From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Sheng Yong <shengyong1@huawei.com>,
Jaegeuk Kim <jaegeuk@kernel.org>, Sasha Levin <sashal@kernel.org>,
linux-f2fs-devel@lists.sourceforge.net
Subject: [PATCH AUTOSEL 4.19 23/57] f2fs: cleanup dirty pages if recover failed
Date: Fri, 29 Mar 2019 21:28:16 -0400 [thread overview]
Message-ID: <20190330012854.32212-23-sashal@kernel.org> (raw)
In-Reply-To: <20190330012854.32212-1-sashal@kernel.org>
From: Sheng Yong <shengyong1@huawei.com>
[ Upstream commit 26b5a079197c8cb6725565968b7fd3299bd1877b ]
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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
fs/f2fs/recovery.c | 32 +++++++++++++++++++++-----------
fs/f2fs/super.c | 15 ++++++++++++++-
2 files changed, 35 insertions(+), 12 deletions(-)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 9a8579fb3a30..ae0e5f2e67b4 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -99,8 +99,12 @@ static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
return ERR_PTR(err);
}
-static void del_fsync_inode(struct fsync_inode_entry *entry)
+static void del_fsync_inode(struct fsync_inode_entry *entry, int drop)
{
+ 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);
@@ -321,12 +325,12 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
return err;
}
-static void destroy_fsync_dnodes(struct list_head *head)
+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)
- del_fsync_inode(entry);
+ del_fsync_inode(entry, drop);
}
static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -561,7 +565,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
}
static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
- struct list_head *dir_list)
+ struct list_head *tmp_inode_list, struct list_head *dir_list)
{
struct curseg_info *curseg;
struct page *page = NULL;
@@ -615,7 +619,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
}
if (entry->blkaddr == blkaddr)
- del_fsync_inode(entry);
+ list_move_tail(&entry->list, tmp_inode_list);
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
@@ -628,7 +632,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
- struct list_head inode_list;
+ struct list_head inode_list, tmp_inode_list;
struct list_head dir_list;
int err;
int ret = 0;
@@ -659,6 +663,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
}
INIT_LIST_HEAD(&inode_list);
+ INIT_LIST_HEAD(&tmp_inode_list);
INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
@@ -677,11 +682,16 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
need_writecp = true;
/* step #2: recover data */
- err = recover_data(sbi, &inode_list, &dir_list);
+ err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
+ else {
+ /* restore s_flags to let iput() trash data */
+ sbi->sb->s_flags = s_flags;
+ }
skip:
- destroy_fsync_dnodes(&inode_list);
+ 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),
@@ -690,13 +700,13 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
+ } else {
+ clear_sbi_flag(sbi, SBI_POR_DOING);
}
-
- clear_sbi_flag(sbi, SBI_POR_DOING);
mutex_unlock(&sbi->cp_mutex);
/* let's drop all the directory inodes for clean checkpoint */
- destroy_fsync_dnodes(&dir_list);
+ destroy_fsync_dnodes(&dir_list, err);
if (need_writecp) {
set_sbi_flag(sbi, SBI_IS_RECOVERED);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 442cc9023dfc..08162f39d3f7 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1884,6 +1884,19 @@ void f2fs_quota_off_umount(struct super_block *sb)
}
}
+static void f2fs_truncate_quota_inode_pages(struct super_block *sb)
+{
+ struct quota_info *dqopt = sb_dqopt(sb);
+ int type;
+
+ for (type = 0; type < MAXQUOTAS; type++) {
+ if (!dqopt->files[type])
+ continue;
+ f2fs_inode_synced(dqopt->files[type]);
+ }
+}
+
+
static int f2fs_get_projid(struct inode *inode, kprojid_t *projid)
{
*projid = F2FS_I(inode)->i_projid;
@@ -3130,10 +3143,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
free_meta:
#ifdef CONFIG_QUOTA
+ f2fs_truncate_quota_inode_pages(sb);
if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb))
f2fs_quota_off_umount(sbi->sb);
#endif
- f2fs_sync_inode_meta(sbi);
/*
* Some dirty meta pages can be produced by f2fs_recover_orphan_inodes()
* failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
--
2.19.1
next prev parent reply other threads:[~2019-03-30 1:28 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-30 1:27 [PATCH AUTOSEL 4.19 01/57] drm/cirrus: Use drm_framebuffer_put to avoid kernel oops in clean-up Sasha Levin
2019-03-30 1:27 ` [PATCH AUTOSEL 4.19 02/57] gpio: pxa: handle corner case of unprobed device Sasha Levin
2019-03-30 1:27 ` [PATCH AUTOSEL 4.19 03/57] rsi: improve kernel thread handling to fix kernel panic Sasha Levin
2019-03-30 1:27 ` [PATCH AUTOSEL 4.19 04/57] f2fs: fix to avoid NULL pointer dereference on se->discard_map Sasha Levin
2019-03-30 1:27 ` [PATCH AUTOSEL 4.19 05/57] 9p: do not trust pdu content for stat item size Sasha Levin
2019-03-30 1:27 ` [PATCH AUTOSEL 4.19 06/57] 9p locks: add mount option for lock retry interval Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 07/57] ASoC: Fix UBSAN warning at snd_soc_get/put_volsw_sx() Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 08/57] f2fs: fix to do sanity check with current segment number Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 09/57] netfilter: xt_cgroup: shrink size of v2 path Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 10/57] serial: uartps: console_setup() can't be placed to init section Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 11/57] powerpc/pseries: Remove prrn_work workqueue Sasha Levin
2019-03-30 1:28 ` Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 12/57] media: au0828: cannot kfree dev before usb disconnect Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 13/57] Bluetooth: Fix debugfs NULL pointer dereference Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 14/57] HID: i2c-hid: override HID descriptors for certain devices Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 15/57] pinctrl: core: make sure strcmp() doesn't get a null parameter Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 16/57] ARM: samsung: Limit SAMSUNG_PM_CHECK config option to non-Exynos platforms Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 17/57] usbip: fix vhci_hcd controller counting Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 18/57] ACPI / SBS: Fix GPE storm on recent MacBookPro's Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 19/57] HID: usbhid: Add quirk for Redragon/Dragonrise Seymur 2 Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 20/57] KVM: nVMX: restore host state in nested_vmx_vmexit for VMFail Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 21/57] compiler.h: update definition of unreachable() Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 22/57] netfilter: nf_flow_table: remove flowtable hook flush routine in netns exit routine Sasha Levin
2019-03-30 1:28 ` Sasha Levin [this message]
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 24/57] net: stmmac: Set OWN bit for jumbo frames Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 25/57] cifs: fallback to older infolevels on findfirst queryinfo retry Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 26/57] kernel: hung_task.c: disable on suspend Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 27/57] platform/x86: Add Intel AtomISP2 dummy / power-management driver Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 28/57] nvme-pci: fix conflicting p2p resource adds Sasha Levin
2019-03-30 1:28 ` Sasha Levin
2019-04-01 17:36 ` Heitke, Kenneth
2019-04-01 17:36 ` Heitke, Kenneth
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 29/57] drm/ttm: Fix bo_global and mem_global kfree error Sasha Levin
2019-03-30 1:28 ` Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 30/57] ALSA: hda: fix front speakers on Huawei MBXP Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 31/57] ACPI: EC / PM: Disable non-wakeup GPEs for suspend-to-idle Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 32/57] net/rds: fix warn in rds_message_alloc_sgs Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 33/57] blk-mq: protect debugfs_create_files() from failures Sasha Levin
2019-03-30 5:43 ` Greg Kroah-Hartman
2019-04-03 16:17 ` Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 34/57] xfrm: destroy xfrm_state synchronously on net exit path Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 35/57] crypto: sha256/arm - fix crash bug in Thumb2 build Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 36/57] crypto: sha512/arm " Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 37/57] net: ip6_gre: fix possible NULL pointer dereference in ip6erspan_set_version Sasha Levin
[not found] ` <20190330012854.32212-1-sashal-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 38/57] iommu/dmar: Fix buffer overflow during PCI bus notification Sasha Levin
2019-03-30 1:28 ` Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 39/57] scsi: core: Avoid that system resume triggers a kernel warning Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 40/57] kvm: properly check debugfs dentry before using it Sasha Levin
2019-03-30 5:43 ` Greg Kroah-Hartman
2019-04-03 16:16 ` Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 41/57] soc/tegra: pmc: Drop locking from tegra_powergate_is_powered() Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 42/57] ext4: prohibit fstrim in norecovery mode Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 43/57] lkdtm: Print real addresses Sasha Levin
2019-03-30 1:28 ` [PATCH AUTOSEL 4.19 44/57] lkdtm: Add tests for NULL pointer dereference Sasha Levin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190330012854.32212-23-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=jaegeuk@kernel.org \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=shengyong1@huawei.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.