struct timespec is not y2038 safe. Transition vfs to use
y2038 safe struct timespec64 instead.

The change was made with the help of the following cocinelle
script. This catches about 80% of the changes.
All the header file and logic changes are included in the
first 5 rules. The rest are trivial substitutions.
I avoid changing any of the function signatures or any other
filesystem specific data structures to keep the patch simple
for review.

The script can be a little shorter by combining different cases.
But, this version was sufficient for my usecase.

virtual patch

@ depends on patch @
identifier now;
@@
- struct timespec
+ struct timespec64
  current_time ( ... )
  {
- struct timespec now = current_kernel_time();
+ struct timespec64 now = current_kernel_time64();
  ...
- return timespec_trunc(
+ return timespec64_trunc(
  ... );
  }

@ depends on patch @
identifier xtime;
@@
 struct \( iattr \| inode \| kstat \) {
 ...
-       struct timespec xtime;
+       struct timespec64 xtime;
 ...
 }

@ depends on patch @
identifier t;
@@
 struct inode_operations {
 ...
int (*update_time) (...,
-       struct timespec t,
+       struct timespec64 t,
...);
 ...
 }

@ depends on patch @
identifier t;
identifier fn_update_time =~ "update_time$";
@@
 fn_update_time (...,
- struct timespec *t,
+ struct timespec64 *t,
 ...) { ... }

@ depends on patch @
identifier t;
@@
lease_get_mtime( ... ,
- struct timespec *t
+ struct timespec64 *t
  ) { ... }

@te depends on patch forall@
identifier ts;
local idexpression struct inode *inode_node;
identifier i_xtime =~ "^i_[acm]time$";
identifier ia_xtime =~ "^ia_[acm]time$";
identifier fn_update_time =~ "update_time$";
identifier fn;
expression e, E3;
local idexpression struct inode *node1;
local idexpression struct inode *node2;
local idexpression struct iattr *attr1;
local idexpression struct iattr *attr2;
local idexpression struct iattr attr;
identifier i_xtime1 =~ "^i_[acm]time$";
identifier i_xtime2 =~ "^i_[acm]time$";
identifier ia_xtime1 =~ "^ia_[acm]time$";
identifier ia_xtime2 =~ "^ia_[acm]time$";
@@
(
(
- struct timespec ts;
+ struct timespec64 ts;
|
- struct timespec ts = current_time(inode_node);
+ struct timespec64 ts = current_time(inode_node);
)

<+... when != ts
(
- timespec_equal(&inode_node->i_xtime, &ts)
+ timespec64_equal(&inode_node->i_xtime, &ts)
|
- timespec_equal(&ts, &inode_node->i_xtime)
+ timespec64_equal(&ts, &inode_node->i_xtime)
|
- timespec_compare(&inode_node->i_xtime, &ts)
+ timespec64_compare(&inode_node->i_xtime, &ts)
|
- timespec_compare(&ts, &inode_node->i_xtime)
+ timespec64_compare(&ts, &inode_node->i_xtime)
|
ts = current_time(e)
|
fn_update_time(..., &ts,...)
|
inode_node->i_xtime = ts
|
node1->i_xtime = ts
|
ts = inode_node->i_xtime
|
<+... attr1->ia_xtime ...+> = ts
|
ts = attr1->ia_xtime
|
ts.tv_sec
|
ts.tv_nsec
|
btrfs_set_stack_timespec_sec(..., ts.tv_sec)
|
btrfs_set_stack_timespec_nsec(..., ts.tv_nsec)
|
- ts = timespec64_to_timespec(
+ ts =
...
-)
|
- ts = ktime_to_timespec(
+ ts = ktime_to_timespec64(
...)
|
- ts = E3
+ ts = timespec_to_timespec64(E3)
|
- ktime_get_real_ts(&ts)
+ ktime_get_real_ts64(&ts)
|
fn(...,
- ts
+ timespec64_to_timespec(ts)
,...)
)
...+>
(
<... when != ts
- return ts;
+ return timespec64_to_timespec(ts);
...>
)
|
- timespec_equal(&node1->i_xtime1, &node2->i_xtime2)
+ timespec64_equal(&node1->i_xtime2, &node2->i_xtime2)
|
- timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2)
+ timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2)
|
- timespec_compare(&node1->i_xtime1, &node2->i_xtime2)
+ timespec64_compare(&node1->i_xtime1, &node2->i_xtime2)
|
node1->i_xtime1 =
- timespec_trunc(attr1->ia_xtime1,
+ timespec64_trunc(attr1->ia_xtime1,
...)
|
- attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2,
+ attr1->ia_xtime1 =  timespec64_trunc(attr2->ia_xtime2,
...)
|
- ktime_get_real_ts(&attr1->ia_xtime1)
+ ktime_get_real_ts64(&attr1->ia_xtime1)
|
- ktime_get_real_ts(&attr.ia_xtime1)
+ ktime_get_real_ts64(&attr.ia_xtime1)
)

@ depends on patch @
struct inode *node;
struct iattr *attr;
identifier fn;
identifier i_xtime =~ "^i_[acm]time$";
identifier ia_xtime =~ "^ia_[acm]time$";
expression e;
@@
(
- fn(node->i_xtime);
+ fn(timespec64_to_timespec(node->i_xtime));
|
 fn(...,
- node->i_xtime);
+ timespec64_to_timespec(node->i_xtime));
|
- e = fn(attr->ia_xtime);
+ e = fn(timespec64_to_timespec(attr->ia_xtime));
)

@ depends on patch forall @
struct inode *node;
struct iattr *attr;
identifier i_xtime =~ "^i_[acm]time$";
identifier ia_xtime =~ "^ia_[acm]time$";
identifier fn;
@@
{
+ struct timespec ts;
<+...
(
+ ts = timespec64_to_timespec(node->i_xtime);
fn (...,
- &node->i_xtime,
+ &ts,
...);
|
+ ts = timespec64_to_timespec(attr->ia_xtime);
fn (...,
- &attr->ia_xtime,
+ &ts,
...);
)
...+>
}

@ depends on patch forall @
struct inode *node;
struct iattr *attr;
struct kstat *stat;
identifier ia_xtime =~ "^ia_[acm]time$";
identifier i_xtime =~ "^i_[acm]time$";
identifier xtime =~ "^[acm]time$";
identifier fn, ret;
@@
{
+ struct timespec ts;
<+...
(
+ ts = timespec64_to_timespec(node->i_xtime);
ret = fn (...,
- &node->i_xtime,
+ &ts,
...);
|
+ ts = timespec64_to_timespec(node->i_xtime);
ret = fn (...,
- &node->i_xtime);
+ &ts);
|
+ ts = timespec64_to_timespec(attr->ia_xtime);
ret = fn (...,
- &attr->ia_xtime,
+ &ts,
...);
|
+ ts = timespec64_to_timespec(attr->ia_xtime);
ret = fn (...,
- &attr->ia_xtime);
+ &ts);
|
+ ts = timespec64_to_timespec(stat->xtime);
ret = fn (...,
- &stat->xtime);
+ &ts);
)
...+>
}

@ depends on patch @
struct inode *node;
struct inode *node2;
identifier i_xtime1 =~ "^i_[acm]time$";
identifier i_xtime2 =~ "^i_[acm]time$";
identifier i_xtime3 =~ "^i_[acm]time$";
struct iattr *attrp;
struct iattr *attrp2;
struct iattr attr ;
identifier ia_xtime1 =~ "^ia_[acm]time$";
identifier ia_xtime2 =~ "^ia_[acm]time$";
struct kstat *stat;
struct kstat stat1;
struct timespec64 ts;
identifier xtime =~ "^[acmb]time$";
expression e;
@@
(
( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1  ;
|
 node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \);
|
 node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \);
|
 node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \);
|
 stat->xtime = node2->i_xtime1;
|
 stat1.xtime = node2->i_xtime1;
|
( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1  ;
|
( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2;
|
- e = node->i_xtime1;
+ e = timespec64_to_timespec( node->i_xtime1 );
|
- e = attrp->ia_xtime1;
+ e = timespec64_to_timespec( attrp->ia_xtime1 );
|
node->i_xtime1 = current_time(...);
|
 node->i_xtime2 = node->i_xtime1 = node->i_xtime3 =
- e;
+ timespec_to_timespec64(e);
|
 node->i_xtime1 = node->i_xtime3 =
- e;
+ timespec_to_timespec64(e);
|
- node->i_xtime1 = e;
+ node->i_xtime1 = timespec_to_timespec64(e);
)
Signed-off-by: NDeepa Dinamani <deepa.kernel@gmail.com>
Cc: <anton@tuxera.com>
Cc: <balbi@kernel.org>
Cc: <bfields@fieldses.org>
Cc: <darrick.wong@oracle.com>
Cc: <dhowells@redhat.com>
Cc: <dsterba@suse.com>
Cc: <dwmw2@infradead.org>
Cc: <hch@lst.de>
Cc: <hirofumi@mail.parknet.co.jp>
Cc: <hubcap@omnibond.com>
Cc: <jack@suse.com>
Cc: <jaegeuk@kernel.org>
Cc: <jaharkes@cs.cmu.edu>
Cc: <jslaby@suse.com>
Cc: <keescook@chromium.org>
Cc: <mark@fasheh.com>
Cc: <miklos@szeredi.hu>
Cc: <nico@linaro.org>
Cc: <reiserfs-devel@vger.kernel.org>
Cc: <richard@nod.at>
Cc: <sage@redhat.com>
Cc: <sfrench@samba.org>
Cc: <swhiteho@redhat.com>
Cc: <tj@kernel.org>
Cc: <trond.myklebust@primarydata.com>
Cc: <tytso@mit.edu>
Cc: <viro@zeniv.linux.org.uk>

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: NTheodore Ts'o <tytso@mit.edu>
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

f2fs doesn't allow abuse on atomic write class interface, so except
limiting in-mem pages' total memory usage capacity, we need to limit
atomic-write usage as well when filesystem is seriously fragmented,
otherwise we may run into infinite loop during foreground GC because
target blocks in victim segment are belong to atomic opened file for
long time.

Now, we will detect failure due to atomic write in foreground GC, if
the count exceeds threshold, we will drop all atomic written data in
cache, by this, I expect it can keep our system running safely to
prevent Dos attack.

In addition, his patch adds to show GC skip information in debugfs,
now it just shows count of skipped caused by atomic write.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

- rename is_valid_blkaddr() to is_valid_meta_blkaddr() for readability.
- introduce is_valid_blkaddr() for cleanup.

No logic change in this patch.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

i_current_depth is used only for directory inode, but its space is
shared with i_gc_failures field used for regular inode, in order to
avoid affecting i_gc_failures' value, this patch fixes to initialize
the union's fields according to inode type.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

syzbot has tested the proposed patch but the reproducer still triggered crash:
kernel BUG at fs/f2fs/inode.c:LINE!

F2FS-fs (loop1): invalid crc value
F2FS-fs (loop5): Magic Mismatch, valid(0xf2f52010) - read(0x0)
F2FS-fs (loop5): Can't find valid F2FS filesystem in 1th superblock
F2FS-fs (loop5): invalid crc value
------------[ cut here ]------------
kernel BUG at fs/f2fs/inode.c:238!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 4886 Comm: syz-executor1 Not tainted 4.17.0-rc1+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:do_read_inode fs/f2fs/inode.c:238 [inline]
RIP: 0010:f2fs_iget+0x3307/0x3ca0 fs/f2fs/inode.c:313
RSP: 0018:ffff8801c44a70e8 EFLAGS: 00010293
RAX: ffff8801ce208040 RBX: ffff8801b3621080 RCX: ffffffff82eace18
F2FS-fs (loop2): Magic Mismatch, valid(0xf2f52010) - read(0x0)
RDX: 0000000000000000 RSI: ffffffff82eaf047 RDI: 0000000000000007
RBP: ffff8801c44a7410 R08: ffff8801ce208040 R09: ffffed0039ee4176
R10: ffffed0039ee4176 R11: ffff8801cf720bb7 R12: ffff8801c0efa000
R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000
FS:  00007f753aa9d700(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000
------------[ cut here ]------------
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
kernel BUG at fs/f2fs/inode.c:238!
CR2: 0000000001b03018 CR3: 00000001c8b74000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 f2fs_fill_super+0x4377/0x7bf0 fs/f2fs/super.c:2842
 mount_bdev+0x30c/0x3e0 fs/super.c:1165
 f2fs_mount+0x34/0x40 fs/f2fs/super.c:3020
 mount_fs+0xae/0x328 fs/super.c:1268
 vfs_kern_mount.part.34+0xd4/0x4d0 fs/namespace.c:1037
 vfs_kern_mount fs/namespace.c:1027 [inline]
 do_new_mount fs/namespace.c:2517 [inline]
 do_mount+0x564/0x3070 fs/namespace.c:2847
 ksys_mount+0x12d/0x140 fs/namespace.c:3063
 __do_sys_mount fs/namespace.c:3077 [inline]
 __se_sys_mount fs/namespace.c:3074 [inline]
 __x64_sys_mount+0xbe/0x150 fs/namespace.c:3074
 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457daa
RSP: 002b:00007f753aa9cba8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a5
RAX: ffffffffffffffda RBX: 0000000020000000 RCX: 0000000000457daa
RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007f753aa9cbf0
RBP: 0000000000000064 R08: 0000000020016a00 R09: 0000000020000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003
R13: 0000000000000064 R14: 00000000006fcb80 R15: 0000000000000000
RIP: do_read_inode fs/f2fs/inode.c:238 [inline] RSP: ffff8801c44a70e8
RIP: f2fs_iget+0x3307/0x3ca0 fs/f2fs/inode.c:313 RSP: ffff8801c44a70e8
invalid opcode: 0000 [#2] SMP KASAN
---[ end trace 1cbcbec2156680bc ]---

Reported-and-tested-by: syzbot+41a1b341571f0952badb@syzkaller.appspotmail.com
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

syzbot hit the following crash on upstream commit
83beed7b (Fri Apr 20 17:56:32 2018 +0000)
Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal
syzbot dashboard link: https://syzkaller.appspot.com/bug?extid=d154ec99402c6f628887

C reproducer: https://syzkaller.appspot.com/x/repro.c?id=5414336294027264
syzkaller reproducer: https://syzkaller.appspot.com/x/repro.syz?id=5471683234234368
Raw console output: https://syzkaller.appspot.com/x/log.txt?id=5436660795834368
Kernel config: https://syzkaller.appspot.com/x/.config?id=1808800213120130118
compiler: gcc (GCC) 8.0.1 20180413 (experimental)

IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+d154ec99402c6f628887@syzkaller.appspotmail.com
It will help syzbot understand when the bug is fixed. See footer for details.
If you forward the report, please keep this part and the footer.

F2FS-fs (loop0): Magic Mismatch, valid(0xf2f52010) - read(0x0)
F2FS-fs (loop0): Can't find valid F2FS filesystem in 1th superblock
F2FS-fs (loop0): invalid crc value
------------[ cut here ]------------
kernel BUG at fs/f2fs/node.c:1185!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 4549 Comm: syzkaller704305 Not tainted 4.17.0-rc1+ #10
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:__get_node_page+0xb68/0x16e0 fs/f2fs/node.c:1185
RSP: 0018:ffff8801d960e820 EFLAGS: 00010293
RAX: ffff8801d88205c0 RBX: 0000000000000003 RCX: ffffffff82f6cc06
RDX: 0000000000000000 RSI: ffffffff82f6d5e8 RDI: 0000000000000004
RBP: ffff8801d960ec30 R08: ffff8801d88205c0 R09: ffffed003b5e46c2
R10: 0000000000000003 R11: 0000000000000003 R12: ffff8801a86e00c0
R13: 0000000000000001 R14: ffff8801a86e0530 R15: ffff8801d9745240
FS:  000000000072c880(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f3d403209b8 CR3: 00000001d8f3f000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 get_node_page fs/f2fs/node.c:1237 [inline]
 truncate_xattr_node+0x152/0x2e0 fs/f2fs/node.c:1014
 remove_inode_page+0x200/0xaf0 fs/f2fs/node.c:1039
 f2fs_evict_inode+0xe86/0x1710 fs/f2fs/inode.c:547
 evict+0x4a6/0x960 fs/inode.c:557
 iput_final fs/inode.c:1519 [inline]
 iput+0x62d/0xa80 fs/inode.c:1545
 f2fs_fill_super+0x5f4e/0x7bf0 fs/f2fs/super.c:2849
 mount_bdev+0x30c/0x3e0 fs/super.c:1164
 f2fs_mount+0x34/0x40 fs/f2fs/super.c:3020
 mount_fs+0xae/0x328 fs/super.c:1267
 vfs_kern_mount.part.34+0xd4/0x4d0 fs/namespace.c:1037
 vfs_kern_mount fs/namespace.c:1027 [inline]
 do_new_mount fs/namespace.c:2518 [inline]
 do_mount+0x564/0x3070 fs/namespace.c:2848
 ksys_mount+0x12d/0x140 fs/namespace.c:3064
 __do_sys_mount fs/namespace.c:3078 [inline]
 __se_sys_mount fs/namespace.c:3075 [inline]
 __x64_sys_mount+0xbe/0x150 fs/namespace.c:3075
 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x443dea
RSP: 002b:00007ffcc7882368 EFLAGS: 00000297 ORIG_RAX: 00000000000000a5
RAX: ffffffffffffffda RBX: 0000000020000c00 RCX: 0000000000443dea
RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffcc7882370
RBP: 0000000000000003 R08: 0000000020016a00 R09: 000000000000000a
R10: 0000000000000000 R11: 0000000000000297 R12: 0000000000000004
R13: 0000000000402ce0 R14: 0000000000000000 R15: 0000000000000000
RIP: __get_node_page+0xb68/0x16e0 fs/f2fs/node.c:1185 RSP: ffff8801d960e820
---[ end trace 4edbeb71f002bb76 ]---

Reported-and-tested-by: syzbot+d154ec99402c6f628887@syzkaller.appspotmail.com
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

In the structure of f2fs_inode, i_extra_size's type is __le16,
so we should keep type consistent when using it.

Fixes: 704956ec ("f2fs: support inode checksum")
Signed-off-by: NZhikang Zhang <zhangzhikang1@huawei.com>
Signed-off-by: NYunlei He <heyunlei@huawei.com>
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Related to https://lkml.org/lkml/2018/4/8/661

Sometimes, we need to write meta data to new allocated block address,
then we will allocate a zeroed page in inner inode's address space, and
fill partial data in it, and leave other place with zero value which means
some fields are initial status.

There are two inner inodes (meta inode and node inode) setting __GFP_ZERO,
I have just checked them, for both of them, we can avoid using __GFP_ZERO,
and do initialization by ourselves to avoid unneeded/redundant zeroing
from mm.

Cc: <stable@vger.kernel.org>
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Previously, we use generic FS_*_FL defined by vfs to indicate inode status
for each bit of i_flags, so f2fs's flag status definition is tied to vfs'
one, it will be hard for f2fs to reuse bits f2fs never used to indicate
new status..

In order to solve this issue, we introduce private inode status mapping,
Note, for these bits have already been persisted into disk, we should
never change their definition, for other ones, we can remap them for
later new coming status.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This fixes xfstests/generic/392.

The failure was caused by different times between 1) one marked in the last
fsync(2) call and 2) the other given by roll-forward recovery after power-cut.
The reason was that we skipped updating inode block at 1), since its i_size
was recoverable along with 4KB-aligned data writes, which was fixed by:
  "f2fs: fix a wrong condition in f2fs_skip_inode_update"
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

When setting COLD_BIT_SHIFT flag in node block, we only need to call
set_cold_node() in new_node_page() and recover_inode_page() during
node page initialization. So remove unneeded set_cold_node() in other
places.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Previous dentry page uses highmem, which will cause panic in platforms
using highmem (such as arm), since the address space of dentry pages
from highmem directly goes into the decryption path via the function
fscrypt_fname_disk_to_usr. But sg_init_one assumes the address is not
from highmem, and then cause panic since it doesn't call kmap_high but
kunmap_high is triggered at the end. To fix this problem in a simple
way, this patch avoids to put dentry page in pagecache into highmem.
Signed-off-by: NYunlong Song <yunlong.song@huawei.com>
Reviewed-by: NChao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: fix coding style]
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch adds creation time field in inode layout to support showing
kstat.btime in ->statx.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Now, we invoke f2fs_mark_inode_dirty_sync() to make an inode dirty in
advance of creating a new node page for the inode. By this, some inodes
whose node page is not created yet can be linked into the global dirty
list.

If the checkpoint is executed at this moment, the inode will be written
back by writeback_single_inode() and finally update_inode_page() will
fail to detach the inode from the global dirty list because the inode
doesn't have a node page.

The problem is that the inode's state in VFS layer will become clean
after execution of writeback_single_inode() and it's still linked in
the global dirty list of f2fs and this will cause a kernel panic.

So, we will prevent the newly created inode from being dirtied during
the FI_NEW_INODE flag of the inode is set. We will make it dirty
right after the flag is cleared.
Signed-off-by: NDaeho Jeong <daeho.jeong@samsung.com>
Signed-off-by: NYoungjin Gil <youngjin.gil@samsung.com>
Tested-by: NHobin Woo <hobin.woo@samsung.com>
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

fscrypt_put_encryption_info() is only called when evicting an inode, so
the 'struct fscrypt_info *ci' parameter is always NULL, and there cannot
be races with other threads.  This was cruft left over from the broken
key revocation code.  Remove the unused parameter and the cmpxchg().

Also remove the #ifdefs around the fscrypt_put_encryption_info() calls,
since fscrypt_notsupp.h defines a no-op stub for it.
Signed-off-by: NEric Biggers <ebiggers@google.com>
Signed-off-by: NTheodore Ts'o <tytso@mit.edu>

-Thread A                             Thread B

-write_checkpoint
 -block_operations
  -f2fs_unlock_all                    -f2fs_sync_file
                                       -f2fs_write_inode
                                        -f2fs_inode_synced
    -f2fs_sync_inode_meta
     -sync_node_pages
                                        -set_page_drity

In this case, if sudden power off without next new checkpoint,
the last inode page update will lost. wb_writeback is same with
fsync.

Yunlei also reproduced the bug by:

@@ -366,7 +366,7 @@ int update_inode(struct inode *inode, struct page *node_page)
        struct extent_tree *et = F2FS_I(inode)->extent_tree;

        f2fs_inode_synced(inode);
-
+       msleep(10000);
        f2fs_wait_on_page_writeback(node_page, NODE, true);

shell 1:                                       shell2:

dd if=/dev/zero of=./test bs=1M count=10
sync
echo "hello" >> ./test
fsync test  // sleep 10s
                                               sync //return quickly
echo c > /proc/sysrq-trigger
Signed-off-by: NYunlei He <heyunlei@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Now, in product, more and more features based on file encryption were
introduced, their demand of xattr space is increasing, however, inline
xattr has fixed-size of 200 bytes, once inline xattr space is full, new
increased xattr data would occupy additional xattr block which may bring
us more space usage and performance regression during persisting.

In order to resolve above issue, it's better to expand inline xattr size
flexibly according to user's requirement.

So this patch introduces new filesystem feature 'flexible inline xattr',
and new mount option 'inline_xattr_size=%u', once mkfs enables the
feature, we can use the option to make f2fs supporting flexible inline
xattr size.

To support this feature, we add extra attribute i_inline_xattr_size in
inode layout, indicating that how many space inline xattr borrows from
block address mapping space in inode layout, by this, we can easily
locate and store flexible-sized inline xattr data in inode.

Inode disk layout:
  +----------------------+
  | .i_mode              |
  | ...                  |
  | .i_ext               |
  +----------------------+
  | .i_extra_isize       |
  | .i_inline_xattr_size |-----------+
  | ...                  |           |
  +----------------------+           |
  | .i_addr              |           |
  |  - block address or  |           |
  |  - inline data       |           |
  +----------------------+<---+      v
  |    inline xattr      |    +---inline xattr range
  +----------------------+<---+
  | .i_nid               |
  +----------------------+
  |   node_footer        |
  | (nid, ino, offset)   |
  +----------------------+

Note that, we have to cnosider backward compatibility which reserved
inline_data space, 200 bytes, all the time, reported by Sheng Yong.

Previous inline data or directory always reserved 200 bytes in inode layout,
even if inline_xattr is disabled. In order to keep inline_dentry's structure
for backward compatibility, we get the space back only from inline_data.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Reported-by: NSheng Yong <shengyong1@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

When doing fault injection test, f2fs_evict_inode() didn't remove gdirty_list
which incurs a kernel panic due to wrong pointer access.
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Introduce a flag S_ENCRYPTED which can be set in ->i_flags to indicate
that the inode is encrypted using the fscrypt (fs/crypto/) mechanism.

Checking this flag will give the same information that
inode->i_sb->s_cop->is_encrypted(inode) currently does, but will be more
efficient.  This will be useful for adding higher-level helper functions
for filesystems to use.  For example we'll be able to replace this:

	if (ext4_encrypted_inode(inode)) {
		ret = fscrypt_get_encryption_info(inode);
		if (ret)
			return ret;
		if (!fscrypt_has_encryption_key(inode))
			return -ENOKEY;
	}

with this:

	ret = fscrypt_require_key(inode);
	if (ret)
		return ret;

... since we'll be able to retain the fast path for unencrypted files as
a single flag check, using an inline function.  This wasn't possible
before because we'd have had to frequently call through the
->i_sb->s_cop->is_encrypted function pointer, even when the encryption
support was disabled or not being used.

Note: we don't define S_ENCRYPTED to 0 if CONFIG_FS_ENCRYPTION is
disabled because we want to continue to return an error if an encrypted
file is accessed without encryption support, rather than pretending that
it is unencrypted.
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Acked-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NEric Biggers <ebiggers@google.com>
Signed-off-by: NTheodore Ts'o <tytso@mit.edu>

When multiple device feature is enabled, during ->fsync we will issue
flush in all devices to make sure node/data of the file being persisted
into storage. But some flushes of device could be unneeded as file's
data may be not writebacked into those devices. So this patch adds and
manage bitmap per inode in global cache to indicate which device is
dirty and it needs to issue flush during ->fsync, hence, we could improve
performance of fsync in scenario of multiple device.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Add a bugon in f2fs_evict_inode to detect inconsistent status between
inode cache and related node page cache.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

If another thread already made the page dirtied or writebacked, we must avoid
to verify checksum. If we got an error, we need to remove its uptodate as well.
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch adds to support inode checksum in f2fs.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
[Jaegeuk Kim: fix verification flow]
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch adds to support plain project quota.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

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: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch tries to make below macros calculating max inline size,
inline dentry field size considerring reserving size-changeable
space:
- MAX_INLINE_DATA
- NR_INLINE_DENTRY
- INLINE_DENTRY_BITMAP_SIZE
- INLINE_RESERVED_SIZE

Then, when inline_{data,dentry} options is enabled, it allows us to
reserve inline space with different size flexibly for adding newly
introduced inode attribute.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch adds to support plain user/group quota.

Change Note by Jaegeuk Kim.

- Use f2fs page cache for quota files in order to consider garbage collection.
  so, quota files are not tolerable for sudden power-cuts, so user needs to do
  quotacheck.

- setattr() calls dquot_transfer which will transfer inode->i_blocks.
  We can't reclaim that during f2fs_evict_inode(). So, we need to count
  node blocks as well in order to match i_blocks with dquot's space.

  Note that, Chao wrote a patch to count inode->i_blocks without inode block.
  (f2fs: don't count inode block in in-memory inode.i_blocks)

- in f2fs_remount, we need to make RW in prior to dquot_resume.

- handle fault_injection case during f2fs_quota_off_umount

- TODO: Project quota
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Previously, we count all inode consumed blocks including inode block,
xattr block, index block, data block into i_blocks, for other generic
filesystems, they won't count inode block into i_blocks, so for
userspace applications or quota system, they may detect incorrect block
count according to i_blocks value in inode.

This patch changes to count all blocks into inode.i_blocks excluding
inode block, for on-disk i_blocks, we keep counting inode block for
backward compatibility.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Both in memory or on disk, generic filesystems record i_blocks with
512bytes sized sector count, also VFS sub module such as disk quota
follows this rule, but f2fs records it with 4096bytes sized block
count, this difference leads to that once we use dquota's function
which inc/dec iblocks, it will make i_blocks of f2fs being inconsistent
between in memory and on disk.

In order to resolve this issue, this patch changes to make in-memory
i_blocks of f2fs recording sector count instead of block count,
meanwhile leaving on-disk i_blocks recording block count.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

For example,

f2fs_create
 - new_node_page is failed
 - handle_failed_inode
  - skip to add it into orphan list, since ni.blk_addr == NULL_ADDR
   : set_inode_flag(inode, FI_FREE_NID)

f2fs_evict_inode
 - EIO due to fault injection
 - f2fs_bug_on() is triggered

So, we don't need to call f2fs_bug_on in this case.
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch fixes missing inode flag loaded from disk, reported by Tom.

[tom@localhost ~]$ sudo mount /dev/loop0 /mnt/
[tom@localhost ~]$ sudo chown tom:tom /mnt/
[tom@localhost ~]$ touch /mnt/testfile
[tom@localhost ~]$ sudo chattr +i /mnt/testfile
[tom@localhost ~]$ echo test > /mnt/testfile
bash: /mnt/testfile: Operation not permitted
[tom@localhost ~]$ rm /mnt/testfile
rm: cannot remove '/mnt/testfile': Operation not permitted
[tom@localhost ~]$ sudo umount /mnt/
[tom@localhost ~]$ sudo mount /dev/loop0 /mnt/
[tom@localhost ~]$ lsattr /mnt/testfile
----i-------------- /mnt/testfile
[tom@localhost ~]$ echo test > /mnt/testfile
[tom@localhost ~]$ rm /mnt/testfile
[tom@localhost ~]$ sudo umount /mnt/

Cc: stable@vger.kernel.org
Reported-by: NTom Yan <tom.ty89@outlook.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch also reverts d0db7703 ("f2fs: do SSR in higher priority").

This patch fixes out of free segments caused by many small file creation by
1) mkfs -s 1 2G
2) mount
3) untar
 - preoduce 60000 small files burstly
4) sync
 - flush node pages
 - flush imeta

Here, when we do f2fs_balance_fs, we missed # of imeta blocks, resulting in
skipping to check has_not_enough_free_secs.

Another test is done by
1) mkfs -s 12 2G
2) mount
3) untar
 - preoduce 60000 small files burstly
4) sync
 - flush node pages
 - flush imeta

In this case, this patch also fixes wrong block allocation under large section
size.
Reported-by: NWilliam Brana <wbrana@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch fixes the following scenario.

- f2fs_create/f2fs_mkdir             - write_checkpoint
 - f2fs_mark_inode_dirty_sync         - block_operations
                                       - f2fs_lock_all
                                       - f2fs_sync_inode_meta
                                        - f2fs_unlock_all
                                        - sync_inode_metadata
 - f2fs_lock_op
                                         - f2fs_write_inode
                                          - update_inode_page
                                           - get_node_page
                                             return -ENOENT
 - new_inode_page
  - fill_node_footer
 - f2fs_mark_inode_dirty_sync
 - ...
 - f2fs_unlock_op
                                          - f2fs_inode_synced
                                       - f2fs_lock_all
                                       - do_checkpoint

In this checkpoint, we can get an inode page which contains zeros having valid
node footer only.

Cc: <stable@vger.kernel.org>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

The previous one was not a proper location to inject an error, since there
is no point to get errors. Instead, we can emulate EIO during truncation,
and the below logic should handle it correctly.
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

If f2fs_new_inode() is failed, the bad inode will invalidate 0'th node page
during f2fs_evict_inode(), which doesn't need to do.
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

Previously kernel message can show that in which function we do the
injection, but unfortunately, most of the caller are the same, for
tracking more information of injection path, it needs to show upper
caller's name. This patch supports that ability.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

We should record updating status of inode only for living inode, for those
unlinked inode it needs to clear its ino cache, otherwise after the ino
was been reused, it will cause unneeded node page writing during ->fsync.
Signed-off-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This patch tries to make more clean inodes when flushing dirty inodes in
checkpoint.
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>

This is to avoid no free segment bug during checkpoint caused by a number of
dirty inodes.

The case was reported by Chao like this.
1. mount with lazytime option
2. fill 4k file until disk is full
3. sync filesystem
4. read all files in the image
5. umount

In this case, we actually don't need to flush dirty inode to inode page during
checkpoint.
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NJaegeuk Kim <jaegeuk@kernel.org>