linux/fs/f2fs/inline.c

556 lines
13 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"
bool f2fs_may_inline_data(struct inode *inode)
{
if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
return false;
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);
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_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);
SetPageUptodate(page);
}
bool truncate_inline_inode(struct page *ipage, u64 from)
{
void *addr;
if (from >= MAX_INLINE_DATA)
return false;
addr = inline_data_addr(ipage);
f2fs_wait_on_page_writeback(ipage, NODE);
memset(addr + from, 0, MAX_INLINE_DATA - from);
return true;
}
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)
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
else
read_inline_data(page, ipage);
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)
{
void *src_addr, *dst_addr;
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
int dirty, err;
f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
if (!f2fs_exist_data(dn->inode))
goto clear_out;
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
f2fs_wait_on_page_writeback(page, DATA);
if (PageUptodate(page))
goto no_update;
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(dn->inode_page);
dst_addr = kmap_atomic(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
flush_dcache_page(page);
kunmap_atomic(dst_addr);
SetPageUptodate(page);
no_update:
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.blk_addr = dn->data_blkaddr;
write_data_page(dn, &fio);
set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
f2fs_wait_on_page_writeback(page, DATA);
if (dirty)
inode_dec_dirty_pages(dn->inode);
/* this converted inline_data should be recovered. */
set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode_page, 0);
clear_out:
stat_dec_inline_inode(dn->inode);
f2fs_clear_inline_inode(dn->inode);
sync_inode_page(dn);
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;
page = grab_cache_page(inode->i_mapping, 0);
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);
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);
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_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
sync_inode_page(&dn);
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);
src_addr = inline_data_addr(npage);
dst_addr = inline_data_addr(ipage);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
update_inode(inode, 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(ipage, 0);
f2fs_clear_inline_inode(inode);
update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
truncate_blocks(inode, 0, false);
goto process_inline;
}
return false;
}
struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
struct f2fs_filename *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))
return NULL;
namehash = f2fs_dentry_hash(&name);
inline_dentry = inline_data_addr(ipage);
make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
de = find_target_dentry(fname, namehash, NULL, &d);
unlock_page(ipage);
if (de)
*res_page = ipage;
else
f2fs_put_page(ipage, 0);
/*
* For the most part, it should be a bug when name_len is zero.
* We stop here for figuring out where the bugs has occurred.
*/
f2fs_bug_on(sbi, d.max < 0);
return de;
}
struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *dir,
struct page **p)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct page *ipage;
struct f2fs_dir_entry *de;
struct f2fs_inline_dentry *dentry_blk;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return NULL;
dentry_blk = inline_data_addr(ipage);
de = &dentry_blk->dentry[1];
*p = ipage;
unlock_page(ipage);
return de;
}
int make_empty_inline_dir(struct inode *inode, struct inode *parent,
struct page *ipage)
{
struct f2fs_inline_dentry *dentry_blk;
struct f2fs_dentry_ptr d;
dentry_blk = inline_data_addr(ipage);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
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) {
i_size_write(inode, MAX_INLINE_DATA);
set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
}
return 0;
}
static int f2fs_convert_inline_dir(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 = grab_cache_page(dir->i_mapping, 0);
if (!page)
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);
zero_user_segment(page, 0, PAGE_CACHE_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);
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);
SetPageUptodate(page);
set_page_dirty(page);
/* clear inline dir and flag after data writeback */
truncate_inline_inode(ipage, 0);
stat_dec_inline_dir(dir);
clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
if (i_size_read(dir) < PAGE_CACHE_SIZE) {
i_size_write(dir, PAGE_CACHE_SIZE);
set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
sync_inode_page(&dn);
out:
f2fs_put_page(page, 1);
return err;
}
int f2fs_add_inline_entry(struct inode *dir, const struct qstr *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;
size_t namelen = name->len;
struct f2fs_inline_dentry *dentry_blk = NULL;
struct f2fs_dentry_ptr d;
int slots = GET_DENTRY_SLOTS(namelen);
struct page *page = NULL;
int err = 0;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
dentry_blk = inline_data_addr(ipage);
bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
slots, NR_INLINE_DENTRY);
if (bit_pos >= NR_INLINE_DENTRY) {
err = f2fs_convert_inline_dir(dir, ipage, dentry_blk);
if (!err)
err = -EAGAIN;
goto out;
}
if (inode) {
down_write(&F2FS_I(inode)->i_sem);
page = init_inode_metadata(inode, dir, 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);
name_hash = f2fs_dentry_hash(name);
make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos);
set_page_dirty(ipage);
/* we don't need to mark_inode_dirty now */
if (inode) {
F2FS_I(inode)->i_pino = dir->i_ino;
update_inode(inode, page);
f2fs_put_page(page, 1);
}
update_parent_metadata(dir, inode, 0);
fail:
if (inode)
up_write(&F2FS_I(inode)->i_sem);
if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
update_inode(dir, ipage);
clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
}
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);
inline_dentry = inline_data_addr(page);
bit_pos = dentry - inline_dentry->dentry;
for (i = 0; i < slots; i++)
test_and_clear_bit_le(bit_pos + i,
&inline_dentry->dentry_bitmap);
set_page_dirty(page);
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
if (inode)
f2fs_drop_nlink(dir, inode, page);
f2fs_put_page(page, 1);
}
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 *dentry_blk;
ipage = get_node_page(sbi, dir->i_ino);
if (IS_ERR(ipage))
return false;
dentry_blk = inline_data_addr(ipage);
bit_pos = find_next_bit_le(&dentry_blk->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 f2fs_str *fstr)
{
struct inode *inode = file_inode(file);
struct f2fs_inline_dentry *inline_dentry = NULL;
struct page *ipage = NULL;
struct f2fs_dentry_ptr d;
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(inode, &d, (void *)inline_dentry, 2);
if (!f2fs_fill_dentries(ctx, &d, 0, fstr))
ctx->pos = NR_INLINE_DENTRY;
f2fs_put_page(ipage, 1);
return 0;
}