diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index bd3c56c67380..b91e2f26b672 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -98,8 +98,13 @@ Cleaning Overhead
MOUNT OPTIONS
================================================================================
-background_gc_off Turn off cleaning operations, namely garbage collection,
- triggered in background when I/O subsystem is idle.
+background_gc=%s Turn on/off cleaning operations, namely garbage
+ collection, triggered in background when I/O subsystem is
+ idle. If background_gc=on, it will turn on the garbage
+ collection and if background_gc=off, garbage collection
+ will be truned off.
+ Default value for this option is on. So garbage
+ collection is on by default.
disable_roll_forward Disable the roll-forward recovery routine
discard Issue discard/TRIM commands when a segment is cleaned.
no_heap Disable heap-style segment allocation which finds free
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index fd27e7e6326e..e06e0995e00f 100644
--- a/fs/f2fs/Kconfig
+++ b/fs/f2fs/Kconfig
@@ -51,3 +51,15 @@ config F2FS_FS_POSIX_ACL
Linux website .
If you don't know what Access Control Lists are, say N
+
+config F2FS_FS_SECURITY
+ bool "F2FS Security Labels"
+ depends on F2FS_FS_XATTR
+ help
+ Security labels provide an access control facility to support Linux
+ Security Models (LSMs) accepted by AppArmor, SELinux, Smack and TOMOYO
+ Linux. This option enables an extended attribute handler for file
+ security labels in the f2fs filesystem, so that it requires enabling
+ the extended attribute support in advance.
+
+ If you are not using a security module, say N.
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 44abc2f286e0..b7826ec1b470 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -250,7 +250,7 @@ static int f2fs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
}
}
- error = f2fs_setxattr(inode, name_index, "", value, size);
+ error = f2fs_setxattr(inode, name_index, "", value, size, NULL);
kfree(value);
if (!error)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index b1de01da1a40..66a6b85a51d8 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -357,8 +357,8 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
unsigned long blk_size = sbi->blocksize;
struct f2fs_checkpoint *cp_block;
unsigned long long cur_version = 0, pre_version = 0;
- unsigned int crc = 0;
size_t crc_offset;
+ __u32 crc = 0;
/* Read the 1st cp block in this CP pack */
cp_page_1 = get_meta_page(sbi, cp_addr);
@@ -369,7 +369,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
if (crc_offset >= blk_size)
goto invalid_cp1;
- crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset);
+ crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
if (!f2fs_crc_valid(crc, cp_block, crc_offset))
goto invalid_cp1;
@@ -384,7 +384,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
if (crc_offset >= blk_size)
goto invalid_cp2;
- crc = *(unsigned int *)((unsigned char *)cp_block + crc_offset);
+ crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
if (!f2fs_crc_valid(crc, cp_block, crc_offset))
goto invalid_cp2;
@@ -450,13 +450,30 @@ fail_no_cp:
return -EINVAL;
}
-void set_dirty_dir_page(struct inode *inode, struct page *page)
+static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct list_head *head = &sbi->dir_inode_list;
- struct dir_inode_entry *new;
struct list_head *this;
+ list_for_each(this, head) {
+ struct dir_inode_entry *entry;
+ entry = list_entry(this, struct dir_inode_entry, list);
+ if (entry->inode == inode)
+ return -EEXIST;
+ }
+ list_add_tail(&new->list, head);
+#ifdef CONFIG_F2FS_STAT_FS
+ sbi->n_dirty_dirs++;
+#endif
+ return 0;
+}
+
+void set_dirty_dir_page(struct inode *inode, struct page *page)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct dir_inode_entry *new;
+
if (!S_ISDIR(inode->i_mode))
return;
retry:
@@ -469,23 +486,31 @@ retry:
INIT_LIST_HEAD(&new->list);
spin_lock(&sbi->dir_inode_lock);
- list_for_each(this, head) {
- struct dir_inode_entry *entry;
- entry = list_entry(this, struct dir_inode_entry, list);
- if (entry->inode == inode) {
- kmem_cache_free(inode_entry_slab, new);
- goto out;
- }
- }
- list_add_tail(&new->list, head);
- sbi->n_dirty_dirs++;
+ if (__add_dirty_inode(inode, new))
+ kmem_cache_free(inode_entry_slab, new);
- BUG_ON(!S_ISDIR(inode->i_mode));
-out:
inc_page_count(sbi, F2FS_DIRTY_DENTS);
inode_inc_dirty_dents(inode);
SetPagePrivate(page);
+ spin_unlock(&sbi->dir_inode_lock);
+}
+void add_dirty_dir_inode(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct dir_inode_entry *new;
+retry:
+ new = kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
+ if (!new) {
+ cond_resched();
+ goto retry;
+ }
+ new->inode = inode;
+ INIT_LIST_HEAD(&new->list);
+
+ spin_lock(&sbi->dir_inode_lock);
+ if (__add_dirty_inode(inode, new))
+ kmem_cache_free(inode_entry_slab, new);
spin_unlock(&sbi->dir_inode_lock);
}
@@ -499,8 +524,10 @@ void remove_dirty_dir_inode(struct inode *inode)
return;
spin_lock(&sbi->dir_inode_lock);
- if (atomic_read(&F2FS_I(inode)->dirty_dents))
- goto out;
+ if (atomic_read(&F2FS_I(inode)->dirty_dents)) {
+ spin_unlock(&sbi->dir_inode_lock);
+ return;
+ }
list_for_each(this, head) {
struct dir_inode_entry *entry;
@@ -508,12 +535,38 @@ void remove_dirty_dir_inode(struct inode *inode)
if (entry->inode == inode) {
list_del(&entry->list);
kmem_cache_free(inode_entry_slab, entry);
+#ifdef CONFIG_F2FS_STAT_FS
sbi->n_dirty_dirs--;
+#endif
break;
}
}
-out:
spin_unlock(&sbi->dir_inode_lock);
+
+ /* Only from the recovery routine */
+ if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
+ clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
+ iput(inode);
+ }
+}
+
+struct inode *check_dirty_dir_inode(struct f2fs_sb_info *sbi, nid_t ino)
+{
+ struct list_head *head = &sbi->dir_inode_list;
+ struct list_head *this;
+ struct inode *inode = NULL;
+
+ spin_lock(&sbi->dir_inode_lock);
+ list_for_each(this, head) {
+ struct dir_inode_entry *entry;
+ entry = list_entry(this, struct dir_inode_entry, list);
+ if (entry->inode->i_ino == ino) {
+ inode = entry->inode;
+ break;
+ }
+ }
+ spin_unlock(&sbi->dir_inode_lock);
+ return inode;
}
void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
@@ -595,7 +648,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
block_t start_blk;
struct page *cp_page;
unsigned int data_sum_blocks, orphan_blocks;
- unsigned int crc32 = 0;
+ __u32 crc32 = 0;
void *kaddr;
int i;
@@ -664,8 +717,8 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
- *(__le32 *)((unsigned char *)ckpt +
- le32_to_cpu(ckpt->checksum_offset))
+ *((__le32 *)((unsigned char *)ckpt +
+ le32_to_cpu(ckpt->checksum_offset)))
= cpu_to_le32(crc32);
start_blk = __start_cp_addr(sbi);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ce11d9a92aed..035f9a345cdf 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -68,7 +68,9 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
struct buffer_head *bh_result)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
+#ifdef CONFIG_F2FS_STAT_FS
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+#endif
pgoff_t start_fofs, end_fofs;
block_t start_blkaddr;
@@ -78,7 +80,9 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
return 0;
}
+#ifdef CONFIG_F2FS_STAT_FS
sbi->total_hit_ext++;
+#endif
start_fofs = fi->ext.fofs;
end_fofs = fi->ext.fofs + fi->ext.len - 1;
start_blkaddr = fi->ext.blk_addr;
@@ -96,7 +100,9 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
else
bh_result->b_size = UINT_MAX;
+#ifdef CONFIG_F2FS_STAT_FS
sbi->read_hit_ext++;
+#endif
read_unlock(&fi->ext.ext_lock);
return 1;
}
@@ -199,7 +205,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
if (dn.data_blkaddr == NEW_ADDR)
return ERR_PTR(-EINVAL);
- page = grab_cache_page(mapping, index);
+ page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -233,19 +239,24 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
struct page *page;
int err;
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
- if (err)
- return ERR_PTR(err);
- f2fs_put_dnode(&dn);
-
- if (dn.data_blkaddr == NULL_ADDR)
- return ERR_PTR(-ENOENT);
repeat:
- page = grab_cache_page(mapping, index);
+ page = grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
if (!page)
return ERR_PTR(-ENOMEM);
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(err);
+ }
+ f2fs_put_dnode(&dn);
+
+ if (dn.data_blkaddr == NULL_ADDR) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-ENOENT);
+ }
+
if (PageUptodate(page))
return page;
@@ -274,9 +285,10 @@ repeat:
*
* Also, caller should grab and release a mutex by calling mutex_lock_op() and
* mutex_unlock_op().
+ * Note that, npage is set only by make_empty_dir.
*/
-struct page *get_new_data_page(struct inode *inode, pgoff_t index,
- bool new_i_size)
+struct page *get_new_data_page(struct inode *inode,
+ struct page *npage, pgoff_t index, bool new_i_size)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
@@ -284,18 +296,20 @@ struct page *get_new_data_page(struct inode *inode, pgoff_t index,
struct dnode_of_data dn;
int err;
- set_new_dnode(&dn, inode, NULL, NULL, 0);
+ set_new_dnode(&dn, inode, npage, npage, 0);
err = get_dnode_of_data(&dn, index, ALLOC_NODE);
if (err)
return ERR_PTR(err);
if (dn.data_blkaddr == NULL_ADDR) {
if (reserve_new_block(&dn)) {
- f2fs_put_dnode(&dn);
+ if (!npage)
+ f2fs_put_dnode(&dn);
return ERR_PTR(-ENOSPC);
}
}
- f2fs_put_dnode(&dn);
+ if (!npage)
+ f2fs_put_dnode(&dn);
repeat:
page = grab_cache_page(mapping, index);
if (!page)
@@ -325,6 +339,8 @@ repeat:
if (new_i_size &&
i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
+ /* Only the directory inode sets new_i_size */
+ set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
mark_inode_dirty_sync(inode);
}
return page;
@@ -481,8 +497,9 @@ int do_write_data_page(struct page *page)
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
- if (old_blk_addr != NEW_ADDR && !is_cold_data(page) &&
- need_inplace_update(inode)) {
+ if (unlikely(old_blk_addr != NEW_ADDR &&
+ !is_cold_data(page) &&
+ need_inplace_update(inode))) {
rewrite_data_page(F2FS_SB(inode->i_sb), page,
old_blk_addr);
} else {
@@ -684,6 +701,27 @@ err:
return err;
}
+static int f2fs_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = page->mapping->host;
+
+ SetPageUptodate(page);
+ set_page_dirty(page);
+
+ if (pos + copied > i_size_read(inode)) {
+ i_size_write(inode, pos + copied);
+ mark_inode_dirty(inode);
+ update_inode_page(inode);
+ }
+
+ unlock_page(page);
+ page_cache_release(page);
+ return copied;
+}
+
static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset, unsigned long nr_segs)
{
@@ -741,7 +779,7 @@ const struct address_space_operations f2fs_dblock_aops = {
.writepage = f2fs_write_data_page,
.writepages = f2fs_write_data_pages,
.write_begin = f2fs_write_begin,
- .write_end = nobh_write_end,
+ .write_end = f2fs_write_end,
.set_page_dirty = f2fs_set_data_page_dirty,
.invalidatepage = f2fs_invalidate_data_page,
.releasepage = f2fs_release_data_page,
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 8d9943786c31..0d6c6aafb235 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -175,12 +175,12 @@ get_cache:
static int stat_show(struct seq_file *s, void *v)
{
- struct f2fs_stat_info *si, *next;
+ struct f2fs_stat_info *si;
int i = 0;
int j;
mutex_lock(&f2fs_stat_mutex);
- list_for_each_entry_safe(si, next, &f2fs_stat_list, stat_list) {
+ list_for_each_entry(si, &f2fs_stat_list, stat_list) {
char devname[BDEVNAME_SIZE];
update_general_status(si->sbi);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 600bb5efe603..9d1cd423450d 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -13,6 +13,7 @@
#include "f2fs.h"
#include "node.h"
#include "acl.h"
+#include "xattr.h"
static unsigned long dir_blocks(struct inode *inode)
{
@@ -215,9 +216,9 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
{
- struct page *page = NULL;
- struct f2fs_dir_entry *de = NULL;
- struct f2fs_dentry_block *dentry_blk = NULL;
+ struct page *page;
+ struct f2fs_dir_entry *de;
+ struct f2fs_dentry_block *dentry_blk;
page = get_lock_data_page(dir, 0);
if (IS_ERR(page))
@@ -264,15 +265,10 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
f2fs_put_page(page, 1);
}
-void init_dent_inode(const struct qstr *name, struct page *ipage)
+static void init_dent_inode(const struct qstr *name, struct page *ipage)
{
struct f2fs_node *rn;
- if (IS_ERR(ipage))
- return;
-
- wait_on_page_writeback(ipage);
-
/* copy name info. to this inode page */
rn = (struct f2fs_node *)page_address(ipage);
rn->i.i_namelen = cpu_to_le32(name->len);
@@ -280,14 +276,15 @@ void init_dent_inode(const struct qstr *name, struct page *ipage)
set_page_dirty(ipage);
}
-static int make_empty_dir(struct inode *inode, struct inode *parent)
+static int make_empty_dir(struct inode *inode,
+ struct inode *parent, struct page *page)
{
struct page *dentry_page;
struct f2fs_dentry_block *dentry_blk;
struct f2fs_dir_entry *de;
void *kaddr;
- dentry_page = get_new_data_page(inode, 0, true);
+ dentry_page = get_new_data_page(inode, page, 0, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
@@ -317,63 +314,76 @@ static int make_empty_dir(struct inode *inode, struct inode *parent)
return 0;
}
-static int init_inode_metadata(struct inode *inode,
+static struct page *init_inode_metadata(struct inode *inode,
struct inode *dir, const struct qstr *name)
{
+ struct page *page;
+ int err;
+
if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
- int err;
- err = new_inode_page(inode, name);
- if (err)
- return err;
+ page = new_inode_page(inode, name);
+ if (IS_ERR(page))
+ return page;
if (S_ISDIR(inode->i_mode)) {
- err = make_empty_dir(inode, dir);
- if (err) {
- remove_inode_page(inode);
- return err;
- }
+ err = make_empty_dir(inode, dir, page);
+ if (err)
+ goto error;
}
err = f2fs_init_acl(inode, dir);
- if (err) {
- remove_inode_page(inode);
- return err;
- }
+ if (err)
+ goto error;
+
+ err = f2fs_init_security(inode, dir, name, page);
+ if (err)
+ goto error;
+
+ wait_on_page_writeback(page);
} else {
- struct page *ipage;
- ipage = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
- if (IS_ERR(ipage))
- return PTR_ERR(ipage);
- set_cold_node(inode, ipage);
- init_dent_inode(name, ipage);
- f2fs_put_page(ipage, 1);
+ page = get_node_page(F2FS_SB(dir->i_sb), inode->i_ino);
+ if (IS_ERR(page))
+ return page;
+
+ wait_on_page_writeback(page);
+ set_cold_node(inode, page);
}
+
+ init_dent_inode(name, page);
+
+ /*
+ * This file should be checkpointed during fsync.
+ * We lost i_pino from now on.
+ */
if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
+ file_lost_pino(inode);
inc_nlink(inode);
- update_inode_page(inode);
}
- return 0;
+ return page;
+
+error:
+ f2fs_put_page(page, 1);
+ remove_inode_page(inode);
+ return ERR_PTR(err);
}
static void update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth)
{
- bool need_dir_update = false;
-
if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
if (S_ISDIR(inode->i_mode)) {
inc_nlink(dir);
- need_dir_update = true;
+ set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
}
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
if (F2FS_I(dir)->i_current_depth != current_depth) {
F2FS_I(dir)->i_current_depth = current_depth;
- need_dir_update = true;
+ set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
- if (need_dir_update)
+ if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR))
update_inode_page(dir);
else
mark_inode_dirty(dir);
@@ -423,6 +433,7 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, struct inode *in
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
int slots = GET_DENTRY_SLOTS(namelen);
+ struct page *page;
int err = 0;
int i;
@@ -448,7 +459,7 @@ start:
bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
for (block = bidx; block <= (bidx + nblock - 1); block++) {
- dentry_page = get_new_data_page(dir, block, true);
+ dentry_page = get_new_data_page(dir, NULL, block, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
@@ -465,12 +476,13 @@ start:
++level;
goto start;
add_dentry:
- err = init_inode_metadata(inode, dir, name);
- if (err)
- goto fail;
-
wait_on_page_writeback(dentry_page);
+ page = init_inode_metadata(inode, dir, name);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto fail;
+ }
de = &dentry_blk->dentry[bit_pos];
de->hash_code = dentry_hash;
de->name_len = cpu_to_le16(namelen);
@@ -481,11 +493,14 @@ add_dentry:
test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
set_page_dirty(dentry_page);
- update_parent_metadata(dir, inode, current_depth);
-
- /* update parent inode number before releasing dentry page */
+ /* we don't need to mark_inode_dirty now */
F2FS_I(inode)->i_pino = dir->i_ino;
+ update_inode(inode, page);
+ f2fs_put_page(page, 1);
+
+ update_parent_metadata(dir, inode, current_depth);
fail:
+ clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
return err;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 20aab02f2a42..467d42d65c48 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -37,21 +37,35 @@
typecheck(unsigned long long, b) && \
((long long)((a) - (b)) > 0))
-typedef u64 block_t;
+typedef u32 block_t; /*
+ * should not change u32, since it is the on-disk block
+ * address format, __le32.
+ */
typedef u32 nid_t;
struct f2fs_mount_info {
unsigned int opt;
};
-static inline __u32 f2fs_crc32(void *buff, size_t len)
+#define CRCPOLY_LE 0xedb88320
+
+static inline __u32 f2fs_crc32(void *buf, size_t len)
{
- return crc32_le(F2FS_SUPER_MAGIC, buff, len);
+ unsigned char *p = (unsigned char *)buf;
+ __u32 crc = F2FS_SUPER_MAGIC;
+ int i;
+
+ while (len--) {
+ crc ^= *p++;
+ for (i = 0; i < 8; i++)
+ crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+ }
+ return crc;
}
-static inline bool f2fs_crc_valid(__u32 blk_crc, void *buff, size_t buff_size)
+static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size)
{
- return f2fs_crc32(buff, buff_size) == blk_crc;
+ return f2fs_crc32(buf, buf_size) == blk_crc;
}
/*
@@ -148,7 +162,7 @@ struct extent_info {
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
*/
#define FADVISE_COLD_BIT 0x01
-#define FADVISE_CP_BIT 0x02
+#define FADVISE_LOST_PINO_BIT 0x02
struct f2fs_inode_info {
struct inode vfs_inode; /* serve a vfs inode */
@@ -369,7 +383,6 @@ struct f2fs_sb_info {
/* for directory inode management */
struct list_head dir_inode_list; /* dir inode list */
spinlock_t dir_inode_lock; /* for dir inode list lock */
- unsigned int n_dirty_dirs; /* # of dir inodes */
/* basic file system units */
unsigned int log_sectors_per_block; /* log2 sectors per block */
@@ -406,12 +419,15 @@ struct f2fs_sb_info {
* for stat information.
* one is for the LFS mode, and the other is for the SSR mode.
*/
+#ifdef CONFIG_F2FS_STAT_FS
struct f2fs_stat_info *stat_info; /* FS status information */
unsigned int segment_count[2]; /* # of allocated segments */
unsigned int block_count[2]; /* # of allocated blocks */
- unsigned int last_victim[2]; /* last victim segment # */
int total_hit_ext, read_hit_ext; /* extent cache hit ratio */
int bg_gc; /* background gc calls */
+ unsigned int n_dirty_dirs; /* # of dir inodes */
+#endif
+ unsigned int last_victim[2]; /* last victim segment # */
spinlock_t stat_lock; /* lock for stat operations */
};
@@ -495,9 +511,17 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
static inline void mutex_lock_all(struct f2fs_sb_info *sbi)
{
- int i = 0;
- for (; i < NR_GLOBAL_LOCKS; i++)
- mutex_lock(&sbi->fs_lock[i]);
+ int i;
+
+ for (i = 0; i < NR_GLOBAL_LOCKS; i++) {
+ /*
+ * This is the only time we take multiple fs_lock[]
+ * instances; the order is immaterial since we
+ * always hold cp_mutex, which serializes multiple
+ * such operations.
+ */
+ mutex_lock_nest_lock(&sbi->fs_lock[i], &sbi->cp_mutex);
+ }
}
static inline void mutex_unlock_all(struct f2fs_sb_info *sbi)
@@ -843,9 +867,12 @@ static inline int f2fs_clear_bit(unsigned int nr, char *addr)
/* used for f2fs_inode_info->flags */
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
+ FI_DIRTY_INODE, /* indicate inode is dirty or not */
FI_INC_LINK, /* need to increment i_nlink */
FI_ACL_MODE, /* indicate acl mode */
FI_NO_ALLOC, /* should not allocate any blocks */
+ FI_UPDATE_DIR, /* should update inode block for consistency */
+ FI_DELAY_IPUT, /* used for the recovery */
};
static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -878,14 +905,21 @@ static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
return 0;
}
+static inline int f2fs_readonly(struct super_block *sb)
+{
+ return sb->s_flags & MS_RDONLY;
+}
+
/*
* file.c
*/
int f2fs_sync_file(struct file *, loff_t, loff_t, int);
void truncate_data_blocks(struct dnode_of_data *);
void f2fs_truncate(struct inode *);
+int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
int f2fs_setattr(struct dentry *, struct iattr *);
int truncate_hole(struct inode *, pgoff_t, pgoff_t);
+int truncate_data_blocks_range(struct dnode_of_data *, int);
long f2fs_ioctl(struct file *, unsigned int, unsigned long);
long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
@@ -913,7 +947,6 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
struct page *, struct inode *);
-void init_dent_inode(const struct qstr *, struct page *);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *);
int f2fs_make_empty(struct inode *, struct inode *);
@@ -948,8 +981,8 @@ void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
int remove_inode_page(struct inode *);
-int new_inode_page(struct inode *, const struct qstr *);
-struct page *new_node_page(struct dnode_of_data *, unsigned int);
+struct page *new_inode_page(struct inode *, const struct qstr *);
+struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
void ra_node_page(struct f2fs_sb_info *, nid_t);
struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_node_page_ra(struct page *, int);
@@ -974,7 +1007,6 @@ void destroy_node_manager_caches(void);
*/
void f2fs_balance_fs(struct f2fs_sb_info *);
void invalidate_blocks(struct f2fs_sb_info *, block_t);
-void locate_dirty_segment(struct f2fs_sb_info *, unsigned int);
void clear_prefree_segments(struct f2fs_sb_info *);
int npages_for_summary_flush(struct f2fs_sb_info *);
void allocate_new_segments(struct f2fs_sb_info *);
@@ -1011,7 +1043,9 @@ void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
int recover_orphan_inodes(struct f2fs_sb_info *);
int get_valid_checkpoint(struct f2fs_sb_info *);
void set_dirty_dir_page(struct inode *, struct page *);
+void add_dirty_dir_inode(struct inode *);
void remove_dirty_dir_inode(struct inode *);
+struct inode *check_dirty_dir_inode(struct f2fs_sb_info *, nid_t);
void sync_dirty_dir_inodes(struct f2fs_sb_info *);
void write_checkpoint(struct f2fs_sb_info *, bool);
void init_orphan_info(struct f2fs_sb_info *);
@@ -1025,7 +1059,7 @@ int reserve_new_block(struct dnode_of_data *);
void update_extent_cache(block_t, struct dnode_of_data *);
struct page *find_data_page(struct inode *, pgoff_t, bool);
struct page *get_lock_data_page(struct inode *, pgoff_t);
-struct page *get_new_data_page(struct inode *, pgoff_t, bool);
+struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
int f2fs_readpage(struct f2fs_sb_info *, struct page *, block_t, int);
int do_write_data_page(struct page *);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 1cae864f8dfc..d2d2b7dbdcc1 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -63,9 +63,10 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
f2fs_put_dnode(&dn);
mutex_unlock_op(sbi, ilock);
+ file_update_time(vma->vm_file);
lock_page(page);
if (page->mapping != inode->i_mapping ||
- page_offset(page) >= i_size_read(inode) ||
+ page_offset(page) > i_size_read(inode) ||
!PageUptodate(page)) {
unlock_page(page);
err = -EFAULT;
@@ -76,10 +77,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
- goto out;
-
- /* fill the page */
- wait_on_page_writeback(page);
+ goto mapped;
/* page is wholly or partially inside EOF */
if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
@@ -90,7 +88,9 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
set_page_dirty(page);
SetPageUptodate(page);
- file_update_time(vma->vm_file);
+mapped:
+ /* fill the page */
+ wait_on_page_writeback(page);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(err);
@@ -102,6 +102,24 @@ static const struct vm_operations_struct f2fs_file_vm_ops = {
.remap_pages = generic_file_remap_pages,
};
+static int get_parent_ino(struct inode *inode, nid_t *pino)
+{
+ struct dentry *dentry;
+
+ inode = igrab(inode);
+ dentry = d_find_any_alias(inode);
+ iput(inode);
+ if (!dentry)
+ return 0;
+
+ inode = igrab(dentry->d_parent->d_inode);
+ dput(dentry);
+
+ *pino = inode->i_ino;
+ iput(inode);
+ return 1;
+}
+
int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
@@ -114,7 +132,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
.for_reclaim = 0,
};
- if (inode->i_sb->s_flags & MS_RDONLY)
+ if (f2fs_readonly(inode->i_sb))
return 0;
trace_f2fs_sync_file_enter(inode);
@@ -134,7 +152,7 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
need_cp = true;
- else if (is_cp_file(inode))
+ else if (file_wrong_pino(inode))
need_cp = true;
else if (!space_for_roll_forward(sbi))
need_cp = true;
@@ -142,11 +160,23 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
need_cp = true;
if (need_cp) {
+ nid_t pino;
+
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
+ if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
+ get_parent_ino(inode, &pino)) {
+ F2FS_I(inode)->i_pino = pino;
+ file_got_pino(inode);
+ mark_inode_dirty_sync(inode);
+ ret = f2fs_write_inode(inode, NULL);
+ if (ret)
+ goto out;
+ }
} else {
/* if there is no written node page, write its inode page */
while (!sync_node_pages(sbi, inode->i_ino, &wbc)) {
+ mark_inode_dirty_sync(inode);
ret = f2fs_write_inode(inode, NULL);
if (ret)
goto out;
@@ -168,7 +198,7 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
return 0;
}
-static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
+int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
int nr_free = 0, ofs = dn->ofs_in_node;
struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
@@ -185,10 +215,10 @@ static int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
update_extent_cache(NULL_ADDR, dn);
invalidate_blocks(sbi, blkaddr);
- dec_valid_block_count(sbi, dn->inode, 1);
nr_free++;
}
if (nr_free) {
+ dec_valid_block_count(sbi, dn->inode, nr_free);
set_page_dirty(dn->node_page);
sync_inode_page(dn);
}
@@ -291,7 +321,7 @@ void f2fs_truncate(struct inode *inode)
}
}
-static int f2fs_getattr(struct vfsmount *mnt,
+int f2fs_getattr(struct vfsmount *mnt,
struct dentry *dentry, struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
@@ -387,7 +417,7 @@ static void fill_zero(struct inode *inode, pgoff_t index,
f2fs_balance_fs(sbi);
ilock = mutex_lock_op(sbi);
- page = get_new_data_page(inode, index, false);
+ page = get_new_data_page(inode, NULL, index, false);
mutex_unlock_op(sbi, ilock);
if (!IS_ERR(page)) {
@@ -575,10 +605,10 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
int ret;
switch (cmd) {
- case FS_IOC_GETFLAGS:
+ case F2FS_IOC_GETFLAGS:
flags = fi->i_flags & FS_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
- case FS_IOC_SETFLAGS:
+ case F2FS_IOC_SETFLAGS:
{
unsigned int oldflags;
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 14961593e93c..35f9b1a196aa 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -76,7 +76,9 @@ static int gc_thread_func(void *data)
else
wait_ms = increase_sleep_time(wait_ms);
+#ifdef CONFIG_F2FS_STAT_FS
sbi->bg_gc++;
+#endif
/* if return value is not zero, no victim was selected */
if (f2fs_gc(sbi))
@@ -89,23 +91,28 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
{
struct f2fs_gc_kthread *gc_th;
dev_t dev = sbi->sb->s_bdev->bd_dev;
+ int err = 0;
if (!test_opt(sbi, BG_GC))
- return 0;
+ goto out;
gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
- if (!gc_th)
- return -ENOMEM;
+ if (!gc_th) {
+ err = -ENOMEM;
+ goto out;
+ }
sbi->gc_thread = gc_th;
init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
"f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(gc_th->f2fs_gc_task)) {
+ err = PTR_ERR(gc_th->f2fs_gc_task);
kfree(gc_th);
sbi->gc_thread = NULL;
- return -ENOMEM;
}
- return 0;
+
+out:
+ return err;
}
void stop_gc_thread(struct f2fs_sb_info *sbi)
@@ -234,14 +241,14 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct victim_sel_policy p;
- unsigned int secno;
+ unsigned int secno, max_cost;
int nsearched = 0;
p.alloc_mode = alloc_mode;
select_policy(sbi, gc_type, type, &p);
p.min_segno = NULL_SEGNO;
- p.min_cost = get_max_cost(sbi, &p);
+ p.min_cost = max_cost = get_max_cost(sbi, &p);
mutex_lock(&dirty_i->seglist_lock);
@@ -280,7 +287,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
p.min_cost = cost;
}
- if (cost == get_max_cost(sbi, &p))
+ if (cost == max_cost)
continue;
if (nsearched++ >= MAX_VICTIM_SEARCH) {
@@ -288,8 +295,8 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
break;
}
}
-got_it:
if (p.min_segno != NULL_SEGNO) {
+got_it:
if (p.alloc_mode == LFS) {
secno = GET_SECNO(sbi, p.min_segno);
if (gc_type == FG_GC)
@@ -314,28 +321,21 @@ static const struct victim_selection default_v_ops = {
static struct inode *find_gc_inode(nid_t ino, struct list_head *ilist)
{
- struct list_head *this;
struct inode_entry *ie;
- list_for_each(this, ilist) {
- ie = list_entry(this, struct inode_entry, list);
+ list_for_each_entry(ie, ilist, list)
if (ie->inode->i_ino == ino)
return ie->inode;
- }
return NULL;
}
static void add_gc_inode(struct inode *inode, struct list_head *ilist)
{
- struct list_head *this;
- struct inode_entry *new_ie, *ie;
+ struct inode_entry *new_ie;
- list_for_each(this, ilist) {
- ie = list_entry(this, struct inode_entry, list);
- if (ie->inode == inode) {
- iput(inode);
- return;
- }
+ if (inode == find_gc_inode(inode->i_ino, ilist)) {
+ iput(inode);
+ return;
}
repeat:
new_ie = kmem_cache_alloc(winode_slab, GFP_NOFS);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 91ac7f9d88ee..2b2d45d19e3e 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -109,12 +109,6 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
ret = do_read_inode(inode);
if (ret)
goto bad_inode;
-
- if (!sbi->por_doing && inode->i_nlink == 0) {
- ret = -ENOENT;
- goto bad_inode;
- }
-
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
@@ -130,8 +124,7 @@ make_now:
inode->i_op = &f2fs_dir_inode_operations;
inode->i_fop = &f2fs_dir_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
- mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER_MOVABLE |
- __GFP_ZERO);
+ mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
@@ -199,6 +192,7 @@ void update_inode(struct inode *inode, struct page *node_page)
set_cold_node(inode, node_page);
set_page_dirty(node_page);
+ clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
}
int update_inode_page(struct inode *inode)
@@ -224,6 +218,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
inode->i_ino == F2FS_META_INO(sbi))
return 0;
+ if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
+ return 0;
+
if (wbc)
f2fs_balance_fs(sbi);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 47abc9722b17..64c07169df05 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -112,7 +112,7 @@ static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode,
int count = le32_to_cpu(sbi->raw_super->extension_count);
for (i = 0; i < count; i++) {
if (is_multimedia_file(name, extlist[i])) {
- set_cold_file(inode);
+ file_set_cold(inode);
break;
}
}
@@ -149,8 +149,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
alloc_nid_done(sbi, ino);
- if (!sbi->por_doing)
- d_instantiate(dentry, inode);
+ d_instantiate(dentry, inode);
unlock_new_inode(inode);
return 0;
out:
@@ -173,7 +172,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
f2fs_balance_fs(sbi);
inode->i_ctime = CURRENT_TIME;
- atomic_inc(&inode->i_count);
+ ihold(inode);
set_inode_flag(F2FS_I(inode), FI_INC_LINK);
ilock = mutex_lock_op(sbi);
@@ -182,17 +181,10 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
if (err)
goto out;
- /*
- * This file should be checkpointed during fsync.
- * We lost i_pino from now on.
- */
- set_cp_file(inode);
-
d_instantiate(dentry, inode);
return 0;
out:
clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
- make_bad_inode(inode);
iput(inode);
return err;
}
@@ -498,6 +490,7 @@ const struct inode_operations f2fs_dir_inode_operations = {
.rmdir = f2fs_rmdir,
.mknod = f2fs_mknod,
.rename = f2fs_rename,
+ .getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
@@ -512,6 +505,7 @@ const struct inode_operations f2fs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.put_link = page_put_link,
+ .getattr = f2fs_getattr,
.setattr = f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
.setxattr = generic_setxattr,
@@ -522,6 +516,7 @@ const struct inode_operations f2fs_symlink_inode_operations = {
};
const struct inode_operations f2fs_special_inode_operations = {
+ .getattr = f2fs_getattr,
.setattr = f2fs_setattr,
.get_acl = f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 74f3c7b03eb2..b418aee09573 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -408,10 +408,13 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
level = get_node_path(index, offset, noffset);
nids[0] = dn->inode->i_ino;
- npage[0] = get_node_page(sbi, nids[0]);
- if (IS_ERR(npage[0]))
- return PTR_ERR(npage[0]);
+ npage[0] = dn->inode_page;
+ if (!npage[0]) {
+ npage[0] = get_node_page(sbi, nids[0]);
+ if (IS_ERR(npage[0]))
+ return PTR_ERR(npage[0]);
+ }
parent = npage[0];
if (level != 0)
nids[1] = get_nid(parent, offset[0], true);
@@ -430,7 +433,7 @@ 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]);
+ npage[i] = new_node_page(dn, noffset[i], NULL);
if (IS_ERR(npage[i])) {
alloc_nid_failed(sbi, nids[i]);
err = PTR_ERR(npage[i]);
@@ -803,22 +806,19 @@ int remove_inode_page(struct inode *inode)
return 0;
}
-int new_inode_page(struct inode *inode, const struct qstr *name)
+struct page *new_inode_page(struct inode *inode, const struct qstr *name)
{
- struct page *page;
struct dnode_of_data dn;
/* allocate inode page for new inode */
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
- page = new_node_page(&dn, 0);
- init_dent_inode(name, page);
- if (IS_ERR(page))
- return PTR_ERR(page);
- f2fs_put_page(page, 1);
- return 0;
+
+ /* caller should f2fs_put_page(page, 1); */
+ return new_node_page(&dn, 0, NULL);
}
-struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs)
+struct page *new_node_page(struct dnode_of_data *dn,
+ unsigned int ofs, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
struct address_space *mapping = sbi->node_inode->i_mapping;
@@ -851,7 +851,10 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs)
set_cold_node(dn->inode, page);
dn->node_page = page;
- sync_inode_page(dn);
+ if (ipage)
+ update_inode(dn->inode, ipage);
+ else
+ sync_inode_page(dn);
set_page_dirty(page);
if (ofs == 0)
inc_valid_inode_count(sbi);
@@ -1493,9 +1496,10 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
new_ni = old_ni;
new_ni.ino = ino;
+ if (!inc_valid_node_count(sbi, NULL, 1))
+ WARN_ON(1);
set_node_addr(sbi, &new_ni, NEW_ADDR);
inc_valid_inode_count(sbi);
-
f2fs_put_page(ipage, 1);
return 0;
}
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 0a2d72f0024d..c65fb4f4230f 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -275,25 +275,27 @@ static inline nid_t get_nid(struct page *p, int off, bool i)
* - Mark cold node blocks in their node footer
* - Mark cold data pages in page cache
*/
-static inline int is_cold_file(struct inode *inode)
+static inline int is_file(struct inode *inode, int type)
{
- return F2FS_I(inode)->i_advise & FADVISE_COLD_BIT;
+ return F2FS_I(inode)->i_advise & type;
}
-static inline void set_cold_file(struct inode *inode)
+static inline void set_file(struct inode *inode, int type)
{
- F2FS_I(inode)->i_advise |= FADVISE_COLD_BIT;
+ F2FS_I(inode)->i_advise |= type;
}
-static inline int is_cp_file(struct inode *inode)
+static inline void clear_file(struct inode *inode, int type)
{
- return F2FS_I(inode)->i_advise & FADVISE_CP_BIT;
+ F2FS_I(inode)->i_advise &= ~type;
}
-static inline void set_cp_file(struct inode *inode)
-{
- F2FS_I(inode)->i_advise |= FADVISE_CP_BIT;
-}
+#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
+#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
+#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT)
+#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT)
+#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT)
+#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT)
static inline int is_cold_data(struct page *page)
{
@@ -310,29 +312,16 @@ static inline void clear_cold_data(struct page *page)
ClearPageChecked(page);
}
-static inline int is_cold_node(struct page *page)
+static inline int is_node(struct page *page, int type)
{
void *kaddr = page_address(page);
struct f2fs_node *rn = (struct f2fs_node *)kaddr;
- unsigned int flag = le32_to_cpu(rn->footer.flag);
- return flag & (0x1 << COLD_BIT_SHIFT);
+ return le32_to_cpu(rn->footer.flag) & (1 << type);
}
-static inline unsigned char is_fsync_dnode(struct page *page)
-{
- void *kaddr = page_address(page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
- unsigned int flag = le32_to_cpu(rn->footer.flag);
- return flag & (0x1 << FSYNC_BIT_SHIFT);
-}
-
-static inline unsigned char is_dent_dnode(struct page *page)
-{
- void *kaddr = page_address(page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
- unsigned int flag = le32_to_cpu(rn->footer.flag);
- return flag & (0x1 << DENT_BIT_SHIFT);
-}
+#define is_cold_node(page) is_node(page, COLD_BIT_SHIFT)
+#define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT)
+#define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT)
static inline void set_cold_node(struct inode *inode, struct page *page)
{
@@ -346,26 +335,15 @@ static inline void set_cold_node(struct inode *inode, struct page *page)
rn->footer.flag = cpu_to_le32(flag);
}
-static inline void set_fsync_mark(struct page *page, int mark)
+static inline void set_mark(struct page *page, int mark, int type)
{
- void *kaddr = page_address(page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = (struct f2fs_node *)page_address(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
if (mark)
- flag |= (0x1 << FSYNC_BIT_SHIFT);
+ flag |= (0x1 << type);
else
- flag &= ~(0x1 << FSYNC_BIT_SHIFT);
- rn->footer.flag = cpu_to_le32(flag);
-}
-
-static inline void set_dentry_mark(struct page *page, int mark)
-{
- void *kaddr = page_address(page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
- unsigned int flag = le32_to_cpu(rn->footer.flag);
- if (mark)
- flag |= (0x1 << DENT_BIT_SHIFT);
- else
- flag &= ~(0x1 << DENT_BIT_SHIFT);
+ flag &= ~(0x1 << type);
rn->footer.flag = cpu_to_le32(flag);
}
+#define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT)
+#define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 60c8a5097058..d56d951c2253 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -40,36 +40,54 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
static int recover_dentry(struct page *ipage, struct inode *inode)
{
- struct f2fs_node *raw_node = (struct f2fs_node *)kmap(ipage);
+ void *kaddr = page_address(ipage);
+ struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
struct f2fs_inode *raw_inode = &(raw_node->i);
- struct qstr name;
+ nid_t pino = le32_to_cpu(raw_inode->i_pino);
struct f2fs_dir_entry *de;
+ struct qstr name;
struct page *page;
- struct inode *dir;
+ struct inode *dir, *einode;
int err = 0;
- if (!is_dent_dnode(ipage))
- goto out;
-
- dir = f2fs_iget(inode->i_sb, le32_to_cpu(raw_inode->i_pino));
- if (IS_ERR(dir)) {
- err = PTR_ERR(dir);
- goto out;
+ dir = check_dirty_dir_inode(F2FS_SB(inode->i_sb), pino);
+ if (!dir) {
+ dir = f2fs_iget(inode->i_sb, pino);
+ if (IS_ERR(dir)) {
+ err = PTR_ERR(dir);
+ goto out;
+ }
+ set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
+ add_dirty_dir_inode(dir);
}
name.len = le32_to_cpu(raw_inode->i_namelen);
name.name = raw_inode->i_name;
-
+retry:
de = f2fs_find_entry(dir, &name, &page);
- if (de) {
+ if (de && inode->i_ino == le32_to_cpu(de->ino)) {
kunmap(page);
f2fs_put_page(page, 0);
- } else {
- err = __f2fs_add_link(dir, &name, inode);
+ goto out;
}
- iput(dir);
+ if (de) {
+ einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino));
+ if (IS_ERR(einode)) {
+ WARN_ON(1);
+ if (PTR_ERR(einode) == -ENOENT)
+ err = -EEXIST;
+ goto out;
+ }
+ f2fs_delete_entry(de, page, einode);
+ iput(einode);
+ goto retry;
+ }
+ err = __f2fs_add_link(dir, &name, inode);
out:
- kunmap(ipage);
+ f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode and its dentry: "
+ "ino = %x, name = %s, dir = %lx, err = %d",
+ ino_of_node(ipage), raw_inode->i_name,
+ IS_ERR(dir) ? 0 : dir->i_ino, err);
return err;
}
@@ -79,6 +97,9 @@ static int recover_inode(struct inode *inode, struct page *node_page)
struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
struct f2fs_inode *raw_inode = &(raw_node->i);
+ if (!IS_INODE(node_page))
+ return 0;
+
inode->i_mode = le16_to_cpu(raw_inode->i_mode);
i_size_write(inode, le64_to_cpu(raw_inode->i_size));
inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
@@ -88,7 +109,12 @@ static int recover_inode(struct inode *inode, struct page *node_page)
inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
- return recover_dentry(node_page, inode);
+ if (is_dent_dnode(node_page))
+ return recover_dentry(node_page, inode);
+
+ f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
+ ino_of_node(node_page), raw_inode->i_name);
+ return 0;
}
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
@@ -119,14 +145,13 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
lock_page(page);
if (cp_ver != cpver_of_node(page))
- goto unlock_out;
+ break;
if (!is_fsync_dnode(page))
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
if (entry) {
- entry->blkaddr = blkaddr;
if (IS_INODE(page) && is_dent_dnode(page))
set_inode_flag(F2FS_I(entry->inode),
FI_INC_LINK);
@@ -134,48 +159,40 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
if (IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
if (err)
- goto unlock_out;
+ break;
}
/* add this fsync inode to the list */
entry = kmem_cache_alloc(fsync_entry_slab, GFP_NOFS);
if (!entry) {
err = -ENOMEM;
- goto unlock_out;
+ break;
}
entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
if (IS_ERR(entry->inode)) {
err = PTR_ERR(entry->inode);
kmem_cache_free(fsync_entry_slab, entry);
- goto unlock_out;
+ break;
}
-
list_add_tail(&entry->list, head);
- entry->blkaddr = blkaddr;
- }
- if (IS_INODE(page)) {
- err = recover_inode(entry->inode, page);
- if (err == -ENOENT) {
- goto next;
- } else if (err) {
- err = -EINVAL;
- goto unlock_out;
- }
}
+ entry->blkaddr = blkaddr;
+
+ err = recover_inode(entry->inode, page);
+ if (err && err != -ENOENT)
+ break;
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
}
-unlock_out:
unlock_page(page);
out:
__free_pages(page, 0);
return err;
}
-static void destroy_fsync_dnodes(struct f2fs_sb_info *sbi,
- struct list_head *head)
+static void destroy_fsync_dnodes(struct list_head *head)
{
struct fsync_inode_entry *entry, *tmp;
@@ -186,15 +203,15 @@ static void destroy_fsync_dnodes(struct f2fs_sb_info *sbi,
}
}
-static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
- block_t blkaddr)
+static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
+ block_t blkaddr, struct dnode_of_data *dn)
{
struct seg_entry *sentry;
unsigned int segno = GET_SEGNO(sbi, blkaddr);
unsigned short blkoff = GET_SEGOFF_FROM_SEG0(sbi, blkaddr) &
(sbi->blocks_per_seg - 1);
struct f2fs_summary sum;
- nid_t ino;
+ nid_t ino, nid;
void *kaddr;
struct inode *inode;
struct page *node_page;
@@ -203,7 +220,7 @@ static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
sentry = get_seg_entry(sbi, segno);
if (!f2fs_test_bit(blkoff, sentry->cur_valid_map))
- return;
+ return 0;
/* Get the previous summary */
for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) {
@@ -222,20 +239,39 @@ static void check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
f2fs_put_page(sum_page, 1);
}
+ /* Use the locked dnode page and inode */
+ nid = le32_to_cpu(sum.nid);
+ if (dn->inode->i_ino == nid) {
+ struct dnode_of_data tdn = *dn;
+ tdn.nid = nid;
+ tdn.node_page = dn->inode_page;
+ tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
+ truncate_data_blocks_range(&tdn, 1);
+ return 0;
+ } else if (dn->nid == nid) {
+ struct dnode_of_data tdn = *dn;
+ tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
+ truncate_data_blocks_range(&tdn, 1);
+ return 0;
+ }
+
/* Get the node page */
- node_page = get_node_page(sbi, le32_to_cpu(sum.nid));
+ node_page = get_node_page(sbi, nid);
+ if (IS_ERR(node_page))
+ return PTR_ERR(node_page);
bidx = start_bidx_of_node(ofs_of_node(node_page)) +
- le16_to_cpu(sum.ofs_in_node);
+ le16_to_cpu(sum.ofs_in_node);
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
/* Deallocate previous index in the node page */
inode = f2fs_iget(sbi->sb, ino);
if (IS_ERR(inode))
- return;
+ return PTR_ERR(inode);
truncate_hole(inode, bidx, bidx + 1);
iput(inode);
+ return 0;
}
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
@@ -245,7 +281,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct dnode_of_data dn;
struct f2fs_summary sum;
struct node_info ni;
- int err = 0;
+ int err = 0, recovered = 0;
int ilock;
start = start_bidx_of_node(ofs_of_node(page));
@@ -283,13 +319,16 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
}
/* Check the previous node page having this index */
- check_index_in_prev_nodes(sbi, dest);
+ err = check_index_in_prev_nodes(sbi, dest, &dn);
+ if (err)
+ goto err;
set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
/* write dummy data page */
recover_data_page(sbi, NULL, &sum, src, dest);
update_extent_cache(dest, &dn);
+ recovered++;
}
dn.ofs_in_node++;
}
@@ -305,9 +344,14 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
set_page_dirty(dn.node_page);
recover_node_page(sbi, dn.node_page, &sum, &ni, blkaddr);
+err:
f2fs_put_dnode(&dn);
mutex_unlock_op(sbi, ilock);
- return 0;
+
+ f2fs_msg(sbi->sb, KERN_NOTICE, "recover_data: ino = %lx, "
+ "recovered_data = %d blocks, err = %d",
+ inode->i_ino, recovered, err);
+ return err;
}
static int recover_data(struct f2fs_sb_info *sbi,
@@ -340,7 +384,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
lock_page(page);
if (cp_ver != cpver_of_node(page))
- goto unlock_out;
+ break;
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry)
@@ -348,7 +392,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
err = do_recover_data(sbi, entry->inode, page, blkaddr);
if (err)
- goto out;
+ break;
if (entry->blkaddr == blkaddr) {
iput(entry->inode);
@@ -359,7 +403,6 @@ next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
}
-unlock_out:
unlock_page(page);
out:
__free_pages(page, 0);
@@ -382,6 +425,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
INIT_LIST_HEAD(&inode_list);
/* step #1: find fsynced inode numbers */
+ sbi->por_doing = 1;
err = find_fsync_dnodes(sbi, &inode_list);
if (err)
goto out;
@@ -390,13 +434,13 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
goto out;
/* step #2: recover data */
- sbi->por_doing = 1;
err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
- sbi->por_doing = 0;
BUG_ON(!list_empty(&inode_list));
out:
- destroy_fsync_dnodes(sbi, &inode_list);
+ destroy_fsync_dnodes(&inode_list);
kmem_cache_destroy(fsync_entry_slab);
- write_checkpoint(sbi, false);
+ sbi->por_doing = 0;
+ if (!err)
+ write_checkpoint(sbi, false);
return err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index d8e84e49a5c3..a86d125a9885 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -94,7 +94,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
* Adding dirty entry into seglist is not critical operation.
* If a given segment is one of current working segments, it won't be added.
*/
-void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
+static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned short valid_blocks;
@@ -126,17 +126,16 @@ void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int segno, offset = 0;
+ unsigned int segno = -1;
unsigned int total_segs = TOTAL_SEGS(sbi);
mutex_lock(&dirty_i->seglist_lock);
while (1) {
segno = find_next_bit(dirty_i->dirty_segmap[PRE], total_segs,
- offset);
+ segno + 1);
if (segno >= total_segs)
break;
__set_test_and_free(sbi, segno);
- offset = segno + 1;
}
mutex_unlock(&dirty_i->seglist_lock);
}
@@ -144,17 +143,16 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
void clear_prefree_segments(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned int segno, offset = 0;
+ unsigned int segno = -1;
unsigned int total_segs = TOTAL_SEGS(sbi);
mutex_lock(&dirty_i->seglist_lock);
while (1) {
segno = find_next_bit(dirty_i->dirty_segmap[PRE], total_segs,
- offset);
+ segno + 1);
if (segno >= total_segs)
break;
- offset = segno + 1;
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[PRE]))
dirty_i->nr_dirty[PRE]--;
@@ -257,11 +255,11 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr)
* This function should be resided under the curseg_mutex lock
*/
static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
- struct f2fs_summary *sum, unsigned short offset)
+ struct f2fs_summary *sum)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
void *addr = curseg->sum_blk;
- addr += offset * sizeof(struct f2fs_summary);
+ addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
memcpy(addr, sum, sizeof(struct f2fs_summary));
return;
}
@@ -311,64 +309,14 @@ static void write_sum_page(struct f2fs_sb_info *sbi,
f2fs_put_page(page, 1);
}
-static unsigned int check_prefree_segments(struct f2fs_sb_info *sbi, int type)
-{
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- unsigned long *prefree_segmap = dirty_i->dirty_segmap[PRE];
- unsigned int segno;
- unsigned int ofs = 0;
-
- /*
- * If there is not enough reserved sections,
- * we should not reuse prefree segments.
- */
- if (has_not_enough_free_secs(sbi, 0))
- return NULL_SEGNO;
-
- /*
- * NODE page should not reuse prefree segment,
- * since those information is used for SPOR.
- */
- if (IS_NODESEG(type))
- return NULL_SEGNO;
-next:
- segno = find_next_bit(prefree_segmap, TOTAL_SEGS(sbi), ofs);
- ofs += sbi->segs_per_sec;
-
- if (segno < TOTAL_SEGS(sbi)) {
- int i;
-
- /* skip intermediate segments in a section */
- if (segno % sbi->segs_per_sec)
- goto next;
-
- /* skip if the section is currently used */
- if (sec_usage_check(sbi, GET_SECNO(sbi, segno)))
- goto next;
-
- /* skip if whole section is not prefree */
- for (i = 1; i < sbi->segs_per_sec; i++)
- if (!test_bit(segno + i, prefree_segmap))
- goto next;
-
- /* skip if whole section was not free at the last checkpoint */
- for (i = 0; i < sbi->segs_per_sec; i++)
- if (get_seg_entry(sbi, segno + i)->ckpt_valid_blocks)
- goto next;
-
- return segno;
- }
- return NULL_SEGNO;
-}
-
static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
- unsigned int segno = curseg->segno;
+ unsigned int segno = curseg->segno + 1;
struct free_segmap_info *free_i = FREE_I(sbi);
- if (segno + 1 < TOTAL_SEGS(sbi) && (segno + 1) % sbi->segs_per_sec)
- return !test_bit(segno + 1, free_i->free_segmap);
+ if (segno < TOTAL_SEGS(sbi) && segno % sbi->segs_per_sec)
+ return !test_bit(segno, free_i->free_segmap);
return 0;
}
@@ -495,7 +443,7 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
int dir = ALLOC_LEFT;
write_sum_page(sbi, curseg->sum_blk,
- GET_SUM_BLOCK(sbi, curseg->segno));
+ GET_SUM_BLOCK(sbi, segno));
if (type == CURSEG_WARM_DATA || type == CURSEG_COLD_DATA)
dir = ALLOC_RIGHT;
@@ -599,11 +547,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
goto out;
}
- curseg->next_segno = check_prefree_segments(sbi, type);
-
- if (curseg->next_segno != NULL_SEGNO)
- change_curseg(sbi, type, false);
- else if (type == CURSEG_WARM_NODE)
+ if (type == CURSEG_WARM_NODE)
new_curseg(sbi, type, false);
else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
new_curseg(sbi, type, false);
@@ -612,7 +556,10 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
else
new_curseg(sbi, type, false);
out:
+#ifdef CONFIG_F2FS_STAT_FS
sbi->segment_count[curseg->alloc_type]++;
+#endif
+ return;
}
void allocate_new_segments(struct f2fs_sb_info *sbi)
@@ -795,7 +742,7 @@ static int __get_segment_type_6(struct page *page, enum page_type p_type)
if (S_ISDIR(inode->i_mode))
return CURSEG_HOT_DATA;
- else if (is_cold_data(page) || is_cold_file(inode))
+ else if (is_cold_data(page) || file_is_cold(inode))
return CURSEG_COLD_DATA;
else
return CURSEG_WARM_DATA;
@@ -844,11 +791,13 @@ static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
* because, this function updates a summary entry in the
* current summary block.
*/
- __add_sum_entry(sbi, type, sum, curseg->next_blkoff);
+ __add_sum_entry(sbi, type, sum);
mutex_lock(&sit_i->sentry_lock);
__refresh_next_blkoff(sbi, curseg);
+#ifdef CONFIG_F2FS_STAT_FS
sbi->block_count[curseg->alloc_type]++;
+#endif
/*
* SIT information should be updated before segment allocation,
@@ -943,7 +892,7 @@ void recover_data_page(struct f2fs_sb_info *sbi,
curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, new_blkaddr) &
(sbi->blocks_per_seg - 1);
- __add_sum_entry(sbi, type, sum, curseg->next_blkoff);
+ __add_sum_entry(sbi, type, sum);
refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
@@ -980,7 +929,7 @@ void rewrite_node_page(struct f2fs_sb_info *sbi,
}
curseg->next_blkoff = GET_SEGOFF_FROM_SEG0(sbi, new_blkaddr) &
(sbi->blocks_per_seg - 1);
- __add_sum_entry(sbi, type, sum, curseg->next_blkoff);
+ __add_sum_entry(sbi, type, sum);
/* change the current log to the next block addr in advance */
if (next_segno != segno) {
@@ -1579,13 +1528,13 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int segno = 0, offset = 0;
+ unsigned int segno = 0, offset = 0, total_segs = TOTAL_SEGS(sbi);
unsigned short valid_blocks;
- while (segno < TOTAL_SEGS(sbi)) {
+ while (1) {
/* find dirty segment based on free segmap */
- segno = find_next_inuse(free_i, TOTAL_SEGS(sbi), offset);
- if (segno >= TOTAL_SEGS(sbi))
+ segno = find_next_inuse(free_i, total_segs, offset);
+ if (segno >= total_segs)
break;
offset = segno + 1;
valid_blocks = get_valid_blocks(sbi, segno, 0);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8555f7df82c7..75c7dc363e92 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -34,7 +34,7 @@
static struct kmem_cache *f2fs_inode_cachep;
enum {
- Opt_gc_background_off,
+ Opt_gc_background,
Opt_disable_roll_forward,
Opt_discard,
Opt_noheap,
@@ -46,7 +46,7 @@ enum {
};
static match_table_t f2fs_tokens = {
- {Opt_gc_background_off, "background_gc_off"},
+ {Opt_gc_background, "background_gc=%s"},
{Opt_disable_roll_forward, "disable_roll_forward"},
{Opt_discard, "discard"},
{Opt_noheap, "no_heap"},
@@ -76,6 +76,91 @@ static void init_once(void *foo)
inode_init_once(&fi->vfs_inode);
}
+static int parse_options(struct super_block *sb, char *options)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ substring_t args[MAX_OPT_ARGS];
+ char *p, *name;
+ int arg = 0;
+
+ if (!options)
+ return 0;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ int token;
+ if (!*p)
+ continue;
+ /*
+ * Initialize args struct so we know whether arg was
+ * found; some options take optional arguments.
+ */
+ args[0].to = args[0].from = NULL;
+ token = match_token(p, f2fs_tokens, args);
+
+ switch (token) {
+ case Opt_gc_background:
+ name = match_strdup(&args[0]);
+
+ if (!name)
+ return -ENOMEM;
+ if (!strncmp(name, "on", 2))
+ set_opt(sbi, BG_GC);
+ else if (!strncmp(name, "off", 3))
+ clear_opt(sbi, BG_GC);
+ else {
+ kfree(name);
+ return -EINVAL;
+ }
+ kfree(name);
+ break;
+ case Opt_disable_roll_forward:
+ set_opt(sbi, DISABLE_ROLL_FORWARD);
+ break;
+ case Opt_discard:
+ set_opt(sbi, DISCARD);
+ break;
+ case Opt_noheap:
+ set_opt(sbi, NOHEAP);
+ break;
+#ifdef CONFIG_F2FS_FS_XATTR
+ case Opt_nouser_xattr:
+ clear_opt(sbi, XATTR_USER);
+ break;
+#else
+ case Opt_nouser_xattr:
+ f2fs_msg(sb, KERN_INFO,
+ "nouser_xattr options not supported");
+ break;
+#endif
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+ case Opt_noacl:
+ clear_opt(sbi, POSIX_ACL);
+ break;
+#else
+ case Opt_noacl:
+ f2fs_msg(sb, KERN_INFO, "noacl options not supported");
+ break;
+#endif
+ case Opt_active_logs:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE)
+ return -EINVAL;
+ sbi->active_logs = arg;
+ break;
+ case Opt_disable_ext_identify:
+ set_opt(sbi, DISABLE_EXT_IDENTIFY);
+ break;
+ default:
+ f2fs_msg(sb, KERN_ERR,
+ "Unrecognized mount option \"%s\" or missing value",
+ p);
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
static struct inode *f2fs_alloc_inode(struct super_block *sb)
{
struct f2fs_inode_info *fi;
@@ -112,6 +197,17 @@ static int f2fs_drop_inode(struct inode *inode)
return generic_drop_inode(inode);
}
+/*
+ * f2fs_dirty_inode() is called from __mark_inode_dirty()
+ *
+ * We should call set_dirty_inode to write the dirty inode through write_inode.
+ */
+static void f2fs_dirty_inode(struct inode *inode, int flags)
+{
+ set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
+ return;
+}
+
static void f2fs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
@@ -170,7 +266,7 @@ static int f2fs_freeze(struct super_block *sb)
{
int err;
- if (sb->s_flags & MS_RDONLY)
+ if (f2fs_readonly(sb))
return 0;
err = f2fs_sync_fs(sb, 1);
@@ -214,10 +310,10 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
- if (test_opt(sbi, BG_GC))
- seq_puts(seq, ",background_gc_on");
+ if (!(root->d_sb->s_flags & MS_RDONLY) && test_opt(sbi, BG_GC))
+ seq_printf(seq, ",background_gc=%s", "on");
else
- seq_puts(seq, ",background_gc_off");
+ seq_printf(seq, ",background_gc=%s", "off");
if (test_opt(sbi, DISABLE_ROLL_FORWARD))
seq_puts(seq, ",disable_roll_forward");
if (test_opt(sbi, DISCARD))
@@ -244,11 +340,64 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
return 0;
}
+static int f2fs_remount(struct super_block *sb, int *flags, char *data)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct f2fs_mount_info org_mount_opt;
+ int err, active_logs;
+
+ /*
+ * Save the old mount options in case we
+ * need to restore them.
+ */
+ org_mount_opt = sbi->mount_opt;
+ active_logs = sbi->active_logs;
+
+ /* parse mount options */
+ err = parse_options(sb, data);
+ if (err)
+ goto restore_opts;
+
+ /*
+ * Previous and new state of filesystem is RO,
+ * so no point in checking GC conditions.
+ */
+ if ((sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY))
+ goto skip;
+
+ /*
+ * We stop the GC thread if FS is mounted as RO
+ * or if background_gc = off is passed in mount
+ * option. Also sync the filesystem.
+ */
+ if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
+ if (sbi->gc_thread) {
+ stop_gc_thread(sbi);
+ f2fs_sync_fs(sb, 1);
+ }
+ } else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) {
+ err = start_gc_thread(sbi);
+ if (err)
+ goto restore_opts;
+ }
+skip:
+ /* Update the POSIXACL Flag */
+ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+ return 0;
+
+restore_opts:
+ sbi->mount_opt = org_mount_opt;
+ sbi->active_logs = active_logs;
+ return err;
+}
+
static struct super_operations f2fs_sops = {
.alloc_inode = f2fs_alloc_inode,
.drop_inode = f2fs_drop_inode,
.destroy_inode = f2fs_destroy_inode,
.write_inode = f2fs_write_inode,
+ .dirty_inode = f2fs_dirty_inode,
.show_options = f2fs_show_options,
.evict_inode = f2fs_evict_inode,
.put_super = f2fs_put_super,
@@ -256,6 +405,7 @@ static struct super_operations f2fs_sops = {
.freeze_fs = f2fs_freeze,
.unfreeze_fs = f2fs_unfreeze,
.statfs = f2fs_statfs,
+ .remount_fs = f2fs_remount,
};
static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
@@ -303,79 +453,6 @@ static const struct export_operations f2fs_export_ops = {
.get_parent = f2fs_get_parent,
};
-static int parse_options(struct super_block *sb, struct f2fs_sb_info *sbi,
- char *options)
-{
- substring_t args[MAX_OPT_ARGS];
- char *p;
- int arg = 0;
-
- if (!options)
- return 0;
-
- while ((p = strsep(&options, ",")) != NULL) {
- int token;
- if (!*p)
- continue;
- /*
- * Initialize args struct so we know whether arg was
- * found; some options take optional arguments.
- */
- args[0].to = args[0].from = NULL;
- token = match_token(p, f2fs_tokens, args);
-
- switch (token) {
- case Opt_gc_background_off:
- clear_opt(sbi, BG_GC);
- break;
- case Opt_disable_roll_forward:
- set_opt(sbi, DISABLE_ROLL_FORWARD);
- break;
- case Opt_discard:
- set_opt(sbi, DISCARD);
- break;
- case Opt_noheap:
- set_opt(sbi, NOHEAP);
- break;
-#ifdef CONFIG_F2FS_FS_XATTR
- case Opt_nouser_xattr:
- clear_opt(sbi, XATTR_USER);
- break;
-#else
- case Opt_nouser_xattr:
- f2fs_msg(sb, KERN_INFO,
- "nouser_xattr options not supported");
- break;
-#endif
-#ifdef CONFIG_F2FS_FS_POSIX_ACL
- case Opt_noacl:
- clear_opt(sbi, POSIX_ACL);
- break;
-#else
- case Opt_noacl:
- f2fs_msg(sb, KERN_INFO, "noacl options not supported");
- break;
-#endif
- case Opt_active_logs:
- if (args->from && match_int(args, &arg))
- return -EINVAL;
- if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE)
- return -EINVAL;
- sbi->active_logs = arg;
- break;
- case Opt_disable_ext_identify:
- set_opt(sbi, DISABLE_EXT_IDENTIFY);
- break;
- default:
- f2fs_msg(sb, KERN_ERR,
- "Unrecognized mount option \"%s\" or missing value",
- p);
- return -EINVAL;
- }
- }
- return 0;
-}
-
static loff_t max_file_size(unsigned bits)
{
loff_t result = ADDRS_PER_INODE;
@@ -541,6 +618,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
if (err)
goto free_sb_buf;
}
+ sb->s_fs_info = sbi;
/* init some FS parameters */
sbi->active_logs = NR_CURSEG_TYPE;
@@ -553,7 +631,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
set_opt(sbi, POSIX_ACL);
#endif
/* parse mount options */
- err = parse_options(sb, sbi, (char *)data);
+ err = parse_options(sb, (char *)data);
if (err)
goto free_sb_buf;
@@ -565,7 +643,6 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_xattr = f2fs_xattr_handlers;
sb->s_export_op = &f2fs_export_ops;
sb->s_magic = F2FS_SUPER_MAGIC;
- sb->s_fs_info = sbi;
sb->s_time_gran = 1;
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
@@ -674,10 +751,16 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
"Cannot recover all fsync data errno=%ld", err);
}
- /* After POR, we can run background GC thread */
- err = start_gc_thread(sbi);
- if (err)
- goto fail;
+ /*
+ * If filesystem is not mounted as read-only then
+ * do start the gc_thread.
+ */
+ if (!(sb->s_flags & MS_RDONLY)) {
+ /* After POR, we can run background GC thread.*/
+ err = start_gc_thread(sbi);
+ if (err)
+ goto fail;
+ }
err = f2fs_build_stats(sbi);
if (err)
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 0b02dce31356..3ab07ecd86ca 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -20,6 +20,7 @@
*/
#include
#include
+#include
#include "f2fs.h"
#include "xattr.h"
@@ -43,6 +44,10 @@ static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
prefix = XATTR_TRUSTED_PREFIX;
prefix_len = XATTR_TRUSTED_PREFIX_LEN;
break;
+ case F2FS_XATTR_INDEX_SECURITY:
+ prefix = XATTR_SECURITY_PREFIX;
+ prefix_len = XATTR_SECURITY_PREFIX_LEN;
+ break;
default:
return -EINVAL;
}
@@ -50,7 +55,7 @@ static size_t f2fs_xattr_generic_list(struct dentry *dentry, char *list,
total_len = prefix_len + name_len + 1;
if (list && total_len <= list_size) {
memcpy(list, prefix, prefix_len);
- memcpy(list+prefix_len, name, name_len);
+ memcpy(list + prefix_len, name, name_len);
list[prefix_len + name_len] = '\0';
}
return total_len;
@@ -70,13 +75,14 @@ static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
break;
+ case F2FS_XATTR_INDEX_SECURITY:
+ break;
default:
return -EINVAL;
}
if (strcmp(name, "") == 0)
return -EINVAL;
- return f2fs_getxattr(dentry->d_inode, type, name,
- buffer, size);
+ return f2fs_getxattr(dentry->d_inode, type, name, buffer, size);
}
static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
@@ -93,13 +99,15 @@ static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
break;
+ case F2FS_XATTR_INDEX_SECURITY:
+ break;
default:
return -EINVAL;
}
if (strcmp(name, "") == 0)
return -EINVAL;
- return f2fs_setxattr(dentry->d_inode, type, name, value, size);
+ return f2fs_setxattr(dentry->d_inode, type, name, value, size, NULL);
}
static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list,
@@ -145,6 +153,31 @@ static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
return 0;
}
+#ifdef CONFIG_F2FS_FS_SECURITY
+static int f2fs_initxattrs(struct inode *inode, const struct xattr *xattr_array,
+ void *page)
+{
+ const struct xattr *xattr;
+ int err = 0;
+
+ for (xattr = xattr_array; xattr->name != NULL; xattr++) {
+ err = f2fs_setxattr(inode, F2FS_XATTR_INDEX_SECURITY,
+ xattr->name, xattr->value,
+ xattr->value_len, (struct page *)page);
+ if (err < 0)
+ break;
+ }
+ return err;
+}
+
+int f2fs_init_security(struct inode *inode, struct inode *dir,
+ const struct qstr *qstr, struct page *ipage)
+{
+ return security_inode_init_security(inode, dir, qstr,
+ &f2fs_initxattrs, ipage);
+}
+#endif
+
const struct xattr_handler f2fs_xattr_user_handler = {
.prefix = XATTR_USER_PREFIX,
.flags = F2FS_XATTR_INDEX_USER,
@@ -169,6 +202,14 @@ const struct xattr_handler f2fs_xattr_advise_handler = {
.set = f2fs_xattr_advise_set,
};
+const struct xattr_handler f2fs_xattr_security_handler = {
+ .prefix = XATTR_SECURITY_PREFIX,
+ .flags = F2FS_XATTR_INDEX_SECURITY,
+ .list = f2fs_xattr_generic_list,
+ .get = f2fs_xattr_generic_get,
+ .set = f2fs_xattr_generic_set,
+};
+
static const struct xattr_handler *f2fs_xattr_handler_map[] = {
[F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler,
#ifdef CONFIG_F2FS_FS_POSIX_ACL
@@ -176,6 +217,9 @@ static const struct xattr_handler *f2fs_xattr_handler_map[] = {
[F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &f2fs_xattr_acl_default_handler,
#endif
[F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler,
+#ifdef CONFIG_F2FS_FS_SECURITY
+ [F2FS_XATTR_INDEX_SECURITY] = &f2fs_xattr_security_handler,
+#endif
[F2FS_XATTR_INDEX_ADVISE] = &f2fs_xattr_advise_handler,
};
@@ -186,6 +230,9 @@ const struct xattr_handler *f2fs_xattr_handlers[] = {
&f2fs_xattr_acl_default_handler,
#endif
&f2fs_xattr_trusted_handler,
+#ifdef CONFIG_F2FS_FS_SECURITY
+ &f2fs_xattr_security_handler,
+#endif
&f2fs_xattr_advise_handler,
NULL,
};
@@ -218,6 +265,8 @@ int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
return -ENODATA;
page = get_node_page(sbi, fi->i_xattr_nid);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
base_addr = page_address(page);
list_for_each_xattr(entry, base_addr) {
@@ -268,6 +317,8 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
return 0;
page = get_node_page(sbi, fi->i_xattr_nid);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
base_addr = page_address(page);
list_for_each_xattr(entry, base_addr) {
@@ -296,7 +347,7 @@ cleanup:
}
int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
- const void *value, size_t value_len)
+ const void *value, size_t value_len, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -335,7 +386,7 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
set_new_dnode(&dn, inode, NULL, NULL, fi->i_xattr_nid);
mark_inode_dirty(inode);
- page = new_node_page(&dn, XATTR_NODE_OFFSET);
+ page = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
if (IS_ERR(page)) {
alloc_nid_failed(sbi, fi->i_xattr_nid);
fi->i_xattr_nid = 0;
@@ -435,7 +486,10 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
inode->i_ctime = CURRENT_TIME;
clear_inode_flag(fi, FI_ACL_MODE);
}
- update_inode_page(inode);
+ if (ipage)
+ update_inode(inode, ipage);
+ else
+ update_inode_page(inode);
mutex_unlock_op(sbi, ilock);
return 0;
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 49c9558305e3..3c0817bef25d 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -112,21 +112,19 @@ extern const struct xattr_handler f2fs_xattr_trusted_handler;
extern const struct xattr_handler f2fs_xattr_acl_access_handler;
extern const struct xattr_handler f2fs_xattr_acl_default_handler;
extern const struct xattr_handler f2fs_xattr_advise_handler;
+extern const struct xattr_handler f2fs_xattr_security_handler;
extern const struct xattr_handler *f2fs_xattr_handlers[];
-extern int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
- const void *value, size_t value_len);
-extern int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
- void *buffer, size_t buffer_size);
-extern ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer,
- size_t buffer_size);
-
+extern int f2fs_setxattr(struct inode *, int, const char *,
+ const void *, size_t, struct page *);
+extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t);
+extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
#else
#define f2fs_xattr_handlers NULL
static inline int f2fs_setxattr(struct inode *inode, int name_index,
- const char *name, const void *value, size_t value_len)
+ const char *name, const void *value, size_t value_len)
{
return -EOPNOTSUPP;
}
@@ -142,4 +140,14 @@ static inline ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer,
}
#endif
+#ifdef CONFIG_F2FS_FS_SECURITY
+extern int f2fs_init_security(struct inode *, struct inode *,
+ const struct qstr *, struct page *);
+#else
+static inline int f2fs_init_security(struct inode *inode, struct inode *dir,
+ const struct qstr *qstr, struct page *ipage)
+{
+ return 0;
+}
+#endif
#endif /* __F2FS_XATTR_H__ */
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index df6fab82f87e..383d5e39b280 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -20,8 +20,8 @@
#define F2FS_BLKSIZE 4096 /* support only 4KB block */
#define F2FS_MAX_EXTENSION 64 /* # of extension entries */
-#define NULL_ADDR 0x0U
-#define NEW_ADDR -1U
+#define NULL_ADDR ((block_t)0) /* used as block_t addresses */
+#define NEW_ADDR ((block_t)-1) /* used as block_t addresses */
#define F2FS_ROOT_INO(sbi) (sbi->root_ino_num)
#define F2FS_NODE_INO(sbi) (sbi->node_ino_num)