};
trace_f2fs_writepage(page, NODE);
@@ -1395,6 +1407,8 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted,
if (submitted)
*submitted = fio.submitted;
+ if (do_balance)
+ f2fs_balance_fs(sbi, false);
return 0;
redirty_out:
@@ -1405,7 +1419,7 @@ redirty_out:
static int f2fs_write_node_page(struct page *page,
struct writeback_control *wbc)
{
- return __write_node_page(page, false, NULL, wbc);
+ return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO);
}
int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
@@ -1493,7 +1507,8 @@ continue_unlock:
ret = __write_node_page(page, atomic &&
page == last_page,
- &submitted, wbc);
+ &submitted, wbc, true,
+ FS_NODE_IO);
if (ret) {
unlock_page(page);
f2fs_put_page(last_page, 0);
@@ -1530,7 +1545,8 @@ out:
return ret ? -EIO: 0;
}
-int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc,
+ bool do_balance, enum iostat_type io_type)
{
pgoff_t index, end;
struct pagevec pvec;
@@ -1608,7 +1624,8 @@ continue_unlock:
set_fsync_mark(page, 0);
set_dentry_mark(page, 0);
- ret = __write_node_page(page, false, &submitted, wbc);
+ ret = __write_node_page(page, false, &submitted,
+ wbc, do_balance, io_type);
if (ret)
unlock_page(page);
else if (submitted)
@@ -1697,7 +1714,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
diff = nr_pages_to_write(sbi, NODE, wbc);
wbc->sync_mode = WB_SYNC_NONE;
blk_start_plug(&plug);
- sync_node_pages(sbi, wbc);
+ sync_node_pages(sbi, wbc, true, FS_NODE_IO);
blk_finish_plug(&plug);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
return 0;
@@ -2191,7 +2208,8 @@ int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
- nid_t new_xnid = nid_of_node(page);
+ nid_t new_xnid;
+ struct dnode_of_data dn;
struct node_info ni;
struct page *xpage;
@@ -2207,22 +2225,22 @@ int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
recover_xnid:
/* 2: update xattr nid in inode */
- remove_free_nid(sbi, new_xnid);
- f2fs_i_xnid_write(inode, new_xnid);
- if (unlikely(inc_valid_node_count(sbi, inode, false)))
- f2fs_bug_on(sbi, 1);
+ if (!alloc_nid(sbi, &new_xnid))
+ return -ENOSPC;
+
+ set_new_dnode(&dn, inode, NULL, NULL, new_xnid);
+ xpage = new_node_page(&dn, XATTR_NODE_OFFSET);
+ if (IS_ERR(xpage)) {
+ alloc_nid_failed(sbi, new_xnid);
+ return PTR_ERR(xpage);
+ }
+
+ alloc_nid_done(sbi, new_xnid);
update_inode_page(inode);
/* 3: update and set xattr node page dirty */
- xpage = grab_cache_page(NODE_MAPPING(sbi), new_xnid);
- if (!xpage)
- return -ENOMEM;
-
- memcpy(F2FS_NODE(xpage), F2FS_NODE(page), PAGE_SIZE);
+ memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE);
- get_node_info(sbi, new_xnid, &ni);
- ni.ino = inode->i_ino;
- set_node_addr(sbi, &ni, NEW_ADDR, false);
set_page_dirty(xpage);
f2fs_put_page(xpage, 1);
@@ -2262,7 +2280,14 @@ retry:
dst->i_blocks = cpu_to_le64(1);
dst->i_links = cpu_to_le32(1);
dst->i_xattr_nid = 0;
- dst->i_inline = src->i_inline & F2FS_INLINE_XATTR;
+ dst->i_inline = src->i_inline & (F2FS_INLINE_XATTR | F2FS_EXTRA_ATTR);
+ if (dst->i_inline & F2FS_EXTRA_ATTR) {
+ dst->i_extra_isize = src->i_extra_isize;
+ if (f2fs_sb_has_project_quota(sbi->sb) &&
+ F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
+ i_projid))
+ dst->i_projid = src->i_projid;
+ }
new_ni = old_ni;
new_ni.ino = ino;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 907d6b7dde6a..9626758bc762 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -69,20 +69,34 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
}
static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
- struct list_head *head, nid_t ino)
+ struct list_head *head, nid_t ino, bool quota_inode)
{
struct inode *inode;
struct fsync_inode_entry *entry;
+ int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
+ err = dquot_initialize(inode);
+ if (err)
+ goto err_out;
+
+ if (quota_inode) {
+ err = dquot_alloc_inode(inode);
+ if (err)
+ goto err_out;
+ }
+
entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
entry->inode = inode;
list_add_tail(&entry->list, head);
return entry;
+err_out:
+ iput(inode);
+ return ERR_PTR(err);
}
static void del_fsync_inode(struct fsync_inode_entry *entry)
@@ -107,7 +121,8 @@ static int recover_dentry(struct inode *inode, struct page *ipage,
entry = get_fsync_inode(dir_list, pino);
if (!entry) {
- entry = add_fsync_inode(F2FS_I_SB(inode), dir_list, pino);
+ entry = add_fsync_inode(F2FS_I_SB(inode), dir_list,
+ pino, false);
if (IS_ERR(entry)) {
dir = ERR_CAST(entry);
err = PTR_ERR(entry);
@@ -140,6 +155,13 @@ retry:
err = -EEXIST;
goto out_unmap_put;
}
+
+ err = dquot_initialize(einode);
+ if (err) {
+ iput(einode);
+ goto out_unmap_put;
+ }
+
err = acquire_orphan_inode(F2FS_I_SB(inode));
if (err) {
iput(einode);
@@ -226,18 +248,22 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry) {
+ bool quota_inode = false;
+
if (!check_only &&
IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
if (err)
break;
+ quota_inode = true;
}
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
- entry = add_fsync_inode(sbi, head, ino_of_node(page));
+ entry = add_fsync_inode(sbi, head, ino_of_node(page),
+ quota_inode);
if (IS_ERR(entry)) {
err = PTR_ERR(entry);
if (err == -ENOENT) {
@@ -291,7 +317,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
return 0;
/* Get the previous summary */
- for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) {
+ for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
struct curseg_info *curseg = CURSEG_I(sbi, i);
if (curseg->segno == segno) {
sum = curseg->sum_blk->entries[blkoff];
@@ -328,10 +354,18 @@ got_it:
f2fs_put_page(node_page, 1);
if (ino != dn->inode->i_ino) {
+ int ret;
+
/* Deallocate previous index in the node page */
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return PTR_ERR(inode);
+
+ ret = dquot_initialize(inode);
+ if (ret) {
+ iput(inode);
+ return ret;
+ }
} else {
inode = dn->inode;
}
@@ -361,7 +395,8 @@ out:
return 0;
truncate_out:
- if (datablock_addr(tdn.node_page, tdn.ofs_in_node) == blkaddr)
+ if (datablock_addr(tdn.inode, tdn.node_page,
+ tdn.ofs_in_node) == blkaddr)
truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
@@ -414,8 +449,8 @@ retry_dn:
for (; start < end; start++, dn.ofs_in_node++) {
block_t src, dest;
- src = datablock_addr(dn.node_page, dn.ofs_in_node);
- dest = datablock_addr(page, dn.ofs_in_node);
+ src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
+ dest = datablock_addr(dn.inode, page, dn.ofs_in_node);
/* skip recovering if dest is the same as src */
if (src == dest)
@@ -557,12 +592,27 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
struct list_head dir_list;
int err;
int ret = 0;
+ unsigned long s_flags = sbi->sb->s_flags;
bool need_writecp = false;
+ if (s_flags & MS_RDONLY) {
+ f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
+ sbi->sb->s_flags &= ~MS_RDONLY;
+ }
+
+#ifdef CONFIG_QUOTA
+ /* Needed for iput() to work correctly and not trash data */
+ sbi->sb->s_flags |= MS_ACTIVE;
+ /* Turn on quotas so that they are updated correctly */
+ f2fs_enable_quota_files(sbi);
+#endif
+
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
sizeof(struct fsync_inode_entry));
- if (!fsync_entry_slab)
- return -ENOMEM;
+ if (!fsync_entry_slab) {
+ err = -ENOMEM;
+ goto out;
+ }
INIT_LIST_HEAD(&inode_list);
INIT_LIST_HEAD(&dir_list);
@@ -573,11 +623,11 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list, check_only);
if (err || list_empty(&inode_list))
- goto out;
+ goto skip;
if (check_only) {
ret = 1;
- goto out;
+ goto skip;
}
need_writecp = true;
@@ -586,7 +636,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
err = recover_data(sbi, &inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
-out:
+skip:
destroy_fsync_dnodes(&inode_list);
/* truncate meta pages to be used by the recovery */
@@ -599,8 +649,6 @@ out:
}
clear_sbi_flag(sbi, SBI_POR_DOING);
- if (err)
- set_ckpt_flags(sbi, CP_ERROR_FLAG);
mutex_unlock(&sbi->cp_mutex);
/* let's drop all the directory inodes for clean checkpoint */
@@ -614,5 +662,12 @@ out:
}
kmem_cache_destroy(fsync_entry_slab);
+out:
+#ifdef CONFIG_QUOTA
+ /* Turn quotas off */
+ f2fs_quota_off_umount(sbi->sb);
+#endif
+ sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */
+
return ret ? ret: err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 6f8fc4a6e701..621b9b3d320b 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -17,10 +17,12 @@
#include <linux/swap.h>
#include <linux/timer.h>
#include <linux/freezer.h>
+#include <linux/sched/signal.h>
#include "f2fs.h"
#include "segment.h"
#include "node.h"
+#include "gc.h"
#include "trace.h"
#include <trace/events/f2fs.h>
@@ -167,6 +169,21 @@ found:
return result - size + __reverse_ffz(tmp);
}
+bool need_SSR(struct f2fs_sb_info *sbi)
+{
+ int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
+ int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+ int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+
+ if (test_opt(sbi, LFS))
+ return false;
+ if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
+ return true;
+
+ return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
+ 2 * reserved_sections(sbi));
+}
+
void register_inmem_page(struct inode *inode, struct page *page)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -213,9 +230,15 @@ static int __revoke_inmem_pages(struct inode *inode,
struct node_info ni;
trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
-
+retry:
set_new_dnode(&dn, inode, NULL, NULL, 0);
- if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) {
+ err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
+ if (err) {
+ if (err == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ cond_resched();
+ goto retry;
+ }
err = -EAGAIN;
goto next;
}
@@ -248,6 +271,7 @@ void drop_inmem_pages(struct inode *inode)
mutex_unlock(&fi->inmem_lock);
clear_inode_flag(inode, FI_ATOMIC_FILE);
+ clear_inode_flag(inode, FI_HOT_DATA);
stat_dec_atomic_write(inode);
}
@@ -292,6 +316,7 @@ static int __commit_inmem_pages(struct inode *inode,
.type = DATA,
.op = REQ_OP_WRITE,
.op_flags = REQ_SYNC | REQ_PRIO,
+ .io_type = FS_DATA_IO,
};
pgoff_t last_idx = ULONG_MAX;
int err = 0;
@@ -309,17 +334,21 @@ static int __commit_inmem_pages(struct inode *inode,
inode_dec_dirty_pages(inode);
remove_dirty_inode(inode);
}
-
+retry:
fio.page = page;
fio.old_blkaddr = NULL_ADDR;
fio.encrypted_page = NULL;
fio.need_lock = LOCK_DONE;
err = do_write_data_page(&fio);
if (err) {
+ if (err == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ cond_resched();
+ goto retry;
+ }
unlock_page(page);
break;
}
-
/* record old blkaddr for revoking */
cur->old_addr = fio.old_blkaddr;
last_idx = page->index;
@@ -481,6 +510,8 @@ repeat:
if (kthread_should_stop())
return 0;
+ sb_start_intwrite(sbi->sb);
+
if (!llist_empty(&fcc->issue_list)) {
struct flush_cmd *cmd, *next;
int ret;
@@ -499,6 +530,8 @@ repeat:
fcc->dispatch_list = NULL;
}
+ sb_end_intwrite(sbi->sb);
+
wait_event_interruptible(*q,
kthread_should_stop() || !llist_empty(&fcc->issue_list));
goto repeat;
@@ -519,8 +552,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
return ret;
}
- if (!atomic_read(&fcc->issing_flush)) {
- atomic_inc(&fcc->issing_flush);
+ if (atomic_inc_return(&fcc->issing_flush) == 1) {
ret = submit_flush_wait(sbi);
atomic_dec(&fcc->issing_flush);
@@ -530,18 +562,39 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
init_completion(&cmd.wait);
- atomic_inc(&fcc->issing_flush);
llist_add(&cmd.llnode, &fcc->issue_list);
- if (!fcc->dispatch_list)
+ /* update issue_list before we wake up issue_flush thread */
+ smp_mb();
+
+ if (waitqueue_active(&fcc->flush_wait_queue))
wake_up(&fcc->flush_wait_queue);
if (fcc->f2fs_issue_flush) {
wait_for_completion(&cmd.wait);
atomic_dec(&fcc->issing_flush);
} else {
- llist_del_all(&fcc->issue_list);
- atomic_set(&fcc->issing_flush, 0);
+ struct llist_node *list;
+
+ list = llist_del_all(&fcc->issue_list);
+ if (!list) {
+ wait_for_completion(&cmd.wait);
+ atomic_dec(&fcc->issing_flush);
+ } else {
+ struct flush_cmd *tmp, *next;
+
+ ret = submit_flush_wait(sbi);
+
+ llist_for_each_entry_safe(tmp, next, list, llnode) {
+ if (tmp == &cmd) {
+ cmd.ret = ret;
+ atomic_dec(&fcc->issing_flush);
+ continue;
+ }
+ tmp->ret = ret;
+ complete(&tmp->wait);
+ }
+ }
}
return cmd.ret;
@@ -778,11 +831,14 @@ void __check_sit_bitmap(struct f2fs_sb_info *sbi,
sentry = get_seg_entry(sbi, segno);
offset = GET_BLKOFF_FROM_SEG0(sbi, blk);
- size = min((unsigned long)(end - blk), max_blocks);
+ if (end < START_BLOCK(sbi, segno + 1))
+ size = GET_BLKOFF_FROM_SEG0(sbi, end);
+ else
+ size = max_blocks;
map = (unsigned long *)(sentry->cur_valid_map);
offset = __find_rev_next_bit(map, size, offset);
f2fs_bug_on(sbi, offset != size);
- blk += size;
+ blk = START_BLOCK(sbi, segno + 1);
}
#endif
}
@@ -815,6 +871,8 @@ static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
submit_bio(bio);
list_move_tail(&dc->list, &dcc->wait_list);
__check_sit_bitmap(sbi, dc->start, dc->start + dc->len);
+
+ f2fs_update_iostat(sbi, FS_DISCARD, 1);
}
} else {
__remove_discard_cmd(sbi, dc);
@@ -996,32 +1054,81 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
return 0;
}
-static void __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond)
+static int __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond)
{
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
struct list_head *pend_list;
struct discard_cmd *dc, *tmp;
struct blk_plug plug;
- int i, iter = 0;
+ int iter = 0, issued = 0;
+ int i;
+ bool io_interrupted = false;
mutex_lock(&dcc->cmd_lock);
f2fs_bug_on(sbi,
!__check_rb_tree_consistence(sbi, &dcc->root));
blk_start_plug(&plug);
- for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+ for (i = MAX_PLIST_NUM - 1;
+ i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) {
pend_list = &dcc->pend_list[i];
list_for_each_entry_safe(dc, tmp, pend_list, list) {
f2fs_bug_on(sbi, dc->state != D_PREP);
- if (!issue_cond || is_idle(sbi))
+ /* Hurry up to finish fstrim */
+ if (dcc->pend_list_tag[i] & P_TRIM) {
+ __submit_discard_cmd(sbi, dc);
+ issued++;
+
+ if (fatal_signal_pending(current))
+ break;
+ continue;
+ }
+
+ if (!issue_cond) {
__submit_discard_cmd(sbi, dc);
- if (issue_cond && iter++ > DISCARD_ISSUE_RATE)
+ issued++;
+ continue;
+ }
+
+ if (is_idle(sbi)) {
+ __submit_discard_cmd(sbi, dc);
+ issued++;
+ } else {
+ io_interrupted = true;
+ }
+
+ if (++iter >= DISCARD_ISSUE_RATE)
goto out;
}
+ if (list_empty(pend_list) && dcc->pend_list_tag[i] & P_TRIM)
+ dcc->pend_list_tag[i] &= (~P_TRIM);
}
out:
blk_finish_plug(&plug);
mutex_unlock(&dcc->cmd_lock);
+
+ if (!issued && io_interrupted)
+ issued = -1;
+
+ return issued;
+}
+
+static void __drop_discard_cmd(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *pend_list;
+ struct discard_cmd *dc, *tmp;
+ int i;
+
+ mutex_lock(&dcc->cmd_lock);
+ for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+ pend_list = &dcc->pend_list[i];
+ list_for_each_entry_safe(dc, tmp, pend_list, list) {
+ f2fs_bug_on(sbi, dc->state != D_PREP);
+ __remove_discard_cmd(sbi, dc);
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
}
static void __wait_one_discard_bio(struct f2fs_sb_info *sbi,
@@ -1102,34 +1209,63 @@ void stop_discard_thread(struct f2fs_sb_info *sbi)
}
}
-/* This comes from f2fs_put_super */
+/* This comes from f2fs_put_super and f2fs_trim_fs */
void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
{
__issue_discard_cmd(sbi, false);
+ __drop_discard_cmd(sbi);
__wait_discard_cmd(sbi, false);
}
+static void mark_discard_range_all(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ int i;
+
+ mutex_lock(&dcc->cmd_lock);
+ for (i = 0; i < MAX_PLIST_NUM; i++)
+ dcc->pend_list_tag[i] |= P_TRIM;
+ mutex_unlock(&dcc->cmd_lock);
+}
+
static int issue_discard_thread(void *data)
{
struct f2fs_sb_info *sbi = data;
struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
wait_queue_head_t *q = &dcc->discard_wait_queue;
+ unsigned int wait_ms = DEF_MIN_DISCARD_ISSUE_TIME;
+ int issued;
set_freezable();
do {
- wait_event_interruptible(*q, kthread_should_stop() ||
- freezing(current) ||
- atomic_read(&dcc->discard_cmd_cnt));
+ wait_event_interruptible_timeout(*q,
+ kthread_should_stop() || freezing(current) ||
+ dcc->discard_wake,
+ msecs_to_jiffies(wait_ms));
if (try_to_freeze())
continue;
if (kthread_should_stop())
return 0;
- __issue_discard_cmd(sbi, true);
- __wait_discard_cmd(sbi, true);
+ if (dcc->discard_wake) {
+ dcc->discard_wake = 0;
+ if (sbi->gc_thread && sbi->gc_thread->gc_urgent)
+ mark_discard_range_all(sbi);
+ }
+
+ sb_start_intwrite(sbi->sb);
+
+ issued = __issue_discard_cmd(sbi, true);
+ if (issued) {
+ __wait_discard_cmd(sbi, true);
+ wait_ms = DEF_MIN_DISCARD_ISSUE_TIME;
+ } else {
+ wait_ms = DEF_MAX_DISCARD_ISSUE_TIME;
+ }
+
+ sb_end_intwrite(sbi->sb);
- congestion_wait(BLK_RW_SYNC, HZ/50);
} while (!kthread_should_stop());
return 0;
}
@@ -1320,7 +1456,8 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
- struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *head = &dcc->entry_list;
struct discard_entry *entry, *this;
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
@@ -1402,11 +1539,11 @@ skip:
goto find_next;
list_del(&entry->list);
- SM_I(sbi)->dcc_info->nr_discards -= total_len;
+ dcc->nr_discards -= total_len;
kmem_cache_free(discard_entry_slab, entry);
}
- wake_up(&SM_I(sbi)->dcc_info->discard_wait_queue);
+ wake_up_discard_thread(sbi, false);
}
static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
@@ -1424,9 +1561,13 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
if (!dcc)
return -ENOMEM;
+ dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY;
INIT_LIST_HEAD(&dcc->entry_list);
- for (i = 0; i < MAX_PLIST_NUM; i++)
+ for (i = 0; i < MAX_PLIST_NUM; i++) {
INIT_LIST_HEAD(&dcc->pend_list[i]);
+ if (i >= dcc->discard_granularity - 1)
+ dcc->pend_list_tag[i] |= P_ACTIVE;
+ }
INIT_LIST_HEAD(&dcc->wait_list);
mutex_init(&dcc->cmd_lock);
atomic_set(&dcc->issued_discard, 0);
@@ -1491,6 +1632,10 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
struct seg_entry *se;
unsigned int segno, offset;
long int new_vblocks;
+ bool exist;
+#ifdef CONFIG_F2FS_CHECK_FS
+ bool mir_exist;
+#endif
segno = GET_SEGNO(sbi, blkaddr);
@@ -1507,17 +1652,25 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
/* Update valid block bitmap */
if (del > 0) {
- if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) {
+ exist = f2fs_test_and_set_bit(offset, se->cur_valid_map);
#ifdef CONFIG_F2FS_CHECK_FS
- if (f2fs_test_and_set_bit(offset,
- se->cur_valid_map_mir))
- f2fs_bug_on(sbi, 1);
- else
- WARN_ON(1);
-#else
+ mir_exist = f2fs_test_and_set_bit(offset,
+ se->cur_valid_map_mir);
+ if (unlikely(exist != mir_exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
+ "when setting bitmap, blk:%u, old bit:%d",
+ blkaddr, exist);
f2fs_bug_on(sbi, 1);
+ }
#endif
+ if (unlikely(exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Bitmap was wrongly set, blk:%u", blkaddr);
+ f2fs_bug_on(sbi, 1);
+ se->valid_blocks--;
+ del = 0;
}
+
if (f2fs_discard_en(sbi) &&
!f2fs_test_and_set_bit(offset, se->discard_map))
sbi->discard_blks--;
@@ -1528,17 +1681,25 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
se->ckpt_valid_blocks++;
}
} else {
- if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) {
+ exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map);
#ifdef CONFIG_F2FS_CHECK_FS
- if (!f2fs_test_and_clear_bit(offset,
- se->cur_valid_map_mir))
- f2fs_bug_on(sbi, 1);
- else
- WARN_ON(1);
-#else
+ mir_exist = f2fs_test_and_clear_bit(offset,
+ se->cur_valid_map_mir);
+ if (unlikely(exist != mir_exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
+ "when clearing bitmap, blk:%u, old bit:%d",
+ blkaddr, exist);
f2fs_bug_on(sbi, 1);
+ }
#endif
+ if (unlikely(!exist)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Bitmap was wrongly cleared, blk:%u", blkaddr);
+ f2fs_bug_on(sbi, 1);
+ se->valid_blocks++;
+ del = 0;
}
+
if (f2fs_discard_en(sbi) &&
f2fs_test_and_clear_bit(offset, se->discard_map))
sbi->discard_blks++;
@@ -1900,7 +2061,7 @@ static void __refresh_next_blkoff(struct f2fs_sb_info *sbi,
* This function always allocates a used segment(from dirty seglist) by SSR
* manner, so it should recover the existing segment information of valid blocks
*/
-static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
+static void change_curseg(struct f2fs_sb_info *sbi, int type)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -1921,12 +2082,10 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse)
curseg->alloc_type = SSR;
__next_free_blkoff(sbi, curseg, 0);
- if (reuse) {
- sum_page = get_sum_page(sbi, new_segno);
- sum_node = (struct f2fs_summary_block *)page_address(sum_page);
- memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
- f2fs_put_page(sum_page, 1);
- }
+ sum_page = get_sum_page(sbi, new_segno);
+ sum_node = (struct f2fs_summary_block *)page_address(sum_page);
+ memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE);
+ f2fs_put_page(sum_page, 1);
}
static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
@@ -1990,7 +2149,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
new_curseg(sbi, type, false);
else if (need_SSR(sbi) && get_ssr_segment(sbi, type))
- change_curseg(sbi, type, true);
+ change_curseg(sbi, type);
else
new_curseg(sbi, type, false);
@@ -2083,6 +2242,9 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
schedule();
}
+ /* It's time to issue all the filed discards */
+ mark_discard_range_all(sbi);
+ f2fs_wait_discard_bios(sbi);
out:
range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
return err;
@@ -2202,9 +2364,12 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
mutex_unlock(&sit_i->sentry_lock);
- if (page && IS_NODESEG(type))
+ if (page && IS_NODESEG(type)) {
fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
+ f2fs_inode_chksum_set(sbi, page);
+ }
+
if (add_list) {
struct f2fs_bio_info *io;
@@ -2236,7 +2401,8 @@ reallocate:
}
}
-void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page,
+ enum iostat_type io_type)
{
struct f2fs_io_info fio = {
.sbi = sbi,
@@ -2255,6 +2421,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
set_page_writeback(page);
f2fs_submit_page_write(&fio);
+
+ f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE);
}
void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
@@ -2263,6 +2431,8 @@ void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
set_summary(&sum, nid, 0, 0);
do_write_page(&sum, fio);
+
+ f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
}
void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
@@ -2276,13 +2446,22 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
do_write_page(&sum, fio);
f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
+
+ f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE);
}
int rewrite_data_page(struct f2fs_io_info *fio)
{
+ int err;
+
fio->new_blkaddr = fio->old_blkaddr;
stat_inc_inplace_blocks(fio->sbi);
- return f2fs_submit_page_bio(fio);
+
+ err = f2fs_submit_page_bio(fio);
+
+ f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE);
+
+ return err;
}
void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -2324,7 +2503,7 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
/* change the current segment */
if (segno != curseg->segno) {
curseg->next_segno = segno;
- change_curseg(sbi, type, true);
+ change_curseg(sbi, type);
}
curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
@@ -2343,7 +2522,7 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
if (recover_curseg) {
if (old_cursegno != curseg->segno) {
curseg->next_segno = old_cursegno;
- change_curseg(sbi, type, true);
+ change_curseg(sbi, type);
}
curseg->next_blkoff = old_blkoff;
}
@@ -2382,8 +2561,7 @@ void f2fs_wait_on_page_writeback(struct page *page,
}
}
-void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
- block_t blkaddr)
+void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr)
{
struct page *cpage;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 6b871b492fd5..e0a6cc23ace3 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -492,29 +492,11 @@ static inline int overprovision_segments(struct f2fs_sb_info *sbi)
return SM_I(sbi)->ovp_segments;
}
-static inline int overprovision_sections(struct f2fs_sb_info *sbi)
-{
- return GET_SEC_FROM_SEG(sbi, (unsigned int)overprovision_segments(sbi));
-}
-
static inline int reserved_sections(struct f2fs_sb_info *sbi)
{
return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
}
-static inline bool need_SSR(struct f2fs_sb_info *sbi)
-{
- int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
- int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
- int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
-
- if (test_opt(sbi, LFS))
- return false;
-
- return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
- 2 * reserved_sections(sbi));
-}
-
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
int freed, int needed)
{
@@ -577,6 +559,10 @@ static inline bool need_inplace_update_policy(struct inode *inode,
if (test_opt(sbi, LFS))
return false;
+ /* if this is cold file, we should overwrite to avoid fragmentation */
+ if (file_is_cold(inode))
+ return true;
+
if (policy & (0x1 << F2FS_IPU_FORCE))
return true;
if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
@@ -799,3 +785,28 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
wbc->nr_to_write = desired;
return desired - nr_to_write;
}
+
+static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ bool wakeup = false;
+ int i;
+
+ if (force)
+ goto wake_up;
+
+ mutex_lock(&dcc->cmd_lock);
+ for (i = MAX_PLIST_NUM - 1;
+ i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) {
+ if (!list_empty(&dcc->pend_list[i])) {
+ wakeup = true;
+ break;
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
+ if (!wakeup)
+ return;
+wake_up:
+ dcc->discard_wake = 1;
+ wake_up_interruptible_all(&dcc->discard_wait_queue);
+}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 32e4c025e97e..89f61eb3d167 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -25,6 +25,7 @@
#include <linux/quotaops.h>
#include <linux/f2fs_fs.h>
#include <linux/sysfs.h>
+#include <linux/quota.h>
#include "f2fs.h"
#include "node.h"
@@ -107,8 +108,20 @@ enum {
Opt_fault_injection,
Opt_lazytime,
Opt_nolazytime,
+ Opt_quota,
+ Opt_noquota,
Opt_usrquota,
Opt_grpquota,
+ Opt_prjquota,
+ Opt_usrjquota,
+ Opt_grpjquota,
+ Opt_prjjquota,
+ Opt_offusrjquota,
+ Opt_offgrpjquota,
+ Opt_offprjjquota,
+ Opt_jqfmt_vfsold,
+ Opt_jqfmt_vfsv0,
+ Opt_jqfmt_vfsv1,
Opt_err,
};
@@ -144,8 +157,20 @@ static match_table_t f2fs_tokens = {
{Opt_fault_injection, "fault_injection=%u"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
+ {Opt_quota, "quota"},
+ {Opt_noquota, "noquota"},
{Opt_usrquota, "usrquota"},
{Opt_grpquota, "grpquota"},
+ {Opt_prjquota, "prjquota"},
+ {Opt_usrjquota, "usrjquota=%s"},
+ {Opt_grpjquota, "grpjquota=%s"},
+ {Opt_prjjquota, "prjjquota=%s"},
+ {Opt_offusrjquota, "usrjquota="},
+ {Opt_offgrpjquota, "grpjquota="},
+ {Opt_offprjjquota, "prjjquota="},
+ {Opt_jqfmt_vfsold, "jqfmt=vfsold"},
+ {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"},
+ {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"},
{Opt_err, NULL},
};
@@ -157,7 +182,7 @@ void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
+ printk_ratelimited("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf);
va_end(args);
}
@@ -168,6 +193,104 @@ static void init_once(void *foo)
inode_init_once(&fi->vfs_inode);
}
+#ifdef CONFIG_QUOTA
+static const char * const quotatypes[] = INITQFNAMES;
+#define QTYPE2NAME(t) (quotatypes[t])
+static int f2fs_set_qf_name(struct super_block *sb, int qtype,
+ substring_t *args)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ char *qname;
+ int ret = -EINVAL;
+
+ if (sb_any_quota_loaded(sb) && !sbi->s_qf_names[qtype]) {
+ f2fs_msg(sb, KERN_ERR,
+ "Cannot change journaled "
+ "quota options when quota turned on");
+ return -EINVAL;
+ }
+ qname = match_strdup(args);
+ if (!qname) {
+ f2fs_msg(sb, KERN_ERR,
+ "Not enough memory for storing quotafile name");
+ return -EINVAL;
+ }
+ if (sbi->s_qf_names[qtype]) {
+ if (strcmp(sbi->s_qf_names[qtype], qname) == 0)
+ ret = 0;
+ else
+ f2fs_msg(sb, KERN_ERR,
+ "%s quota file already specified",
+ QTYPE2NAME(qtype));
+ goto errout;
+ }
+ if (strchr(qname, '/')) {
+ f2fs_msg(sb, KERN_ERR,
+ "quotafile must be on filesystem root");
+ goto errout;
+ }
+ sbi->s_qf_names[qtype] = qname;
+ set_opt(sbi, QUOTA);
+ return 0;
+errout:
+ kfree(qname);
+ return ret;
+}
+
+static int f2fs_clear_qf_name(struct super_block *sb, int qtype)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+ if (sb_any_quota_loaded(sb) && sbi->s_qf_names[qtype]) {
+ f2fs_msg(sb, KERN_ERR, "Cannot change journaled quota options"
+ " when quota turned on");
+ return -EINVAL;
+ }
+ kfree(sbi->s_qf_names[qtype]);
+ sbi->s_qf_names[qtype] = NULL;
+ return 0;
+}
+
+static int f2fs_check_quota_options(struct f2fs_sb_info *sbi)
+{
+ /*
+ * We do the test below only for project quotas. 'usrquota' and
+ * 'grpquota' mount options are allowed even without quota feature
+ * to support legacy quotas in quota files.
+ */
+ if (test_opt(sbi, PRJQUOTA) && !f2fs_sb_has_project_quota(sbi->sb)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "Project quota feature not enabled. "
+ "Cannot enable project quota enforcement.");
+ return -1;
+ }
+ if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA] ||
+ sbi->s_qf_names[PRJQUOTA]) {
+ if (test_opt(sbi, USRQUOTA) && sbi->s_qf_names[USRQUOTA])
+ clear_opt(sbi, USRQUOTA);
+
+ if (test_opt(sbi, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA])
+ clear_opt(sbi, GRPQUOTA);
+
+ if (test_opt(sbi, PRJQUOTA) && sbi->s_qf_names[PRJQUOTA])
+ clear_opt(sbi, PRJQUOTA);
+
+ if (test_opt(sbi, GRPQUOTA) || test_opt(sbi, USRQUOTA) ||
+ test_opt(sbi, PRJQUOTA)) {
+ f2fs_msg(sbi->sb, KERN_ERR, "old and new quota "
+ "format mixing");
+ return -1;
+ }
+
+ if (!sbi->s_jquota_fmt) {
+ f2fs_msg(sbi->sb, KERN_ERR, "journaled quota format "
+ "not specified");
+ return -1;
+ }
+ }
+ return 0;
+}
+#endif
+
static int parse_options(struct super_block *sb, char *options)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -175,6 +298,9 @@ static int parse_options(struct super_block *sb, char *options)
substring_t args[MAX_OPT_ARGS];
char *p, *name;
int arg = 0;
+#ifdef CONFIG_QUOTA
+ int ret;
+#endif
if (!options)
return 0;
@@ -386,15 +512,76 @@ static int parse_options(struct super_block *sb, char *options)
sb->s_flags &= ~MS_LAZYTIME;
break;
#ifdef CONFIG_QUOTA
+ case Opt_quota:
case Opt_usrquota:
set_opt(sbi, USRQUOTA);
break;
case Opt_grpquota:
set_opt(sbi, GRPQUOTA);
break;
+ case Opt_prjquota:
+ set_opt(sbi, PRJQUOTA);
+ break;
+ case Opt_usrjquota:
+ ret = f2fs_set_qf_name(sb, USRQUOTA, &args[0]);
+ if (ret)
+ return ret;
+ break;
+ case Opt_grpjquota:
+ ret = f2fs_set_qf_name(sb, GRPQUOTA, &args[0]);
+ if (ret)
+ return ret;
+ break;
+ case Opt_prjjquota:
+ ret = f2fs_set_qf_name(sb, PRJQUOTA, &args[0]);
+ if (ret)
+ return ret;
+ break;
+ case Opt_offusrjquota:
+ ret = f2fs_clear_qf_name(sb, USRQUOTA);
+ if (ret)
+ return ret;
+ break;
+ case Opt_offgrpjquota:
+ ret = f2fs_clear_qf_name(sb, GRPQUOTA);
+ if (ret)
+ return ret;
+ break;
+ case Opt_offprjjquota:
+ ret = f2fs_clear_qf_name(sb, PRJQUOTA);
+ if (ret)
+ return ret;
+ break;
+ case Opt_jqfmt_vfsold:
+ sbi->s_jquota_fmt = QFMT_VFS_OLD;
+ break;
+ case Opt_jqfmt_vfsv0:
+ sbi->s_jquota_fmt = QFMT_VFS_V0;
+ break;
+ case Opt_jqfmt_vfsv1:
+ sbi->s_jquota_fmt = QFMT_VFS_V1;
+ break;
+ case Opt_noquota:
+ clear_opt(sbi, QUOTA);
+ clear_opt(sbi, USRQUOTA);
+ clear_opt(sbi, GRPQUOTA);
+ clear_opt(sbi, PRJQUOTA);
+ break;
#else
+ case Opt_quota:
case Opt_usrquota:
case Opt_grpquota:
+ case Opt_prjquota:
+ case Opt_usrjquota:
+ case Opt_grpjquota:
+ case Opt_prjjquota:
+ case Opt_offusrjquota:
+ case Opt_offgrpjquota:
+ case Opt_offprjjquota:
+ case Opt_jqfmt_vfsold:
+ case Opt_jqfmt_vfsv0:
+ case Opt_jqfmt_vfsv1:
+ case Opt_noquota:
f2fs_msg(sb, KERN_INFO,
"quota operations not supported");
break;
@@ -406,6 +593,10 @@ static int parse_options(struct super_block *sb, char *options)
return -EINVAL;
}
}
+#ifdef CONFIG_QUOTA
+ if (f2fs_check_quota_options(sbi))
+ return -EINVAL;
+#endif
if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
f2fs_msg(sb, KERN_ERR,
@@ -439,6 +630,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
init_rwsem(&fi->dio_rwsem[READ]);
init_rwsem(&fi->dio_rwsem[WRITE]);
init_rwsem(&fi->i_mmap_sem);
+ init_rwsem(&fi->i_xattr_sem);
#ifdef CONFIG_QUOTA
memset(&fi->i_dquot, 0, sizeof(fi->i_dquot));
@@ -446,6 +638,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
#endif
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
+
return &fi->vfs_inode;
}
@@ -584,7 +777,6 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
kfree(sbi->devs);
}
-static void f2fs_quota_off_umount(struct super_block *sb);
static void f2fs_put_super(struct super_block *sb)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -642,7 +834,7 @@ static void f2fs_put_super(struct super_block *sb)
kfree(sbi->ckpt);
- f2fs_exit_sysfs(sbi);
+ f2fs_unregister_sysfs(sbi);
sb->s_fs_info = NULL;
if (sbi->s_chksum_driver)
@@ -651,6 +843,10 @@ static void f2fs_put_super(struct super_block *sb)
destroy_device_list(sbi);
mempool_destroy(sbi->write_io_dummy);
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
+#endif
destroy_percpu_info(sbi);
for (i = 0; i < NR_PAGE_TYPE; i++)
kfree(sbi->write_io[i]);
@@ -664,6 +860,9 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
trace_f2fs_sync_fs(sb, sync);
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ return -EAGAIN;
+
if (sync) {
struct cp_control cpc;
@@ -698,6 +897,48 @@ static int f2fs_unfreeze(struct super_block *sb)
return 0;
}
+#ifdef CONFIG_QUOTA
+static int f2fs_statfs_project(struct super_block *sb,
+ kprojid_t projid, struct kstatfs *buf)
+{
+ struct kqid qid;
+ struct dquot *dquot;
+ u64 limit;
+ u64 curblock;
+
+ qid = make_kqid_projid(projid);
+ dquot = dqget(sb, qid);
+ if (IS_ERR(dquot))
+ return PTR_ERR(dquot);
+ spin_lock(&dq_data_lock);
+
+ limit = (dquot->dq_dqb.dqb_bsoftlimit ?
+ dquot->dq_dqb.dqb_bsoftlimit :
+ dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits;
+ if (limit && buf->f_blocks > limit) {
+ curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits;
+ buf->f_blocks = limit;
+ buf->f_bfree = buf->f_bavail =
+ (buf->f_blocks > curblock) ?
+ (buf->f_blocks - curblock) : 0;
+ }
+
+ limit = dquot->dq_dqb.dqb_isoftlimit ?
+ dquot->dq_dqb.dqb_isoftlimit :
+ dquot->dq_dqb.dqb_ihardlimit;
+ if (limit && buf->f_files > limit) {
+ buf->f_files = limit;
+ buf->f_ffree =
+ (buf->f_files > dquot->dq_dqb.dqb_curinodes) ?
+ (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0;
+ }
+
+ spin_unlock(&dq_data_lock);
+ dqput(dquot);
+ return 0;
+}
+#endif
+
static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
@@ -733,9 +974,49 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
+#ifdef CONFIG_QUOTA
+ if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) &&
+ sb_has_quota_limits_enabled(sb, PRJQUOTA)) {
+ f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf);
+ }
+#endif
return 0;
}
+static inline void f2fs_show_quota_options(struct seq_file *seq,
+ struct super_block *sb)
+{
+#ifdef CONFIG_QUOTA
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+
+ if (sbi->s_jquota_fmt) {
+ char *fmtname = "";
+
+ switch (sbi->s_jquota_fmt) {
+ case QFMT_VFS_OLD:
+ fmtname = "vfsold";
+ break;
+ case QFMT_VFS_V0:
+ fmtname = "vfsv0";
+ break;
+ case QFMT_VFS_V1:
+ fmtname = "vfsv1";
+ break;
+ }
+ seq_printf(seq, ",jqfmt=%s", fmtname);
+ }
+
+ if (sbi->s_qf_names[USRQUOTA])
+ seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]);
+
+ if (sbi->s_qf_names[GRPQUOTA])
+ seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]);
+
+ if (sbi->s_qf_names[PRJQUOTA])
+ seq_show_option(seq, "prjjquota", sbi->s_qf_names[PRJQUOTA]);
+#endif
+}
+
static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
@@ -809,11 +1090,16 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
sbi->fault_info.inject_rate);
#endif
#ifdef CONFIG_QUOTA
+ if (test_opt(sbi, QUOTA))
+ seq_puts(seq, ",quota");
if (test_opt(sbi, USRQUOTA))
seq_puts(seq, ",usrquota");
if (test_opt(sbi, GRPQUOTA))
seq_puts(seq, ",grpquota");
+ if (test_opt(sbi, PRJQUOTA))
+ seq_puts(seq, ",prjquota");
#endif
+ f2fs_show_quota_options(seq, sbi->sb);
return 0;
}
@@ -862,6 +1148,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
#ifdef CONFIG_F2FS_FAULT_INJECTION
struct f2fs_fault_info ffi = sbi->fault_info;
#endif
+#ifdef CONFIG_QUOTA
+ int s_jquota_fmt;
+ char *s_qf_names[MAXQUOTAS];
+ int i, j;
+#endif
/*
* Save the old mount options in case we
@@ -871,6 +1162,23 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
old_sb_flags = sb->s_flags;
active_logs = sbi->active_logs;
+#ifdef CONFIG_QUOTA
+ s_jquota_fmt = sbi->s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (sbi->s_qf_names[i]) {
+ s_qf_names[i] = kstrdup(sbi->s_qf_names[i],
+ GFP_KERNEL);
+ if (!s_qf_names[i]) {
+ for (j = 0; j < i; j++)
+ kfree(s_qf_names[j]);
+ return -ENOMEM;
+ }
+ } else {
+ s_qf_names[i] = NULL;
+ }
+ }
+#endif
+
/* recover superblocks we couldn't write due to previous RO mount */
if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
err = f2fs_commit_super(sbi, false);
@@ -952,6 +1260,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
goto restore_gc;
}
skip:
+#ifdef CONFIG_QUOTA
+ /* Release old quota file names */
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(s_qf_names[i]);
+#endif
/* Update the POSIXACL Flag */
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
@@ -966,6 +1279,13 @@ restore_gc:
stop_gc_thread(sbi);
}
restore_opts:
+#ifdef CONFIG_QUOTA
+ sbi->s_jquota_fmt = s_jquota_fmt;
+ for (i = 0; i < MAXQUOTAS; i++) {
+ kfree(sbi->s_qf_names[i]);
+ sbi->s_qf_names[i] = s_qf_names[i];
+ }
+#endif
sbi->mount_opt = org_mount_opt;
sbi->active_logs = active_logs;
sb->s_flags = old_sb_flags;
@@ -1065,7 +1385,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type,
}
if (len == towrite)
- return err;
+ return 0;
inode->i_version++;
inode->i_mtime = inode->i_ctime = current_time(inode);
f2fs_mark_inode_dirty_sync(inode, false);
@@ -1082,6 +1402,27 @@ static qsize_t *f2fs_get_reserved_space(struct inode *inode)
return &F2FS_I(inode)->i_reserved_quota;
}
+static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type)
+{
+ return dquot_quota_on_mount(sbi->sb, sbi->s_qf_names[type],
+ sbi->s_jquota_fmt, type);
+}
+
+void f2fs_enable_quota_files(struct f2fs_sb_info *sbi)
+{
+ int i, ret;
+
+ for (i = 0; i < MAXQUOTAS; i++) {
+ if (sbi->s_qf_names[i]) {
+ ret = f2fs_quota_on_mount(sbi, i);
+ if (ret < 0)
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Cannot turn on journaled "
+ "quota: error %d", ret);
+ }
+ }
+}
+
static int f2fs_quota_sync(struct super_block *sb, int type)
{
struct quota_info *dqopt = sb_dqopt(sb);
@@ -1119,7 +1460,7 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
struct inode *inode;
int err;
- err = f2fs_quota_sync(sb, -1);
+ err = f2fs_quota_sync(sb, type);
if (err)
return err;
@@ -1147,7 +1488,7 @@ static int f2fs_quota_off(struct super_block *sb, int type)
if (!inode || !igrab(inode))
return dquot_quota_off(sb, type);
- f2fs_quota_sync(sb, -1);
+ f2fs_quota_sync(sb, type);
err = dquot_quota_off(sb, type);
if (err)
@@ -1163,7 +1504,7 @@ out_put:
return err;
}
-static void f2fs_quota_off_umount(struct super_block *sb)
+void f2fs_quota_off_umount(struct super_block *sb)
{
int type;
@@ -1171,6 +1512,12 @@ static void f2fs_quota_off_umount(struct super_block *sb)
f2fs_quota_off(sb, type);
}
+int f2fs_get_projid(struct inode *inode, kprojid_t *projid)
+{
+ *projid = F2FS_I(inode)->i_projid;
+ return 0;
+}
+
static const struct dquot_operations f2fs_quota_operations = {
.get_reserved_space = f2fs_get_reserved_space,
.write_dquot = dquot_commit,
@@ -1180,6 +1527,7 @@ static const struct dquot_operations f2fs_quota_operations = {
.write_info = dquot_commit_info,
.alloc_dquot = dquot_alloc,
.destroy_dquot = dquot_destroy,
+ .get_projid = f2fs_get_projid,
.get_next_id = dquot_get_next_id,
};
@@ -1194,12 +1542,12 @@ static const struct quotactl_ops f2fs_quotactl_ops = {
.get_nextdqblk = dquot_get_next_dqblk,
};
#else
-static inline void f2fs_quota_off_umount(struct super_block *sb)
+void f2fs_quota_off_umount(struct super_block *sb)
{
}
#endif
-static struct super_operations f2fs_sops = {
+static const struct super_operations f2fs_sops = {
.alloc_inode = f2fs_alloc_inode,
.drop_inode = f2fs_drop_inode,
.destroy_inode = f2fs_destroy_inode,
@@ -1303,9 +1651,16 @@ static const struct export_operations f2fs_export_ops = {
static loff_t max_file_blocks(void)
{
- loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
+ loff_t result = 0;
loff_t leaf_count = ADDRS_PER_BLOCK;
+ /*
+ * note: previously, result is equal to (DEF_ADDRS_PER_INODE -
+ * F2FS_INLINE_XATTR_ADDRS), but now f2fs try to reserve more
+ * space in inode.i_addr, it will be more safe to reassign
+ * result as zero.
+ */
+
/* two direct node blocks */
result += (leaf_count * 2);
@@ -1922,6 +2277,11 @@ try_onemore:
sb->s_fs_info = sbi;
sbi->raw_super = raw_super;
+ /* precompute checksum seed for metadata */
+ if (f2fs_sb_has_inode_chksum(sb))
+ sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid,
+ sizeof(raw_super->uuid));
+
/*
* The BLKZONED feature indicates that the drive was formatted with
* zone alignment optimization. This is optional for host-aware
@@ -1956,7 +2316,7 @@ try_onemore:
#ifdef CONFIG_QUOTA
sb->dq_op = &f2fs_quota_operations;
sb->s_qcop = &f2fs_quotactl_ops;
- sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
+ sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
#endif
sb->s_op = &f2fs_sops;
@@ -1980,6 +2340,10 @@ try_onemore:
set_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
+ /* init iostat info */
+ spin_lock_init(&sbi->iostat_lock);
+ sbi->iostat_enable = false;
+
for (i = 0; i < NR_PAGE_TYPE; i++) {
int n = (i == META) ? 1: NR_TEMP_TYPE;
int j;
@@ -2098,11 +2462,6 @@ try_onemore:
if (err)
goto free_nm;
- /* if there are nt orphan nodes free them */
- err = recover_orphan_inodes(sbi);
- if (err)
- goto free_node_inode;
-
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
if (IS_ERR(root)) {
@@ -2122,10 +2481,15 @@ try_onemore:
goto free_root_inode;
}
- err = f2fs_init_sysfs(sbi);
+ err = f2fs_register_sysfs(sbi);
if (err)
goto free_root_inode;
+ /* if there are nt orphan nodes free them */
+ err = recover_orphan_inodes(sbi);
+ if (err)
+ goto free_sysfs;
+
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
/*
@@ -2135,7 +2499,7 @@ try_onemore:
if (bdev_read_only(sb->s_bdev) &&
!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
err = -EROFS;
- goto free_sysfs;
+ goto free_meta;
}
if (need_fsck)
@@ -2149,7 +2513,7 @@ try_onemore:
need_fsck = true;
f2fs_msg(sb, KERN_ERR,
"Cannot recover all fsync data errno=%d", err);
- goto free_sysfs;
+ goto free_meta;
}
} else {
err = recover_fsync_data(sbi, true);
@@ -2173,7 +2537,7 @@ skip_recovery:
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
if (err)
- goto free_sysfs;
+ goto free_meta;
}
kfree(options);
@@ -2191,9 +2555,17 @@ skip_recovery:
f2fs_update_time(sbi, REQ_TIME);
return 0;
-free_sysfs:
+free_meta:
f2fs_sync_inode_meta(sbi);
- f2fs_exit_sysfs(sbi);
+ /*
+ * Some dirty meta pages can be produced by recover_orphan_inodes()
+ * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
+ * followed by write_checkpoint() through f2fs_write_node_pages(), which
+ * falls into an infinite loop in sync_meta_pages().
+ */
+ truncate_inode_pages_final(META_MAPPING(sbi));
+free_sysfs:
+ f2fs_unregister_sysfs(sbi);
free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
@@ -2202,13 +2574,6 @@ free_node_inode:
mutex_lock(&sbi->umount_mutex);
release_ino_entry(sbi, true);
f2fs_leave_shrinker(sbi);
- /*
- * Some dirty meta pages can be produced by recover_orphan_inodes()
- * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
- * followed by write_checkpoint() through f2fs_write_node_pages(), which
- * falls into an infinite loop in sync_meta_pages().
- */
- truncate_inode_pages_final(META_MAPPING(sbi));
iput(sbi->node_inode);
mutex_unlock(&sbi->umount_mutex);
f2fs_destroy_stats(sbi);
@@ -2228,6 +2593,10 @@ free_options:
for (i = 0; i < NR_PAGE_TYPE; i++)
kfree(sbi->write_io[i]);
destroy_percpu_info(sbi);
+#ifdef CONFIG_QUOTA
+ for (i = 0; i < MAXQUOTAS; i++)
+ kfree(sbi->s_qf_names[i]);
+#endif
kfree(options);
free_sb_buf:
kfree(raw_super);
@@ -2311,7 +2680,7 @@ static int __init init_f2fs_fs(void)
err = create_extent_cache();
if (err)
goto free_checkpoint_caches;
- err = f2fs_register_sysfs();
+ err = f2fs_init_sysfs();
if (err)
goto free_extent_cache;
err = register_shrinker(&f2fs_shrinker_info);
@@ -2330,7 +2699,7 @@ free_filesystem:
free_shrinker:
unregister_shrinker(&f2fs_shrinker_info);
free_sysfs:
- f2fs_unregister_sysfs();
+ f2fs_exit_sysfs();
free_extent_cache:
destroy_extent_cache();
free_checkpoint_caches:
@@ -2350,7 +2719,7 @@ static void __exit exit_f2fs_fs(void)
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
unregister_shrinker(&f2fs_shrinker_info);
- f2fs_unregister_sysfs();
+ f2fs_exit_sysfs();
destroy_extent_cache();
destroy_checkpoint_caches();
destroy_segment_manager_caches();
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index 71191d89917d..e2c258f717cd 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -18,7 +18,6 @@
#include "gc.h"
static struct proc_dir_entry *f2fs_proc_root;
-static struct kset *f2fs_kset;
/* Sysfs support for f2fs */
enum {
@@ -41,6 +40,7 @@ struct f2fs_attr {
const char *, size_t);
int struct_type;
int offset;
+ int id;
};
static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
@@ -76,6 +76,34 @@ static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
BD_PART_WRITTEN(sbi)));
}
+static ssize_t features_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct super_block *sb = sbi->sb;
+ int len = 0;
+
+ if (!sb->s_bdev->bd_part)
+ return snprintf(buf, PAGE_SIZE, "0\n");
+
+ if (f2fs_sb_has_crypto(sb))
+ len += snprintf(buf, PAGE_SIZE - len, "%s",
+ "encryption");
+ if (f2fs_sb_mounted_blkzoned(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "blkzoned");
+ if (f2fs_sb_has_extra_attr(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "extra_attr");
+ if (f2fs_sb_has_project_quota(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "projquota");
+ if (f2fs_sb_has_inode_chksum(sb))
+ len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
+ len ? ", " : "", "inode_checksum");
+ len += snprintf(buf + len, PAGE_SIZE - len, "\n");
+ return len;
+}
+
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -124,7 +152,39 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
spin_unlock(&sbi->stat_lock);
return count;
}
+
+ if (!strcmp(a->attr.name, "discard_granularity")) {
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ int i;
+
+ if (t == 0 || t > MAX_PLIST_NUM)
+ return -EINVAL;
+ if (t == *ui)
+ return count;
+
+ mutex_lock(&dcc->cmd_lock);
+ for (i = 0; i < MAX_PLIST_NUM; i++) {
+ if (i >= t - 1)
+ dcc->pend_list_tag[i] |= P_ACTIVE;
+ else
+ dcc->pend_list_tag[i] &= (~P_ACTIVE);
+ }
+ mutex_unlock(&dcc->cmd_lock);
+
+ *ui = t;
+ return count;
+ }
+
*ui = t;
+
+ if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0)
+ f2fs_reset_iostat(sbi);
+ if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && 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);
+ }
+
return count;
}
@@ -155,6 +215,30 @@ static void f2fs_sb_release(struct kobject *kobj)
complete(&sbi->s_kobj_unregister);
}
+enum feat_id {
+ FEAT_CRYPTO = 0,
+ FEAT_BLKZONED,
+ FEAT_ATOMIC_WRITE,
+ FEAT_EXTRA_ATTR,
+ FEAT_PROJECT_QUOTA,
+ FEAT_INODE_CHECKSUM,
+};
+
+static ssize_t f2fs_feature_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ switch (a->id) {
+ case FEAT_CRYPTO:
+ case FEAT_BLKZONED:
+ case FEAT_ATOMIC_WRITE:
+ case FEAT_EXTRA_ATTR:
+ case FEAT_PROJECT_QUOTA:
+ case FEAT_INODE_CHECKSUM:
+ return snprintf(buf, PAGE_SIZE, "supported\n");
+ }
+ return 0;
+}
+
#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
static struct f2fs_attr f2fs_attr_##_name = { \
.attr = {.name = __stringify(_name), .mode = _mode }, \
@@ -172,12 +256,23 @@ static struct f2fs_attr f2fs_attr_##_name = { \
#define F2FS_GENERAL_RO_ATTR(name) \
static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+#define F2FS_FEATURE_RO_ATTR(_name, _id) \
+static struct f2fs_attr f2fs_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = 0444 }, \
+ .show = f2fs_feature_show, \
+ .id = _id, \
+}
+
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time,
+ urgent_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent, gc_urgent);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
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);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
@@ -191,20 +286,36 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable);
#ifdef CONFIG_F2FS_FAULT_INJECTION
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_GENERAL_RO_ATTR(lifetime_write_kbytes);
+F2FS_GENERAL_RO_ATTR(features);
+
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
+#endif
+#ifdef CONFIG_BLK_DEV_ZONED
+F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED);
+#endif
+F2FS_FEATURE_RO_ATTR(atomic_write, FEAT_ATOMIC_WRITE);
+F2FS_FEATURE_RO_ATTR(extra_attr, FEAT_EXTRA_ATTR);
+F2FS_FEATURE_RO_ATTR(project_quota, FEAT_PROJECT_QUOTA);
+F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
+ ATTR_LIST(gc_urgent_sleep_time),
ATTR_LIST(gc_min_sleep_time),
ATTR_LIST(gc_max_sleep_time),
ATTR_LIST(gc_no_gc_sleep_time),
ATTR_LIST(gc_idle),
+ ATTR_LIST(gc_urgent),
ATTR_LIST(reclaim_segments),
ATTR_LIST(max_small_discards),
+ ATTR_LIST(discard_granularity),
ATTR_LIST(batched_trim_sections),
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
@@ -217,26 +328,59 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(dirty_nats_ratio),
ATTR_LIST(cp_interval),
ATTR_LIST(idle_interval),
+ ATTR_LIST(iostat_enable),
#ifdef CONFIG_F2FS_FAULT_INJECTION
ATTR_LIST(inject_rate),
ATTR_LIST(inject_type),
#endif
ATTR_LIST(lifetime_write_kbytes),
+ ATTR_LIST(features),
ATTR_LIST(reserved_blocks),
NULL,
};
+static struct attribute *f2fs_feat_attrs[] = {
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ ATTR_LIST(encryption),
+#endif
+#ifdef CONFIG_BLK_DEV_ZONED
+ ATTR_LIST(block_zoned),
+#endif
+ ATTR_LIST(atomic_write),
+ ATTR_LIST(extra_attr),
+ ATTR_LIST(project_quota),
+ ATTR_LIST(inode_checksum),
+ NULL,
+};
+
static const struct sysfs_ops f2fs_attr_ops = {
.show = f2fs_attr_show,
.store = f2fs_attr_store,
};
-static struct kobj_type f2fs_ktype = {
+static struct kobj_type f2fs_sb_ktype = {
.default_attrs = f2fs_attrs,
.sysfs_ops = &f2fs_attr_ops,
.release = f2fs_sb_release,
};
+static struct kobj_type f2fs_ktype = {
+ .sysfs_ops = &f2fs_attr_ops,
+};
+
+static struct kset f2fs_kset = {
+ .kobj = {.ktype = &f2fs_ktype},
+};
+
+static struct kobj_type f2fs_feat_ktype = {
+ .default_attrs = f2fs_feat_attrs,
+ .sysfs_ops = &f2fs_attr_ops,
+};
+
+static struct kobject f2fs_feat = {
+ .kset = &f2fs_kset,
+};
+
static int segment_info_seq_show(struct seq_file *seq, void *offset)
{
struct super_block *sb = seq->private;
@@ -288,6 +432,48 @@ static int segment_bits_seq_show(struct seq_file *seq, void *offset)
return 0;
}
+static int iostat_info_seq_show(struct seq_file *seq, void *offset)
+{
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ time64_t now = ktime_get_real_seconds();
+
+ if (!sbi->iostat_enable)
+ return 0;
+
+ seq_printf(seq, "time: %-16llu\n", now);
+
+ /* print app IOs */
+ seq_printf(seq, "app buffered: %-16llu\n",
+ sbi->write_iostat[APP_BUFFERED_IO]);
+ seq_printf(seq, "app direct: %-16llu\n",
+ sbi->write_iostat[APP_DIRECT_IO]);
+ seq_printf(seq, "app mapped: %-16llu\n",
+ sbi->write_iostat[APP_MAPPED_IO]);
+
+ /* print fs IOs */
+ seq_printf(seq, "fs data: %-16llu\n",
+ sbi->write_iostat[FS_DATA_IO]);
+ seq_printf(seq, "fs node: %-16llu\n",
+ sbi->write_iostat[FS_NODE_IO]);
+ seq_printf(seq, "fs meta: %-16llu\n",
+ sbi->write_iostat[FS_META_IO]);
+ seq_printf(seq, "fs gc data: %-16llu\n",
+ sbi->write_iostat[FS_GC_DATA_IO]);
+ seq_printf(seq, "fs gc node: %-16llu\n",
+ sbi->write_iostat[FS_GC_NODE_IO]);
+ seq_printf(seq, "fs cp data: %-16llu\n",
+ sbi->write_iostat[FS_CP_DATA_IO]);
+ seq_printf(seq, "fs cp node: %-16llu\n",
+ sbi->write_iostat[FS_CP_NODE_IO]);
+ seq_printf(seq, "fs cp meta: %-16llu\n",
+ sbi->write_iostat[FS_CP_META_IO]);
+ seq_printf(seq, "fs discard: %-16llu\n",
+ sbi->write_iostat[FS_DISCARD]);
+
+ return 0;
+}
+
#define F2FS_PROC_FILE_DEF(_name) \
static int _name##_open_fs(struct inode *inode, struct file *file) \
{ \
@@ -303,28 +489,47 @@ static const struct file_operations f2fs_seq_##_name##_fops = { \
F2FS_PROC_FILE_DEF(segment_info);
F2FS_PROC_FILE_DEF(segment_bits);
+F2FS_PROC_FILE_DEF(iostat_info);
-int __init f2fs_register_sysfs(void)
+int __init f2fs_init_sysfs(void)
{
- f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ int ret;
- f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
- if (!f2fs_kset)
- return -ENOMEM;
- return 0;
+ kobject_set_name(&f2fs_kset.kobj, "f2fs");
+ f2fs_kset.kobj.parent = fs_kobj;
+ ret = kset_register(&f2fs_kset);
+ if (ret)
+ return ret;
+
+ ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype,
+ NULL, "features");
+ if (ret)
+ kset_unregister(&f2fs_kset);
+ else
+ f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ return ret;
}
-void f2fs_unregister_sysfs(void)
+void f2fs_exit_sysfs(void)
{
- kset_unregister(f2fs_kset);
+ kobject_put(&f2fs_feat);
+ kset_unregister(&f2fs_kset);
remove_proc_entry("fs/f2fs", NULL);
+ f2fs_proc_root = NULL;
}
-int f2fs_init_sysfs(struct f2fs_sb_info *sbi)
+int f2fs_register_sysfs(struct f2fs_sb_info *sbi)
{
struct super_block *sb = sbi->sb;
int err;
+ sbi->s_kobj.kset = &f2fs_kset;
+ init_completion(&sbi->s_kobj_unregister);
+ err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL,
+ "%s", sb->s_id);
+ if (err)
+ return err;
+
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
@@ -333,33 +538,19 @@ int f2fs_init_sysfs(struct f2fs_sb_info *sbi)
&f2fs_seq_segment_info_fops, sb);
proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_bits_fops, sb);
+ proc_create_data("iostat_info", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_iostat_info_fops, sb);
}
-
- sbi->s_kobj.kset = f2fs_kset;
- init_completion(&sbi->s_kobj_unregister);
- err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
- "%s", sb->s_id);
- if (err)
- goto err_out;
return 0;
-err_out:
- if (sbi->s_proc) {
- remove_proc_entry("segment_info", sbi->s_proc);
- remove_proc_entry("segment_bits", sbi->s_proc);
- remove_proc_entry(sb->s_id, f2fs_proc_root);
- }
- return err;
}
-void f2fs_exit_sysfs(struct f2fs_sb_info *sbi)
+void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi)
{
- kobject_del(&sbi->s_kobj);
- kobject_put(&sbi->s_kobj);
- wait_for_completion(&sbi->s_kobj_unregister);
-
if (sbi->s_proc) {
+ remove_proc_entry("iostat_info", sbi->s_proc);
remove_proc_entry("segment_info", sbi->s_proc);
remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
}
+ kobject_del(&sbi->s_kobj);
}
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 832c5110abab..7c65540148f8 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -442,7 +442,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
} else {
struct dnode_of_data dn;
set_new_dnode(&dn, inode, NULL, NULL, new_nid);
- xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
+ xpage = new_node_page(&dn, XATTR_NODE_OFFSET);
if (IS_ERR(xpage)) {
alloc_nid_failed(sbi, new_nid);
return PTR_ERR(xpage);
@@ -473,8 +473,10 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
if (len > F2FS_NAME_LEN)
return -ERANGE;
+ down_read(&F2FS_I(inode)->i_xattr_sem);
error = lookup_all_xattrs(inode, ipage, index, len, name,
&entry, &base_addr);
+ up_read(&F2FS_I(inode)->i_xattr_sem);
if (error)
return error;
@@ -503,7 +505,9 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
int error = 0;
size_t rest = buffer_size;
+ down_read(&F2FS_I(inode)->i_xattr_sem);
error = read_all_xattrs(inode, NULL, &base_addr);
+ up_read(&F2FS_I(inode)->i_xattr_sem);
if (error)
return error;
@@ -686,7 +690,9 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
f2fs_lock_op(sbi);
/* protect xattr_ver */
down_write(&F2FS_I(inode)->i_sem);
+ down_write(&F2FS_I(inode)->i_xattr_sem);
err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags);
+ up_write(&F2FS_I(inode)->i_xattr_sem);
up_write(&F2FS_I(inode)->i_sem);
f2fs_unlock_op(sbi);