OpenCloudOS-Kernel/fs/f2fs/inline.c

670 lines
16 KiB
C
Raw Normal View History

/*
* fs/f2fs/inline.c
* Copyright (c) 2013, Intel Corporation
* Authors: Huajun Li <huajun.li@intel.com>
* Haicheng Li <haicheng.li@intel.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 "f2fs.h"
#include "node.h"
bool f2fs_may_inline_data(struct inode *inode)
{
if (f2fs_is_atomic_file(inode))
return false;
if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
return false;
if (i_size_read(inode) > MAX_INLINE_DATA)
return false;
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
return false;
return true;
}
bool f2fs_may_inline_dentry(struct inode *inode)
{
if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY))
return false;
if (!S_ISDIR(inode->i_mode))
return false;
return true;
}
void read_inline_data(struct page *page, struct page *ipage)
{
void *src_addr, *dst_addr;
if (PageUptodate(page))
return;
f2fs_bug_on(F2FS_P_SB(page), page->index);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(ipage);
dst_addr = kmap_atomic(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
flush_dcache_page(page);
kunmap_atomic(dst_addr);
if (!PageUptodate(page))
SetPageUptodate(page);
}
void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from)
{
void *addr;
if (from >= MAX_INLINE_DATA)
return;
addr = inline_data_addr(ipage);
f2fs_wait_on_page_writeback(ipage, NODE, true);
memset(addr + from, 0, MAX_INLINE_DATA - from);
set_page_dirty(ipage);
if (from == 0)
clear_inode_flag(inode, FI_DATA_EXIST);
}
int f2fs_read_inline_data(struct inode *inode, struct page *page)
{
struct page *ipage;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
unlock_page(page);
return PTR_ERR(ipage);
}
if (!f2fs_has_inline_data(inode)) {
f2fs_put_page(ipage, 1);
return -EAGAIN;
}
if (page->index)
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
zero_user_segment(page, 0, PAGE_SIZE);
else
read_inline_data(page, ipage);
if (!PageUptodate(page))
SetPageUptodate(page);
f2fs_put_page(ipage, 1);
unlock_page(page);
return 0;
}
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
.op = REQ_OP_WRITE,
.op_flags = REQ_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
int dirty, err;
if (!f2fs_exist_data(dn->inode))
goto clear_out;
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
read_inline_data(page, dn->inode_page);
f2fs: call set_page_dirty to attach i_wb for cgroup The cgroup attaches inode->i_wb via mark_inode_dirty and when set_page_writeback is called, __inc_wb_stat() updates i_wb's stat. So, we need to explicitly call set_page_dirty->__mark_inode_dirty in prior to any writebacking pages. This patch should resolve the following kernel panic reported by Andreas Reis. https://bugzilla.kernel.org/show_bug.cgi?id=101801 --- Comment #2 from Andreas Reis <andreas.reis@gmail.com> --- BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8 IP: [<ffffffff8149deea>] __percpu_counter_add+0x1a/0x90 PGD 2951ff067 PUD 2df43f067 PMD 0 Oops: 0000 [#1] PREEMPT SMP Modules linked in: CPU: 7 PID: 10356 Comm: gcc Tainted: G W 4.2.0-1-cu #1 Hardware name: Gigabyte Technology Co., Ltd. G1.Sniper M5/G1.Sniper M5, BIOS T01 02/03/2015 task: ffff880295044f80 ti: ffff880295140000 task.ti: ffff880295140000 RIP: 0010:[<ffffffff8149deea>] [<ffffffff8149deea>] __percpu_counter_add+0x1a/0x90 RSP: 0018:ffff880295143ac8 EFLAGS: 00010082 RAX: 0000000000000003 RBX: ffffea000a526d40 RCX: 0000000000000001 RDX: 0000000000000020 RSI: 0000000000000001 RDI: 0000000000000088 RBP: ffff880295143ae8 R08: 0000000000000000 R09: ffff88008f69bb30 R10: 00000000fffffffa R11: 0000000000000000 R12: 0000000000000088 R13: 0000000000000001 R14: ffff88041d099000 R15: ffff880084a205d0 FS: 00007f8549374700(0000) GS:ffff88042f3c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000a8 CR3: 000000033e1d5000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Stack: 0000000000000000 ffffea000a526d40 ffff880084a20738 ffff880084a20750 ffff880295143b48 ffffffff811cc91e ffff880000000000 0000000000000296 0000000000000000 ffff880417090198 0000000000000000 ffffea000a526d40 Call Trace: [<ffffffff811cc91e>] __test_set_page_writeback+0xde/0x1d0 [<ffffffff813fee87>] do_write_data_page+0xe7/0x3a0 [<ffffffff813faeea>] gc_data_segment+0x5aa/0x640 [<ffffffff813fb0b8>] do_garbage_collect+0x138/0x150 [<ffffffff813fb3fe>] f2fs_gc+0x1be/0x3e0 [<ffffffff81405541>] f2fs_balance_fs+0x81/0x90 [<ffffffff813ee357>] f2fs_unlink+0x47/0x1d0 [<ffffffff81239329>] vfs_unlink+0x109/0x1b0 [<ffffffff8123e3d7>] do_unlinkat+0x287/0x2c0 [<ffffffff8123ebc6>] SyS_unlink+0x16/0x20 [<ffffffff81942e2e>] entry_SYSCALL_64_fastpath+0x12/0x71 Code: 41 5e 5d c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 55 48 89 e5 41 55 49 89 f5 41 54 49 89 fc 53 48 83 ec 08 65 ff 05 e6 d9 b6 7e <48> 8b 47 20 48 63 ca 65 8b 18 48 63 db 48 01 f3 48 39 cb 7d 0a RIP [<ffffffff8149deea>] __percpu_counter_add+0x1a/0x90 RSP <ffff880295143ac8> CR2: 00000000000000a8 ---[ end trace 5132449a58ed93a3 ]--- note: gcc[10356] exited with preempt_count 2 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-07-25 15:29:17 +08:00
set_page_dirty(page);
/* clear dirty state */
dirty = clear_page_dirty_for_io(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
fio.old_blkaddr = dn->data_blkaddr;
set_inode_flag(dn->inode, FI_HOT_DATA);
write_data_page(dn, &fio);
f2fs_wait_on_page_writeback(page, DATA, true);
if (dirty) {
inode_dec_dirty_pages(dn->inode);
remove_dirty_inode(dn->inode);
}
/* this converted inline_data should be recovered. */
set_inode_flag(dn->inode, FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode, dn->inode_page, 0);
clear_inline_node(dn->inode_page);
clear_out:
stat_dec_inline_inode(dn->inode);
clear_inode_flag(dn->inode, FI_INLINE_DATA);
f2fs_put_dnode(dn);
return 0;
}
int f2fs_convert_inline_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
struct page *ipage, *page;
int err = 0;
if (!f2fs_has_inline_data(inode))
return 0;
page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
if (!page)
return -ENOMEM;
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode))
err = f2fs_convert_inline_page(&dn, page);
f2fs_put_dnode(&dn);
out:
f2fs_unlock_op(sbi);
f2fs_put_page(page, 1);
f2fs_balance_fs(sbi, dn.node_changed);
return err;
}
int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
if (!f2fs_has_inline_data(inode)) {
f2fs_put_dnode(&dn);
return -EAGAIN;
}
f2fs_bug_on(F2FS_I_SB(inode), page->index);
f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
src_addr = kmap_atomic(page);
dst_addr = inline_data_addr(dn.inode_page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap_atomic(src_addr);
set_page_dirty(dn.inode_page);
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
clear_inline_node(dn.inode_page);
f2fs_put_dnode(&dn);
return 0;
}
bool recover_inline_data(struct inode *inode, struct page *npage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode *ri = NULL;
void *src_addr, *dst_addr;
struct page *ipage;
/*
* The inline_data recovery policy is as follows.
* [prev.] [next] of inline_data flag
* o o -> recover inline_data
* o x -> remove inline_data, and then recover data blocks
* x o -> remove inline_data, and then recover inline_data
* x x -> recover data blocks
*/
if (IS_INODE(npage))
ri = F2FS_INODE(npage);
if (f2fs_has_inline_data(inode) &&
ri && (ri->i_inline & F2FS_INLINE_DATA)) {
process_inline:
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
f2fs_wait_on_page_writeback(ipage, NODE, true);
src_addr = inline_data_addr(npage);
dst_addr = inline_data_addr(ipage);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
set_inode_flag(inode, FI_INLINE_DATA);
set_inode_flag(inode, FI_DATA_EXIST);
set_page_dirty(ipage);
f2fs_put_page(ipage, 1);
return true;
}
if (f2fs_has_inline_data(inode)) {
ipage = get_node_page(sbi, inode->i_ino);
f2fs_bug_on(sbi, IS_ERR(ipage));
truncate_inline_inode(inode, ipage, 0);
clear_inode_flag(inode, FI_INLINE_DATA);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
if (truncate_blocks(inode, 0, false))
return false;
goto process_inline;
}
return false;
}
struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
struct fscrypt_name *fname, struct page **res_page)
{
struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
struct f2fs_inline_dentry *inline_dentry;
struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
struct f2fs_dir_entry *de;
struct f2fs_dentry_ptr d;
struct page *ipage;
f2fs_hash_t namehash;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage)) {
*res_page = ipage;
return NULL;
}
namehash = f2fs_dentry_hash(&name, fname);
inline_dentry = inline_data_addr(ipage);
make_dentry_ptr_inline(NULL, &d, inline_dentry);
de = find_target_dentry(fname, namehash, NULL, &d);
unlock_page(ipage);
if (de)
*res_page = ipage;
else
f2fs_put_page(ipage, 0);
return de;
}
int make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage)
{
struct f2fs_inline_dentry *inline_dentry;
struct f2fs_dentry_ptr d;
inline_dentry = inline_data_addr(ipage);
make_dentry_ptr_inline(NULL, &d, inline_dentry);
do_make_empty_dir(inode, parent, &d);
set_page_dirty(ipage);
/* update i_size to MAX_INLINE_DATA */
if (i_size_read(inode) < MAX_INLINE_DATA)
f2fs_i_size_write(inode, MAX_INLINE_DATA);
return 0;
}
/*
* NOTE: ipage is grabbed by caller, but if any error occurs, we should
* release ipage in this function.
*/
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct page *page;
struct dnode_of_data dn;
struct f2fs_dentry_block *dentry_blk;
int err;
page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
if (!page) {
f2fs_put_page(ipage, 1);
return -ENOMEM;
}
set_new_dnode(&dn, dir, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
if (err)
goto out;
f2fs_wait_on_page_writeback(page, DATA, true);
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
dentry_blk = kmap_atomic(page);
/* copy data from inline dentry block to new dentry block */
memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap,
INLINE_DENTRY_BITMAP_SIZE);
memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0,
SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE);
/*
* we do not need to zero out remainder part of dentry and filename
* field, since we have used bitmap for marking the usage status of
* them, besides, we can also ignore copying/zeroing reserved space
* of dentry block, because them haven't been used so far.
*/
memcpy(dentry_blk->dentry, inline_dentry->dentry,
sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY);
memcpy(dentry_blk->filename, inline_dentry->filename,
NR_INLINE_DENTRY * F2FS_SLOT_LEN);
kunmap_atomic(dentry_blk);
if (!PageUptodate(page))
SetPageUptodate(page);
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
truncate_inline_inode(dir, ipage, 0);
stat_dec_inline_dir(dir);
clear_inode_flag(dir, FI_INLINE_DENTRY);
f2fs_i_depth_write(dir, 1);
if (i_size_read(dir) < PAGE_SIZE)
f2fs_i_size_write(dir, PAGE_SIZE);
out:
f2fs_put_page(page, 1);
return err;
}
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
static int f2fs_add_inline_entries(struct inode *dir,
struct f2fs_inline_dentry *inline_dentry)
{
struct f2fs_dentry_ptr d;
unsigned long bit_pos = 0;
int err = 0;
make_dentry_ptr_inline(NULL, &d, inline_dentry);
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
while (bit_pos < d.max) {
struct f2fs_dir_entry *de;
struct qstr new_name;
nid_t ino;
umode_t fake_mode;
if (!test_bit_le(bit_pos, d.bitmap)) {
bit_pos++;
continue;
}
de = &d.dentry[bit_pos];
if (unlikely(!de->name_len)) {
bit_pos++;
continue;
}
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
new_name.name = d.filename[bit_pos];
new_name.len = le16_to_cpu(de->name_len);
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
ino = le32_to_cpu(de->ino);
fake_mode = get_de_type(de) << S_SHIFT;
err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL,
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
ino, fake_mode);
if (err)
goto punch_dentry_pages;
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
}
return 0;
punch_dentry_pages:
truncate_inode_pages(&dir->i_data, 0);
truncate_blocks(dir, 0, false);
remove_dirty_inode(dir);
return err;
}
static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
struct f2fs_inline_dentry *backup_dentry;
int err;
backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir),
sizeof(struct f2fs_inline_dentry), GFP_F2FS_ZERO);
if (!backup_dentry) {
f2fs_put_page(ipage, 1);
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
return -ENOMEM;
}
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
truncate_inline_inode(dir, ipage, 0);
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
unlock_page(ipage);
err = f2fs_add_inline_entries(dir, backup_dentry);
if (err)
goto recover;
lock_page(ipage);
stat_dec_inline_dir(dir);
clear_inode_flag(dir, FI_INLINE_DENTRY);
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
kfree(backup_dentry);
return 0;
recover:
lock_page(ipage);
memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
f2fs_i_depth_write(dir, 0);
f2fs_i_size_write(dir, MAX_INLINE_DATA);
set_page_dirty(ipage);
f2fs: fix to convert inline directory correctly With below serials, we will lose parts of dirents: 1) mount f2fs with inline_dentry option 2) echo 1 > /sys/fs/f2fs/sdX/dir_level 3) mkdir dir 4) touch 180 files named [1-180] in dir 5) touch 181 in dir 6) echo 3 > /proc/sys/vm/drop_caches 7) ll dir ls: cannot access 2: No such file or directory ls: cannot access 4: No such file or directory ls: cannot access 5: No such file or directory ls: cannot access 6: No such file or directory ls: cannot access 8: No such file or directory ls: cannot access 9: No such file or directory ... total 360 drwxr-xr-x 2 root root 4096 Feb 19 15:12 ./ drwxr-xr-x 3 root root 4096 Feb 19 15:11 ../ -rw-r--r-- 1 root root 0 Feb 19 15:12 1 -rw-r--r-- 1 root root 0 Feb 19 15:12 10 -rw-r--r-- 1 root root 0 Feb 19 15:12 100 -????????? ? ? ? ? ? 101 -????????? ? ? ? ? ? 102 -????????? ? ? ? ? ? 103 ... The reason is: when doing the inline dir conversion, we didn't consider that directory has hierarchical hash structure which can be configured through sysfs interface 'dir_level'. By default, dir_level of directory inode is 0, it means we have one bucket in hash table located in first level, all dirents will be hashed in this bucket, so it has no problem for us to do the duplication simply between inline dentry page and converted normal dentry page. However, if we configured dir_level with the value N (greater than 0), it will expand the bucket number of first level hash table by 2^N - 1, it hashs dirents into different buckets according their hash value, if we still move all dirents to first bucket, it makes incorrent locating for inline dirents, the result is, although we can iterate all dirents through ->readdir, we can't stat some of them in ->lookup which based on hash table searching. This patch fixes this issue by rehashing dirents into correct position when converting inline directory. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-02-22 18:29:18 +08:00
f2fs_put_page(ipage, 1);
kfree(backup_dentry);
return err;
}
static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
struct f2fs_inline_dentry *inline_dentry)
{
if (!F2FS_I(dir)->i_dir_level)
return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
else
return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
}
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
const struct qstr *orig_name,
struct inode *inode, nid_t ino, umode_t mode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
unsigned int bit_pos;
f2fs_hash_t name_hash;
struct f2fs_inline_dentry *inline_dentry = NULL;
struct f2fs_dentry_ptr d;
int slots = GET_DENTRY_SLOTS(new_name->len);
struct page *page = NULL;
int err = 0;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
inline_dentry = inline_data_addr(ipage);
bit_pos = room_for_filename(&inline_dentry->dentry_bitmap,
slots, NR_INLINE_DENTRY);
if (bit_pos >= NR_INLINE_DENTRY) {
err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
if (err)
return err;
err = -EAGAIN;
goto out;
}
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, new_name,
orig_name, ipage);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
}
f2fs: avoid deadlock on init_inode_metadata Previously, init_inode_metadata does not hold any parent directory's inode page. So, f2fs_init_acl can grab its parent inode page without any problem. But, when we use inline_dentry, that page is grabbed during f2fs_add_link, so that we can fall into deadlock condition like below. INFO: task mknod:11006 blocked for more than 120 seconds. Tainted: G OE 3.17.0-rc1+ #13 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mknod D ffff88003fc94580 0 11006 11004 0x00000000 ffff880007717b10 0000000000000002 ffff88003c323220 ffff880007717fd8 0000000000014580 0000000000014580 ffff88003daecb30 ffff88003c323220 ffff88003fc94e80 ffff88003ffbb4e8 ffff880007717ba0 0000000000000002 Call Trace: [<ffffffff8173dc40>] ? bit_wait+0x50/0x50 [<ffffffff8173d4cd>] io_schedule+0x9d/0x130 [<ffffffff8173dc6c>] bit_wait_io+0x2c/0x50 [<ffffffff8173da3b>] __wait_on_bit_lock+0x4b/0xb0 [<ffffffff811640a7>] __lock_page+0x67/0x70 [<ffffffff810acf50>] ? autoremove_wake_function+0x40/0x40 [<ffffffff811652cc>] pagecache_get_page+0x14c/0x1e0 [<ffffffffa029afa9>] get_node_page+0x59/0x130 [f2fs] [<ffffffffa02a63ad>] read_all_xattrs+0x24d/0x430 [f2fs] [<ffffffffa02a6ca2>] f2fs_getxattr+0x52/0xe0 [f2fs] [<ffffffffa02a7481>] f2fs_get_acl+0x41/0x2d0 [f2fs] [<ffffffff8122d847>] get_acl+0x47/0x70 [<ffffffff8122db5a>] posix_acl_create+0x5a/0x150 [<ffffffffa02a7759>] f2fs_init_acl+0x29/0xcb [f2fs] [<ffffffffa0286a8d>] init_inode_metadata+0x5d/0x340 [f2fs] [<ffffffffa029253a>] f2fs_add_inline_entry+0x12a/0x2e0 [f2fs] [<ffffffffa0286ea5>] __f2fs_add_link+0x45/0x4a0 [f2fs] [<ffffffffa028b5b6>] ? f2fs_new_inode+0x146/0x220 [f2fs] [<ffffffffa028b816>] f2fs_mknod+0x86/0xf0 [f2fs] [<ffffffff811e3ec1>] vfs_mknod+0xe1/0x160 [<ffffffff811e4b26>] SyS_mknod+0x1f6/0x200 [<ffffffff81741d7f>] tracesys+0xe1/0xe6 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-10-14 10:42:53 +08:00
f2fs_wait_on_page_writeback(ipage, NODE, true);
name_hash = f2fs_dentry_hash(new_name, NULL);
make_dentry_ptr_inline(NULL, &d, inline_dentry);
f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
set_page_dirty(ipage);
/* we don't need to mark_inode_dirty now */
if (inode) {
f2fs_i_pino_write(inode, dir->i_ino);
f2fs_put_page(page, 1);
}
update_parent_metadata(dir, inode, 0);
fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
out:
f2fs_put_page(ipage, 1);
return err;
}
void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
struct inode *dir, struct inode *inode)
{
struct f2fs_inline_dentry *inline_dentry;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
unsigned int bit_pos;
int i;
lock_page(page);
f2fs_wait_on_page_writeback(page, NODE, true);
inline_dentry = inline_data_addr(page);
bit_pos = dentry - inline_dentry->dentry;
for (i = 0; i < slots; i++)
__clear_bit_le(bit_pos + i,
&inline_dentry->dentry_bitmap);
set_page_dirty(page);
f2fs_put_page(page, 1);
dir->i_ctime = dir->i_mtime = current_time(dir);
f2fs_mark_inode_dirty_sync(dir, false);
if (inode)
f2fs_drop_nlink(dir, inode);
}
bool f2fs_empty_inline_dir(struct inode *dir)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
unsigned int bit_pos = 2;
struct f2fs_inline_dentry *inline_dentry;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return false;
inline_dentry = inline_data_addr(ipage);
bit_pos = find_next_bit_le(&inline_dentry->dentry_bitmap,
NR_INLINE_DENTRY,
bit_pos);
f2fs_put_page(ipage, 1);
if (bit_pos < NR_INLINE_DENTRY)
return false;
return true;
}
int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
struct fscrypt_str *fstr)
{
struct inode *inode = file_inode(file);
struct f2fs_inline_dentry *inline_dentry = NULL;
struct page *ipage = NULL;
struct f2fs_dentry_ptr d;
int err;
if (ctx->pos == NR_INLINE_DENTRY)
return 0;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
inline_dentry = inline_data_addr(ipage);
make_dentry_ptr_inline(inode, &d, inline_dentry);
err = f2fs_fill_dentries(ctx, &d, 0, fstr);
if (!err)
ctx->pos = NR_INLINE_DENTRY;
f2fs_put_page(ipage, 1);
return err < 0 ? err : 0;
}
int f2fs_inline_data_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, __u64 start, __u64 len)
{
__u64 byteaddr, ilen;
__u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED |
FIEMAP_EXTENT_LAST;
struct node_info ni;
struct page *ipage;
int err = 0;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
if (!f2fs_has_inline_data(inode)) {
err = -EAGAIN;
goto out;
}
ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode));
if (start >= ilen)
goto out;
if (start + len < ilen)
ilen = start + len;
ilen -= start;
get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage);
err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
out:
f2fs_put_page(ipage, 1);
return err;
}