linux/fs/f2fs/recovery.c

817 lines
19 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/recovery.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
/*
* Roll forward recovery scenarios.
*
* [Term] F: fsync_mark, D: dentry_mark
*
* 1. inode(x) | CP | inode(x) | dnode(F)
* -> Update the latest inode(x).
*
* 2. inode(x) | CP | inode(F) | dnode(F)
* -> No problem.
*
* 3. inode(x) | CP | dnode(F) | inode(x)
* -> Recover to the latest dnode(F), and drop the last inode(x)
*
* 4. inode(x) | CP | dnode(F) | inode(F)
* -> No problem.
*
* 5. CP | inode(x) | dnode(F)
* -> The inode(DF) was missing. Should drop this dnode(F).
*
* 6. CP | inode(DF) | dnode(F)
* -> No problem.
*
* 7. CP | dnode(F) | inode(DF)
* -> If f2fs_iget fails, then goto next to find inode(DF).
*
* 8. CP | dnode(F) | inode(x)
* -> If f2fs_iget fails, then goto next to find inode(DF).
* But it will fail due to no inode(DF).
*/
static struct kmem_cache *fsync_entry_slab;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi)
{
s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
return false;
return true;
}
static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
nid_t ino)
{
struct fsync_inode_entry *entry;
list_for_each_entry(entry, head, list)
if (entry->inode->i_ino == ino)
return entry;
return NULL;
}
static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
struct list_head *head, nid_t ino, bool quota_inode)
{
struct inode *inode;
struct fsync_inode_entry *entry;
int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return ERR_CAST(inode);
err = dquot_initialize(inode);
if (err)
goto err_out;
if (quota_inode) {
err = dquot_alloc_inode(inode);
if (err)
goto err_out;
}
entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
entry->inode = inode;
list_add_tail(&entry->list, head);
return entry;
err_out:
iput(inode);
return ERR_PTR(err);
}
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
static void del_fsync_inode(struct fsync_inode_entry *entry, int drop)
{
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
if (drop) {
/* inode should not be recovered, drop it */
f2fs_inode_synced(entry->inode);
}
iput(entry->inode);
list_del(&entry->list);
kmem_cache_free(fsync_entry_slab, entry);
}
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
static int recover_dentry(struct inode *inode, struct page *ipage,
struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
struct f2fs_dir_entry *de;
struct fscrypt_name fname;
struct page *page;
struct inode *dir, *einode;
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
struct fsync_inode_entry *entry;
int err = 0;
char *name;
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
entry = get_fsync_inode(dir_list, pino);
if (!entry) {
entry = add_fsync_inode(F2FS_I_SB(inode), dir_list,
pino, false);
if (IS_ERR(entry)) {
dir = ERR_CAST(entry);
err = PTR_ERR(entry);
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
goto out;
}
}
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
dir = entry->inode;
memset(&fname, 0, sizeof(struct fscrypt_name));
fname.disk_name.len = le32_to_cpu(raw_inode->i_namelen);
fname.disk_name.name = raw_inode->i_name;
if (unlikely(fname.disk_name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
goto out;
}
retry:
de = __f2fs_find_entry(dir, &fname, &page);
if (de && inode->i_ino == le32_to_cpu(de->ino))
goto out_put;
if (de) {
einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino));
if (IS_ERR(einode)) {
WARN_ON(1);
err = PTR_ERR(einode);
if (err == -ENOENT)
err = -EEXIST;
goto out_put;
}
err = dquot_initialize(einode);
if (err) {
iput(einode);
goto out_put;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_acquire_orphan_inode(F2FS_I_SB(inode));
if (err) {
iput(einode);
goto out_put;
}
f2fs_delete_entry(de, page, dir, einode);
iput(einode);
goto retry;
} else if (IS_ERR(page)) {
err = PTR_ERR(page);
} else {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_add_dentry(dir, &fname, inode,
inode->i_ino, inode->i_mode);
}
if (err == -ENOMEM)
goto retry;
goto out;
out_put:
f2fs_put_page(page, 0);
out:
if (file_enc_name(inode))
name = "<encrypted>";
else
name = raw_inode->i_name;
f2fs_notice(F2FS_I_SB(inode), "%s: ino = %x, name = %s, dir = %lx, err = %d",
__func__, ino_of_node(ipage), name,
IS_ERR(dir) ? 0 : dir->i_ino, err);
return err;
}
static int recover_quota_data(struct inode *inode, struct page *page)
{
struct f2fs_inode *raw = F2FS_INODE(page);
struct iattr attr;
uid_t i_uid = le32_to_cpu(raw->i_uid);
gid_t i_gid = le32_to_cpu(raw->i_gid);
int err;
memset(&attr, 0, sizeof(attr));
attr.ia_uid = make_kuid(inode->i_sb->s_user_ns, i_uid);
attr.ia_gid = make_kgid(inode->i_sb->s_user_ns, i_gid);
if (!uid_eq(attr.ia_uid, inode->i_uid))
attr.ia_valid |= ATTR_UID;
if (!gid_eq(attr.ia_gid, inode->i_gid))
attr.ia_valid |= ATTR_GID;
if (!attr.ia_valid)
return 0;
err = dquot_transfer(inode, &attr);
if (err)
set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR);
return err;
}
static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri)
{
if (ri->i_inline & F2FS_PIN_FILE)
set_inode_flag(inode, FI_PIN_FILE);
else
clear_inode_flag(inode, FI_PIN_FILE);
if (ri->i_inline & F2FS_DATA_EXIST)
set_inode_flag(inode, FI_DATA_EXIST);
else
clear_inode_flag(inode, FI_DATA_EXIST);
}
static int recover_inode(struct inode *inode, struct page *page)
{
struct f2fs_inode *raw = F2FS_INODE(page);
char *name;
int err;
inode->i_mode = le16_to_cpu(raw->i_mode);
err = recover_quota_data(inode, page);
if (err)
return err;
i_uid_write(inode, le32_to_cpu(raw->i_uid));
i_gid_write(inode, le32_to_cpu(raw->i_gid));
if (raw->i_inline & F2FS_EXTRA_ATTR) {
if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) &&
F2FS_FITS_IN_INODE(raw, le16_to_cpu(raw->i_extra_isize),
i_projid)) {
projid_t i_projid;
kprojid_t kprojid;
i_projid = (projid_t)le32_to_cpu(raw->i_projid);
kprojid = make_kprojid(&init_user_ns, i_projid);
if (!projid_eq(kprojid, F2FS_I(inode)->i_projid)) {
err = f2fs_transfer_project_quota(inode,
kprojid);
if (err)
return err;
F2FS_I(inode)->i_projid = kprojid;
}
}
}
f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
inode->i_atime.tv_nsec = le32_to_cpu(raw->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
F2FS_I(inode)->i_advise = raw->i_advise;
F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags);
f2fs_set_inode_flags(inode);
F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] =
le16_to_cpu(raw->i_gc_failures);
recover_inline_flags(inode, raw);
f2fs_mark_inode_dirty_sync(inode, true);
if (file_enc_name(inode))
name = "<encrypted>";
else
name = F2FS_INODE(page)->i_name;
f2fs_notice(F2FS_I_SB(inode), "recover_inode: ino = %x, name = %s, inline = %x",
ino_of_node(page), name, raw->i_inline);
return 0;
}
f2fs: avoid dirty node pages in check_only recovery In the check_only mode, we should not make any dirty node pages. Otherwise, we can get this panic: F2FS-fs (nvme0n1p1): Need to recover fsync data ------------[ cut here ]------------ kernel BUG at fs/f2fs/node.c:2204! CPU: 7 PID: 19923 Comm: mount Tainted: G OE 4.9.8 #2 RIP: 0010:[<ffffffffc0979c0b>] [<ffffffffc0979c0b>] flush_nat_entries+0x43b/0x7d0 [f2fs] Call Trace: [<ffffffffc096ddaa>] ? __f2fs_submit_merged_bio+0x5a/0xd0 [f2fs] [<ffffffffc096ddaa>] ? __f2fs_submit_merged_bio+0x5a/0xd0 [f2fs] [<ffffffffc096dddb>] ? __f2fs_submit_merged_bio+0x8b/0xd0 [f2fs] [<ffffffff860e450f>] ? up_write+0x1f/0x40 [<ffffffffc096dddb>] ? __f2fs_submit_merged_bio+0x8b/0xd0 [f2fs] [<ffffffffc0969f04>] write_checkpoint+0x2f4/0xf20 [f2fs] [<ffffffff860e938d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffffc0960bc9>] ? f2fs_sync_fs+0x79/0x190 [f2fs] [<ffffffffc0960bc9>] ? f2fs_sync_fs+0x79/0x190 [f2fs] [<ffffffffc0960bd5>] f2fs_sync_fs+0x85/0x190 [f2fs] [<ffffffffc097b6de>] f2fs_balance_fs_bg+0x7e/0x1c0 [f2fs] [<ffffffffc0977b64>] f2fs_write_node_pages+0x34/0x350 [f2fs] [<ffffffff860e5f42>] ? __lock_is_held+0x52/0x70 [<ffffffff861d9b31>] do_writepages+0x21/0x30 [<ffffffff86298ce1>] __writeback_single_inode+0x61/0x760 [<ffffffff86909127>] ? _raw_spin_unlock+0x27/0x40 [<ffffffff8629a735>] writeback_single_inode+0xd5/0x190 [<ffffffff8629a889>] write_inode_now+0x99/0xc0 [<ffffffff86283876>] iput+0x1f6/0x2c0 [<ffffffffc0964b52>] f2fs_fill_super+0xc32/0x10c0 [f2fs] [<ffffffff86266462>] mount_bdev+0x182/0x1b0 [<ffffffffc0963f20>] ? f2fs_commit_super+0x100/0x100 [f2fs] [<ffffffffc0960da5>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff86266e08>] mount_fs+0x38/0x170 [<ffffffff86288bab>] vfs_kern_mount+0x6b/0x160 [<ffffffff8628bcfe>] do_mount+0x1be/0xd60 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-04-14 22:46:23 +00:00
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
bool check_only)
{
struct curseg_info *curseg;
struct page *page = NULL;
block_t blkaddr;
unsigned int loop_cnt = 0;
unsigned int free_blocks = MAIN_SEGS(sbi) * sbi->blocks_per_seg -
valid_user_blocks(sbi);
int err = 0;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
return 0;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
}
if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
if (!is_fsync_dnode(page))
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
if (!entry) {
bool quota_inode = false;
f2fs: avoid dirty node pages in check_only recovery In the check_only mode, we should not make any dirty node pages. Otherwise, we can get this panic: F2FS-fs (nvme0n1p1): Need to recover fsync data ------------[ cut here ]------------ kernel BUG at fs/f2fs/node.c:2204! CPU: 7 PID: 19923 Comm: mount Tainted: G OE 4.9.8 #2 RIP: 0010:[<ffffffffc0979c0b>] [<ffffffffc0979c0b>] flush_nat_entries+0x43b/0x7d0 [f2fs] Call Trace: [<ffffffffc096ddaa>] ? __f2fs_submit_merged_bio+0x5a/0xd0 [f2fs] [<ffffffffc096ddaa>] ? __f2fs_submit_merged_bio+0x5a/0xd0 [f2fs] [<ffffffffc096dddb>] ? __f2fs_submit_merged_bio+0x8b/0xd0 [f2fs] [<ffffffff860e450f>] ? up_write+0x1f/0x40 [<ffffffffc096dddb>] ? __f2fs_submit_merged_bio+0x8b/0xd0 [f2fs] [<ffffffffc0969f04>] write_checkpoint+0x2f4/0xf20 [f2fs] [<ffffffff860e938d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffffc0960bc9>] ? f2fs_sync_fs+0x79/0x190 [f2fs] [<ffffffffc0960bc9>] ? f2fs_sync_fs+0x79/0x190 [f2fs] [<ffffffffc0960bd5>] f2fs_sync_fs+0x85/0x190 [f2fs] [<ffffffffc097b6de>] f2fs_balance_fs_bg+0x7e/0x1c0 [f2fs] [<ffffffffc0977b64>] f2fs_write_node_pages+0x34/0x350 [f2fs] [<ffffffff860e5f42>] ? __lock_is_held+0x52/0x70 [<ffffffff861d9b31>] do_writepages+0x21/0x30 [<ffffffff86298ce1>] __writeback_single_inode+0x61/0x760 [<ffffffff86909127>] ? _raw_spin_unlock+0x27/0x40 [<ffffffff8629a735>] writeback_single_inode+0xd5/0x190 [<ffffffff8629a889>] write_inode_now+0x99/0xc0 [<ffffffff86283876>] iput+0x1f6/0x2c0 [<ffffffffc0964b52>] f2fs_fill_super+0xc32/0x10c0 [f2fs] [<ffffffff86266462>] mount_bdev+0x182/0x1b0 [<ffffffffc0963f20>] ? f2fs_commit_super+0x100/0x100 [f2fs] [<ffffffffc0960da5>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff86266e08>] mount_fs+0x38/0x170 [<ffffffff86288bab>] vfs_kern_mount+0x6b/0x160 [<ffffffff8628bcfe>] do_mount+0x1be/0xd60 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-04-14 22:46:23 +00:00
if (!check_only &&
IS_INODE(page) && is_dent_dnode(page)) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_recover_inode_page(sbi, page);
if (err) {
f2fs_put_page(page, 1);
break;
}
quota_inode = true;
}
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
entry = add_fsync_inode(sbi, head, ino_of_node(page),
quota_inode);
if (IS_ERR(entry)) {
err = PTR_ERR(entry);
if (err == -ENOENT) {
err = 0;
goto next;
}
f2fs_put_page(page, 1);
break;
}
}
entry->blkaddr = blkaddr;
if (IS_INODE(page) && is_dent_dnode(page))
entry->last_dentry = blkaddr;
next:
/* sanity check in order to detect looped node chain */
if (++loop_cnt >= free_blocks ||
blkaddr == next_blkaddr_of_node(page)) {
f2fs_notice(sbi, "%s: detect looped node chain, blkaddr:%u, next:%u",
__func__, blkaddr,
next_blkaddr_of_node(page));
f2fs_put_page(page, 1);
err = -EINVAL;
break;
}
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_ra_meta_pages_cond(sbi, blkaddr);
}
return err;
}
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
static void destroy_fsync_dnodes(struct list_head *head, int drop)
{
struct fsync_inode_entry *entry, *tmp;
list_for_each_entry_safe(entry, tmp, head, list)
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
del_fsync_inode(entry, drop);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
f2fs: reuse the locked dnode page and its inode This patch fixes the following deadlock bug during the recovery. INFO: task mount:1322 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount D ffffffff81125870 0 1322 1266 0x00000000 ffff8801207e39d8 0000000000000046 ffff88012ab1dee0 0000000000000046 ffff8801207e3a08 ffff880115903f40 ffff8801207e3fd8 ffff8801207e3fd8 ffff8801207e3fd8 ffff880115903f40 ffff8801207e39d8 ffff88012fc94520 Call Trace: [<ffffffff81125870>] ? __lock_page+0x70/0x70 [<ffffffff816a92d9>] schedule+0x29/0x70 [<ffffffff816a93af>] io_schedule+0x8f/0xd0 [<ffffffff8112587e>] sleep_on_page+0xe/0x20 [<ffffffff816a649a>] __wait_on_bit_lock+0x5a/0xc0 [<ffffffff81125867>] __lock_page+0x67/0x70 [<ffffffff8106c7b0>] ? autoremove_wake_function+0x40/0x40 [<ffffffff81126857>] find_lock_page+0x67/0x80 [<ffffffff8112698f>] find_or_create_page+0x3f/0xb0 [<ffffffffa03901a8>] ? sync_inode_page+0xa8/0xd0 [f2fs] [<ffffffffa038fdf7>] get_node_page+0x67/0x180 [f2fs] [<ffffffffa039818b>] recover_fsync_data+0xacb/0xff0 [f2fs] [<ffffffff816aaa1e>] ? _raw_spin_unlock+0x3e/0x40 [<ffffffffa0389634>] f2fs_fill_super+0x7d4/0x850 [f2fs] [<ffffffff81184cf9>] mount_bdev+0x1c9/0x210 [<ffffffffa0388e60>] ? validate_superblock+0x180/0x180 [f2fs] [<ffffffffa0387635>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff81185a13>] mount_fs+0x43/0x1b0 [<ffffffff81145ba0>] ? __alloc_percpu+0x10/0x20 [<ffffffff811a0796>] vfs_kern_mount+0x76/0x120 [<ffffffff811a2cb7>] do_mount+0x237/0xa10 [<ffffffff81140b9b>] ? strndup_user+0x5b/0x80 [<ffffffff811a3520>] SyS_mount+0x90/0xe0 [<ffffffff816b3502>] system_call_fastpath+0x16/0x1b The bug is triggered when check_index_in_prev_nodes tries to get the direct node page by calling get_node_page. At this point, if the direct node page is already locked by get_dnode_of_data, its caller, we got a deadlock condition. This patch adds additional condition check for the reuse of locked direct node pages prior to the get_node_page call. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-05-21 23:02:02 +00:00
block_t blkaddr, struct dnode_of_data *dn)
{
struct seg_entry *sentry;
unsigned int segno = GET_SEGNO(sbi, blkaddr);
unsigned short blkoff = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
struct f2fs_summary_block *sum_node;
struct f2fs_summary sum;
struct page *sum_page, *node_page;
struct dnode_of_data tdn = *dn;
f2fs: reuse the locked dnode page and its inode This patch fixes the following deadlock bug during the recovery. INFO: task mount:1322 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount D ffffffff81125870 0 1322 1266 0x00000000 ffff8801207e39d8 0000000000000046 ffff88012ab1dee0 0000000000000046 ffff8801207e3a08 ffff880115903f40 ffff8801207e3fd8 ffff8801207e3fd8 ffff8801207e3fd8 ffff880115903f40 ffff8801207e39d8 ffff88012fc94520 Call Trace: [<ffffffff81125870>] ? __lock_page+0x70/0x70 [<ffffffff816a92d9>] schedule+0x29/0x70 [<ffffffff816a93af>] io_schedule+0x8f/0xd0 [<ffffffff8112587e>] sleep_on_page+0xe/0x20 [<ffffffff816a649a>] __wait_on_bit_lock+0x5a/0xc0 [<ffffffff81125867>] __lock_page+0x67/0x70 [<ffffffff8106c7b0>] ? autoremove_wake_function+0x40/0x40 [<ffffffff81126857>] find_lock_page+0x67/0x80 [<ffffffff8112698f>] find_or_create_page+0x3f/0xb0 [<ffffffffa03901a8>] ? sync_inode_page+0xa8/0xd0 [f2fs] [<ffffffffa038fdf7>] get_node_page+0x67/0x180 [f2fs] [<ffffffffa039818b>] recover_fsync_data+0xacb/0xff0 [f2fs] [<ffffffff816aaa1e>] ? _raw_spin_unlock+0x3e/0x40 [<ffffffffa0389634>] f2fs_fill_super+0x7d4/0x850 [f2fs] [<ffffffff81184cf9>] mount_bdev+0x1c9/0x210 [<ffffffffa0388e60>] ? validate_superblock+0x180/0x180 [f2fs] [<ffffffffa0387635>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff81185a13>] mount_fs+0x43/0x1b0 [<ffffffff81145ba0>] ? __alloc_percpu+0x10/0x20 [<ffffffff811a0796>] vfs_kern_mount+0x76/0x120 [<ffffffff811a2cb7>] do_mount+0x237/0xa10 [<ffffffff81140b9b>] ? strndup_user+0x5b/0x80 [<ffffffff811a3520>] SyS_mount+0x90/0xe0 [<ffffffff816b3502>] system_call_fastpath+0x16/0x1b The bug is triggered when check_index_in_prev_nodes tries to get the direct node page by calling get_node_page. At this point, if the direct node page is already locked by get_dnode_of_data, its caller, we got a deadlock condition. This patch adds additional condition check for the reuse of locked direct node pages prior to the get_node_page call. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-05-21 23:02:02 +00:00
nid_t ino, nid;
struct inode *inode;
unsigned int offset;
block_t bidx;
int i;
sentry = get_seg_entry(sbi, segno);
if (!f2fs_test_bit(blkoff, sentry->cur_valid_map))
return 0;
/* Get the previous summary */
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
struct curseg_info *curseg = CURSEG_I(sbi, i);
if (curseg->segno == segno) {
sum = curseg->sum_blk->entries[blkoff];
goto got_it;
}
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
sum_page = f2fs_get_sum_page(sbi, segno);
if (IS_ERR(sum_page))
return PTR_ERR(sum_page);
sum_node = (struct f2fs_summary_block *)page_address(sum_page);
sum = sum_node->entries[blkoff];
f2fs_put_page(sum_page, 1);
got_it:
f2fs: reuse the locked dnode page and its inode This patch fixes the following deadlock bug during the recovery. INFO: task mount:1322 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount D ffffffff81125870 0 1322 1266 0x00000000 ffff8801207e39d8 0000000000000046 ffff88012ab1dee0 0000000000000046 ffff8801207e3a08 ffff880115903f40 ffff8801207e3fd8 ffff8801207e3fd8 ffff8801207e3fd8 ffff880115903f40 ffff8801207e39d8 ffff88012fc94520 Call Trace: [<ffffffff81125870>] ? __lock_page+0x70/0x70 [<ffffffff816a92d9>] schedule+0x29/0x70 [<ffffffff816a93af>] io_schedule+0x8f/0xd0 [<ffffffff8112587e>] sleep_on_page+0xe/0x20 [<ffffffff816a649a>] __wait_on_bit_lock+0x5a/0xc0 [<ffffffff81125867>] __lock_page+0x67/0x70 [<ffffffff8106c7b0>] ? autoremove_wake_function+0x40/0x40 [<ffffffff81126857>] find_lock_page+0x67/0x80 [<ffffffff8112698f>] find_or_create_page+0x3f/0xb0 [<ffffffffa03901a8>] ? sync_inode_page+0xa8/0xd0 [f2fs] [<ffffffffa038fdf7>] get_node_page+0x67/0x180 [f2fs] [<ffffffffa039818b>] recover_fsync_data+0xacb/0xff0 [f2fs] [<ffffffff816aaa1e>] ? _raw_spin_unlock+0x3e/0x40 [<ffffffffa0389634>] f2fs_fill_super+0x7d4/0x850 [f2fs] [<ffffffff81184cf9>] mount_bdev+0x1c9/0x210 [<ffffffffa0388e60>] ? validate_superblock+0x180/0x180 [f2fs] [<ffffffffa0387635>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff81185a13>] mount_fs+0x43/0x1b0 [<ffffffff81145ba0>] ? __alloc_percpu+0x10/0x20 [<ffffffff811a0796>] vfs_kern_mount+0x76/0x120 [<ffffffff811a2cb7>] do_mount+0x237/0xa10 [<ffffffff81140b9b>] ? strndup_user+0x5b/0x80 [<ffffffff811a3520>] SyS_mount+0x90/0xe0 [<ffffffff816b3502>] system_call_fastpath+0x16/0x1b The bug is triggered when check_index_in_prev_nodes tries to get the direct node page by calling get_node_page. At this point, if the direct node page is already locked by get_dnode_of_data, its caller, we got a deadlock condition. This patch adds additional condition check for the reuse of locked direct node pages prior to the get_node_page call. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-05-21 23:02:02 +00:00
/* Use the locked dnode page and inode */
nid = le32_to_cpu(sum.nid);
if (dn->inode->i_ino == nid) {
tdn.nid = nid;
if (!dn->inode_page_locked)
lock_page(dn->inode_page);
f2fs: reuse the locked dnode page and its inode This patch fixes the following deadlock bug during the recovery. INFO: task mount:1322 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount D ffffffff81125870 0 1322 1266 0x00000000 ffff8801207e39d8 0000000000000046 ffff88012ab1dee0 0000000000000046 ffff8801207e3a08 ffff880115903f40 ffff8801207e3fd8 ffff8801207e3fd8 ffff8801207e3fd8 ffff880115903f40 ffff8801207e39d8 ffff88012fc94520 Call Trace: [<ffffffff81125870>] ? __lock_page+0x70/0x70 [<ffffffff816a92d9>] schedule+0x29/0x70 [<ffffffff816a93af>] io_schedule+0x8f/0xd0 [<ffffffff8112587e>] sleep_on_page+0xe/0x20 [<ffffffff816a649a>] __wait_on_bit_lock+0x5a/0xc0 [<ffffffff81125867>] __lock_page+0x67/0x70 [<ffffffff8106c7b0>] ? autoremove_wake_function+0x40/0x40 [<ffffffff81126857>] find_lock_page+0x67/0x80 [<ffffffff8112698f>] find_or_create_page+0x3f/0xb0 [<ffffffffa03901a8>] ? sync_inode_page+0xa8/0xd0 [f2fs] [<ffffffffa038fdf7>] get_node_page+0x67/0x180 [f2fs] [<ffffffffa039818b>] recover_fsync_data+0xacb/0xff0 [f2fs] [<ffffffff816aaa1e>] ? _raw_spin_unlock+0x3e/0x40 [<ffffffffa0389634>] f2fs_fill_super+0x7d4/0x850 [f2fs] [<ffffffff81184cf9>] mount_bdev+0x1c9/0x210 [<ffffffffa0388e60>] ? validate_superblock+0x180/0x180 [f2fs] [<ffffffffa0387635>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff81185a13>] mount_fs+0x43/0x1b0 [<ffffffff81145ba0>] ? __alloc_percpu+0x10/0x20 [<ffffffff811a0796>] vfs_kern_mount+0x76/0x120 [<ffffffff811a2cb7>] do_mount+0x237/0xa10 [<ffffffff81140b9b>] ? strndup_user+0x5b/0x80 [<ffffffff811a3520>] SyS_mount+0x90/0xe0 [<ffffffff816b3502>] system_call_fastpath+0x16/0x1b The bug is triggered when check_index_in_prev_nodes tries to get the direct node page by calling get_node_page. At this point, if the direct node page is already locked by get_dnode_of_data, its caller, we got a deadlock condition. This patch adds additional condition check for the reuse of locked direct node pages prior to the get_node_page call. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-05-21 23:02:02 +00:00
tdn.node_page = dn->inode_page;
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
f2fs: reuse the locked dnode page and its inode This patch fixes the following deadlock bug during the recovery. INFO: task mount:1322 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount D ffffffff81125870 0 1322 1266 0x00000000 ffff8801207e39d8 0000000000000046 ffff88012ab1dee0 0000000000000046 ffff8801207e3a08 ffff880115903f40 ffff8801207e3fd8 ffff8801207e3fd8 ffff8801207e3fd8 ffff880115903f40 ffff8801207e39d8 ffff88012fc94520 Call Trace: [<ffffffff81125870>] ? __lock_page+0x70/0x70 [<ffffffff816a92d9>] schedule+0x29/0x70 [<ffffffff816a93af>] io_schedule+0x8f/0xd0 [<ffffffff8112587e>] sleep_on_page+0xe/0x20 [<ffffffff816a649a>] __wait_on_bit_lock+0x5a/0xc0 [<ffffffff81125867>] __lock_page+0x67/0x70 [<ffffffff8106c7b0>] ? autoremove_wake_function+0x40/0x40 [<ffffffff81126857>] find_lock_page+0x67/0x80 [<ffffffff8112698f>] find_or_create_page+0x3f/0xb0 [<ffffffffa03901a8>] ? sync_inode_page+0xa8/0xd0 [f2fs] [<ffffffffa038fdf7>] get_node_page+0x67/0x180 [f2fs] [<ffffffffa039818b>] recover_fsync_data+0xacb/0xff0 [f2fs] [<ffffffff816aaa1e>] ? _raw_spin_unlock+0x3e/0x40 [<ffffffffa0389634>] f2fs_fill_super+0x7d4/0x850 [f2fs] [<ffffffff81184cf9>] mount_bdev+0x1c9/0x210 [<ffffffffa0388e60>] ? validate_superblock+0x180/0x180 [f2fs] [<ffffffffa0387635>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff81185a13>] mount_fs+0x43/0x1b0 [<ffffffff81145ba0>] ? __alloc_percpu+0x10/0x20 [<ffffffff811a0796>] vfs_kern_mount+0x76/0x120 [<ffffffff811a2cb7>] do_mount+0x237/0xa10 [<ffffffff81140b9b>] ? strndup_user+0x5b/0x80 [<ffffffff811a3520>] SyS_mount+0x90/0xe0 [<ffffffff816b3502>] system_call_fastpath+0x16/0x1b The bug is triggered when check_index_in_prev_nodes tries to get the direct node page by calling get_node_page. At this point, if the direct node page is already locked by get_dnode_of_data, its caller, we got a deadlock condition. This patch adds additional condition check for the reuse of locked direct node pages prior to the get_node_page call. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-05-21 23:02:02 +00:00
} else if (dn->nid == nid) {
tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
goto truncate_out;
f2fs: reuse the locked dnode page and its inode This patch fixes the following deadlock bug during the recovery. INFO: task mount:1322 blocked for more than 120 seconds. "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. mount D ffffffff81125870 0 1322 1266 0x00000000 ffff8801207e39d8 0000000000000046 ffff88012ab1dee0 0000000000000046 ffff8801207e3a08 ffff880115903f40 ffff8801207e3fd8 ffff8801207e3fd8 ffff8801207e3fd8 ffff880115903f40 ffff8801207e39d8 ffff88012fc94520 Call Trace: [<ffffffff81125870>] ? __lock_page+0x70/0x70 [<ffffffff816a92d9>] schedule+0x29/0x70 [<ffffffff816a93af>] io_schedule+0x8f/0xd0 [<ffffffff8112587e>] sleep_on_page+0xe/0x20 [<ffffffff816a649a>] __wait_on_bit_lock+0x5a/0xc0 [<ffffffff81125867>] __lock_page+0x67/0x70 [<ffffffff8106c7b0>] ? autoremove_wake_function+0x40/0x40 [<ffffffff81126857>] find_lock_page+0x67/0x80 [<ffffffff8112698f>] find_or_create_page+0x3f/0xb0 [<ffffffffa03901a8>] ? sync_inode_page+0xa8/0xd0 [f2fs] [<ffffffffa038fdf7>] get_node_page+0x67/0x180 [f2fs] [<ffffffffa039818b>] recover_fsync_data+0xacb/0xff0 [f2fs] [<ffffffff816aaa1e>] ? _raw_spin_unlock+0x3e/0x40 [<ffffffffa0389634>] f2fs_fill_super+0x7d4/0x850 [f2fs] [<ffffffff81184cf9>] mount_bdev+0x1c9/0x210 [<ffffffffa0388e60>] ? validate_superblock+0x180/0x180 [f2fs] [<ffffffffa0387635>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff81185a13>] mount_fs+0x43/0x1b0 [<ffffffff81145ba0>] ? __alloc_percpu+0x10/0x20 [<ffffffff811a0796>] vfs_kern_mount+0x76/0x120 [<ffffffff811a2cb7>] do_mount+0x237/0xa10 [<ffffffff81140b9b>] ? strndup_user+0x5b/0x80 [<ffffffff811a3520>] SyS_mount+0x90/0xe0 [<ffffffff816b3502>] system_call_fastpath+0x16/0x1b The bug is triggered when check_index_in_prev_nodes tries to get the direct node page by calling get_node_page. At this point, if the direct node page is already locked by get_dnode_of_data, its caller, we got a deadlock condition. This patch adds additional condition check for the reuse of locked direct node pages prior to the get_node_page call. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-05-21 23:02:02 +00:00
}
/* Get the node page */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
node_page = f2fs_get_node_page(sbi, nid);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
offset = ofs_of_node(node_page);
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
if (ino != dn->inode->i_ino) {
int ret;
/* Deallocate previous index in the node page */
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return PTR_ERR(inode);
ret = dquot_initialize(inode);
if (ret) {
iput(inode);
return ret;
}
} else {
inode = dn->inode;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
bidx = f2fs_start_bidx_of_node(offset, inode) +
le16_to_cpu(sum.ofs_in_node);
/*
* if inode page is locked, unlock temporarily, but its reference
* count keeps alive.
*/
if (ino == dn->inode->i_ino && dn->inode_page_locked)
unlock_page(dn->inode_page);
set_new_dnode(&tdn, inode, NULL, NULL, 0);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
goto out;
if (tdn.data_blkaddr == blkaddr)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_truncate_data_blocks_range(&tdn, 1);
f2fs_put_dnode(&tdn);
out:
if (ino != dn->inode->i_ino)
iput(inode);
else if (dn->inode_page_locked)
lock_page(dn->inode_page);
return 0;
truncate_out:
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 (datablock_addr(tdn.inode, tdn.node_page,
tdn.ofs_in_node) == blkaddr)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_truncate_data_blocks_range(&tdn, 1);
if (dn->inode->i_ino == nid && !dn->inode_page_locked)
unlock_page(dn->inode_page);
return 0;
}
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page)
{
struct dnode_of_data dn;
struct node_info ni;
unsigned int start, end;
int err = 0, recovered = 0;
/* step 1: recover xattr */
if (IS_INODE(page)) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_recover_inline_xattr(inode, page);
} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_recover_xattr_data(inode, page);
if (!err)
recovered++;
goto out;
}
/* step 2: recover inline data */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
if (f2fs_recover_inline_data(inode, page))
goto out;
/* step 3: recover data indices */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
start = f2fs_start_bidx_of_node(ofs_of_node(page), inode);
end = start + ADDRS_PER_PAGE(page, inode);
set_new_dnode(&dn, inode, NULL, NULL, 0);
retry_dn:
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_dn;
}
goto out;
}
f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true);
err = f2fs_get_node_info(sbi, dn.nid, &ni);
if (err)
goto err;
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
if (ofs_of_node(dn.node_page) != ofs_of_node(page)) {
f2fs_warn(sbi, "Inconsistent ofs_of_node, ino:%lu, ofs:%u, %u",
inode->i_ino, ofs_of_node(dn.node_page),
ofs_of_node(page));
err = -EFSCORRUPTED;
goto err;
}
for (; start < end; start++, dn.ofs_in_node++) {
block_t src, dest;
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
src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node);
dest = datablock_addr(dn.inode, page, dn.ofs_in_node);
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
if (__is_valid_data_blkaddr(src) &&
!f2fs_is_valid_blkaddr(sbi, src, META_POR)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
goto err;
}
if (__is_valid_data_blkaddr(dest) &&
!f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
err = -EFSCORRUPTED;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 07:26:32 +00:00
goto err;
}
/* skip recovering if dest is the same as src */
if (src == dest)
continue;
/* dest is invalid, just invalidate src block */
if (dest == NULL_ADDR) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_truncate_data_blocks_range(&dn, 1);
continue;
}
if (!file_keep_isize(inode) &&
(i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
f2fs_i_size_write(inode,
(loff_t)(start + 1) << PAGE_SHIFT);
/*
* dest is reserved block, invalidate src block
* and then reserve one new block in dnode page.
*/
if (dest == NEW_ADDR) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_truncate_data_blocks_range(&dn, 1);
f2fs_reserve_new_block(&dn);
continue;
}
/* dest is valid block, try to recover from src to dest */
if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) {
if (src == NULL_ADDR) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_reserve_new_block(&dn);
while (err &&
IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION))
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
err = f2fs_reserve_new_block(&dn);
/* We should not get -ENOSPC */
f2fs_bug_on(sbi, err);
if (err)
goto err;
}
retry_prev:
/* Check the previous node page having this index */
err = check_index_in_prev_nodes(sbi, dest, &dn);
if (err) {
if (err == -ENOMEM) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry_prev;
}
goto err;
}
/* write dummy data page */
f2fs_replace_block(sbi, &dn, src, dest,
ni.version, false, false);
recovered++;
}
}
copy_node_footer(dn.node_page, page);
fill_node_footer(dn.node_page, dn.nid, ni.ino,
ofs_of_node(page), false);
set_page_dirty(dn.node_page);
err:
f2fs_put_dnode(&dn);
out:
f2fs_notice(sbi, "recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
inode->i_ino, file_keep_isize(inode) ? "keep" : "recover",
recovered, err);
return err;
}
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
struct list_head *tmp_inode_list, struct list_head *dir_list)
{
struct curseg_info *curseg;
struct page *page = NULL;
int err = 0;
block_t blkaddr;
/* get node pages in the current segment */
curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
struct fsync_inode_entry *entry;
if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR))
break;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
f2fs_ra_meta_pages_cond(sbi, blkaddr);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
page = f2fs_get_tmp_page(sbi, blkaddr);
if (IS_ERR(page)) {
err = PTR_ERR(page);
break;
}
if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
* inode(x) | CP | inode(x) | dnode(F)
* In this case, we can lose the latest inode(x).
* So, call recover_inode for the inode update.
*/
if (IS_INODE(page)) {
err = recover_inode(entry->inode, page);
if (err) {
f2fs_put_page(page, 1);
break;
}
}
if (entry->last_dentry == blkaddr) {
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
err = recover_dentry(entry->inode, page, dir_list);
if (err) {
f2fs_put_page(page, 1);
break;
}
}
err = do_recover_data(sbi, entry->inode, page);
if (err) {
f2fs_put_page(page, 1);
break;
}
if (entry->blkaddr == blkaddr)
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
list_move_tail(&entry->list, tmp_inode_list);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
}
if (!err)
f2fs_allocate_new_segments(sbi, NO_CHECK_TYPE);
return err;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 16:20:41 +00:00
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
struct list_head inode_list, tmp_inode_list;
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
struct list_head dir_list;
int err;
int ret = 0;
unsigned long s_flags = sbi->sb->s_flags;
bool need_writecp = false;
#ifdef CONFIG_QUOTA
int quota_enabled;
#endif
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 21:05:09 +00:00
if (s_flags & SB_RDONLY) {
f2fs_info(sbi, "recover fsync data on readonly fs");
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 21:05:09 +00:00
sbi->sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 21:05:09 +00:00
sbi->sb->s_flags |= SB_ACTIVE;
/* Turn on quotas so that they are updated correctly */
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 21:05:09 +00:00
quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
#endif
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
sizeof(struct fsync_inode_entry));
if (!fsync_entry_slab) {
err = -ENOMEM;
goto out;
}
INIT_LIST_HEAD(&inode_list);
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
INIT_LIST_HEAD(&tmp_inode_list);
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
/* step #1: find fsynced inode numbers */
f2fs: avoid dirty node pages in check_only recovery In the check_only mode, we should not make any dirty node pages. Otherwise, we can get this panic: F2FS-fs (nvme0n1p1): Need to recover fsync data ------------[ cut here ]------------ kernel BUG at fs/f2fs/node.c:2204! CPU: 7 PID: 19923 Comm: mount Tainted: G OE 4.9.8 #2 RIP: 0010:[<ffffffffc0979c0b>] [<ffffffffc0979c0b>] flush_nat_entries+0x43b/0x7d0 [f2fs] Call Trace: [<ffffffffc096ddaa>] ? __f2fs_submit_merged_bio+0x5a/0xd0 [f2fs] [<ffffffffc096ddaa>] ? __f2fs_submit_merged_bio+0x5a/0xd0 [f2fs] [<ffffffffc096dddb>] ? __f2fs_submit_merged_bio+0x8b/0xd0 [f2fs] [<ffffffff860e450f>] ? up_write+0x1f/0x40 [<ffffffffc096dddb>] ? __f2fs_submit_merged_bio+0x8b/0xd0 [f2fs] [<ffffffffc0969f04>] write_checkpoint+0x2f4/0xf20 [f2fs] [<ffffffff860e938d>] ? trace_hardirqs_on+0xd/0x10 [<ffffffffc0960bc9>] ? f2fs_sync_fs+0x79/0x190 [f2fs] [<ffffffffc0960bc9>] ? f2fs_sync_fs+0x79/0x190 [f2fs] [<ffffffffc0960bd5>] f2fs_sync_fs+0x85/0x190 [f2fs] [<ffffffffc097b6de>] f2fs_balance_fs_bg+0x7e/0x1c0 [f2fs] [<ffffffffc0977b64>] f2fs_write_node_pages+0x34/0x350 [f2fs] [<ffffffff860e5f42>] ? __lock_is_held+0x52/0x70 [<ffffffff861d9b31>] do_writepages+0x21/0x30 [<ffffffff86298ce1>] __writeback_single_inode+0x61/0x760 [<ffffffff86909127>] ? _raw_spin_unlock+0x27/0x40 [<ffffffff8629a735>] writeback_single_inode+0xd5/0x190 [<ffffffff8629a889>] write_inode_now+0x99/0xc0 [<ffffffff86283876>] iput+0x1f6/0x2c0 [<ffffffffc0964b52>] f2fs_fill_super+0xc32/0x10c0 [f2fs] [<ffffffff86266462>] mount_bdev+0x182/0x1b0 [<ffffffffc0963f20>] ? f2fs_commit_super+0x100/0x100 [f2fs] [<ffffffffc0960da5>] f2fs_mount+0x15/0x20 [f2fs] [<ffffffff86266e08>] mount_fs+0x38/0x170 [<ffffffff86288bab>] vfs_kern_mount+0x6b/0x160 [<ffffffff8628bcfe>] do_mount+0x1be/0xd60 Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-04-14 22:46:23 +00:00
err = find_fsync_dnodes(sbi, &inode_list, check_only);
if (err || list_empty(&inode_list))
goto skip;
if (check_only) {
ret = 1;
goto skip;
}
need_writecp = true;
/* step #2: recover data */
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
else {
/* restore s_flags to let iput() trash data */
sbi->sb->s_flags = s_flags;
}
skip:
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
destroy_fsync_dnodes(&inode_list, err);
destroy_fsync_dnodes(&tmp_inode_list, err);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
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 12:29:47 +00:00
(loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
} else {
clear_sbi_flag(sbi, SBI_POR_DOING);
}
mutex_unlock(&sbi->cp_mutex);
/* let's drop all the directory inodes for clean checkpoint */
f2fs: cleanup dirty pages if recover failed During recover, we will try to create new dentries for inodes with dentry_mark. But if the parent is missing (e.g. killed by fsck), recover will break. But those recovered dirty pages are not cleanup. This will hit f2fs_bug_on: [ 53.519566] F2FS-fs (loop0): Found nat_bits in checkpoint [ 53.539354] F2FS-fs (loop0): recover_inode: ino = 5, name = file, inline = 3 [ 53.539402] F2FS-fs (loop0): recover_dentry: ino = 5, name = file, dir = 0, err = -2 [ 53.545760] F2FS-fs (loop0): Cannot recover all fsync data errno=-2 [ 53.546105] F2FS-fs (loop0): access invalid blkaddr:4294967295 [ 53.546171] WARNING: CPU: 1 PID: 1798 at fs/f2fs/checkpoint.c:163 f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546174] Modules linked in: [ 53.546183] CPU: 1 PID: 1798 Comm: mount Not tainted 4.19.0-rc2+ #1 [ 53.546186] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 53.546191] RIP: 0010:f2fs_is_valid_blkaddr+0x26c/0x320 [ 53.546195] Code: 85 bb 00 00 00 48 89 df 88 44 24 07 e8 ad a8 db ff 48 8b 3b 44 89 e1 48 c7 c2 40 03 72 a9 48 c7 c6 e0 01 72 a9 e8 84 3c ff ff <0f> 0b 0f b6 44 24 07 e9 8a 00 00 00 48 8d bf 38 01 00 00 e8 7c a8 [ 53.546201] RSP: 0018:ffff88006c067768 EFLAGS: 00010282 [ 53.546208] RAX: 0000000000000000 RBX: ffff880068844200 RCX: ffffffffa83e1a33 [ 53.546211] RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffff88006d51e590 [ 53.546215] RBP: 0000000000000005 R08: ffffed000daa3cb3 R09: ffffed000daa3cb3 [ 53.546218] R10: 0000000000000001 R11: ffffed000daa3cb2 R12: 00000000ffffffff [ 53.546221] R13: ffff88006a1f8000 R14: 0000000000000200 R15: 0000000000000009 [ 53.546226] FS: 00007fb2f3646840(0000) GS:ffff88006d500000(0000) knlGS:0000000000000000 [ 53.546229] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 53.546234] CR2: 00007f0fd77f0008 CR3: 00000000687e6002 CR4: 00000000000206e0 [ 53.546237] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 53.546240] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 53.546242] Call Trace: [ 53.546248] f2fs_submit_page_bio+0x95/0x740 [ 53.546253] read_node_page+0x161/0x1e0 [ 53.546271] ? truncate_node+0x650/0x650 [ 53.546283] ? add_to_page_cache_lru+0x12c/0x170 [ 53.546288] ? pagecache_get_page+0x262/0x2d0 [ 53.546292] __get_node_page+0x200/0x660 [ 53.546302] f2fs_update_inode_page+0x4a/0x160 [ 53.546306] f2fs_write_inode+0x86/0xb0 [ 53.546317] __writeback_single_inode+0x49c/0x620 [ 53.546322] writeback_single_inode+0xe4/0x1e0 [ 53.546326] sync_inode_metadata+0x93/0xd0 [ 53.546330] ? sync_inode+0x10/0x10 [ 53.546342] ? do_raw_spin_unlock+0xed/0x100 [ 53.546347] f2fs_sync_inode_meta+0xe0/0x130 [ 53.546351] f2fs_fill_super+0x287d/0x2d10 [ 53.546367] ? vsnprintf+0x742/0x7a0 [ 53.546372] ? f2fs_commit_super+0x180/0x180 [ 53.546379] ? up_write+0x20/0x40 [ 53.546385] ? set_blocksize+0x5f/0x140 [ 53.546391] ? f2fs_commit_super+0x180/0x180 [ 53.546402] mount_bdev+0x181/0x200 [ 53.546406] mount_fs+0x94/0x180 [ 53.546411] vfs_kern_mount+0x6c/0x1e0 [ 53.546415] do_mount+0xe5e/0x1510 [ 53.546420] ? fs_reclaim_release+0x9/0x30 [ 53.546424] ? copy_mount_string+0x20/0x20 [ 53.546428] ? fs_reclaim_acquire+0xd/0x30 [ 53.546435] ? __might_sleep+0x2c/0xc0 [ 53.546440] ? ___might_sleep+0x53/0x170 [ 53.546453] ? __might_fault+0x4c/0x60 [ 53.546468] ? _copy_from_user+0x95/0xa0 [ 53.546474] ? memdup_user+0x39/0x60 [ 53.546478] ksys_mount+0x88/0xb0 [ 53.546482] __x64_sys_mount+0x5d/0x70 [ 53.546495] do_syscall_64+0x65/0x130 [ 53.546503] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 53.547639] ---[ end trace b804d1ea2fec893e ]--- So if recover fails, we need to drop all recovered data. Signed-off-by: Sheng Yong <shengyong1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-10-12 10:49:26 +00:00
destroy_fsync_dnodes(&dir_list, err);
f2fs: fix to flush all dirty inodes recovered in readonly fs generic/417 reported as blow: ------------[ cut here ]------------ kernel BUG at /home/yuchao/git/devf2fs/inode.c:695! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 1 PID: 21697 Comm: umount Tainted: G W O 4.18.0-rc2+ #39 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_evict_inode+0x556/0x580 [f2fs] Call Trace: ? _raw_spin_unlock+0x2c/0x50 evict+0xa8/0x170 dispose_list+0x34/0x40 evict_inodes+0x118/0x120 generic_shutdown_super+0x41/0x100 ? rcu_read_lock_sched_held+0x97/0xa0 kill_block_super+0x22/0x50 kill_f2fs_super+0x6f/0x80 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x81/0xa0 exit_to_usermode_loop+0x59/0xa7 do_fast_syscall_32+0x1f5/0x22c entry_SYSENTER_32+0x53/0x86 EIP: f2fs_evict_inode+0x556/0x580 [f2fs] It can simply reproduced with scripts: Enable quota feature during mkfs. Testcase1: 1. mkfs.f2fs /dev/zram0 2. mount -t f2fs /dev/zram0 /mnt/f2fs 3. xfs_io -f /mnt/f2fs/file -c "pwrite 0 4k" -c "fsync" 4. godown /mnt/f2fs 5. umount /mnt/f2fs 6. mount -t f2fs -o ro /dev/zram0 /mnt/f2fs 7. umount /mnt/f2fs Testcase2: 1. mkfs.f2fs /dev/zram0 2. mount -t f2fs /dev/zram0 /mnt/f2fs 3. touch /mnt/f2fs/file 4. create process[pid = x] do: a) open /mnt/f2fs/file; b) unlink /mnt/f2fs/file 5. godown -f /mnt/f2fs 6. kill process[pid = x] 7. umount /mnt/f2fs 8. mount -t f2fs -o ro /dev/zram0 /mnt/f2fs 9. umount /mnt/f2fs The reason is: during recovery, i_{c,m}time of inode will be updated, then the inode can be set dirty w/o being tracked in sbi->inode_list[DIRTY_META] global list, so later write_checkpoint will not flush such dirty inode into node page. Once umount is called, sync_filesystem() in generic_shutdown_super() will skip syncng dirty inodes due to sb_rdonly check, leaving dirty inodes there. To solve this issue, during umount, add remove SB_RDONLY flag in sb->s_flags, to make sure sync_filesystem() will not be skipped. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-22 09:11:05 +00:00
if (need_writecp) {
set_sbi_flag(sbi, SBI_IS_RECOVERED);
if (!err) {
struct cp_control cpc = {
.reason = CP_RECOVERY,
};
err = f2fs_write_checkpoint(sbi, &cpc);
}
}
f2fs: fix inode cache leak When testing f2fs with inline_dentry option, generic/342 reports: VFS: Busy inodes after unmount of dm-0. Self-destruct in 5 seconds. Have a nice day... After rmmod f2fs module, kenrel shows following dmesg: ============================================================================= BUG f2fs_inode_cache (Tainted: G O ): Objects remaining in f2fs_inode_cache on __kmem_cache_shutdown() ----------------------------------------------------------------------------- Disabling lock debugging due to kernel taint INFO: Slab 0xf51ca0e0 objects=22 used=1 fp=0xd1e6fc60 flags=0x40004080 CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000086 00000086 d062fe18 c13a83a0 f51ca0e0 d062fe38 d062fea4 c11c7276 c1981040 f51ca0e0 00000016 00000001 d1e6fc60 40004080 656a624f 20737463 616d6572 6e696e69 6e692067 66326620 6e695f73 5f65646f 68636163 6e6f2065 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c11c7276>] slab_err+0x76/0x80 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfc0>] ? __kmem_cache_shutdown+0x100/0x2f0 [<c11cbfe5>] __kmem_cache_shutdown+0x125/0x2f0 [<c1198a38>] kmem_cache_destroy+0x158/0x1f0 [<c176b43d>] ? mutex_unlock+0xd/0x10 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 INFO: Object 0xd1e6d9e0 @offset=6624 kmem_cache_destroy f2fs_inode_cache: Slab cache still has objects CPU: 3 PID: 7455 Comm: rmmod Tainted: G B O 4.6.0-rc4+ #16 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 00000286 00000286 d062fef4 c13a83a0 f174b000 d062ff14 d062ff28 c1198ac7 c197fe18 f3c5b980 d062ff20 000d04f2 d062ff0c d062ff0c d062ff14 d062ff14 f8f20dc0 fffffff5 d062e000 d062ff30 f8f15aa3 d062ff7c c10f596c 73663266 Call Trace: [<c13a83a0>] dump_stack+0x5f/0x8f [<c1198ac7>] kmem_cache_destroy+0x1e7/0x1f0 [<f8f15aa3>] exit_f2fs_fs+0x4b/0x5a8 [f2fs] [<c10f596c>] SyS_delete_module+0x16c/0x1d0 [<c1001b10>] ? do_fast_syscall_32+0x30/0x1c0 [<c13c59bf>] ? __this_cpu_preempt_check+0xf/0x20 [<c10afa7d>] ? trace_hardirqs_on_caller+0xdd/0x210 [<c10ad50b>] ? trace_hardirqs_off+0xb/0x10 [<c1001b81>] do_fast_syscall_32+0xa1/0x1c0 [<c176d888>] sysenter_past_esp+0x45/0x74 The reason is: in recovery flow, we use delayed iput mechanism for directory which has recovered dentry block. It means the reference of inode will be held until last dirty dentry page being writebacked. But when we mount f2fs with inline_dentry option, during recovery, dirent may only be recovered into dir inode page rather than dentry page, so there are no chance for us to release inode reference in ->writepage when writebacking last dentry page. We can call paired iget/iput explicityly for inline_dentry case, but for non-inline_dentry case, iput will call writeback_single_inode to write all data pages synchronously, but during recovery, ->writepages of f2fs skips writing all pages, result in losing dirent. This patch fixes this issue by obsoleting old mechanism, and introduce a new dir_list to hold all directory inodes which has recovered datas until finishing recovery. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-05-07 08:15:05 +00:00
kmem_cache_destroy(fsync_entry_slab);
out:
#ifdef CONFIG_QUOTA
/* Turn quotas off */
if (quota_enabled)
f2fs_quota_off_umount(sbi->sb);
#endif
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 21:05:09 +00:00
sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
return ret ? ret: err;
}