treewide: Use array_size() in f2fs_kmalloc()

The f2fs_kmalloc() function has no 2-factor argument form, so
multiplication factors need to be wrapped in array_size(). This patch
replaces cases of:

        f2fs_kmalloc(handle, a * b, gfp)

with:
        f2fs_kmalloc(handle, array_size(a, b), gfp)

as well as handling cases of:

        f2fs_kmalloc(handle, a * b * c, gfp)

with:

        f2fs_kmalloc(handle, array3_size(a, b, c), gfp)

This does, however, attempt to ignore constant size factors like:

        f2fs_kmalloc(handle, 4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
expression HANDLE;
type TYPE;
expression THING, E;
@@

(
  f2fs_kmalloc(HANDLE,
- (sizeof(TYPE)) * E
+ sizeof(TYPE) * E
  , ...)
|
  f2fs_kmalloc(HANDLE,
- (sizeof(THING)) * E
+ sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression HANDLE;
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  f2fs_kmalloc(HANDLE,
- sizeof(u8) * (COUNT)
+ COUNT
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(__u8) * (COUNT)
+ COUNT
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(char) * (COUNT)
+ COUNT
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(unsigned char) * (COUNT)
+ COUNT
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(u8) * COUNT
+ COUNT
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(__u8) * COUNT
+ COUNT
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(char) * COUNT
+ COUNT
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(unsigned char) * COUNT
+ COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
expression HANDLE;
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * (COUNT_ID)
+ array_size(COUNT_ID, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * COUNT_ID
+ array_size(COUNT_ID, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * (COUNT_CONST)
+ array_size(COUNT_CONST, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * COUNT_CONST
+ array_size(COUNT_CONST, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * (COUNT_ID)
+ array_size(COUNT_ID, sizeof(THING))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * COUNT_ID
+ array_size(COUNT_ID, sizeof(THING))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * (COUNT_CONST)
+ array_size(COUNT_CONST, sizeof(THING))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * COUNT_CONST
+ array_size(COUNT_CONST, sizeof(THING))
  , ...)
)

// 2-factor product, only identifiers.
@@
expression HANDLE;
identifier SIZE, COUNT;
@@

  f2fs_kmalloc(HANDLE,
- SIZE * COUNT
+ array_size(COUNT, SIZE)
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression HANDLE;
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * (COUNT) * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * (COUNT) * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * COUNT * (STRIDE)
+ array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING) * COUNT * STRIDE
+ array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression HANDLE;
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(THING1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE1) * sizeof(THING2) * COUNT
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  f2fs_kmalloc(HANDLE,
- sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+ array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
expression HANDLE;
identifier STRIDE, SIZE, COUNT;
@@

(
  f2fs_kmalloc(HANDLE,
- (COUNT) * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  f2fs_kmalloc(HANDLE,
- COUNT * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  f2fs_kmalloc(HANDLE,
- COUNT * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  f2fs_kmalloc(HANDLE,
- (COUNT) * (STRIDE) * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  f2fs_kmalloc(HANDLE,
- COUNT * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  f2fs_kmalloc(HANDLE,
- (COUNT) * STRIDE * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  f2fs_kmalloc(HANDLE,
- (COUNT) * (STRIDE) * (SIZE)
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  f2fs_kmalloc(HANDLE,
- COUNT * STRIDE * SIZE
+ array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products
// when they're not all constants...
@@
expression HANDLE;
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  f2fs_kmalloc(HANDLE, C1 * C2 * C3, ...)
|
  f2fs_kmalloc(HANDLE,
- E1 * E2 * E3
+ array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants.
@@
expression HANDLE;
expression E1, E2;
constant C1, C2;
@@

(
  f2fs_kmalloc(HANDLE, C1 * C2, ...)
|
  f2fs_kmalloc(HANDLE,
- E1 * E2
+ array_size(E1, E2)
  , ...)
)

Signed-off-by: Kees Cook <keescook@chromium.org>

overflow.h: Add allocation size calculation helpers

In preparation for replacing unchecked overflows for memory allocations,
this creates helpers for the 3 most common calculations:

array_size(a, b): 2-dimensional array
array3_size(a, b, c): 3-dimensional array
struct_size(ptr, member, n): struct followed by n-many trailing members

Each of these return SIZE_MAX on overflow instead of wrapping around.

(Additionally renames a variable named "array_size" to avoid future
collision.)

Co-developed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Kees Cook <keescook@chromium.org>

f2fs: fix to clear FI_VOLATILE_FILE correctly

Thread A Thread B
- f2fs_release_file
 - clear_inode_flag(FI_VOLATILE_FILE)
- wb_writeback
 - writeback_sb_inodes
  - __writeback_single_inode
   - do_writepages
    - f2fs_write_data_pages
     - __write_data_page
     all volatile file's pages
     are writebacked to storage
 - set_inode_flag(FI_DROP_CACHE)
 - filemap_fdatawrite

There is a hole that mm can flush all dirty pages of volatile file as
inode is not tagged with both FI_VOLATILE_FILE and FI_DROP_CACHE flags,
we should never writeback the page #0 and also it's unneeded to writeback
other pages.

This patch adjusts to relocate clear_inode_flag(FI_VOLATILE_FILE), so that
FI_VOLATILE_FILE flag can be remained before all dirty pages were dropped
to avoid issue.

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

f2fs: let sync node IO interrupt async one

Although mixed sync/async IOs can have continuous LBA, as they have
different IO priority, block IO scheduler will add them into different
queues and commit them separately, result in splited IOs which causes
wrose performance.

This patch gives high priority to synchronous IO of nodes, means that
once synchronous flow starts, it can interrupt asynchronous writeback
flow of system flusher, so more big IOs can be expected.

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

f2fs: don't change wbc->sync_mode

We should never falsify wbc->sync_mode passed from mm, otherwise
mm can trigger writeback with wrong IO priority.

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

f2fs: fix to update mtime correctly

If we change system time to the past, get_mtime() will return a
overflowed time, and SIT_I(sbi)->max_mtime will be udpated
incorrectly, this patch fixes the two issues.

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

fs: f2fs: insert space around that ':' and ', '

clean up checkpatch error:
ERROR: space required after that ':'
ERROR: space required after that ','

Signed-off-by: youngjun yoo <youngjun.willow@gmail.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

fs: f2fs: add missing blank lines after declarations

clean up checkpatch warning:
WARNING: Missing a blank line after declarations

Signed-off-by: youngjun yoo <youngjun.willow@gmail.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

fs: f2fs: changed variable type of offset "unsigned" to "loff_t"

clean up checkpatch warning:
WARNING: Prefer 'unsigned int' to bare use of 'unsigned'

Signed-off-by: youngjun yoo <youngjun.willow@gmail.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

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>

f2fs: make set_de_type() static

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

f2fs: make __f2fs_write_data_pages() static

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

f2fs: fix to avoid accessing cross the boundary

Configure io_bits with 2 and enable LFS mode, generic/017 reports below dmesg:

BUG: unable to handle kernel NULL pointer dereference at 00000039
*pdpt = 000000002fcb2001 *pde = 0000000000000000
Oops: 0000 [#1] PREEMPT SMP
Modules linked in: crc32_generic zram f2fs(O) bnep rfcomm bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi pcbc snd_seq joydev aesni_intel aes_i586 snd_seq_device snd_timer crypto_simd cryptd snd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic usbhid psmouse hid e1000
CPU: 2 PID: 20779 Comm: xfs_io Tainted: G           O      4.17.0-rc2 #38
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
EIP: is_checkpointed_data+0x84/0xd0 [f2fs]
EFLAGS: 00010207 CPU: 2
EAX: 00000000 EBX: f5cd7000 ECX: fffffe32 EDX: 00000039
ESI: 000001cd EDI: ec95fb6c EBP: e264bd80 ESP: e264bd6c
 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
CR0: 80050033 CR2: 00000039 CR3: 2fe55660 CR4: 000406f0
Call Trace:
 __exchange_data_block+0xb3f/0x1000 [f2fs]
 f2fs_fallocate+0xab9/0x16b0 [f2fs]
 vfs_fallocate+0x17c/0x2d0
 ksys_fallocate+0x42/0x70
 sys_fallocate+0x31/0x40
 do_fast_syscall_32+0xaa/0x22c
 entry_SYSENTER_32+0x4c/0x7b
EIP: 0xb7f98c51
EFLAGS: 00000293 CPU: 2
EAX: ffffffda EBX: 00000003 ECX: 00000008 EDX: 01001000
ESI: 00000000 EDI: 00001000 EBP: 00000000 ESP: bfc0357c
 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b
Code: 00 00 d3 e8 8b 4d ec 2b 02 8b 55 f0 6b c0 1c 03 41 70 29 d6 8b 93 d0 06 00 00 8b 40 0c 83 ea 01 21 d6 89 f2 89 f1 c1 ea 03 f7 d1 <0f> be 14 10 83 e1 07 b8 01 00 00 00 d3 e0 85 c2 89 f8 0f 95 c3
EIP: is_checkpointed_data+0x84/0xd0 [f2fs] SS:ESP: 0068:e264bd6c
CR2: 0000000000000039
---[ end trace 9a4d4087cce6080a ]---

This is because in recovery flow of __exchange_data_block, we didn't pass olen to
__roll_back_blkaddrs, instead we passed len, which indicates wrong array size, result
in copying random block address into dnode page.

Later, once that random block address was accessed by is_checkpointed_data, it can
cause NULL pointer dereference.

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

f2fs: fix to let caller retry allocating block address

Configure io_bits with 2 and enable LFS mode, generic/013 reports below dmesg:

BUG: unable to handle kernel NULL pointer dereference at 00000104
*pdpt = 0000000029b7b001 *pde = 0000000000000000
Oops: 0002 [#1] PREEMPT SMP
Modules linked in: crc32_generic zram f2fs(O) rfcomm bnep bluetooth ecdh_generic snd_intel8x0 snd_ac97_codec ac97_bus snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq pcbc joydev snd_seq_device aesni_intel snd_timer aes_i586 snd crypto_simd cryptd soundcore i2c_piix4 serio_raw mac_hid video parport_pc ppdev lp parport hid_generic psmouse usbhid hid e1000
CPU: 0 PID: 11161 Comm: fsstress Tainted: G           O      4.17.0-rc2 #38
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs]
EFLAGS: 00010206 CPU: 0
EAX: e863dcd8 EBX: 00000000 ECX: 00000100 EDX: 00000200
ESI: e863dcf4 EDI: f6f82768 EBP: e863dbb0 ESP: e863db74
 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
CR0: 80050033 CR2: 00000104 CR3: 29a62020 CR4: 000406f0
Call Trace:
 do_write_page+0x6f/0xc0 [f2fs]
 write_data_page+0x4a/0xd0 [f2fs]
 do_write_data_page+0x327/0x630 [f2fs]
 __write_data_page+0x34b/0x820 [f2fs]
 __f2fs_write_data_pages+0x42d/0x8c0 [f2fs]
 f2fs_write_data_pages+0x27/0x30 [f2fs]
 do_writepages+0x1a/0x70
 __filemap_fdatawrite_range+0x94/0xd0
 filemap_write_and_wait_range+0x3d/0xa0
 __generic_file_write_iter+0x11a/0x1f0
 f2fs_file_write_iter+0xdd/0x3b0 [f2fs]
 __vfs_write+0xd2/0x150
 vfs_write+0x9b/0x190
 ksys_write+0x45/0x90
 sys_write+0x16/0x20
 do_fast_syscall_32+0xaa/0x22c
 entry_SYSENTER_32+0x4c/0x7b
EIP: 0xb7fc8c51
EFLAGS: 00000246 CPU: 0
EAX: ffffffda EBX: 00000003 ECX: 09cde000 EDX: 00001000
ESI: 00000003 EDI: 00001000 EBP: 00000000 ESP: bfbded38
 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b
Code: e8 f9 77 34 c9 8b 45 e0 8b 80 b8 00 00 00 39 45 d8 0f 84 bb 02 00 00 8b 45 e0 8b 80 b8 00 00 00 8d 50 d8 8b 08 89 55 f0 8b 50 04 <89> 51 04 89 0a c7 00 00 01 00 00 c7 40 04 00 02 00 00 8b 45 dc
EIP: f2fs_submit_page_write+0x28d/0x550 [f2fs] SS:ESP: 0068:e863db74
CR2: 0000000000000104
---[ end trace 4cac79c0d1305ee6 ]---

allocate_data_block will submit all sequential pending IOs sorted by a
FIFO list, If we failed to submit other user's IO due to unaligned write,
we will retry to allocate new block address for current IO, then it will
initialize fio.list again, if fio was in the list before, it can break
FIFO list, result in above panic.

Thread A Thread B
- do_write_page
 - allocate_data_block
  - list_add_tail
  : fioA cached in FIFO list.
- do_write_page
 - allocate_data_block
  - list_add_tail
  : fioB cached in FIFO list.
 - f2fs_submit_page_write
 : fail to submit IO
 - allocate_data_block
  - INIT_LIST_HEAD
 - f2fs_submit_page_write
  - list_del  <-- NULL pointer dereference

This patch adds fio.retry parameter to indicate failure status for each
IO, and avoid bailing out if there is still pending IO in FIFO list for
fixing.

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

disable loading f2fs module on PAGE_SIZE > 4KB

The following patch disables loading of f2fs module on architectures
which have PAGE_SIZE > 4096 , since it is impossible to mount f2fs on
such architectures , log messages are:

mount: /mnt: wrong fs type, bad option, bad superblock on
/dev/vdiskb1, missing codepage or helper program, or other error.
/dev/vdiskb1: F2FS filesystem,
UUID=1d8b9ca4-2389-4910-af3b-10998969f09c, volume name ""

May 15 18:03:13 ttip kernel: F2FS-fs (vdiskb1): Invalid
page_cache_size (8192), supports only 4KB
May 15 18:03:13 ttip kernel: F2FS-fs (vdiskb1): Can't find valid F2FS
filesystem in 1th superblock
May 15 18:03:13 ttip kernel: F2FS-fs (vdiskb1): Invalid
page_cache_size (8192), supports only 4KB
May 15 18:03:13 ttip kernel: F2FS-fs (vdiskb1): Can't find valid F2FS
filesystem in 2th superblock
May 15 18:03:13 ttip kernel: F2FS-fs (vdiskb1): Invalid
page_cache_size (8192), supports only 4KB

which was introduced by git commit 5c9b469295fb6b10d98923eab5e79c4edb80ed20

tested on git kernel 4.17.0-rc6-00309-gec30dcf7f425

with patch applied:

modprobe: ERROR: could not insert 'f2fs': Invalid argument
May 28 01:40:28 v215 kernel: F2FS not supported on PAGE_SIZE(8192) != 4096

Signed-off-by: Anatoly Pugachev <matorola@gmail.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix error path of move_data_page

This patch fixes error path of move_data_page:
- clear cold data flag if it fails to write page.
- redirty page for non-ENOMEM case.

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

f2fs: don't drop dentry pages after fs shutdown

As description in commit "f2fs: don't drop any page on f2fs_cp_error()
case":

"We still provide readdir() after shtudown, so we should keep pages to
avoid additional IOs."

In order to provider lastest directory structure, let's keep dentry
pages in cache after fs shutdown.

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

f2fs: fix to avoid race during access gc_thread pointer

Thread A Thread B
- f2fs_remount
 - stop_gc_thread
- f2fs_sbi_store
   sbi->gc_thread = NULL;
  access sbi->gc_thread->gc_*

Previously, we allocate memory for sbi->gc_thread based on background
gc thread mount option, the memory can be released if we turn off
that mount option, but still there are several places access gc_thread
pointer without considering race condition, result in NULL point
dereference.

In order to fix this issue, use sb->s_umount to exclude those operations.

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

f2fs: clean up with clear_radix_tree_dirty_tag

Introduce clear_radix_tree_dirty_tag to include common codes for cleanup.

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

f2fs: fix to don't trigger writeback during recovery

- f2fs_fill_super
 - recover_fsync_data
  - recover_data
   - del_fsync_inode
    - iput
     - iput_final
      - write_inode_now
       - f2fs_write_inode
        - f2fs_balance_fs
         - f2fs_balance_fs_bg
          - sync_dirty_inodes

With data_flush mount option, during recovery, in order to avoid entering
above writeback flow, let's detect recovery status and do skip in
f2fs_balance_fs_bg.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Yunlei He <heyunlei@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: clear discard_wake earlier

If SBI_NEED_FSCK is set, discard_wake will never be cleared. As a
result, the condition of wait_event_interruptible_timeout() is always
true, which gets discard thread run too frequently.

Signed-off-by: Sheng Yong <shengyong1@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: let discard thread wait a little longer if dev is busy

This patch modify discard thread wait policy as below:
issued       io_interrupted     wait time(ms)
1.        8                 0               50
2.      (0,8)               1               50
3.        0                 1              500 (dev is busy)
4.        0                 0            60000 (no candidates)

Signed-off-by: Yunlei He <heyunlei@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: avoid stucking GC due to atomic write

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

f2fs: introduce sbi->gc_mode to determine the policy

This is to avoid sbi->gc_thread pointer access.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: keep migration IO order in LFS mode

For non-migration IO, we will keep order of data/node blocks' submitting
as allocation sequence by sorting IOs in per log io_list list, but for
migration IO, it could be out-of-order.

In LFS mode, we should keep all IOs including migration IO be ordered,
so that this patch fixes to add an additional lock to keep submitting
order.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Yunlong Song <yunlong.song@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix to wait page writeback during revoking atomic write

After revoking atomic write, related LBA can be reused by others, so we
need to wait page writeback before reusing the LBA, in order to avoid
interference between old atomic written in-flight IO and new IO.

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

f2fs: Fix deadlock in shutdown ioctl

f2fs_ioc_shutdown() ioctl gets stuck in the below path
when issued with F2FS_GOING_DOWN_FULLSYNC option.

__switch_to+0x90/0xc4
percpu_down_write+0x8c/0xc0
freeze_super+0xec/0x1e4
freeze_bdev+0xc4/0xcc
f2fs_ioctl+0xc0c/0x1ce0
f2fs_compat_ioctl+0x98/0x1f0

Signed-off-by: Sahitya Tummala <stummala@codeaurora.org>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: detect synchronous writeback more earlier

This patch changes to detect synchronous writeback more earlier before,
in order to avoid unnecessary page writeback before exiting asynchronous
writeback.

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

mm: remove nr_pages argument from pagevec_lookup_{,range}_tag()

All users of pagevec_lookup() and pagevec_lookup_range() now pass
PAGEVEC_SIZE as a desired number of pages.  Just drop the argument.

Link: http://lkml.kernel.org/r/20171009151359.31984-15-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

ceph: use pagevec_lookup_range_nr_tag()

Use new function for looking up pages since nr_pages argument from
pagevec_lookup_range_tag() is going away.

Link: http://lkml.kernel.org/r/20171009151359.31984-14-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm: add variant of pagevec_lookup_range_tag() taking number of pages

Currently pagevec_lookup_range_tag() takes number of pages to look up
but most users don't need this.  Create a new function
pagevec_lookup_range_nr_tag() that takes maximum number of pages to
lookup for Ceph which wants this functionality so that we can drop
nr_pages argument from pagevec_lookup_range_tag().

Link: http://lkml.kernel.org/r/20171009151359.31984-13-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm: use pagevec_lookup_range_tag() in write_cache_pages()

Use pagevec_lookup_range_tag() in write_cache_pages() as it is
interested only in pages from given range.  Remove unnecessary code
resulting from this.

Link: http://lkml.kernel.org/r/20171009151359.31984-12-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm: use pagevec_lookup_range_tag() in __filemap_fdatawait_range()

Use pagevec_lookup_range_tag() in __filemap_fdatawait_range() as it is
interested only in pages from given range.  Remove unnecessary code
resulting from this.

Link: http://lkml.kernel.org/r/20171009151359.31984-11-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

nilfs2: use pagevec_lookup_range_tag()

We want only pages from given range in nilfs_lookup_dirty_data_buffers().
Use pagevec_lookup_range_tag() instead of pagevec_lookup_tag() and
remove unnecessary code.

Link: http://lkml.kernel.org/r/20171009151359.31984-10-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

gfs2: use pagevec_lookup_range_tag()

We want only pages from given range in gfs2_write_cache_jdata().  Use
pagevec_lookup_range_tag() instead of pagevec_lookup_tag() and remove
unnecessary code.

Link: http://lkml.kernel.org/r/20171009151359.31984-9-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

f2fs: use find_get_pages_tag() for looking up single page

__get_first_dirty_index() wants to lookup only the first dirty page
after given index.  There's no point in using pagevec_lookup_tag() for
that.  Just use find_get_pages_tag() directly.

Link: http://lkml.kernel.org/r/20171009151359.31984-8-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

f2fs: simplify page iteration loops

In several places we want to iterate over all tagged pages in a mapping.
However the code was apparently copied from places that iterate only
over a limited range and thus it checks for index <= end, optimizes the
case where we are coming close to range end which is all pointless when
end == ULONG_MAX.  So just remove this dead code.

[akpm@linux-foundation.org: fix warnings]
Link: http://lkml.kernel.org/r/20171009151359.31984-7-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

f2fs: use pagevec_lookup_range_tag()

We want only pages from given range in f2fs_write_cache_pages().  Use
pagevec_lookup_range_tag() instead of pagevec_lookup_tag() and remove
unnecessary code.

Link: http://lkml.kernel.org/r/20171009151359.31984-6-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

ext4: use pagevec_lookup_range_tag()

We want only pages from given range in ext4_writepages().  Use
pagevec_lookup_range_tag() instead of pagevec_lookup_tag() and remove
unnecessary code.

Link: http://lkml.kernel.org/r/20171009151359.31984-5-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

ceph: use pagevec_lookup_range_tag()

We want only pages from given range in ceph_writepages_start().  Use
pagevec_lookup_range_tag() instead of pagevec_lookup_tag() and remove
unnecessary code.

Link: http://lkml.kernel.org/r/20171009151359.31984-4-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

btrfs: use pagevec_lookup_range_tag()

We want only pages from given range in btree_write_cache_pages() and
extent_write_cache_pages().  Use pagevec_lookup_range_tag() instead of
pagevec_lookup_tag() and remove unnecessary code.

Link: http://lkml.kernel.org/r/20171009151359.31984-3-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: David Sterba <dsterba@suse.com>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: David Sterba <dsterba@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm: implement find_get_pages_range_tag()

Patch series "Ranged pagevec tagged lookup", v3.

In this series I provide a ranged variant of pagevec_lookup_tag() and
use it in places where it makes sense.  This series removes some common
code and it also has a potential for speeding up some operations
similarly as for pagevec_lookup_range() (but for now I can think of only
artificial cases where this happens).

This patch (of 16):

Implement a variant of find_get_pages_tag() that stops iterating at
given index.  Lots of users of this function (through pagevec_lookup())
actually want a range lookup and all of them are currently open-coding
this.

Also create corresponding pagevec_lookup_range_tag() function.

Link: http://lkml.kernel.org/r/20171009151359.31984-2-jack@suse.cz
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Bob Peterson <rpeterso@redhat.com>
Cc: Chao Yu <yuchao0@huawei.com>
Cc: David Howells <dhowells@redhat.com>
Cc: David Sterba <dsterba@suse.com>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: Steve French <sfrench@samba.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

f2fs: clean up with is_valid_blkaddr()

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

f2fs: fix to initialize min_mtime with ULLONG_MAX

Since sit_i.min_mtime's type is unsigned long long, so we should
initialize it with max value of the type ULLONG_MAX instead of
LLONG_MAX.

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

f2fs: fix to let checkpoint guarantee atomic page persistence

1. thread A: commit_inmem_pages submit data into block layer, but
haven't waited it writeback.
2. thread A: commit_inmem_pages update related node.
3. thread B: do checkpoint, flush all nodes to disk.
4. SPOR

Then, atomic file becomes corrupted since nodes is flushed before data.

This patch fixes to treat atomic page as checkpoint guaranteed one,
then in checkpoint, we can make sure all atomic page can be writebacked
with metadata of atomic file.

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

f2fs: fix to initialize i_current_depth according to inode type

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

Revert "f2fs: add ovp valid_blocks check for bg gc victim to fg_gc"

For extreme case:
10 section, op = 10%, no_fggc_threshold = 90%
All section usage: 85% 85% 85% 85% 90% 90% 95% 95% 95% 95%

During foreground GC, if we skip select dirty section whose usage
is larger than no_fggc_threshold, we can only recycle 80% invalid
space from four 85% usage sections and two 90% usage sections,
result in encountering out-of-space issue.

This reverts commit e93b9865251a0503d83fd570e7d5a7c8bc351715 to
fix this issue, besides, we keep the logic that we scan all dirty
section when searching a victim, so that GC can select victim with
least valid blocks.

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

f2fs: don't drop any page on f2fs_cp_error() case

We still provide readdir() after shtudown, so we should keep pages to avoid
additional IOs.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix spelling mistake: "extenstion" -> "extension"

Trivial fix to spelling mistake in extension list text

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: enhance sanity_check_raw_super() to avoid potential overflows

In order to avoid the below overflow issue, we should have checked the
boundaries in superblock before reaching out to allocation. As Linus suggested,
the right place should be sanity_check_raw_super().

Dr Silvio Cesare of InfoSect reported:

There are integer overflows with using the cp_payload superblock field in the
f2fs filesystem potentially leading to memory corruption.

include/linux/f2fs_fs.h

struct f2fs_super_block {
...
        __le32 cp_payload;

fs/f2fs/f2fs.h

typedef u32 block_t;    /*
                         * should not change u32, since it is the on-disk block
                         * address format, __le32.
                         */
...

static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
{
        return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
}

fs/f2fs/checkpoint.c

        block_t start_blk, orphan_blocks, i, j;
...
        start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
        orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);

+++ integer overflows

...
        unsigned int cp_blks = 1 + __cp_payload(sbi);
...
        sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL);

+++ integer overflow leading to incorrect heap allocation.

        int cp_payload_blks = __cp_payload(sbi);
...
        ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
                        orphan_blocks);

+++ sign bug and integer overflow

...
        for (i = 1; i < 1 + cp_payload_blks; i++)

+++ integer overflow

...

      sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
                        NR_CURSEG_TYPE - __cp_payload(sbi)) *
                                F2FS_ORPHANS_PER_BLOCK;

+++ integer overflow

Reported-by: Greg KH <greg@kroah.com>
Reported-by: Silvio Cesare <silvio.cesare@gmail.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: treat volatile file's data as hot one

Volatile file's data will be updated oftenly, so it'd better to place
its data into hot data segment.

In addition, for atomic file, we change to check FI_ATOMIC_FILE instead
of FI_HOT_DATA to make code readability better.

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

f2fs: introduce release_discard_addr() for cleanup

Introduce release_discard_addr() to include common codes for cleanup.

Signed-off-by: Chao Yu <yuchao0@huawei.com>
[Fengguang Wu: declare static function, reported by kbuild test robot]
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix potential overflow

In build_sit_entries(), if valid_blocks in SIT block is smaller than
valid_blocks in journal, for below calculation:

sbi->discard_blks += old_valid_blocks - se->valid_blocks;

There will be two times potential overflow:
- old_valid_blocks - se->valid_blocks will overflow, and be a very
large number.
- sbi->discard_blks += result will overflow again, comes out a correct
result accidently.

Anyway, it should be fixed.

Fixes: d600af236da5 ("f2fs: avoid unneeded loop in build_sit_entries")
Fixes: 1f43e2ad7bff ("f2fs: introduce CP_TRIMMED_FLAG to avoid unneeded discard")
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: rename dio_rwsem to i_gc_rwsem

RW semphore dio_rwsem in struct f2fs_inode_info is introduced to avoid
race between dio and data gc, but now, it is more wildly used to avoid
foreground operation vs data gc. So rename it to i_gc_rwsem to improve
its readability.

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

f2fs: move mnt_want_write_file after range check

This patch move mnt_want_write_file after range check,
it's needless to check arguments with it.

Signed-off-by: Yunlei He <heyunlei@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix missing clear FI_NO_PREALLOC in some error case

This patch fix missing clear FI_NO_PREALLOC in some error case

Signed-off-by: Yunlei He <heyunlei@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: enforce fsync_mode=strict for renamed directory

This is to give a option for user to be able to recover B/foo in the below
case.

mkdir A
sync()
rename(A, B)
creat (B/foo)
fsync (B/foo)
---crash---

Sugessted-by: Velayudhan Pillai <vijay@cs.utexas.edu>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: sanity check for total valid node blocks

This patch enhances sanity check for SIT entries.

syzbot hit the following crash on upstream commit
83beed7b2b26f232d782127792dd0cd4362fdc41 (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
link: https://syzkaller.appspot.com/bug?extid=bf9253040425feb155ad
syzkaller reproducer: https://syzkaller.appspot.com/x/repro.syz?id=5692130282438656
Raw console output: https://syzkaller.appspot.com/x/log.txt?id=5095924598571008
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+bf9253040425feb155ad@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): invalid crc value
F2FS-fs (loop0): Try to recover 1th superblock, ret: 0
F2FS-fs (loop0): Mounted with checkpoint version = d
F2FS-fs (loop0): Bitmap was wrongly cleared, blk:9740
------------[ cut here ]------------
kernel BUG at fs/f2fs/segment.c:1884!
invalid opcode: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 1 PID: 4508 Comm: syz-executor0 Not tainted 4.17.0-rc1+ #10
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:update_sit_entry+0x1215/0x1590 fs/f2fs/segment.c:1882
RSP: 0018:ffff8801af526708 EFLAGS: 00010282
RAX: ffffed0035ea4cc0 RBX: ffff8801ad454f90 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff82eeb87e RDI: ffffed0035ea4cb6
RBP: ffff8801af526760 R08: ffff8801ad4a2480 R09: ffffed003b5e4f90
R10: ffffed003b5e4f90 R11: ffff8801daf27c87 R12: ffff8801adb8d380
R13: 0000000000000001 R14: 0000000000000008 R15: 00000000ffffffff
FS:  00000000014af940(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f06bc223000 CR3: 00000001adb02000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 allocate_data_block+0x66f/0x2050 fs/f2fs/segment.c:2663
 do_write_page+0x105/0x1b0 fs/f2fs/segment.c:2727
 write_node_page+0x129/0x350 fs/f2fs/segment.c:2770
 __write_node_page+0x7da/0x1370 fs/f2fs/node.c:1398
 sync_node_pages+0x18cf/0x1eb0 fs/f2fs/node.c:1652
 block_operations+0x429/0xa60 fs/f2fs/checkpoint.c:1088
 write_checkpoint+0x3ba/0x5380 fs/f2fs/checkpoint.c:1405
 f2fs_sync_fs+0x2fb/0x6a0 fs/f2fs/super.c:1077
 __sync_filesystem fs/sync.c:39 [inline]
 sync_filesystem+0x265/0x310 fs/sync.c:67
 generic_shutdown_super+0xd7/0x520 fs/super.c:429
 kill_block_super+0xa4/0x100 fs/super.c:1191
 kill_f2fs_super+0x9f/0xd0 fs/f2fs/super.c:3030
 deactivate_locked_super+0x97/0x100 fs/super.c:316
 deactivate_super+0x188/0x1b0 fs/super.c:347
 cleanup_mnt+0xbf/0x160 fs/namespace.c:1174
 __cleanup_mnt+0x16/0x20 fs/namespace.c:1181
 task_work_run+0x1e4/0x290 kernel/task_work.c:113
 tracehook_notify_resume include/linux/tracehook.h:191 [inline]
 exit_to_usermode_loop+0x2bd/0x310 arch/x86/entry/common.c:166
 prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
 syscall_return_slowpath arch/x86/entry/common.c:265 [inline]
 do_syscall_64+0x6ac/0x800 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x457d97
RSP: 002b:00007ffd46f9c8e8 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000457d97
RDX: 00000000014b09a3 RSI: 0000000000000002 RDI: 00007ffd46f9da50
RBP: 00007ffd46f9da50 R08: 0000000000000000 R09: 0000000000000009
R10: 0000000000000005 R11: 0000000000000246 R12: 00000000014b0940
R13: 0000000000000000 R14: 0000000000000002 R15: 000000000000658e
RIP: update_sit_entry+0x1215/0x1590 fs/f2fs/segment.c:1882 RSP: ffff8801af526708
---[ end trace f498328bb02610a2 ]---

Reported-and-tested-by: syzbot+bf9253040425feb155ad@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+7d6d31d3bc702f566ce3@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+0a725420475916460f12@syzkaller.appspotmail.com
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: sanity check on sit entry

syzbot hit the following crash on upstream commit
87ef12027b9b1dd0e0b12cf311fbcb19f9d92539 (Wed Apr 18 19:48:17 2018 +0000)
Merge tag 'ceph-for-4.17-rc2' of git://github.com/ceph/ceph-client
link: https://syzkaller.appspot.com/bug?extid=83699adeb2d13579c31e
C reproducer: https://syzkaller.appspot.com/x/repro.c?id=5805208181407744
syzkaller reproducer: https://syzkaller.appspot.com/x/repro.syz?id=6005073343676416
Raw console output: https://syzkaller.appspot.com/x/log.txt?id=6555047731134464
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+83699adeb2d13579c31e@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
BUG: unable to handle kernel paging request at ffffed006b2a50c0
PGD 21ffee067 P4D 21ffee067 PUD 21fbeb067 PMD 0
Oops: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
   (ftrace buffer empty)
Modules linked in:
CPU: 0 PID: 4514 Comm: syzkaller989480 Not tainted 4.17.0-rc1+ #8
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:build_sit_entries fs/f2fs/segment.c:3653 [inline]
RIP: 0010:build_segment_manager+0x7ef7/0xbf70 fs/f2fs/segment.c:3852
RSP: 0018:ffff8801b102e5b0 EFLAGS: 00010a06
RAX: 1ffff1006b2a50c0 RBX: 0000000000000004 RCX: 0000000000000001
RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8801ac74243e
RBP: ffff8801b102f410 R08: ffff8801acbd46c0 R09: fffffbfff14d9af8
R10: fffffbfff14d9af8 R11: ffff8801acbd46c0 R12: ffff8801ac742a80
R13: ffff8801d9519100 R14: dffffc0000000000 R15: ffff880359528600
FS:  0000000001e04880(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffed006b2a50c0 CR3: 00000001ac6ac000 CR4: 00000000001406f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 f2fs_fill_super+0x4095/0x7bf0 fs/f2fs/super.c:2803
 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: 0033:0x443d6a
RSP: 002b:00007ffd312813c8 EFLAGS: 00000297 ORIG_RAX: 00000000000000a5
RAX: ffffffffffffffda RBX: 0000000020000c00 RCX: 0000000000443d6a
RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffd312813d0
RBP: 0000000000000003 R08: 0000000020016a00 R09: 000000000000000a
R10: 0000000000000000 R11: 0000000000000297 R12: 0000000000000004
R13: 0000000000402c60 R14: 0000000000000000 R15: 0000000000000000
RIP: build_sit_entries fs/f2fs/segment.c:3653 [inline] RSP: ffff8801b102e5b0
RIP: build_segment_manager+0x7ef7/0xbf70 fs/f2fs/segment.c:3852 RSP: ffff8801b102e5b0
CR2: ffffed006b2a50c0
---[ end trace a2034989e196ff17 ]---

Reported-and-tested-by: syzbot+83699adeb2d13579c31e@syzkaller.appspotmail.com
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: avoid bug_on on corrupted inode

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

f2fs: give message and set need_fsck given broken node id

syzbot hit the following crash on upstream commit
83beed7b2b26f232d782127792dd0cd4362fdc41 (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
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: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: clean up commit_inmem_pages()

This patch moves error handling from commit_inmem_pages() into
__commit_inmem_page() for cleanup, no logic change.

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

f2fs: do not check F2FS_INLINE_DOTS in recover

Only dir may have F2FS_INLINE_DOTS flag, so there is no need to check
the flag in recover flow.

Signed-off-by: Sheng Yong <shengyong1@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: remove duplicated dquot_initialize and fix error handling

This patch removes duplicated dquot_initialize in recover_orphan_inode(),
and fix the error handling if dquot_initialize fails.

Signed-off-by: Sheng Yong <shengyong1@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix to detect failure of dquot_initialize

dquot_initialize() can fail due to any exception inside quota subsystem,
f2fs needs to be aware of it, and return correct return value to caller.

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

f2fs: stop issue discard if something wrong with f2fs

v4->v5: move data corruption check to __submit_discard_cmd, in order to
control discard io submitted more accurately, besides, increase async
thread wait time if data corruption detected.

This patch stop async thread and umount process to issue discard
if something wrong with f2fs, which is similar to fstrim.

Signed-off-by: Yunlei He <heyunlei@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix return value in f2fs_ioc_commit_atomic_write

In f2fs_ioc_commit_atomic_write, if file is volatile, return -EINVAL to
indicate that commit failure.

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

f2fs: allocate hot_data for atomic write more strictly

If a file not set type as hot, has dirty pages more than
threshold 64 before starting atomic write, may be lose hot
flag.

v1->v2: move set FI_ATOMIC_FILE flag behind flush dirty pages too,
in case of dirty pages before starting atomic use atomic mode to
write back.

Signed-off-by: Yunlei He <heyunlei@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: check if inmem_pages list is empty correctly

`cur' will never be NULL, we should check inmem_pages list instead.

Signed-off-by: Sheng Yong <shengyong1@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: fix race in between GC and atomic open

Thread GC thread
- f2fs_ioc_start_atomic_write
 - get_dirty_pages
 - filemap_write_and_wait_range
- f2fs_gc
 - do_garbage_collect
  - gc_data_segment
   - move_data_page
    - f2fs_is_atomic_file
    - set_page_dirty
 - set_inode_flag(, FI_ATOMIC_FILE)

Dirty data page can still be generated by GC in race condition as
above call stack.

This patch adds fi->dio_rwsem[WRITE] in f2fs_ioc_start_atomic_write
to avoid such race.

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

f2fs: change le32 to le16 of f2fs_inode->i_extra_size

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

Fixes: 704956ecf5bc ("f2fs: support inode checksum")
Signed-off-by: Zhikang Zhang <zhangzhikang1@huawei.com>
Signed-off-by: Yunlei He <heyunlei@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: check cur_valid_map_mir & raw_sit block count when flush sit entries

We should check valid_map_mir and block count to ensure
the flushed raw_sit is correct.

Signed-off-by: Zhikang Zhang <zhangzhikang1@huawei.com>
Signed-off-by: Yunlei He <heyunlei@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: correct return value of f2fs_trim_fs

Correct return value in two cases:
- return EINVAL if end boundary is out-of-range.
- return EIO if fs needs off-line check.

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

f2fs: fix to show missing bits in FS_IOC_GETFLAGS

This patch fixes to show missing encrypt/inline_data flag in
FS_IOC_GETFLAGS like ext4 does.

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

f2fs: remove unneeded F2FS_PROJINHERIT_FL

Now F2FS_FL_USER_VISIBLE and F2FS_FL_USER_MODIFIABLE has included
F2FS_PROJINHERIT_FL, so remove unneeded F2FS_PROJINHERIT_FL when
using visible/modifiable flag macro.

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

f2fs: don't use GFP_ZERO for page caches

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

f2fs: issue all big range discards in umount process

This patch modify max_requests to UINT_MAX, to issue
all big range discards in umount.

Signed-off-by: Yunlei He <heyunlei@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: remove redundant block plug

For buffered IO, we don't need to use block plug to cache bio,
for direct IO, generic f2fs_direct_IO has already added block
plug, so let's remove redundant one in .write_iter.

As Yunlei described in his patch:

-f2fs_file_write_iter
  -blk_start_plug
    -__generic_file_write_iter
...
  -do_blockdev_direct_IO
    -blk_start_plug
...
    -blk_finish_plug
...
  -blk_finish_plug

which may conduct performance decrease in our platform

Signed-off-by: Yunlei He <heyunlei@huawei.com>
Signed-off-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: remove unmatched zero_user_segment when convert inline dentry

Since the layout of regular dentry block is different from inline dentry
block, zero_user_segment starting from MAX_INLINE_DATA(dir) is not
correct for regular dentry block, besides, bitmap is already copied and
used, so there is no necessary to zero page at all, so just remove the
zero_user_segment is OK.

Signed-off-by: Yunlong Song <yunlong.song@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

f2fs: introduce private inode status mapping

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

fscrypt: log the crypto algorithm implementations

Log the crypto algorithm driver name for each fscrypt encryption mode on
its first use, also showing a friendly name for the mode.

This will help people determine whether the expected implementations are
being used.  In some cases we've seen people do benchmarks and reject
using encryption for performance reasons, when in fact they used a much
slower implementation of AES-XTS than was possible on the hardware.  It
can make an enormous difference; e.g., AES-XTS on ARM is about 10x
faster with the crypto extensions (AES instructions) than without.

This also makes it more obvious which modes are being used, now that
fscrypt supports multiple combinations of modes.

Example messages (with default modes, on x86_64):

[   35.492057] fscrypt: AES-256-CTS-CBC using implementation "cts(cbc-aes-aesni)"
[   35.492171] fscrypt: AES-256-XTS using implementation "xts-aes-aesni"

Note: algorithms can be dynamically added to the crypto API, which can
result in different implementations being used at different times.  But
this is rare; for most users, showing the first will be good enough.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: add Speck128/256 support

fscrypt currently only supports AES encryption.  However, many low-end
mobile devices have older CPUs that don't have AES instructions, e.g.
the ARMv8 Cryptography Extensions.  Currently, user data on such devices
is not encrypted at rest because AES is too slow, even when the NEON
bit-sliced implementation of AES is used.  Unfortunately, it is
infeasible to encrypt these devices at all when AES is the only option.

Therefore, this patch updates fscrypt to support the Speck block cipher,
which was recently added to the crypto API.  The C implementation of
Speck is not especially fast, but Speck can be implemented very
efficiently with general-purpose vector instructions, e.g. ARM NEON.
For example, on an ARMv7 processor, we measured the NEON-accelerated
Speck128/256-XTS at 69 MB/s for both encryption and decryption, while
AES-256-XTS with the NEON bit-sliced implementation was only 22 MB/s
encryption and 19 MB/s decryption.

There are multiple variants of Speck.  This patch only adds support for
Speck128/256, which is the variant with a 128-bit block size and 256-bit
key size -- the same as AES-256.  This is believed to be the most secure
variant of Speck, and it's only about 6% slower than Speck128/128.
Speck64/128 would be at least 20% faster because it has 20% rounds, and
it can be even faster on CPUs that can't efficiently do the 64-bit
operations needed for Speck128.  However, Speck64's 64-bit block size is
not preferred security-wise.  ARM NEON also supports the needed 64-bit
operations even on 32-bit CPUs, resulting in Speck128 being fast enough
for our targeted use cases so far.

The chosen modes of operation are XTS for contents and CTS-CBC for
filenames.  These are the same modes of operation that fscrypt defaults
to for AES.  Note that as with the other fscrypt modes, Speck will not
be used unless userspace chooses to use it.  Nor are any of the existing
modes (which are all AES-based) being removed, of course.

We intentionally don't make CONFIG_FS_ENCRYPTION select
CONFIG_CRYPTO_SPECK, so people will have to enable Speck support
themselves if they need it.  This is because we shouldn't bloat the
FS_ENCRYPTION dependencies with every new cipher, especially ones that
aren't recommended for most users.  Moreover, CRYPTO_SPECK is just the
generic implementation, which won't be fast enough for many users; in
practice, they'll need to enable CRYPTO_SPECK_NEON to get acceptable
performance.

More details about our choice of Speck can be found in our patches that
added Speck to the crypto API, and the follow-on discussion threads.
We're planning a publication that explains the choice in more detail.
But briefly, we can't use ChaCha20 as we previously proposed, since it
would be insecure to use a stream cipher in this context, with potential
IV reuse during writes on f2fs and/or on wear-leveling flash storage.

We also evaluated many other lightweight and/or ARX-based block ciphers
such as Chaskey-LTS, RC5, LEA, CHAM, Threefish, RC6, NOEKEON, SPARX, and
XTEA.  However, all had disadvantages vs. Speck, such as insufficient
performance with NEON, much less published cryptanalysis, or an
insufficient security level.  Various design choices in Speck make it
perform better with NEON than competing ciphers while still having a
security margin similar to AES, and in the case of Speck128 also the
same available security levels.  Unfortunately, Speck does have some
political baggage attached -- it's an NSA designed cipher, and was
rejected from an ISO standard (though for context, as far as I know none
of the above-mentioned alternatives are ISO standards either).
Nevertheless, we believe it is a good solution to the problem from a
technical perspective.

Certain algorithms constructed from ChaCha or the ChaCha permutation,
such as MEM (Masked Even-Mansour) or HPolyC, may also meet our
performance requirements.  However, these are new constructions that
need more time to receive the cryptographic review and acceptance needed
to be confident in their security.  HPolyC hasn't been published yet,
and we are concerned that MEM makes stronger assumptions about the
underlying permutation than the ChaCha stream cipher does.  In contrast,
the XTS mode of operation is relatively well accepted, and Speck has
over 70 cryptanalysis papers.  Of course, these ChaCha-based algorithms
can still be added later if they become ready.

The best known attack on Speck128/256 is a differential cryptanalysis
attack on 25 of 34 rounds with 2^253 time complexity and 2^125 chosen
plaintexts, i.e. only marginally faster than brute force.  There is no
known attack on the full 34 rounds.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: only derive the needed portion of the key

Currently the key derivation function in fscrypt uses the master key
length as the amount of output key material to derive.  This works, but
it means we can waste time deriving more key material than is actually
used, e.g. most commonly, deriving 64 bytes for directories which only
take a 32-byte AES-256-CTS-CBC key.  It also forces us to validate that
the master key length is a multiple of AES_BLOCK_SIZE, which wouldn't
otherwise be necessary.

Fix it to only derive the needed length key.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: separate key lookup from key derivation

Refactor the confusingly-named function 'validate_user_key()' into a new
function 'find_and_derive_key()' which first finds the keyring key, then
does the key derivation.  Among other benefits this avoids the strange
behavior we had previously where if key derivation failed for some
reason, then we would fall back to the alternate key prefix.  Now, we'll
only fall back to the alternate key prefix if a valid key isn't found.

This patch also improves the warning messages that are logged when the
keyring key's payload is invalid.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: use a common logging function

Use a common function for fscrypt warning and error messages so that all
the messages are consistently ratelimited, include the "fscrypt:"
prefix, and include the filesystem name if applicable.

Also fix up a few of the log messages to be more descriptive.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: remove internal key size constants

With one exception, the internal key size constants such as
FS_AES_256_XTS_KEY_SIZE are only used for the 'available_modes' array,
where they really only serve to obfuscate what the values are.  Also
some of the constants are unused, and the key sizes tend to be in the
names of the algorithms anyway.  In the past these values were also
misused, e.g. we used to have FS_AES_256_XTS_KEY_SIZE in places that
technically should have been FS_MAX_KEY_SIZE.

The exception is that FS_AES_128_ECB_KEY_SIZE is used for key
derivation.  But it's more appropriate to use
FS_KEY_DERIVATION_NONCE_SIZE for that instead.

Thus, just put the sizes directly in the 'available_modes' array.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: remove unnecessary check for non-logon key type

We're passing 'key_type_logon' to request_key(), so the found key is
guaranteed to be of type "logon".  Thus, there is no reason to check
later that the key is really a "logon" key.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: make fscrypt_operations.max_namelen an integer

Now ->max_namelen() is only called to limit the filename length when
adding NUL padding, and only for real filenames -- not symlink targets.
It also didn't give the correct length for symlink targets anyway since
it forgot to subtract 'sizeof(struct fscrypt_symlink_data)'.

Thus, change ->max_namelen from a function to a simple 'unsigned int'
that gives the filesystem's maximum filename length.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: drop empty name check from fname_decrypt()

fname_decrypt() is validating that the encrypted filename is nonempty.
However, earlier a stronger precondition was already enforced: the
encrypted filename must be at least 16 (FS_CRYPTO_BLOCK_SIZE) bytes.

Drop the redundant check for an empty filename.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: drop max_namelen check from fname_decrypt()

fname_decrypt() returns an error if the input filename is longer than
the inode's ->max_namelen() as given by the filesystem.  But, this
doesn't actually make sense because the filesystem provided the input
filename in the first place, where it was subject to the filesystem's
limits.  And fname_decrypt() has no internal limit itself.

Thus, remove this unnecessary check.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: don't special-case EOPNOTSUPP from fscrypt_get_encryption_info()

In fscrypt_setup_filename(), remove the unnecessary check for
fscrypt_get_encryption_info() returning EOPNOTSUPP.  There's no reason
to handle this error differently from any other.  I think there may have
been some confusion because the "notsupp" version of
fscrypt_get_encryption_info() returns EOPNOTSUPP -- but that's not
applicable from inside fs/crypto/.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: don't clear flags on crypto transform

fscrypt is clearing the flags on the crypto_skcipher it allocates for
each inode.  But, this is unnecessary and may cause problems in the
future because it will even clear flags that are meant to be internal to
the crypto API, e.g. CRYPTO_TFM_NEED_KEY.

Remove the unnecessary flag clearing.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: remove stale comment from fscrypt_d_revalidate()

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: remove error messages for skcipher_request_alloc() failure

skcipher_request_alloc() can only fail due to lack of memory, and in
that case the memory allocator will have already printed a detailed
error message.  Thus, remove the redundant error messages from fscrypt.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: remove unnecessary NULL check when allocating skcipher

crypto_alloc_skcipher() returns an ERR_PTR() on failure, not NULL.
Remove the unnecessary check for NULL.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: clean up after fscrypt_prepare_lookup() conversions

Now that all filesystems have been converted to use
fscrypt_prepare_lookup(), we can remove the fscrypt_set_d_op() and
fscrypt_set_encrypted_dentry() functions as well as un-export
fscrypt_d_ops.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

ubifs: switch to fscrypt_prepare_lookup()

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Richard Weinberger <richard@nod.at>

ext4: switch to fscrypt_prepare_lookup()

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

fscrypt: use unbound workqueue for decryption

Improve fscrypt read performance by switching the decryption workqueue
from bound to unbound.  With the bound workqueue, when multiple bios
completed on the same CPU, they were decrypted on that same CPU.  But
with the unbound queue, they are now decrypted in parallel on any CPU.

Although fscrypt read performance can be tough to measure due to the
many sources of variation, this change is most beneficial when
decryption is slow, e.g. on CPUs without AES instructions.  For example,
I timed tarring up encrypted directories on f2fs.  On x86 with AES-NI
instructions disabled, the unbound workqueue improved performance by
about 25-35%, using 1 to NUM_CPUs jobs with 4 or 8 CPUs available.  But
with AES-NI enabled, performance was unchanged to within ~2%.

I also did the same test on a quad-core ARM CPU using xts-speck128-neon
encryption.  There performance was usually about 10% better with the
unbound workqueue, bringing it closer to the unencrypted speed.

The unbound workqueue may be worse in some cases due to worse locality,
but I think it's still the better default.  dm-crypt uses an unbound
workqueue by default too, so this change makes fscrypt match.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

f2fs: run fstrim asynchronously if runtime discard is on

We don't need to wait for whole bunch of discard candidates in fstrim, since
runtime discard will issue them in idle time.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>