linux/fs/f2fs/inode.c

436 lines
12 KiB
C
Raw Normal View History

/*
* fs/f2fs/inode.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include "f2fs.h"
#include "node.h"
#include <trace/events/f2fs.h>
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
unsigned int new_fl = 0;
if (flags & FS_SYNC_FL)
new_fl |= S_SYNC;
if (flags & FS_APPEND_FL)
new_fl |= S_APPEND;
if (flags & FS_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
if (flags & FS_NOATIME_FL)
new_fl |= S_NOATIME;
if (flags & FS_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
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]));
else
inode->i_rdev =
new_decode_dev(le32_to_cpu(ri->i_addr[1]));
}
}
static bool __written_first_block(struct f2fs_inode *ri)
{
block_t addr = le32_to_cpu(ri->i_addr[0]);
if (addr != NEW_ADDR && addr != NULL_ADDR)
return true;
return false;
}
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
ri->i_addr[0] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
ri->i_addr[1] = 0;
} else {
ri->i_addr[0] = 0;
ri->i_addr[1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
ri->i_addr[2] = 0;
}
}
}
static void __recover_inline_status(struct inode *inode, struct page *ipage)
{
void *inline_data = inline_data_addr(ipage);
__le32 *start = inline_data;
__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
while (start < end) {
if (*start++) {
f2fs_wait_on_page_writeback(ipage, NODE);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
set_page_dirty(ipage);
return;
}
}
return;
}
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;
/* Check if ino is within scope */
if (check_nid_range(sbi, inode->i_ino)) {
f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
(unsigned long) inode->i_ino);
WARN_ON(1);
return -EINVAL;
}
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
ri = F2FS_INODE(node_page);
inode->i_mode = le16_to_cpu(ri->i_mode);
i_uid_write(inode, le32_to_cpu(ri->i_uid));
i_gid_write(inode, le32_to_cpu(ri->i_gid));
set_nlink(inode, le32_to_cpu(ri->i_links));
inode->i_size = le64_to_cpu(ri->i_size);
inode->i_blocks = le64_to_cpu(ri->i_blocks);
inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(ri->i_mtime);
inode->i_atime.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
inode->i_generation = le32_to_cpu(ri->i_generation);
fi->i_current_depth = le32_to_cpu(ri->i_current_depth);
fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid);
fi->i_flags = le32_to_cpu(ri->i_flags);
fi->flags = 0;
fi->i_advise = ri->i_advise;
fi->i_pino = le32_to_cpu(ri->i_pino);
f2fs: introduce large directory support This patch introduces an i_dir_level field to support large directory. Previously, f2fs maintains multi-level hash tables to find a dentry quickly from a bunch of chiild dentries in a directory, and the hash tables consist of the following tree structure as below. In Documentation/filesystems/f2fs.txt, ---------------------- A : bucket B : block N : MAX_DIR_HASH_DEPTH ---------------------- level #0 | A(2B) | level #1 | A(2B) - A(2B) | level #2 | A(2B) - A(2B) - A(2B) - A(2B) . | . . . . level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) But, if we can guess that a directory will handle a number of child files, we don't need to traverse the tree from level #0 to #N all the time. Since the lower level tables contain relatively small number of dentries, the miss ratio of the target dentry is likely to be high. In order to avoid that, we can configure the hash tables sparsely from level #0 like this. level #0 | A(2B) - A(2B) - A(2B) - A(2B) level #1 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) With this structure, we can skip the ineffective tree searches in lower level hash tables. This patch adds just a facility for this by introducing i_dir_level in f2fs_inode. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2014-02-27 09:20:00 +00:00
fi->i_dir_level = ri->i_dir_level;
f2fs_init_extent_tree(inode, &ri->i_ext);
get_inline_info(fi, ri);
/* check data exist */
if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
__recover_inline_status(inode, node_page);
/* get rdev by using inline_info */
__get_inode_rdev(inode, ri);
if (__written_first_block(ri))
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
f2fs_put_page(node_page, 1);
stat_inc_inline_xattr(inode);
stat_inc_inline_inode(inode);
stat_inc_inline_dir(inode);
return 0;
}
struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
struct inode *inode;
int ret = 0;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW)) {
trace_f2fs_iget(inode);
return inode;
}
if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi))
goto make_now;
ret = do_read_inode(inode);
if (ret)
goto bad_inode;
make_now:
if (ino == F2FS_NODE_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_node_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
} else if (ino == F2FS_META_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_meta_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
} else if (S_ISREG(inode->i_mode)) {
inode->i_op = &f2fs_file_inode_operations;
inode->i_fop = &f2fs_file_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISDIR(inode->i_mode)) {
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_F2FS_HIGH_ZERO);
} else if (S_ISLNK(inode->i_mode)) {
if (f2fs_encrypted_inode(inode))
inode->i_op = &f2fs_encrypted_symlink_inode_operations;
else
inode->i_op = &f2fs_symlink_inode_operations;
inode->i_mapping->a_ops = &f2fs_dblock_aops;
} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &f2fs_special_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
} else {
ret = -EIO;
goto bad_inode;
}
unlock_new_inode(inode);
trace_f2fs_iget(inode);
return inode;
bad_inode:
iget_failed(inode);
trace_f2fs_iget_exit(inode, ret);
return ERR_PTR(ret);
}
void update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
f2fs_wait_on_page_writeback(node_page, NODE);
ri = F2FS_INODE(node_page);
ri->i_mode = cpu_to_le16(inode->i_mode);
ri->i_advise = F2FS_I(inode)->i_advise;
ri->i_uid = cpu_to_le32(i_uid_read(inode));
ri->i_gid = cpu_to_le32(i_gid_read(inode));
ri->i_links = cpu_to_le32(inode->i_nlink);
ri->i_size = cpu_to_le64(i_size_read(inode));
ri->i_blocks = cpu_to_le64(inode->i_blocks);
if (F2FS_I(inode)->extent_tree)
set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
&ri->i_ext);
else
memset(&ri->i_ext, 0, sizeof(ri->i_ext));
set_raw_inline(F2FS_I(inode), ri);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
ri->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth);
ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid);
ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
ri->i_generation = cpu_to_le32(inode->i_generation);
f2fs: introduce large directory support This patch introduces an i_dir_level field to support large directory. Previously, f2fs maintains multi-level hash tables to find a dentry quickly from a bunch of chiild dentries in a directory, and the hash tables consist of the following tree structure as below. In Documentation/filesystems/f2fs.txt, ---------------------- A : bucket B : block N : MAX_DIR_HASH_DEPTH ---------------------- level #0 | A(2B) | level #1 | A(2B) - A(2B) | level #2 | A(2B) - A(2B) - A(2B) - A(2B) . | . . . . level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) But, if we can guess that a directory will handle a number of child files, we don't need to traverse the tree from level #0 to #N all the time. Since the lower level tables contain relatively small number of dentries, the miss ratio of the target dentry is likely to be high. In order to avoid that, we can configure the hash tables sparsely from level #0 like this. level #0 | A(2B) - A(2B) - A(2B) - A(2B) level #1 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B) . | . . . . level #N | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B) With this structure, we can skip the ineffective tree searches in lower level hash tables. This patch adds just a facility for this by introducing i_dir_level in f2fs_inode. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2014-02-27 09:20:00 +00:00
ri->i_dir_level = F2FS_I(inode)->i_dir_level;
__set_inode_rdev(inode, ri);
set_cold_node(inode, node_page);
set_page_dirty(node_page);
clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
}
void update_inode_page(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *node_page;
retry:
node_page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(node_page)) {
int err = PTR_ERR(node_page);
if (err == -ENOMEM) {
cond_resched();
goto retry;
} else if (err != -ENOENT) {
f2fs_stop_checkpoint(sbi);
}
return;
}
update_inode(inode, node_page);
f2fs_put_page(node_page, 1);
}
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
return 0;
if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
return 0;
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
/*
* We need to lock here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
*/
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 10:08:30 +00:00
f2fs_lock_op(sbi);
update_inode_page(inode);
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 10:08:30 +00:00
f2fs_unlock_op(sbi);
if (wbc)
f2fs_balance_fs(sbi);
return 0;
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
}
/*
* Called at the last iput() if i_nlink is zero
*/
void f2fs_evict_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
nid_t xnid = fi->i_xattr_nid;
int err = 0;
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
commit_inmem_pages(inode, true);
trace_f2fs_evict_inode(inode);
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 21:47:49 +00:00
truncate_inode_pages_final(&inode->i_data);
if (inode->i_ino == F2FS_NODE_INO(sbi) ||
inode->i_ino == F2FS_META_INO(sbi))
f2fs: avoid use invalid mapping of node_inode when evict meta inode Andrey Tsyvarev reported: "Using memory error detector reveals the following use-after-free error in 3.15.0: AddressSanitizer: heap-use-after-free in f2fs_evict_inode Read of size 8 by thread T22279: [<ffffffffa02d8702>] f2fs_evict_inode+0x102/0x2e0 [f2fs] [<ffffffff812359af>] evict+0x15f/0x290 [< inlined >] iput+0x196/0x280 iput_final [<ffffffff812369a6>] iput+0x196/0x280 [<ffffffffa02dc416>] f2fs_put_super+0xd6/0x170 [f2fs] [<ffffffff81210095>] generic_shutdown_super+0xc5/0x1b0 [<ffffffff812105fd>] kill_block_super+0x4d/0xb0 [<ffffffff81210a86>] deactivate_locked_super+0x66/0x80 [<ffffffff81211c98>] deactivate_super+0x68/0x80 [<ffffffff8123cc88>] mntput_no_expire+0x198/0x250 [< inlined >] SyS_umount+0xe9/0x1a0 SYSC_umount [<ffffffff8123f1c9>] SyS_umount+0xe9/0x1a0 [<ffffffff81cc8df9>] system_call_fastpath+0x16/0x1b Freed by thread T3: [<ffffffffa02dc337>] f2fs_i_callback+0x27/0x30 [f2fs] [< inlined >] rcu_process_callbacks+0x2d6/0x930 __rcu_reclaim [< inlined >] rcu_process_callbacks+0x2d6/0x930 rcu_do_batch [< inlined >] rcu_process_callbacks+0x2d6/0x930 invoke_rcu_callbacks [< inlined >] rcu_process_callbacks+0x2d6/0x930 __rcu_process_callbacks [<ffffffff810fd266>] rcu_process_callbacks+0x2d6/0x930 [<ffffffff8107cce2>] __do_softirq+0x142/0x380 [<ffffffff8107cf50>] run_ksoftirqd+0x30/0x50 [<ffffffff810b2a87>] smpboot_thread_fn+0x197/0x280 [<ffffffff810a8238>] kthread+0x148/0x160 [<ffffffff81cc8d4c>] ret_from_fork+0x7c/0xb0 Allocated by thread T22276: [<ffffffffa02dc7dd>] f2fs_alloc_inode+0x2d/0x170 [f2fs] [<ffffffff81235e2a>] iget_locked+0x10a/0x230 [<ffffffffa02d7495>] f2fs_iget+0x35/0xa80 [f2fs] [<ffffffffa02e2393>] f2fs_fill_super+0xb53/0xff0 [f2fs] [<ffffffff81211bce>] mount_bdev+0x1de/0x240 [<ffffffffa02dbce0>] f2fs_mount+0x10/0x20 [f2fs] [<ffffffff81212a85>] mount_fs+0x55/0x220 [<ffffffff8123c026>] vfs_kern_mount+0x66/0x200 [< inlined >] do_mount+0x2b4/0x1120 do_new_mount [<ffffffff812400d4>] do_mount+0x2b4/0x1120 [< inlined >] SyS_mount+0xb2/0x110 SYSC_mount [<ffffffff812414a2>] SyS_mount+0xb2/0x110 [<ffffffff81cc8df9>] system_call_fastpath+0x16/0x1b The buggy address ffff8800587866c8 is located 48 bytes inside of 680-byte region [ffff880058786698, ffff880058786940) Memory state around the buggy address: ffff880058786100: ffffffff ffffffff ffffffff ffffffff ffff880058786200: ffffffff ffffffff ffffffrr rrrrrrrr ffff880058786300: rrrrrrrr rrffffff ffffffff ffffffff ffff880058786400: ffffffff ffffffff ffffffff ffffffff ffff880058786500: ffffffff ffffffff ffffffff fffffffr >ffff880058786600: rrrrrrrr rrrrrrrr rrrfffff ffffffff ^ ffff880058786700: ffffffff ffffffff ffffffff ffffffff ffff880058786800: ffffffff ffffffff ffffffff ffffffff ffff880058786900: ffffffff rrrrrrrr rrrrrrrr rrrr.... ffff880058786a00: ........ ........ ........ ........ ffff880058786b00: ........ ........ ........ ........ Legend: f - 8 freed bytes r - 8 redzone bytes . - 8 allocated bytes x=1..7 - x allocated bytes + (8-x) redzone bytes Investigation shows, that f2fs_evict_inode, when called for 'meta_inode', uses invalidate_mapping_pages() for 'node_inode'. But 'node_inode' is deleted before 'meta_inode' in f2fs_put_super via iput(). It seems that in common usage scenario this use-after-free is benign, because 'node_inode' remains partially valid data even after kmem_cache_free(). But things may change if, while 'meta_inode' is evicted in one f2fs filesystem, another (mounted) f2fs filesystem requests inode from cache, and formely 'node_inode' of the first filesystem is returned." Nids for both meta_inode and node_inode are reservation, so it's not necessary for us to invalidate pages which will never be allocated. To fix this issue, let's skipping needlessly invalidating pages for {meta,node}_inode in f2fs_evict_inode. Reported-by: Andrey Tsyvarev <tsyvarev@ispras.ru> Tested-by: Andrey Tsyvarev <tsyvarev@ispras.ru> Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-07-25 04:00:57 +00:00
goto out_clear;
f2fs_bug_on(sbi, get_dirty_pages(inode));
remove_dirty_dir_inode(inode);
f2fs_destroy_extent_tree(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
sb_start_intwrite(inode->i_sb);
set_inode_flag(fi, FI_NO_ALLOC);
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode, true);
if (!err) {
f2fs_lock_op(sbi);
err = remove_inode_page(inode);
f2fs_unlock_op(sbi);
}
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 07:21:29 +00:00
sb_end_intwrite(inode->i_sb);
no_delete:
stat_dec_inline_xattr(inode);
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
if (xnid)
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
if (is_inode_flag_set(fi, FI_APPEND_WRITE))
add_dirty_inode(sbi, inode->i_ino, APPEND_INO);
if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
add_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
if (is_inode_flag_set(fi, FI_FREE_NID)) {
if (err && err != -ENOENT)
alloc_nid_done(sbi, inode->i_ino);
else
alloc_nid_failed(sbi, inode->i_ino);
clear_inode_flag(fi, FI_FREE_NID);
}
if (err && err != -ENOENT) {
if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) {
/*
* get here because we failed to release resource
* of inode previously, reminder our user to run fsck
* for fixing.
*/
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"inode (ino:%lu) resource leak, run fsck "
"to fix this issue!", inode->i_ino);
}
}
f2fs: avoid use invalid mapping of node_inode when evict meta inode Andrey Tsyvarev reported: "Using memory error detector reveals the following use-after-free error in 3.15.0: AddressSanitizer: heap-use-after-free in f2fs_evict_inode Read of size 8 by thread T22279: [<ffffffffa02d8702>] f2fs_evict_inode+0x102/0x2e0 [f2fs] [<ffffffff812359af>] evict+0x15f/0x290 [< inlined >] iput+0x196/0x280 iput_final [<ffffffff812369a6>] iput+0x196/0x280 [<ffffffffa02dc416>] f2fs_put_super+0xd6/0x170 [f2fs] [<ffffffff81210095>] generic_shutdown_super+0xc5/0x1b0 [<ffffffff812105fd>] kill_block_super+0x4d/0xb0 [<ffffffff81210a86>] deactivate_locked_super+0x66/0x80 [<ffffffff81211c98>] deactivate_super+0x68/0x80 [<ffffffff8123cc88>] mntput_no_expire+0x198/0x250 [< inlined >] SyS_umount+0xe9/0x1a0 SYSC_umount [<ffffffff8123f1c9>] SyS_umount+0xe9/0x1a0 [<ffffffff81cc8df9>] system_call_fastpath+0x16/0x1b Freed by thread T3: [<ffffffffa02dc337>] f2fs_i_callback+0x27/0x30 [f2fs] [< inlined >] rcu_process_callbacks+0x2d6/0x930 __rcu_reclaim [< inlined >] rcu_process_callbacks+0x2d6/0x930 rcu_do_batch [< inlined >] rcu_process_callbacks+0x2d6/0x930 invoke_rcu_callbacks [< inlined >] rcu_process_callbacks+0x2d6/0x930 __rcu_process_callbacks [<ffffffff810fd266>] rcu_process_callbacks+0x2d6/0x930 [<ffffffff8107cce2>] __do_softirq+0x142/0x380 [<ffffffff8107cf50>] run_ksoftirqd+0x30/0x50 [<ffffffff810b2a87>] smpboot_thread_fn+0x197/0x280 [<ffffffff810a8238>] kthread+0x148/0x160 [<ffffffff81cc8d4c>] ret_from_fork+0x7c/0xb0 Allocated by thread T22276: [<ffffffffa02dc7dd>] f2fs_alloc_inode+0x2d/0x170 [f2fs] [<ffffffff81235e2a>] iget_locked+0x10a/0x230 [<ffffffffa02d7495>] f2fs_iget+0x35/0xa80 [f2fs] [<ffffffffa02e2393>] f2fs_fill_super+0xb53/0xff0 [f2fs] [<ffffffff81211bce>] mount_bdev+0x1de/0x240 [<ffffffffa02dbce0>] f2fs_mount+0x10/0x20 [f2fs] [<ffffffff81212a85>] mount_fs+0x55/0x220 [<ffffffff8123c026>] vfs_kern_mount+0x66/0x200 [< inlined >] do_mount+0x2b4/0x1120 do_new_mount [<ffffffff812400d4>] do_mount+0x2b4/0x1120 [< inlined >] SyS_mount+0xb2/0x110 SYSC_mount [<ffffffff812414a2>] SyS_mount+0xb2/0x110 [<ffffffff81cc8df9>] system_call_fastpath+0x16/0x1b The buggy address ffff8800587866c8 is located 48 bytes inside of 680-byte region [ffff880058786698, ffff880058786940) Memory state around the buggy address: ffff880058786100: ffffffff ffffffff ffffffff ffffffff ffff880058786200: ffffffff ffffffff ffffffrr rrrrrrrr ffff880058786300: rrrrrrrr rrffffff ffffffff ffffffff ffff880058786400: ffffffff ffffffff ffffffff ffffffff ffff880058786500: ffffffff ffffffff ffffffff fffffffr >ffff880058786600: rrrrrrrr rrrrrrrr rrrfffff ffffffff ^ ffff880058786700: ffffffff ffffffff ffffffff ffffffff ffff880058786800: ffffffff ffffffff ffffffff ffffffff ffff880058786900: ffffffff rrrrrrrr rrrrrrrr rrrr.... ffff880058786a00: ........ ........ ........ ........ ffff880058786b00: ........ ........ ........ ........ Legend: f - 8 freed bytes r - 8 redzone bytes . - 8 allocated bytes x=1..7 - x allocated bytes + (8-x) redzone bytes Investigation shows, that f2fs_evict_inode, when called for 'meta_inode', uses invalidate_mapping_pages() for 'node_inode'. But 'node_inode' is deleted before 'meta_inode' in f2fs_put_super via iput(). It seems that in common usage scenario this use-after-free is benign, because 'node_inode' remains partially valid data even after kmem_cache_free(). But things may change if, while 'meta_inode' is evicted in one f2fs filesystem, another (mounted) f2fs filesystem requests inode from cache, and formely 'node_inode' of the first filesystem is returned." Nids for both meta_inode and node_inode are reservation, so it's not necessary for us to invalidate pages which will never be allocated. To fix this issue, let's skipping needlessly invalidating pages for {meta,node}_inode in f2fs_evict_inode. Reported-by: Andrey Tsyvarev <tsyvarev@ispras.ru> Tested-by: Andrey Tsyvarev <tsyvarev@ispras.ru> Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-07-25 04:00:57 +00:00
out_clear:
#ifdef CONFIG_F2FS_FS_ENCRYPTION
if (fi->i_crypt_info)
f2fs_free_encryption_info(inode, fi->i_crypt_info);
#endif
f2fs: avoid use invalid mapping of node_inode when evict meta inode Andrey Tsyvarev reported: "Using memory error detector reveals the following use-after-free error in 3.15.0: AddressSanitizer: heap-use-after-free in f2fs_evict_inode Read of size 8 by thread T22279: [<ffffffffa02d8702>] f2fs_evict_inode+0x102/0x2e0 [f2fs] [<ffffffff812359af>] evict+0x15f/0x290 [< inlined >] iput+0x196/0x280 iput_final [<ffffffff812369a6>] iput+0x196/0x280 [<ffffffffa02dc416>] f2fs_put_super+0xd6/0x170 [f2fs] [<ffffffff81210095>] generic_shutdown_super+0xc5/0x1b0 [<ffffffff812105fd>] kill_block_super+0x4d/0xb0 [<ffffffff81210a86>] deactivate_locked_super+0x66/0x80 [<ffffffff81211c98>] deactivate_super+0x68/0x80 [<ffffffff8123cc88>] mntput_no_expire+0x198/0x250 [< inlined >] SyS_umount+0xe9/0x1a0 SYSC_umount [<ffffffff8123f1c9>] SyS_umount+0xe9/0x1a0 [<ffffffff81cc8df9>] system_call_fastpath+0x16/0x1b Freed by thread T3: [<ffffffffa02dc337>] f2fs_i_callback+0x27/0x30 [f2fs] [< inlined >] rcu_process_callbacks+0x2d6/0x930 __rcu_reclaim [< inlined >] rcu_process_callbacks+0x2d6/0x930 rcu_do_batch [< inlined >] rcu_process_callbacks+0x2d6/0x930 invoke_rcu_callbacks [< inlined >] rcu_process_callbacks+0x2d6/0x930 __rcu_process_callbacks [<ffffffff810fd266>] rcu_process_callbacks+0x2d6/0x930 [<ffffffff8107cce2>] __do_softirq+0x142/0x380 [<ffffffff8107cf50>] run_ksoftirqd+0x30/0x50 [<ffffffff810b2a87>] smpboot_thread_fn+0x197/0x280 [<ffffffff810a8238>] kthread+0x148/0x160 [<ffffffff81cc8d4c>] ret_from_fork+0x7c/0xb0 Allocated by thread T22276: [<ffffffffa02dc7dd>] f2fs_alloc_inode+0x2d/0x170 [f2fs] [<ffffffff81235e2a>] iget_locked+0x10a/0x230 [<ffffffffa02d7495>] f2fs_iget+0x35/0xa80 [f2fs] [<ffffffffa02e2393>] f2fs_fill_super+0xb53/0xff0 [f2fs] [<ffffffff81211bce>] mount_bdev+0x1de/0x240 [<ffffffffa02dbce0>] f2fs_mount+0x10/0x20 [f2fs] [<ffffffff81212a85>] mount_fs+0x55/0x220 [<ffffffff8123c026>] vfs_kern_mount+0x66/0x200 [< inlined >] do_mount+0x2b4/0x1120 do_new_mount [<ffffffff812400d4>] do_mount+0x2b4/0x1120 [< inlined >] SyS_mount+0xb2/0x110 SYSC_mount [<ffffffff812414a2>] SyS_mount+0xb2/0x110 [<ffffffff81cc8df9>] system_call_fastpath+0x16/0x1b The buggy address ffff8800587866c8 is located 48 bytes inside of 680-byte region [ffff880058786698, ffff880058786940) Memory state around the buggy address: ffff880058786100: ffffffff ffffffff ffffffff ffffffff ffff880058786200: ffffffff ffffffff ffffffrr rrrrrrrr ffff880058786300: rrrrrrrr rrffffff ffffffff ffffffff ffff880058786400: ffffffff ffffffff ffffffff ffffffff ffff880058786500: ffffffff ffffffff ffffffff fffffffr >ffff880058786600: rrrrrrrr rrrrrrrr rrrfffff ffffffff ^ ffff880058786700: ffffffff ffffffff ffffffff ffffffff ffff880058786800: ffffffff ffffffff ffffffff ffffffff ffff880058786900: ffffffff rrrrrrrr rrrrrrrr rrrr.... ffff880058786a00: ........ ........ ........ ........ ffff880058786b00: ........ ........ ........ ........ Legend: f - 8 freed bytes r - 8 redzone bytes . - 8 allocated bytes x=1..7 - x allocated bytes + (8-x) redzone bytes Investigation shows, that f2fs_evict_inode, when called for 'meta_inode', uses invalidate_mapping_pages() for 'node_inode'. But 'node_inode' is deleted before 'meta_inode' in f2fs_put_super via iput(). It seems that in common usage scenario this use-after-free is benign, because 'node_inode' remains partially valid data even after kmem_cache_free(). But things may change if, while 'meta_inode' is evicted in one f2fs filesystem, another (mounted) f2fs filesystem requests inode from cache, and formely 'node_inode' of the first filesystem is returned." Nids for both meta_inode and node_inode are reservation, so it's not necessary for us to invalidate pages which will never be allocated. To fix this issue, let's skipping needlessly invalidating pages for {meta,node}_inode in f2fs_evict_inode. Reported-by: Andrey Tsyvarev <tsyvarev@ispras.ru> Tested-by: Andrey Tsyvarev <tsyvarev@ispras.ru> Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-07-25 04:00:57 +00:00
clear_inode(inode);
}
/* caller should call f2fs_lock_op() */
void handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int err = 0;
clear_nlink(inode);
make_bad_inode(inode);
unlock_new_inode(inode);
i_size_write(inode, 0);
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode, false);
if (!err)
err = remove_inode_page(inode);
/*
* if we skip truncate_node in remove_inode_page bacause we failed
* before, it's better to find another way to release resource of
* this inode (e.g. valid block count, node block or nid). Here we
* choose to add this inode to orphan list, so that we can call iput
* for releasing in orphan recovery flow.
*
* Note: we should add inode to orphan list before f2fs_unlock_op()
* so we can prevent losing this orphan when encoutering checkpoint
* and following suddenly power-off.
*/
if (err && err != -ENOENT) {
err = acquire_orphan_inode(sbi);
if (!err)
add_orphan_inode(sbi, inode->i_ino);
}
set_inode_flag(F2FS_I(inode), FI_FREE_NID);
f2fs_unlock_op(sbi);
/* iput will drop the inode object */
iput(inode);
}