linux/fs/f2fs/inode.c

664 lines
18 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/backing-dev.h>
#include <linux/writeback.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include <trace/events/f2fs.h>
void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
{
if (is_inode_flag_set(inode, FI_NEW_INODE))
return;
if (f2fs_inode_dirtied(inode, sync))
return;
mark_inode_dirty_sync(inode);
}
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
unsigned int new_fl = 0;
if (flags & F2FS_SYNC_FL)
new_fl |= S_SYNC;
if (flags & F2FS_APPEND_FL)
new_fl |= S_APPEND;
if (flags & F2FS_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
if (flags & F2FS_NOATIME_FL)
new_fl |= S_NOATIME;
if (flags & F2FS_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
if (f2fs_encrypted_inode(inode))
new_fl |= S_ENCRYPTED;
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|
S_ENCRYPTED);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
int extra_size = get_extra_isize(inode);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
if (ri->i_addr[extra_size])
inode->i_rdev = old_decode_dev(
le32_to_cpu(ri->i_addr[extra_size]));
else
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
inode->i_rdev = new_decode_dev(
le32_to_cpu(ri->i_addr[extra_size + 1]));
}
}
static bool __written_first_block(struct f2fs_inode *ri)
{
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]);
if (addr != NEW_ADDR && addr != NULL_ADDR)
return true;
return false;
}
static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
{
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
int extra_size = get_extra_isize(inode);
if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
if (old_valid_dev(inode->i_rdev)) {
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
ri->i_addr[extra_size] =
cpu_to_le32(old_encode_dev(inode->i_rdev));
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
ri->i_addr[extra_size + 1] = 0;
} else {
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
ri->i_addr[extra_size] = 0;
ri->i_addr[extra_size + 1] =
cpu_to_le32(new_encode_dev(inode->i_rdev));
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
ri->i_addr[extra_size + 2] = 0;
}
}
}
static void __recover_inline_status(struct inode *inode, struct page *ipage)
{
void *inline_data = inline_data_addr(inode, ipage);
__le32 *start = inline_data;
__le32 *end = start + MAX_INLINE_DATA(inode) / sizeof(__le32);
while (start < end) {
if (*start++) {
f2fs_wait_on_page_writeback(ipage, NODE, true);
set_inode_flag(inode, FI_DATA_EXIST);
set_raw_inline(inode, F2FS_INODE(ipage));
set_page_dirty(ipage);
return;
}
}
return;
}
static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *ri = &F2FS_NODE(page)->i;
if (!f2fs_sb_has_inode_chksum(sbi->sb))
return false;
if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR))
return false;
if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize),
i_inode_checksum))
return false;
return true;
}
static __u32 f2fs_inode_chksum(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_node *node = F2FS_NODE(page);
struct f2fs_inode *ri = &node->i;
__le32 ino = node->footer.ino;
__le32 gen = ri->i_generation;
__u32 chksum, chksum_seed;
__u32 dummy_cs = 0;
unsigned int offset = offsetof(struct f2fs_inode, i_inode_checksum);
unsigned int cs_size = sizeof(dummy_cs);
chksum = f2fs_chksum(sbi, sbi->s_chksum_seed, (__u8 *)&ino,
sizeof(ino));
chksum_seed = f2fs_chksum(sbi, chksum, (__u8 *)&gen, sizeof(gen));
chksum = f2fs_chksum(sbi, chksum_seed, (__u8 *)ri, offset);
chksum = f2fs_chksum(sbi, chksum, (__u8 *)&dummy_cs, cs_size);
offset += cs_size;
chksum = f2fs_chksum(sbi, chksum, (__u8 *)ri + offset,
F2FS_BLKSIZE - offset);
return chksum;
}
bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *ri;
__u32 provided, calculated;
if (!f2fs_enable_inode_chksum(sbi, page) ||
PageDirty(page) || PageWriteback(page))
return true;
ri = &F2FS_NODE(page)->i;
provided = le32_to_cpu(ri->i_inode_checksum);
calculated = f2fs_inode_chksum(sbi, page);
if (provided != calculated)
f2fs_msg(sbi->sb, KERN_WARNING,
"checksum invalid, ino = %x, %x vs. %x",
ino_of_node(page), provided, calculated);
return provided == calculated;
}
void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_inode *ri = &F2FS_NODE(page)->i;
if (!f2fs_enable_inode_chksum(sbi, page))
return;
ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page));
}
f2fs: avoid bug_on on corrupted inode syzbot has tested the proposed patch but the reproducer still triggered crash: kernel BUG at fs/f2fs/inode.c:LINE! F2FS-fs (loop1): invalid crc value F2FS-fs (loop5): Magic Mismatch, valid(0xf2f52010) - read(0x0) F2FS-fs (loop5): Can't find valid F2FS filesystem in 1th superblock F2FS-fs (loop5): invalid crc value ------------[ cut here ]------------ kernel BUG at fs/f2fs/inode.c:238! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 4886 Comm: syz-executor1 Not tainted 4.17.0-rc1+ #1 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:do_read_inode fs/f2fs/inode.c:238 [inline] RIP: 0010:f2fs_iget+0x3307/0x3ca0 fs/f2fs/inode.c:313 RSP: 0018:ffff8801c44a70e8 EFLAGS: 00010293 RAX: ffff8801ce208040 RBX: ffff8801b3621080 RCX: ffffffff82eace18 F2FS-fs (loop2): Magic Mismatch, valid(0xf2f52010) - read(0x0) RDX: 0000000000000000 RSI: ffffffff82eaf047 RDI: 0000000000000007 RBP: ffff8801c44a7410 R08: ffff8801ce208040 R09: ffffed0039ee4176 R10: ffffed0039ee4176 R11: ffff8801cf720bb7 R12: ffff8801c0efa000 R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f753aa9d700(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 ------------[ cut here ]------------ CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 kernel BUG at fs/f2fs/inode.c:238! CR2: 0000000001b03018 CR3: 00000001c8b74000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_fill_super+0x4377/0x7bf0 fs/f2fs/super.c:2842 mount_bdev+0x30c/0x3e0 fs/super.c:1165 f2fs_mount+0x34/0x40 fs/f2fs/super.c:3020 mount_fs+0xae/0x328 fs/super.c:1268 vfs_kern_mount.part.34+0xd4/0x4d0 fs/namespace.c:1037 vfs_kern_mount fs/namespace.c:1027 [inline] do_new_mount fs/namespace.c:2517 [inline] do_mount+0x564/0x3070 fs/namespace.c:2847 ksys_mount+0x12d/0x140 fs/namespace.c:3063 __do_sys_mount fs/namespace.c:3077 [inline] __se_sys_mount fs/namespace.c:3074 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3074 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457daa RSP: 002b:00007f753aa9cba8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 0000000000457daa RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007f753aa9cbf0 RBP: 0000000000000064 R08: 0000000020016a00 R09: 0000000020000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 0000000000000064 R14: 00000000006fcb80 R15: 0000000000000000 RIP: do_read_inode fs/f2fs/inode.c:238 [inline] RSP: ffff8801c44a70e8 RIP: f2fs_iget+0x3307/0x3ca0 fs/f2fs/inode.c:313 RSP: ffff8801c44a70e8 invalid opcode: 0000 [#2] SMP KASAN ---[ end trace 1cbcbec2156680bc ]--- Reported-and-tested-by: syzbot+41a1b341571f0952badb@syzkaller.appspotmail.com Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-04-24 17:37:18 +00:00
static bool sanity_check_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)
&& !f2fs_has_extra_attr(inode)) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: corrupted inode ino=%lx, run fsck to fix.",
__func__, inode->i_ino);
return false;
}
return true;
}
static int do_read_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct page *node_page;
struct f2fs_inode *ri;
projid_t i_projid;
/* Check if ino is within scope */
f2fs: give message and set need_fsck given broken node id syzbot hit the following crash on upstream commit 83beed7b2b26f232d782127792dd0cd4362fdc41 (Fri Apr 20 17:56:32 2018 +0000) Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal syzbot dashboard link: https://syzkaller.appspot.com/bug?extid=d154ec99402c6f628887 C reproducer: https://syzkaller.appspot.com/x/repro.c?id=5414336294027264 syzkaller reproducer: https://syzkaller.appspot.com/x/repro.syz?id=5471683234234368 Raw console output: https://syzkaller.appspot.com/x/log.txt?id=5436660795834368 Kernel config: https://syzkaller.appspot.com/x/.config?id=1808800213120130118 compiler: gcc (GCC) 8.0.1 20180413 (experimental) IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+d154ec99402c6f628887@syzkaller.appspotmail.com It will help syzbot understand when the bug is fixed. See footer for details. If you forward the report, please keep this part and the footer. F2FS-fs (loop0): Magic Mismatch, valid(0xf2f52010) - read(0x0) F2FS-fs (loop0): Can't find valid F2FS filesystem in 1th superblock F2FS-fs (loop0): invalid crc value ------------[ cut here ]------------ kernel BUG at fs/f2fs/node.c:1185! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 4549 Comm: syzkaller704305 Not tainted 4.17.0-rc1+ #10 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__get_node_page+0xb68/0x16e0 fs/f2fs/node.c:1185 RSP: 0018:ffff8801d960e820 EFLAGS: 00010293 RAX: ffff8801d88205c0 RBX: 0000000000000003 RCX: ffffffff82f6cc06 RDX: 0000000000000000 RSI: ffffffff82f6d5e8 RDI: 0000000000000004 RBP: ffff8801d960ec30 R08: ffff8801d88205c0 R09: ffffed003b5e46c2 R10: 0000000000000003 R11: 0000000000000003 R12: ffff8801a86e00c0 R13: 0000000000000001 R14: ffff8801a86e0530 R15: ffff8801d9745240 FS: 000000000072c880(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3d403209b8 CR3: 00000001d8f3f000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: get_node_page fs/f2fs/node.c:1237 [inline] truncate_xattr_node+0x152/0x2e0 fs/f2fs/node.c:1014 remove_inode_page+0x200/0xaf0 fs/f2fs/node.c:1039 f2fs_evict_inode+0xe86/0x1710 fs/f2fs/inode.c:547 evict+0x4a6/0x960 fs/inode.c:557 iput_final fs/inode.c:1519 [inline] iput+0x62d/0xa80 fs/inode.c:1545 f2fs_fill_super+0x5f4e/0x7bf0 fs/f2fs/super.c:2849 mount_bdev+0x30c/0x3e0 fs/super.c:1164 f2fs_mount+0x34/0x40 fs/f2fs/super.c:3020 mount_fs+0xae/0x328 fs/super.c:1267 vfs_kern_mount.part.34+0xd4/0x4d0 fs/namespace.c:1037 vfs_kern_mount fs/namespace.c:1027 [inline] do_new_mount fs/namespace.c:2518 [inline] do_mount+0x564/0x3070 fs/namespace.c:2848 ksys_mount+0x12d/0x140 fs/namespace.c:3064 __do_sys_mount fs/namespace.c:3078 [inline] __se_sys_mount fs/namespace.c:3075 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3075 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x443dea RSP: 002b:00007ffcc7882368 EFLAGS: 00000297 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000020000c00 RCX: 0000000000443dea RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffcc7882370 RBP: 0000000000000003 R08: 0000000020016a00 R09: 000000000000000a R10: 0000000000000000 R11: 0000000000000297 R12: 0000000000000004 R13: 0000000000402ce0 R14: 0000000000000000 R15: 0000000000000000 RIP: __get_node_page+0xb68/0x16e0 fs/f2fs/node.c:1185 RSP: ffff8801d960e820 ---[ end trace 4edbeb71f002bb76 ]--- Reported-and-tested-by: syzbot+d154ec99402c6f628887@syzkaller.appspotmail.com Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-04-24 05:02:31 +00:00
if (check_nid_range(sbi, inode->i_ino))
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 = SECTOR_FROM_BLOCK(le64_to_cpu(ri->i_blocks) - 1);
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;
if (f2fs_init_extent_tree(inode, &ri->i_ext))
set_page_dirty(node_page);
get_inline_info(inode, ri);
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
fi->i_extra_isize = f2fs_has_extra_attr(inode) ?
le16_to_cpu(ri->i_extra_isize) : 0;
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) {
fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size);
} else if (f2fs_has_inline_xattr(inode) ||
f2fs_has_inline_dentry(inode)) {
fi->i_inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS;
} else {
/*
* Previous inline data or directory always reserved 200 bytes
* in inode layout, even if inline_xattr is disabled. In order
* to keep inline_dentry's structure for backward compatibility,
* we get the space back only from inline_data.
*/
fi->i_inline_xattr_size = 0;
}
/* 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(inode, FI_FIRST_BLOCK_WRITTEN);
if (!need_inode_block_update(sbi, inode->i_ino))
fi->last_disk_size = inode->i_size;
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) &&
F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid))
i_projid = (projid_t)le32_to_cpu(ri->i_projid);
else
i_projid = F2FS_DEF_PROJID;
fi->i_projid = make_kprojid(&init_user_ns, i_projid);
if (f2fs_has_extra_attr(inode) && f2fs_sb_has_inode_crtime(sbi->sb) &&
F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) {
fi->i_crtime.tv_sec = le64_to_cpu(ri->i_crtime);
fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec);
}
F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
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;
f2fs: avoid bug_on on corrupted inode syzbot has tested the proposed patch but the reproducer still triggered crash: kernel BUG at fs/f2fs/inode.c:LINE! F2FS-fs (loop1): invalid crc value F2FS-fs (loop5): Magic Mismatch, valid(0xf2f52010) - read(0x0) F2FS-fs (loop5): Can't find valid F2FS filesystem in 1th superblock F2FS-fs (loop5): invalid crc value ------------[ cut here ]------------ kernel BUG at fs/f2fs/inode.c:238! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 4886 Comm: syz-executor1 Not tainted 4.17.0-rc1+ #1 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:do_read_inode fs/f2fs/inode.c:238 [inline] RIP: 0010:f2fs_iget+0x3307/0x3ca0 fs/f2fs/inode.c:313 RSP: 0018:ffff8801c44a70e8 EFLAGS: 00010293 RAX: ffff8801ce208040 RBX: ffff8801b3621080 RCX: ffffffff82eace18 F2FS-fs (loop2): Magic Mismatch, valid(0xf2f52010) - read(0x0) RDX: 0000000000000000 RSI: ffffffff82eaf047 RDI: 0000000000000007 RBP: ffff8801c44a7410 R08: ffff8801ce208040 R09: ffffed0039ee4176 R10: ffffed0039ee4176 R11: ffff8801cf720bb7 R12: ffff8801c0efa000 R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f753aa9d700(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 ------------[ cut here ]------------ CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 kernel BUG at fs/f2fs/inode.c:238! CR2: 0000000001b03018 CR3: 00000001c8b74000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_fill_super+0x4377/0x7bf0 fs/f2fs/super.c:2842 mount_bdev+0x30c/0x3e0 fs/super.c:1165 f2fs_mount+0x34/0x40 fs/f2fs/super.c:3020 mount_fs+0xae/0x328 fs/super.c:1268 vfs_kern_mount.part.34+0xd4/0x4d0 fs/namespace.c:1037 vfs_kern_mount fs/namespace.c:1027 [inline] do_new_mount fs/namespace.c:2517 [inline] do_mount+0x564/0x3070 fs/namespace.c:2847 ksys_mount+0x12d/0x140 fs/namespace.c:3063 __do_sys_mount fs/namespace.c:3077 [inline] __se_sys_mount fs/namespace.c:3074 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3074 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x457daa RSP: 002b:00007f753aa9cba8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 0000000000457daa RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007f753aa9cbf0 RBP: 0000000000000064 R08: 0000000020016a00 R09: 0000000020000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 0000000000000064 R14: 00000000006fcb80 R15: 0000000000000000 RIP: do_read_inode fs/f2fs/inode.c:238 [inline] RSP: ffff8801c44a70e8 RIP: f2fs_iget+0x3307/0x3ca0 fs/f2fs/inode.c:313 RSP: ffff8801c44a70e8 invalid opcode: 0000 [#2] SMP KASAN ---[ end trace 1cbcbec2156680bc ]--- Reported-and-tested-by: syzbot+41a1b341571f0952badb@syzkaller.appspotmail.com Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-04-24 17:37:18 +00:00
if (!sanity_check_inode(inode)) {
ret = -EINVAL;
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_NOFS);
} else if (ino == F2FS_META_INO(sbi)) {
inode->i_mapping->a_ops = &f2fs_meta_aops;
mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
} 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;
inode_nohighmem(inode);
} 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_nohighmem(inode);
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;
}
f2fs_set_inode_flags(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);
}
struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
{
struct inode *inode;
retry:
inode = f2fs_iget(sb, ino);
if (IS_ERR(inode)) {
if (PTR_ERR(inode) == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
}
}
return inode;
}
void update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
struct extent_tree *et = F2FS_I(inode)->extent_tree;
f2fs_wait_on_page_writeback(node_page, NODE, true);
set_page_dirty(node_page);
f2fs_inode_synced(inode);
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(SECTOR_TO_BLOCK(inode->i_blocks) + 1);
if (et) {
read_lock(&et->lock);
set_raw_extent(&et->largest, &ri->i_ext);
read_unlock(&et->lock);
} else {
memset(&ri->i_ext, 0, sizeof(ri->i_ext));
}
set_raw_inline(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;
if (f2fs_has_extra_attr(inode)) {
f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-18 16:19:06 +00:00
ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize);
f2fs: support flexible inline xattr size Now, in product, more and more features based on file encryption were introduced, their demand of xattr space is increasing, however, inline xattr has fixed-size of 200 bytes, once inline xattr space is full, new increased xattr data would occupy additional xattr block which may bring us more space usage and performance regression during persisting. In order to resolve above issue, it's better to expand inline xattr size flexibly according to user's requirement. So this patch introduces new filesystem feature 'flexible inline xattr', and new mount option 'inline_xattr_size=%u', once mkfs enables the feature, we can use the option to make f2fs supporting flexible inline xattr size. To support this feature, we add extra attribute i_inline_xattr_size in inode layout, indicating that how many space inline xattr borrows from block address mapping space in inode layout, by this, we can easily locate and store flexible-sized inline xattr data in inode. Inode disk layout: +----------------------+ | .i_mode | | ... | | .i_ext | +----------------------+ | .i_extra_isize | | .i_inline_xattr_size |-----------+ | ... | | +----------------------+ | | .i_addr | | | - block address or | | | - inline data | | +----------------------+<---+ v | inline xattr | +---inline xattr range +----------------------+<---+ | .i_nid | +----------------------+ | node_footer | | (nid, ino, offset) | +----------------------+ Note that, we have to cnosider backward compatibility which reserved inline_data space, 200 bytes, all the time, reported by Sheng Yong. Previous inline data or directory always reserved 200 bytes in inode layout, even if inline_xattr is disabled. In order to keep inline_dentry's structure for backward compatibility, we get the space back only from inline_data. Signed-off-by: Chao Yu <yuchao0@huawei.com> Reported-by: Sheng Yong <shengyong1@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-09-06 13:59:50 +00:00
if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode)->sb))
ri->i_inline_xattr_size =
cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size);
if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) &&
F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
i_projid)) {
projid_t i_projid;
i_projid = from_kprojid(&init_user_ns,
F2FS_I(inode)->i_projid);
ri->i_projid = cpu_to_le32(i_projid);
}
if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)->sb) &&
F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize,
i_crtime)) {
ri->i_crtime =
cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec);
ri->i_crtime_nsec =
cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec);
}
}
__set_inode_rdev(inode, ri);
/* deleted inode */
if (inode->i_nlink == 0)
clear_inline_node(node_page);
F2FS_I(inode)->i_disk_time[0] = inode->i_atime;
F2FS_I(inode)->i_disk_time[1] = inode->i_ctime;
F2FS_I(inode)->i_disk_time[2] = inode->i_mtime;
F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime;
}
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, false);
}
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(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 balance fs here to prevent from producing dirty node pages
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
* during the urgent cleaning time when runing out of free sections.
*/
update_inode_page(inode);
if (wbc && wbc->nr_to_write)
f2fs_balance_fs(sbi, true);
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);
nid_t xnid = F2FS_I(inode)->i_xattr_nid;
int err = 0;
/* some remained atomic pages should discarded */
if (f2fs_is_atomic_file(inode))
drop_inmem_pages(inode);
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_inode(inode);
f2fs_destroy_extent_tree(inode);
if (inode->i_nlink || is_bad_inode(inode))
goto no_delete;
dquot_initialize(inode);
remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
remove_ino_entry(sbi, inode->i_ino, FLUSH_INO);
sb_start_intwrite(inode->i_sb);
set_inode_flag(inode, FI_NO_ALLOC);
i_size_write(inode, 0);
retry:
if (F2FS_HAS_BLOCKS(inode))
err = f2fs_truncate(inode);
#ifdef CONFIG_F2FS_FAULT_INJECTION
if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
f2fs_show_injection_info(FAULT_EVICT_INODE);
err = -EIO;
}
#endif
if (!err) {
f2fs_lock_op(sbi);
err = remove_inode_page(inode);
f2fs_unlock_op(sbi);
if (err == -ENOENT)
err = 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
/* give more chances, if ENOMEM case */
if (err == -ENOMEM) {
err = 0;
goto retry;
}
if (err)
update_inode_page(inode);
dquot_free_inode(inode);
sb_end_intwrite(inode->i_sb);
no_delete:
dquot_drop(inode);
stat_dec_inline_xattr(inode);
stat_dec_inline_dir(inode);
stat_dec_inline_inode(inode);
if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG)))
f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE));
else
f2fs_inode_synced(inode);
/* ino == 0, if f2fs_new_inode() was failed t*/
if (inode->i_ino)
invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
inode->i_ino);
if (xnid)
invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
if (inode->i_nlink) {
if (is_inode_flag_set(inode, FI_APPEND_WRITE))
add_ino_entry(sbi, inode->i_ino, APPEND_INO);
if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
}
if (is_inode_flag_set(inode, FI_FREE_NID)) {
alloc_nid_failed(sbi, inode->i_ino);
clear_inode_flag(inode, FI_FREE_NID);
} else {
f2fs: give message and set need_fsck given broken node id syzbot hit the following crash on upstream commit 83beed7b2b26f232d782127792dd0cd4362fdc41 (Fri Apr 20 17:56:32 2018 +0000) Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal syzbot dashboard link: https://syzkaller.appspot.com/bug?extid=d154ec99402c6f628887 C reproducer: https://syzkaller.appspot.com/x/repro.c?id=5414336294027264 syzkaller reproducer: https://syzkaller.appspot.com/x/repro.syz?id=5471683234234368 Raw console output: https://syzkaller.appspot.com/x/log.txt?id=5436660795834368 Kernel config: https://syzkaller.appspot.com/x/.config?id=1808800213120130118 compiler: gcc (GCC) 8.0.1 20180413 (experimental) IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+d154ec99402c6f628887@syzkaller.appspotmail.com It will help syzbot understand when the bug is fixed. See footer for details. If you forward the report, please keep this part and the footer. F2FS-fs (loop0): Magic Mismatch, valid(0xf2f52010) - read(0x0) F2FS-fs (loop0): Can't find valid F2FS filesystem in 1th superblock F2FS-fs (loop0): invalid crc value ------------[ cut here ]------------ kernel BUG at fs/f2fs/node.c:1185! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 4549 Comm: syzkaller704305 Not tainted 4.17.0-rc1+ #10 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__get_node_page+0xb68/0x16e0 fs/f2fs/node.c:1185 RSP: 0018:ffff8801d960e820 EFLAGS: 00010293 RAX: ffff8801d88205c0 RBX: 0000000000000003 RCX: ffffffff82f6cc06 RDX: 0000000000000000 RSI: ffffffff82f6d5e8 RDI: 0000000000000004 RBP: ffff8801d960ec30 R08: ffff8801d88205c0 R09: ffffed003b5e46c2 R10: 0000000000000003 R11: 0000000000000003 R12: ffff8801a86e00c0 R13: 0000000000000001 R14: ffff8801a86e0530 R15: ffff8801d9745240 FS: 000000000072c880(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3d403209b8 CR3: 00000001d8f3f000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: get_node_page fs/f2fs/node.c:1237 [inline] truncate_xattr_node+0x152/0x2e0 fs/f2fs/node.c:1014 remove_inode_page+0x200/0xaf0 fs/f2fs/node.c:1039 f2fs_evict_inode+0xe86/0x1710 fs/f2fs/inode.c:547 evict+0x4a6/0x960 fs/inode.c:557 iput_final fs/inode.c:1519 [inline] iput+0x62d/0xa80 fs/inode.c:1545 f2fs_fill_super+0x5f4e/0x7bf0 fs/f2fs/super.c:2849 mount_bdev+0x30c/0x3e0 fs/super.c:1164 f2fs_mount+0x34/0x40 fs/f2fs/super.c:3020 mount_fs+0xae/0x328 fs/super.c:1267 vfs_kern_mount.part.34+0xd4/0x4d0 fs/namespace.c:1037 vfs_kern_mount fs/namespace.c:1027 [inline] do_new_mount fs/namespace.c:2518 [inline] do_mount+0x564/0x3070 fs/namespace.c:2848 ksys_mount+0x12d/0x140 fs/namespace.c:3064 __do_sys_mount fs/namespace.c:3078 [inline] __se_sys_mount fs/namespace.c:3075 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3075 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x443dea RSP: 002b:00007ffcc7882368 EFLAGS: 00000297 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000020000c00 RCX: 0000000000443dea RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffcc7882370 RBP: 0000000000000003 R08: 0000000020016a00 R09: 000000000000000a R10: 0000000000000000 R11: 0000000000000297 R12: 0000000000000004 R13: 0000000000402ce0 R14: 0000000000000000 R15: 0000000000000000 RIP: __get_node_page+0xb68/0x16e0 fs/f2fs/node.c:1185 RSP: ffff8801d960e820 ---[ end trace 4edbeb71f002bb76 ]--- Reported-and-tested-by: syzbot+d154ec99402c6f628887@syzkaller.appspotmail.com Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-04-24 05:02:31 +00:00
/*
* If xattr nid is corrupted, we can reach out error condition,
* err & !exist_written_data(sbi, inode->i_ino, ORPHAN_INO)).
* In that case, check_nid_range() is enough to give a clue.
*/
}
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:
fscrypt_put_encryption_info(inode);
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);
struct node_info ni;
/*
* clear nlink of inode in order to release resource of inode
* immediately.
*/
clear_nlink(inode);
/*
* we must call this to avoid inode being remained as dirty, resulting
* in a panic when flushing dirty inodes in gdirty_list.
*/
update_inode_page(inode);
f2fs_inode_synced(inode);
/* don't make bad inode, since it becomes a regular file. */
unlock_new_inode(inode);
/*
* 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.
*/
get_node_info(sbi, inode->i_ino, &ni);
if (ni.blk_addr != NULL_ADDR) {
int err = acquire_orphan_inode(sbi);
if (err) {
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"Too many orphan inodes, run fsck to fix.");
} else {
add_orphan_inode(inode);
}
alloc_nid_done(sbi, inode->i_ino);
} else {
set_inode_flag(inode, FI_FREE_NID);
}
f2fs_unlock_op(sbi);
/* iput will drop the inode object */
iput(inode);
}