linux/fs/f2fs/checkpoint.c

1690 lines
41 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* fs/f2fs/checkpoint.c
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*/
#include <linux/fs.h>
#include <linux/bio.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/f2fs_fs.h>
#include <linux/pagevec.h>
#include <linux/swap.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "trace.h"
#include <trace/events/f2fs.h>
static struct kmem_cache *ino_entry_slab;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
struct kmem_cache *f2fs_inode_entry_slab;
void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
{
f2fs_build_fault_attr(sbi, 0, 0);
set_ckpt_flags(sbi, CP_ERROR_FLAG);
if (!end_io)
f2fs_flush_merged_writes(sbi);
}
/*
* We guarantee no failure on the returned page.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page = NULL;
repeat:
page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
}
f2fs_wait_on_page_writeback(page, META, true, true);
if (!PageUptodate(page))
SetPageUptodate(page);
return page;
}
/*
* We guarantee no failure on the returned page.
*/
static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
bool is_meta)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
.op = REQ_OP_READ,
.op_flags = REQ_META | REQ_PRIO,
.old_blkaddr = index,
.new_blkaddr = index,
.encrypted_page = NULL,
.is_por = !is_meta,
};
int err;
if (unlikely(!is_meta))
fio.op_flags &= ~REQ_META;
repeat:
page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
}
if (PageUptodate(page))
goto out;
fio.page = page;
err = f2fs_submit_page_bio(&fio);
if (err) {
f2fs_put_page(page, 1);
return ERR_PTR(err);
}
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
if (unlikely(!PageUptodate(page))) {
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
out:
return page;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, true);
}
struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct page *page;
int count = 0;
retry:
page = __get_meta_page(sbi, index, true);
if (IS_ERR(page)) {
if (PTR_ERR(page) == -EIO &&
++count <= DEFAULT_RETRY_IO_COUNT)
goto retry;
f2fs_stop_checkpoint(sbi, false);
}
return page;
}
/* for POR only */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
return __get_meta_page(sbi, index, false);
}
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 09:26:32 +02:00
static bool __is_bitmap_valid(struct f2fs_sb_info *sbi, block_t blkaddr,
int type)
{
struct seg_entry *se;
unsigned int segno, offset;
bool exist;
if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ)
return true;
segno = GET_SEGNO(sbi, blkaddr);
offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
se = get_seg_entry(sbi, segno);
exist = f2fs_test_bit(offset, se->cur_valid_map);
if (!exist && type == DATA_GENERIC_ENHANCE) {
f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error "
"blkaddr:%u, sit bitmap:%d", blkaddr, exist);
set_sbi_flag(sbi, SBI_NEED_FSCK);
WARN_ON(1);
}
return exist;
}
bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi,
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
block_t blkaddr, int type)
{
switch (type) {
case META_NAT:
break;
case META_SIT:
if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
return false;
break;
case META_SSA:
if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
blkaddr < SM_I(sbi)->ssa_blkaddr))
return false;
break;
case META_CP:
if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
blkaddr < __start_cp_addr(sbi)))
return false;
break;
case META_POR:
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 09:26:32 +02:00
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
blkaddr < MAIN_BLKADDR(sbi)))
return false;
break;
case DATA_GENERIC:
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 09:26:32 +02:00
case DATA_GENERIC_ENHANCE:
case DATA_GENERIC_ENHANCE_READ:
if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 09:26:32 +02:00
blkaddr < MAIN_BLKADDR(sbi))) {
f2fs_msg(sbi->sb, KERN_WARNING,
"access invalid blkaddr:%u", blkaddr);
set_sbi_flag(sbi, SBI_NEED_FSCK);
WARN_ON(1);
return false;
f2fs: introduce DATA_GENERIC_ENHANCE Previously, f2fs_is_valid_blkaddr(, blkaddr, DATA_GENERIC) will check whether @blkaddr locates in main area or not. That check is weak, since the block address in range of main area can point to the address which is not valid in segment info table, and we can not detect such condition, we may suffer worse corruption as system continues running. So this patch introduce DATA_GENERIC_ENHANCE to enhance the sanity check which trigger SIT bitmap check rather than only range check. This patch did below changes as wel: - set SBI_NEED_FSCK in f2fs_is_valid_blkaddr(). - get rid of is_valid_data_blkaddr() to avoid panic if blkaddr is invalid. - introduce verify_fio_blkaddr() to wrap fio {new,old}_blkaddr validation check. - spread blkaddr check in: * f2fs_get_node_info() * __read_out_blkaddrs() * f2fs_submit_page_read() * ra_data_block() * do_recover_data() This patch can fix bug reported from bugzilla below: https://bugzilla.kernel.org/show_bug.cgi?id=203215 https://bugzilla.kernel.org/show_bug.cgi?id=203223 https://bugzilla.kernel.org/show_bug.cgi?id=203231 https://bugzilla.kernel.org/show_bug.cgi?id=203235 https://bugzilla.kernel.org/show_bug.cgi?id=203241 = Update by Jaegeuk Kim = DATA_GENERIC_ENHANCE enhanced to validate block addresses on read/write paths. But, xfstest/generic/446 compalins some generated kernel messages saying invalid bitmap was detected when reading a block. The reaons is, when we get the block addresses from extent_cache, there is no lock to synchronize it from truncating the blocks in parallel. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-15 09:26:32 +02:00
} else {
return __is_bitmap_valid(sbi, blkaddr, type);
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 13:13:44 +02:00
}
break;
case META_GENERIC:
if (unlikely(blkaddr < SEG0_BLKADDR(sbi) ||
blkaddr >= MAIN_BLKADDR(sbi)))
return false;
break;
default:
BUG();
}
return true;
}
/*
* Readahead CP/NAT/SIT/SSA pages
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
int type, bool sync)
{
struct page *page;
block_t blkno = start;
struct f2fs_io_info fio = {
.sbi = sbi,
.type = META,
.op = REQ_OP_READ,
.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
.encrypted_page = NULL,
.in_list = false,
.is_por = (type == META_POR),
};
struct blk_plug plug;
if (unlikely(type == META_POR))
fio.op_flags &= ~REQ_META;
blk_start_plug(&plug);
for (; nrpages-- > 0; blkno++) {
if (!f2fs_is_valid_blkaddr(sbi, blkno, type))
goto out;
switch (type) {
case META_NAT:
if (unlikely(blkno >=
NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
blkno = 0;
/* get nat block addr */
fio.new_blkaddr = current_nat_addr(sbi,
blkno * NAT_ENTRY_PER_BLOCK);
break;
case META_SIT:
/* get sit block addr */
fio.new_blkaddr = current_sit_addr(sbi,
blkno * SIT_ENTRY_PER_BLOCK);
break;
case META_SSA:
case META_CP:
case META_POR:
fio.new_blkaddr = blkno;
break;
default:
BUG();
}
page = f2fs_grab_cache_page(META_MAPPING(sbi),
fio.new_blkaddr, false);
if (!page)
continue;
if (PageUptodate(page)) {
f2fs_put_page(page, 1);
continue;
}
fio.page = page;
f2fs_submit_page_bio(&fio);
f2fs_put_page(page, 0);
}
out:
blk_finish_plug(&plug);
return blkno - start;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
{
struct page *page;
bool readahead = false;
page = find_get_page(META_MAPPING(sbi), index);
if (!page || !PageUptodate(page))
readahead = true;
f2fs_put_page(page, 0);
if (readahead)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
}
static int __f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc,
enum iostat_type io_type)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
trace_f2fs_writepage(page, META);
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_do_write_meta_page(sbi, page, io_type);
dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim)
f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META);
unlock_page(page);
if (unlikely(f2fs_cp_error(sbi)))
f2fs_submit_merged_write(sbi, META);
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
return AOP_WRITEPAGE_ACTIVATE;
}
static int f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc)
{
return __f2fs_write_meta_page(page, wbc, FS_META_IO);
}
static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto skip_write;
/* collect a number of dirty meta pages and write together */
if (wbc->sync_mode != WB_SYNC_ALL &&
get_pages(sbi, F2FS_DIRTY_META) <
nr_pages_to_skip(sbi, META))
goto skip_write;
/* if locked failed, cp will flush dirty pages instead */
if (!mutex_trylock(&sbi->cp_mutex))
goto skip_write;
trace_f2fs_writepages(mapping->host, wbc, META);
diff = nr_pages_to_write(sbi, META, wbc);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO);
mutex_unlock(&sbi->cp_mutex);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff);
return 0;
skip_write:
wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META);
trace_f2fs_writepages(mapping->host, wbc, META);
return 0;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
long nr_to_write, enum iostat_type io_type)
{
struct address_space *mapping = META_MAPPING(sbi);
pgoff_t index = 0, prev = ULONG_MAX;
struct pagevec pvec;
long nwritten = 0;
int nr_pages;
struct writeback_control wbc = {
.for_reclaim = 0,
};
struct blk_plug plug;
pagevec_init(&pvec);
blk_start_plug(&plug);
while ((nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
PAGECACHE_TAG_DIRTY))) {
int i;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
if (prev == ULONG_MAX)
f2fs: merge meta writes as many possible This patch tries to merge IOs as many as possible when background flusher conducts flushing the dirty meta pages. [Before] ... 2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124320, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124560, size = 32768 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 95720, size = 987136 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123928, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123944, size = 8192 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123968, size = 45056 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124064, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 97648, size = 1007616 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123776, size = 8192 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123800, size = 32768 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124624, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 99616, size = 921600 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123608, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123624, size = 77824 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123792, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123864, size = 32768 ... [After] ... f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 92168, size = 892928 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 93912, size = 753664 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 95384, size = 716800 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 96784, size = 712704 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 104160, size = 364544 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 104872, size = 356352 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 105568, size = 278528 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 106112, size = 319488 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 106736, size = 258048 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 107240, size = 270336 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 107768, size = 180224 ... Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-10-02 01:42:55 +02:00
prev = page->index - 1;
if (nr_to_write != LONG_MAX && page->index != prev + 1) {
pagevec_release(&pvec);
goto stop;
}
lock_page(page);
if (unlikely(page->mapping != mapping)) {
continue_unlock:
unlock_page(page);
continue;
}
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
f2fs_wait_on_page_writeback(page, META, true, true);
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
if (__f2fs_write_meta_page(page, &wbc, io_type)) {
unlock_page(page);
break;
}
nwritten++;
f2fs: merge meta writes as many possible This patch tries to merge IOs as many as possible when background flusher conducts flushing the dirty meta pages. [Before] ... 2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124320, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124560, size = 32768 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 95720, size = 987136 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123928, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123944, size = 8192 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123968, size = 45056 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124064, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 97648, size = 1007616 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123776, size = 8192 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123800, size = 32768 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124624, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 99616, size = 921600 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123608, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123624, size = 77824 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123792, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123864, size = 32768 ... [After] ... f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 92168, size = 892928 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 93912, size = 753664 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 95384, size = 716800 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 96784, size = 712704 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 104160, size = 364544 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 104872, size = 356352 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 105568, size = 278528 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 106112, size = 319488 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 106736, size = 258048 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 107240, size = 270336 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 107768, size = 180224 ... Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-10-02 01:42:55 +02:00
prev = page->index;
if (unlikely(nwritten >= nr_to_write))
break;
}
pagevec_release(&pvec);
cond_resched();
}
f2fs: merge meta writes as many possible This patch tries to merge IOs as many as possible when background flusher conducts flushing the dirty meta pages. [Before] ... 2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124320, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124560, size = 32768 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 95720, size = 987136 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123928, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123944, size = 8192 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123968, size = 45056 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124064, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 97648, size = 1007616 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123776, size = 8192 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123800, size = 32768 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 124624, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 99616, size = 921600 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123608, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123624, size = 77824 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123792, size = 4096 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 123864, size = 32768 ... [After] ... f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 92168, size = 892928 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 93912, size = 753664 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 95384, size = 716800 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 96784, size = 712704 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 104160, size = 364544 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 104872, size = 356352 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 105568, size = 278528 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 106112, size = 319488 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 106736, size = 258048 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 107240, size = 270336 f2fs_submit_write_bio: dev = (8,18), WRITE_SYNC(MP), META, sector = 107768, size = 180224 ... Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-10-02 01:42:55 +02:00
stop:
if (nwritten)
f2fs_submit_merged_write(sbi, type);
blk_finish_plug(&plug);
return nwritten;
}
static int f2fs_set_meta_page_dirty(struct page *page)
{
trace_f2fs_set_page_dirty(page, META);
if (!PageUptodate(page))
SetPageUptodate(page);
if (!PageDirty(page)) {
__set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
f2fs_set_page_private(page, 0);
f2fs_trace_pid(page);
return 1;
}
return 0;
}
const struct address_space_operations f2fs_meta_aops = {
.writepage = f2fs_write_meta_page,
.writepages = f2fs_write_meta_pages,
.set_page_dirty = f2fs_set_meta_page_dirty,
.invalidatepage = f2fs_invalidate_page,
.releasepage = f2fs_release_page,
#ifdef CONFIG_MIGRATION
.migratepage = f2fs_migrate_page,
#endif
};
static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
struct inode_management *im = &sbi->im[type];
struct ino_entry *e, *tmp;
tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
if (!e) {
e = tmp;
if (unlikely(radix_tree_insert(&im->ino_root, ino, e)))
f2fs_bug_on(sbi, 1);
memset(e, 0, sizeof(struct ino_entry));
e->ino = ino;
list_add_tail(&e->list, &im->ino_list);
if (type != ORPHAN_INO)
im->ino_num++;
}
if (type == FLUSH_INO)
f2fs_set_bit(devidx, (char *)&e->dirty_device);
spin_unlock(&im->ino_lock);
radix_tree_preload_end();
if (e != tmp)
kmem_cache_free(ino_entry_slab, tmp);
}
static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
if (e) {
list_del(&e->list);
radix_tree_delete(&im->ino_root, ino);
im->ino_num--;
spin_unlock(&im->ino_lock);
kmem_cache_free(ino_entry_slab, e);
return;
}
spin_unlock(&im->ino_lock);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* add new dirty ino entry into list */
__add_ino_entry(sbi, ino, 0, type);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* remove dirty ino entry from list */
__remove_ino_entry(sbi, ino, type);
}
/* mode should be APPEND_INO or UPDATE_INO */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
struct inode_management *im = &sbi->im[mode];
struct ino_entry *e;
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
spin_unlock(&im->ino_lock);
return e ? true : false;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all)
{
struct ino_entry *e, *tmp;
int i;
for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) {
struct inode_management *im = &sbi->im[i];
spin_lock(&im->ino_lock);
list_for_each_entry_safe(e, tmp, &im->ino_list, list) {
list_del(&e->list);
radix_tree_delete(&im->ino_root, e->ino);
kmem_cache_free(ino_entry_slab, e);
im->ino_num--;
}
spin_unlock(&im->ino_lock);
}
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
__add_ino_entry(sbi, ino, devidx, type);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino,
unsigned int devidx, int type)
{
struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
bool is_dirty = false;
spin_lock(&im->ino_lock);
e = radix_tree_lookup(&im->ino_root, ino);
if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device))
is_dirty = true;
spin_unlock(&im->ino_lock);
return is_dirty;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
spin_lock(&im->ino_lock);
if (time_to_inject(sbi, FAULT_ORPHAN)) {
spin_unlock(&im->ino_lock);
f2fs_show_injection_info(FAULT_ORPHAN);
return -ENOSPC;
}
if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
im->ino_num++;
spin_unlock(&im->ino_lock);
return err;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi)
{
struct inode_management *im = &sbi->im[ORPHAN_INO];
spin_lock(&im->ino_lock);
f2fs_bug_on(sbi, im->ino_num == 0);
im->ino_num--;
spin_unlock(&im->ino_lock);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_add_orphan_inode(struct inode *inode)
{
/* add new orphan ino entry into list */
__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_update_inode_page(inode);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
/* remove orphan entry from orphan list */
__remove_ino_entry(sbi, ino, ORPHAN_INO);
}
static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct inode *inode;
struct node_info ni;
int err;
inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode)) {
/*
* there should be a bug that we can't find the entry
* to orphan inode.
*/
f2fs_bug_on(sbi, PTR_ERR(inode) == -ENOENT);
return PTR_ERR(inode);
}
err = dquot_initialize(inode);
if (err) {
iput(inode);
goto err_out;
}
clear_nlink(inode);
/* truncate all the data during iput */
iput(inode);
err = f2fs_get_node_info(sbi, ino, &ni);
if (err)
goto err_out;
/* ENOMEM was fully retried in f2fs_evict_inode. */
if (ni.blk_addr != NULL_ADDR) {
err = -EIO;
goto err_out;
}
return 0;
err_out:
set_sbi_flag(sbi, SBI_NEED_FSCK);
f2fs_msg(sbi->sb, KERN_WARNING,
"%s: orphan failed (ino=%x), run fsck to fix.",
__func__, ino);
return err;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
block_t start_blk, orphan_blocks, i, j;
unsigned int s_flags = sbi->sb->s_flags;
int err = 0;
#ifdef CONFIG_QUOTA
int quota_enabled;
#endif
if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
return 0;
if (bdev_read_only(sbi->sb->s_bdev)) {
f2fs_msg(sbi->sb, KERN_INFO, "write access "
"unavailable, skipping orphan cleanup");
return 0;
}
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 22:05:09 +01:00
if (s_flags & SB_RDONLY) {
f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs");
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 22:05:09 +01:00
sbi->sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 22:05:09 +01:00
sbi->sb->s_flags |= SB_ACTIVE;
/*
* Turn on quotas which were not enabled for read-only mounts if
* filesystem has quota feature, so that they are updated correctly.
*/
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 22:05:09 +01:00
quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
#endif
start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
for (i = 0; i < orphan_blocks; i++) {
struct page *page;
struct f2fs_orphan_block *orphan_blk;
page = f2fs_get_meta_page(sbi, start_blk + i);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out;
}
orphan_blk = (struct f2fs_orphan_block *)page_address(page);
for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
err = recover_orphan_inode(sbi, ino);
if (err) {
f2fs_put_page(page, 1);
goto out;
}
}
f2fs_put_page(page, 1);
}
/* clear Orphan Flag */
clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
out:
f2fs: fix to flush all dirty inodes recovered in readonly fs generic/417 reported as blow: ------------[ cut here ]------------ kernel BUG at /home/yuchao/git/devf2fs/inode.c:695! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 1 PID: 21697 Comm: umount Tainted: G W O 4.18.0-rc2+ #39 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 EIP: f2fs_evict_inode+0x556/0x580 [f2fs] Call Trace: ? _raw_spin_unlock+0x2c/0x50 evict+0xa8/0x170 dispose_list+0x34/0x40 evict_inodes+0x118/0x120 generic_shutdown_super+0x41/0x100 ? rcu_read_lock_sched_held+0x97/0xa0 kill_block_super+0x22/0x50 kill_f2fs_super+0x6f/0x80 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x81/0xa0 exit_to_usermode_loop+0x59/0xa7 do_fast_syscall_32+0x1f5/0x22c entry_SYSENTER_32+0x53/0x86 EIP: f2fs_evict_inode+0x556/0x580 [f2fs] It can simply reproduced with scripts: Enable quota feature during mkfs. Testcase1: 1. mkfs.f2fs /dev/zram0 2. mount -t f2fs /dev/zram0 /mnt/f2fs 3. xfs_io -f /mnt/f2fs/file -c "pwrite 0 4k" -c "fsync" 4. godown /mnt/f2fs 5. umount /mnt/f2fs 6. mount -t f2fs -o ro /dev/zram0 /mnt/f2fs 7. umount /mnt/f2fs Testcase2: 1. mkfs.f2fs /dev/zram0 2. mount -t f2fs /dev/zram0 /mnt/f2fs 3. touch /mnt/f2fs/file 4. create process[pid = x] do: a) open /mnt/f2fs/file; b) unlink /mnt/f2fs/file 5. godown -f /mnt/f2fs 6. kill process[pid = x] 7. umount /mnt/f2fs 8. mount -t f2fs -o ro /dev/zram0 /mnt/f2fs 9. umount /mnt/f2fs The reason is: during recovery, i_{c,m}time of inode will be updated, then the inode can be set dirty w/o being tracked in sbi->inode_list[DIRTY_META] global list, so later write_checkpoint will not flush such dirty inode into node page. Once umount is called, sync_filesystem() in generic_shutdown_super() will skip syncng dirty inodes due to sb_rdonly check, leaving dirty inodes there. To solve this issue, during umount, add remove SB_RDONLY flag in sb->s_flags, to make sure sync_filesystem() will not be skipped. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-22 11:11:05 +02:00
set_sbi_flag(sbi, SBI_IS_RECOVERED);
#ifdef CONFIG_QUOTA
/* Turn quotas off */
if (quota_enabled)
f2fs_quota_off_umount(sbi->sb);
#endif
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 22:05:09 +01:00
sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
return err;
}
static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
{
struct list_head *head;
struct f2fs_orphan_block *orphan_blk = NULL;
unsigned int nentries = 0;
unsigned short index = 1;
unsigned short orphan_blocks;
struct page *page = NULL;
struct ino_entry *orphan = NULL;
struct inode_management *im = &sbi->im[ORPHAN_INO];
orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num);
/*
* we don't need to do spin_lock(&im->ino_lock) here, since all the
* orphan inode operations are covered under f2fs_lock_op().
* And, spin_lock should be avoided due to page operations below.
*/
head = &im->ino_list;
/* loop for each orphan inode entry and write them in Jornal block */
list_for_each_entry(orphan, head, list) {
if (!page) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
page = f2fs_grab_meta_page(sbi, start_blk++);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
}
orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino);
if (nentries == F2FS_ORPHANS_PER_BLOCK) {
/*
* an orphan block is full of 1020 entries,
* then we need to flush current orphan blocks
* and bring another one in memory
*/
orphan_blk->blk_addr = cpu_to_le16(index);
orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
orphan_blk->entry_count = cpu_to_le32(nentries);
set_page_dirty(page);
f2fs_put_page(page, 1);
index++;
nentries = 0;
page = NULL;
}
}
if (page) {
orphan_blk->blk_addr = cpu_to_le16(index);
orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
orphan_blk->entry_count = cpu_to_le32(nentries);
set_page_dirty(page);
f2fs_put_page(page, 1);
}
}
static __u32 f2fs_checkpoint_chksum(struct f2fs_sb_info *sbi,
struct f2fs_checkpoint *ckpt)
{
unsigned int chksum_ofs = le32_to_cpu(ckpt->checksum_offset);
__u32 chksum;
chksum = f2fs_crc32(sbi, ckpt, chksum_ofs);
if (chksum_ofs < CP_CHKSUM_OFFSET) {
chksum_ofs += sizeof(chksum);
chksum = f2fs_chksum(sbi, chksum, (__u8 *)ckpt + chksum_ofs,
F2FS_BLKSIZE - chksum_ofs);
}
return chksum;
}
static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
struct f2fs_checkpoint **cp_block, struct page **cp_page,
unsigned long long *version)
{
size_t crc_offset = 0;
__u32 crc;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
*cp_page = f2fs_get_meta_page(sbi, cp_addr);
if (IS_ERR(*cp_page))
return PTR_ERR(*cp_page);
*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
if (crc_offset < CP_MIN_CHKSUM_OFFSET ||
crc_offset > CP_CHKSUM_OFFSET) {
f2fs: fix invalid memory access syzbot found the following crash on: HEAD commit: d9bd94c0bcaa Add linux-next specific files for 20180801 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1001189c400000 kernel config: https://syzkaller.appspot.com/x/.config?x=cc8964ea4d04518c dashboard link: https://syzkaller.appspot.com/bug?extid=c966a82db0b14aa37e81 compiler: gcc (GCC) 8.0.1 20180413 (experimental) Unfortunately, I don't have any reproducer for this crash yet. IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+c966a82db0b14aa37e81@syzkaller.appspotmail.com loop7: rw=12288, want=8200, limit=20 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. openvswitch: netlink: Message has 8 unknown bytes. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN CPU: 1 PID: 7615 Comm: syz-executor7 Not tainted 4.18.0-rc7-next-20180801+ #29 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_get_valid_checkpoint+0x436/0x1ec0 fs/f2fs/checkpoint.c:860 f2fs_fill_super+0x2d42/0x8110 fs/f2fs/super.c:2883 mount_bdev+0x314/0x3e0 fs/super.c:1344 f2fs_mount+0x3c/0x50 fs/f2fs/super.c:3133 legacy_get_tree+0x131/0x460 fs/fs_context.c:729 vfs_get_tree+0x1cb/0x5c0 fs/super.c:1743 do_new_mount fs/namespace.c:2603 [inline] do_mount+0x6f2/0x1e20 fs/namespace.c:2927 ksys_mount+0x12d/0x140 fs/namespace.c:3143 __do_sys_mount fs/namespace.c:3157 [inline] __se_sys_mount fs/namespace.c:3154 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3154 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x45943a Code: b8 a6 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 bd 8a fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 9a 8a fb ff c3 66 0f 1f 84 00 00 00 00 00 RSP: 002b:00007f36a61d4a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007f36a61d4b30 RCX: 000000000045943a RDX: 00007f36a61d4ad0 RSI: 0000000020000100 RDI: 00007f36a61d4af0 RBP: 0000000020000100 R08: 00007f36a61d4b30 R09: 00007f36a61d4ad0 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000013 R13: 0000000000000000 R14: 00000000004c8ea0 R15: 0000000000000000 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace bd8550c129352286 ]--- RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 openvswitch: netlink: Message has 8 unknown bytes. R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 In validate_checkpoint(), if we failed to call get_checkpoint_version(), we will pass returned invalid page pointer into f2fs_put_page, cause accessing invalid memory, this patch tries to handle error path correctly to fix this issue. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 16:59:12 +02:00
f2fs_put_page(*cp_page, 1);
f2fs_msg(sbi->sb, KERN_WARNING,
"invalid crc_offset: %zu", crc_offset);
return -EINVAL;
}
2019-04-22 11:33:53 +02:00
if (__is_set_ckpt_flags(*cp_block, CP_LARGE_NAT_BITMAP_FLAG)) {
if (crc_offset != CP_MIN_CHKSUM_OFFSET) {
f2fs_put_page(*cp_page, 1);
f2fs_msg(sbi->sb, KERN_WARNING,
"layout of large_nat_bitmap is deprecated, "
"run fsck to repair, chksum_offset: %zu",
crc_offset);
return -EINVAL;
}
}
crc = f2fs_checkpoint_chksum(sbi, *cp_block);
if (crc != cur_cp_crc(*cp_block)) {
f2fs: fix invalid memory access syzbot found the following crash on: HEAD commit: d9bd94c0bcaa Add linux-next specific files for 20180801 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1001189c400000 kernel config: https://syzkaller.appspot.com/x/.config?x=cc8964ea4d04518c dashboard link: https://syzkaller.appspot.com/bug?extid=c966a82db0b14aa37e81 compiler: gcc (GCC) 8.0.1 20180413 (experimental) Unfortunately, I don't have any reproducer for this crash yet. IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+c966a82db0b14aa37e81@syzkaller.appspotmail.com loop7: rw=12288, want=8200, limit=20 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. openvswitch: netlink: Message has 8 unknown bytes. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN CPU: 1 PID: 7615 Comm: syz-executor7 Not tainted 4.18.0-rc7-next-20180801+ #29 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_get_valid_checkpoint+0x436/0x1ec0 fs/f2fs/checkpoint.c:860 f2fs_fill_super+0x2d42/0x8110 fs/f2fs/super.c:2883 mount_bdev+0x314/0x3e0 fs/super.c:1344 f2fs_mount+0x3c/0x50 fs/f2fs/super.c:3133 legacy_get_tree+0x131/0x460 fs/fs_context.c:729 vfs_get_tree+0x1cb/0x5c0 fs/super.c:1743 do_new_mount fs/namespace.c:2603 [inline] do_mount+0x6f2/0x1e20 fs/namespace.c:2927 ksys_mount+0x12d/0x140 fs/namespace.c:3143 __do_sys_mount fs/namespace.c:3157 [inline] __se_sys_mount fs/namespace.c:3154 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3154 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x45943a Code: b8 a6 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 bd 8a fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 9a 8a fb ff c3 66 0f 1f 84 00 00 00 00 00 RSP: 002b:00007f36a61d4a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007f36a61d4b30 RCX: 000000000045943a RDX: 00007f36a61d4ad0 RSI: 0000000020000100 RDI: 00007f36a61d4af0 RBP: 0000000020000100 R08: 00007f36a61d4b30 R09: 00007f36a61d4ad0 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000013 R13: 0000000000000000 R14: 00000000004c8ea0 R15: 0000000000000000 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace bd8550c129352286 ]--- RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 openvswitch: netlink: Message has 8 unknown bytes. R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 In validate_checkpoint(), if we failed to call get_checkpoint_version(), we will pass returned invalid page pointer into f2fs_put_page, cause accessing invalid memory, this patch tries to handle error path correctly to fix this issue. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 16:59:12 +02:00
f2fs_put_page(*cp_page, 1);
f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
return -EINVAL;
}
*version = cur_cp_version(*cp_block);
return 0;
}
static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
block_t cp_addr, unsigned long long *version)
{
struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
struct f2fs_checkpoint *cp_block = NULL;
unsigned long long cur_version = 0, pre_version = 0;
int err;
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
&cp_page_1, version);
if (err)
f2fs: fix invalid memory access syzbot found the following crash on: HEAD commit: d9bd94c0bcaa Add linux-next specific files for 20180801 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1001189c400000 kernel config: https://syzkaller.appspot.com/x/.config?x=cc8964ea4d04518c dashboard link: https://syzkaller.appspot.com/bug?extid=c966a82db0b14aa37e81 compiler: gcc (GCC) 8.0.1 20180413 (experimental) Unfortunately, I don't have any reproducer for this crash yet. IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+c966a82db0b14aa37e81@syzkaller.appspotmail.com loop7: rw=12288, want=8200, limit=20 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. openvswitch: netlink: Message has 8 unknown bytes. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN CPU: 1 PID: 7615 Comm: syz-executor7 Not tainted 4.18.0-rc7-next-20180801+ #29 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_get_valid_checkpoint+0x436/0x1ec0 fs/f2fs/checkpoint.c:860 f2fs_fill_super+0x2d42/0x8110 fs/f2fs/super.c:2883 mount_bdev+0x314/0x3e0 fs/super.c:1344 f2fs_mount+0x3c/0x50 fs/f2fs/super.c:3133 legacy_get_tree+0x131/0x460 fs/fs_context.c:729 vfs_get_tree+0x1cb/0x5c0 fs/super.c:1743 do_new_mount fs/namespace.c:2603 [inline] do_mount+0x6f2/0x1e20 fs/namespace.c:2927 ksys_mount+0x12d/0x140 fs/namespace.c:3143 __do_sys_mount fs/namespace.c:3157 [inline] __se_sys_mount fs/namespace.c:3154 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3154 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x45943a Code: b8 a6 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 bd 8a fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 9a 8a fb ff c3 66 0f 1f 84 00 00 00 00 00 RSP: 002b:00007f36a61d4a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007f36a61d4b30 RCX: 000000000045943a RDX: 00007f36a61d4ad0 RSI: 0000000020000100 RDI: 00007f36a61d4af0 RBP: 0000000020000100 R08: 00007f36a61d4b30 R09: 00007f36a61d4ad0 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000013 R13: 0000000000000000 R14: 00000000004c8ea0 R15: 0000000000000000 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace bd8550c129352286 ]--- RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 openvswitch: netlink: Message has 8 unknown bytes. R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 In validate_checkpoint(), if we failed to call get_checkpoint_version(), we will pass returned invalid page pointer into f2fs_put_page, cause accessing invalid memory, this patch tries to handle error path correctly to fix this issue. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 16:59:12 +02:00
return NULL;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 13:13:44 +02:00
if (le32_to_cpu(cp_block->cp_pack_total_block_count) >
sbi->blocks_per_seg) {
f2fs_msg(sbi->sb, KERN_WARNING,
"invalid cp_pack_total_block_count:%u",
le32_to_cpu(cp_block->cp_pack_total_block_count));
f2fs: fix invalid memory access syzbot found the following crash on: HEAD commit: d9bd94c0bcaa Add linux-next specific files for 20180801 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1001189c400000 kernel config: https://syzkaller.appspot.com/x/.config?x=cc8964ea4d04518c dashboard link: https://syzkaller.appspot.com/bug?extid=c966a82db0b14aa37e81 compiler: gcc (GCC) 8.0.1 20180413 (experimental) Unfortunately, I don't have any reproducer for this crash yet. IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+c966a82db0b14aa37e81@syzkaller.appspotmail.com loop7: rw=12288, want=8200, limit=20 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. openvswitch: netlink: Message has 8 unknown bytes. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN CPU: 1 PID: 7615 Comm: syz-executor7 Not tainted 4.18.0-rc7-next-20180801+ #29 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_get_valid_checkpoint+0x436/0x1ec0 fs/f2fs/checkpoint.c:860 f2fs_fill_super+0x2d42/0x8110 fs/f2fs/super.c:2883 mount_bdev+0x314/0x3e0 fs/super.c:1344 f2fs_mount+0x3c/0x50 fs/f2fs/super.c:3133 legacy_get_tree+0x131/0x460 fs/fs_context.c:729 vfs_get_tree+0x1cb/0x5c0 fs/super.c:1743 do_new_mount fs/namespace.c:2603 [inline] do_mount+0x6f2/0x1e20 fs/namespace.c:2927 ksys_mount+0x12d/0x140 fs/namespace.c:3143 __do_sys_mount fs/namespace.c:3157 [inline] __se_sys_mount fs/namespace.c:3154 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3154 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x45943a Code: b8 a6 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 bd 8a fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 9a 8a fb ff c3 66 0f 1f 84 00 00 00 00 00 RSP: 002b:00007f36a61d4a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007f36a61d4b30 RCX: 000000000045943a RDX: 00007f36a61d4ad0 RSI: 0000000020000100 RDI: 00007f36a61d4af0 RBP: 0000000020000100 R08: 00007f36a61d4b30 R09: 00007f36a61d4ad0 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000013 R13: 0000000000000000 R14: 00000000004c8ea0 R15: 0000000000000000 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace bd8550c129352286 ]--- RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 openvswitch: netlink: Message has 8 unknown bytes. R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 In validate_checkpoint(), if we failed to call get_checkpoint_version(), we will pass returned invalid page pointer into f2fs_put_page, cause accessing invalid memory, this patch tries to handle error path correctly to fix this issue. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 16:59:12 +02:00
goto invalid_cp;
f2fs: fix to do sanity check with block address in main area This patch add to do sanity check with below field: - cp_pack_total_block_count - blkaddr of data/node - extent info - Overview BUG() in verify_block_addr() when writing to a corrupted f2fs image - Reproduce (4.18 upstream kernel) - POC (poc.c) static void activity(char *mpoint) { char *foo_bar_baz; int err; static int buf[8192]; memset(buf, 0, sizeof(buf)); err = asprintf(&foo_bar_baz, "%s/foo/bar/baz", mpoint); int fd = open(foo_bar_baz, O_RDWR | O_TRUNC, 0777); if (fd >= 0) { write(fd, (char *)buf, sizeof(buf)); fdatasync(fd); close(fd); } } int main(int argc, char *argv[]) { activity(argv[1]); return 0; } - Kernel message [ 689.349473] F2FS-fs (loop0): Mounted with checkpoint version = 3 [ 699.728662] WARNING: CPU: 0 PID: 1309 at fs/f2fs/segment.c:2860 f2fs_inplace_write_data+0x232/0x240 [ 699.728670] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.729056] CPU: 0 PID: 1309 Comm: a.out Not tainted 4.18.0-rc1+ #4 [ 699.729064] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.729074] RIP: 0010:f2fs_inplace_write_data+0x232/0x240 [ 699.729076] Code: ff e9 cf fe ff ff 49 8d 7d 10 e8 39 45 ad ff 4d 8b 7d 10 be 04 00 00 00 49 8d 7f 48 e8 07 49 ad ff 45 8b 7f 48 e9 fb fe ff ff <0f> 0b f0 41 80 4d 48 04 e9 65 fe ff ff 90 66 66 66 66 90 55 48 8d [ 699.729130] RSP: 0018:ffff8801f43af568 EFLAGS: 00010202 [ 699.729139] RAX: 000000000000003f RBX: ffff8801f43af7b8 RCX: ffffffffb88c9113 [ 699.729142] RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8802024e5540 [ 699.729144] RBP: ffff8801f43af590 R08: 0000000000000009 R09: ffffffffffffffe8 [ 699.729147] R10: 0000000000000001 R11: ffffed0039b0596a R12: ffff8802024e5540 [ 699.729149] R13: ffff8801f0335500 R14: ffff8801e3e7a700 R15: ffff8801e1ee4450 [ 699.729154] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.729156] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.729159] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.729171] Call Trace: [ 699.729192] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.729203] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.729238] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.729269] ? __radix_tree_replace+0xa3/0x120 [ 699.729276] __write_data_page+0x5c7/0xe30 [ 699.729291] ? kasan_check_read+0x11/0x20 [ 699.729310] ? page_mapped+0x8a/0x110 [ 699.729321] ? page_mkclean+0xe9/0x160 [ 699.729327] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.729331] ? invalid_page_referenced_vma+0x130/0x130 [ 699.729345] ? clear_page_dirty_for_io+0x332/0x450 [ 699.729351] f2fs_write_cache_pages+0x4ca/0x860 [ 699.729358] ? __write_data_page+0xe30/0xe30 [ 699.729374] ? percpu_counter_add_batch+0x22/0xa0 [ 699.729380] ? kasan_check_write+0x14/0x20 [ 699.729391] ? _raw_spin_lock+0x17/0x40 [ 699.729403] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.729413] ? iov_iter_advance+0x113/0x640 [ 699.729418] ? f2fs_write_end+0x133/0x2e0 [ 699.729423] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.729428] f2fs_write_data_pages+0x329/0x520 [ 699.729433] ? generic_perform_write+0x250/0x320 [ 699.729438] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729454] ? current_time+0x110/0x110 [ 699.729459] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.729464] do_writepages+0x37/0xb0 [ 699.729468] ? f2fs_write_cache_pages+0x860/0x860 [ 699.729472] ? do_writepages+0x37/0xb0 [ 699.729478] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.729483] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.729496] ? __vfs_write+0x2b2/0x410 [ 699.729501] file_write_and_wait_range+0x66/0xb0 [ 699.729506] f2fs_do_sync_file+0x1f9/0xd90 [ 699.729511] ? truncate_partial_data_page+0x290/0x290 [ 699.729521] ? __sb_end_write+0x30/0x50 [ 699.729526] ? vfs_write+0x20f/0x260 [ 699.729530] f2fs_sync_file+0x9a/0xb0 [ 699.729534] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.729548] vfs_fsync_range+0x68/0x100 [ 699.729554] ? __fget_light+0xc9/0xe0 [ 699.729558] do_fsync+0x3d/0x70 [ 699.729562] __x64_sys_fdatasync+0x24/0x30 [ 699.729585] do_syscall_64+0x78/0x170 [ 699.729595] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.729613] RIP: 0033:0x7f9bf930d800 [ 699.729615] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.729668] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.729673] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.729675] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.729678] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.729680] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.729683] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.729687] ---[ end trace 4ce02f25ff7d3df5 ]--- [ 699.729782] ------------[ cut here ]------------ [ 699.729785] kernel BUG at fs/f2fs/segment.h:654! [ 699.731055] invalid opcode: 0000 [#1] SMP KASAN PTI [ 699.732104] CPU: 0 PID: 1309 Comm: a.out Tainted: G W 4.18.0-rc1+ #4 [ 699.733684] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.735611] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.736649] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.740524] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.741573] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.743006] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.744426] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.745833] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.747256] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.748683] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.750293] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.751462] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.752874] Call Trace: [ 699.753386] ? f2fs_inplace_write_data+0x93/0x240 [ 699.754341] f2fs_inplace_write_data+0xd2/0x240 [ 699.755271] f2fs_do_write_data_page+0x2e2/0xe00 [ 699.756214] ? f2fs_should_update_outplace+0xd0/0xd0 [ 699.757215] ? memcg_drain_all_list_lrus+0x280/0x280 [ 699.758209] ? __radix_tree_replace+0xa3/0x120 [ 699.759164] __write_data_page+0x5c7/0xe30 [ 699.760002] ? kasan_check_read+0x11/0x20 [ 699.760823] ? page_mapped+0x8a/0x110 [ 699.761573] ? page_mkclean+0xe9/0x160 [ 699.762345] ? f2fs_do_write_data_page+0xe00/0xe00 [ 699.763332] ? invalid_page_referenced_vma+0x130/0x130 [ 699.764374] ? clear_page_dirty_for_io+0x332/0x450 [ 699.765347] f2fs_write_cache_pages+0x4ca/0x860 [ 699.766276] ? __write_data_page+0xe30/0xe30 [ 699.767161] ? percpu_counter_add_batch+0x22/0xa0 [ 699.768112] ? kasan_check_write+0x14/0x20 [ 699.768951] ? _raw_spin_lock+0x17/0x40 [ 699.769739] ? f2fs_mark_inode_dirty_sync.part.18+0x16/0x30 [ 699.770885] ? iov_iter_advance+0x113/0x640 [ 699.771743] ? f2fs_write_end+0x133/0x2e0 [ 699.772569] ? balance_dirty_pages_ratelimited+0x239/0x640 [ 699.773680] f2fs_write_data_pages+0x329/0x520 [ 699.774603] ? generic_perform_write+0x250/0x320 [ 699.775544] ? f2fs_write_cache_pages+0x860/0x860 [ 699.776510] ? current_time+0x110/0x110 [ 699.777299] ? f2fs_preallocate_blocks+0x1ef/0x370 [ 699.778279] do_writepages+0x37/0xb0 [ 699.779026] ? f2fs_write_cache_pages+0x860/0x860 [ 699.779978] ? do_writepages+0x37/0xb0 [ 699.780755] __filemap_fdatawrite_range+0x19a/0x1f0 [ 699.781746] ? delete_from_page_cache_batch+0x4e0/0x4e0 [ 699.782820] ? __vfs_write+0x2b2/0x410 [ 699.783597] file_write_and_wait_range+0x66/0xb0 [ 699.784540] f2fs_do_sync_file+0x1f9/0xd90 [ 699.785381] ? truncate_partial_data_page+0x290/0x290 [ 699.786415] ? __sb_end_write+0x30/0x50 [ 699.787204] ? vfs_write+0x20f/0x260 [ 699.787941] f2fs_sync_file+0x9a/0xb0 [ 699.788694] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.789572] vfs_fsync_range+0x68/0x100 [ 699.790360] ? __fget_light+0xc9/0xe0 [ 699.791128] do_fsync+0x3d/0x70 [ 699.791779] __x64_sys_fdatasync+0x24/0x30 [ 699.792614] do_syscall_64+0x78/0x170 [ 699.793371] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 699.794406] RIP: 0033:0x7f9bf930d800 [ 699.795134] Code: 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d 49 bf 2c 00 00 75 10 b8 4b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8 be 78 01 00 48 89 04 24 [ 699.798960] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.800483] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.801923] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.803373] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.804798] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.806233] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.807667] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep snd_hda_core snd_pcm snd_timer snd mac_hid i2c_piix4 soundcore ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx raid1 raid0 multipath linear 8139too crct10dif_pclmul crc32_pclmul qxl drm_kms_helper syscopyarea aesni_intel sysfillrect sysimgblt fb_sys_fops ttm drm aes_x86_64 crypto_simd cryptd 8139cp glue_helper mii pata_acpi floppy [ 699.817079] ---[ end trace 4ce02f25ff7d3df6 ]--- [ 699.818068] RIP: 0010:f2fs_submit_page_bio+0x29b/0x730 [ 699.819114] Code: 54 49 8d bd 18 04 00 00 e8 b2 59 af ff 41 8b 8d 18 04 00 00 8b 45 b8 41 d3 e6 44 01 f0 4c 8d 73 14 41 39 c7 0f 82 37 fe ff ff <0f> 0b 65 8b 05 2c 04 77 47 89 c0 48 0f a3 05 52 c1 d5 01 0f 92 c0 [ 699.822919] RSP: 0018:ffff8801f43af508 EFLAGS: 00010283 [ 699.823977] RAX: 0000000000000000 RBX: ffff8801f43af7b8 RCX: ffffffffb88a7cef [ 699.825436] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8801e3e7a64c [ 699.826881] RBP: ffff8801f43af558 R08: ffffed003e066b55 R09: ffffed003e066b55 [ 699.828292] R10: 0000000000000001 R11: ffffed003e066b54 R12: ffffea0007876940 [ 699.829750] R13: ffff8801f0335500 R14: ffff8801e3e7a600 R15: 0000000000000001 [ 699.831192] FS: 00007f9bf97f5700(0000) GS:ffff8801f6e00000(0000) knlGS:0000000000000000 [ 699.832793] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 699.833981] CR2: 00007f9bf925d170 CR3: 00000001f0c34000 CR4: 00000000000006f0 [ 699.835556] ================================================================== [ 699.837029] BUG: KASAN: stack-out-of-bounds in update_stack_state+0x38c/0x3e0 [ 699.838462] Read of size 8 at addr ffff8801f43af970 by task a.out/1309 [ 699.840086] CPU: 0 PID: 1309 Comm: a.out Tainted: G D W 4.18.0-rc1+ #4 [ 699.841603] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 699.843475] Call Trace: [ 699.843982] dump_stack+0x7b/0xb5 [ 699.844661] print_address_description+0x70/0x290 [ 699.845607] kasan_report+0x291/0x390 [ 699.846351] ? update_stack_state+0x38c/0x3e0 [ 699.853831] __asan_load8+0x54/0x90 [ 699.854569] update_stack_state+0x38c/0x3e0 [ 699.855428] ? __read_once_size_nocheck.constprop.7+0x20/0x20 [ 699.856601] ? __save_stack_trace+0x5e/0x100 [ 699.857476] unwind_next_frame.part.5+0x18e/0x490 [ 699.858448] ? unwind_dump+0x290/0x290 [ 699.859217] ? clear_page_dirty_for_io+0x332/0x450 [ 699.860185] __unwind_start+0x106/0x190 [ 699.860974] __save_stack_trace+0x5e/0x100 [ 699.861808] ? __save_stack_trace+0x5e/0x100 [ 699.862691] ? unlink_anon_vmas+0xba/0x2c0 [ 699.863525] save_stack_trace+0x1f/0x30 [ 699.864312] save_stack+0x46/0xd0 [ 699.864993] ? __alloc_pages_slowpath+0x1420/0x1420 [ 699.865990] ? flush_tlb_mm_range+0x15e/0x220 [ 699.866889] ? kasan_check_write+0x14/0x20 [ 699.867724] ? __dec_node_state+0x92/0xb0 [ 699.868543] ? lock_page_memcg+0x85/0xf0 [ 699.869350] ? unlock_page_memcg+0x16/0x80 [ 699.870185] ? page_remove_rmap+0x198/0x520 [ 699.871048] ? mark_page_accessed+0x133/0x200 [ 699.871930] ? _cond_resched+0x1a/0x50 [ 699.872700] ? unmap_page_range+0xcd4/0xe50 [ 699.873551] ? rb_next+0x58/0x80 [ 699.874217] ? rb_next+0x58/0x80 [ 699.874895] __kasan_slab_free+0x13c/0x1a0 [ 699.875734] ? unlink_anon_vmas+0xba/0x2c0 [ 699.876563] kasan_slab_free+0xe/0x10 [ 699.877315] kmem_cache_free+0x89/0x1e0 [ 699.878095] unlink_anon_vmas+0xba/0x2c0 [ 699.878913] free_pgtables+0x101/0x1b0 [ 699.879677] exit_mmap+0x146/0x2a0 [ 699.880378] ? __ia32_sys_munmap+0x50/0x50 [ 699.881214] ? kasan_check_read+0x11/0x20 [ 699.882052] ? mm_update_next_owner+0x322/0x380 [ 699.882985] mmput+0x8b/0x1d0 [ 699.883602] do_exit+0x43a/0x1390 [ 699.884288] ? mm_update_next_owner+0x380/0x380 [ 699.885212] ? f2fs_sync_file+0x9a/0xb0 [ 699.885995] ? f2fs_do_sync_file+0xd90/0xd90 [ 699.886877] ? vfs_fsync_range+0x68/0x100 [ 699.887694] ? __fget_light+0xc9/0xe0 [ 699.888442] ? do_fsync+0x3d/0x70 [ 699.889118] ? __x64_sys_fdatasync+0x24/0x30 [ 699.889996] rewind_stack_do_exit+0x17/0x20 [ 699.890860] RIP: 0033:0x7f9bf930d800 [ 699.891585] Code: Bad RIP value. [ 699.892268] RSP: 002b:00007ffee3606c68 EFLAGS: 00000246 ORIG_RAX: 000000000000004b [ 699.893781] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f9bf930d800 [ 699.895220] RDX: 0000000000008000 RSI: 00000000006010a0 RDI: 0000000000000003 [ 699.896643] RBP: 00007ffee3606ca0 R08: 0000000001503010 R09: 0000000000000000 [ 699.898069] R10: 00000000000002e8 R11: 0000000000000246 R12: 0000000000400610 [ 699.899505] R13: 00007ffee3606da0 R14: 0000000000000000 R15: 0000000000000000 [ 699.901241] The buggy address belongs to the page: [ 699.902215] page:ffffea0007d0ebc0 count:0 mapcount:0 mapping:0000000000000000 index:0x0 [ 699.903811] flags: 0x2ffff0000000000() [ 699.904585] raw: 02ffff0000000000 0000000000000000 ffffffff07d00101 0000000000000000 [ 699.906125] raw: 0000000000000000 0000000000240000 00000000ffffffff 0000000000000000 [ 699.907673] page dumped because: kasan: bad access detected [ 699.909108] Memory state around the buggy address: [ 699.910077] ffff8801f43af800: 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 00 [ 699.911528] ffff8801f43af880: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 699.912953] >ffff8801f43af900: 00 00 00 00 00 00 00 00 f1 01 f4 f4 f4 f2 f2 f2 [ 699.914392] ^ [ 699.915758] ffff8801f43af980: f2 00 f4 f4 00 00 00 00 f2 00 00 00 00 00 00 00 [ 699.917193] ffff8801f43afa00: 00 00 00 00 00 00 00 00 00 f3 f3 f3 00 00 00 00 [ 699.918634] ================================================================== - Location https://elixir.bootlin.com/linux/v4.18-rc1/source/fs/f2fs/segment.h#L644 Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 13:13:44 +02:00
}
pre_version = *version;
cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
err = get_checkpoint_version(sbi, cp_addr, &cp_block,
&cp_page_2, version);
if (err)
f2fs: fix invalid memory access syzbot found the following crash on: HEAD commit: d9bd94c0bcaa Add linux-next specific files for 20180801 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1001189c400000 kernel config: https://syzkaller.appspot.com/x/.config?x=cc8964ea4d04518c dashboard link: https://syzkaller.appspot.com/bug?extid=c966a82db0b14aa37e81 compiler: gcc (GCC) 8.0.1 20180413 (experimental) Unfortunately, I don't have any reproducer for this crash yet. IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+c966a82db0b14aa37e81@syzkaller.appspotmail.com loop7: rw=12288, want=8200, limit=20 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. openvswitch: netlink: Message has 8 unknown bytes. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN CPU: 1 PID: 7615 Comm: syz-executor7 Not tainted 4.18.0-rc7-next-20180801+ #29 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_get_valid_checkpoint+0x436/0x1ec0 fs/f2fs/checkpoint.c:860 f2fs_fill_super+0x2d42/0x8110 fs/f2fs/super.c:2883 mount_bdev+0x314/0x3e0 fs/super.c:1344 f2fs_mount+0x3c/0x50 fs/f2fs/super.c:3133 legacy_get_tree+0x131/0x460 fs/fs_context.c:729 vfs_get_tree+0x1cb/0x5c0 fs/super.c:1743 do_new_mount fs/namespace.c:2603 [inline] do_mount+0x6f2/0x1e20 fs/namespace.c:2927 ksys_mount+0x12d/0x140 fs/namespace.c:3143 __do_sys_mount fs/namespace.c:3157 [inline] __se_sys_mount fs/namespace.c:3154 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3154 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x45943a Code: b8 a6 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 bd 8a fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 9a 8a fb ff c3 66 0f 1f 84 00 00 00 00 00 RSP: 002b:00007f36a61d4a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007f36a61d4b30 RCX: 000000000045943a RDX: 00007f36a61d4ad0 RSI: 0000000020000100 RDI: 00007f36a61d4af0 RBP: 0000000020000100 R08: 00007f36a61d4b30 R09: 00007f36a61d4ad0 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000013 R13: 0000000000000000 R14: 00000000004c8ea0 R15: 0000000000000000 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace bd8550c129352286 ]--- RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 openvswitch: netlink: Message has 8 unknown bytes. R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 In validate_checkpoint(), if we failed to call get_checkpoint_version(), we will pass returned invalid page pointer into f2fs_put_page, cause accessing invalid memory, this patch tries to handle error path correctly to fix this issue. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 16:59:12 +02:00
goto invalid_cp;
cur_version = *version;
if (cur_version == pre_version) {
*version = cur_version;
f2fs_put_page(cp_page_2, 1);
return cp_page_1;
}
f2fs_put_page(cp_page_2, 1);
f2fs: fix invalid memory access syzbot found the following crash on: HEAD commit: d9bd94c0bcaa Add linux-next specific files for 20180801 git tree: linux-next console output: https://syzkaller.appspot.com/x/log.txt?x=1001189c400000 kernel config: https://syzkaller.appspot.com/x/.config?x=cc8964ea4d04518c dashboard link: https://syzkaller.appspot.com/bug?extid=c966a82db0b14aa37e81 compiler: gcc (GCC) 8.0.1 20180413 (experimental) Unfortunately, I don't have any reproducer for this crash yet. IMPORTANT: if you fix the bug, please add the following tag to the commit: Reported-by: syzbot+c966a82db0b14aa37e81@syzkaller.appspotmail.com loop7: rw=12288, want=8200, limit=20 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. openvswitch: netlink: Message has 8 unknown bytes. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN CPU: 1 PID: 7615 Comm: syz-executor7 Not tainted 4.18.0-rc7-next-20180801+ #29 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: f2fs_get_valid_checkpoint+0x436/0x1ec0 fs/f2fs/checkpoint.c:860 f2fs_fill_super+0x2d42/0x8110 fs/f2fs/super.c:2883 mount_bdev+0x314/0x3e0 fs/super.c:1344 f2fs_mount+0x3c/0x50 fs/f2fs/super.c:3133 legacy_get_tree+0x131/0x460 fs/fs_context.c:729 vfs_get_tree+0x1cb/0x5c0 fs/super.c:1743 do_new_mount fs/namespace.c:2603 [inline] do_mount+0x6f2/0x1e20 fs/namespace.c:2927 ksys_mount+0x12d/0x140 fs/namespace.c:3143 __do_sys_mount fs/namespace.c:3157 [inline] __se_sys_mount fs/namespace.c:3154 [inline] __x64_sys_mount+0xbe/0x150 fs/namespace.c:3154 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x45943a Code: b8 a6 00 00 00 0f 05 48 3d 01 f0 ff ff 0f 83 bd 8a fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 9a 8a fb ff c3 66 0f 1f 84 00 00 00 00 00 RSP: 002b:00007f36a61d4a88 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007f36a61d4b30 RCX: 000000000045943a RDX: 00007f36a61d4ad0 RSI: 0000000020000100 RDI: 00007f36a61d4af0 RBP: 0000000020000100 R08: 00007f36a61d4b30 R09: 00007f36a61d4ad0 R10: 0000000000000000 R11: 0000000000000206 R12: 0000000000000013 R13: 0000000000000000 R14: 00000000004c8ea0 R15: 0000000000000000 Modules linked in: Dumping ftrace buffer: (ftrace buffer empty) ---[ end trace bd8550c129352286 ]--- RIP: 0010:__read_once_size include/linux/compiler.h:188 [inline] RIP: 0010:compound_head include/linux/page-flags.h:142 [inline] RIP: 0010:PageLocked include/linux/page-flags.h:272 [inline] RIP: 0010:f2fs_put_page fs/f2fs/f2fs.h:2011 [inline] RIP: 0010:validate_checkpoint+0x66d/0xec0 fs/f2fs/checkpoint.c:835 Code: e8 58 05 7f fe 4c 8d 6b 80 4d 8d 74 24 08 48 b8 00 00 00 00 00 fc ff df 4c 89 ea 48 c1 ea 03 c6 04 02 00 4c 89 f2 48 c1 ea 03 <80> 3c 02 00 0f 85 f4 06 00 00 4c 89 ea 4d 8b 7c 24 08 48 b8 00 00 RSP: 0018:ffff8801937cebe8 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: ffff8801937cef30 RCX: ffffc90006035000 RDX: 0000000000000000 RSI: ffffffff82fd9658 RDI: 0000000000000005 netlink: 65342 bytes leftover after parsing attributes in process `syz-executor4'. RBP: ffff8801937cef58 R08: ffff8801ab254700 R09: fffff94000d9e026 openvswitch: netlink: Message has 8 unknown bytes. R10: fffff94000d9e026 R11: ffffea0006cf0137 R12: fffffffffffffffb R13: ffff8801937ceeb0 R14: 0000000000000003 R15: ffff880193419b40 FS: 00007f36a61d5700(0000) GS:ffff8801db100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fc04ff93000 CR3: 00000001d0562000 CR4: 00000000001426e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 In validate_checkpoint(), if we failed to call get_checkpoint_version(), we will pass returned invalid page pointer into f2fs_put_page, cause accessing invalid memory, this patch tries to handle error path correctly to fix this issue. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 16:59:12 +02:00
invalid_cp:
f2fs_put_page(cp_page_1, 1);
return NULL;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *cp_block;
struct f2fs_super_block *fsb = sbi->raw_super;
struct page *cp1, *cp2, *cur_page;
unsigned long blk_size = sbi->blocksize;
unsigned long long cp1_version = 0, cp2_version = 0;
unsigned long long cp_start_blk_no;
unsigned int cp_blks = 1 + __cp_payload(sbi);
block_t cp_blk_no;
int i;
treewide: Use array_size() in f2fs_kzalloc() The f2fs_kzalloc() function has no 2-factor argument form, so multiplication factors need to be wrapped in array_size(). This patch replaces cases of: f2fs_kzalloc(handle, a * b, gfp) with: f2fs_kzalloc(handle, array_size(a, b), gfp) as well as handling cases of: f2fs_kzalloc(handle, a * b * c, gfp) with: f2fs_kzalloc(handle, array3_size(a, b, c), gfp) This does, however, attempt to ignore constant size factors like: f2fs_kzalloc(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_kzalloc(HANDLE, - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | f2fs_kzalloc(HANDLE, - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression HANDLE; expression COUNT; typedef u8; typedef __u8; @@ ( f2fs_kzalloc(HANDLE, - sizeof(u8) * (COUNT) + COUNT , ...) | f2fs_kzalloc(HANDLE, - sizeof(__u8) * (COUNT) + COUNT , ...) | f2fs_kzalloc(HANDLE, - sizeof(char) * (COUNT) + COUNT , ...) | f2fs_kzalloc(HANDLE, - sizeof(unsigned char) * (COUNT) + COUNT , ...) | f2fs_kzalloc(HANDLE, - sizeof(u8) * COUNT + COUNT , ...) | f2fs_kzalloc(HANDLE, - sizeof(__u8) * COUNT + COUNT , ...) | f2fs_kzalloc(HANDLE, - sizeof(char) * COUNT + COUNT , ...) | f2fs_kzalloc(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_kzalloc(HANDLE, - sizeof(TYPE) * (COUNT_ID) + array_size(COUNT_ID, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE) * COUNT_ID + array_size(COUNT_ID, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE) * COUNT_CONST + array_size(COUNT_CONST, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING) * (COUNT_ID) + array_size(COUNT_ID, sizeof(THING)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING) * COUNT_ID + array_size(COUNT_ID, sizeof(THING)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING) * (COUNT_CONST) + array_size(COUNT_CONST, sizeof(THING)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING) * COUNT_CONST + array_size(COUNT_CONST, sizeof(THING)) , ...) ) // 2-factor product, only identifiers. @@ expression HANDLE; identifier SIZE, COUNT; @@ f2fs_kzalloc(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_kzalloc(HANDLE, - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | f2fs_kzalloc(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_kzalloc(HANDLE, - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | f2fs_kzalloc(HANDLE, - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | f2fs_kzalloc(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_kzalloc(HANDLE, - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | f2fs_kzalloc(HANDLE, - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | f2fs_kzalloc(HANDLE, - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | f2fs_kzalloc(HANDLE, - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | f2fs_kzalloc(HANDLE, - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | f2fs_kzalloc(HANDLE, - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | f2fs_kzalloc(HANDLE, - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | f2fs_kzalloc(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_kzalloc(HANDLE, C1 * C2 * C3, ...) | f2fs_kzalloc(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_kzalloc(HANDLE, C1 * C2, ...) | f2fs_kzalloc(HANDLE, - E1 * E2 + array_size(E1, E2) , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 23:28:23 +02:00
sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks),
GFP_KERNEL);
if (!sbi->ckpt)
return -ENOMEM;
/*
* Finding out valid cp block involves read both
* sets( cp pack1 and cp pack 2)
*/
cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr);
cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version);
/* The second checkpoint pack should start at the next segment */
cp_start_blk_no += ((unsigned long long)1) <<
le32_to_cpu(fsb->log_blocks_per_seg);
cp2 = validate_checkpoint(sbi, cp_start_blk_no, &cp2_version);
if (cp1 && cp2) {
if (ver_after(cp2_version, cp1_version))
cur_page = cp2;
else
cur_page = cp1;
} else if (cp1) {
cur_page = cp1;
} else if (cp2) {
cur_page = cp2;
} else {
goto fail_no_cp;
}
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
memcpy(sbi->ckpt, cp_block, blk_size);
if (cur_page == cp1)
sbi->cur_cp_pack = 1;
else
sbi->cur_cp_pack = 2;
f2fs: fix to do sanity check with cp_pack_start_sum After fuzzing, cp_pack_start_sum could be corrupted, so current log's summary info should be wrong due to loading incorrect summary block. Then, if segment's type in current log is exceeded NR_CURSEG_TYPE, it can lead accessing invalid dirty_i->dirty_segmap bitmap finally. Add sanity check for cp_pack_start_sum to fix this issue. https://bugzilla.kernel.org/show_bug.cgi?id=200419 - Reproduce - Kernel message (f2fs-dev w/ KASAN) [ 3117.578432] F2FS-fs (loop0): Invalid log blocks per segment (8) [ 3117.578445] F2FS-fs (loop0): Can't find valid F2FS filesystem in 2th superblock [ 3117.581364] F2FS-fs (loop0): invalid crc_offset: 30716 [ 3117.583564] WARNING: CPU: 1 PID: 1225 at fs/f2fs/checkpoint.c:90 __get_meta_page+0x448/0x4b0 [ 3117.583570] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_timer joydev input_leds serio_raw snd soundcore mac_hid i2c_piix4 ib_iser rdma_cm iw_cm ib_cm ib_core configfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi btrfs zstd_decompress zstd_compress xxhash raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear 8139too qxl ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel psmouse aes_x86_64 8139cp crypto_simd cryptd mii glue_helper pata_acpi floppy [ 3117.584014] CPU: 1 PID: 1225 Comm: mount Not tainted 4.17.0+ #1 [ 3117.584017] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 3117.584022] RIP: 0010:__get_meta_page+0x448/0x4b0 [ 3117.584023] Code: 00 49 8d bc 24 84 00 00 00 e8 74 54 da ff 41 83 8c 24 84 00 00 00 08 4c 89 f6 4c 89 ef e8 c0 d9 95 00 48 89 ef e8 18 e3 00 00 <0f> 0b f0 80 4d 48 04 e9 0f fe ff ff 0f 0b 48 89 c7 48 89 04 24 e8 [ 3117.584072] RSP: 0018:ffff88018eb678c0 EFLAGS: 00010286 [ 3117.584082] RAX: ffff88018f0a6a78 RBX: ffffea0007a46600 RCX: ffffffff9314d1b2 [ 3117.584085] RDX: ffffffff00000001 RSI: 0000000000000000 RDI: ffff88018f0a6a98 [ 3117.584087] RBP: ffff88018ebe9980 R08: 0000000000000002 R09: 0000000000000001 [ 3117.584090] R10: 0000000000000001 R11: ffffed00326e4450 R12: ffff880193722200 [ 3117.584092] R13: ffff88018ebe9afc R14: 0000000000000206 R15: ffff88018eb67900 [ 3117.584096] FS: 00007f5694636840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000 [ 3117.584098] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3117.584101] CR2: 00000000016f21b8 CR3: 0000000191c22000 CR4: 00000000000006e0 [ 3117.584112] Call Trace: [ 3117.584121] ? f2fs_set_meta_page_dirty+0x150/0x150 [ 3117.584127] ? f2fs_build_segment_manager+0xbf9/0x3190 [ 3117.584133] ? f2fs_npages_for_summary_flush+0x75/0x120 [ 3117.584145] f2fs_build_segment_manager+0xda8/0x3190 [ 3117.584151] ? f2fs_get_valid_checkpoint+0x298/0xa00 [ 3117.584156] ? f2fs_flush_sit_entries+0x10e0/0x10e0 [ 3117.584184] ? map_id_range_down+0x17c/0x1b0 [ 3117.584188] ? __put_user_ns+0x30/0x30 [ 3117.584206] ? find_next_bit+0x53/0x90 [ 3117.584237] ? cpumask_next+0x16/0x20 [ 3117.584249] f2fs_fill_super+0x1948/0x2b40 [ 3117.584258] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.584279] ? sget_userns+0x65e/0x690 [ 3117.584296] ? set_blocksize+0x88/0x130 [ 3117.584302] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.584305] mount_bdev+0x1c0/0x200 [ 3117.584310] mount_fs+0x5c/0x190 [ 3117.584320] vfs_kern_mount+0x64/0x190 [ 3117.584330] do_mount+0x2e4/0x1450 [ 3117.584343] ? lockref_put_return+0x130/0x130 [ 3117.584347] ? copy_mount_string+0x20/0x20 [ 3117.584357] ? kasan_unpoison_shadow+0x31/0x40 [ 3117.584362] ? kasan_kmalloc+0xa6/0xd0 [ 3117.584373] ? memcg_kmem_put_cache+0x16/0x90 [ 3117.584377] ? __kmalloc_track_caller+0x196/0x210 [ 3117.584383] ? _copy_from_user+0x61/0x90 [ 3117.584396] ? memdup_user+0x3e/0x60 [ 3117.584401] ksys_mount+0x7e/0xd0 [ 3117.584405] __x64_sys_mount+0x62/0x70 [ 3117.584427] do_syscall_64+0x73/0x160 [ 3117.584440] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 3117.584455] RIP: 0033:0x7f5693f14b9a [ 3117.584456] Code: 48 8b 0d 01 c3 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ce c2 2b 00 f7 d8 64 89 01 48 [ 3117.584505] RSP: 002b:00007fff27346488 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 3117.584510] RAX: ffffffffffffffda RBX: 00000000016e2030 RCX: 00007f5693f14b9a [ 3117.584512] RDX: 00000000016e2210 RSI: 00000000016e3f30 RDI: 00000000016ee040 [ 3117.584514] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013 [ 3117.584516] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 00000000016ee040 [ 3117.584519] R13: 00000000016e2210 R14: 0000000000000000 R15: 0000000000000003 [ 3117.584523] ---[ end trace a8e0d899985faf31 ]--- [ 3117.685663] F2FS-fs (loop0): f2fs_check_nid_range: out-of-range nid=2, run fsck to fix. [ 3117.685673] F2FS-fs (loop0): recover_data: ino = 2 (i_size: recover) recovered = 1, err = 0 [ 3117.685707] ================================================================== [ 3117.685955] BUG: KASAN: slab-out-of-bounds in __remove_dirty_segment+0xdd/0x1e0 [ 3117.686175] Read of size 8 at addr ffff88018f0a63d0 by task mount/1225 [ 3117.686477] CPU: 0 PID: 1225 Comm: mount Tainted: G W 4.17.0+ #1 [ 3117.686481] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 3117.686483] Call Trace: [ 3117.686494] dump_stack+0x71/0xab [ 3117.686512] print_address_description+0x6b/0x290 [ 3117.686517] kasan_report+0x28e/0x390 [ 3117.686522] ? __remove_dirty_segment+0xdd/0x1e0 [ 3117.686527] __remove_dirty_segment+0xdd/0x1e0 [ 3117.686532] locate_dirty_segment+0x189/0x190 [ 3117.686538] f2fs_allocate_new_segments+0xa9/0xe0 [ 3117.686543] recover_data+0x703/0x2c20 [ 3117.686547] ? f2fs_recover_fsync_data+0x48f/0xd50 [ 3117.686553] ? ksys_mount+0x7e/0xd0 [ 3117.686564] ? policy_nodemask+0x1a/0x90 [ 3117.686567] ? policy_node+0x56/0x70 [ 3117.686571] ? add_fsync_inode+0xf0/0xf0 [ 3117.686592] ? blk_finish_plug+0x44/0x60 [ 3117.686597] ? f2fs_ra_meta_pages+0x38b/0x5e0 [ 3117.686602] ? find_inode_fast+0xac/0xc0 [ 3117.686606] ? f2fs_is_valid_blkaddr+0x320/0x320 [ 3117.686618] ? __radix_tree_lookup+0x150/0x150 [ 3117.686633] ? dqget+0x670/0x670 [ 3117.686648] ? pagecache_get_page+0x29/0x410 [ 3117.686656] ? kmem_cache_alloc+0x176/0x1e0 [ 3117.686660] ? f2fs_is_valid_blkaddr+0x11d/0x320 [ 3117.686664] f2fs_recover_fsync_data+0xc23/0xd50 [ 3117.686670] ? f2fs_space_for_roll_forward+0x60/0x60 [ 3117.686674] ? rb_insert_color+0x323/0x3d0 [ 3117.686678] ? f2fs_recover_orphan_inodes+0xa5/0x700 [ 3117.686683] ? proc_register+0x153/0x1d0 [ 3117.686686] ? f2fs_remove_orphan_inode+0x10/0x10 [ 3117.686695] ? f2fs_attr_store+0x50/0x50 [ 3117.686700] ? proc_create_single_data+0x52/0x60 [ 3117.686707] f2fs_fill_super+0x1d06/0x2b40 [ 3117.686728] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.686735] ? sget_userns+0x65e/0x690 [ 3117.686740] ? set_blocksize+0x88/0x130 [ 3117.686745] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.686748] mount_bdev+0x1c0/0x200 [ 3117.686753] mount_fs+0x5c/0x190 [ 3117.686758] vfs_kern_mount+0x64/0x190 [ 3117.686762] do_mount+0x2e4/0x1450 [ 3117.686769] ? lockref_put_return+0x130/0x130 [ 3117.686773] ? copy_mount_string+0x20/0x20 [ 3117.686777] ? kasan_unpoison_shadow+0x31/0x40 [ 3117.686780] ? kasan_kmalloc+0xa6/0xd0 [ 3117.686786] ? memcg_kmem_put_cache+0x16/0x90 [ 3117.686790] ? __kmalloc_track_caller+0x196/0x210 [ 3117.686795] ? _copy_from_user+0x61/0x90 [ 3117.686801] ? memdup_user+0x3e/0x60 [ 3117.686804] ksys_mount+0x7e/0xd0 [ 3117.686809] __x64_sys_mount+0x62/0x70 [ 3117.686816] do_syscall_64+0x73/0x160 [ 3117.686824] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 3117.686829] RIP: 0033:0x7f5693f14b9a [ 3117.686830] Code: 48 8b 0d 01 c3 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ce c2 2b 00 f7 d8 64 89 01 48 [ 3117.686887] RSP: 002b:00007fff27346488 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 3117.686892] RAX: ffffffffffffffda RBX: 00000000016e2030 RCX: 00007f5693f14b9a [ 3117.686894] RDX: 00000000016e2210 RSI: 00000000016e3f30 RDI: 00000000016ee040 [ 3117.686896] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013 [ 3117.686899] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 00000000016ee040 [ 3117.686901] R13: 00000000016e2210 R14: 0000000000000000 R15: 0000000000000003 [ 3117.687005] Allocated by task 1225: [ 3117.687152] kasan_kmalloc+0xa6/0xd0 [ 3117.687157] kmem_cache_alloc_trace+0xfd/0x200 [ 3117.687161] f2fs_build_segment_manager+0x2d09/0x3190 [ 3117.687165] f2fs_fill_super+0x1948/0x2b40 [ 3117.687168] mount_bdev+0x1c0/0x200 [ 3117.687171] mount_fs+0x5c/0x190 [ 3117.687174] vfs_kern_mount+0x64/0x190 [ 3117.687177] do_mount+0x2e4/0x1450 [ 3117.687180] ksys_mount+0x7e/0xd0 [ 3117.687182] __x64_sys_mount+0x62/0x70 [ 3117.687186] do_syscall_64+0x73/0x160 [ 3117.687190] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 3117.687285] Freed by task 19: [ 3117.687412] __kasan_slab_free+0x137/0x190 [ 3117.687416] kfree+0x8b/0x1b0 [ 3117.687460] ttm_bo_man_put_node+0x61/0x80 [ttm] [ 3117.687476] ttm_bo_cleanup_refs+0x15f/0x250 [ttm] [ 3117.687492] ttm_bo_delayed_delete+0x2f0/0x300 [ttm] [ 3117.687507] ttm_bo_delayed_workqueue+0x17/0x50 [ttm] [ 3117.687528] process_one_work+0x2f9/0x740 [ 3117.687531] worker_thread+0x78/0x6b0 [ 3117.687541] kthread+0x177/0x1c0 [ 3117.687545] ret_from_fork+0x35/0x40 [ 3117.687638] The buggy address belongs to the object at ffff88018f0a6300 which belongs to the cache kmalloc-192 of size 192 [ 3117.688014] The buggy address is located 16 bytes to the right of 192-byte region [ffff88018f0a6300, ffff88018f0a63c0) [ 3117.688382] The buggy address belongs to the page: [ 3117.688554] page:ffffea00063c2980 count:1 mapcount:0 mapping:ffff8801f3403180 index:0x0 [ 3117.688788] flags: 0x17fff8000000100(slab) [ 3117.688944] raw: 017fff8000000100 ffffea00063c2840 0000000e0000000e ffff8801f3403180 [ 3117.689166] raw: 0000000000000000 0000000080100010 00000001ffffffff 0000000000000000 [ 3117.689386] page dumped because: kasan: bad access detected [ 3117.689653] Memory state around the buggy address: [ 3117.689816] ffff88018f0a6280: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc [ 3117.690027] ffff88018f0a6300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 3117.690239] >ffff88018f0a6380: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 3117.690448] ^ [ 3117.690644] ffff88018f0a6400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 3117.690868] ffff88018f0a6480: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 3117.691077] ================================================================== [ 3117.691290] Disabling lock debugging due to kernel taint [ 3117.693893] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [ 3117.694120] PGD 80000001f01bc067 P4D 80000001f01bc067 PUD 1d9638067 PMD 0 [ 3117.694338] Oops: 0002 [#1] SMP KASAN PTI [ 3117.694490] CPU: 1 PID: 1225 Comm: mount Tainted: G B W 4.17.0+ #1 [ 3117.694703] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [ 3117.695073] RIP: 0010:__remove_dirty_segment+0xe2/0x1e0 [ 3117.695246] Code: c4 48 89 c7 e8 cf bb d7 ff 45 0f b6 24 24 41 83 e4 3f 44 88 64 24 07 41 83 e4 3f 4a 8d 7c e3 08 e8 b3 bc d7 ff 4a 8b 4c e3 08 <f0> 4c 0f b3 29 0f 82 94 00 00 00 48 8d bd 20 04 00 00 e8 97 bb d7 [ 3117.695793] RSP: 0018:ffff88018eb67638 EFLAGS: 00010292 [ 3117.695969] RAX: 0000000000000000 RBX: ffff88018f0a6300 RCX: 0000000000000000 [ 3117.696182] RDX: 0000000000000000 RSI: 0000000000000297 RDI: 0000000000000297 [ 3117.696391] RBP: ffff88018ebe9980 R08: ffffed003e743ebb R09: ffffed003e743ebb [ 3117.696604] R10: 0000000000000001 R11: ffffed003e743eba R12: 0000000000000019 [ 3117.696813] R13: 0000000000000014 R14: 0000000000000320 R15: ffff88018ebe99e0 [ 3117.697032] FS: 00007f5694636840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000 [ 3117.697280] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3117.702357] CR2: 00007fe89bb1a000 CR3: 0000000191c22000 CR4: 00000000000006e0 [ 3117.707235] Call Trace: [ 3117.712077] locate_dirty_segment+0x189/0x190 [ 3117.716891] f2fs_allocate_new_segments+0xa9/0xe0 [ 3117.721617] recover_data+0x703/0x2c20 [ 3117.726316] ? f2fs_recover_fsync_data+0x48f/0xd50 [ 3117.730957] ? ksys_mount+0x7e/0xd0 [ 3117.735573] ? policy_nodemask+0x1a/0x90 [ 3117.740198] ? policy_node+0x56/0x70 [ 3117.744829] ? add_fsync_inode+0xf0/0xf0 [ 3117.749487] ? blk_finish_plug+0x44/0x60 [ 3117.754152] ? f2fs_ra_meta_pages+0x38b/0x5e0 [ 3117.758831] ? find_inode_fast+0xac/0xc0 [ 3117.763448] ? f2fs_is_valid_blkaddr+0x320/0x320 [ 3117.768046] ? __radix_tree_lookup+0x150/0x150 [ 3117.772603] ? dqget+0x670/0x670 [ 3117.777159] ? pagecache_get_page+0x29/0x410 [ 3117.781648] ? kmem_cache_alloc+0x176/0x1e0 [ 3117.786067] ? f2fs_is_valid_blkaddr+0x11d/0x320 [ 3117.790476] f2fs_recover_fsync_data+0xc23/0xd50 [ 3117.794790] ? f2fs_space_for_roll_forward+0x60/0x60 [ 3117.799086] ? rb_insert_color+0x323/0x3d0 [ 3117.803304] ? f2fs_recover_orphan_inodes+0xa5/0x700 [ 3117.807563] ? proc_register+0x153/0x1d0 [ 3117.811766] ? f2fs_remove_orphan_inode+0x10/0x10 [ 3117.815947] ? f2fs_attr_store+0x50/0x50 [ 3117.820087] ? proc_create_single_data+0x52/0x60 [ 3117.824262] f2fs_fill_super+0x1d06/0x2b40 [ 3117.828367] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.832432] ? sget_userns+0x65e/0x690 [ 3117.836500] ? set_blocksize+0x88/0x130 [ 3117.840501] ? f2fs_commit_super+0x1a0/0x1a0 [ 3117.844420] mount_bdev+0x1c0/0x200 [ 3117.848275] mount_fs+0x5c/0x190 [ 3117.852053] vfs_kern_mount+0x64/0x190 [ 3117.855810] do_mount+0x2e4/0x1450 [ 3117.859441] ? lockref_put_return+0x130/0x130 [ 3117.862996] ? copy_mount_string+0x20/0x20 [ 3117.866417] ? kasan_unpoison_shadow+0x31/0x40 [ 3117.869719] ? kasan_kmalloc+0xa6/0xd0 [ 3117.872948] ? memcg_kmem_put_cache+0x16/0x90 [ 3117.876121] ? __kmalloc_track_caller+0x196/0x210 [ 3117.879333] ? _copy_from_user+0x61/0x90 [ 3117.882467] ? memdup_user+0x3e/0x60 [ 3117.885604] ksys_mount+0x7e/0xd0 [ 3117.888700] __x64_sys_mount+0x62/0x70 [ 3117.891742] do_syscall_64+0x73/0x160 [ 3117.894692] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 3117.897669] RIP: 0033:0x7f5693f14b9a [ 3117.900563] Code: 48 8b 0d 01 c3 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ce c2 2b 00 f7 d8 64 89 01 48 [ 3117.906922] RSP: 002b:00007fff27346488 EFLAGS: 00000206 ORIG_RAX: 00000000000000a5 [ 3117.910159] RAX: ffffffffffffffda RBX: 00000000016e2030 RCX: 00007f5693f14b9a [ 3117.913469] RDX: 00000000016e2210 RSI: 00000000016e3f30 RDI: 00000000016ee040 [ 3117.916764] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000013 [ 3117.920071] R10: 00000000c0ed0000 R11: 0000000000000206 R12: 00000000016ee040 [ 3117.923393] R13: 00000000016e2210 R14: 0000000000000000 R15: 0000000000000003 [ 3117.926680] Modules linked in: snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_timer joydev input_leds serio_raw snd soundcore mac_hid i2c_piix4 ib_iser rdma_cm iw_cm ib_cm ib_core configfs iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi btrfs zstd_decompress zstd_compress xxhash raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid1 raid0 multipath linear 8139too qxl ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel psmouse aes_x86_64 8139cp crypto_simd cryptd mii glue_helper pata_acpi floppy [ 3117.949979] CR2: 0000000000000000 [ 3117.954283] ---[ end trace a8e0d899985faf32 ]--- [ 3117.958575] RIP: 0010:__remove_dirty_segment+0xe2/0x1e0 [ 3117.962810] Code: c4 48 89 c7 e8 cf bb d7 ff 45 0f b6 24 24 41 83 e4 3f 44 88 64 24 07 41 83 e4 3f 4a 8d 7c e3 08 e8 b3 bc d7 ff 4a 8b 4c e3 08 <f0> 4c 0f b3 29 0f 82 94 00 00 00 48 8d bd 20 04 00 00 e8 97 bb d7 [ 3117.971789] RSP: 0018:ffff88018eb67638 EFLAGS: 00010292 [ 3117.976333] RAX: 0000000000000000 RBX: ffff88018f0a6300 RCX: 0000000000000000 [ 3117.980926] RDX: 0000000000000000 RSI: 0000000000000297 RDI: 0000000000000297 [ 3117.985497] RBP: ffff88018ebe9980 R08: ffffed003e743ebb R09: ffffed003e743ebb [ 3117.990098] R10: 0000000000000001 R11: ffffed003e743eba R12: 0000000000000019 [ 3117.994761] R13: 0000000000000014 R14: 0000000000000320 R15: ffff88018ebe99e0 [ 3117.999392] FS: 00007f5694636840(0000) GS:ffff8801f3b00000(0000) knlGS:0000000000000000 [ 3118.004096] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3118.008816] CR2: 00007fe89bb1a000 CR3: 0000000191c22000 CR4: 00000000000006e0 - Location https://elixir.bootlin.com/linux/v4.18-rc3/source/fs/f2fs/segment.c#L775 if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t])) dirty_i->nr_dirty[t]--; Here dirty_i->dirty_segmap[t] can be NULL which leads to crash in test_and_clear_bit() Reported-by Wen Xu <wen.xu@gatech.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-01 13:16:11 +02:00
/* Sanity checking of checkpoint */
if (f2fs_sanity_check_ckpt(sbi))
goto free_fail_no_cp;
if (cp_blks <= 1)
goto done;
cp_blk_no = le32_to_cpu(fsb->cp_blkaddr);
if (cur_page == cp2)
cp_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
for (i = 1; i < cp_blks; i++) {
void *sit_bitmap_ptr;
unsigned char *ckpt = (unsigned char *)sbi->ckpt;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i);
if (IS_ERR(cur_page))
goto free_fail_no_cp;
sit_bitmap_ptr = page_address(cur_page);
memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size);
f2fs_put_page(cur_page, 1);
}
done:
f2fs_put_page(cp1, 1);
f2fs_put_page(cp2, 1);
return 0;
free_fail_no_cp:
f2fs_put_page(cp1, 1);
f2fs_put_page(cp2, 1);
fail_no_cp:
kvfree(sbi->ckpt);
return -EINVAL;
}
static void __add_dirty_inode(struct inode *inode, enum inode_type type)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
if (is_inode_flag_set(inode, flag))
return;
set_inode_flag(inode, flag);
if (!f2fs_is_volatile_file(inode))
list_add_tail(&F2FS_I(inode)->dirty_list,
&sbi->inode_list[type]);
stat_inc_dirty_inode(sbi, type);
}
static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
{
int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag))
return;
list_del_init(&F2FS_I(inode)->dirty_list);
clear_inode_flag(inode, flag);
stat_dec_dirty_inode(F2FS_I_SB(inode), type);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_update_dirty_page(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
return;
spin_lock(&sbi->inode_lock[type]);
if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH))
__add_dirty_inode(inode, type);
inode_inc_dirty_pages(inode);
spin_unlock(&sbi->inode_lock[type]);
f2fs_set_page_private(page, 0);
f2fs_trace_pid(page);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_remove_dirty_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
return;
if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH))
return;
spin_lock(&sbi->inode_lock[type]);
__remove_dirty_inode(inode, type);
spin_unlock(&sbi->inode_lock[type]);
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
{
struct list_head *head;
struct inode *inode;
struct f2fs_inode_info *fi;
bool is_dir = (type == DIR_INODE);
unsigned long ino = 0;
trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
retry:
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
spin_lock(&sbi->inode_lock[type]);
head = &sbi->inode_list[type];
if (list_empty(head)) {
spin_unlock(&sbi->inode_lock[type]);
trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
get_pages(sbi, is_dir ?
F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
return 0;
}
fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
inode = igrab(&fi->vfs_inode);
spin_unlock(&sbi->inode_lock[type]);
if (inode) {
unsigned long cur_ino = inode->i_ino;
f2fs: fix potential recursive call when enabling data_flush As Hagbard Celine reported: Hi, this is a long standing bug that I've hit before on older kernels, but I was not able to get the syslog saved because of the nature of the bug. This time I had booted form a pen-drive, and was able to save the log to it's efi-partition. What i did to trigger it was to create a partition and format it f2fs, then mount it with options: "rw,relatime,lazytime,background_gc=on,disable_ext_identify,discard,heap,user_xattr,inline_xattr,acl,inline_data,inline_dentry,flush_merge,data_flush,extent_cache,mode=adaptive,active_logs=6,whint_mode=fs-based,alloc_mode=default,fsync_mode=strict". Then I unpacked a big .tar.xz to the partition (I used a gentoo-stage3-tarball as I was in process of installing Gentoo). Same options just without data_flush gives no problems. Mar 20 20:54:01 usbgentoo kernel: FAT-fs (nvme0n1p4): Volume was not properly unmounted. Some data may be corrupt. Please run fsck. Mar 20 21:05:23 usbgentoo kernel: kworker/dying (1588) used greatest stack depth: 12064 bytes left Mar 20 21:06:40 usbgentoo kernel: BUG: stack guard page was hit at 00000000a4b0733c (stack is 0000000056016422..0000000096e7463f) Mar 20 21:06:40 usbgentoo kernel: kernel stack overflow ...... Mar 20 21:06:40 usbgentoo kernel: Call Trace: Mar 20 21:06:40 usbgentoo kernel: read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: ? xas_load+0x8/0x50 Mar 20 21:06:40 usbgentoo kernel: __get_node_page+0x73/0x2a0 Mar 20 21:06:40 usbgentoo kernel: f2fs_get_dnode_of_data+0x34e/0x580 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_inline_data+0x5e/0x2a0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x421/0x690 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_cache_pages+0x1cf/0x460 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_data_pages+0x2b3/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_chksum_verify+0x1d/0xc0 Mar 20 21:06:40 usbgentoo kernel: ? read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: do_writepages+0x3c/0xd0 Mar 20 21:06:40 usbgentoo kernel: __filemap_fdatawrite_range+0x7c/0xb0 Mar 20 21:06:40 usbgentoo kernel: f2fs_sync_dirty_inodes+0xf2/0x200 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs_bg+0x2a3/0x2c0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_dirtied+0x21/0xc0 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs+0xd6/0x2b0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x4fb/0x690 ...... Mar 20 21:06:40 usbgentoo kernel: __writeback_single_inode+0x2a1/0x340 Mar 20 21:06:40 usbgentoo kernel: ? soft_cursor+0x1b4/0x220 Mar 20 21:06:40 usbgentoo kernel: writeback_sb_inodes+0x1d5/0x3e0 Mar 20 21:06:40 usbgentoo kernel: __writeback_inodes_wb+0x58/0xa0 Mar 20 21:06:40 usbgentoo kernel: wb_writeback+0x250/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? 0xffffffff8c000000 Mar 20 21:06:40 usbgentoo kernel: ? cpumask_next+0x16/0x20 Mar 20 21:06:40 usbgentoo kernel: wb_workfn+0x2f6/0x3b0 Mar 20 21:06:40 usbgentoo kernel: ? __switch_to_asm+0x40/0x70 Mar 20 21:06:40 usbgentoo kernel: process_one_work+0x1f5/0x3f0 Mar 20 21:06:40 usbgentoo kernel: worker_thread+0x28/0x3c0 Mar 20 21:06:40 usbgentoo kernel: ? rescuer_thread+0x330/0x330 Mar 20 21:06:40 usbgentoo kernel: kthread+0x10e/0x130 Mar 20 21:06:40 usbgentoo kernel: ? kthread_create_on_node+0x60/0x60 Mar 20 21:06:40 usbgentoo kernel: ret_from_fork+0x35/0x40 The root cause is that we run into an infinite recursive calling in between f2fs_balance_fs_bg and writepage() as described below: - f2fs_write_data_pages --- A - __write_data_page - f2fs_balance_fs - f2fs_balance_fs_bg --- B - f2fs_sync_dirty_inodes - filemap_fdatawrite - f2fs_write_data_pages --- A ... - f2fs_balance_fs_bg --- B ... In order to fix this issue, let's detect such condition in __write_data_page() and just skip calling f2fs_balance_fs() recursively. Reported-by: Hagbard Celine <hagbardcelin@gmail.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-02 12:52:19 +02:00
F2FS_I(inode)->cp_task = current;
filemap_fdatawrite(inode->i_mapping);
f2fs: fix potential recursive call when enabling data_flush As Hagbard Celine reported: Hi, this is a long standing bug that I've hit before on older kernels, but I was not able to get the syslog saved because of the nature of the bug. This time I had booted form a pen-drive, and was able to save the log to it's efi-partition. What i did to trigger it was to create a partition and format it f2fs, then mount it with options: "rw,relatime,lazytime,background_gc=on,disable_ext_identify,discard,heap,user_xattr,inline_xattr,acl,inline_data,inline_dentry,flush_merge,data_flush,extent_cache,mode=adaptive,active_logs=6,whint_mode=fs-based,alloc_mode=default,fsync_mode=strict". Then I unpacked a big .tar.xz to the partition (I used a gentoo-stage3-tarball as I was in process of installing Gentoo). Same options just without data_flush gives no problems. Mar 20 20:54:01 usbgentoo kernel: FAT-fs (nvme0n1p4): Volume was not properly unmounted. Some data may be corrupt. Please run fsck. Mar 20 21:05:23 usbgentoo kernel: kworker/dying (1588) used greatest stack depth: 12064 bytes left Mar 20 21:06:40 usbgentoo kernel: BUG: stack guard page was hit at 00000000a4b0733c (stack is 0000000056016422..0000000096e7463f) Mar 20 21:06:40 usbgentoo kernel: kernel stack overflow ...... Mar 20 21:06:40 usbgentoo kernel: Call Trace: Mar 20 21:06:40 usbgentoo kernel: read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: ? xas_load+0x8/0x50 Mar 20 21:06:40 usbgentoo kernel: __get_node_page+0x73/0x2a0 Mar 20 21:06:40 usbgentoo kernel: f2fs_get_dnode_of_data+0x34e/0x580 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_inline_data+0x5e/0x2a0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x421/0x690 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_cache_pages+0x1cf/0x460 Mar 20 21:06:40 usbgentoo kernel: f2fs_write_data_pages+0x2b3/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_chksum_verify+0x1d/0xc0 Mar 20 21:06:40 usbgentoo kernel: ? read_node_page+0x71/0xf0 Mar 20 21:06:40 usbgentoo kernel: do_writepages+0x3c/0xd0 Mar 20 21:06:40 usbgentoo kernel: __filemap_fdatawrite_range+0x7c/0xb0 Mar 20 21:06:40 usbgentoo kernel: f2fs_sync_dirty_inodes+0xf2/0x200 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs_bg+0x2a3/0x2c0 Mar 20 21:06:40 usbgentoo kernel: ? f2fs_inode_dirtied+0x21/0xc0 Mar 20 21:06:40 usbgentoo kernel: f2fs_balance_fs+0xd6/0x2b0 Mar 20 21:06:40 usbgentoo kernel: __write_data_page+0x4fb/0x690 ...... Mar 20 21:06:40 usbgentoo kernel: __writeback_single_inode+0x2a1/0x340 Mar 20 21:06:40 usbgentoo kernel: ? soft_cursor+0x1b4/0x220 Mar 20 21:06:40 usbgentoo kernel: writeback_sb_inodes+0x1d5/0x3e0 Mar 20 21:06:40 usbgentoo kernel: __writeback_inodes_wb+0x58/0xa0 Mar 20 21:06:40 usbgentoo kernel: wb_writeback+0x250/0x2e0 Mar 20 21:06:40 usbgentoo kernel: ? 0xffffffff8c000000 Mar 20 21:06:40 usbgentoo kernel: ? cpumask_next+0x16/0x20 Mar 20 21:06:40 usbgentoo kernel: wb_workfn+0x2f6/0x3b0 Mar 20 21:06:40 usbgentoo kernel: ? __switch_to_asm+0x40/0x70 Mar 20 21:06:40 usbgentoo kernel: process_one_work+0x1f5/0x3f0 Mar 20 21:06:40 usbgentoo kernel: worker_thread+0x28/0x3c0 Mar 20 21:06:40 usbgentoo kernel: ? rescuer_thread+0x330/0x330 Mar 20 21:06:40 usbgentoo kernel: kthread+0x10e/0x130 Mar 20 21:06:40 usbgentoo kernel: ? kthread_create_on_node+0x60/0x60 Mar 20 21:06:40 usbgentoo kernel: ret_from_fork+0x35/0x40 The root cause is that we run into an infinite recursive calling in between f2fs_balance_fs_bg and writepage() as described below: - f2fs_write_data_pages --- A - __write_data_page - f2fs_balance_fs - f2fs_balance_fs_bg --- B - f2fs_sync_dirty_inodes - filemap_fdatawrite - f2fs_write_data_pages --- A ... - f2fs_balance_fs_bg --- B ... In order to fix this issue, let's detect such condition in __write_data_page() and just skip calling f2fs_balance_fs() recursively. Reported-by: Hagbard Celine <hagbardcelin@gmail.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-02 12:52:19 +02:00
F2FS_I(inode)->cp_task = NULL;
iput(inode);
/* We need to give cpu to another writers. */
if (ino == cur_ino)
cond_resched();
else
ino = cur_ino;
} else {
/*
* We should submit bio, since it exists several
* wribacking dentry pages in the freeing inode.
*/
f2fs_submit_merged_write(sbi, DATA);
f2fs: add cond_resched() to sync_dirty_dir_inodes() In a preempt-off enviroment a alot of FS activity (write/delete) I run into a CPU stall: | NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [kworker/u2:2:59] | Modules linked in: | CPU: 0 PID: 59 Comm: kworker/u2:2 Tainted: G W 3.19.0-00010-g10c11c51ffed #153 | Workqueue: writeback bdi_writeback_workfn (flush-179:0) | task: df230000 ti: df23e000 task.ti: df23e000 | PC is at __submit_merged_bio+0x6c/0x110 | LR is at f2fs_submit_merged_bio+0x74/0x80 … | [<c00085c4>] (gic_handle_irq) from [<c0012e84>] (__irq_svc+0x44/0x5c) | Exception stack(0xdf23fb48 to 0xdf23fb90) | fb40: deef3484 ffff0001 ffff0001 00000027 deef3484 00000000 | fb60: deef3440 00000000 de426000 deef34ec deefc440 df23fbb4 df23fbb8 df23fb90 | fb80: c02191f0 c0218fa0 60000013 ffffffff | [<c0012e84>] (__irq_svc) from [<c0218fa0>] (__submit_merged_bio+0x6c/0x110) | [<c0218fa0>] (__submit_merged_bio) from [<c02191f0>] (f2fs_submit_merged_bio+0x74/0x80) | [<c02191f0>] (f2fs_submit_merged_bio) from [<c021624c>] (sync_dirty_dir_inodes+0x70/0x78) | [<c021624c>] (sync_dirty_dir_inodes) from [<c0216358>] (write_checkpoint+0x104/0xc10) | [<c0216358>] (write_checkpoint) from [<c021231c>] (f2fs_sync_fs+0x80/0xbc) | [<c021231c>] (f2fs_sync_fs) from [<c0221eb8>] (f2fs_balance_fs_bg+0x4c/0x68) | [<c0221eb8>] (f2fs_balance_fs_bg) from [<c021e9b8>] (f2fs_write_node_pages+0x40/0x110) | [<c021e9b8>] (f2fs_write_node_pages) from [<c00de620>] (do_writepages+0x34/0x48) | [<c00de620>] (do_writepages) from [<c0145714>] (__writeback_single_inode+0x50/0x228) | [<c0145714>] (__writeback_single_inode) from [<c0146184>] (writeback_sb_inodes+0x1a8/0x378) | [<c0146184>] (writeback_sb_inodes) from [<c01463e4>] (__writeback_inodes_wb+0x90/0xc8) | [<c01463e4>] (__writeback_inodes_wb) from [<c01465f8>] (wb_writeback+0x1dc/0x28c) | [<c01465f8>] (wb_writeback) from [<c0146dd8>] (bdi_writeback_workfn+0x2ac/0x460) | [<c0146dd8>] (bdi_writeback_workfn) from [<c003c3fc>] (process_one_work+0x11c/0x3a4) | [<c003c3fc>] (process_one_work) from [<c003c844>] (worker_thread+0x17c/0x490) | [<c003c844>] (worker_thread) from [<c0041398>] (kthread+0xec/0x100) | [<c0041398>] (kthread) from [<c000ed10>] (ret_from_fork+0x14/0x24) As it turns out, the code loops in sync_dirty_dir_inodes() and waits for others to make progress but since it never leaves the CPU there is no progress made. At the time of this stall, there is also a rm process blocked: | rm R running 0 1989 1774 0x00000000 | [<c047c55c>] (__schedule) from [<c00486dc>] (__cond_resched+0x30/0x4c) | [<c00486dc>] (__cond_resched) from [<c047c8c8>] (_cond_resched+0x4c/0x54) | [<c047c8c8>] (_cond_resched) from [<c00e1aec>] (truncate_inode_pages_range+0x1f0/0x5e8) | [<c00e1aec>] (truncate_inode_pages_range) from [<c00e1fd8>] (truncate_inode_pages+0x28/0x30) | [<c00e1fd8>] (truncate_inode_pages) from [<c00e2148>] (truncate_inode_pages_final+0x60/0x64) | [<c00e2148>] (truncate_inode_pages_final) from [<c020c92c>] (f2fs_evict_inode+0x4c/0x268) | [<c020c92c>] (f2fs_evict_inode) from [<c0137214>] (evict+0x94/0x140) | [<c0137214>] (evict) from [<c01377e8>] (iput+0xc8/0x134) | [<c01377e8>] (iput) from [<c01333e4>] (d_delete+0x154/0x180) | [<c01333e4>] (d_delete) from [<c0129870>] (vfs_rmdir+0x114/0x12c) | [<c0129870>] (vfs_rmdir) from [<c012d644>] (do_rmdir+0x158/0x168) | [<c012d644>] (do_rmdir) from [<c012dd90>] (SyS_unlinkat+0x30/0x3c) | [<c012dd90>] (SyS_unlinkat) from [<c000ec40>] (ret_fast_syscall+0x0/0x4c) As explained by Jaegeuk Kim: |This inode is the directory (c.f., do_rmdir) causing a infinite loop on |sync_dirty_dir_inodes. |The sync_dirty_dir_inodes tries to flush dirty dentry pages, but if the |inode is under eviction, it submits bios and do it again until eviction |is finished. This patch adds a cond_resched() (as suggested by Jaegeuk) after a BIO is submitted so other thread can make progress. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> [Jaegeuk Kim: change fs/f2fs to f2fs in subject as naming convention] Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2015-02-27 13:13:14 +01:00
cond_resched();
}
goto retry;
}
int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
{
struct list_head *head = &sbi->inode_list[DIRTY_META];
struct inode *inode;
struct f2fs_inode_info *fi;
s64 total = get_pages(sbi, F2FS_DIRTY_IMETA);
while (total--) {
if (unlikely(f2fs_cp_error(sbi)))
return -EIO;
spin_lock(&sbi->inode_lock[DIRTY_META]);
if (list_empty(head)) {
spin_unlock(&sbi->inode_lock[DIRTY_META]);
return 0;
}
fi = list_first_entry(head, struct f2fs_inode_info,
gdirty_list);
inode = igrab(&fi->vfs_inode);
spin_unlock(&sbi->inode_lock[DIRTY_META]);
if (inode) {
sync_inode_metadata(inode, 0);
/* it's on eviction */
if (is_inode_flag_set(inode, FI_DIRTY_INODE))
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_update_inode_page(inode);
iput(inode);
}
}
return 0;
}
static void __prepare_cp_block(struct f2fs_sb_info *sbi)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct f2fs_nm_info *nm_i = NM_I(sbi);
nid_t last_nid = nm_i->next_scan_nid;
next_free_nid(sbi, &last_nid);
ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
ckpt->next_free_nid = cpu_to_le32(last_nid);
}
static bool __need_flush_quota(struct f2fs_sb_info *sbi)
{
if (!is_journalled_quota(sbi))
return false;
if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
return false;
if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
return false;
if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH))
return true;
if (get_pages(sbi, F2FS_DIRTY_QDATA))
return true;
return false;
}
/*
* Freeze all the FS-operations for checkpoint.
*/
static int block_operations(struct f2fs_sb_info *sbi)
{
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.for_reclaim = 0,
};
f2fs: give a chance to merge IOs by IO scheduler Previously, background GC submits many 4KB read requests to load victim blocks and/or its (i)node blocks. ... f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb61, blkaddr = 0x3b964ed f2fs_gc : block_rq_complete: 8,16 R () 499854968 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb6f, blkaddr = 0x3b964ee f2fs_gc : block_rq_complete: 8,16 R () 499854976 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb79, blkaddr = 0x3b964ef f2fs_gc : block_rq_complete: 8,16 R () 499854984 + 8 [0] ... However, by the fact that many IOs are sequential, we can give a chance to merge the IOs by IO scheduler. In order to do that, let's use blk_plug. ... f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c6, blkaddr = 0x2e6ee f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c7, blkaddr = 0x2e6ef <idle> : block_rq_complete: 8,16 R () 1519616 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1519848 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1520432 + 96 [0] <idle> : block_rq_complete: 8,16 R () 1520536 + 104 [0] <idle> : block_rq_complete: 8,16 R () 1521008 + 112 [0] <idle> : block_rq_complete: 8,16 R () 1521440 + 152 [0] <idle> : block_rq_complete: 8,16 R () 1521688 + 144 [0] <idle> : block_rq_complete: 8,16 R () 1522128 + 192 [0] <idle> : block_rq_complete: 8,16 R () 1523256 + 328 [0] ... Note that this issue should be addressed in checkpoint, and some readahead flows too. Reviewed-by: Namjae Jeon <namjae.jeon@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-04-24 06:19:56 +02:00
struct blk_plug plug;
int err = 0, cnt = 0;
f2fs: give a chance to merge IOs by IO scheduler Previously, background GC submits many 4KB read requests to load victim blocks and/or its (i)node blocks. ... f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb61, blkaddr = 0x3b964ed f2fs_gc : block_rq_complete: 8,16 R () 499854968 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb6f, blkaddr = 0x3b964ee f2fs_gc : block_rq_complete: 8,16 R () 499854976 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb79, blkaddr = 0x3b964ef f2fs_gc : block_rq_complete: 8,16 R () 499854984 + 8 [0] ... However, by the fact that many IOs are sequential, we can give a chance to merge the IOs by IO scheduler. In order to do that, let's use blk_plug. ... f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c6, blkaddr = 0x2e6ee f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c7, blkaddr = 0x2e6ef <idle> : block_rq_complete: 8,16 R () 1519616 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1519848 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1520432 + 96 [0] <idle> : block_rq_complete: 8,16 R () 1520536 + 104 [0] <idle> : block_rq_complete: 8,16 R () 1521008 + 112 [0] <idle> : block_rq_complete: 8,16 R () 1521440 + 152 [0] <idle> : block_rq_complete: 8,16 R () 1521688 + 144 [0] <idle> : block_rq_complete: 8,16 R () 1522128 + 192 [0] <idle> : block_rq_complete: 8,16 R () 1523256 + 328 [0] ... Note that this issue should be addressed in checkpoint, and some readahead flows too. Reviewed-by: Namjae Jeon <namjae.jeon@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-04-24 06:19:56 +02:00
blk_start_plug(&plug);
retry_flush_quotas:
if (__need_flush_quota(sbi)) {
int locked;
if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) {
set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
f2fs_lock_all(sbi);
goto retry_flush_dents;
}
clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH);
/* only failed during mount/umount/freeze/quotactl */
locked = down_read_trylock(&sbi->sb->s_umount);
f2fs_quota_sync(sbi->sb, -1);
if (locked)
up_read(&sbi->sb->s_umount);
}
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 12:08:30 +02:00
f2fs_lock_all(sbi);
if (__need_flush_quota(sbi)) {
f2fs_unlock_all(sbi);
cond_resched();
goto retry_flush_quotas;
}
retry_flush_dents:
/* write all the dirty dentry pages */
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 12:08:30 +02:00
f2fs_unlock_all(sbi);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
err = f2fs_sync_dirty_inodes(sbi, DIR_INODE);
if (err)
goto out;
cond_resched();
goto retry_flush_quotas;
}
/*
* POR: we should ensure that there are no dirty node pages
* until finishing nat/sit flush. inode->i_blocks can be updated.
*/
down_write(&sbi->node_change);
if (__need_flush_quota(sbi)) {
up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
goto retry_flush_quotas;
}
if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
err = f2fs_sync_inode_meta(sbi);
if (err)
goto out;
cond_resched();
goto retry_flush_quotas;
}
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 08:21:29 +01:00
retry_flush_nodes:
down_write(&sbi->node_write);
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
atomic_inc(&sbi->wb_sync_req[NODE]);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
atomic_dec(&sbi->wb_sync_req[NODE]);
if (err) {
up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
goto out;
}
cond_resched();
f2fs: introduce a new global lock scheme In the previous version, f2fs uses global locks according to the usage types, such as directory operations, block allocation, block write, and so on. Reference the following lock types in f2fs.h. enum lock_type { RENAME, /* for renaming operations */ DENTRY_OPS, /* for directory operations */ DATA_WRITE, /* for data write */ DATA_NEW, /* for data allocation */ DATA_TRUNC, /* for data truncate */ NODE_NEW, /* for node allocation */ NODE_TRUNC, /* for node truncate */ NODE_WRITE, /* for node write */ NR_LOCK_TYPE, }; In that case, we lose the performance under the multi-threading environment, since every types of operations must be conducted one at a time. In order to address the problem, let's share the locks globally with a mutex array regardless of any types. So, let users grab a mutex and perform their jobs in parallel as much as possbile. For this, I propose a new global lock scheme as follows. 0. Data structure - f2fs_sb_info -> mutex_lock[NR_GLOBAL_LOCKS] - f2fs_sb_info -> node_write 1. mutex_lock_op(sbi) - try to get an avaiable lock from the array. - returns the index of the gottern lock variable. 2. mutex_unlock_op(sbi, index of the lock) - unlock the given index of the lock. 3. mutex_lock_all(sbi) - grab all the locks in the array before the checkpoint. 4. mutex_unlock_all(sbi) - release all the locks in the array after checkpoint. 5. block_operations() - call mutex_lock_all() - sync_dirty_dir_inodes() - grab node_write - sync_node_pages() Note that, the pairs of mutex_lock_op()/mutex_unlock_op() and mutex_lock_all()/mutex_unlock_all() should be used together. Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2012-11-22 08:21:29 +01:00
goto retry_flush_nodes;
}
/*
* sbi->node_change is used only for AIO write_begin path which produces
* dirty node blocks and some checkpoint values by block allocation.
*/
__prepare_cp_block(sbi);
up_write(&sbi->node_change);
out:
f2fs: give a chance to merge IOs by IO scheduler Previously, background GC submits many 4KB read requests to load victim blocks and/or its (i)node blocks. ... f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb61, blkaddr = 0x3b964ed f2fs_gc : block_rq_complete: 8,16 R () 499854968 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb6f, blkaddr = 0x3b964ee f2fs_gc : block_rq_complete: 8,16 R () 499854976 + 8 [0] f2fs_gc : f2fs_readpage: ino = 1, page_index = 0xb79, blkaddr = 0x3b964ef f2fs_gc : block_rq_complete: 8,16 R () 499854984 + 8 [0] ... However, by the fact that many IOs are sequential, we can give a chance to merge the IOs by IO scheduler. In order to do that, let's use blk_plug. ... f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c6, blkaddr = 0x2e6ee f2fs_gc : f2fs_iget: ino = 143 f2fs_gc : f2fs_readpage: ino = 143, page_index = 0x1c7, blkaddr = 0x2e6ef <idle> : block_rq_complete: 8,16 R () 1519616 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1519848 + 8 [0] <idle> : block_rq_complete: 8,16 R () 1520432 + 96 [0] <idle> : block_rq_complete: 8,16 R () 1520536 + 104 [0] <idle> : block_rq_complete: 8,16 R () 1521008 + 112 [0] <idle> : block_rq_complete: 8,16 R () 1521440 + 152 [0] <idle> : block_rq_complete: 8,16 R () 1521688 + 144 [0] <idle> : block_rq_complete: 8,16 R () 1522128 + 192 [0] <idle> : block_rq_complete: 8,16 R () 1523256 + 328 [0] ... Note that this issue should be addressed in checkpoint, and some readahead flows too. Reviewed-by: Namjae Jeon <namjae.jeon@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-04-24 06:19:56 +02:00
blk_finish_plug(&plug);
return err;
}
static void unblock_operations(struct f2fs_sb_info *sbi)
{
up_write(&sbi->node_write);
f2fs: use rw_sem instead of fs_lock(locks mutex) The fs_locks is used to block other ops(ex, recovery) when doing checkpoint. And each other operate routine(besides checkpoint) needs to acquire a fs_lock, there is a terrible problem here, if these are too many concurrency threads acquiring fs_lock, so that they will block each other and may lead to some performance problem, but this is not the phenomenon we want to see. Though there are some optimization patches introduced to enhance the usage of fs_lock, but the thorough solution is using a *rw_sem* to replace the fs_lock. Checkpoint routine takes write_sem, and other ops take read_sem, so that we can block other ops(ex, recovery) when doing checkpoint, and other ops will not disturb each other, this can avoid the problem described above completely. Because of the weakness of rw_sem, the above change may introduce a potential problem that the checkpoint thread might get starved if other threads are intensively locking the read semaphore for I/O.(Pointed out by Xu Jin) In order to avoid this, a wait_list is introduced, the appending read semaphore ops will be dropped into the wait_list if checkpoint thread is waiting for write semaphore, and will be waked up when checkpoint thread gives up write semaphore. Thanks to Kim's previous review and test, and will be very glad to see other guys' performance tests about this patch. V2: -fix the potential starvation problem. -use more suitable func name suggested by Xu Jin. Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com> [Jaegeuk Kim: adjust minor coding standard] Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
2013-09-27 12:08:30 +02:00
f2fs_unlock_all(sbi);
}
f2fs: fix to avoid broken of dnode block list f2fs recovery flow is relying on dnode block link list, it means fsynced file recovery depends on previous dnode's persistence in the list, so during fsync() we should wait on all regular inode's dnode writebacked before issuing flush. By this way, we can avoid dnode block list being broken by out-of-order IO submission due to IO scheduler or driver. Sheng Yong helps to do the test with this patch: Target:/data (f2fs, -) 64MB / 32768KB / 4KB / 8 1 / PERSIST / Index Base: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 867.82 204.15 41440.03 41370.54 680.8 1025.94 1031.08 2 871.87 205.87 41370.3 40275.2 791.14 1065.84 1101.7 3 866.52 205.69 41795.67 40596.16 694.69 1037.16 1031.48 Avg 868.7366667 205.2366667 41535.33333 40747.3 722.21 1042.98 1054.753333 After: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 798.81 202.5 41143 40613.87 602.71 838.08 913.83 2 805.79 206.47 40297.2 41291.46 604.44 840.75 924.27 3 814.83 206.17 41209.57 40453.62 602.85 834.66 927.91 Avg 806.4766667 205.0466667 40883.25667 40786.31667 603.3333333 837.83 922.0033333 Patched/Original: 0.928332713 0.999074239 0.984300676 1.000957528 0.835398753 0.803303994 0.874141189 It looks like atomic write will suffer performance regression. I suspect that the criminal is that we forcing to wait all dnode being in storage cache before we issue PREFLUSH+FUA. BTW, will commit ("f2fs: don't need to wait for node writes for atomic write") cause the problem: we will lose data of last transaction after SPO, even if atomic write return no error: - atomic_open(); - write() P1, P2, P3; - atomic_commit(); - writeback data: P1, P2, P3; - writeback node: N1, N2, N3; <--- If N1, N2 is not writebacked, N3 with fsync_mark is writebacked, In SPOR, we won't find N3 since node chain is broken, turns out that losing last transaction. - preflush + fua; - power-cut If we don't wait dnode writeback for atomic_write: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 779.91 206.03 41621.5 40333.16 716.9 1038.21 1034.85 2 848.51 204.35 40082.44 39486.17 791.83 1119.96 1083.77 3 772.12 206.27 41335.25 41599.65 723.29 1055.07 971.92 Avg 800.18 205.55 41013.06333 40472.99333 744.0066667 1071.08 1030.18 Patched/Original: 0.92108464 1.001526693 0.987425886 0.993268102 1.030180511 1.026942031 0.976702294 SQLite's performance recovers. Jaegeuk: "Practically, I don't see db corruption becase of this. We can excuse to lose the last transaction." Finally, we decide to keep original implementation of atomic write interface sematics that we don't wait all dnode writeback before preflush+fua submission. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 17:03:19 +02:00
void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
{
DEFINE_WAIT(wait);
for (;;) {
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
if (!get_pages(sbi, F2FS_WB_CP_DATA))
break;
if (unlikely(f2fs_cp_error(sbi)))
break;
io_schedule_timeout(5*HZ);
}
finish_wait(&sbi->cp_wait, &wait);
}
static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
f2fs: use spin_{,un}lock_irq{save,restore} generic/361 reports below warning, this is because: once, there is someone entering into critical region of sbi.cp_lock, if write_end_io. f2fs_stop_checkpoint is invoked from an triggered IRQ, we will encounter deadlock. So this patch changes to use spin_{,un}lock_irq{save,restore} to create critical region without IRQ enabled to avoid potential deadlock. irq event stamp: 83391573 loop: Write error at byte offset 438729728, length 1024. hardirqs last enabled at (83391573): [<c1809752>] restore_all+0xf/0x65 hardirqs last disabled at (83391572): [<c1809eac>] reschedule_interrupt+0x30/0x3c loop: Write error at byte offset 438860288, length 1536. softirqs last enabled at (83389244): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (83389237): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 loop: Write error at byte offset 438990848, length 2048. ================================ WARNING: inconsistent lock state 4.12.0-rc2+ #30 Tainted: G O -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. xfs_io/7959 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&sbi->cp_lock)->rlock){?.+...}, at: [<f96f96cc>] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] {HARDIRQ-ON-W} state was registered at: __lock_acquire+0x527/0x7b0 lock_acquire+0xae/0x220 _raw_spin_lock+0x42/0x50 do_checkpoint+0x165/0x9e0 [f2fs] write_checkpoint+0x33f/0x740 [f2fs] __f2fs_sync_fs+0x92/0x1f0 [f2fs] f2fs_sync_fs+0x12/0x20 [f2fs] sync_filesystem+0x67/0x80 generic_shutdown_super+0x27/0x100 kill_block_super+0x22/0x50 kill_f2fs_super+0x3a/0x40 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x69/0x80 exit_to_usermode_loop+0x57/0x85 do_fast_syscall_32+0x18c/0x1b0 entry_SYSENTER_32+0x4c/0x7b irq event stamp: 1957420 hardirqs last enabled at (1957419): [<c1808f37>] _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (1957420): [<c1809f9c>] call_function_single_interrupt+0x30/0x3c softirqs last enabled at (1953784): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (1953773): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&sbi->cp_lock)->rlock); <Interrupt> lock(&(&sbi->cp_lock)->rlock); *** DEADLOCK *** 2 locks held by xfs_io/7959: #0: (sb_writers#13){.+.+.+}, at: [<c11fd7ca>] vfs_write+0x16a/0x190 #1: (&sb->s_type->i_mutex_key#16){+.+.+.}, at: [<f96e33f5>] f2fs_file_write_iter+0x25/0x140 [f2fs] stack backtrace: CPU: 2 PID: 7959 Comm: xfs_io Tainted: G O 4.12.0-rc2+ #30 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: dump_stack+0x5f/0x92 print_usage_bug+0x1d3/0x1dd ? check_usage_backwards+0xe0/0xe0 mark_lock+0x23d/0x280 __lock_acquire+0x699/0x7b0 ? __this_cpu_preempt_check+0xf/0x20 ? trace_hardirqs_off_caller+0x91/0xe0 lock_acquire+0xae/0x220 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] _raw_spin_lock+0x42/0x50 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_write_end_io+0x147/0x150 [f2fs] bio_endio+0x7a/0x1e0 blk_update_request+0xad/0x410 blk_mq_end_request+0x16/0x60 lo_complete_rq+0x3c/0x70 __blk_mq_complete_request_remote+0x11/0x20 flush_smp_call_function_queue+0x6d/0x120 ? debug_smp_processor_id+0x12/0x20 generic_smp_call_function_single_interrupt+0x12/0x30 smp_call_function_single_interrupt+0x25/0x40 call_function_single_interrupt+0x37/0x3c EIP: _raw_spin_unlock_irq+0x2d/0x50 EFLAGS: 00000296 CPU: 2 EAX: 00000001 EBX: d2ccc51c ECX: 00000001 EDX: c1aacebd ESI: 00000000 EDI: 00000000 EBP: c96c9d1c ESP: c96c9d18 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 ? inherit_task_group.isra.98.part.99+0x6b/0xb0 __add_to_page_cache_locked+0x1d4/0x290 add_to_page_cache_lru+0x38/0xb0 pagecache_get_page+0x8e/0x200 f2fs_write_begin+0x96/0xf00 [f2fs] ? trace_hardirqs_on_caller+0xdd/0x1c0 ? current_time+0x17/0x50 ? trace_hardirqs_on+0xb/0x10 generic_perform_write+0xa9/0x170 __generic_file_write_iter+0x1a2/0x1f0 ? f2fs_preallocate_blocks+0x137/0x160 [f2fs] f2fs_file_write_iter+0x6e/0x140 [f2fs] ? __lock_acquire+0x429/0x7b0 __vfs_write+0xc1/0x140 vfs_write+0x9b/0x190 SyS_pwrite64+0x63/0xa0 do_fast_syscall_32+0xa1/0x1b0 entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7786c61 EFLAGS: 00000293 CPU: 2 EAX: ffffffda EBX: 00000003 ECX: 08416000 EDX: 00001000 ESI: 18b24000 EDI: 00000000 EBP: 00000003 ESP: bf9b36b0 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Fixes: aaec2b1d1879 ("f2fs: introduce cp_lock to protect updating of ckpt_flags") Cc: stable@vger.kernel.org Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-07 08:10:15 +02:00
unsigned long flags;
f2fs: use spin_{,un}lock_irq{save,restore} generic/361 reports below warning, this is because: once, there is someone entering into critical region of sbi.cp_lock, if write_end_io. f2fs_stop_checkpoint is invoked from an triggered IRQ, we will encounter deadlock. So this patch changes to use spin_{,un}lock_irq{save,restore} to create critical region without IRQ enabled to avoid potential deadlock. irq event stamp: 83391573 loop: Write error at byte offset 438729728, length 1024. hardirqs last enabled at (83391573): [<c1809752>] restore_all+0xf/0x65 hardirqs last disabled at (83391572): [<c1809eac>] reschedule_interrupt+0x30/0x3c loop: Write error at byte offset 438860288, length 1536. softirqs last enabled at (83389244): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (83389237): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 loop: Write error at byte offset 438990848, length 2048. ================================ WARNING: inconsistent lock state 4.12.0-rc2+ #30 Tainted: G O -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. xfs_io/7959 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&sbi->cp_lock)->rlock){?.+...}, at: [<f96f96cc>] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] {HARDIRQ-ON-W} state was registered at: __lock_acquire+0x527/0x7b0 lock_acquire+0xae/0x220 _raw_spin_lock+0x42/0x50 do_checkpoint+0x165/0x9e0 [f2fs] write_checkpoint+0x33f/0x740 [f2fs] __f2fs_sync_fs+0x92/0x1f0 [f2fs] f2fs_sync_fs+0x12/0x20 [f2fs] sync_filesystem+0x67/0x80 generic_shutdown_super+0x27/0x100 kill_block_super+0x22/0x50 kill_f2fs_super+0x3a/0x40 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x69/0x80 exit_to_usermode_loop+0x57/0x85 do_fast_syscall_32+0x18c/0x1b0 entry_SYSENTER_32+0x4c/0x7b irq event stamp: 1957420 hardirqs last enabled at (1957419): [<c1808f37>] _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (1957420): [<c1809f9c>] call_function_single_interrupt+0x30/0x3c softirqs last enabled at (1953784): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (1953773): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&sbi->cp_lock)->rlock); <Interrupt> lock(&(&sbi->cp_lock)->rlock); *** DEADLOCK *** 2 locks held by xfs_io/7959: #0: (sb_writers#13){.+.+.+}, at: [<c11fd7ca>] vfs_write+0x16a/0x190 #1: (&sb->s_type->i_mutex_key#16){+.+.+.}, at: [<f96e33f5>] f2fs_file_write_iter+0x25/0x140 [f2fs] stack backtrace: CPU: 2 PID: 7959 Comm: xfs_io Tainted: G O 4.12.0-rc2+ #30 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: dump_stack+0x5f/0x92 print_usage_bug+0x1d3/0x1dd ? check_usage_backwards+0xe0/0xe0 mark_lock+0x23d/0x280 __lock_acquire+0x699/0x7b0 ? __this_cpu_preempt_check+0xf/0x20 ? trace_hardirqs_off_caller+0x91/0xe0 lock_acquire+0xae/0x220 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] _raw_spin_lock+0x42/0x50 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_write_end_io+0x147/0x150 [f2fs] bio_endio+0x7a/0x1e0 blk_update_request+0xad/0x410 blk_mq_end_request+0x16/0x60 lo_complete_rq+0x3c/0x70 __blk_mq_complete_request_remote+0x11/0x20 flush_smp_call_function_queue+0x6d/0x120 ? debug_smp_processor_id+0x12/0x20 generic_smp_call_function_single_interrupt+0x12/0x30 smp_call_function_single_interrupt+0x25/0x40 call_function_single_interrupt+0x37/0x3c EIP: _raw_spin_unlock_irq+0x2d/0x50 EFLAGS: 00000296 CPU: 2 EAX: 00000001 EBX: d2ccc51c ECX: 00000001 EDX: c1aacebd ESI: 00000000 EDI: 00000000 EBP: c96c9d1c ESP: c96c9d18 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 ? inherit_task_group.isra.98.part.99+0x6b/0xb0 __add_to_page_cache_locked+0x1d4/0x290 add_to_page_cache_lru+0x38/0xb0 pagecache_get_page+0x8e/0x200 f2fs_write_begin+0x96/0xf00 [f2fs] ? trace_hardirqs_on_caller+0xdd/0x1c0 ? current_time+0x17/0x50 ? trace_hardirqs_on+0xb/0x10 generic_perform_write+0xa9/0x170 __generic_file_write_iter+0x1a2/0x1f0 ? f2fs_preallocate_blocks+0x137/0x160 [f2fs] f2fs_file_write_iter+0x6e/0x140 [f2fs] ? __lock_acquire+0x429/0x7b0 __vfs_write+0xc1/0x140 vfs_write+0x9b/0x190 SyS_pwrite64+0x63/0xa0 do_fast_syscall_32+0xa1/0x1b0 entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7786c61 EFLAGS: 00000293 CPU: 2 EAX: ffffffda EBX: 00000003 ECX: 08416000 EDX: 00001000 ESI: 18b24000 EDI: 00000000 EBP: 00000003 ESP: bf9b36b0 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Fixes: aaec2b1d1879 ("f2fs: introduce cp_lock to protect updating of ckpt_flags") Cc: stable@vger.kernel.org Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-07 08:10:15 +02:00
spin_lock_irqsave(&sbi->cp_lock, flags);
if ((cpc->reason & CP_UMOUNT) &&
le32_to_cpu(ckpt->cp_pack_total_block_count) >
sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
disable_nat_bits(sbi, false);
if (cpc->reason & CP_TRIMMED)
__set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
else
__clear_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
if (cpc->reason & CP_UMOUNT)
__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
if (cpc->reason & CP_FASTBOOT)
__set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
if (orphan_num)
__set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
else
__clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED))
__set_ckpt_flags(ckpt, CP_DISABLED_FLAG);
else
__clear_ckpt_flags(ckpt, CP_DISABLED_FLAG);
if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK))
__set_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
else
__clear_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG);
if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH))
__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
/*
* TODO: we count on fsck.f2fs to clear this flag until we figure out
* missing cases which clear it incorrectly.
*/
if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR))
__set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG);
/* set this flag to activate crc|cp_ver for recovery */
__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
__clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG);
f2fs: use spin_{,un}lock_irq{save,restore} generic/361 reports below warning, this is because: once, there is someone entering into critical region of sbi.cp_lock, if write_end_io. f2fs_stop_checkpoint is invoked from an triggered IRQ, we will encounter deadlock. So this patch changes to use spin_{,un}lock_irq{save,restore} to create critical region without IRQ enabled to avoid potential deadlock. irq event stamp: 83391573 loop: Write error at byte offset 438729728, length 1024. hardirqs last enabled at (83391573): [<c1809752>] restore_all+0xf/0x65 hardirqs last disabled at (83391572): [<c1809eac>] reschedule_interrupt+0x30/0x3c loop: Write error at byte offset 438860288, length 1536. softirqs last enabled at (83389244): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (83389237): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 loop: Write error at byte offset 438990848, length 2048. ================================ WARNING: inconsistent lock state 4.12.0-rc2+ #30 Tainted: G O -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. xfs_io/7959 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&sbi->cp_lock)->rlock){?.+...}, at: [<f96f96cc>] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] {HARDIRQ-ON-W} state was registered at: __lock_acquire+0x527/0x7b0 lock_acquire+0xae/0x220 _raw_spin_lock+0x42/0x50 do_checkpoint+0x165/0x9e0 [f2fs] write_checkpoint+0x33f/0x740 [f2fs] __f2fs_sync_fs+0x92/0x1f0 [f2fs] f2fs_sync_fs+0x12/0x20 [f2fs] sync_filesystem+0x67/0x80 generic_shutdown_super+0x27/0x100 kill_block_super+0x22/0x50 kill_f2fs_super+0x3a/0x40 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x69/0x80 exit_to_usermode_loop+0x57/0x85 do_fast_syscall_32+0x18c/0x1b0 entry_SYSENTER_32+0x4c/0x7b irq event stamp: 1957420 hardirqs last enabled at (1957419): [<c1808f37>] _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (1957420): [<c1809f9c>] call_function_single_interrupt+0x30/0x3c softirqs last enabled at (1953784): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (1953773): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&sbi->cp_lock)->rlock); <Interrupt> lock(&(&sbi->cp_lock)->rlock); *** DEADLOCK *** 2 locks held by xfs_io/7959: #0: (sb_writers#13){.+.+.+}, at: [<c11fd7ca>] vfs_write+0x16a/0x190 #1: (&sb->s_type->i_mutex_key#16){+.+.+.}, at: [<f96e33f5>] f2fs_file_write_iter+0x25/0x140 [f2fs] stack backtrace: CPU: 2 PID: 7959 Comm: xfs_io Tainted: G O 4.12.0-rc2+ #30 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: dump_stack+0x5f/0x92 print_usage_bug+0x1d3/0x1dd ? check_usage_backwards+0xe0/0xe0 mark_lock+0x23d/0x280 __lock_acquire+0x699/0x7b0 ? __this_cpu_preempt_check+0xf/0x20 ? trace_hardirqs_off_caller+0x91/0xe0 lock_acquire+0xae/0x220 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] _raw_spin_lock+0x42/0x50 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_write_end_io+0x147/0x150 [f2fs] bio_endio+0x7a/0x1e0 blk_update_request+0xad/0x410 blk_mq_end_request+0x16/0x60 lo_complete_rq+0x3c/0x70 __blk_mq_complete_request_remote+0x11/0x20 flush_smp_call_function_queue+0x6d/0x120 ? debug_smp_processor_id+0x12/0x20 generic_smp_call_function_single_interrupt+0x12/0x30 smp_call_function_single_interrupt+0x25/0x40 call_function_single_interrupt+0x37/0x3c EIP: _raw_spin_unlock_irq+0x2d/0x50 EFLAGS: 00000296 CPU: 2 EAX: 00000001 EBX: d2ccc51c ECX: 00000001 EDX: c1aacebd ESI: 00000000 EDI: 00000000 EBP: c96c9d1c ESP: c96c9d18 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 ? inherit_task_group.isra.98.part.99+0x6b/0xb0 __add_to_page_cache_locked+0x1d4/0x290 add_to_page_cache_lru+0x38/0xb0 pagecache_get_page+0x8e/0x200 f2fs_write_begin+0x96/0xf00 [f2fs] ? trace_hardirqs_on_caller+0xdd/0x1c0 ? current_time+0x17/0x50 ? trace_hardirqs_on+0xb/0x10 generic_perform_write+0xa9/0x170 __generic_file_write_iter+0x1a2/0x1f0 ? f2fs_preallocate_blocks+0x137/0x160 [f2fs] f2fs_file_write_iter+0x6e/0x140 [f2fs] ? __lock_acquire+0x429/0x7b0 __vfs_write+0xc1/0x140 vfs_write+0x9b/0x190 SyS_pwrite64+0x63/0xa0 do_fast_syscall_32+0xa1/0x1b0 entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7786c61 EFLAGS: 00000293 CPU: 2 EAX: ffffffda EBX: 00000003 ECX: 08416000 EDX: 00001000 ESI: 18b24000 EDI: 00000000 EBP: 00000003 ESP: bf9b36b0 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Fixes: aaec2b1d1879 ("f2fs: introduce cp_lock to protect updating of ckpt_flags") Cc: stable@vger.kernel.org Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-07 08:10:15 +02:00
spin_unlock_irqrestore(&sbi->cp_lock, flags);
}
static void commit_checkpoint(struct f2fs_sb_info *sbi,
void *src, block_t blk_addr)
{
struct writeback_control wbc = {
.for_reclaim = 0,
};
/*
* pagevec_lookup_tag and lock_page again will take
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
* some extra time. Therefore, f2fs_update_meta_pages and
* f2fs_sync_meta_pages are combined in this function.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
struct page *page = f2fs_grab_meta_page(sbi, blk_addr);
int err;
f2fs_wait_on_page_writeback(page, META, true, true);
memcpy(page_address(page), src, PAGE_SIZE);
set_page_dirty(page);
if (unlikely(!clear_page_dirty_for_io(page)))
f2fs_bug_on(sbi, 1);
/* writeout cp pack 2 page */
err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO);
if (unlikely(err && f2fs_cp_error(sbi))) {
f2fs_put_page(page, 1);
return;
}
f2fs_bug_on(sbi, err);
f2fs_put_page(page, 0);
/* submit checkpoint (with barrier if NOBARRIER is not set) */
f2fs_submit_merged_write(sbi, META_FLUSH);
}
static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct f2fs_nm_info *nm_i = NM_I(sbi);
f2fs: use spin_{,un}lock_irq{save,restore} generic/361 reports below warning, this is because: once, there is someone entering into critical region of sbi.cp_lock, if write_end_io. f2fs_stop_checkpoint is invoked from an triggered IRQ, we will encounter deadlock. So this patch changes to use spin_{,un}lock_irq{save,restore} to create critical region without IRQ enabled to avoid potential deadlock. irq event stamp: 83391573 loop: Write error at byte offset 438729728, length 1024. hardirqs last enabled at (83391573): [<c1809752>] restore_all+0xf/0x65 hardirqs last disabled at (83391572): [<c1809eac>] reschedule_interrupt+0x30/0x3c loop: Write error at byte offset 438860288, length 1536. softirqs last enabled at (83389244): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (83389237): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 loop: Write error at byte offset 438990848, length 2048. ================================ WARNING: inconsistent lock state 4.12.0-rc2+ #30 Tainted: G O -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. xfs_io/7959 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&sbi->cp_lock)->rlock){?.+...}, at: [<f96f96cc>] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] {HARDIRQ-ON-W} state was registered at: __lock_acquire+0x527/0x7b0 lock_acquire+0xae/0x220 _raw_spin_lock+0x42/0x50 do_checkpoint+0x165/0x9e0 [f2fs] write_checkpoint+0x33f/0x740 [f2fs] __f2fs_sync_fs+0x92/0x1f0 [f2fs] f2fs_sync_fs+0x12/0x20 [f2fs] sync_filesystem+0x67/0x80 generic_shutdown_super+0x27/0x100 kill_block_super+0x22/0x50 kill_f2fs_super+0x3a/0x40 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x69/0x80 exit_to_usermode_loop+0x57/0x85 do_fast_syscall_32+0x18c/0x1b0 entry_SYSENTER_32+0x4c/0x7b irq event stamp: 1957420 hardirqs last enabled at (1957419): [<c1808f37>] _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (1957420): [<c1809f9c>] call_function_single_interrupt+0x30/0x3c softirqs last enabled at (1953784): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (1953773): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&sbi->cp_lock)->rlock); <Interrupt> lock(&(&sbi->cp_lock)->rlock); *** DEADLOCK *** 2 locks held by xfs_io/7959: #0: (sb_writers#13){.+.+.+}, at: [<c11fd7ca>] vfs_write+0x16a/0x190 #1: (&sb->s_type->i_mutex_key#16){+.+.+.}, at: [<f96e33f5>] f2fs_file_write_iter+0x25/0x140 [f2fs] stack backtrace: CPU: 2 PID: 7959 Comm: xfs_io Tainted: G O 4.12.0-rc2+ #30 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: dump_stack+0x5f/0x92 print_usage_bug+0x1d3/0x1dd ? check_usage_backwards+0xe0/0xe0 mark_lock+0x23d/0x280 __lock_acquire+0x699/0x7b0 ? __this_cpu_preempt_check+0xf/0x20 ? trace_hardirqs_off_caller+0x91/0xe0 lock_acquire+0xae/0x220 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] _raw_spin_lock+0x42/0x50 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_write_end_io+0x147/0x150 [f2fs] bio_endio+0x7a/0x1e0 blk_update_request+0xad/0x410 blk_mq_end_request+0x16/0x60 lo_complete_rq+0x3c/0x70 __blk_mq_complete_request_remote+0x11/0x20 flush_smp_call_function_queue+0x6d/0x120 ? debug_smp_processor_id+0x12/0x20 generic_smp_call_function_single_interrupt+0x12/0x30 smp_call_function_single_interrupt+0x25/0x40 call_function_single_interrupt+0x37/0x3c EIP: _raw_spin_unlock_irq+0x2d/0x50 EFLAGS: 00000296 CPU: 2 EAX: 00000001 EBX: d2ccc51c ECX: 00000001 EDX: c1aacebd ESI: 00000000 EDI: 00000000 EBP: c96c9d1c ESP: c96c9d18 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 ? inherit_task_group.isra.98.part.99+0x6b/0xb0 __add_to_page_cache_locked+0x1d4/0x290 add_to_page_cache_lru+0x38/0xb0 pagecache_get_page+0x8e/0x200 f2fs_write_begin+0x96/0xf00 [f2fs] ? trace_hardirqs_on_caller+0xdd/0x1c0 ? current_time+0x17/0x50 ? trace_hardirqs_on+0xb/0x10 generic_perform_write+0xa9/0x170 __generic_file_write_iter+0x1a2/0x1f0 ? f2fs_preallocate_blocks+0x137/0x160 [f2fs] f2fs_file_write_iter+0x6e/0x140 [f2fs] ? __lock_acquire+0x429/0x7b0 __vfs_write+0xc1/0x140 vfs_write+0x9b/0x190 SyS_pwrite64+0x63/0xa0 do_fast_syscall_32+0xa1/0x1b0 entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7786c61 EFLAGS: 00000293 CPU: 2 EAX: ffffffda EBX: 00000003 ECX: 08416000 EDX: 00001000 ESI: 18b24000 EDI: 00000000 EBP: 00000003 ESP: bf9b36b0 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Fixes: aaec2b1d1879 ("f2fs: introduce cp_lock to protect updating of ckpt_flags") Cc: stable@vger.kernel.org Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-07 08:10:15 +02:00
unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num, flags;
block_t start_blk;
unsigned int data_sum_blocks, orphan_blocks;
__u32 crc32 = 0;
int i;
int cp_payload_blks = __cp_payload(sbi);
struct super_block *sb = sbi->sb;
struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
u64 kbytes_written;
int err;
/* Flush all the NAT/SIT pages */
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
!f2fs_cp_error(sbi));
/*
* modify checkpoint
* version number is already updated
*/
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true));
ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
ckpt->cur_node_segno[i] =
cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE));
ckpt->cur_node_blkoff[i] =
cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE));
ckpt->alloc_type[i + CURSEG_HOT_NODE] =
curseg_alloc_type(sbi, i + CURSEG_HOT_NODE);
}
for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
ckpt->cur_data_segno[i] =
cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA));
ckpt->cur_data_blkoff[i] =
cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA));
ckpt->alloc_type[i + CURSEG_HOT_DATA] =
curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
}
/* 2 cp + n data seg summary + orphan inode blocks */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false);
f2fs: use spin_{,un}lock_irq{save,restore} generic/361 reports below warning, this is because: once, there is someone entering into critical region of sbi.cp_lock, if write_end_io. f2fs_stop_checkpoint is invoked from an triggered IRQ, we will encounter deadlock. So this patch changes to use spin_{,un}lock_irq{save,restore} to create critical region without IRQ enabled to avoid potential deadlock. irq event stamp: 83391573 loop: Write error at byte offset 438729728, length 1024. hardirqs last enabled at (83391573): [<c1809752>] restore_all+0xf/0x65 hardirqs last disabled at (83391572): [<c1809eac>] reschedule_interrupt+0x30/0x3c loop: Write error at byte offset 438860288, length 1536. softirqs last enabled at (83389244): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (83389237): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 loop: Write error at byte offset 438990848, length 2048. ================================ WARNING: inconsistent lock state 4.12.0-rc2+ #30 Tainted: G O -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. xfs_io/7959 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&sbi->cp_lock)->rlock){?.+...}, at: [<f96f96cc>] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] {HARDIRQ-ON-W} state was registered at: __lock_acquire+0x527/0x7b0 lock_acquire+0xae/0x220 _raw_spin_lock+0x42/0x50 do_checkpoint+0x165/0x9e0 [f2fs] write_checkpoint+0x33f/0x740 [f2fs] __f2fs_sync_fs+0x92/0x1f0 [f2fs] f2fs_sync_fs+0x12/0x20 [f2fs] sync_filesystem+0x67/0x80 generic_shutdown_super+0x27/0x100 kill_block_super+0x22/0x50 kill_f2fs_super+0x3a/0x40 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x69/0x80 exit_to_usermode_loop+0x57/0x85 do_fast_syscall_32+0x18c/0x1b0 entry_SYSENTER_32+0x4c/0x7b irq event stamp: 1957420 hardirqs last enabled at (1957419): [<c1808f37>] _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (1957420): [<c1809f9c>] call_function_single_interrupt+0x30/0x3c softirqs last enabled at (1953784): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (1953773): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&sbi->cp_lock)->rlock); <Interrupt> lock(&(&sbi->cp_lock)->rlock); *** DEADLOCK *** 2 locks held by xfs_io/7959: #0: (sb_writers#13){.+.+.+}, at: [<c11fd7ca>] vfs_write+0x16a/0x190 #1: (&sb->s_type->i_mutex_key#16){+.+.+.}, at: [<f96e33f5>] f2fs_file_write_iter+0x25/0x140 [f2fs] stack backtrace: CPU: 2 PID: 7959 Comm: xfs_io Tainted: G O 4.12.0-rc2+ #30 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: dump_stack+0x5f/0x92 print_usage_bug+0x1d3/0x1dd ? check_usage_backwards+0xe0/0xe0 mark_lock+0x23d/0x280 __lock_acquire+0x699/0x7b0 ? __this_cpu_preempt_check+0xf/0x20 ? trace_hardirqs_off_caller+0x91/0xe0 lock_acquire+0xae/0x220 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] _raw_spin_lock+0x42/0x50 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_write_end_io+0x147/0x150 [f2fs] bio_endio+0x7a/0x1e0 blk_update_request+0xad/0x410 blk_mq_end_request+0x16/0x60 lo_complete_rq+0x3c/0x70 __blk_mq_complete_request_remote+0x11/0x20 flush_smp_call_function_queue+0x6d/0x120 ? debug_smp_processor_id+0x12/0x20 generic_smp_call_function_single_interrupt+0x12/0x30 smp_call_function_single_interrupt+0x25/0x40 call_function_single_interrupt+0x37/0x3c EIP: _raw_spin_unlock_irq+0x2d/0x50 EFLAGS: 00000296 CPU: 2 EAX: 00000001 EBX: d2ccc51c ECX: 00000001 EDX: c1aacebd ESI: 00000000 EDI: 00000000 EBP: c96c9d1c ESP: c96c9d18 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 ? inherit_task_group.isra.98.part.99+0x6b/0xb0 __add_to_page_cache_locked+0x1d4/0x290 add_to_page_cache_lru+0x38/0xb0 pagecache_get_page+0x8e/0x200 f2fs_write_begin+0x96/0xf00 [f2fs] ? trace_hardirqs_on_caller+0xdd/0x1c0 ? current_time+0x17/0x50 ? trace_hardirqs_on+0xb/0x10 generic_perform_write+0xa9/0x170 __generic_file_write_iter+0x1a2/0x1f0 ? f2fs_preallocate_blocks+0x137/0x160 [f2fs] f2fs_file_write_iter+0x6e/0x140 [f2fs] ? __lock_acquire+0x429/0x7b0 __vfs_write+0xc1/0x140 vfs_write+0x9b/0x190 SyS_pwrite64+0x63/0xa0 do_fast_syscall_32+0xa1/0x1b0 entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7786c61 EFLAGS: 00000293 CPU: 2 EAX: ffffffda EBX: 00000003 ECX: 08416000 EDX: 00001000 ESI: 18b24000 EDI: 00000000 EBP: 00000003 ESP: bf9b36b0 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Fixes: aaec2b1d1879 ("f2fs: introduce cp_lock to protect updating of ckpt_flags") Cc: stable@vger.kernel.org Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-07 08:10:15 +02:00
spin_lock_irqsave(&sbi->cp_lock, flags);
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
__set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
else
__clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
f2fs: use spin_{,un}lock_irq{save,restore} generic/361 reports below warning, this is because: once, there is someone entering into critical region of sbi.cp_lock, if write_end_io. f2fs_stop_checkpoint is invoked from an triggered IRQ, we will encounter deadlock. So this patch changes to use spin_{,un}lock_irq{save,restore} to create critical region without IRQ enabled to avoid potential deadlock. irq event stamp: 83391573 loop: Write error at byte offset 438729728, length 1024. hardirqs last enabled at (83391573): [<c1809752>] restore_all+0xf/0x65 hardirqs last disabled at (83391572): [<c1809eac>] reschedule_interrupt+0x30/0x3c loop: Write error at byte offset 438860288, length 1536. softirqs last enabled at (83389244): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (83389237): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 loop: Write error at byte offset 438990848, length 2048. ================================ WARNING: inconsistent lock state 4.12.0-rc2+ #30 Tainted: G O -------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. xfs_io/7959 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&sbi->cp_lock)->rlock){?.+...}, at: [<f96f96cc>] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] {HARDIRQ-ON-W} state was registered at: __lock_acquire+0x527/0x7b0 lock_acquire+0xae/0x220 _raw_spin_lock+0x42/0x50 do_checkpoint+0x165/0x9e0 [f2fs] write_checkpoint+0x33f/0x740 [f2fs] __f2fs_sync_fs+0x92/0x1f0 [f2fs] f2fs_sync_fs+0x12/0x20 [f2fs] sync_filesystem+0x67/0x80 generic_shutdown_super+0x27/0x100 kill_block_super+0x22/0x50 kill_f2fs_super+0x3a/0x40 [f2fs] deactivate_locked_super+0x3d/0x70 deactivate_super+0x40/0x60 cleanup_mnt+0x39/0x70 __cleanup_mnt+0x10/0x20 task_work_run+0x69/0x80 exit_to_usermode_loop+0x57/0x85 do_fast_syscall_32+0x18c/0x1b0 entry_SYSENTER_32+0x4c/0x7b irq event stamp: 1957420 hardirqs last enabled at (1957419): [<c1808f37>] _raw_spin_unlock_irq+0x27/0x50 hardirqs last disabled at (1957420): [<c1809f9c>] call_function_single_interrupt+0x30/0x3c softirqs last enabled at (1953784): [<c180cc4e>] __do_softirq+0x1ae/0x476 softirqs last disabled at (1953773): [<c101ca7c>] do_softirq_own_stack+0x2c/0x40 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&sbi->cp_lock)->rlock); <Interrupt> lock(&(&sbi->cp_lock)->rlock); *** DEADLOCK *** 2 locks held by xfs_io/7959: #0: (sb_writers#13){.+.+.+}, at: [<c11fd7ca>] vfs_write+0x16a/0x190 #1: (&sb->s_type->i_mutex_key#16){+.+.+.}, at: [<f96e33f5>] f2fs_file_write_iter+0x25/0x140 [f2fs] stack backtrace: CPU: 2 PID: 7959 Comm: xfs_io Tainted: G O 4.12.0-rc2+ #30 Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 Call Trace: dump_stack+0x5f/0x92 print_usage_bug+0x1d3/0x1dd ? check_usage_backwards+0xe0/0xe0 mark_lock+0x23d/0x280 __lock_acquire+0x699/0x7b0 ? __this_cpu_preempt_check+0xf/0x20 ? trace_hardirqs_off_caller+0x91/0xe0 lock_acquire+0xae/0x220 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] _raw_spin_lock+0x42/0x50 ? f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_stop_checkpoint+0x1c/0x50 [f2fs] f2fs_write_end_io+0x147/0x150 [f2fs] bio_endio+0x7a/0x1e0 blk_update_request+0xad/0x410 blk_mq_end_request+0x16/0x60 lo_complete_rq+0x3c/0x70 __blk_mq_complete_request_remote+0x11/0x20 flush_smp_call_function_queue+0x6d/0x120 ? debug_smp_processor_id+0x12/0x20 generic_smp_call_function_single_interrupt+0x12/0x30 smp_call_function_single_interrupt+0x25/0x40 call_function_single_interrupt+0x37/0x3c EIP: _raw_spin_unlock_irq+0x2d/0x50 EFLAGS: 00000296 CPU: 2 EAX: 00000001 EBX: d2ccc51c ECX: 00000001 EDX: c1aacebd ESI: 00000000 EDI: 00000000 EBP: c96c9d1c ESP: c96c9d18 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 ? inherit_task_group.isra.98.part.99+0x6b/0xb0 __add_to_page_cache_locked+0x1d4/0x290 add_to_page_cache_lru+0x38/0xb0 pagecache_get_page+0x8e/0x200 f2fs_write_begin+0x96/0xf00 [f2fs] ? trace_hardirqs_on_caller+0xdd/0x1c0 ? current_time+0x17/0x50 ? trace_hardirqs_on+0xb/0x10 generic_perform_write+0xa9/0x170 __generic_file_write_iter+0x1a2/0x1f0 ? f2fs_preallocate_blocks+0x137/0x160 [f2fs] f2fs_file_write_iter+0x6e/0x140 [f2fs] ? __lock_acquire+0x429/0x7b0 __vfs_write+0xc1/0x140 vfs_write+0x9b/0x190 SyS_pwrite64+0x63/0xa0 do_fast_syscall_32+0xa1/0x1b0 entry_SYSENTER_32+0x4c/0x7b EIP: 0xb7786c61 EFLAGS: 00000293 CPU: 2 EAX: ffffffda EBX: 00000003 ECX: 08416000 EDX: 00001000 ESI: 18b24000 EDI: 00000000 EBP: 00000003 ESP: bf9b36b0 DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 007b Fixes: aaec2b1d1879 ("f2fs: introduce cp_lock to protect updating of ckpt_flags") Cc: stable@vger.kernel.org Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2017-07-07 08:10:15 +02:00
spin_unlock_irqrestore(&sbi->cp_lock, flags);
orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
if (__remain_node_summaries(cpc->reason))
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
cp_payload_blks + data_sum_blocks +
orphan_blocks + NR_CURSEG_NODE_TYPE);
else
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
cp_payload_blks + data_sum_blocks +
orphan_blocks);
/* update ckpt flag for checkpoint */
update_ckpt_flags(sbi, cpc);
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
crc32 = f2fs_checkpoint_chksum(sbi, ckpt);
*((__le32 *)((unsigned char *)ckpt +
le32_to_cpu(ckpt->checksum_offset)))
= cpu_to_le32(crc32);
start_blk = __start_cp_next_addr(sbi);
/* write nat bits */
if (enabled_nat_bits(sbi, cpc)) {
__u64 cp_ver = cur_cp_version(ckpt);
block_t blk;
cp_ver |= ((__u64)crc32 << 32);
*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
for (i = 0; i < nm_i->nat_bits_blocks; i++)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_update_meta_page(sbi, nm_i->nat_bits +
(i << F2FS_BLKSIZE_BITS), blk + i);
}
/* write out checkpoint buffer at block 0 */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_update_meta_page(sbi, ckpt, start_blk++);
for (i = 1; i < 1 + cp_payload_blks; i++)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
start_blk++);
if (orphan_num) {
write_orphan_inodes(sbi, start_blk);
start_blk += orphan_blocks;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
/* Record write statistics in the hot node summary */
kbytes_written = sbi->kbytes_written;
if (sb->s_bdev->bd_part)
kbytes_written += BD_PART_WRITTEN(sbi);
seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
if (__remain_node_summaries(cpc->reason)) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
/* update user_block_counts */
sbi->last_valid_block_count = sbi->total_valid_block_count;
percpu_counter_set(&sbi->alloc_valid_block_count, 0);
/* Here, we have one bio having CP pack except cp pack 2 page */
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) &&
!f2fs_cp_error(sbi));
/* wait for previous submitted meta pages writeback */
f2fs: fix to avoid broken of dnode block list f2fs recovery flow is relying on dnode block link list, it means fsynced file recovery depends on previous dnode's persistence in the list, so during fsync() we should wait on all regular inode's dnode writebacked before issuing flush. By this way, we can avoid dnode block list being broken by out-of-order IO submission due to IO scheduler or driver. Sheng Yong helps to do the test with this patch: Target:/data (f2fs, -) 64MB / 32768KB / 4KB / 8 1 / PERSIST / Index Base: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 867.82 204.15 41440.03 41370.54 680.8 1025.94 1031.08 2 871.87 205.87 41370.3 40275.2 791.14 1065.84 1101.7 3 866.52 205.69 41795.67 40596.16 694.69 1037.16 1031.48 Avg 868.7366667 205.2366667 41535.33333 40747.3 722.21 1042.98 1054.753333 After: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 798.81 202.5 41143 40613.87 602.71 838.08 913.83 2 805.79 206.47 40297.2 41291.46 604.44 840.75 924.27 3 814.83 206.17 41209.57 40453.62 602.85 834.66 927.91 Avg 806.4766667 205.0466667 40883.25667 40786.31667 603.3333333 837.83 922.0033333 Patched/Original: 0.928332713 0.999074239 0.984300676 1.000957528 0.835398753 0.803303994 0.874141189 It looks like atomic write will suffer performance regression. I suspect that the criminal is that we forcing to wait all dnode being in storage cache before we issue PREFLUSH+FUA. BTW, will commit ("f2fs: don't need to wait for node writes for atomic write") cause the problem: we will lose data of last transaction after SPO, even if atomic write return no error: - atomic_open(); - write() P1, P2, P3; - atomic_commit(); - writeback data: P1, P2, P3; - writeback node: N1, N2, N3; <--- If N1, N2 is not writebacked, N3 with fsync_mark is writebacked, In SPOR, we won't find N3 since node chain is broken, turns out that losing last transaction. - preflush + fua; - power-cut If we don't wait dnode writeback for atomic_write: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 779.91 206.03 41621.5 40333.16 716.9 1038.21 1034.85 2 848.51 204.35 40082.44 39486.17 791.83 1119.96 1083.77 3 772.12 206.27 41335.25 41599.65 723.29 1055.07 971.92 Avg 800.18 205.55 41013.06333 40472.99333 744.0066667 1071.08 1030.18 Patched/Original: 0.92108464 1.001526693 0.987425886 0.993268102 1.030180511 1.026942031 0.976702294 SQLite's performance recovers. Jaegeuk: "Practically, I don't see db corruption becase of this. We can excuse to lose the last transaction." Finally, we decide to keep original implementation of atomic write interface sematics that we don't wait all dnode writeback before preflush+fua submission. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 17:03:19 +02:00
f2fs_wait_on_all_pages_writeback(sbi);
/* flush all device cache */
err = f2fs_flush_device_cache(sbi);
if (err)
return err;
/* barrier and flush checkpoint cp pack 2 page if it can */
commit_checkpoint(sbi, ckpt, start_blk);
f2fs: fix to avoid broken of dnode block list f2fs recovery flow is relying on dnode block link list, it means fsynced file recovery depends on previous dnode's persistence in the list, so during fsync() we should wait on all regular inode's dnode writebacked before issuing flush. By this way, we can avoid dnode block list being broken by out-of-order IO submission due to IO scheduler or driver. Sheng Yong helps to do the test with this patch: Target:/data (f2fs, -) 64MB / 32768KB / 4KB / 8 1 / PERSIST / Index Base: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 867.82 204.15 41440.03 41370.54 680.8 1025.94 1031.08 2 871.87 205.87 41370.3 40275.2 791.14 1065.84 1101.7 3 866.52 205.69 41795.67 40596.16 694.69 1037.16 1031.48 Avg 868.7366667 205.2366667 41535.33333 40747.3 722.21 1042.98 1054.753333 After: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 798.81 202.5 41143 40613.87 602.71 838.08 913.83 2 805.79 206.47 40297.2 41291.46 604.44 840.75 924.27 3 814.83 206.17 41209.57 40453.62 602.85 834.66 927.91 Avg 806.4766667 205.0466667 40883.25667 40786.31667 603.3333333 837.83 922.0033333 Patched/Original: 0.928332713 0.999074239 0.984300676 1.000957528 0.835398753 0.803303994 0.874141189 It looks like atomic write will suffer performance regression. I suspect that the criminal is that we forcing to wait all dnode being in storage cache before we issue PREFLUSH+FUA. BTW, will commit ("f2fs: don't need to wait for node writes for atomic write") cause the problem: we will lose data of last transaction after SPO, even if atomic write return no error: - atomic_open(); - write() P1, P2, P3; - atomic_commit(); - writeback data: P1, P2, P3; - writeback node: N1, N2, N3; <--- If N1, N2 is not writebacked, N3 with fsync_mark is writebacked, In SPOR, we won't find N3 since node chain is broken, turns out that losing last transaction. - preflush + fua; - power-cut If we don't wait dnode writeback for atomic_write: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 779.91 206.03 41621.5 40333.16 716.9 1038.21 1034.85 2 848.51 204.35 40082.44 39486.17 791.83 1119.96 1083.77 3 772.12 206.27 41335.25 41599.65 723.29 1055.07 971.92 Avg 800.18 205.55 41013.06333 40472.99333 744.0066667 1071.08 1030.18 Patched/Original: 0.92108464 1.001526693 0.987425886 0.993268102 1.030180511 1.026942031 0.976702294 SQLite's performance recovers. Jaegeuk: "Practically, I don't see db corruption becase of this. We can excuse to lose the last transaction." Finally, we decide to keep original implementation of atomic write interface sematics that we don't wait all dnode writeback before preflush+fua submission. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 17:03:19 +02:00
f2fs_wait_on_all_pages_writeback(sbi);
/*
* invalidate intermediate page cache borrowed from meta inode
* which are used for migration of encrypted inode's blocks.
*/
if (f2fs_sb_has_encrypt(sbi))
invalidate_mapping_pages(META_MAPPING(sbi),
MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_release_ino_entry(sbi, false);
f2fs: fix to avoid broken of dnode block list f2fs recovery flow is relying on dnode block link list, it means fsynced file recovery depends on previous dnode's persistence in the list, so during fsync() we should wait on all regular inode's dnode writebacked before issuing flush. By this way, we can avoid dnode block list being broken by out-of-order IO submission due to IO scheduler or driver. Sheng Yong helps to do the test with this patch: Target:/data (f2fs, -) 64MB / 32768KB / 4KB / 8 1 / PERSIST / Index Base: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 867.82 204.15 41440.03 41370.54 680.8 1025.94 1031.08 2 871.87 205.87 41370.3 40275.2 791.14 1065.84 1101.7 3 866.52 205.69 41795.67 40596.16 694.69 1037.16 1031.48 Avg 868.7366667 205.2366667 41535.33333 40747.3 722.21 1042.98 1054.753333 After: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 798.81 202.5 41143 40613.87 602.71 838.08 913.83 2 805.79 206.47 40297.2 41291.46 604.44 840.75 924.27 3 814.83 206.17 41209.57 40453.62 602.85 834.66 927.91 Avg 806.4766667 205.0466667 40883.25667 40786.31667 603.3333333 837.83 922.0033333 Patched/Original: 0.928332713 0.999074239 0.984300676 1.000957528 0.835398753 0.803303994 0.874141189 It looks like atomic write will suffer performance regression. I suspect that the criminal is that we forcing to wait all dnode being in storage cache before we issue PREFLUSH+FUA. BTW, will commit ("f2fs: don't need to wait for node writes for atomic write") cause the problem: we will lose data of last transaction after SPO, even if atomic write return no error: - atomic_open(); - write() P1, P2, P3; - atomic_commit(); - writeback data: P1, P2, P3; - writeback node: N1, N2, N3; <--- If N1, N2 is not writebacked, N3 with fsync_mark is writebacked, In SPOR, we won't find N3 since node chain is broken, turns out that losing last transaction. - preflush + fua; - power-cut If we don't wait dnode writeback for atomic_write: SEQ-RD(MB/s) SEQ-WR(MB/s) RND-RD(IOPS) RND-WR(IOPS) Insert(TPS) Update(TPS) Delete(TPS) 1 779.91 206.03 41621.5 40333.16 716.9 1038.21 1034.85 2 848.51 204.35 40082.44 39486.17 791.83 1119.96 1083.77 3 772.12 206.27 41335.25 41599.65 723.29 1055.07 971.92 Avg 800.18 205.55 41013.06333 40472.99333 744.0066667 1071.08 1030.18 Patched/Original: 0.92108464 1.001526693 0.987425886 0.993268102 1.030180511 1.026942031 0.976702294 SQLite's performance recovers. Jaegeuk: "Practically, I don't see db corruption becase of this. We can excuse to lose the last transaction." Finally, we decide to keep original implementation of atomic write interface sematics that we don't wait all dnode writeback before preflush+fua submission. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-08-02 17:03:19 +02:00
f2fs_reset_fsync_node_info(sbi);
clear_sbi_flag(sbi, SBI_IS_DIRTY);
clear_sbi_flag(sbi, SBI_NEED_CP);
clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH);
spin_lock(&sbi->stat_lock);
sbi->unusable_block_count = 0;
spin_unlock(&sbi->stat_lock);
__set_cp_next_pack(sbi);
f2fs: fix to set superblock dirty correctly tests/generic/251 of fstest suit complains us with below message: ------------[ cut here ]------------ invalid opcode: 0000 [#1] PREEMPT SMP CPU: 2 PID: 7698 Comm: fstrim Tainted: G O 4.7.0+ #21 task: e9f4e000 task.stack: e7262000 EIP: 0060:[<f89fcefe>] EFLAGS: 00010202 CPU: 2 EIP is at write_checkpoint+0xfde/0x1020 [f2fs] EAX: f33eb300 EBX: eecac310 ECX: 00000001 EDX: ffff0001 ESI: eecac000 EDI: eecac5f0 EBP: e7263dec ESP: e7263d18 DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 CR0: 80050033 CR2: b76ab01c CR3: 2eb89de0 CR4: 000406f0 Stack: 00000001 a220fb7b e9f4e000 00000002 419ff2d3 b3a05151 00000002 e9f4e5d8 e9f4e000 419ff2d3 b3a05151 eecac310 c10b8154 b3a05151 419ff2d3 c10b78bd e9f4e000 e9f4e000 e9f4e5d8 00000001 e9f4e000 ec409000 eecac2cc eecac288 Call Trace: [<c10b8154>] ? __lock_acquire+0x3c4/0x760 [<c10b78bd>] ? mark_held_locks+0x5d/0x80 [<f8a10632>] f2fs_trim_fs+0x1c2/0x2e0 [f2fs] [<f89e9f56>] f2fs_ioctl+0x6b6/0x10b0 [f2fs] [<c13d51df>] ? __this_cpu_preempt_check+0xf/0x20 [<c10b4281>] ? trace_hardirqs_off_caller+0x91/0x120 [<f89e98a0>] ? __exchange_data_block+0xd30/0xd30 [f2fs] [<c120b2e1>] do_vfs_ioctl+0x81/0x7f0 [<c11d57c5>] ? kmem_cache_free+0x245/0x2e0 [<c1217840>] ? get_unused_fd_flags+0x40/0x40 [<c1206eec>] ? putname+0x4c/0x50 [<c11f631e>] ? do_sys_open+0x16e/0x1d0 [<c1001990>] ? do_fast_syscall_32+0x30/0x1c0 [<c13d51df>] ? __this_cpu_preempt_check+0xf/0x20 [<c120baa8>] SyS_ioctl+0x58/0x80 [<c1001a01>] do_fast_syscall_32+0xa1/0x1c0 [<c178cc54>] sysenter_past_esp+0x45/0x74 EIP: [<f89fcefe>] write_checkpoint+0xfde/0x1020 [f2fs] SS:ESP 0068:e7263d18 ---[ end trace 4de95d7e6b3aa7c6 ]--- The reason is: with below call stack, we will encounter BUG_ON during doing fstrim. Thread A Thread B - write_checkpoint - do_checkpoint - f2fs_write_inode - update_inode_page - update_inode - set_page_dirty - f2fs_set_node_page_dirty - inc_page_count - percpu_counter_inc - set_sbi_flag(SBI_IS_DIRTY) - clear_sbi_flag(SBI_IS_DIRTY) Thread C Thread D - f2fs_write_node_page - set_node_addr - __set_nat_cache_dirty - nm_i->dirty_nat_cnt++ - do_vfs_ioctl - f2fs_ioctl - f2fs_trim_fs - write_checkpoint - f2fs_bug_on(nm_i->dirty_nat_cnt) Fix it by setting superblock dirty correctly in do_checkpoint and f2fs_write_node_page. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2016-08-31 04:43:19 +02:00
/*
* redirty superblock if metadata like node page or inode cache is
* updated during writing checkpoint.
*/
if (get_pages(sbi, F2FS_DIRTY_NODES) ||
get_pages(sbi, F2FS_DIRTY_IMETA))
set_sbi_flag(sbi, SBI_IS_DIRTY);
f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0;
}
/*
* We guarantee that this checkpoint procedure will not fail.
*/
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
int err = 0;
f2fs: fix to be aware of readonly device in write_checkpoint() As Park Ju Hyung reported: Probably unrelated but a similar issue: Warning appears upon unmounting a corrupted R/O f2fs loop image. Should be a trivial issue to fix as well :) [ 2373.758424] ------------[ cut here ]------------ [ 2373.758428] generic_make_request: Trying to write to read-only block-device loop1 (partno 0) [ 2373.758455] WARNING: CPU: 1 PID: 13950 at block/blk-core.c:2174 generic_make_request_checks+0x590/0x630 [ 2373.758556] CPU: 1 PID: 13950 Comm: umount Tainted: G O 4.19.35-zen+ #1 [ 2373.758558] Hardware name: System manufacturer System Product Name/ROG MAXIMUS X HERO (WI-FI AC), BIOS 1704 09/14/2018 [ 2373.758564] RIP: 0010:generic_make_request_checks+0x590/0x630 [ 2373.758567] Code: 5c 03 00 00 48 8d 74 24 08 48 89 df c6 05 b5 cd 36 01 01 e8 c2 90 01 00 48 89 c6 44 89 ea 48 c7 c7 98 64 59 82 e8 d5 9b a7 ff <0f> 0b 48 8b 7b 08 e9 f2 fa ff ff 41 8b 86 98 02 00 00 49 8b 16 89 [ 2373.758570] RSP: 0018:ffff8882bdb43950 EFLAGS: 00010282 [ 2373.758573] RAX: 0000000000000050 RBX: ffff8887244c6700 RCX: 0000000000000006 [ 2373.758575] RDX: 0000000000000007 RSI: 0000000000000086 RDI: ffff88884ec56340 [ 2373.758577] RBP: ffff888849c426c0 R08: 0000000000000004 R09: 00000000000003ba [ 2373.758579] R10: 0000000000000001 R11: 0000000000000029 R12: 0000000000001000 [ 2373.758581] R13: 0000000000000000 R14: ffff888844a2e800 R15: ffff8882bdb43ac0 [ 2373.758584] FS: 00007fc0d114f8c0(0000) GS:ffff88884ec40000(0000) knlGS:0000000000000000 [ 2373.758586] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 2373.758588] CR2: 00007fc0d1ad12c0 CR3: 00000002bdb82003 CR4: 00000000003606e0 [ 2373.758590] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 2373.758592] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 2373.758593] Call Trace: [ 2373.758602] ? generic_make_request+0x46/0x3d0 [ 2373.758608] ? wait_woken+0x80/0x80 [ 2373.758612] ? mempool_alloc+0xb7/0x1a0 [ 2373.758618] ? submit_bio+0x30/0x110 [ 2373.758622] ? bvec_alloc+0x7c/0xd0 [ 2373.758628] ? __submit_merged_bio+0x68/0x390 [ 2373.758633] ? f2fs_submit_page_write+0x1bb/0x7f0 [ 2373.758638] ? f2fs_do_write_meta_page+0x7f/0x160 [ 2373.758642] ? __f2fs_write_meta_page+0x70/0x140 [ 2373.758647] ? f2fs_sync_meta_pages+0x140/0x250 [ 2373.758653] ? f2fs_write_checkpoint+0x5c5/0x17b0 [ 2373.758657] ? f2fs_sync_fs+0x9c/0x110 [ 2373.758664] ? sync_filesystem+0x66/0x80 [ 2373.758667] ? generic_shutdown_super+0x1d/0x100 [ 2373.758670] ? kill_block_super+0x1c/0x40 [ 2373.758674] ? kill_f2fs_super+0x64/0xb0 [ 2373.758678] ? deactivate_locked_super+0x2d/0xb0 [ 2373.758682] ? cleanup_mnt+0x65/0xa0 [ 2373.758688] ? task_work_run+0x7f/0xa0 [ 2373.758693] ? exit_to_usermode_loop+0x9c/0xa0 [ 2373.758698] ? do_syscall_64+0xc7/0xf0 [ 2373.758703] ? entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 2373.758706] ---[ end trace 5d3639907c56271b ]--- [ 2373.758780] print_req_error: I/O error, dev loop1, sector 143048 [ 2373.758800] print_req_error: I/O error, dev loop1, sector 152200 [ 2373.758808] print_req_error: I/O error, dev loop1, sector 8192 [ 2373.758819] print_req_error: I/O error, dev loop1, sector 12272 This patch adds to detect readonly device in write_checkpoint() to avoid trigger write IOs on it. Reported-by: Park Ju Hyung <qkrwngud825@gmail.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2019-04-22 14:22:38 +02:00
if (f2fs_readonly(sbi->sb) || f2fs_hw_is_readonly(sbi))
return -EROFS;
if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) {
if (cpc->reason != CP_PAUSE)
return 0;
f2fs_msg(sbi->sb, KERN_WARNING,
"Start checkpoint disabled!");
}
mutex_lock(&sbi->cp_mutex);
if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
((cpc->reason & CP_DISCARD) && !sbi->discard_blks)))
goto out;
if (unlikely(f2fs_cp_error(sbi))) {
err = -EIO;
goto out;
}
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
err = block_operations(sbi);
if (err)
goto out;
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
f2fs_flush_merged_writes(sbi);
/* this is the case of multiple fstrims without any changes */
if (cpc->reason & CP_DISCARD) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
if (!f2fs_exist_trim_candidates(sbi, cpc)) {
unblock_operations(sbi);
goto out;
}
if (NM_I(sbi)->dirty_nat_cnt == 0 &&
SIT_I(sbi)->dirty_sentries == 0 &&
prefree_segments(sbi) == 0) {
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_flush_sit_entries(sbi, cpc);
f2fs_clear_prefree_segments(sbi, cpc);
unblock_operations(sbi);
goto out;
}
}
/*
* update checkpoint pack index
* Increase the version number so that
* SIT entries and seg summaries are written at correct place
*/
ckpt_ver = cur_cp_version(ckpt);
ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
/* write cached NAT/SIT entries to NAT/SIT area */
err = f2fs_flush_nat_entries(sbi, cpc);
if (err)
goto stop;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
err = do_checkpoint(sbi, cpc);
if (err)
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_release_discard_addrs(sbi);
else
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_clear_prefree_segments(sbi, cpc);
stop:
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
if (cpc->reason & CP_RECOVERY)
f2fs_msg(sbi->sb, KERN_NOTICE,
"checkpoint: version = %llx", ckpt_ver);
/* do checkpoint periodically */
f2fs_update_time(sbi, CP_TIME);
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
out:
mutex_unlock(&sbi->cp_mutex);
return err;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi)
{
int i;
for (i = 0; i < MAX_INO_ENTRY; i++) {
struct inode_management *im = &sbi->im[i];
INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC);
spin_lock_init(&im->ino_lock);
INIT_LIST_HEAD(&im->ino_list);
im->ino_num = 0;
}
sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
NR_CURSEG_TYPE - __cp_payload(sbi)) *
F2FS_ORPHANS_PER_BLOCK;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
int __init f2fs_create_checkpoint_caches(void)
{
ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry",
sizeof(struct ino_entry));
if (!ino_entry_slab)
return -ENOMEM;
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
sizeof(struct inode_entry));
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
if (!f2fs_inode_entry_slab) {
kmem_cache_destroy(ino_entry_slab);
return -ENOMEM;
}
return 0;
}
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
void f2fs_destroy_checkpoint_caches(void)
{
kmem_cache_destroy(ino_entry_slab);
f2fs: clean up symbol namespace As Ted reported: "Hi, I was looking at f2fs's sources recently, and I noticed that there is a very large number of non-static symbols which don't have a f2fs prefix. There's well over a hundred (see attached below). As one example, in fs/f2fs/dir.c there is: unsigned char get_de_type(struct f2fs_dir_entry *de) This function is clearly only useful for f2fs, but it has a generic name. This means that if any other file system tries to have the same symbol name, there will be a symbol conflict and the kernel would not successfully build. It also means that when someone is looking f2fs sources, it's not at all obvious whether a function such as read_data_page(), invalidate_blocks(), is a generic kernel function found in the fs, mm, or block layers, or a f2fs specific function. You might want to fix this at some point. Hopefully Kent's bcachefs isn't similarly using genericly named functions, since that might cause conflicts with f2fs's functions --- but just as this would be a problem that we would rightly insist that Kent fix, this is something that we should have rightly insisted that f2fs should have fixed before it was integrated into the mainline kernel. acquire_orphan_inode add_ino_entry add_orphan_inode allocate_data_block allocate_new_segments alloc_nid alloc_nid_done alloc_nid_failed available_free_memory ...." This patch adds "f2fs_" prefix for all non-static symbols in order to: a) avoid conflict with other kernel generic symbols; b) to indicate the function is f2fs specific one instead of generic one; Reported-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2018-05-29 18:20:41 +02:00
kmem_cache_destroy(f2fs_inode_entry_slab);
}